diff --git a/arch/alpha/include/asm/spinlock_types.h b/arch/alpha/include/asm/spinlock_types.h index 1d5716bc060be..6883bc952d224 100644 --- a/arch/alpha/include/asm/spinlock_types.h +++ b/arch/alpha/include/asm/spinlock_types.h @@ -2,10 +2,6 @@ #ifndef _ALPHA_SPINLOCK_TYPES_H #define _ALPHA_SPINLOCK_TYPES_H -#ifndef __LINUX_SPINLOCK_TYPES_H -# error "please don't include this file directly" -#endif - typedef struct { volatile unsigned int lock; } arch_spinlock_t; diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 5da96f5df48f3..876e4d478e57c 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -31,6 +31,7 @@ config ARM select ARCH_OPTIONAL_KERNEL_RWX if ARCH_HAS_STRICT_KERNEL_RWX select ARCH_OPTIONAL_KERNEL_RWX_DEFAULT if CPU_V7 select ARCH_SUPPORTS_ATOMIC_RMW + select ARCH_SUPPORTS_RT if HAVE_POSIX_CPU_TIMERS_TASK_WORK select ARCH_USE_BUILTIN_BSWAP select ARCH_USE_CMPXCHG_LOCKREF select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT if MMU @@ -67,7 +68,7 @@ config ARM select HARDIRQS_SW_RESEND 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_KGDB if !CPU_ENDIAN_BE32 && MMU select HAVE_ARCH_KASAN if MMU && !XIP_KERNEL select HAVE_ARCH_MMAP_RND_BITS if MMU @@ -107,6 +108,7 @@ config ARM select HAVE_PERF_EVENTS select HAVE_PERF_REGS select HAVE_PERF_USER_STACK_DUMP + select HAVE_PREEMPT_LAZY select MMU_GATHER_RCU_TABLE_FREE if SMP && ARM_LPAE select HAVE_REGS_AND_STACK_ACCESS_API select HAVE_RSEQ @@ -122,6 +124,7 @@ config ARM select OLD_SIGSUSPEND3 select PCI_SYSCALL if PCI select PERF_USE_VMALLOC + select HAVE_POSIX_CPU_TIMERS_TASK_WORK if !KVM select RTC_LIB select SET_FS select SYS_SUPPORTS_APM_EMULATION diff --git a/arch/arm/include/asm/spinlock_types.h b/arch/arm/include/asm/spinlock_types.h index 5976958647fe1..a37c0803954ba 100644 --- a/arch/arm/include/asm/spinlock_types.h +++ b/arch/arm/include/asm/spinlock_types.h @@ -2,10 +2,6 @@ #ifndef __ASM_SPINLOCK_TYPES_H #define __ASM_SPINLOCK_TYPES_H -#ifndef __LINUX_SPINLOCK_TYPES_H -# error "please don't include this file directly" -#endif - #define TICKET_SHIFT 16 typedef struct { diff --git a/arch/arm/include/asm/thread_info.h b/arch/arm/include/asm/thread_info.h index 70d4cbc49ae12..b86418b4dfef8 100644 --- a/arch/arm/include/asm/thread_info.h +++ b/arch/arm/include/asm/thread_info.h @@ -54,6 +54,7 @@ struct cpu_context_save { struct thread_info { unsigned long flags; /* low level flags */ int preempt_count; /* 0 => preemptable, <0 => bug */ + int preempt_lazy_count; /* 0 => preemptable, <0 => bug */ mm_segment_t addr_limit; /* address limit */ struct task_struct *task; /* main task structure */ __u32 cpu; /* cpu */ @@ -146,6 +147,7 @@ extern int vfp_restore_user_hwstate(struct user_vfp *, #define TIF_SYSCALL_TRACEPOINT 6 /* syscall tracepoint instrumentation */ #define TIF_SECCOMP 7 /* seccomp syscall filtering active */ #define TIF_NOTIFY_SIGNAL 8 /* signal notifications exist */ +#define TIF_NEED_RESCHED_LAZY 9 #define TIF_USING_IWMMXT 17 #define TIF_MEMDIE 18 /* is terminating due to OOM killer */ @@ -160,6 +162,7 @@ extern int vfp_restore_user_hwstate(struct user_vfp *, #define _TIF_SYSCALL_TRACEPOINT (1 << TIF_SYSCALL_TRACEPOINT) #define _TIF_SECCOMP (1 << TIF_SECCOMP) #define _TIF_NOTIFY_SIGNAL (1 << TIF_NOTIFY_SIGNAL) +#define _TIF_NEED_RESCHED_LAZY (1 << TIF_NEED_RESCHED_LAZY) #define _TIF_USING_IWMMXT (1 << TIF_USING_IWMMXT) /* Checks for any syscall work in entry-common.S */ @@ -169,7 +172,8 @@ extern int vfp_restore_user_hwstate(struct user_vfp *, /* * Change these and you break ASM code in entry-common.S */ -#define _TIF_WORK_MASK (_TIF_NEED_RESCHED | _TIF_SIGPENDING | \ +#define _TIF_WORK_MASK (_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY | \ + _TIF_SIGPENDING | \ _TIF_NOTIFY_RESUME | _TIF_UPROBE | \ _TIF_NOTIFY_SIGNAL) diff --git a/arch/arm/kernel/asm-offsets.c b/arch/arm/kernel/asm-offsets.c index be8050b0c3dfb..884e40a525ce4 100644 --- a/arch/arm/kernel/asm-offsets.c +++ b/arch/arm/kernel/asm-offsets.c @@ -42,6 +42,7 @@ int main(void) BLANK(); DEFINE(TI_FLAGS, offsetof(struct thread_info, flags)); DEFINE(TI_PREEMPT, offsetof(struct thread_info, preempt_count)); + DEFINE(TI_PREEMPT_LAZY, offsetof(struct thread_info, preempt_lazy_count)); DEFINE(TI_ADDR_LIMIT, offsetof(struct thread_info, addr_limit)); DEFINE(TI_TASK, offsetof(struct thread_info, task)); DEFINE(TI_CPU, offsetof(struct thread_info, cpu)); diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S index 0ea8529a48726..fa0d155d21b3f 100644 --- a/arch/arm/kernel/entry-armv.S +++ b/arch/arm/kernel/entry-armv.S @@ -206,11 +206,18 @@ ENDPROC(__dabt_svc) #ifdef CONFIG_PREEMPTION ldr r8, [tsk, #TI_PREEMPT] @ get preempt count - ldr r0, [tsk, #TI_FLAGS] @ get flags teq r8, #0 @ if preempt count != 0 + bne 1f @ return from exeption + ldr r0, [tsk, #TI_FLAGS] @ get flags + tst r0, #_TIF_NEED_RESCHED @ if NEED_RESCHED is set + blne svc_preempt @ preempt! + + ldr r8, [tsk, #TI_PREEMPT_LAZY] @ get preempt lazy count + teq r8, #0 @ if preempt lazy count != 0 movne r0, #0 @ force flags to 0 - tst r0, #_TIF_NEED_RESCHED + tst r0, #_TIF_NEED_RESCHED_LAZY blne svc_preempt +1: #endif svc_exit r5, irq = 1 @ return from exception @@ -225,8 +232,14 @@ ENDPROC(__irq_svc) 1: bl preempt_schedule_irq @ irq en/disable is done inside ldr r0, [tsk, #TI_FLAGS] @ get new tasks TI_FLAGS tst r0, #_TIF_NEED_RESCHED + bne 1b + tst r0, #_TIF_NEED_RESCHED_LAZY reteq r8 @ go again - b 1b + ldr r0, [tsk, #TI_PREEMPT_LAZY] @ get preempt lazy count + teq r0, #0 @ if preempt lazy count != 0 + beq 1b + ret r8 @ go again + #endif __und_fault: diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c index a3a38d0a4c853..f04ccf19ab1fd 100644 --- a/arch/arm/kernel/signal.c +++ b/arch/arm/kernel/signal.c @@ -649,7 +649,8 @@ do_work_pending(struct pt_regs *regs, unsigned int thread_flags, int syscall) */ trace_hardirqs_off(); do { - if (likely(thread_flags & _TIF_NEED_RESCHED)) { + if (likely(thread_flags & (_TIF_NEED_RESCHED | + _TIF_NEED_RESCHED_LAZY))) { schedule(); } else { if (unlikely(!user_mode(regs))) diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c index 74679240a9d8e..0dd2d733ad628 100644 --- a/arch/arm/kernel/smp.c +++ b/arch/arm/kernel/smp.c @@ -668,9 +668,7 @@ static void do_handle_IPI(int ipinr) break; case IPI_CPU_BACKTRACE: - printk_nmi_enter(); nmi_cpu_backtrace(get_irq_regs()); - printk_nmi_exit(); break; default: diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c index efa4020250315..59487ee9fd612 100644 --- a/arch/arm/mm/fault.c +++ b/arch/arm/mm/fault.c @@ -400,6 +400,9 @@ 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; @@ -470,6 +473,9 @@ 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; } diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 5656e7aacd698..9cc92459812cd 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -78,6 +78,7 @@ config ARM64 select ARCH_SUPPORTS_ATOMIC_RMW select ARCH_SUPPORTS_INT128 if CC_HAS_INT128 && (GCC_VERSION >= 50000 || CC_IS_CLANG) select ARCH_SUPPORTS_NUMA_BALANCING + select ARCH_SUPPORTS_RT if HAVE_POSIX_CPU_TIMERS_TASK_WORK select ARCH_WANT_COMPAT_IPC_PARSE_VERSION if COMPAT select ARCH_WANT_DEFAULT_BPF_JIT select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT @@ -182,6 +183,7 @@ config ARM64 select HAVE_PERF_REGS select HAVE_PERF_USER_STACK_DUMP select HAVE_REGS_AND_STACK_ACCESS_API + select HAVE_PREEMPT_LAZY select HAVE_FUNCTION_ARG_ACCESS_API select HAVE_FUTEX_CMPXCHG if FUTEX select MMU_GATHER_RCU_TABLE_FREE @@ -202,6 +204,7 @@ config ARM64 select PCI_DOMAINS_GENERIC if PCI select PCI_ECAM if (ACPI && PCI) select PCI_SYSCALL if PCI + select HAVE_POSIX_CPU_TIMERS_TASK_WORK if !KVM select POWER_RESET select POWER_SUPPLY select SPARSE_IRQ diff --git a/arch/arm64/include/asm/preempt.h b/arch/arm64/include/asm/preempt.h index 80e946b2abee2..994f997b15724 100644 --- a/arch/arm64/include/asm/preempt.h +++ b/arch/arm64/include/asm/preempt.h @@ -70,17 +70,43 @@ static inline bool __preempt_count_dec_and_test(void) * interrupt occurring between the non-atomic READ_ONCE/WRITE_ONCE * pair. */ - return !pc || !READ_ONCE(ti->preempt_count); + if (!pc || !READ_ONCE(ti->preempt_count)) + return true; +#ifdef CONFIG_PREEMPT_LAZY + if ((pc & ~PREEMPT_NEED_RESCHED)) + return false; + if (current_thread_info()->preempt_lazy_count) + return false; + return test_thread_flag(TIF_NEED_RESCHED_LAZY); +#else + return false; +#endif } static inline bool should_resched(int preempt_offset) { +#ifdef CONFIG_PREEMPT_LAZY + u64 pc = READ_ONCE(current_thread_info()->preempt_count); + if (pc == preempt_offset) + return true; + + if ((pc & ~PREEMPT_NEED_RESCHED) != preempt_offset) + return false; + + if (current_thread_info()->preempt_lazy_count) + return false; + return test_thread_flag(TIF_NEED_RESCHED_LAZY); +#else u64 pc = READ_ONCE(current_thread_info()->preempt_count); return pc == preempt_offset; +#endif } #ifdef CONFIG_PREEMPTION void preempt_schedule(void); +#ifdef CONFIG_PREEMPT_RT +void preempt_schedule_lock(void); +#endif #define __preempt_schedule() preempt_schedule() void preempt_schedule_notrace(void); #define __preempt_schedule_notrace() preempt_schedule_notrace() diff --git a/arch/arm64/include/asm/spinlock_types.h b/arch/arm64/include/asm/spinlock_types.h index 18782f0c47212..6672b05350b4e 100644 --- a/arch/arm64/include/asm/spinlock_types.h +++ b/arch/arm64/include/asm/spinlock_types.h @@ -5,10 +5,6 @@ #ifndef __ASM_SPINLOCK_TYPES_H #define __ASM_SPINLOCK_TYPES_H -#if !defined(__LINUX_SPINLOCK_TYPES_H) && !defined(__ASM_SPINLOCK_H) -# error "please don't include this file directly" -#endif - #include #include diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h index 9f4e3b266f21a..d3fa570c72355 100644 --- a/arch/arm64/include/asm/thread_info.h +++ b/arch/arm64/include/asm/thread_info.h @@ -26,6 +26,7 @@ struct thread_info { #ifdef CONFIG_ARM64_SW_TTBR0_PAN u64 ttbr0; /* saved TTBR0_EL1 */ #endif + int preempt_lazy_count; /* 0 => preemptable, <0 => bug */ union { u64 preempt_count; /* 0 => preemptible, <0 => bug */ struct { @@ -65,6 +66,7 @@ void arch_release_task_struct(struct task_struct *tsk); #define TIF_UPROBE 4 /* uprobe breakpoint or singlestep */ #define TIF_MTE_ASYNC_FAULT 5 /* MTE Asynchronous Tag Check Fault */ #define TIF_NOTIFY_SIGNAL 6 /* signal notifications exist */ +#define TIF_NEED_RESCHED_LAZY 7 #define TIF_SYSCALL_TRACE 8 /* syscall trace active */ #define TIF_SYSCALL_AUDIT 9 /* syscall auditing */ #define TIF_SYSCALL_TRACEPOINT 10 /* syscall tracepoint for ftrace */ @@ -95,8 +97,10 @@ void arch_release_task_struct(struct task_struct *tsk); #define _TIF_SVE (1 << TIF_SVE) #define _TIF_MTE_ASYNC_FAULT (1 << TIF_MTE_ASYNC_FAULT) #define _TIF_NOTIFY_SIGNAL (1 << TIF_NOTIFY_SIGNAL) +#define _TIF_NEED_RESCHED_LAZY (1 << TIF_NEED_RESCHED_LAZY) -#define _TIF_WORK_MASK (_TIF_NEED_RESCHED | _TIF_SIGPENDING | \ +#define _TIF_WORK_MASK (_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY | \ + _TIF_SIGPENDING | \ _TIF_NOTIFY_RESUME | _TIF_FOREIGN_FPSTATE | \ _TIF_UPROBE | _TIF_MTE_ASYNC_FAULT | \ _TIF_NOTIFY_SIGNAL) @@ -105,6 +109,8 @@ void arch_release_task_struct(struct task_struct *tsk); _TIF_SYSCALL_TRACEPOINT | _TIF_SECCOMP | \ _TIF_SYSCALL_EMU) +#define _TIF_NEED_RESCHED_MASK (_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY) + #ifdef CONFIG_SHADOW_CALL_STACK #define INIT_SCS \ .scs_base = init_shadow_call_stack, \ diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c index a36e2fc330d43..b94354a3af967 100644 --- a/arch/arm64/kernel/asm-offsets.c +++ b/arch/arm64/kernel/asm-offsets.c @@ -30,6 +30,7 @@ int main(void) BLANK(); DEFINE(TSK_TI_FLAGS, offsetof(struct task_struct, thread_info.flags)); DEFINE(TSK_TI_PREEMPT, offsetof(struct task_struct, thread_info.preempt_count)); + DEFINE(TSK_TI_PREEMPT_LAZY, offsetof(struct task_struct, thread_info.preempt_lazy_count)); #ifdef CONFIG_ARM64_SW_TTBR0_PAN DEFINE(TSK_TI_TTBR0, offsetof(struct task_struct, thread_info.ttbr0)); #endif diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index a31a0a713c85d..63e1ad8c2ea87 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -678,9 +678,18 @@ alternative_if ARM64_HAS_IRQ_PRIO_MASKING mrs x0, daif orr x24, x24, x0 alternative_else_nop_endif - cbnz x24, 1f // preempt count != 0 || NMI return path - bl arm64_preempt_schedule_irq // irq en/disable is done inside + + cbz x24, 1f // (need_resched + count) == 0 + cbnz w24, 2f // count != 0 + + ldr w24, [tsk, #TSK_TI_PREEMPT_LAZY] // get preempt lazy count + cbnz w24, 2f // preempt lazy count != 0 + + ldr x0, [tsk, #TSK_TI_FLAGS] // get flags + tbz x0, #TIF_NEED_RESCHED_LAZY, 2f // needs rescheduling? 1: + bl arm64_preempt_schedule_irq // irq en/disable is done inside +2: #endif mov x0, sp diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 062b21f30f942..0ea2df6554e5a 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -226,6 +226,16 @@ static void sve_free(struct task_struct *task) __sve_free(task); } +static void *sve_free_atomic(struct task_struct *task) +{ + void *sve_state = task->thread.sve_state; + + WARN_ON(test_tsk_thread_flag(task, TIF_SVE)); + + task->thread.sve_state = NULL; + return sve_state; +} + /* * TIF_SVE controls whether a task can use SVE without trapping while * in userspace, and also the way a task's FPSIMD/SVE state is stored @@ -1022,6 +1032,7 @@ void fpsimd_thread_switch(struct task_struct *next) void fpsimd_flush_thread(void) { int vl, supported_vl; + void *mem = NULL; if (!system_supports_fpsimd()) return; @@ -1034,7 +1045,7 @@ void fpsimd_flush_thread(void) if (system_supports_sve()) { clear_thread_flag(TIF_SVE); - sve_free(current); + mem = sve_free_atomic(current); /* * Reset the task vector length as required. @@ -1068,6 +1079,7 @@ void fpsimd_flush_thread(void) } put_cpu_fpsimd_context(); + kfree(mem); } /* diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c index 6237486ff6bb7..ab411f336c39d 100644 --- a/arch/arm64/kernel/signal.c +++ b/arch/arm64/kernel/signal.c @@ -915,7 +915,7 @@ asmlinkage void do_notify_resume(struct pt_regs *regs, unsigned long thread_flags) { do { - if (thread_flags & _TIF_NEED_RESCHED) { + if (thread_flags & _TIF_NEED_RESCHED_MASK) { /* Unmask Debug and SError for the next task */ local_daif_restore(DAIF_PROCCTX_NOIRQ); diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 7f06ba76698d8..f9318256d6fba 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -737,7 +737,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) * involves poking the GIC, which must be done in a * non-preemptible context. */ - preempt_disable(); + migrate_disable(); kvm_pmu_flush_hwstate(vcpu); @@ -786,7 +786,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) kvm_timer_sync_user(vcpu); kvm_vgic_sync_hwstate(vcpu); local_irq_enable(); - preempt_enable(); + migrate_enable(); continue; } @@ -858,7 +858,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) /* Exit types that need handling before we can be preempted */ handle_exit_early(vcpu, ret); - preempt_enable(); + migrate_enable(); /* * The ARMv8 architecture doesn't give the hypervisor diff --git a/arch/hexagon/include/asm/spinlock_types.h b/arch/hexagon/include/asm/spinlock_types.h index 19d233497ba52..de72fb23016dc 100644 --- a/arch/hexagon/include/asm/spinlock_types.h +++ b/arch/hexagon/include/asm/spinlock_types.h @@ -8,10 +8,6 @@ #ifndef _ASM_SPINLOCK_TYPES_H #define _ASM_SPINLOCK_TYPES_H -#ifndef __LINUX_SPINLOCK_TYPES_H -# error "please don't include this file directly" -#endif - typedef struct { volatile unsigned int lock; } arch_spinlock_t; diff --git a/arch/ia64/include/asm/spinlock_types.h b/arch/ia64/include/asm/spinlock_types.h index 6e345fefcdcab..681408d6816fb 100644 --- a/arch/ia64/include/asm/spinlock_types.h +++ b/arch/ia64/include/asm/spinlock_types.h @@ -2,10 +2,6 @@ #ifndef _ASM_IA64_SPINLOCK_TYPES_H #define _ASM_IA64_SPINLOCK_TYPES_H -#ifndef __LINUX_SPINLOCK_TYPES_H -# error "please don't include this file directly" -#endif - typedef struct { volatile unsigned int lock; } arch_spinlock_t; diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 386ae12d8523b..a4fe480b4e9dd 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -147,6 +147,7 @@ config PPC select ARCH_OPTIONAL_KERNEL_RWX if ARCH_HAS_STRICT_KERNEL_RWX select ARCH_SUPPORTS_ATOMIC_RMW select ARCH_SUPPORTS_DEBUG_PAGEALLOC if PPC32 || PPC_BOOK3S_64 + 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_QUEUED_RWLOCKS if PPC_QUEUED_SPINLOCKS @@ -231,6 +232,7 @@ config PPC select HAVE_HARDLOCKUP_DETECTOR_PERF if PERF_EVENTS && HAVE_PERF_EVENTS_NMI && !HAVE_HARDLOCKUP_DETECTOR_ARCH select HAVE_PERF_REGS select HAVE_PERF_USER_STACK_DUMP + select HAVE_PREEMPT_LAZY select MMU_GATHER_RCU_TABLE_FREE select MMU_GATHER_PAGE_SIZE select HAVE_REGS_AND_STACK_ACCESS_API @@ -239,6 +241,7 @@ config PPC select HAVE_SYSCALL_TRACEPOINTS select HAVE_VIRT_CPU_ACCOUNTING select HAVE_IRQ_TIME_ACCOUNTING + select HAVE_POSIX_CPU_TIMERS_TASK_WORK if !KVM select HAVE_RSEQ select IOMMU_HELPER if PPC64 select IRQ_DOMAIN diff --git a/arch/powerpc/include/asm/cmpxchg.h b/arch/powerpc/include/asm/cmpxchg.h index cf091c4c22e53..7371f7e23c357 100644 --- a/arch/powerpc/include/asm/cmpxchg.h +++ b/arch/powerpc/include/asm/cmpxchg.h @@ -5,7 +5,7 @@ #ifdef __KERNEL__ #include #include -#include +#include #ifdef __BIG_ENDIAN #define BITOFF_CAL(size, off) ((sizeof(u32) - size - off) * BITS_PER_BYTE) diff --git a/arch/powerpc/include/asm/simple_spinlock_types.h b/arch/powerpc/include/asm/simple_spinlock_types.h index 0f3cdd8faa959..d45561e9e6bab 100644 --- a/arch/powerpc/include/asm/simple_spinlock_types.h +++ b/arch/powerpc/include/asm/simple_spinlock_types.h @@ -2,7 +2,7 @@ #ifndef _ASM_POWERPC_SIMPLE_SPINLOCK_TYPES_H #define _ASM_POWERPC_SIMPLE_SPINLOCK_TYPES_H -#ifndef __LINUX_SPINLOCK_TYPES_H +#if !defined(__LINUX_SPINLOCK_TYPES_H) && !defined(__LINUX_RT_MUTEX_H) # error "please don't include this file directly" #endif diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h index 7a13bc20f0a0c..e0ced3afc667f 100644 --- a/arch/powerpc/include/asm/smp.h +++ b/arch/powerpc/include/asm/smp.h @@ -57,6 +57,7 @@ struct smp_ops_t { extern int smp_send_nmi_ipi(int cpu, void (*fn)(struct pt_regs *), u64 delay_us); extern int smp_send_safe_nmi_ipi(int cpu, void (*fn)(struct pt_regs *), u64 delay_us); +extern void smp_send_debugger_break_cpu(unsigned int cpu); extern void smp_send_debugger_break(void); extern void start_secondary_resume(void); extern void smp_generic_give_timebase(void); diff --git a/arch/powerpc/include/asm/spinlock_types.h b/arch/powerpc/include/asm/spinlock_types.h index c5d742f18021d..cc6922a011ba1 100644 --- a/arch/powerpc/include/asm/spinlock_types.h +++ b/arch/powerpc/include/asm/spinlock_types.h @@ -2,10 +2,6 @@ #ifndef _ASM_POWERPC_SPINLOCK_TYPES_H #define _ASM_POWERPC_SPINLOCK_TYPES_H -#ifndef __LINUX_SPINLOCK_TYPES_H -# error "please don't include this file directly" -#endif - #ifdef CONFIG_PPC_QUEUED_SPINLOCKS #include #include diff --git a/arch/powerpc/include/asm/stackprotector.h b/arch/powerpc/include/asm/stackprotector.h index 1c8460e235838..b1653c160bab9 100644 --- a/arch/powerpc/include/asm/stackprotector.h +++ b/arch/powerpc/include/asm/stackprotector.h @@ -24,7 +24,11 @@ static __always_inline void boot_init_stack_canary(void) unsigned long canary; /* Try to get a semi random initial value. */ +#ifdef CONFIG_PREEMPT_RT + canary = (unsigned long)&canary; +#else canary = get_random_canary(); +#endif canary ^= mftb(); canary ^= LINUX_VERSION_CODE; canary &= CANARY_MASK; diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h index 386d576673a1d..730ce15944ce0 100644 --- a/arch/powerpc/include/asm/thread_info.h +++ b/arch/powerpc/include/asm/thread_info.h @@ -48,6 +48,8 @@ struct thread_info { int preempt_count; /* 0 => preemptable, <0 => BUG */ + int preempt_lazy_count; /* 0 => preemptable, + <0 => BUG */ unsigned long local_flags; /* private flags for thread */ #ifdef CONFIG_LIVEPATCH unsigned long *livepatch_sp; @@ -94,6 +96,7 @@ void arch_setup_new_exec(void); #define TIF_PATCH_PENDING 6 /* pending live patching update */ #define TIF_SYSCALL_AUDIT 7 /* syscall auditing active */ #define TIF_SINGLESTEP 8 /* singlestepping active */ +#define TIF_NEED_RESCHED_LAZY 9 /* lazy rescheduling necessary */ #define TIF_SECCOMP 10 /* secure computing */ #define TIF_RESTOREALL 11 /* Restore all regs (implies NOERROR) */ #define TIF_NOERROR 12 /* Force successful syscall return */ @@ -109,6 +112,7 @@ void arch_setup_new_exec(void); #define TIF_POLLING_NRFLAG 19 /* true if poll_idle() is polling TIF_NEED_RESCHED */ #define TIF_32BIT 20 /* 32 bit binary */ + /* as above, but as bit values */ #define _TIF_SYSCALL_TRACE (1<flags); while (unlikely(ti_flags & (_TIF_USER_WORK_MASK & ~_TIF_RESTORE_TM))) { local_irq_enable(); - if (ti_flags & _TIF_NEED_RESCHED) { + if (ti_flags & _TIF_NEED_RESCHED_MASK) { schedule(); } else { /* @@ -381,7 +381,7 @@ notrace unsigned long interrupt_exit_user_prepare(struct pt_regs *regs, unsigned ti_flags = READ_ONCE(current_thread_info()->flags); while (unlikely(ti_flags & (_TIF_USER_WORK_MASK & ~_TIF_RESTORE_TM))) { local_irq_enable(); /* returning to user: may enable */ - if (ti_flags & _TIF_NEED_RESCHED) { + if (ti_flags & _TIF_NEED_RESCHED_MASK) { schedule(); } else { if (ti_flags & _TIF_SIGPENDING) @@ -473,11 +473,15 @@ notrace unsigned long interrupt_exit_kernel_prepare(struct pt_regs *regs, unsign /* Returning to a kernel context with local irqs enabled. */ WARN_ON_ONCE(!(regs->msr & MSR_EE)); again: - if (IS_ENABLED(CONFIG_PREEMPT)) { + if (IS_ENABLED(CONFIG_PREEMPTION)) { /* Return to preemptible kernel context */ if (unlikely(current_thread_info()->flags & _TIF_NEED_RESCHED)) { if (preempt_count() == 0) preempt_schedule_irq(); + } else if (unlikely(current_thread_info()->flags & _TIF_NEED_RESCHED_LAZY)) { + if ((preempt_count() == 0) && + (current_thread_info()->preempt_lazy_count == 0)) + preempt_schedule_irq(); } } diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index d71fd10a1dd46..4135f7c44dec9 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -751,10 +751,12 @@ void *mcheckirq_ctx[NR_CPUS] __read_mostly; void *softirq_ctx[NR_CPUS] __read_mostly; void *hardirq_ctx[NR_CPUS] __read_mostly; +#ifndef CONFIG_PREEMPT_RT void do_softirq_own_stack(void) { call_do_softirq(softirq_ctx[smp_processor_id()]); } +#endif irq_hw_number_t virq_to_hw(unsigned int virq) { diff --git a/arch/powerpc/kernel/kgdb.c b/arch/powerpc/kernel/kgdb.c index 409080208a6c4..1f716688c9775 100644 --- a/arch/powerpc/kernel/kgdb.c +++ b/arch/powerpc/kernel/kgdb.c @@ -20,6 +20,7 @@ #include #include #include +#include #include #include #include @@ -120,11 +121,19 @@ int kgdb_skipexception(int exception, struct pt_regs *regs) static int kgdb_debugger_ipi(struct pt_regs *regs) { - kgdb_nmicallback(raw_smp_processor_id(), regs); + int cpu = raw_smp_processor_id(); + + if (!console_atomic_kgdb_cpu_delay(cpu)) + kgdb_nmicallback(cpu, regs); return 0; } #ifdef CONFIG_SMP +void kgdb_roundup_cpu(unsigned int cpu) +{ + smp_send_debugger_break_cpu(cpu); +} + void kgdb_roundup_cpus(void) { smp_send_debugger_break(); diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S index 717e658b90fd8..08ee95ad6593a 100644 --- a/arch/powerpc/kernel/misc_32.S +++ b/arch/powerpc/kernel/misc_32.S @@ -31,6 +31,7 @@ * We store the saved ksp_limit in the unused part * of the STACK_FRAME_OVERHEAD */ +#ifndef CONFIG_PREEMPT_RT _GLOBAL(call_do_softirq) mflr r0 stw r0,4(r1) @@ -46,6 +47,7 @@ _GLOBAL(call_do_softirq) stw r10,THREAD+KSP_LIMIT(r2) mtlr r0 blr +#endif /* * void call_do_irq(struct pt_regs *regs, void *sp); diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S index 070465825c210..a6b33f7b32646 100644 --- a/arch/powerpc/kernel/misc_64.S +++ b/arch/powerpc/kernel/misc_64.S @@ -27,6 +27,7 @@ .text +#ifndef CONFIG_PREEMPT_RT _GLOBAL(call_do_softirq) mflr r0 std r0,16(r1) @@ -37,6 +38,7 @@ _GLOBAL(call_do_softirq) ld r0,16(r1) mtlr r0 blr +#endif _GLOBAL(call_do_irq) mflr r0 diff --git a/arch/powerpc/kernel/nvram_64.c b/arch/powerpc/kernel/nvram_64.c index 532f226377831..3c8d9bbb51cfa 100644 --- a/arch/powerpc/kernel/nvram_64.c +++ b/arch/powerpc/kernel/nvram_64.c @@ -647,6 +647,7 @@ static void oops_to_nvram(struct kmsg_dumper *dumper, { struct oops_log_info *oops_hdr = (struct oops_log_info *)oops_buf; static unsigned int oops_count = 0; + static struct kmsg_dump_iter iter; static bool panicking = false; static DEFINE_SPINLOCK(lock); unsigned long flags; @@ -681,13 +682,14 @@ static void oops_to_nvram(struct kmsg_dumper *dumper, return; if (big_oops_buf) { - kmsg_dump_get_buffer(dumper, false, + kmsg_dump_rewind(&iter); + kmsg_dump_get_buffer(&iter, false, big_oops_buf, big_oops_buf_sz, &text_len); rc = zip_oops(text_len); } if (rc != 0) { - kmsg_dump_rewind(dumper); - kmsg_dump_get_buffer(dumper, false, + kmsg_dump_rewind(&iter); + kmsg_dump_get_buffer(&iter, false, oops_data, oops_data_sz, &text_len); err_type = ERR_TYPE_KERNEL_PANIC; oops_hdr->version = cpu_to_be16(OOPS_HDR_VERSION); diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 5a4d59a1070d5..b396c6eafce38 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -582,6 +582,11 @@ static void debugger_ipi_callback(struct pt_regs *regs) debugger_ipi(regs); } +void smp_send_debugger_break_cpu(unsigned int cpu) +{ + smp_send_nmi_ipi(cpu, debugger_ipi_callback, 1000000); +} + void smp_send_debugger_break(void) { smp_send_nmi_ipi(NMI_IPI_ALL_OTHERS, debugger_ipi_callback, 1000000); diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index a44a30b0688ca..6d0f70abed872 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -171,7 +171,6 @@ extern void panic_flush_kmsg_start(void) extern void panic_flush_kmsg_end(void) { - printk_safe_flush_on_panic(); kmsg_dump(KMSG_DUMP_PANIC); bust_spinlocks(0); debug_locks_off(); @@ -261,12 +260,17 @@ 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" : "", diff --git a/arch/powerpc/kernel/watchdog.c b/arch/powerpc/kernel/watchdog.c index c9a8f4781a101..dc17d8903d4f3 100644 --- a/arch/powerpc/kernel/watchdog.c +++ b/arch/powerpc/kernel/watchdog.c @@ -183,11 +183,6 @@ static void watchdog_smp_panic(int cpu, u64 tb) wd_smp_unlock(&flags); - printk_safe_flush(); - /* - * printk_safe_flush() seems to require another print - * before anything actually goes out to console. - */ if (sysctl_hardlockup_all_cpu_backtrace) trigger_allbutself_cpu_backtrace(); diff --git a/arch/powerpc/kexec/crash.c b/arch/powerpc/kexec/crash.c index c9a889880214e..d488311efab1f 100644 --- a/arch/powerpc/kexec/crash.c +++ b/arch/powerpc/kexec/crash.c @@ -311,9 +311,6 @@ void default_machine_crash_shutdown(struct pt_regs *regs) unsigned int i; int (*old_handler)(struct pt_regs *regs); - /* Avoid hardlocking with irresponsive CPU holding logbuf_lock */ - printk_nmi_enter(); - /* * This function is only called after the system * has panicked or is otherwise in a critical state. diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig index e45644657d49d..b826174ce983b 100644 --- a/arch/powerpc/kvm/Kconfig +++ b/arch/powerpc/kvm/Kconfig @@ -179,6 +179,7 @@ config KVM_E500MC config KVM_MPIC bool "KVM in-kernel MPIC emulation" depends on KVM && E500 + depends on !PREEMPT_RT select HAVE_KVM_IRQCHIP select HAVE_KVM_IRQFD select HAVE_KVM_IRQ_ROUTING diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index 4e8ce6d852323..7a59a5c9aa5dc 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -54,7 +54,6 @@ #include -static DEFINE_MUTEX(linear_mapping_mutex); unsigned long long memory_limit; bool init_mem_is_free; @@ -72,6 +71,7 @@ pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, EXPORT_SYMBOL(phys_mem_access_prot); #ifdef CONFIG_MEMORY_HOTPLUG +static DEFINE_MUTEX(linear_mapping_mutex); #ifdef CONFIG_NUMA int memory_add_physaddr_to_nid(u64 start) diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index 9fc5217f0c8e5..4fdb9370b9133 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -24,6 +24,7 @@ #include #include #include +#include #include #include #include @@ -190,7 +191,13 @@ 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, @@ -212,9 +219,10 @@ 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}() @@ -223,12 +231,12 @@ 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, tbl->it_page_shift, npages, uaddr, direction, attrs); } - __this_cpu_write(tce_page, tcep); + __this_cpu_write(tce_page.page, tcep); } rpn = __pa(uaddr) >> TCE_SHIFT; @@ -258,7 +266,7 @@ 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; @@ -429,16 +437,17 @@ 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; @@ -481,7 +490,7 @@ 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; } diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index 3fe37495f63dc..bf7d69625a2e5 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -3001,7 +3001,7 @@ print_address(unsigned long addr) static void dump_log_buf(void) { - struct kmsg_dumper dumper = { .active = 1 }; + struct kmsg_dump_iter iter; unsigned char buf[128]; size_t len; @@ -3013,9 +3013,9 @@ dump_log_buf(void) catch_memory_errors = 1; sync(); - kmsg_dump_rewind_nolock(&dumper); + kmsg_dump_rewind(&iter); xmon_start_pagination(); - while (kmsg_dump_get_line_nolock(&dumper, false, buf, sizeof(buf), &len)) { + while (kmsg_dump_get_line(&iter, false, buf, sizeof(buf), &len)) { buf[len] = '\0'; printf("%s", buf); } diff --git a/arch/s390/include/asm/spinlock_types.h b/arch/s390/include/asm/spinlock_types.h index cfed272e4fd59..8e28e8176ec88 100644 --- a/arch/s390/include/asm/spinlock_types.h +++ b/arch/s390/include/asm/spinlock_types.h @@ -2,10 +2,6 @@ #ifndef __ASM_SPINLOCK_TYPES_H #define __ASM_SPINLOCK_TYPES_H -#ifndef __LINUX_SPINLOCK_TYPES_H -# error "please don't include this file directly" -#endif - typedef struct { int lock; } __attribute__ ((aligned (4))) arch_spinlock_t; diff --git a/arch/sh/include/asm/spinlock_types.h b/arch/sh/include/asm/spinlock_types.h index e82369f286a20..22ca9a98bbb8b 100644 --- a/arch/sh/include/asm/spinlock_types.h +++ b/arch/sh/include/asm/spinlock_types.h @@ -2,10 +2,6 @@ #ifndef __ASM_SH_SPINLOCK_TYPES_H #define __ASM_SH_SPINLOCK_TYPES_H -#ifndef __LINUX_SPINLOCK_TYPES_H -# error "please don't include this file directly" -#endif - typedef struct { volatile unsigned int lock; } arch_spinlock_t; diff --git a/arch/sh/kernel/irq.c b/arch/sh/kernel/irq.c index ef0f0827cf575..2d3eca8fee011 100644 --- a/arch/sh/kernel/irq.c +++ b/arch/sh/kernel/irq.c @@ -149,6 +149,7 @@ void irq_ctx_exit(int cpu) hardirq_ctx[cpu] = NULL; } +#ifndef CONFIG_PREEMPT_RT void do_softirq_own_stack(void) { struct thread_info *curctx; @@ -176,6 +177,7 @@ void do_softirq_own_stack(void) "r5", "r6", "r7", "r8", "r9", "r15", "t", "pr" ); } +#endif #else static inline void handle_one_irq(unsigned int irq) { diff --git a/arch/sparc/kernel/irq_64.c b/arch/sparc/kernel/irq_64.c index c8848bb681a11..41fa1be980a33 100644 --- a/arch/sparc/kernel/irq_64.c +++ b/arch/sparc/kernel/irq_64.c @@ -855,6 +855,7 @@ void __irq_entry handler_irq(int pil, struct pt_regs *regs) set_irq_regs(old_regs); } +#ifndef CONFIG_PREEMPT_RT void do_softirq_own_stack(void) { void *orig_sp, *sp = softirq_stack[smp_processor_id()]; @@ -869,6 +870,7 @@ void do_softirq_own_stack(void) __asm__ __volatile__("mov %0, %%sp" : : "r" (orig_sp)); } +#endif #ifdef CONFIG_HOTPLUG_CPU void fixup_irqs(void) diff --git a/arch/um/kernel/kmsg_dump.c b/arch/um/kernel/kmsg_dump.c index 6516ef1f82745..0224fcb36e22c 100644 --- a/arch/um/kernel/kmsg_dump.c +++ b/arch/um/kernel/kmsg_dump.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include +#include #include #include #include @@ -9,8 +10,11 @@ static void kmsg_dumper_stdout(struct kmsg_dumper *dumper, enum kmsg_dump_reason reason) { + static struct kmsg_dump_iter iter; + static DEFINE_SPINLOCK(lock); static char line[1024]; struct console *con; + unsigned long flags; size_t len = 0; /* only dump kmsg when no console is available */ @@ -29,11 +33,18 @@ static void kmsg_dumper_stdout(struct kmsg_dumper *dumper, if (con) return; + if (!spin_trylock_irqsave(&lock, flags)) + return; + + kmsg_dump_rewind(&iter); + printf("kmsg_dump:\n"); - while (kmsg_dump_get_line(dumper, true, line, sizeof(line), &len)) { + while (kmsg_dump_get_line(&iter, true, line, sizeof(line), &len)) { line[len] = '\0'; printf("%s", line); } + + spin_unlock_irqrestore(&lock, flags); } static struct kmsg_dumper kmsg_dumper = { diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 2792879d398ee..2f4fd6a7e82e0 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -99,6 +99,7 @@ config X86 select ARCH_SUPPORTS_KMAP_LOCAL_FORCE_MAP if NR_CPUS <= 4096 select ARCH_SUPPORTS_LTO_CLANG if X86_64 select ARCH_SUPPORTS_LTO_CLANG_THIN if X86_64 + select ARCH_SUPPORTS_RT select ARCH_USE_BUILTIN_BSWAP select ARCH_USE_QUEUED_RWLOCKS select ARCH_USE_QUEUED_SPINLOCKS @@ -220,6 +221,7 @@ config X86 select HAVE_PCI select HAVE_PERF_REGS select HAVE_PERF_USER_STACK_DUMP + select HAVE_PREEMPT_LAZY select MMU_GATHER_RCU_TABLE_FREE if PARAVIRT select HAVE_POSIX_CPU_TIMERS_TASK_WORK select HAVE_REGS_AND_STACK_ACCESS_API diff --git a/arch/x86/include/asm/fpu/api.h b/arch/x86/include/asm/fpu/api.h index ed33a14188f66..716727dfd1afa 100644 --- a/arch/x86/include/asm/fpu/api.h +++ b/arch/x86/include/asm/fpu/api.h @@ -28,6 +28,7 @@ extern void kernel_fpu_begin_mask(unsigned int kfpu_mask); extern void kernel_fpu_end(void); extern bool irq_fpu_usable(void); extern void fpregs_mark_activate(void); +extern void kernel_fpu_resched(void); /* Code that is unaware of kernel_fpu_begin_mask() can use this */ static inline void kernel_fpu_begin(void) diff --git a/arch/x86/include/asm/irq_stack.h b/arch/x86/include/asm/irq_stack.h index 9b2a0ff76c73e..fe12ba2a5c658 100644 --- a/arch/x86/include/asm/irq_stack.h +++ b/arch/x86/include/asm/irq_stack.h @@ -188,6 +188,7 @@ #define ASM_CALL_SOFTIRQ \ "call %P[__func] \n" +#ifndef CONFIG_PREEMPT_RT /* * Macro to invoke __do_softirq on the irq stack. This is only called from * task context when bottom halfs are about to be reenabled and soft @@ -201,6 +202,8 @@ __this_cpu_write(hardirq_stack_inuse, false); \ } +#endif + #else /* CONFIG_X86_64 */ /* System vector handlers always run on the stack they interrupted. */ #define run_sysvec_on_irqstack_cond(func, regs) \ diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h index f8cb8af4de5ce..dde8f20cb7025 100644 --- a/arch/x86/include/asm/preempt.h +++ b/arch/x86/include/asm/preempt.h @@ -90,20 +90,54 @@ static __always_inline void __preempt_count_sub(int val) * a decrement which hits zero means we have no preempt_count and should * reschedule. */ -static __always_inline bool __preempt_count_dec_and_test(void) +static __always_inline bool ____preempt_count_dec_and_test(void) { return GEN_UNARY_RMWcc("decl", __preempt_count, e, __percpu_arg([var])); } +static __always_inline bool __preempt_count_dec_and_test(void) +{ + if (____preempt_count_dec_and_test()) + return true; +#ifdef CONFIG_PREEMPT_LAZY + if (preempt_count()) + return false; + if (current_thread_info()->preempt_lazy_count) + return false; + return test_thread_flag(TIF_NEED_RESCHED_LAZY); +#else + return false; +#endif +} + /* * Returns true when we need to resched and can (barring IRQ state). */ static __always_inline bool should_resched(int preempt_offset) { +#ifdef CONFIG_PREEMPT_LAZY + u32 tmp; + tmp = raw_cpu_read_4(__preempt_count); + if (tmp == preempt_offset) + return true; + + /* preempt count == 0 ? */ + tmp &= ~PREEMPT_NEED_RESCHED; + if (tmp != preempt_offset) + return false; + /* XXX PREEMPT_LOCK_OFFSET */ + if (current_thread_info()->preempt_lazy_count) + return false; + return test_thread_flag(TIF_NEED_RESCHED_LAZY); +#else return unlikely(raw_cpu_read_4(__preempt_count) == preempt_offset); +#endif } #ifdef CONFIG_PREEMPTION +#ifdef CONFIG_PREEMPT_RT + extern void preempt_schedule_lock(void); +#endif extern asmlinkage void preempt_schedule(void); extern asmlinkage void preempt_schedule_thunk(void); diff --git a/arch/x86/include/asm/signal.h b/arch/x86/include/asm/signal.h index 6fd8410a3910c..f3bf2f515edb3 100644 --- a/arch/x86/include/asm/signal.h +++ b/arch/x86/include/asm/signal.h @@ -28,6 +28,19 @@ typedef struct { #define SA_IA32_ABI 0x02000000u #define SA_X32_ABI 0x01000000u +/* + * Because some traps use the IST stack, we must keep preemption + * disabled while calling do_trap(), but do_trap() may call + * force_sig_info() which will grab the signal spin_locks for the + * task, which in PREEMPT_RT are mutexes. By defining + * ARCH_RT_DELAYS_SIGNAL_SEND the force_sig_info() will set + * TIF_NOTIFY_RESUME and set up the signal to be sent on exit of the + * trap. + */ +#if defined(CONFIG_PREEMPT_RT) +#define ARCH_RT_DELAYS_SIGNAL_SEND +#endif + #ifndef CONFIG_COMPAT typedef sigset_t compat_sigset_t; #endif diff --git a/arch/x86/include/asm/stackprotector.h b/arch/x86/include/asm/stackprotector.h index 7fb482f0f25b0..3df0a95c9e134 100644 --- a/arch/x86/include/asm/stackprotector.h +++ b/arch/x86/include/asm/stackprotector.h @@ -65,7 +65,7 @@ */ static __always_inline void boot_init_stack_canary(void) { - u64 canary; + u64 canary = 0; u64 tsc; #ifdef CONFIG_X86_64 @@ -76,8 +76,14 @@ static __always_inline void boot_init_stack_canary(void) * of randomness. The TSC only matters for very early init, * there it already has some randomness on most systems. Later * on during the bootup the random pool has true entropy too. + * For preempt-rt we need to weaken the randomness a bit, as + * we can't call into the random generator from atomic context + * due to locking constraints. We just leave canary + * uninitialized and use the TSC based randomness on top of it. */ +#ifndef CONFIG_PREEMPT_RT get_random_bytes(&canary, sizeof(canary)); +#endif tsc = rdtsc(); canary += tsc + (tsc << 32UL); canary &= CANARY_MASK; diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index 0d751d5da702e..2e62434951fa7 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -57,11 +57,14 @@ struct thread_info { unsigned long flags; /* low level flags */ unsigned long syscall_work; /* SYSCALL_WORK_ flags */ u32 status; /* thread synchronous flags */ + int preempt_lazy_count; /* 0 => lazy preemptable + <0 => BUG */ }; #define INIT_THREAD_INFO(tsk) \ { \ .flags = 0, \ + .preempt_lazy_count = 0, \ } #else /* !__ASSEMBLY__ */ @@ -90,6 +93,7 @@ struct thread_info { #define TIF_NOTSC 16 /* TSC is not accessible in userland */ #define TIF_NOTIFY_SIGNAL 17 /* signal notifications exist */ #define TIF_SLD 18 /* Restore split lock detection on context switch */ +#define TIF_NEED_RESCHED_LAZY 19 /* lazy rescheduling necessary */ #define TIF_MEMDIE 20 /* is terminating due to OOM killer */ #define TIF_POLLING_NRFLAG 21 /* idle is polling for TIF_NEED_RESCHED */ #define TIF_IO_BITMAP 22 /* uses I/O bitmap */ @@ -113,6 +117,7 @@ struct thread_info { #define _TIF_NOTSC (1 << TIF_NOTSC) #define _TIF_NOTIFY_SIGNAL (1 << TIF_NOTIFY_SIGNAL) #define _TIF_SLD (1 << TIF_SLD) +#define _TIF_NEED_RESCHED_LAZY (1 << TIF_NEED_RESCHED_LAZY) #define _TIF_POLLING_NRFLAG (1 << TIF_POLLING_NRFLAG) #define _TIF_IO_BITMAP (1 << TIF_IO_BITMAP) #define _TIF_FORCED_TF (1 << TIF_FORCED_TF) @@ -143,6 +148,8 @@ struct thread_info { #define _TIF_WORK_CTXSW_NEXT (_TIF_WORK_CTXSW) +#define _TIF_NEED_RESCHED_MASK (_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY) + #define STACK_WARN (THREAD_SIZE/8) /* diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index e88bc296afca0..73a2494a0b2e2 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -85,11 +85,12 @@ EXPORT_SYMBOL_GPL(hv_remove_vmbus_irq); DEFINE_IDTENTRY_SYSVEC(sysvec_hyperv_stimer0) { struct pt_regs *old_regs = set_irq_regs(regs); + u64 ip = regs ? instruction_pointer(regs) : 0; inc_irq_stat(hyperv_stimer0_count); if (hv_stimer0_handler) hv_stimer0_handler(); - add_interrupt_randomness(HYPERV_STIMER0_VECTOR, 0); + add_interrupt_randomness(HYPERV_STIMER0_VECTOR, 0, ip); ack_APIC_irq(); set_irq_regs(old_regs); diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index 571220ac8beaa..d315d45b64faa 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -159,6 +159,18 @@ void kernel_fpu_end(void) } EXPORT_SYMBOL_GPL(kernel_fpu_end); +void kernel_fpu_resched(void) +{ + WARN_ON_FPU(!this_cpu_read(in_kernel_fpu)); + + if (should_resched(PREEMPT_OFFSET)) { + kernel_fpu_end(); + cond_resched(); + kernel_fpu_begin(); + } +} +EXPORT_SYMBOL_GPL(kernel_fpu_resched); + /* * Save the FPU state (mark it for reload if necessary): * diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c index 044902d5a3c4a..e5dd6da78713b 100644 --- a/arch/x86/kernel/irq_32.c +++ b/arch/x86/kernel/irq_32.c @@ -132,6 +132,7 @@ int irq_init_percpu_irqstack(unsigned int cpu) return 0; } +#ifndef CONFIG_PREEMPT_RT void do_softirq_own_stack(void) { struct irq_stack *irqstk; @@ -148,6 +149,7 @@ void do_softirq_own_stack(void) call_on_stack(__do_softirq, isp); } +#endif void __handle_irq(struct irq_desc *desc, struct pt_regs *regs) { diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c index ff7878df96b46..ac9d63b0b8645 100644 --- a/arch/x86/kernel/kgdb.c +++ b/arch/x86/kernel/kgdb.c @@ -32,6 +32,7 @@ #include #include #include +#include #include #include #include @@ -502,9 +503,12 @@ static int kgdb_nmi_handler(unsigned int cmd, struct pt_regs *regs) if (atomic_read(&kgdb_active) != -1) { /* KGDB CPU roundup */ cpu = raw_smp_processor_id(); - kgdb_nmicallback(cpu, regs); - set_bit(cpu, was_in_debug_nmi); - touch_nmi_watchdog(); + + if (!console_atomic_kgdb_cpu_delay(cpu)) { + kgdb_nmicallback(cpu, regs); + set_bit(cpu, was_in_debug_nmi); + touch_nmi_watchdog(); + } return NMI_HANDLED; } diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 47e021bdcc94a..891c3239e2b0c 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -7979,6 +7979,14 @@ int kvm_arch_init(void *opaque) goto out; } +#ifdef CONFIG_PREEMPT_RT + if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) { + pr_err("RT requires X86_FEATURE_CONSTANT_TSC\n"); + r = -EOPNOTSUPP; + goto out; + } +#endif + r = -ENOMEM; x86_fpu_cache = kmem_cache_create("x86_fpu", sizeof(struct fpu), __alignof__(struct fpu), SLAB_ACCOUNT, diff --git a/arch/xtensa/include/asm/spinlock_types.h b/arch/xtensa/include/asm/spinlock_types.h index 64c9389254f13..dc846323b1cd7 100644 --- a/arch/xtensa/include/asm/spinlock_types.h +++ b/arch/xtensa/include/asm/spinlock_types.h @@ -2,10 +2,6 @@ #ifndef __ASM_SPINLOCK_TYPES_H #define __ASM_SPINLOCK_TYPES_H -#if !defined(__LINUX_SPINLOCK_TYPES_H) && !defined(__ASM_SPINLOCK_H) -# error "please don't include this file directly" -#endif - #include #include diff --git a/block/blk-mq.c b/block/blk-mq.c index d4d7c1caa4396..2003865f725bc 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -1560,14 +1560,14 @@ static void __blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async, return; if (!async && !(hctx->flags & BLK_MQ_F_BLOCKING)) { - int cpu = get_cpu(); + int cpu = get_cpu_light(); if (cpumask_test_cpu(cpu, hctx->cpumask)) { __blk_mq_run_hw_queue(hctx); - put_cpu(); + put_cpu_light(); return; } - put_cpu(); + put_cpu_light(); } kblockd_mod_delayed_work_on(blk_mq_hctx_next_cpu(hctx), &hctx->run_work, diff --git a/crypto/cryptd.c b/crypto/cryptd.c index a1bea0f4baa88..5f8ca8c1f59cd 100644 --- a/crypto/cryptd.c +++ b/crypto/cryptd.c @@ -36,6 +36,7 @@ static struct workqueue_struct *cryptd_wq; struct cryptd_cpu_queue { struct crypto_queue queue; struct work_struct work; + spinlock_t qlock; }; struct cryptd_queue { @@ -105,6 +106,7 @@ static int cryptd_init_queue(struct cryptd_queue *queue, cpu_queue = per_cpu_ptr(queue->cpu_queue, cpu); crypto_init_queue(&cpu_queue->queue, max_cpu_qlen); INIT_WORK(&cpu_queue->work, cryptd_queue_worker); + spin_lock_init(&cpu_queue->qlock); } pr_info("cryptd: max_cpu_qlen set to %d\n", max_cpu_qlen); return 0; @@ -129,8 +131,10 @@ static int cryptd_enqueue_request(struct cryptd_queue *queue, struct cryptd_cpu_queue *cpu_queue; refcount_t *refcnt; - cpu = get_cpu(); - cpu_queue = this_cpu_ptr(queue->cpu_queue); + cpu_queue = raw_cpu_ptr(queue->cpu_queue); + spin_lock_bh(&cpu_queue->qlock); + cpu = smp_processor_id(); + err = crypto_enqueue_request(&cpu_queue->queue, request); refcnt = crypto_tfm_ctx(request->tfm); @@ -146,7 +150,7 @@ static int cryptd_enqueue_request(struct cryptd_queue *queue, refcount_inc(refcnt); out_put_cpu: - put_cpu(); + spin_unlock_bh(&cpu_queue->qlock); return err; } @@ -162,16 +166,11 @@ static void cryptd_queue_worker(struct work_struct *work) cpu_queue = container_of(work, struct cryptd_cpu_queue, work); /* * Only handle one request at a time to avoid hogging crypto workqueue. - * preempt_disable/enable is used to prevent being preempted by - * cryptd_enqueue_request(). local_bh_disable/enable is used to prevent - * cryptd_enqueue_request() being accessed from software interrupts. */ - local_bh_disable(); - preempt_disable(); + spin_lock_bh(&cpu_queue->qlock); backlog = crypto_get_backlog(&cpu_queue->queue); req = crypto_dequeue_request(&cpu_queue->queue); - preempt_enable(); - local_bh_enable(); + spin_unlock_bh(&cpu_queue->qlock); if (!req) return; diff --git a/drivers/atm/eni.c b/drivers/atm/eni.c index b574cce98dc36..422753d52244b 100644 --- a/drivers/atm/eni.c +++ b/drivers/atm/eni.c @@ -2054,7 +2054,7 @@ static int eni_send(struct atm_vcc *vcc,struct sk_buff *skb) } submitted++; ATM_SKB(skb)->vcc = vcc; - tasklet_disable(&ENI_DEV(vcc->dev)->task); + tasklet_disable_in_atomic(&ENI_DEV(vcc->dev)->task); res = do_tx(skb); tasklet_enable(&ENI_DEV(vcc->dev)->task); if (res == enq_ok) return 0; diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index cf8deecc39efb..5c7999ebc4e08 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -59,6 +59,40 @@ static void zram_free_page(struct zram *zram, size_t index); static int zram_bvec_read(struct zram *zram, struct bio_vec *bvec, u32 index, int offset, struct bio *bio); +#ifdef CONFIG_PREEMPT_RT +static void zram_meta_init_table_locks(struct zram *zram, size_t num_pages) +{ + size_t index; + + for (index = 0; index < num_pages; index++) + spin_lock_init(&zram->table[index].lock); +} + +static int zram_slot_trylock(struct zram *zram, u32 index) +{ + int ret; + + ret = spin_trylock(&zram->table[index].lock); + if (ret) + __set_bit(ZRAM_LOCK, &zram->table[index].flags); + return ret; +} + +static void zram_slot_lock(struct zram *zram, u32 index) +{ + spin_lock(&zram->table[index].lock); + __set_bit(ZRAM_LOCK, &zram->table[index].flags); +} + +static void zram_slot_unlock(struct zram *zram, u32 index) +{ + __clear_bit(ZRAM_LOCK, &zram->table[index].flags); + spin_unlock(&zram->table[index].lock); +} + +#else + +static void zram_meta_init_table_locks(struct zram *zram, size_t num_pages) { } static int zram_slot_trylock(struct zram *zram, u32 index) { @@ -74,6 +108,7 @@ static void zram_slot_unlock(struct zram *zram, u32 index) { bit_spin_unlock(ZRAM_LOCK, &zram->table[index].flags); } +#endif static inline bool init_done(struct zram *zram) { @@ -1169,6 +1204,7 @@ static bool zram_meta_alloc(struct zram *zram, u64 disksize) if (!huge_class_size) huge_class_size = zs_huge_class_size(zram->mem_pool); + zram_meta_init_table_locks(zram, num_pages); return true; } diff --git a/drivers/block/zram/zram_drv.h b/drivers/block/zram/zram_drv.h index 419a7e8281ee3..561c7ba1421ff 100644 --- a/drivers/block/zram/zram_drv.h +++ b/drivers/block/zram/zram_drv.h @@ -63,6 +63,7 @@ struct zram_table_entry { unsigned long element; }; unsigned long flags; + spinlock_t lock; #ifdef CONFIG_ZRAM_MEMORY_TRACKING ktime_t ac_time; #endif diff --git a/drivers/char/random.c b/drivers/char/random.c index 0fe9e200e4c84..da0a1ef9615c5 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -1252,26 +1252,25 @@ static __u32 get_reg(struct fast_pool *f, struct pt_regs *regs) return *ptr; } -void add_interrupt_randomness(int irq, int irq_flags) +void add_interrupt_randomness(int irq, int irq_flags, __u64 ip) { struct entropy_store *r; struct fast_pool *fast_pool = this_cpu_ptr(&irq_randomness); - struct pt_regs *regs = get_irq_regs(); unsigned long now = jiffies; cycles_t cycles = random_get_entropy(); __u32 c_high, j_high; - __u64 ip; if (cycles == 0) - cycles = get_reg(fast_pool, regs); + cycles = get_reg(fast_pool, NULL); c_high = (sizeof(cycles) > 4) ? cycles >> 32 : 0; j_high = (sizeof(now) > 4) ? now >> 32 : 0; fast_pool->pool[0] ^= cycles ^ j_high ^ irq; fast_pool->pool[1] ^= now ^ c_high; - ip = regs ? instruction_pointer(regs) : _RET_IP_; + if (!ip) + ip = _RET_IP_; fast_pool->pool[2] ^= ip; fast_pool->pool[3] ^= (sizeof(ip) > 4) ? ip >> 32 : - get_reg(fast_pool, regs); + get_reg(fast_pool, NULL); fast_mix(fast_pool); add_interrupt_bench(cycles); diff --git a/drivers/char/tpm/tpm_tis.c b/drivers/char/tpm/tpm_tis.c index 4ed6e660273a4..c2bd0d40b5fc2 100644 --- a/drivers/char/tpm/tpm_tis.c +++ b/drivers/char/tpm/tpm_tis.c @@ -50,6 +50,31 @@ static inline struct tpm_tis_tcg_phy *to_tpm_tis_tcg_phy(struct tpm_tis_data *da return container_of(data, struct tpm_tis_tcg_phy, priv); } +#ifdef CONFIG_PREEMPT_RT +/* + * Flushes previous write operations to chip so that a subsequent + * ioread*()s won't stall a cpu. + */ +static inline void tpm_tis_flush(void __iomem *iobase) +{ + ioread8(iobase + TPM_ACCESS(0)); +} +#else +#define tpm_tis_flush(iobase) do { } while (0) +#endif + +static inline void tpm_tis_iowrite8(u8 b, void __iomem *iobase, u32 addr) +{ + iowrite8(b, iobase + addr); + tpm_tis_flush(iobase); +} + +static inline void tpm_tis_iowrite32(u32 b, void __iomem *iobase, u32 addr) +{ + iowrite32(b, iobase + addr); + tpm_tis_flush(iobase); +} + static int interrupts = -1; module_param(interrupts, int, 0444); MODULE_PARM_DESC(interrupts, "Enable interrupts"); @@ -169,7 +194,7 @@ static int tpm_tcg_write_bytes(struct tpm_tis_data *data, u32 addr, u16 len, struct tpm_tis_tcg_phy *phy = to_tpm_tis_tcg_phy(data); while (len--) - iowrite8(*value++, phy->iobase + addr); + tpm_tis_iowrite8(*value++, phy->iobase, addr); return 0; } @@ -196,7 +221,7 @@ static int tpm_tcg_write32(struct tpm_tis_data *data, u32 addr, u32 value) { struct tpm_tis_tcg_phy *phy = to_tpm_tis_tcg_phy(data); - iowrite32(value, phy->iobase + addr); + tpm_tis_iowrite32(value, phy->iobase, addr); return 0; } diff --git a/drivers/firewire/ohci.c b/drivers/firewire/ohci.c index 9811c40956e54..17c9d825188bb 100644 --- a/drivers/firewire/ohci.c +++ b/drivers/firewire/ohci.c @@ -2545,7 +2545,7 @@ static int ohci_cancel_packet(struct fw_card *card, struct fw_packet *packet) struct driver_data *driver_data = packet->driver_data; int ret = -ENOENT; - tasklet_disable(&ctx->tasklet); + tasklet_disable_in_atomic(&ctx->tasklet); if (packet->ack != 0) goto out; @@ -3465,7 +3465,7 @@ static int ohci_flush_iso_completions(struct fw_iso_context *base) struct iso_context *ctx = container_of(base, struct iso_context, base); int ret = 0; - tasklet_disable(&ctx->context.tasklet); + tasklet_disable_in_atomic(&ctx->context.tasklet); if (!test_and_set_bit_lock(0, &ctx->flushing_completions)) { context_tasklet((unsigned long)&ctx->context); diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index df3f9bcab581c..709c65c0a8160 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -66,7 +66,7 @@ struct mm_struct efi_mm = { struct workqueue_struct *efi_rts_wq; -static bool disable_runtime; +static bool disable_runtime = IS_ENABLED(CONFIG_PREEMPT_RT); static int __init setup_noefi(char *arg) { disable_runtime = true; @@ -97,6 +97,9 @@ static int __init parse_efi_cmdline(char *str) if (parse_option_str(str, "noruntime")) disable_runtime = true; + if (parse_option_str(str, "runtime")) + disable_runtime = false; + if (parse_option_str(str, "nosoftreserve")) set_bit(EFI_MEM_NO_SOFT_RESERVE, &efi.flags); diff --git a/drivers/gpu/drm/i915/display/intel_sprite.c b/drivers/gpu/drm/i915/display/intel_sprite.c index 993543334a1ef..cc0dd8a1e4205 100644 --- a/drivers/gpu/drm/i915/display/intel_sprite.c +++ b/drivers/gpu/drm/i915/display/intel_sprite.c @@ -127,7 +127,8 @@ void intel_pipe_update_start(const struct intel_crtc_state *new_crtc_state) "PSR idle timed out 0x%x, atomic update may fail\n", psr_status); - local_irq_disable(); + if (!IS_ENABLED(CONFIG_PREEMPT_RT)) + local_irq_disable(); crtc->debug.min_vbl = min; crtc->debug.max_vbl = max; @@ -152,11 +153,13 @@ void intel_pipe_update_start(const struct intel_crtc_state *new_crtc_state) 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); @@ -189,7 +192,8 @@ void intel_pipe_update_start(const struct intel_crtc_state *new_crtc_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) @@ -268,7 +272,8 @@ void intel_pipe_update_end(struct intel_crtc_state *new_crtc_state) new_crtc_state->uapi.event = NULL; } - local_irq_enable(); + if (!IS_ENABLED(CONFIG_PREEMPT_RT)) + local_irq_enable(); /* Send VRR Push to terminate Vblank */ intel_vrr_send_push(new_crtc_state); diff --git a/drivers/gpu/drm/i915/gt/intel_engine_pm.c b/drivers/gpu/drm/i915/gt/intel_engine_pm.c index e67d09259dd0c..2a480b47dac26 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_pm.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_pm.c @@ -81,9 +81,10 @@ static int __engine_unpark(struct intel_wakeref *wf) static unsigned long __timeline_mark_lock(struct intel_context *ce) { - unsigned long flags; + unsigned long flags = 0; - local_irq_save(flags); + if (!force_irqthreads) + local_irq_save(flags); mutex_acquire(&ce->timeline->mutex.dep_map, 2, 0, _THIS_IP_); return flags; @@ -93,7 +94,8 @@ static void __timeline_mark_unlock(struct intel_context *ce, unsigned long flags) { mutex_release(&ce->timeline->mutex.dep_map, _THIS_IP_); - local_irq_restore(flags); + if (!force_irqthreads) + local_irq_restore(flags); } #else diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index 1a701367a7181..32db99bead7d2 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -888,6 +888,7 @@ static bool i915_get_crtc_scanoutpos(struct drm_crtc *_crtc, spin_lock_irqsave(&dev_priv->uncore.lock, irqflags); /* preempt_disable_rt() should go right here in PREEMPT_RT patchset. */ + preempt_disable_rt(); /* Get optional system timestamp before query. */ if (stime) @@ -952,6 +953,7 @@ static bool i915_get_crtc_scanoutpos(struct drm_crtc *_crtc, *etime = ktime_get(); /* preempt_enable_rt() should go right here in PREEMPT_RT patchset. */ + preempt_enable_rt(); spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags); diff --git a/drivers/gpu/drm/i915/i915_trace.h b/drivers/gpu/drm/i915/i915_trace.h index a4addcc649782..396b6598694d3 100644 --- a/drivers/gpu/drm/i915/i915_trace.h +++ b/drivers/gpu/drm/i915/i915_trace.h @@ -2,6 +2,10 @@ #if !defined(_I915_TRACE_H_) || defined(TRACE_HEADER_MULTI_READ) #define _I915_TRACE_H_ +#ifdef CONFIG_PREEMPT_RT +#define NOTRACE +#endif + #include #include #include @@ -778,7 +782,7 @@ DEFINE_EVENT(i915_request, i915_request_add, TP_ARGS(rq) ); -#if defined(CONFIG_DRM_I915_LOW_LEVEL_TRACEPOINTS) +#if defined(CONFIG_DRM_I915_LOW_LEVEL_TRACEPOINTS) && !defined(NOTRACE) DEFINE_EVENT(i915_request, i915_request_submit, TP_PROTO(struct i915_request *rq), TP_ARGS(rq) diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c index 652af7a134bd0..a2f5a4c0134f4 100644 --- a/drivers/gpu/drm/radeon/radeon_display.c +++ b/drivers/gpu/drm/radeon/radeon_display.c @@ -1813,6 +1813,7 @@ int radeon_get_crtc_scanoutpos(struct drm_device *dev, unsigned int pipe, struct radeon_device *rdev = dev->dev_private; /* preempt_disable_rt() should go right here in PREEMPT_RT patchset. */ + preempt_disable_rt(); /* Get optional system timestamp before query. */ if (stime) @@ -1905,6 +1906,7 @@ int radeon_get_crtc_scanoutpos(struct drm_device *dev, unsigned int pipe, *etime = ktime_get(); /* preempt_enable_rt() should go right here in PREEMPT_RT patchset. */ + preempt_enable_rt(); /* Decode into vertical and horizontal scanout position. */ *vpos = position & 0x1fff; diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h index 9416e09ebd58c..4a5767a155444 100644 --- a/drivers/hv/hyperv_vmbus.h +++ b/drivers/hv/hyperv_vmbus.h @@ -18,6 +18,7 @@ #include #include #include +#include #include "hv_trace.h" diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c index 10dce9f912168..10a36833ad69c 100644 --- a/drivers/hv/vmbus_drv.c +++ b/drivers/hv/vmbus_drv.c @@ -22,6 +22,7 @@ #include #include #include +#include #include #include @@ -1337,6 +1338,8 @@ static void vmbus_isr(void) void *page_addr = hv_cpu->synic_event_page; struct hv_message *msg; union hv_synic_event_flags *event; + struct pt_regs *regs = get_irq_regs(); + u64 ip = regs ? instruction_pointer(regs) : 0; bool handled = false; if (unlikely(page_addr == NULL)) @@ -1381,7 +1384,7 @@ static void vmbus_isr(void) tasklet_schedule(&hv_cpu->msg_dpc); } - add_interrupt_randomness(hv_get_vector(), 0); + add_interrupt_randomness(hv_get_vector(), 0, ip); } /* @@ -1391,6 +1394,7 @@ static void vmbus_isr(void) static void hv_kmsg_dump(struct kmsg_dumper *dumper, enum kmsg_dump_reason reason) { + struct kmsg_dump_iter iter; size_t bytes_written; phys_addr_t panic_pa; @@ -1404,7 +1408,8 @@ static void hv_kmsg_dump(struct kmsg_dumper *dumper, * Write dump contents to the page. No need to synchronize; panic should * be single-threaded. */ - kmsg_dump_get_buffer(dumper, false, hv_panic_page, HV_HYP_PAGE_SIZE, + kmsg_dump_rewind(&iter); + kmsg_dump_get_buffer(&iter, false, hv_panic_page, HV_HYP_PAGE_SIZE, &bytes_written); if (bytes_written) hyperv_report_panic_msg(panic_pa, bytes_written); diff --git a/drivers/leds/trigger/Kconfig b/drivers/leds/trigger/Kconfig index b77a01bd27f47..aa74e2a057980 100644 --- a/drivers/leds/trigger/Kconfig +++ b/drivers/leds/trigger/Kconfig @@ -64,6 +64,7 @@ config LEDS_TRIGGER_BACKLIGHT config LEDS_TRIGGER_CPU bool "LED CPU Trigger" + depends on !PREEMPT_RT help This allows LEDs to be controlled by active CPUs. This shows the active CPUs across an array of LEDs so you can see which diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 5d57a5bd171fa..86d6a676a5092 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -2216,8 +2216,9 @@ static void raid_run_ops(struct stripe_head *sh, unsigned long ops_request) struct raid5_percpu *percpu; unsigned long cpu; - cpu = get_cpu(); + cpu = get_cpu_light(); percpu = per_cpu_ptr(conf->percpu, cpu); + spin_lock(&percpu->lock); if (test_bit(STRIPE_OP_BIOFILL, &ops_request)) { ops_run_biofill(sh); overlap_clear++; @@ -2276,7 +2277,8 @@ static void raid_run_ops(struct stripe_head *sh, unsigned long ops_request) if (test_and_clear_bit(R5_Overlap, &dev->flags)) wake_up(&sh->raid_conf->wait_for_overlap); } - put_cpu(); + spin_unlock(&percpu->lock); + put_cpu_light(); } static void free_stripe(struct kmem_cache *sc, struct stripe_head *sh) @@ -7079,6 +7081,7 @@ static int raid456_cpu_up_prepare(unsigned int cpu, struct hlist_node *node) __func__, cpu); return -ENOMEM; } + spin_lock_init(&per_cpu_ptr(conf->percpu, cpu)->lock); return 0; } diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h index 5c05acf20e1f2..665fe138ab4f7 100644 --- a/drivers/md/raid5.h +++ b/drivers/md/raid5.h @@ -635,6 +635,7 @@ struct r5conf { int recovery_disabled; /* per cpu variables */ struct raid5_percpu { + spinlock_t lock; /* Protection for -RT */ struct page *spare_page; /* Used when checking P/Q in raid6 */ void *scribble; /* space for constructing buffer * lists and performing address diff --git a/drivers/mtd/mtdoops.c b/drivers/mtd/mtdoops.c index 774970bfcf859..862c4a8892346 100644 --- a/drivers/mtd/mtdoops.c +++ b/drivers/mtd/mtdoops.c @@ -52,6 +52,7 @@ static struct mtdoops_context { int nextcount; unsigned long *oops_page_used; + unsigned long oops_buf_busy; void *oops_buf; } oops_cxt; @@ -180,6 +181,9 @@ static void mtdoops_write(struct mtdoops_context *cxt, int panic) u32 *hdr; int ret; + if (test_and_set_bit(0, &cxt->oops_buf_busy)) + return; + /* Add mtdoops header to the buffer */ hdr = cxt->oops_buf; hdr[0] = cxt->nextcount; @@ -190,7 +194,7 @@ static void mtdoops_write(struct mtdoops_context *cxt, int panic) record_size, &retlen, cxt->oops_buf); if (ret == -EOPNOTSUPP) { printk(KERN_ERR "mtdoops: Cannot write from panic without panic_write\n"); - return; + goto out; } } else ret = mtd_write(mtd, cxt->nextpage * record_size, @@ -203,6 +207,8 @@ static void mtdoops_write(struct mtdoops_context *cxt, int panic) memset(cxt->oops_buf, 0xff, record_size); mtdoops_inc_counter(cxt); +out: + clear_bit(0, &cxt->oops_buf_busy); } static void mtdoops_workfunc_write(struct work_struct *work) @@ -271,13 +277,19 @@ static void mtdoops_do_dump(struct kmsg_dumper *dumper, { struct mtdoops_context *cxt = container_of(dumper, struct mtdoops_context, dump); + struct kmsg_dump_iter iter; /* Only dump oopses if dump_oops is set */ if (reason == KMSG_DUMP_OOPS && !dump_oops) return; - kmsg_dump_get_buffer(dumper, true, cxt->oops_buf + MTDOOPS_HEADER_SIZE, + kmsg_dump_rewind(&iter); + + if (test_and_set_bit(0, &cxt->oops_buf_busy)) + return; + kmsg_dump_get_buffer(&iter, true, cxt->oops_buf + MTDOOPS_HEADER_SIZE, record_size - MTDOOPS_HEADER_SIZE, NULL); + clear_bit(0, &cxt->oops_buf_busy); if (reason != KMSG_DUMP_OOPS) { /* Panics must be written immediately */ @@ -394,6 +406,7 @@ static int __init mtdoops_init(void) return -ENOMEM; } memset(cxt->oops_buf, 0xff, record_size); + cxt->oops_buf_busy = 0; INIT_WORK(&cxt->work_erase, mtdoops_workfunc_erase); INIT_WORK(&cxt->work_write, mtdoops_workfunc_write); diff --git a/drivers/net/ethernet/dlink/sundance.c b/drivers/net/ethernet/dlink/sundance.c index e3a8858915b37..df0eab479d512 100644 --- a/drivers/net/ethernet/dlink/sundance.c +++ b/drivers/net/ethernet/dlink/sundance.c @@ -963,7 +963,7 @@ static void tx_timeout(struct net_device *dev, unsigned int txqueue) unsigned long flag; netif_stop_queue(dev); - tasklet_disable(&np->tx_tasklet); + tasklet_disable_in_atomic(&np->tx_tasklet); iowrite16(0, ioaddr + IntrEnable); printk(KERN_WARNING "%s: Transmit timed out, TxStatus %2.2x " "TxFrameId %2.2x," diff --git a/drivers/net/ethernet/jme.c b/drivers/net/ethernet/jme.c index e9efe074edc11..f1b9284e0bea8 100644 --- a/drivers/net/ethernet/jme.c +++ b/drivers/net/ethernet/jme.c @@ -1265,9 +1265,9 @@ jme_stop_shutdown_timer(struct jme_adapter *jme) jwrite32f(jme, JME_APMC, apmc); } -static void jme_link_change_tasklet(struct tasklet_struct *t) +static void jme_link_change_work(struct work_struct *work) { - struct jme_adapter *jme = from_tasklet(jme, t, linkch_task); + struct jme_adapter *jme = container_of(work, struct jme_adapter, linkch_task); struct net_device *netdev = jme->dev; int rc; @@ -1510,7 +1510,7 @@ jme_intr_msi(struct jme_adapter *jme, u32 intrstat) * all other events are ignored */ jwrite32(jme, JME_IEVE, intrstat); - tasklet_schedule(&jme->linkch_task); + schedule_work(&jme->linkch_task); goto out_reenable; } @@ -1832,7 +1832,6 @@ jme_open(struct net_device *netdev) jme_clear_pm_disable_wol(jme); JME_NAPI_ENABLE(jme); - tasklet_setup(&jme->linkch_task, jme_link_change_tasklet); tasklet_setup(&jme->txclean_task, jme_tx_clean_tasklet); tasklet_setup(&jme->rxclean_task, jme_rx_clean_tasklet); tasklet_setup(&jme->rxempty_task, jme_rx_empty_tasklet); @@ -1920,7 +1919,7 @@ jme_close(struct net_device *netdev) JME_NAPI_DISABLE(jme); - tasklet_kill(&jme->linkch_task); + cancel_work_sync(&jme->linkch_task); tasklet_kill(&jme->txclean_task); tasklet_kill(&jme->rxclean_task); tasklet_kill(&jme->rxempty_task); @@ -3035,6 +3034,7 @@ jme_init_one(struct pci_dev *pdev, atomic_set(&jme->rx_empty, 1); tasklet_setup(&jme->pcc_task, jme_pcc_tasklet); + INIT_WORK(&jme->linkch_task, jme_link_change_work); jme->dpi.cur = PCC_P1; jme->reg_ghc = 0; diff --git a/drivers/net/ethernet/jme.h b/drivers/net/ethernet/jme.h index a2c3b00d939d0..2af76329b4a27 100644 --- a/drivers/net/ethernet/jme.h +++ b/drivers/net/ethernet/jme.h @@ -411,7 +411,7 @@ struct jme_adapter { struct tasklet_struct rxempty_task; struct tasklet_struct rxclean_task; struct tasklet_struct txclean_task; - struct tasklet_struct linkch_task; + struct work_struct linkch_task; struct tasklet_struct pcc_task; unsigned long flags; u32 reg_txcs; diff --git a/drivers/net/wireless/ath/ath9k/beacon.c b/drivers/net/wireless/ath/ath9k/beacon.c index 71e2ada86793f..72e2e71aac0e6 100644 --- a/drivers/net/wireless/ath/ath9k/beacon.c +++ b/drivers/net/wireless/ath/ath9k/beacon.c @@ -251,7 +251,7 @@ void ath9k_beacon_ensure_primary_slot(struct ath_softc *sc) int first_slot = ATH_BCBUF; int slot; - tasklet_disable(&sc->bcon_tasklet); + tasklet_disable_in_atomic(&sc->bcon_tasklet); /* Find first taken slot. */ for (slot = 0; slot < ATH_BCBUF; slot++) { diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c index 27a17a1e4a7c3..a313708bcf754 100644 --- a/drivers/pci/controller/pci-hyperv.c +++ b/drivers/pci/controller/pci-hyperv.c @@ -1458,7 +1458,7 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) * Prevents hv_pci_onchannelcallback() from running concurrently * in the tasklet. */ - tasklet_disable(&channel->callback_event); + tasklet_disable_in_atomic(&channel->callback_event); /* * Since this function is called with IRQ locks held, can't diff --git a/drivers/scsi/fcoe/fcoe.c b/drivers/scsi/fcoe/fcoe.c index 03bf49adaafe6..52e0a2486b43b 100644 --- a/drivers/scsi/fcoe/fcoe.c +++ b/drivers/scsi/fcoe/fcoe.c @@ -1452,11 +1452,11 @@ static int fcoe_rcv(struct sk_buff *skb, struct net_device *netdev, static int fcoe_alloc_paged_crc_eof(struct sk_buff *skb, int tlen) { struct fcoe_percpu_s *fps; - int rc; + int rc, cpu = get_cpu_light(); - fps = &get_cpu_var(fcoe_percpu); + fps = &per_cpu(fcoe_percpu, cpu); rc = fcoe_get_paged_crc_eof(skb, tlen, fps); - put_cpu_var(fcoe_percpu); + put_cpu_light(); return rc; } @@ -1641,11 +1641,11 @@ static inline int fcoe_filter_frames(struct fc_lport *lport, return 0; } - stats = per_cpu_ptr(lport->stats, get_cpu()); + stats = per_cpu_ptr(lport->stats, get_cpu_light()); stats->InvalidCRCCount++; if (stats->InvalidCRCCount < 5) printk(KERN_WARNING "fcoe: dropping frame with CRC error\n"); - put_cpu(); + put_cpu_light(); return -EINVAL; } @@ -1686,7 +1686,7 @@ static void fcoe_recv_frame(struct sk_buff *skb) */ hp = (struct fcoe_hdr *) skb_network_header(skb); - stats = per_cpu_ptr(lport->stats, get_cpu()); + stats = per_cpu_ptr(lport->stats, get_cpu_light()); if (unlikely(FC_FCOE_DECAPS_VER(hp) != FC_FCOE_VER)) { if (stats->ErrorFrames < 5) printk(KERN_WARNING "fcoe: FCoE version " @@ -1718,13 +1718,13 @@ static void fcoe_recv_frame(struct sk_buff *skb) goto drop; if (!fcoe_filter_frames(lport, fp)) { - put_cpu(); + put_cpu_light(); fc_exch_recv(lport, fp); return; } drop: stats->ErrorFrames++; - put_cpu(); + put_cpu_light(); kfree_skb(skb); } diff --git a/drivers/scsi/fcoe/fcoe_ctlr.c b/drivers/scsi/fcoe/fcoe_ctlr.c index 5ea426effa609..0d6b9acc7cf81 100644 --- a/drivers/scsi/fcoe/fcoe_ctlr.c +++ b/drivers/scsi/fcoe/fcoe_ctlr.c @@ -828,7 +828,7 @@ static unsigned long fcoe_ctlr_age_fcfs(struct fcoe_ctlr *fip) INIT_LIST_HEAD(&del_list); - stats = per_cpu_ptr(fip->lp->stats, get_cpu()); + stats = per_cpu_ptr(fip->lp->stats, get_cpu_light()); list_for_each_entry_safe(fcf, next, &fip->fcfs, list) { deadline = fcf->time + fcf->fka_period + fcf->fka_period / 2; @@ -864,7 +864,7 @@ static unsigned long fcoe_ctlr_age_fcfs(struct fcoe_ctlr *fip) sel_time = fcf->time; } } - put_cpu(); + put_cpu_light(); list_for_each_entry_safe(fcf, next, &del_list, list) { /* Removes fcf from current list */ diff --git a/drivers/scsi/libfc/fc_exch.c b/drivers/scsi/libfc/fc_exch.c index 841000445b9a1..26d661ddc9509 100644 --- a/drivers/scsi/libfc/fc_exch.c +++ b/drivers/scsi/libfc/fc_exch.c @@ -825,10 +825,10 @@ static struct fc_exch *fc_exch_em_alloc(struct fc_lport *lport, } memset(ep, 0, sizeof(*ep)); - cpu = get_cpu(); + cpu = get_cpu_light(); pool = per_cpu_ptr(mp->pool, cpu); spin_lock_bh(&pool->lock); - put_cpu(); + put_cpu_light(); /* peek cache of free slot */ if (pool->left != FC_XID_UNKNOWN) { diff --git a/drivers/tty/serial/8250/8250.h b/drivers/tty/serial/8250/8250.h index 52bb21205bb68..5cbcaafbb4aa2 100644 --- a/drivers/tty/serial/8250/8250.h +++ b/drivers/tty/serial/8250/8250.h @@ -130,12 +130,55 @@ static inline void serial_dl_write(struct uart_8250_port *up, int value) up->dl_write(up, value); } +static inline void serial8250_set_IER(struct uart_8250_port *up, + unsigned char ier) +{ + struct uart_port *port = &up->port; + unsigned int flags; + bool is_console; + + is_console = uart_console(port); + + if (is_console) + console_atomic_lock(&flags); + + serial_out(up, UART_IER, ier); + + if (is_console) + console_atomic_unlock(flags); +} + +static inline unsigned char serial8250_clear_IER(struct uart_8250_port *up) +{ + struct uart_port *port = &up->port; + unsigned int clearval = 0; + unsigned int prior; + unsigned int flags; + bool is_console; + + is_console = uart_console(port); + + if (up->capabilities & UART_CAP_UUE) + clearval = UART_IER_UUE; + + if (is_console) + console_atomic_lock(&flags); + + prior = serial_port_in(port, UART_IER); + serial_port_out(port, UART_IER, clearval); + + if (is_console) + console_atomic_unlock(flags); + + return prior; +} + static inline bool serial8250_set_THRI(struct uart_8250_port *up) { if (up->ier & UART_IER_THRI) return false; up->ier |= UART_IER_THRI; - serial_out(up, UART_IER, up->ier); + serial8250_set_IER(up, up->ier); return true; } @@ -144,7 +187,7 @@ static inline bool serial8250_clear_THRI(struct uart_8250_port *up) if (!(up->ier & UART_IER_THRI)) return false; up->ier &= ~UART_IER_THRI; - serial_out(up, UART_IER, up->ier); + serial8250_set_IER(up, up->ier); return true; } diff --git a/drivers/tty/serial/8250/8250_core.c b/drivers/tty/serial/8250/8250_core.c index cae61d1ebec5a..47dd230562719 100644 --- a/drivers/tty/serial/8250/8250_core.c +++ b/drivers/tty/serial/8250/8250_core.c @@ -274,10 +274,8 @@ static void serial8250_backup_timeout(struct timer_list *t) * Must disable interrupts or else we risk racing with the interrupt * based handler. */ - if (up->port.irq) { - ier = serial_in(up, UART_IER); - serial_out(up, UART_IER, 0); - } + if (up->port.irq) + ier = serial8250_clear_IER(up); iir = serial_in(up, UART_IIR); @@ -300,7 +298,7 @@ static void serial8250_backup_timeout(struct timer_list *t) serial8250_tx_chars(up); if (up->port.irq) - serial_out(up, UART_IER, ier); + serial8250_set_IER(up, ier); spin_unlock_irqrestore(&up->port.lock, flags); @@ -578,6 +576,14 @@ serial8250_register_ports(struct uart_driver *drv, struct device *dev) #ifdef CONFIG_SERIAL_8250_CONSOLE +static void univ8250_console_write_atomic(struct console *co, const char *s, + unsigned int count) +{ + struct uart_8250_port *up = &serial8250_ports[co->index]; + + serial8250_console_write_atomic(up, s, count); +} + static void univ8250_console_write(struct console *co, const char *s, unsigned int count) { @@ -671,6 +677,7 @@ static int univ8250_console_match(struct console *co, char *name, int idx, static struct console univ8250_console = { .name = "ttyS", + .write_atomic = univ8250_console_write_atomic, .write = univ8250_console_write, .device = uart_console_device, .setup = univ8250_console_setup, diff --git a/drivers/tty/serial/8250/8250_fsl.c b/drivers/tty/serial/8250/8250_fsl.c index fbcc90c31ca11..b33cb454ce037 100644 --- a/drivers/tty/serial/8250/8250_fsl.c +++ b/drivers/tty/serial/8250/8250_fsl.c @@ -60,9 +60,18 @@ int fsl8250_handle_irq(struct uart_port *port) /* Stop processing interrupts on input overrun */ if ((orig_lsr & UART_LSR_OE) && (up->overrun_backoff_time_ms > 0)) { + unsigned int ca_flags; unsigned long delay; + bool is_console; + is_console = uart_console(port); + + if (is_console) + console_atomic_lock(&ca_flags); up->ier = port->serial_in(port, UART_IER); + if (is_console) + console_atomic_unlock(ca_flags); + if (up->ier & (UART_IER_RLSI | UART_IER_RDI)) { port->ops->stop_rx(port); } else { diff --git a/drivers/tty/serial/8250/8250_ingenic.c b/drivers/tty/serial/8250/8250_ingenic.c index 988bf6bcce42d..bcd26d6725395 100644 --- a/drivers/tty/serial/8250/8250_ingenic.c +++ b/drivers/tty/serial/8250/8250_ingenic.c @@ -146,6 +146,8 @@ OF_EARLYCON_DECLARE(x1000_uart, "ingenic,x1000-uart", static void ingenic_uart_serial_out(struct uart_port *p, int offset, int value) { + unsigned int flags; + bool is_console; int ier; switch (offset) { @@ -167,7 +169,12 @@ static void ingenic_uart_serial_out(struct uart_port *p, int offset, int value) * If we have enabled modem status IRQs we should enable * modem mode. */ + is_console = uart_console(p); + if (is_console) + console_atomic_lock(&flags); ier = p->serial_in(p, UART_IER); + if (is_console) + console_atomic_unlock(flags); if (ier & UART_IER_MSI) value |= UART_MCR_MDCE | UART_MCR_FCM; diff --git a/drivers/tty/serial/8250/8250_mtk.c b/drivers/tty/serial/8250/8250_mtk.c index f7d3023f860f0..8133713dcf5eb 100644 --- a/drivers/tty/serial/8250/8250_mtk.c +++ b/drivers/tty/serial/8250/8250_mtk.c @@ -213,12 +213,37 @@ static void mtk8250_shutdown(struct uart_port *port) static void mtk8250_disable_intrs(struct uart_8250_port *up, int mask) { - serial_out(up, UART_IER, serial_in(up, UART_IER) & (~mask)); + struct uart_port *port = &up->port; + unsigned int flags; + unsigned int ier; + bool is_console; + + is_console = uart_console(port); + + if (is_console) + console_atomic_lock(&flags); + + ier = serial_in(up, UART_IER); + serial_out(up, UART_IER, ier & (~mask)); + + if (is_console) + console_atomic_unlock(flags); } static void mtk8250_enable_intrs(struct uart_8250_port *up, int mask) { - serial_out(up, UART_IER, serial_in(up, UART_IER) | mask); + struct uart_port *port = &up->port; + unsigned int flags; + unsigned int ier; + + if (uart_console(port)) + console_atomic_lock(&flags); + + ier = serial_in(up, UART_IER); + serial_out(up, UART_IER, ier | mask); + + if (uart_console(port)) + console_atomic_unlock(flags); } static void mtk8250_set_flow_ctrl(struct uart_8250_port *up, int mode) diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c index b0af13074cd36..b05f8c34b291a 100644 --- a/drivers/tty/serial/8250/8250_port.c +++ b/drivers/tty/serial/8250/8250_port.c @@ -757,7 +757,7 @@ static void serial8250_set_sleep(struct uart_8250_port *p, int sleep) serial_out(p, UART_EFR, UART_EFR_ECB); serial_out(p, UART_LCR, 0); } - serial_out(p, UART_IER, sleep ? UART_IERX_SLEEP : 0); + serial8250_set_IER(p, sleep ? UART_IERX_SLEEP : 0); if (p->capabilities & UART_CAP_EFR) { serial_out(p, UART_LCR, UART_LCR_CONF_MODE_B); serial_out(p, UART_EFR, efr); @@ -1429,7 +1429,7 @@ static void serial8250_stop_rx(struct uart_port *port) up->ier &= ~(UART_IER_RLSI | UART_IER_RDI); up->port.read_status_mask &= ~UART_LSR_DR; - serial_port_out(port, UART_IER, up->ier); + serial8250_set_IER(up, up->ier); serial8250_rpm_put(up); } @@ -1459,7 +1459,7 @@ void serial8250_em485_stop_tx(struct uart_8250_port *p) serial8250_clear_and_reinit_fifos(p); p->ier |= UART_IER_RLSI | UART_IER_RDI; - serial_port_out(&p->port, UART_IER, p->ier); + serial8250_set_IER(p, p->ier); } } EXPORT_SYMBOL_GPL(serial8250_em485_stop_tx); @@ -1687,7 +1687,7 @@ static void serial8250_disable_ms(struct uart_port *port) mctrl_gpio_disable_ms(up->gpios); up->ier &= ~UART_IER_MSI; - serial_port_out(port, UART_IER, up->ier); + serial8250_set_IER(up, up->ier); } static void serial8250_enable_ms(struct uart_port *port) @@ -1703,7 +1703,7 @@ static void serial8250_enable_ms(struct uart_port *port) up->ier |= UART_IER_MSI; serial8250_rpm_get(up); - serial_port_out(port, UART_IER, up->ier); + serial8250_set_IER(up, up->ier); serial8250_rpm_put(up); } @@ -2118,14 +2118,7 @@ static void serial8250_put_poll_char(struct uart_port *port, struct uart_8250_port *up = up_to_u8250p(port); serial8250_rpm_get(up); - /* - * First save the IER then disable the interrupts - */ - ier = serial_port_in(port, UART_IER); - if (up->capabilities & UART_CAP_UUE) - serial_port_out(port, UART_IER, UART_IER_UUE); - else - serial_port_out(port, UART_IER, 0); + ier = serial8250_clear_IER(up); wait_for_xmitr(up, BOTH_EMPTY); /* @@ -2138,7 +2131,7 @@ static void serial8250_put_poll_char(struct uart_port *port, * and restore the IER */ wait_for_xmitr(up, BOTH_EMPTY); - serial_port_out(port, UART_IER, ier); + serial8250_set_IER(up, ier); serial8250_rpm_put(up); } @@ -2441,7 +2434,7 @@ void serial8250_do_shutdown(struct uart_port *port) */ spin_lock_irqsave(&port->lock, flags); up->ier = 0; - serial_port_out(port, UART_IER, 0); + serial8250_set_IER(up, 0); spin_unlock_irqrestore(&port->lock, flags); synchronize_irq(port->irq); @@ -2771,7 +2764,7 @@ serial8250_do_set_termios(struct uart_port *port, struct ktermios *termios, if (up->capabilities & UART_CAP_RTOIE) up->ier |= UART_IER_RTOIE; - serial_port_out(port, UART_IER, up->ier); + serial8250_set_IER(up, up->ier); if (up->capabilities & UART_CAP_EFR) { unsigned char efr = 0; @@ -3237,7 +3230,7 @@ EXPORT_SYMBOL_GPL(serial8250_set_defaults); #ifdef CONFIG_SERIAL_8250_CONSOLE -static void serial8250_console_putchar(struct uart_port *port, int ch) +static void serial8250_console_putchar_locked(struct uart_port *port, int ch) { struct uart_8250_port *up = up_to_u8250p(port); @@ -3245,6 +3238,18 @@ static void serial8250_console_putchar(struct uart_port *port, int ch) serial_port_out(port, UART_TX, ch); } +static void serial8250_console_putchar(struct uart_port *port, int ch) +{ + struct uart_8250_port *up = up_to_u8250p(port); + unsigned int flags; + + wait_for_xmitr(up, UART_LSR_THRE); + + console_atomic_lock(&flags); + serial8250_console_putchar_locked(port, ch); + console_atomic_unlock(flags); +} + /* * Restore serial console when h/w power-off detected */ @@ -3266,6 +3271,32 @@ static void serial8250_console_restore(struct uart_8250_port *up) serial8250_out_MCR(up, UART_MCR_DTR | UART_MCR_RTS); } +void serial8250_console_write_atomic(struct uart_8250_port *up, + const char *s, unsigned int count) +{ + struct uart_port *port = &up->port; + unsigned int flags; + unsigned int ier; + + console_atomic_lock(&flags); + + touch_nmi_watchdog(); + + ier = serial8250_clear_IER(up); + + if (atomic_fetch_inc(&up->console_printing)) { + uart_console_write(port, "\n", 1, + serial8250_console_putchar_locked); + } + uart_console_write(port, s, count, serial8250_console_putchar_locked); + atomic_dec(&up->console_printing); + + wait_for_xmitr(up, BOTH_EMPTY); + serial8250_set_IER(up, ier); + + console_atomic_unlock(flags); +} + /* * Print a string to the serial port trying not to disturb * any possible real use of the port... @@ -3282,24 +3313,12 @@ void serial8250_console_write(struct uart_8250_port *up, const char *s, struct uart_port *port = &up->port; unsigned long flags; unsigned int ier; - int locked = 1; touch_nmi_watchdog(); - if (oops_in_progress) - locked = spin_trylock_irqsave(&port->lock, flags); - else - spin_lock_irqsave(&port->lock, flags); + spin_lock_irqsave(&port->lock, flags); - /* - * First save the IER then disable the interrupts - */ - ier = serial_port_in(port, UART_IER); - - if (up->capabilities & UART_CAP_UUE) - serial_port_out(port, UART_IER, UART_IER_UUE); - else - serial_port_out(port, UART_IER, 0); + ier = 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))) { @@ -3313,7 +3332,9 @@ void serial8250_console_write(struct uart_8250_port *up, const char *s, mdelay(port->rs485.delay_rts_before_send); } + atomic_inc(&up->console_printing); uart_console_write(port, s, count, serial8250_console_putchar); + atomic_dec(&up->console_printing); /* * Finally, wait for transmitter to become empty @@ -3326,8 +3347,7 @@ void serial8250_console_write(struct uart_8250_port *up, const char *s, if (em485->tx_stopped) up->rs485_stop_tx(up); } - - serial_port_out(port, UART_IER, ier); + serial8250_set_IER(up, ier); /* * The receive handling will happen properly because the @@ -3339,8 +3359,7 @@ void serial8250_console_write(struct uart_8250_port *up, const char *s, if (up->msr_saved_flags) serial8250_modem_status(up); - if (locked) - spin_unlock_irqrestore(&port->lock, flags); + spin_unlock_irqrestore(&port->lock, flags); } static unsigned int probe_baud(struct uart_port *port) @@ -3360,6 +3379,7 @@ 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'; @@ -3369,6 +3389,8 @@ int serial8250_console_setup(struct uart_port *port, char *options, bool probe) if (!port->iobase && !port->membase) return -ENODEV; + atomic_set(&up->console_printing, 0); + if (options) uart_parse_options(options, &baud, &parity, &bits, &flow); else if (probe) diff --git a/drivers/tty/serial/amba-pl011.c b/drivers/tty/serial/amba-pl011.c index 4ead0c9048a89..1bbc56263c2d8 100644 --- a/drivers/tty/serial/amba-pl011.c +++ b/drivers/tty/serial/amba-pl011.c @@ -2201,18 +2201,24 @@ pl011_console_write(struct console *co, const char *s, unsigned int count) { struct uart_amba_port *uap = amba_ports[co->index]; unsigned int old_cr = 0, new_cr; - unsigned long flags; + unsigned long flags = 0; int locked = 1; clk_enable(uap->clk); - local_irq_save(flags); + /* + * local_irq_save(flags); + * + * This local_irq_save() is nonsense. If we come in via sysrq + * handling then interrupts are already disabled. Aside of + * that the port.sysrq check is racy on SMP regardless. + */ if (uap->port.sysrq) locked = 0; else if (oops_in_progress) - locked = spin_trylock(&uap->port.lock); + locked = spin_trylock_irqsave(&uap->port.lock, flags); else - spin_lock(&uap->port.lock); + spin_lock_irqsave(&uap->port.lock, flags); /* * First save the CR then disable the interrupts @@ -2238,8 +2244,7 @@ pl011_console_write(struct console *co, const char *s, unsigned int count) pl011_write(old_cr, uap, REG_CR); if (locked) - spin_unlock(&uap->port.lock); - local_irq_restore(flags); + spin_unlock_irqrestore(&uap->port.lock, flags); clk_disable(uap->clk); } diff --git a/drivers/tty/serial/omap-serial.c b/drivers/tty/serial/omap-serial.c index 76b94d0ff5865..80371598efea4 100644 --- a/drivers/tty/serial/omap-serial.c +++ b/drivers/tty/serial/omap-serial.c @@ -1301,13 +1301,10 @@ serial_omap_console_write(struct console *co, const char *s, pm_runtime_get_sync(up->dev); - local_irq_save(flags); - if (up->port.sysrq) - locked = 0; - else if (oops_in_progress) - locked = spin_trylock(&up->port.lock); + if (up->port.sysrq || oops_in_progress) + locked = spin_trylock_irqsave(&up->port.lock, flags); else - spin_lock(&up->port.lock); + spin_lock_irqsave(&up->port.lock, flags); /* * First save the IER then disable the interrupts @@ -1336,8 +1333,7 @@ serial_omap_console_write(struct console *co, const char *s, pm_runtime_mark_last_busy(up->dev); pm_runtime_put_autosuspend(up->dev); if (locked) - spin_unlock(&up->port.lock); - local_irq_restore(flags); + spin_unlock_irqrestore(&up->port.lock, flags); } static int __init diff --git a/drivers/usb/usbip/usbip_common.h b/drivers/usb/usbip/usbip_common.h index d60ce17d3dd2a..a7dd6c66aee55 100644 --- a/drivers/usb/usbip/usbip_common.h +++ b/drivers/usb/usbip/usbip_common.h @@ -18,6 +18,7 @@ #include #include #include +#include #include #undef pr_fmt diff --git a/fs/afs/dir_silly.c b/fs/afs/dir_silly.c index 04f75a44f2432..60cbce1995a59 100644 --- a/fs/afs/dir_silly.c +++ b/fs/afs/dir_silly.c @@ -236,7 +236,7 @@ int afs_silly_iput(struct dentry *dentry, struct inode *inode) struct dentry *alias; int ret; - DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq); + DECLARE_SWAIT_QUEUE_HEAD_ONSTACK(wq); _enter("%p{%pd},%llx", dentry, dentry, vnode->fid.vnode); diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c index 80bf4c6f4c7bc..a975cfed14f5a 100644 --- a/fs/cifs/readdir.c +++ b/fs/cifs/readdir.c @@ -82,7 +82,7 @@ cifs_prime_dcache(struct dentry *parent, struct qstr *name, struct inode *inode; struct super_block *sb = parent->d_sb; struct cifs_sb_info *cifs_sb = CIFS_SB(sb); - DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq); + DECLARE_SWAIT_QUEUE_HEAD_ONSTACK(wq); cifs_dbg(FYI, "%s: for %s\n", __func__, name->name); diff --git a/fs/dcache.c b/fs/dcache.c index 7d24ff7eb2068..f651134ec182b 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -2536,9 +2536,10 @@ EXPORT_SYMBOL(d_rehash); static inline unsigned start_dir_add(struct inode *dir) { + preempt_disable_rt(); for (;;) { - unsigned n = dir->i_dir_seq; - if (!(n & 1) && cmpxchg(&dir->i_dir_seq, n, n + 1) == n) + unsigned n = dir->__i_dir_seq; + if (!(n & 1) && cmpxchg(&dir->__i_dir_seq, n, n + 1) == n) return n; cpu_relax(); } @@ -2546,26 +2547,30 @@ static inline unsigned start_dir_add(struct inode *dir) static inline void end_dir_add(struct inode *dir, unsigned n) { - smp_store_release(&dir->i_dir_seq, n + 2); + smp_store_release(&dir->__i_dir_seq, n + 2); + preempt_enable_rt(); } static void d_wait_lookup(struct dentry *dentry) { - if (d_in_lookup(dentry)) { - DECLARE_WAITQUEUE(wait, current); - add_wait_queue(dentry->d_wait, &wait); - do { - set_current_state(TASK_UNINTERRUPTIBLE); - spin_unlock(&dentry->d_lock); - schedule(); - spin_lock(&dentry->d_lock); - } while (d_in_lookup(dentry)); - } + struct swait_queue __wait; + + if (!d_in_lookup(dentry)) + return; + + INIT_LIST_HEAD(&__wait.task_list); + do { + prepare_to_swait_exclusive(dentry->d_wait, &__wait, TASK_UNINTERRUPTIBLE); + spin_unlock(&dentry->d_lock); + schedule(); + spin_lock(&dentry->d_lock); + } while (d_in_lookup(dentry)); + finish_swait(dentry->d_wait, &__wait); } struct dentry *d_alloc_parallel(struct dentry *parent, const struct qstr *name, - wait_queue_head_t *wq) + struct swait_queue_head *wq) { unsigned int hash = name->hash; struct hlist_bl_head *b = in_lookup_hash(parent, hash); @@ -2579,7 +2584,7 @@ struct dentry *d_alloc_parallel(struct dentry *parent, retry: rcu_read_lock(); - seq = smp_load_acquire(&parent->d_inode->i_dir_seq); + seq = smp_load_acquire(&parent->d_inode->__i_dir_seq); r_seq = read_seqbegin(&rename_lock); dentry = __d_lookup_rcu(parent, name, &d_seq); if (unlikely(dentry)) { @@ -2607,7 +2612,7 @@ struct dentry *d_alloc_parallel(struct dentry *parent, } hlist_bl_lock(b); - if (unlikely(READ_ONCE(parent->d_inode->i_dir_seq) != seq)) { + if (unlikely(READ_ONCE(parent->d_inode->__i_dir_seq) != seq)) { hlist_bl_unlock(b); rcu_read_unlock(); goto retry; @@ -2680,7 +2685,7 @@ void __d_lookup_done(struct dentry *dentry) hlist_bl_lock(b); dentry->d_flags &= ~DCACHE_PAR_LOOKUP; __hlist_bl_del(&dentry->d_u.d_in_lookup_hash); - wake_up_all(dentry->d_wait); + swake_up_all(dentry->d_wait); dentry->d_wait = NULL; hlist_bl_unlock(b); INIT_HLIST_NODE(&dentry->d_u.d_alias); diff --git a/fs/fuse/readdir.c b/fs/fuse/readdir.c index 3441ffa740f3d..2fcae5cfd2725 100644 --- a/fs/fuse/readdir.c +++ b/fs/fuse/readdir.c @@ -158,7 +158,7 @@ static int fuse_direntplus_link(struct file *file, struct inode *dir = d_inode(parent); struct fuse_conn *fc; struct inode *inode; - DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq); + DECLARE_SWAIT_QUEUE_HEAD_ONSTACK(wq); if (!o->nodeid) { /* diff --git a/fs/inode.c b/fs/inode.c index a047ab306f9a8..814efb88514bb 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -158,7 +158,7 @@ int inode_init_always(struct super_block *sb, struct inode *inode) inode->i_pipe = NULL; inode->i_cdev = NULL; inode->i_link = NULL; - inode->i_dir_seq = 0; + inode->__i_dir_seq = 0; inode->i_rdev = 0; inode->dirtied_when = 0; diff --git a/fs/namei.c b/fs/namei.c index 216f16e74351f..06ffd9490a345 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -1602,7 +1602,7 @@ static struct dentry *__lookup_slow(const struct qstr *name, { struct dentry *dentry, *old; struct inode *inode = dir->d_inode; - DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq); + DECLARE_SWAIT_QUEUE_HEAD_ONSTACK(wq); /* Don't go there if it's already dead */ if (unlikely(IS_DEADDIR(inode))) @@ -3131,7 +3131,7 @@ static struct dentry *lookup_open(struct nameidata *nd, struct file *file, struct dentry *dentry; int error, create_error = 0; umode_t mode = op->mode; - DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq); + DECLARE_SWAIT_QUEUE_HEAD_ONSTACK(wq); if (unlikely(IS_DEADDIR(dir_inode))) return ERR_PTR(-ENOENT); diff --git a/fs/namespace.c b/fs/namespace.c index 56bb5a5fdc0d0..81aafb06f868a 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include #include @@ -342,8 +343,11 @@ int __mnt_want_write(struct vfsmount *m) * incremented count after it has set MNT_WRITE_HOLD. */ smp_mb(); - while (READ_ONCE(mnt->mnt.mnt_flags) & MNT_WRITE_HOLD) - cpu_relax(); + while (READ_ONCE(mnt->mnt.mnt_flags) & MNT_WRITE_HOLD) { + preempt_enable(); + cpu_chill(); + preempt_disable(); + } /* * After the slowpath clears MNT_WRITE_HOLD, mnt_is_readonly will * be set to match its requirements. So we must not load that until diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index fc4f490f2d785..8f00a87b7ae2e 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -636,7 +636,7 @@ void nfs_prime_dcache(struct dentry *parent, struct nfs_entry *entry, unsigned long dir_verifier) { struct qstr filename = QSTR_INIT(entry->name, entry->len); - DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq); + DECLARE_SWAIT_QUEUE_HEAD_ONSTACK(wq); struct dentry *dentry; struct dentry *alias; struct inode *inode; @@ -1868,7 +1868,7 @@ int nfs_atomic_open(struct inode *dir, struct dentry *dentry, struct file *file, unsigned open_flags, umode_t mode) { - DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq); + DECLARE_SWAIT_QUEUE_HEAD_ONSTACK(wq); struct nfs_open_context *ctx; struct dentry *res; struct iattr attr = { .ia_valid = ATTR_OPEN }; diff --git a/fs/nfs/unlink.c b/fs/nfs/unlink.c index 5fa11e1aca4c2..984f26eb888c1 100644 --- a/fs/nfs/unlink.c +++ b/fs/nfs/unlink.c @@ -13,7 +13,7 @@ #include #include #include -#include +#include #include #include @@ -180,7 +180,7 @@ nfs_async_unlink(struct dentry *dentry, const struct qstr *name) data->cred = get_current_cred(); data->res.dir_attr = &data->dir_attr; - init_waitqueue_head(&data->wq); + init_swait_queue_head(&data->wq); status = -EBUSY; spin_lock(&dentry->d_lock); diff --git a/fs/proc/base.c b/fs/proc/base.c index 3851bfcdba56e..b7dd826e825f7 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -95,6 +95,7 @@ #include #include #include +#include #include #include "internal.h" #include "fd.h" @@ -2037,7 +2038,7 @@ bool proc_fill_cache(struct file *file, struct dir_context *ctx, child = d_hash_and_lookup(dir, &qname); if (!child) { - DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq); + DECLARE_SWAIT_QUEUE_HEAD_ONSTACK(wq); child = d_alloc_parallel(dir, &qname, &wq); if (IS_ERR(child)) goto end_instantiate; diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index 984e42f8cb112..2bc8e2409308b 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -683,7 +683,7 @@ static bool proc_sys_fill_cache(struct file *file, child = d_lookup(dir, &qname); if (!child) { - DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq); + DECLARE_SWAIT_QUEUE_HEAD_ONSTACK(wq); child = d_alloc_parallel(dir, &qname, &wq); if (IS_ERR(child)) return false; diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c index d963ae7902f92..b9614db48b1de 100644 --- a/fs/pstore/platform.c +++ b/fs/pstore/platform.c @@ -385,6 +385,7 @@ void pstore_record_init(struct pstore_record *record, static void pstore_dump(struct kmsg_dumper *dumper, enum kmsg_dump_reason reason) { + struct kmsg_dump_iter iter; unsigned long total = 0; const char *why; unsigned int part = 1; @@ -405,6 +406,8 @@ static void pstore_dump(struct kmsg_dumper *dumper, } } + kmsg_dump_rewind(&iter); + oopscount++; while (total < kmsg_bytes) { char *dst; @@ -435,7 +438,7 @@ static void pstore_dump(struct kmsg_dumper *dumper, dst_size -= header_size; /* Write dump contents. */ - if (!kmsg_dump_get_buffer(dumper, true, dst + header_size, + if (!kmsg_dump_get_buffer(&iter, true, dst + header_size, dst_size, &dump_size)) break; diff --git a/include/asm-generic/preempt.h b/include/asm-generic/preempt.h index d683f5e6d7913..71c1535db56a2 100644 --- a/include/asm-generic/preempt.h +++ b/include/asm-generic/preempt.h @@ -79,6 +79,9 @@ static __always_inline bool should_resched(int preempt_offset) } #ifdef CONFIG_PREEMPTION +#ifdef CONFIG_PREEMPT_RT +extern void preempt_schedule_lock(void); +#endif extern asmlinkage void preempt_schedule(void); #define __preempt_schedule() preempt_schedule() extern asmlinkage void preempt_schedule_notrace(void); diff --git a/include/asm-generic/softirq_stack.h b/include/asm-generic/softirq_stack.h index eceeecf6a5bd8..d3e2d81656e04 100644 --- a/include/asm-generic/softirq_stack.h +++ b/include/asm-generic/softirq_stack.h @@ -2,7 +2,7 @@ #ifndef __ASM_GENERIC_SOFTIRQ_STACK_H #define __ASM_GENERIC_SOFTIRQ_STACK_H -#ifdef CONFIG_HAVE_SOFTIRQ_ON_OWN_STACK +#if defined(CONFIG_HAVE_SOFTIRQ_ON_OWN_STACK) && !defined(CONFIG_PREEMPT_RT) void do_softirq_own_stack(void); #else static inline void do_softirq_own_stack(void) diff --git a/include/linux/bottom_half.h b/include/linux/bottom_half.h index a19519f4241dc..eed86eb0a1dea 100644 --- a/include/linux/bottom_half.h +++ b/include/linux/bottom_half.h @@ -4,7 +4,7 @@ #include -#ifdef CONFIG_TRACE_IRQFLAGS +#if defined(CONFIG_PREEMPT_RT) || defined(CONFIG_TRACE_IRQFLAGS) extern void __local_bh_disable_ip(unsigned long ip, unsigned int cnt); #else static __always_inline void __local_bh_disable_ip(unsigned long ip, unsigned int cnt) @@ -32,4 +32,10 @@ static inline void local_bh_enable(void) __local_bh_enable_ip(_THIS_IP_, SOFTIRQ_DISABLE_OFFSET); } +#ifdef CONFIG_PREEMPT_RT +extern bool local_bh_blocked(void); +#else +static inline bool local_bh_blocked(void) { return false; } +#endif + #endif /* _LINUX_BH_H */ diff --git a/include/linux/console.h b/include/linux/console.h index 20874db50bc8a..851daf13de0a5 100644 --- a/include/linux/console.h +++ b/include/linux/console.h @@ -16,6 +16,19 @@ #include #include +#include +#include + +#ifdef CONFIG_PRINTK_NMI +#define PRINTK_CTX_NUM 2 +#else +#define PRINTK_CTX_NUM 1 +#endif + +struct latched_seq { + seqcount_latch_t latch; + u64 val[2]; +}; struct vc_data; struct console_font_op; @@ -136,10 +149,12 @@ static inline int con_debug_leave(void) #define CON_ANYTIME (16) /* Safe to call when cpu is offline */ #define CON_BRL (32) /* Used for a braille device */ #define CON_EXTENDED (64) /* Use the extended output format a la /dev/kmsg */ +#define CON_HANDOVER (128) /* Device was previously a boot console. */ struct console { char name[16]; void (*write)(struct console *, const char *, unsigned); + void (*write_atomic)(struct console *co, const char *s, unsigned int count); int (*read)(struct console *, char *, unsigned); struct tty_driver *(*device)(struct console *, int *); void (*unblank)(void); @@ -149,6 +164,13 @@ struct console { short flags; short index; int cflag; +#ifdef CONFIG_PRINTK + char sync_buf[CONSOLE_LOG_MAX]; +#endif + struct latched_seq printk_seq; + struct latched_seq printk_sync_seq[PRINTK_CTX_NUM]; + + struct task_struct *thread; void *data; struct console *next; }; @@ -229,4 +251,8 @@ extern void console_init(void); void dummycon_register_output_notifier(struct notifier_block *nb); void dummycon_unregister_output_notifier(struct notifier_block *nb); +extern void console_atomic_lock(unsigned int *flags); +extern void console_atomic_unlock(unsigned int flags); +extern bool console_atomic_kgdb_cpu_delay(unsigned int cpu); + #endif /* _LINUX_CONSOLE_H */ diff --git a/include/linux/dcache.h b/include/linux/dcache.h index c1e48014106fa..f2dc84edbcf17 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -107,7 +107,7 @@ struct dentry { union { struct list_head d_lru; /* LRU list */ - wait_queue_head_t *d_wait; /* in-lookup ones only */ + struct swait_queue_head *d_wait; /* in-lookup ones only */ }; struct list_head d_child; /* child of parent list */ struct list_head d_subdirs; /* our children */ @@ -239,7 +239,7 @@ extern void d_set_d_op(struct dentry *dentry, const struct dentry_operations *op extern struct dentry * d_alloc(struct dentry *, const struct qstr *); extern struct dentry * d_alloc_anon(struct super_block *); extern struct dentry * d_alloc_parallel(struct dentry *, const struct qstr *, - wait_queue_head_t *); + struct swait_queue_head *); extern struct dentry * d_splice_alias(struct inode *, struct dentry *); extern struct dentry * d_add_ci(struct dentry *, struct inode *, struct qstr *); extern struct dentry * d_exact_alias(struct dentry *, struct inode *); diff --git a/include/linux/debug_locks.h b/include/linux/debug_locks.h index 2915f56ad4214..5a9e3e3769ce0 100644 --- a/include/linux/debug_locks.h +++ b/include/linux/debug_locks.h @@ -3,8 +3,7 @@ #define __LINUX_DEBUG_LOCKING_H #include -#include -#include +#include struct task_struct; diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h index 883acef895bc4..0aa546532b312 100644 --- a/include/linux/entry-common.h +++ b/include/linux/entry-common.h @@ -59,7 +59,7 @@ #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_MASK | _TIF_PATCH_PENDING | _TIF_NOTIFY_SIGNAL | \ ARCH_EXIT_TO_USER_MODE_WORK) /** diff --git a/include/linux/fs.h b/include/linux/fs.h index ec8f3ddf4a6aa..e180df9417448 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -700,7 +700,7 @@ struct inode { struct pipe_inode_info *i_pipe; struct cdev *i_cdev; char *i_link; - unsigned i_dir_seq; + unsigned __i_dir_seq; }; __u32 i_generation; diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h index 7c9d6a2d7e909..76878b357ffa9 100644 --- a/include/linux/hardirq.h +++ b/include/linux/hardirq.h @@ -6,6 +6,7 @@ #include #include #include +#include #include #include @@ -115,7 +116,6 @@ extern void rcu_nmi_exit(void); do { \ lockdep_off(); \ arch_nmi_enter(); \ - printk_nmi_enter(); \ BUG_ON(in_nmi() == NMI_MASK); \ __preempt_count_add(NMI_OFFSET + HARDIRQ_OFFSET); \ } while (0) @@ -134,7 +134,6 @@ extern void rcu_nmi_exit(void); do { \ BUG_ON(!in_nmi()); \ __preempt_count_sub(NMI_OFFSET + HARDIRQ_OFFSET); \ - printk_nmi_exit(); \ arch_nmi_exit(); \ lockdep_on(); \ } while (0) diff --git a/include/linux/highmem-internal.h b/include/linux/highmem-internal.h index 7902c7d8b55f9..4aa1031d3e4c3 100644 --- a/include/linux/highmem-internal.h +++ b/include/linux/highmem-internal.h @@ -90,7 +90,11 @@ static inline void __kunmap_local(void *vaddr) static inline void *kmap_atomic_prot(struct page *page, pgprot_t prot) { - preempt_disable(); + if (IS_ENABLED(CONFIG_PREEMPT_RT)) + migrate_disable(); + else + preempt_disable(); + pagefault_disable(); return __kmap_local_page_prot(page, prot); } @@ -102,7 +106,11 @@ static inline void *kmap_atomic(struct page *page) static inline void *kmap_atomic_pfn(unsigned long pfn) { - preempt_disable(); + if (IS_ENABLED(CONFIG_PREEMPT_RT)) + migrate_disable(); + else + preempt_disable(); + pagefault_disable(); return __kmap_local_pfn_prot(pfn, kmap_prot); } @@ -111,7 +119,10 @@ static inline void __kunmap_atomic(void *addr) { kunmap_local_indexed(addr); pagefault_enable(); - preempt_enable(); + if (IS_ENABLED(CONFIG_PREEMPT_RT)) + migrate_enable(); + else + preempt_enable(); } unsigned int __nr_free_highpages(void); @@ -179,7 +190,10 @@ static inline void __kunmap_local(void *addr) static inline void *kmap_atomic(struct page *page) { - preempt_disable(); + if (IS_ENABLED(CONFIG_PREEMPT_RT)) + migrate_disable(); + else + preempt_disable(); pagefault_disable(); return page_address(page); } @@ -200,7 +214,10 @@ static inline void __kunmap_atomic(void *addr) kunmap_flush_on_unmap(addr); #endif pagefault_enable(); - preempt_enable(); + if (IS_ENABLED(CONFIG_PREEMPT_RT)) + migrate_enable(); + else + preempt_enable(); } static inline unsigned int nr_free_highpages(void) { return 0; } diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index bb5e7b0a42746..e425a26a5ed88 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -540,4 +540,10 @@ int hrtimers_dead_cpu(unsigned int cpu); #define hrtimers_dead_cpu NULL #endif +#ifdef CONFIG_PREEMPT_RT +extern void cpu_chill(void); +#else +# define cpu_chill() cpu_relax() +#endif + #endif diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 967e257671534..34259d64de0de 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -654,26 +654,25 @@ enum TASKLET_STATE_RUN /* Tasklet is running (SMP only) */ }; -#ifdef CONFIG_SMP +#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT) static inline int tasklet_trylock(struct tasklet_struct *t) { return !test_and_set_bit(TASKLET_STATE_RUN, &(t)->state); } -static inline void tasklet_unlock(struct tasklet_struct *t) -{ - smp_mb__before_atomic(); - clear_bit(TASKLET_STATE_RUN, &(t)->state); -} +void tasklet_unlock(struct tasklet_struct *t); +void tasklet_unlock_wait(struct tasklet_struct *t); -static inline void tasklet_unlock_wait(struct tasklet_struct *t) -{ - while (test_bit(TASKLET_STATE_RUN, &(t)->state)) { barrier(); } -} +/* + * Do not use in new code. Waiting for tasklets from atomic contexts is + * error prone and should be avoided. + */ +void tasklet_unlock_spin_wait(struct tasklet_struct *t); #else -#define tasklet_trylock(t) 1 -#define tasklet_unlock_wait(t) do { } while (0) -#define tasklet_unlock(t) do { } while (0) +static inline int tasklet_trylock(struct tasklet_struct *t) { return 1; } +static inline void tasklet_unlock(struct tasklet_struct *t) { } +static inline void tasklet_unlock_wait(struct tasklet_struct *t) { } +static inline void tasklet_unlock_spin_wait(struct tasklet_struct *t) { } #endif extern void __tasklet_schedule(struct tasklet_struct *t); @@ -698,6 +697,17 @@ static inline void tasklet_disable_nosync(struct tasklet_struct *t) smp_mb__after_atomic(); } +/* + * Do not use in new code. Disabling tasklets from atomic contexts is + * error prone and should be avoided. + */ +static inline void tasklet_disable_in_atomic(struct tasklet_struct *t) +{ + tasklet_disable_nosync(t); + tasklet_unlock_spin_wait(t); + smp_mb(); +} + static inline void tasklet_disable(struct tasklet_struct *t) { tasklet_disable_nosync(t); diff --git a/include/linux/irq_work.h b/include/linux/irq_work.h index ec2a47a81e423..dbbef90897895 100644 --- a/include/linux/irq_work.h +++ b/include/linux/irq_work.h @@ -64,4 +64,10 @@ static inline void irq_work_run(void) { } static inline void irq_work_single(void *arg) { } #endif +#if defined(CONFIG_IRQ_WORK) && defined(CONFIG_PREEMPT_RT) +void irq_work_tick_soft(void); +#else +static inline void irq_work_tick_soft(void) { } +#endif + #endif /* _LINUX_IRQ_WORK_H */ diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h index 891b323266dfc..45d8bda8fd53d 100644 --- a/include/linux/irqdesc.h +++ b/include/linux/irqdesc.h @@ -68,6 +68,7 @@ struct irq_desc { unsigned int irqs_unhandled; atomic_t threads_handled; int threads_handled_last; + u64 random_ip; raw_spinlock_t lock; struct cpumask *percpu_enabled; const struct cpumask *percpu_affinity; diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h index 600c10da321a7..4b140938b03e2 100644 --- a/include/linux/irqflags.h +++ b/include/linux/irqflags.h @@ -71,14 +71,6 @@ do { \ do { \ __this_cpu_dec(hardirq_context); \ } while (0) -# define lockdep_softirq_enter() \ -do { \ - current->softirq_context++; \ -} while (0) -# define lockdep_softirq_exit() \ -do { \ - current->softirq_context--; \ -} while (0) # define lockdep_hrtimer_enter(__hrtimer) \ ({ \ @@ -140,6 +132,21 @@ do { \ # define lockdep_irq_work_exit(__work) do { } while (0) #endif +#if defined(CONFIG_TRACE_IRQFLAGS) && !defined(CONFIG_PREEMPT_RT) +# define lockdep_softirq_enter() \ +do { \ + current->softirq_context++; \ +} while (0) +# define lockdep_softirq_exit() \ +do { \ + current->softirq_context--; \ +} while (0) + +#else +# define lockdep_softirq_enter() do { } while (0) +# define lockdep_softirq_exit() do { } while (0) +#endif + #if defined(CONFIG_IRQSOFF_TRACER) || \ defined(CONFIG_PREEMPT_TRACER) extern void stop_critical_timings(void); diff --git a/include/linux/kcov.h b/include/linux/kcov.h index 4e3037dc12048..55dc338f6bcdd 100644 --- a/include/linux/kcov.h +++ b/include/linux/kcov.h @@ -2,6 +2,7 @@ #ifndef _LINUX_KCOV_H #define _LINUX_KCOV_H +#include #include struct task_struct; diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 5b7ed6dc99acc..0f9315891c17a 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -122,6 +122,10 @@ extern void __cant_migrate(const char *file, int line); */ # define might_sleep() \ do { __might_sleep(__FILE__, __LINE__, 0); might_resched(); } while (0) + +# define might_sleep_no_state_check() \ + do { ___might_sleep(__FILE__, __LINE__, 0); might_resched(); } while (0) + /** * cant_sleep - annotation for functions that cannot sleep * @@ -165,6 +169,7 @@ extern void __cant_migrate(const char *file, int line); static inline void __might_sleep(const char *file, int line, int preempt_offset) { } # define might_sleep() do { might_resched(); } while (0) +# define might_sleep_no_state_check() do { might_resched(); } while (0) # define cant_sleep() do { } while (0) # define cant_migrate() do { } while (0) # define sched_annotate_sleep() do { } while (0) diff --git a/include/linux/kgdb.h b/include/linux/kgdb.h index 392a3670944c6..67197bbdcba84 100644 --- a/include/linux/kgdb.h +++ b/include/linux/kgdb.h @@ -212,6 +212,8 @@ extern void kgdb_call_nmi_hook(void *ignored); */ extern void kgdb_roundup_cpus(void); +extern void kgdb_roundup_cpu(unsigned int cpu); + /** * kgdb_arch_set_pc - Generic call back to the program counter * @regs: Current &struct pt_regs. @@ -365,5 +367,6 @@ extern void kgdb_free_init_mem(void); #define dbg_late_init() static inline void kgdb_panic(const char *msg) {} static inline void kgdb_free_init_mem(void) { } +static inline void kgdb_roundup_cpu(unsigned int cpu) {} #endif /* ! CONFIG_KGDB */ #endif /* _KGDB_H_ */ diff --git a/include/linux/kmsg_dump.h b/include/linux/kmsg_dump.h index 3378bcbe585ea..906521c2329ca 100644 --- a/include/linux/kmsg_dump.h +++ b/include/linux/kmsg_dump.h @@ -29,6 +29,16 @@ enum kmsg_dump_reason { KMSG_DUMP_MAX }; +/** + * struct kmsg_dump_iter - iterator for retrieving kernel messages + * @cur_seq: Points to the oldest message to dump + * @next_seq: Points after the newest message to dump + */ +struct kmsg_dump_iter { + u64 cur_seq; + u64 next_seq; +}; + /** * struct kmsg_dumper - kernel crash message dumper structure * @list: Entry in the dumper list (private) @@ -41,31 +51,19 @@ struct kmsg_dumper { struct list_head list; void (*dump)(struct kmsg_dumper *dumper, enum kmsg_dump_reason reason); enum kmsg_dump_reason max_reason; - bool active; bool registered; - - /* private state of the kmsg iterator */ - u32 cur_idx; - u32 next_idx; - u64 cur_seq; - u64 next_seq; }; #ifdef CONFIG_PRINTK void kmsg_dump(enum kmsg_dump_reason reason); -bool kmsg_dump_get_line_nolock(struct kmsg_dumper *dumper, bool syslog, - char *line, size_t size, size_t *len); - -bool kmsg_dump_get_line(struct kmsg_dumper *dumper, bool syslog, +bool kmsg_dump_get_line(struct kmsg_dump_iter *iter, bool syslog, char *line, size_t size, size_t *len); -bool kmsg_dump_get_buffer(struct kmsg_dumper *dumper, bool syslog, - char *buf, size_t size, size_t *len); +bool kmsg_dump_get_buffer(struct kmsg_dump_iter *iter, bool syslog, + char *buf, size_t size, size_t *len_out); -void kmsg_dump_rewind_nolock(struct kmsg_dumper *dumper); - -void kmsg_dump_rewind(struct kmsg_dumper *dumper); +void kmsg_dump_rewind(struct kmsg_dump_iter *iter); int kmsg_dump_register(struct kmsg_dumper *dumper); @@ -77,30 +75,19 @@ static inline void kmsg_dump(enum kmsg_dump_reason reason) { } -static inline bool kmsg_dump_get_line_nolock(struct kmsg_dumper *dumper, - bool syslog, const char *line, - size_t size, size_t *len) -{ - return false; -} - -static inline bool kmsg_dump_get_line(struct kmsg_dumper *dumper, bool syslog, +static inline bool kmsg_dump_get_line(struct kmsg_dump_iter *iter, bool syslog, const char *line, size_t size, size_t *len) { return false; } -static inline bool kmsg_dump_get_buffer(struct kmsg_dumper *dumper, bool syslog, +static inline bool kmsg_dump_get_buffer(struct kmsg_dump_iter *iter, bool syslog, char *buf, size_t size, size_t *len) { return false; } -static inline void kmsg_dump_rewind_nolock(struct kmsg_dumper *dumper) -{ -} - -static inline void kmsg_dump_rewind(struct kmsg_dumper *dumper) +static inline void kmsg_dump_rewind(struct kmsg_dump_iter *iter) { } diff --git a/include/linux/local_lock_internal.h b/include/linux/local_lock_internal.h index ded90b097e6e8..7162dcd0a847d 100644 --- a/include/linux/local_lock_internal.h +++ b/include/linux/local_lock_internal.h @@ -7,36 +7,94 @@ #include typedef struct { -#ifdef CONFIG_DEBUG_LOCK_ALLOC +#ifdef CONFIG_PREEMPT_RT + spinlock_t lock; + struct task_struct *owner; + int nestcnt; + +#elif defined(CONFIG_DEBUG_LOCK_ALLOC) struct lockdep_map dep_map; struct task_struct *owner; #endif } local_lock_t; -#ifdef CONFIG_DEBUG_LOCK_ALLOC -# define LL_DEP_MAP_INIT(lockname) \ +#ifdef CONFIG_PREEMPT_RT + +#define INIT_LOCAL_LOCK(lockname) { \ + __SPIN_LOCK_UNLOCKED((lockname).lock), \ + .owner = NULL, \ + .nestcnt = 0, \ + } +#else + +# ifdef CONFIG_DEBUG_LOCK_ALLOC +# define LL_DEP_MAP_INIT(lockname) \ .dep_map = { \ .name = #lockname, \ .wait_type_inner = LD_WAIT_CONFIG, \ - .lock_type = LD_LOCK_PERCPU, \ + .lock_type = LD_LOCK_PERCPU, \ } -#else -# define LL_DEP_MAP_INIT(lockname) -#endif +# else +# define LL_DEP_MAP_INIT(lockname) +# endif #define INIT_LOCAL_LOCK(lockname) { LL_DEP_MAP_INIT(lockname) } -#define __local_lock_init(lock) \ +#endif + +#ifdef CONFIG_PREEMPT_RT + +static inline void ___local_lock_init(local_lock_t *l) +{ + l->owner = NULL; + l->nestcnt = 0; +} + +#define __local_lock_init(l) \ +do { \ + spin_lock_init(&(l)->lock); \ + ___local_lock_init(l); \ +} while (0) + +#else + +#define __local_lock_init(l) \ do { \ static struct lock_class_key __key; \ \ - debug_check_no_locks_freed((void *)lock, sizeof(*lock));\ - lockdep_init_map_type(&(lock)->dep_map, #lock, &__key, 0, \ + debug_check_no_locks_freed((void *)l, sizeof(*l)); \ + lockdep_init_map_type(&(l)->dep_map, #l, &__key, 0, \ LD_WAIT_CONFIG, LD_WAIT_INV, \ LD_LOCK_PERCPU); \ } while (0) +#endif + +#ifdef CONFIG_PREEMPT_RT + +static inline void local_lock_acquire(local_lock_t *l) +{ + if (l->owner != current) { + spin_lock(&l->lock); + DEBUG_LOCKS_WARN_ON(l->owner); + DEBUG_LOCKS_WARN_ON(l->nestcnt); + l->owner = current; + } + l->nestcnt++; +} + +static inline void local_lock_release(local_lock_t *l) +{ + DEBUG_LOCKS_WARN_ON(l->nestcnt == 0); + DEBUG_LOCKS_WARN_ON(l->owner != current); + if (--l->nestcnt) + return; + + l->owner = NULL; + spin_unlock(&l->lock); +} + +#elif defined(CONFIG_DEBUG_LOCK_ALLOC) -#ifdef CONFIG_DEBUG_LOCK_ALLOC static inline void local_lock_acquire(local_lock_t *l) { lock_map_acquire(&l->dep_map); @@ -56,12 +114,59 @@ static inline void local_lock_acquire(local_lock_t *l) { } static inline void local_lock_release(local_lock_t *l) { } #endif /* !CONFIG_DEBUG_LOCK_ALLOC */ +#ifdef CONFIG_PREEMPT_RT + +#define __local_lock(lock) \ + do { \ + migrate_disable(); \ + local_lock_acquire(this_cpu_ptr(lock)); \ + } while (0) + +#define __local_unlock(lock) \ + do { \ + local_lock_release(this_cpu_ptr(lock)); \ + migrate_enable(); \ + } while (0) + +#define __local_lock_irq(lock) \ + do { \ + migrate_disable(); \ + local_lock_acquire(this_cpu_ptr(lock)); \ + } while (0) + +#define __local_lock_irqsave(lock, flags) \ + do { \ + migrate_disable(); \ + flags = 0; \ + local_lock_acquire(this_cpu_ptr(lock)); \ + } while (0) + +#define __local_unlock_irq(lock) \ + do { \ + local_lock_release(this_cpu_ptr(lock)); \ + migrate_enable(); \ + } while (0) + +#define __local_unlock_irqrestore(lock, flags) \ + do { \ + local_lock_release(this_cpu_ptr(lock)); \ + migrate_enable(); \ + } while (0) + +#else + #define __local_lock(lock) \ do { \ preempt_disable(); \ local_lock_acquire(this_cpu_ptr(lock)); \ } while (0) +#define __local_unlock(lock) \ + do { \ + local_lock_release(this_cpu_ptr(lock)); \ + preempt_enable(); \ + } while (0) + #define __local_lock_irq(lock) \ do { \ local_irq_disable(); \ @@ -74,12 +179,6 @@ static inline void local_lock_release(local_lock_t *l) { } local_lock_acquire(this_cpu_ptr(lock)); \ } while (0) -#define __local_unlock(lock) \ - do { \ - local_lock_release(this_cpu_ptr(lock)); \ - preempt_enable(); \ - } while (0) - #define __local_unlock_irq(lock) \ do { \ local_lock_release(this_cpu_ptr(lock)); \ @@ -91,3 +190,5 @@ static inline void local_lock_release(local_lock_t *l) { } local_lock_release(this_cpu_ptr(lock)); \ local_irq_restore(flags); \ } while (0) + +#endif diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 6613b26a88946..46562daf2ae26 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -12,6 +12,7 @@ #include #include #include +#include #include #include #include @@ -554,6 +555,9 @@ struct mm_struct { bool tlb_flush_batched; #endif struct uprobes_state uprobes_state; +#ifdef CONFIG_PREEMPT_RT + struct rcu_head delayed_drop; +#endif #ifdef CONFIG_HUGETLB_PAGE atomic_long_t hugetlb_usage; #endif diff --git a/include/linux/mutex.h b/include/linux/mutex.h index 0cd631a197276..d7cfc5dc817bf 100644 --- a/include/linux/mutex.h +++ b/include/linux/mutex.h @@ -22,6 +22,20 @@ struct ww_acquire_ctx; +#ifdef CONFIG_DEBUG_LOCK_ALLOC +# define __DEP_MAP_MUTEX_INITIALIZER(lockname) \ + , .dep_map = { \ + .name = #lockname, \ + .wait_type_inner = LD_WAIT_SLEEP, \ + } +#else +# define __DEP_MAP_MUTEX_INITIALIZER(lockname) +#endif + +#ifdef CONFIG_PREEMPT_RT +# include +#else + /* * Simple, straightforward mutexes with strict semantics: * @@ -68,14 +82,6 @@ struct mutex { struct ww_class; struct ww_acquire_ctx; -struct ww_mutex { - struct mutex base; - struct ww_acquire_ctx *ctx; -#ifdef CONFIG_DEBUG_MUTEXES - struct ww_class *ww_class; -#endif -}; - /* * This is the control structure for tasks blocked on mutex, * which resides on the blocked task's kernel stack: @@ -119,16 +125,6 @@ do { \ __mutex_init((mutex), #mutex, &__key); \ } while (0) -#ifdef CONFIG_DEBUG_LOCK_ALLOC -# define __DEP_MAP_MUTEX_INITIALIZER(lockname) \ - , .dep_map = { \ - .name = #lockname, \ - .wait_type_inner = LD_WAIT_SLEEP, \ - } -#else -# define __DEP_MAP_MUTEX_INITIALIZER(lockname) -#endif - #define __MUTEX_INITIALIZER(lockname) \ { .owner = ATOMIC_LONG_INIT(0) \ , .wait_lock = __SPIN_LOCK_UNLOCKED(lockname.wait_lock) \ @@ -199,4 +195,5 @@ extern void mutex_unlock(struct mutex *lock); extern int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock); +#endif /* !PREEMPT_RT */ #endif /* __LINUX_MUTEX_H */ diff --git a/include/linux/mutex_rt.h b/include/linux/mutex_rt.h new file mode 100644 index 0000000000000..f0b2e07cd5c57 --- /dev/null +++ b/include/linux/mutex_rt.h @@ -0,0 +1,130 @@ +// SPDX-License-Identifier: GPL-2.0-only +#ifndef __LINUX_MUTEX_RT_H +#define __LINUX_MUTEX_RT_H + +#ifndef __LINUX_MUTEX_H +#error "Please include mutex.h" +#endif + +#include + +/* FIXME: Just for __lockfunc */ +#include + +struct mutex { + struct rt_mutex lock; +#ifdef CONFIG_DEBUG_LOCK_ALLOC + struct lockdep_map dep_map; +#endif +}; + +#define __MUTEX_INITIALIZER(mutexname) \ + { \ + .lock = __RT_MUTEX_INITIALIZER(mutexname.lock) \ + __DEP_MAP_MUTEX_INITIALIZER(mutexname) \ + } + +#define DEFINE_MUTEX(mutexname) \ + struct mutex mutexname = __MUTEX_INITIALIZER(mutexname) + +extern void __mutex_do_init(struct mutex *lock, const char *name, struct lock_class_key *key); +extern void __lockfunc _mutex_lock(struct mutex *lock); +extern void __lockfunc _mutex_lock_io_nested(struct mutex *lock, int subclass); +extern int __lockfunc _mutex_lock_interruptible(struct mutex *lock); +extern int __lockfunc _mutex_lock_killable(struct mutex *lock); +extern void __lockfunc _mutex_lock_nested(struct mutex *lock, int subclass); +extern void __lockfunc _mutex_lock_nest_lock(struct mutex *lock, struct lockdep_map *nest_lock); +extern int __lockfunc _mutex_lock_interruptible_nested(struct mutex *lock, int subclass); +extern int __lockfunc _mutex_lock_killable_nested(struct mutex *lock, int subclass); +extern int __lockfunc _mutex_trylock(struct mutex *lock); +extern void __lockfunc _mutex_unlock(struct mutex *lock); + +#define mutex_is_locked(l) rt_mutex_is_locked(&(l)->lock) +#define mutex_lock(l) _mutex_lock(l) +#define mutex_lock_interruptible(l) _mutex_lock_interruptible(l) +#define mutex_lock_killable(l) _mutex_lock_killable(l) +#define mutex_trylock(l) _mutex_trylock(l) +#define mutex_unlock(l) _mutex_unlock(l) +#define mutex_lock_io(l) _mutex_lock_io_nested(l, 0); + +#define __mutex_owner(l) ((l)->lock.owner) + +#ifdef CONFIG_DEBUG_MUTEXES +#define mutex_destroy(l) rt_mutex_destroy(&(l)->lock) +#else +static inline void mutex_destroy(struct mutex *lock) {} +#endif + +#ifdef CONFIG_DEBUG_LOCK_ALLOC +# define mutex_lock_nested(l, s) _mutex_lock_nested(l, s) +# define mutex_lock_interruptible_nested(l, s) \ + _mutex_lock_interruptible_nested(l, s) +# define mutex_lock_killable_nested(l, s) \ + _mutex_lock_killable_nested(l, s) +# define mutex_lock_io_nested(l, s) _mutex_lock_io_nested(l, s) + +# define mutex_lock_nest_lock(lock, nest_lock) \ +do { \ + typecheck(struct lockdep_map *, &(nest_lock)->dep_map); \ + _mutex_lock_nest_lock(lock, &(nest_lock)->dep_map); \ +} while (0) + +#else +# define mutex_lock_nested(l, s) _mutex_lock(l) +# define mutex_lock_interruptible_nested(l, s) \ + _mutex_lock_interruptible(l) +# define mutex_lock_killable_nested(l, s) \ + _mutex_lock_killable(l) +# define mutex_lock_nest_lock(lock, nest_lock) mutex_lock(lock) +# define mutex_lock_io_nested(l, s) _mutex_lock_io_nested(l, s) +#endif + +# define mutex_init(mutex) \ +do { \ + static struct lock_class_key __key; \ + \ + rt_mutex_init(&(mutex)->lock); \ + __mutex_do_init((mutex), #mutex, &__key); \ +} while (0) + +# define __mutex_init(mutex, name, key) \ +do { \ + rt_mutex_init(&(mutex)->lock); \ + __mutex_do_init((mutex), name, key); \ +} while (0) + +/** + * These values are chosen such that FAIL and SUCCESS match the + * values of the regular mutex_trylock(). + */ +enum mutex_trylock_recursive_enum { + MUTEX_TRYLOCK_FAILED = 0, + MUTEX_TRYLOCK_SUCCESS = 1, + MUTEX_TRYLOCK_RECURSIVE, +}; +/** + * mutex_trylock_recursive - trylock variant that allows recursive locking + * @lock: mutex to be locked + * + * This function should not be used, _ever_. It is purely for hysterical GEM + * raisins, and once those are gone this will be removed. + * + * Returns: + * MUTEX_TRYLOCK_FAILED - trylock failed, + * MUTEX_TRYLOCK_SUCCESS - lock acquired, + * MUTEX_TRYLOCK_RECURSIVE - we already owned the lock. + */ +int __rt_mutex_owner_current(struct rt_mutex *lock); + +static inline /* __deprecated */ __must_check enum mutex_trylock_recursive_enum +mutex_trylock_recursive(struct mutex *lock) +{ + if (unlikely(__rt_mutex_owner_current(&lock->lock))) + return MUTEX_TRYLOCK_RECURSIVE; + + return mutex_trylock(lock); +} + +extern int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock); + +#endif diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 3327239fa2f9a..f596a16a5f7b8 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1684,7 +1684,7 @@ struct nfs_unlinkdata { struct nfs_removeargs args; struct nfs_removeres res; struct dentry *dentry; - wait_queue_head_t wq; + struct swait_queue_head wq; const struct cred *cred; struct nfs_fattr dir_attr; long timeout; diff --git a/include/linux/notifier.h b/include/linux/notifier.h index 2fb373a5c1ede..723bc2df63882 100644 --- a/include/linux/notifier.h +++ b/include/linux/notifier.h @@ -58,7 +58,7 @@ struct notifier_block { }; struct atomic_notifier_head { - spinlock_t lock; + raw_spinlock_t lock; struct notifier_block __rcu *head; }; @@ -78,7 +78,7 @@ struct srcu_notifier_head { }; #define ATOMIC_INIT_NOTIFIER_HEAD(name) do { \ - spin_lock_init(&(name)->lock); \ + raw_spin_lock_init(&(name)->lock); \ (name)->head = NULL; \ } while (0) #define BLOCKING_INIT_NOTIFIER_HEAD(name) do { \ @@ -95,7 +95,7 @@ extern void srcu_init_notifier_head(struct srcu_notifier_head *nh); cleanup_srcu_struct(&(name)->srcu); #define ATOMIC_NOTIFIER_INIT(name) { \ - .lock = __SPIN_LOCK_UNLOCKED(name.lock), \ + .lock = __RAW_SPIN_LOCK_UNLOCKED(name.lock), \ .head = NULL } #define BLOCKING_NOTIFIER_INIT(name) { \ .rwsem = __RWSEM_INITIALIZER((name).rwsem), \ diff --git a/include/linux/pid.h b/include/linux/pid.h index fa10acb8d6a42..2f86f84e9fc1a 100644 --- a/include/linux/pid.h +++ b/include/linux/pid.h @@ -3,6 +3,7 @@ #define _LINUX_PID_H #include +#include #include #include diff --git a/include/linux/preempt.h b/include/linux/preempt.h index 69cc8b64aa3a0..af39859f02ee1 100644 --- a/include/linux/preempt.h +++ b/include/linux/preempt.h @@ -79,7 +79,11 @@ #define nmi_count() (preempt_count() & NMI_MASK) #define hardirq_count() (preempt_count() & HARDIRQ_MASK) -#define softirq_count() (preempt_count() & SOFTIRQ_MASK) +#ifdef CONFIG_PREEMPT_RT +# define softirq_count() (current->softirq_disable_cnt & SOFTIRQ_MASK) +#else +# define softirq_count() (preempt_count() & SOFTIRQ_MASK) +#endif #define irq_count() (nmi_count() | hardirq_count() | softirq_count()) /* @@ -117,7 +121,11 @@ /* * The preempt_count offset after spin_lock() */ +#if !defined(CONFIG_PREEMPT_RT) #define PREEMPT_LOCK_OFFSET PREEMPT_DISABLE_OFFSET +#else +#define PREEMPT_LOCK_OFFSET 0 +#endif /* * The preempt_count offset needed for things like: @@ -166,6 +174,20 @@ extern void preempt_count_sub(int val); #define preempt_count_inc() preempt_count_add(1) #define preempt_count_dec() preempt_count_sub(1) +#ifdef CONFIG_PREEMPT_LAZY +#define add_preempt_lazy_count(val) do { preempt_lazy_count() += (val); } while (0) +#define sub_preempt_lazy_count(val) do { preempt_lazy_count() -= (val); } while (0) +#define inc_preempt_lazy_count() add_preempt_lazy_count(1) +#define dec_preempt_lazy_count() sub_preempt_lazy_count(1) +#define preempt_lazy_count() (current_thread_info()->preempt_lazy_count) +#else +#define add_preempt_lazy_count(val) do { } while (0) +#define sub_preempt_lazy_count(val) do { } while (0) +#define inc_preempt_lazy_count() do { } while (0) +#define dec_preempt_lazy_count() do { } while (0) +#define preempt_lazy_count() (0) +#endif + #ifdef CONFIG_PREEMPT_COUNT #define preempt_disable() \ @@ -174,13 +196,25 @@ do { \ barrier(); \ } while (0) +#define preempt_lazy_disable() \ +do { \ + inc_preempt_lazy_count(); \ + barrier(); \ +} while (0) + #define sched_preempt_enable_no_resched() \ do { \ barrier(); \ preempt_count_dec(); \ } while (0) -#define preempt_enable_no_resched() sched_preempt_enable_no_resched() +#ifdef CONFIG_PREEMPT_RT +# define preempt_enable_no_resched() sched_preempt_enable_no_resched() +# define preempt_check_resched_rt() preempt_check_resched() +#else +# define preempt_enable_no_resched() preempt_enable() +# define preempt_check_resched_rt() barrier(); +#endif #define preemptible() (preempt_count() == 0 && !irqs_disabled()) @@ -205,6 +239,18 @@ do { \ __preempt_schedule(); \ } while (0) +/* + * open code preempt_check_resched() because it is not exported to modules and + * used by local_unlock() or bpf_enable_instrumentation(). + */ +#define preempt_lazy_enable() \ +do { \ + dec_preempt_lazy_count(); \ + barrier(); \ + if (should_resched(0)) \ + __preempt_schedule(); \ +} while (0) + #else /* !CONFIG_PREEMPTION */ #define preempt_enable() \ do { \ @@ -212,6 +258,12 @@ do { \ preempt_count_dec(); \ } while (0) +#define preempt_lazy_enable() \ +do { \ + dec_preempt_lazy_count(); \ + barrier(); \ +} while (0) + #define preempt_enable_notrace() \ do { \ barrier(); \ @@ -250,8 +302,12 @@ do { \ #define preempt_disable_notrace() barrier() #define preempt_enable_no_resched_notrace() barrier() #define preempt_enable_notrace() barrier() +#define preempt_check_resched_rt() barrier() #define preemptible() 0 +#define preempt_lazy_disable() barrier() +#define preempt_lazy_enable() barrier() + #endif /* CONFIG_PREEMPT_COUNT */ #ifdef MODULE @@ -270,10 +326,22 @@ do { \ } while (0) #define preempt_fold_need_resched() \ do { \ - if (tif_need_resched()) \ + if (tif_need_resched_now()) \ set_preempt_need_resched(); \ } while (0) +#ifdef CONFIG_PREEMPT_RT +# define preempt_disable_rt() preempt_disable() +# define preempt_enable_rt() preempt_enable() +# define preempt_disable_nort() barrier() +# define preempt_enable_nort() barrier() +#else +# define preempt_disable_rt() barrier() +# define preempt_enable_rt() barrier() +# define preempt_disable_nort() preempt_disable() +# define preempt_enable_nort() preempt_enable() +#endif + #ifdef CONFIG_PREEMPT_NOTIFIERS struct preempt_notifier; @@ -386,8 +454,15 @@ extern void migrate_enable(void); #else -static inline void migrate_disable(void) { } -static inline void migrate_enable(void) { } +static inline void migrate_disable(void) +{ + preempt_lazy_disable(); +} + +static inline void migrate_enable(void) +{ + preempt_lazy_enable(); +} #endif /* CONFIG_SMP */ diff --git a/include/linux/printk.h b/include/linux/printk.h index fe7eb2351610d..0cdd25b49fcc5 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -46,6 +46,12 @@ static inline const char *printk_skip_headers(const char *buffer) #define CONSOLE_EXT_LOG_MAX 8192 +/* + * The maximum size of a record formatted for console printing + * (i.e. with the prefix prepended to every line). + */ +#define CONSOLE_LOG_MAX 1024 + /* printk's without a loglevel use this.. */ #define MESSAGE_LOGLEVEL_DEFAULT CONFIG_MESSAGE_LOGLEVEL_DEFAULT @@ -149,18 +155,6 @@ static inline __printf(1, 2) __cold void early_printk(const char *s, ...) { } #endif -#ifdef CONFIG_PRINTK_NMI -extern void printk_nmi_enter(void); -extern void printk_nmi_exit(void); -extern void printk_nmi_direct_enter(void); -extern void printk_nmi_direct_exit(void); -#else -static inline void printk_nmi_enter(void) { } -static inline void printk_nmi_exit(void) { } -static inline void printk_nmi_direct_enter(void) { } -static inline void printk_nmi_direct_exit(void) { } -#endif /* PRINTK_NMI */ - struct dev_printk_info; #ifdef CONFIG_PRINTK @@ -207,8 +201,6 @@ __printf(1, 2) void dump_stack_set_arch_desc(const char *fmt, ...); void dump_stack_print_info(const char *log_lvl); void show_regs_print_info(const char *log_lvl); extern asmlinkage void dump_stack(void) __cold; -extern void printk_safe_flush(void); -extern void printk_safe_flush_on_panic(void); #else static inline __printf(1, 0) int vprintk(const char *s, va_list args) @@ -272,14 +264,6 @@ static inline void show_regs_print_info(const char *log_lvl) static inline void dump_stack(void) { } - -static inline void printk_safe_flush(void) -{ -} - -static inline void printk_safe_flush_on_panic(void) -{ -} #endif extern int kptr_restrict; @@ -497,6 +481,8 @@ extern int kptr_restrict; no_printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) #endif +bool pr_flush(int timeout_ms, bool reset_on_progress); + /* * ratelimited messages with local ratelimit_state, * no local ratelimit_state used in the !PRINTK case diff --git a/include/linux/random.h b/include/linux/random.h index f45b8be3e3c4e..0e41d05278091 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -35,7 +35,7 @@ static inline void add_latent_entropy(void) {} extern void add_input_randomness(unsigned int type, unsigned int code, unsigned int value) __latent_entropy; -extern void add_interrupt_randomness(int irq, int irq_flags) __latent_entropy; +extern void add_interrupt_randomness(int irq, int irq_flags, __u64 ip) __latent_entropy; extern void get_random_bytes(void *buf, int nbytes); extern int wait_for_random_bytes(void); diff --git a/include/linux/rbtree.h b/include/linux/rbtree.h index d31ecaf4fdd3d..e711efc2e0096 100644 --- a/include/linux/rbtree.h +++ b/include/linux/rbtree.h @@ -19,19 +19,9 @@ #include #include +#include #include -struct rb_node { - unsigned long __rb_parent_color; - struct rb_node *rb_right; - struct rb_node *rb_left; -} __attribute__((aligned(sizeof(long)))); - /* The alignment might seem pointless, but allegedly CRIS needs it */ - -struct rb_root { - struct rb_node *rb_node; -}; - #define rb_parent(r) ((struct rb_node *)((r)->__rb_parent_color & ~3)) #define RB_ROOT (struct rb_root) { NULL, } @@ -112,21 +102,6 @@ static inline void rb_link_node_rcu(struct rb_node *node, struct rb_node *parent typeof(*pos), field); 1; }); \ pos = n) -/* - * Leftmost-cached rbtrees. - * - * We do not cache the rightmost node based on footprint - * size vs number of potential users that could benefit - * from O(1) rb_last(). Just not worth it, users that want - * this feature can always implement the logic explicitly. - * Furthermore, users that want to cache both pointers may - * find it a bit asymmetric, but that's ok. - */ -struct rb_root_cached { - struct rb_root rb_root; - struct rb_node *rb_leftmost; -}; - #define RB_ROOT_CACHED (struct rb_root_cached) { {NULL, }, NULL } /* Same as rb_first(), but O(1) */ diff --git a/include/linux/rbtree_type.h b/include/linux/rbtree_type.h new file mode 100644 index 0000000000000..77a89dd2c7c66 --- /dev/null +++ b/include/linux/rbtree_type.h @@ -0,0 +1,31 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef _LINUX_RBTREE_TYPE_H +#define _LINUX_RBTREE_TYPE_H + +struct rb_node { + unsigned long __rb_parent_color; + struct rb_node *rb_right; + struct rb_node *rb_left; +} __attribute__((aligned(sizeof(long)))); +/* The alignment might seem pointless, but allegedly CRIS needs it */ + +struct rb_root { + struct rb_node *rb_node; +}; + +/* + * Leftmost-cached rbtrees. + * + * We do not cache the rightmost node based on footprint + * size vs number of potential users that could benefit + * from O(1) rb_last(). Just not worth it, users that want + * this feature can always implement the logic explicitly. + * Furthermore, users that want to cache both pointers may + * find it a bit asymmetric, but that's ok. + */ +struct rb_root_cached { + struct rb_root rb_root; + struct rb_node *rb_leftmost; +}; + +#endif diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index bd04f722714f6..8b18be4c38ce2 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -54,6 +54,11 @@ void __rcu_read_unlock(void); * types of kernel builds, the rcu_read_lock() nesting depth is unknowable. */ #define rcu_preempt_depth() (current->rcu_read_lock_nesting) +#ifndef CONFIG_PREEMPT_RT +#define sched_rcu_preempt_depth() rcu_preempt_depth() +#else +static inline int sched_rcu_preempt_depth(void) { return 0; } +#endif #else /* #ifdef CONFIG_PREEMPT_RCU */ @@ -79,6 +84,8 @@ static inline int rcu_preempt_depth(void) return 0; } +#define sched_rcu_preempt_depth() rcu_preempt_depth() + #endif /* #else #ifdef CONFIG_PREEMPT_RCU */ /* Internal to kernel */ @@ -334,7 +341,8 @@ static inline void rcu_preempt_sleep_check(void) { } #define rcu_sleep_check() \ do { \ rcu_preempt_sleep_check(); \ - RCU_LOCKDEP_WARN(lock_is_held(&rcu_bh_lock_map), \ + if (!IS_ENABLED(CONFIG_PREEMPT_RT)) \ + RCU_LOCKDEP_WARN(lock_is_held(&rcu_bh_lock_map), \ "Illegal context switch in RCU-bh read-side critical section"); \ RCU_LOCKDEP_WARN(lock_is_held(&rcu_sched_lock_map), \ "Illegal context switch in RCU-sched read-side critical section"); \ diff --git a/include/linux/rtmutex.h b/include/linux/rtmutex.h index 6fd615a0eea94..b02009f530263 100644 --- a/include/linux/rtmutex.h +++ b/include/linux/rtmutex.h @@ -14,11 +14,15 @@ #define __LINUX_RT_MUTEX_H #include -#include -#include +#include +#include extern int max_lock_depth; /* for sysctl */ +#ifdef CONFIG_DEBUG_MUTEXES +#include +#endif + /** * The rt_mutex structure * @@ -31,12 +35,7 @@ struct rt_mutex { raw_spinlock_t wait_lock; struct rb_root_cached waiters; struct task_struct *owner; -#ifdef CONFIG_DEBUG_RT_MUTEXES int save_state; - const char *name, *file; - int line; - void *magic; -#endif #ifdef CONFIG_DEBUG_LOCK_ALLOC struct lockdep_map dep_map; #endif @@ -49,6 +48,7 @@ struct hrtimer_sleeper; extern int rt_mutex_debug_check_no_locks_freed(const void *from, unsigned long len); extern void rt_mutex_debug_check_no_locks_held(struct task_struct *task); + extern void rt_mutex_debug_task_free(struct task_struct *tsk); #else static inline int rt_mutex_debug_check_no_locks_freed(const void *from, unsigned long len) @@ -56,25 +56,15 @@ struct hrtimer_sleeper; return 0; } # define rt_mutex_debug_check_no_locks_held(task) do { } while (0) +# define rt_mutex_debug_task_free(t) do { } while (0) #endif -#ifdef CONFIG_DEBUG_RT_MUTEXES -# define __DEBUG_RT_MUTEX_INITIALIZER(mutexname) \ - , .name = #mutexname, .file = __FILE__, .line = __LINE__ - -# define rt_mutex_init(mutex) \ +#define rt_mutex_init(mutex) \ do { \ static struct lock_class_key __key; \ __rt_mutex_init(mutex, __func__, &__key); \ } while (0) - extern void rt_mutex_debug_task_free(struct task_struct *tsk); -#else -# define __DEBUG_RT_MUTEX_INITIALIZER(mutexname) -# define rt_mutex_init(mutex) __rt_mutex_init(mutex, NULL, NULL) -# define rt_mutex_debug_task_free(t) do { } while (0) -#endif - #ifdef CONFIG_DEBUG_LOCK_ALLOC #define __DEP_MAP_RT_MUTEX_INITIALIZER(mutexname) \ , .dep_map = { .name = #mutexname } @@ -82,12 +72,19 @@ do { \ #define __DEP_MAP_RT_MUTEX_INITIALIZER(mutexname) #endif -#define __RT_MUTEX_INITIALIZER(mutexname) \ - { .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(mutexname.wait_lock) \ +#define __RT_MUTEX_INITIALIZER_PLAIN(mutexname) \ + .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(mutexname.wait_lock) \ , .waiters = RB_ROOT_CACHED \ , .owner = NULL \ - __DEBUG_RT_MUTEX_INITIALIZER(mutexname) \ - __DEP_MAP_RT_MUTEX_INITIALIZER(mutexname)} + __DEP_MAP_RT_MUTEX_INITIALIZER(mutexname) + +#define __RT_MUTEX_INITIALIZER(mutexname) \ + { __RT_MUTEX_INITIALIZER_PLAIN(mutexname) \ + , .save_state = 0 } + +#define __RT_MUTEX_INITIALIZER_SAVE_STATE(mutexname) \ + { __RT_MUTEX_INITIALIZER_PLAIN(mutexname) \ + , .save_state = 1 } #define DEFINE_RT_MUTEX(mutexname) \ struct rt_mutex mutexname = __RT_MUTEX_INITIALIZER(mutexname) @@ -115,9 +112,6 @@ extern void rt_mutex_lock(struct rt_mutex *lock); #endif extern int rt_mutex_lock_interruptible(struct rt_mutex *lock); -extern int rt_mutex_timed_lock(struct rt_mutex *lock, - struct hrtimer_sleeper *timeout); - extern int rt_mutex_trylock(struct rt_mutex *lock); extern void rt_mutex_unlock(struct rt_mutex *lock); diff --git a/include/linux/rwlock_rt.h b/include/linux/rwlock_rt.h new file mode 100644 index 0000000000000..552b8d69cdb3c --- /dev/null +++ b/include/linux/rwlock_rt.h @@ -0,0 +1,113 @@ +// SPDX-License-Identifier: GPL-2.0-only +#ifndef __LINUX_RWLOCK_RT_H +#define __LINUX_RWLOCK_RT_H + +#ifndef __LINUX_SPINLOCK_H +#error Do not include directly. Use spinlock.h +#endif + +extern void __lockfunc rt_write_lock(rwlock_t *rwlock); +extern void __lockfunc rt_read_lock(rwlock_t *rwlock); +extern int __lockfunc rt_write_trylock(rwlock_t *rwlock); +extern int __lockfunc rt_read_trylock(rwlock_t *rwlock); +extern void __lockfunc rt_write_unlock(rwlock_t *rwlock); +extern void __lockfunc rt_read_unlock(rwlock_t *rwlock); +extern int __lockfunc rt_read_can_lock(rwlock_t *rwlock); +extern int __lockfunc rt_write_can_lock(rwlock_t *rwlock); +extern void __rt_rwlock_init(rwlock_t *rwlock, char *name, struct lock_class_key *key); +extern int __lockfunc rt_rwlock_is_contended(rwlock_t *rwlock); + +#define read_can_lock(rwlock) rt_read_can_lock(rwlock) +#define write_can_lock(rwlock) rt_write_can_lock(rwlock) + +#define read_trylock(lock) __cond_lock(lock, rt_read_trylock(lock)) +#define write_trylock(lock) __cond_lock(lock, rt_write_trylock(lock)) + +static inline int __write_trylock_rt_irqsave(rwlock_t *lock, unsigned long *flags) +{ + *flags = 0; + return rt_write_trylock(lock); +} + +#define write_trylock_irqsave(lock, flags) \ + __cond_lock(lock, __write_trylock_rt_irqsave(lock, &(flags))) + +#define read_lock_irqsave(lock, flags) \ + do { \ + typecheck(unsigned long, flags); \ + rt_read_lock(lock); \ + flags = 0; \ + } while (0) + +#define write_lock_irqsave(lock, flags) \ + do { \ + typecheck(unsigned long, flags); \ + rt_write_lock(lock); \ + flags = 0; \ + } while (0) + +#define read_lock(lock) rt_read_lock(lock) + +#define read_lock_bh(lock) \ + do { \ + local_bh_disable(); \ + rt_read_lock(lock); \ + } while (0) + +#define read_lock_irq(lock) read_lock(lock) + +#define write_lock(lock) rt_write_lock(lock) + +#define write_lock_bh(lock) \ + do { \ + local_bh_disable(); \ + rt_write_lock(lock); \ + } while (0) + +#define write_lock_irq(lock) write_lock(lock) + +#define read_unlock(lock) rt_read_unlock(lock) + +#define read_unlock_bh(lock) \ + do { \ + rt_read_unlock(lock); \ + local_bh_enable(); \ + } while (0) + +#define read_unlock_irq(lock) read_unlock(lock) + +#define write_unlock(lock) rt_write_unlock(lock) + +#define write_unlock_bh(lock) \ + do { \ + rt_write_unlock(lock); \ + local_bh_enable(); \ + } while (0) + +#define write_unlock_irq(lock) write_unlock(lock) + +#define read_unlock_irqrestore(lock, flags) \ + do { \ + typecheck(unsigned long, flags); \ + (void) flags; \ + rt_read_unlock(lock); \ + } while (0) + +#define write_unlock_irqrestore(lock, flags) \ + do { \ + typecheck(unsigned long, flags); \ + (void) flags; \ + rt_write_unlock(lock); \ + } while (0) + +#define rwlock_init(rwl) \ +do { \ + static struct lock_class_key __key; \ + \ + __rt_rwlock_init(rwl, #rwl, &__key); \ +} while (0) + +#define rwlock_is_contended(lock) \ + rt_rwlock_is_contended(lock) + +#endif diff --git a/include/linux/rwlock_types.h b/include/linux/rwlock_types.h index 3bd03e18061c1..0ad226b5d8fd5 100644 --- a/include/linux/rwlock_types.h +++ b/include/linux/rwlock_types.h @@ -1,6 +1,10 @@ #ifndef __LINUX_RWLOCK_TYPES_H #define __LINUX_RWLOCK_TYPES_H +#if !defined(__LINUX_SPINLOCK_TYPES_H) +# error "Do not include directly, include spinlock_types.h" +#endif + /* * include/linux/rwlock_types.h - generic rwlock type definitions * and initializers diff --git a/include/linux/rwlock_types_rt.h b/include/linux/rwlock_types_rt.h new file mode 100644 index 0000000000000..4762391d659bf --- /dev/null +++ b/include/linux/rwlock_types_rt.h @@ -0,0 +1,56 @@ +// SPDX-License-Identifier: GPL-2.0-only +#ifndef __LINUX_RWLOCK_TYPES_RT_H +#define __LINUX_RWLOCK_TYPES_RT_H + +#ifndef __LINUX_SPINLOCK_TYPES_H +#error "Do not include directly. Include spinlock_types.h instead" +#endif + +#ifdef CONFIG_DEBUG_LOCK_ALLOC +# define RW_DEP_MAP_INIT(lockname) .dep_map = { .name = #lockname } +#else +# define RW_DEP_MAP_INIT(lockname) +#endif + +typedef struct rt_rw_lock rwlock_t; + +#define __RW_LOCK_UNLOCKED(name) __RWLOCK_RT_INITIALIZER(name) + +#define DEFINE_RWLOCK(name) \ + rwlock_t name = __RW_LOCK_UNLOCKED(name) + +/* + * A reader biased implementation primarily for CPU pinning. + * + * Can be selected as general replacement for the single reader RT rwlock + * variant + */ +struct rt_rw_lock { + struct rt_mutex rtmutex; + atomic_t readers; +#ifdef CONFIG_DEBUG_LOCK_ALLOC + struct lockdep_map dep_map; +#endif +}; + +#define READER_BIAS (1U << 31) +#define WRITER_BIAS (1U << 30) + +#define __RWLOCK_RT_INITIALIZER(name) \ +{ \ + .readers = ATOMIC_INIT(READER_BIAS), \ + .rtmutex = __RT_MUTEX_INITIALIZER_SAVE_STATE(name.rtmutex), \ + RW_DEP_MAP_INIT(name) \ +} + +void __rwlock_biased_rt_init(struct rt_rw_lock *lock, const char *name, + struct lock_class_key *key); + +#define rwlock_biased_rt_init(rwlock) \ + do { \ + static struct lock_class_key __key; \ + \ + __rwlock_biased_rt_init((rwlock), #rwlock, &__key); \ + } while (0) + +#endif diff --git a/include/linux/rwsem-rt.h b/include/linux/rwsem-rt.h new file mode 100644 index 0000000000000..0ba8aae9a1983 --- /dev/null +++ b/include/linux/rwsem-rt.h @@ -0,0 +1,70 @@ +// SPDX-License-Identifier: GPL-2.0-only +#ifndef _LINUX_RWSEM_RT_H +#define _LINUX_RWSEM_RT_H + +#ifndef _LINUX_RWSEM_H +#error "Include rwsem.h" +#endif + +#include +#include + +#define READER_BIAS (1U << 31) +#define WRITER_BIAS (1U << 30) + +struct rw_semaphore { + atomic_t readers; + struct rt_mutex rtmutex; +#ifdef CONFIG_DEBUG_LOCK_ALLOC + struct lockdep_map dep_map; +#endif +}; + +#define __RWSEM_INITIALIZER(name) \ +{ \ + .readers = ATOMIC_INIT(READER_BIAS), \ + .rtmutex = __RT_MUTEX_INITIALIZER(name.rtmutex), \ + RW_DEP_MAP_INIT(name) \ +} + +#define DECLARE_RWSEM(lockname) \ + struct rw_semaphore lockname = __RWSEM_INITIALIZER(lockname) + +extern void __rwsem_init(struct rw_semaphore *rwsem, const char *name, + struct lock_class_key *key); + +#define __init_rwsem(sem, name, key) \ +do { \ + rt_mutex_init(&(sem)->rtmutex); \ + __rwsem_init((sem), (name), (key)); \ +} while (0) + +#define init_rwsem(sem) \ +do { \ + static struct lock_class_key __key; \ + \ + __init_rwsem((sem), #sem, &__key); \ +} while (0) + +static inline int rwsem_is_locked(struct rw_semaphore *sem) +{ + return atomic_read(&sem->readers) != READER_BIAS; +} + +static inline int rwsem_is_contended(struct rw_semaphore *sem) +{ + return atomic_read(&sem->readers) > 0; +} + +extern void __down_read(struct rw_semaphore *sem); +extern int __down_read_interruptible(struct rw_semaphore *sem); +extern int __down_read_killable(struct rw_semaphore *sem); +extern int __down_read_trylock(struct rw_semaphore *sem); +extern void __down_write(struct rw_semaphore *sem); +extern int __must_check __down_write_killable(struct rw_semaphore *sem); +extern int __down_write_trylock(struct rw_semaphore *sem); +extern void __up_read(struct rw_semaphore *sem); +extern void __up_write(struct rw_semaphore *sem); +extern void __downgrade_write(struct rw_semaphore *sem); + +#endif diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h index 4c715be487171..9323af8a92445 100644 --- a/include/linux/rwsem.h +++ b/include/linux/rwsem.h @@ -16,6 +16,11 @@ #include #include #include + +#ifdef CONFIG_PREEMPT_RT +#include +#else /* PREEMPT_RT */ + #ifdef CONFIG_RWSEM_SPIN_ON_OWNER #include #endif @@ -119,6 +124,13 @@ static inline int rwsem_is_contended(struct rw_semaphore *sem) return !list_empty(&sem->wait_list); } +#endif /* !PREEMPT_RT */ + +/* + * The functions below are the same for all rwsem implementations including + * the RT specific variant. + */ + /* * lock for reading */ diff --git a/include/linux/sched.h b/include/linux/sched.h index ef00bb22164cd..635e08a5aa71a 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -14,7 +14,6 @@ #include #include #include -#include #include #include #include @@ -113,12 +112,8 @@ struct task_group; __TASK_TRACED | EXIT_DEAD | EXIT_ZOMBIE | \ TASK_PARKED) -#define task_is_traced(task) ((task->state & __TASK_TRACED) != 0) - #define task_is_stopped(task) ((task->state & __TASK_STOPPED) != 0) -#define task_is_stopped_or_traced(task) ((task->state & (__TASK_STOPPED | __TASK_TRACED)) != 0) - #ifdef CONFIG_DEBUG_ATOMIC_SLEEP /* @@ -142,6 +137,9 @@ struct task_group; smp_store_mb(current->state, (state_value)); \ } while (0) +#define __set_current_state_no_track(state_value) \ + current->state = (state_value); + #define set_special_state(state_value) \ do { \ unsigned long flags; /* may shadow */ \ @@ -195,6 +193,9 @@ struct task_group; #define set_current_state(state_value) \ smp_store_mb(current->state, (state_value)) +#define __set_current_state_no_track(state_value) \ + __set_current_state(state_value) + /* * set_special_state() should be used for those states when the blocking task * can not use the regular condition based wait-loop. In that case we must @@ -656,6 +657,8 @@ struct task_struct { #endif /* -1 unrunnable, 0 runnable, >0 stopped: */ volatile long state; + /* saved state for "spinlock sleepers" */ + volatile long saved_state; /* * This begins the randomizable portion of task_struct. Only @@ -985,11 +988,16 @@ struct task_struct { /* Signal handlers: */ struct signal_struct *signal; struct sighand_struct __rcu *sighand; + struct sigqueue *sigqueue_cache; sigset_t blocked; sigset_t real_blocked; /* Restored if set_restore_sigmask() was used: */ sigset_t saved_sigmask; struct sigpending pending; +#ifdef CONFIG_PREEMPT_RT + /* TODO: move me into ->restart_block ? */ + struct kernel_siginfo forced_info; +#endif unsigned long sas_ss_sp; size_t sas_ss_size; unsigned int sas_ss_flags; @@ -1017,6 +1025,7 @@ struct task_struct { raw_spinlock_t pi_lock; struct wake_q_node wake_q; + struct wake_q_node wake_q_sleeper; #ifdef CONFIG_RT_MUTEXES /* PI waiters blocked on a rt_mutex held by this task: */ @@ -1044,6 +1053,9 @@ struct task_struct { int softirq_context; int irq_config; #endif +#ifdef CONFIG_PREEMPT_RT + int softirq_disable_cnt; +#endif #ifdef CONFIG_LOCKDEP # define MAX_LOCK_DEPTH 48UL @@ -1778,6 +1790,7 @@ extern struct task_struct *find_get_task_by_vpid(pid_t nr); extern int wake_up_state(struct task_struct *tsk, unsigned int state); extern int wake_up_process(struct task_struct *tsk); +extern int wake_up_lock_sleeper(struct task_struct *tsk); extern void wake_up_new_task(struct task_struct *tsk); #ifdef CONFIG_SMP @@ -1868,6 +1881,89 @@ static inline int test_tsk_need_resched(struct task_struct *tsk) return unlikely(test_tsk_thread_flag(tsk,TIF_NEED_RESCHED)); } +#ifdef CONFIG_PREEMPT_LAZY +static inline void set_tsk_need_resched_lazy(struct task_struct *tsk) +{ + set_tsk_thread_flag(tsk,TIF_NEED_RESCHED_LAZY); +} + +static inline void clear_tsk_need_resched_lazy(struct task_struct *tsk) +{ + clear_tsk_thread_flag(tsk,TIF_NEED_RESCHED_LAZY); +} + +static inline int test_tsk_need_resched_lazy(struct task_struct *tsk) +{ + return unlikely(test_tsk_thread_flag(tsk,TIF_NEED_RESCHED_LAZY)); +} + +static inline int need_resched_lazy(void) +{ + return test_thread_flag(TIF_NEED_RESCHED_LAZY); +} + +static inline int need_resched_now(void) +{ + return test_thread_flag(TIF_NEED_RESCHED); +} + +#else +static inline void clear_tsk_need_resched_lazy(struct task_struct *tsk) { } +static inline int need_resched_lazy(void) { return 0; } + +static inline int need_resched_now(void) +{ + return test_thread_flag(TIF_NEED_RESCHED); +} + +#endif + + +static inline bool __task_is_stopped_or_traced(struct task_struct *task) +{ + if (task->state & (__TASK_STOPPED | __TASK_TRACED)) + return true; +#ifdef CONFIG_PREEMPT_RT + if (task->saved_state & (__TASK_STOPPED | __TASK_TRACED)) + return true; +#endif + return false; +} + +static inline bool task_is_stopped_or_traced(struct task_struct *task) +{ + bool traced_stopped; + +#ifdef CONFIG_PREEMPT_RT + unsigned long flags; + + raw_spin_lock_irqsave(&task->pi_lock, flags); + traced_stopped = __task_is_stopped_or_traced(task); + raw_spin_unlock_irqrestore(&task->pi_lock, flags); +#else + traced_stopped = __task_is_stopped_or_traced(task); +#endif + return traced_stopped; +} + +static inline bool task_is_traced(struct task_struct *task) +{ + bool traced = false; + + if (task->state & __TASK_TRACED) + return true; +#ifdef CONFIG_PREEMPT_RT + /* in case the task is sleeping on tasklist_lock */ + raw_spin_lock_irq(&task->pi_lock); + if (task->state & __TASK_TRACED) + traced = true; + else if (task->saved_state & __TASK_TRACED) + traced = true; + raw_spin_unlock_irq(&task->pi_lock); +#endif + return traced; +} + /* * cond_resched() and cond_resched_lock(): latency reduction via * explicit rescheduling in places that are safe. The return diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index 90b2a0bce11ca..22af69051d1c2 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -49,6 +49,17 @@ static inline void mmdrop(struct mm_struct *mm) __mmdrop(mm); } +#ifdef CONFIG_PREEMPT_RT +extern void __mmdrop_delayed(struct rcu_head *rhp); +static inline void mmdrop_delayed(struct mm_struct *mm) +{ + if (atomic_dec_and_test(&mm->mm_count)) + call_rcu(&mm->delayed_drop, __mmdrop_delayed); +} +#else +# define mmdrop_delayed(mm) mmdrop(mm) +#endif + /** * mmget() - Pin the address space associated with a &struct mm_struct. * @mm: The address space to pin. diff --git a/include/linux/sched/rt.h b/include/linux/sched/rt.h index e5af028c08b49..994c25640e156 100644 --- a/include/linux/sched/rt.h +++ b/include/linux/sched/rt.h @@ -39,20 +39,12 @@ static inline struct task_struct *rt_mutex_get_top_task(struct task_struct *p) } extern void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task); extern void rt_mutex_adjust_pi(struct task_struct *p); -static inline bool tsk_is_pi_blocked(struct task_struct *tsk) -{ - return tsk->pi_blocked_on != NULL; -} #else static inline struct task_struct *rt_mutex_get_top_task(struct task_struct *task) { return NULL; } # define rt_mutex_adjust_pi(p) do { } while (0) -static inline bool tsk_is_pi_blocked(struct task_struct *tsk) -{ - return false; -} #endif extern void normalize_rt_tasks(void); diff --git a/include/linux/sched/wake_q.h b/include/linux/sched/wake_q.h index 26a2013ac39c4..6e2dff721547c 100644 --- a/include/linux/sched/wake_q.h +++ b/include/linux/sched/wake_q.h @@ -58,6 +58,17 @@ static inline bool wake_q_empty(struct wake_q_head *head) extern void wake_q_add(struct wake_q_head *head, struct task_struct *task); extern void wake_q_add_safe(struct wake_q_head *head, struct task_struct *task); -extern void wake_up_q(struct wake_q_head *head); +extern void wake_q_add_sleeper(struct wake_q_head *head, struct task_struct *task); +extern void __wake_up_q(struct wake_q_head *head, bool sleeper); + +static inline void wake_up_q(struct wake_q_head *head) +{ + __wake_up_q(head, false); +} + +static inline void wake_up_q_sleeper(struct wake_q_head *head) +{ + __wake_up_q(head, true); +} #endif /* _LINUX_SCHED_WAKE_Q_H */ diff --git a/include/linux/serial_8250.h b/include/linux/serial_8250.h index 9e655055112d9..ffef674deda7d 100644 --- a/include/linux/serial_8250.h +++ b/include/linux/serial_8250.h @@ -7,6 +7,7 @@ #ifndef _LINUX_SERIAL_8250_H #define _LINUX_SERIAL_8250_H +#include #include #include #include @@ -125,6 +126,8 @@ struct uart_8250_port { #define MSR_SAVE_FLAGS UART_MSR_ANY_DELTA unsigned char msr_saved_flags; + atomic_t console_printing; + struct uart_8250_dma *dma; const struct uart_8250_ops *ops; @@ -180,6 +183,8 @@ 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, const char *s, + unsigned int count); int serial8250_console_setup(struct uart_port *port, char *options, bool probe); int serial8250_console_exit(struct uart_port *port); diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index d82b6f3965885..12b2e41d8f473 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -31,7 +31,7 @@ struct shmem_sb_info { struct percpu_counter used_blocks; /* How many are allocated */ unsigned long max_inodes; /* How many inodes are allowed */ unsigned long free_inodes; /* How many are left for allocation */ - spinlock_t stat_lock; /* Serialize shmem_sb_info changes */ + raw_spinlock_t stat_lock; /* Serialize shmem_sb_info changes */ umode_t mode; /* Mount mode for root directory */ unsigned char huge; /* Whether to try for hugepages */ kuid_t uid; /* Mount uid for root directory */ diff --git a/include/linux/signal.h b/include/linux/signal.h index 205526c4003aa..d47a86790edc8 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -265,6 +265,7 @@ static inline void init_sigpending(struct sigpending *sig) } extern void flush_sigqueue(struct sigpending *queue); +extern void flush_task_sigqueue(struct task_struct *tsk); /* Test if 'sig' is valid signal. Use this instead of testing _NSIG directly */ static inline int valid_signal(unsigned long sig) diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 6d0a33d1c0db6..3402903b5cf0f 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -295,6 +295,7 @@ struct sk_buff_head { __u32 qlen; spinlock_t lock; + raw_spinlock_t raw_lock; }; struct sk_buff; @@ -1902,6 +1903,12 @@ static inline void skb_queue_head_init(struct sk_buff_head *list) __skb_queue_head_init(list); } +static inline void skb_queue_head_init_raw(struct sk_buff_head *list) +{ + raw_spin_lock_init(&list->raw_lock); + __skb_queue_head_init(list); +} + static inline void skb_queue_head_init_class(struct sk_buff_head *list, struct lock_class_key *class) { diff --git a/include/linux/smp.h b/include/linux/smp.h index 70c6f6284dcf6..4c602ca3bc13c 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -238,6 +238,9 @@ static inline int get_boot_cpu_id(void) #define get_cpu() ({ preempt_disable(); __smp_processor_id(); }) #define put_cpu() preempt_enable() +#define get_cpu_light() ({ migrate_disable(); __smp_processor_id(); }) +#define put_cpu_light() migrate_enable() + /* * Callback to arch code if there's nosmp or maxcpus=0 on the * boot command line: diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h index 79897841a2cc8..c3c70291b46c5 100644 --- a/include/linux/spinlock.h +++ b/include/linux/spinlock.h @@ -309,7 +309,11 @@ static inline void do_raw_spin_unlock(raw_spinlock_t *lock) __releases(lock) }) /* Include rwlock functions */ -#include +#ifdef CONFIG_PREEMPT_RT +# include +#else +# include +#endif /* * Pull the _spin_*()/_read_*()/_write_*() functions/declarations: @@ -320,6 +324,10 @@ static inline void do_raw_spin_unlock(raw_spinlock_t *lock) __releases(lock) # include #endif +#ifdef CONFIG_PREEMPT_RT +# include +#else /* PREEMPT_RT */ + /* * Map the spin_lock functions to the raw variants for PREEMPT_RT=n */ @@ -454,6 +462,8 @@ static __always_inline int spin_is_contended(spinlock_t *lock) #define assert_spin_locked(lock) assert_raw_spin_locked(&(lock)->rlock) +#endif /* !PREEMPT_RT */ + /* * Pull the atomic_t declaration: * (asm-mips/atomic.h needs above definitions) diff --git a/include/linux/spinlock_api_smp.h b/include/linux/spinlock_api_smp.h index 19a9be9d97ee5..da38149f28431 100644 --- a/include/linux/spinlock_api_smp.h +++ b/include/linux/spinlock_api_smp.h @@ -187,6 +187,8 @@ static inline int __raw_spin_trylock_bh(raw_spinlock_t *lock) return 0; } -#include +#ifndef CONFIG_PREEMPT_RT +# include +#endif #endif /* __LINUX_SPINLOCK_API_SMP_H */ diff --git a/include/linux/spinlock_rt.h b/include/linux/spinlock_rt.h new file mode 100644 index 0000000000000..3085132eae383 --- /dev/null +++ b/include/linux/spinlock_rt.h @@ -0,0 +1,155 @@ +// SPDX-License-Identifier: GPL-2.0-only +#ifndef __LINUX_SPINLOCK_RT_H +#define __LINUX_SPINLOCK_RT_H + +#ifndef __LINUX_SPINLOCK_H +#error Do not include directly. Use spinlock.h +#endif + +#include + +extern void +__rt_spin_lock_init(spinlock_t *lock, const char *name, struct lock_class_key *key); + +#define spin_lock_init(slock) \ +do { \ + static struct lock_class_key __key; \ + \ + rt_mutex_init(&(slock)->lock); \ + __rt_spin_lock_init(slock, #slock, &__key); \ +} while (0) + +extern void __lockfunc rt_spin_lock(spinlock_t *lock); +extern void __lockfunc rt_spin_lock_nested(spinlock_t *lock, int subclass); +extern void __lockfunc rt_spin_lock_nest_lock(spinlock_t *lock, struct lockdep_map *nest_lock); +extern void __lockfunc rt_spin_unlock(spinlock_t *lock); +extern void __lockfunc rt_spin_lock_unlock(spinlock_t *lock); +extern int __lockfunc rt_spin_trylock_irqsave(spinlock_t *lock, unsigned long *flags); +extern int __lockfunc rt_spin_trylock_bh(spinlock_t *lock); +extern int __lockfunc rt_spin_trylock(spinlock_t *lock); +extern int atomic_dec_and_spin_lock(atomic_t *atomic, spinlock_t *lock); + +/* + * lockdep-less calls, for derived types like rwlock: + * (for trylock they can use rt_mutex_trylock() directly. + * Migrate disable handling must be done at the call site. + */ +extern void __lockfunc __rt_spin_lock(struct rt_mutex *lock); +extern void __lockfunc __rt_spin_trylock(struct rt_mutex *lock); +extern void __lockfunc __rt_spin_unlock(struct rt_mutex *lock); + +#define spin_lock(lock) rt_spin_lock(lock) + +#define spin_lock_bh(lock) \ + do { \ + local_bh_disable(); \ + rt_spin_lock(lock); \ + } while (0) + +#define spin_lock_irq(lock) spin_lock(lock) + +#define spin_do_trylock(lock) __cond_lock(lock, rt_spin_trylock(lock)) + +#define spin_trylock(lock) \ +({ \ + int __locked; \ + __locked = spin_do_trylock(lock); \ + __locked; \ +}) + +#ifdef CONFIG_LOCKDEP +# define spin_lock_nested(lock, subclass) \ + do { \ + rt_spin_lock_nested(lock, subclass); \ + } while (0) + +#define spin_lock_bh_nested(lock, subclass) \ + do { \ + local_bh_disable(); \ + rt_spin_lock_nested(lock, subclass); \ + } while (0) + +# define spin_lock_nest_lock(lock, subclass) \ + do { \ + typecheck(struct lockdep_map *, &(subclass)->dep_map); \ + rt_spin_lock_nest_lock(lock, &(subclass)->dep_map); \ + } while (0) + +# define spin_lock_irqsave_nested(lock, flags, subclass) \ + do { \ + typecheck(unsigned long, flags); \ + flags = 0; \ + rt_spin_lock_nested(lock, subclass); \ + } while (0) +#else +# define spin_lock_nested(lock, subclass) spin_lock(((void)(subclass), (lock))) +# define spin_lock_nest_lock(lock, subclass) spin_lock(((void)(subclass), (lock))) +# define spin_lock_bh_nested(lock, subclass) spin_lock_bh(((void)(subclass), (lock))) + +# define spin_lock_irqsave_nested(lock, flags, subclass) \ + do { \ + typecheck(unsigned long, flags); \ + flags = 0; \ + spin_lock(((void)(subclass), (lock))); \ + } while (0) +#endif + +#define spin_lock_irqsave(lock, flags) \ + do { \ + typecheck(unsigned long, flags); \ + flags = 0; \ + spin_lock(lock); \ + } while (0) + +#define spin_unlock(lock) rt_spin_unlock(lock) + +#define spin_unlock_bh(lock) \ + do { \ + rt_spin_unlock(lock); \ + local_bh_enable(); \ + } while (0) + +#define spin_unlock_irq(lock) spin_unlock(lock) + +#define spin_unlock_irqrestore(lock, flags) \ + do { \ + typecheck(unsigned long, flags); \ + (void) flags; \ + spin_unlock(lock); \ + } while (0) + +#define spin_trylock_bh(lock) __cond_lock(lock, rt_spin_trylock_bh(lock)) +#define spin_trylock_irq(lock) spin_trylock(lock) + +#define spin_trylock_irqsave(lock, flags) \ +({ \ + int __locked; \ + \ + typecheck(unsigned long, flags); \ + flags = 0; \ + __locked = spin_trylock(lock); \ + __locked; \ +}) + +#ifdef CONFIG_GENERIC_LOCKBREAK +# define spin_is_contended(lock) ((lock)->break_lock) +#else +# define spin_is_contended(lock) (((void)(lock), 0)) +#endif + +static inline int spin_can_lock(spinlock_t *lock) +{ + return !rt_mutex_is_locked(&lock->lock); +} + +static inline int spin_is_locked(spinlock_t *lock) +{ + return rt_mutex_is_locked(&lock->lock); +} + +static inline void assert_spin_locked(spinlock_t *lock) +{ + BUG_ON(!spin_is_locked(lock)); +} + +#endif diff --git a/include/linux/spinlock_types.h b/include/linux/spinlock_types.h index b981caafe8bf1..8d896d3e1a017 100644 --- a/include/linux/spinlock_types.h +++ b/include/linux/spinlock_types.h @@ -9,93 +9,15 @@ * Released under the General Public License (GPL). */ -#if defined(CONFIG_SMP) -# include +#include + +#ifndef CONFIG_PREEMPT_RT +# include +# include #else -# include +# include +# include +# include #endif -#include - -typedef struct raw_spinlock { - arch_spinlock_t raw_lock; -#ifdef CONFIG_DEBUG_SPINLOCK - unsigned int magic, owner_cpu; - void *owner; -#endif -#ifdef CONFIG_DEBUG_LOCK_ALLOC - struct lockdep_map dep_map; -#endif -} raw_spinlock_t; - -#define SPINLOCK_MAGIC 0xdead4ead - -#define SPINLOCK_OWNER_INIT ((void *)-1L) - -#ifdef CONFIG_DEBUG_LOCK_ALLOC -# define RAW_SPIN_DEP_MAP_INIT(lockname) \ - .dep_map = { \ - .name = #lockname, \ - .wait_type_inner = LD_WAIT_SPIN, \ - } -# define SPIN_DEP_MAP_INIT(lockname) \ - .dep_map = { \ - .name = #lockname, \ - .wait_type_inner = LD_WAIT_CONFIG, \ - } -#else -# define RAW_SPIN_DEP_MAP_INIT(lockname) -# define SPIN_DEP_MAP_INIT(lockname) -#endif - -#ifdef CONFIG_DEBUG_SPINLOCK -# define SPIN_DEBUG_INIT(lockname) \ - .magic = SPINLOCK_MAGIC, \ - .owner_cpu = -1, \ - .owner = SPINLOCK_OWNER_INIT, -#else -# define SPIN_DEBUG_INIT(lockname) -#endif - -#define __RAW_SPIN_LOCK_INITIALIZER(lockname) \ - { \ - .raw_lock = __ARCH_SPIN_LOCK_UNLOCKED, \ - SPIN_DEBUG_INIT(lockname) \ - RAW_SPIN_DEP_MAP_INIT(lockname) } - -#define __RAW_SPIN_LOCK_UNLOCKED(lockname) \ - (raw_spinlock_t) __RAW_SPIN_LOCK_INITIALIZER(lockname) - -#define DEFINE_RAW_SPINLOCK(x) raw_spinlock_t x = __RAW_SPIN_LOCK_UNLOCKED(x) - -typedef struct spinlock { - union { - struct raw_spinlock rlock; - -#ifdef CONFIG_DEBUG_LOCK_ALLOC -# define LOCK_PADSIZE (offsetof(struct raw_spinlock, dep_map)) - struct { - u8 __padding[LOCK_PADSIZE]; - struct lockdep_map dep_map; - }; -#endif - }; -} spinlock_t; - -#define ___SPIN_LOCK_INITIALIZER(lockname) \ - { \ - .raw_lock = __ARCH_SPIN_LOCK_UNLOCKED, \ - SPIN_DEBUG_INIT(lockname) \ - SPIN_DEP_MAP_INIT(lockname) } - -#define __SPIN_LOCK_INITIALIZER(lockname) \ - { { .rlock = ___SPIN_LOCK_INITIALIZER(lockname) } } - -#define __SPIN_LOCK_UNLOCKED(lockname) \ - (spinlock_t) __SPIN_LOCK_INITIALIZER(lockname) - -#define DEFINE_SPINLOCK(x) spinlock_t x = __SPIN_LOCK_UNLOCKED(x) - -#include - #endif /* __LINUX_SPINLOCK_TYPES_H */ diff --git a/include/linux/spinlock_types_nort.h b/include/linux/spinlock_types_nort.h new file mode 100644 index 0000000000000..e4549f0dd197b --- /dev/null +++ b/include/linux/spinlock_types_nort.h @@ -0,0 +1,39 @@ +#ifndef __LINUX_SPINLOCK_TYPES_NORT_H +#define __LINUX_SPINLOCK_TYPES_NORT_H + +#ifndef __LINUX_SPINLOCK_TYPES_H +#error "Do not include directly. Include spinlock_types.h instead" +#endif + +/* + * The non RT version maps spinlocks to raw_spinlocks + */ +typedef struct spinlock { + union { + struct raw_spinlock rlock; + +#ifdef CONFIG_DEBUG_LOCK_ALLOC +# define LOCK_PADSIZE (offsetof(struct raw_spinlock, dep_map)) + struct { + u8 __padding[LOCK_PADSIZE]; + struct lockdep_map dep_map; + }; +#endif + }; +} spinlock_t; + +#define ___SPIN_LOCK_INITIALIZER(lockname) \ +{ \ + .raw_lock = __ARCH_SPIN_LOCK_UNLOCKED, \ + SPIN_DEBUG_INIT(lockname) \ + SPIN_DEP_MAP_INIT(lockname) } + +#define __SPIN_LOCK_INITIALIZER(lockname) \ + { { .rlock = ___SPIN_LOCK_INITIALIZER(lockname) } } + +#define __SPIN_LOCK_UNLOCKED(lockname) \ + (spinlock_t) __SPIN_LOCK_INITIALIZER(lockname) + +#define DEFINE_SPINLOCK(x) spinlock_t x = __SPIN_LOCK_UNLOCKED(x) + +#endif diff --git a/include/linux/spinlock_types_raw.h b/include/linux/spinlock_types_raw.h new file mode 100644 index 0000000000000..1d4a180e983d7 --- /dev/null +++ b/include/linux/spinlock_types_raw.h @@ -0,0 +1,65 @@ +#ifndef __LINUX_SPINLOCK_TYPES_RAW_H +#define __LINUX_SPINLOCK_TYPES_RAW_H + +#include + +#if defined(CONFIG_SMP) +# include +#else +# include +#endif + +#include + +typedef struct raw_spinlock { + arch_spinlock_t raw_lock; +#ifdef CONFIG_DEBUG_SPINLOCK + unsigned int magic, owner_cpu; + void *owner; +#endif +#ifdef CONFIG_DEBUG_LOCK_ALLOC + struct lockdep_map dep_map; +#endif +} raw_spinlock_t; + +#define SPINLOCK_MAGIC 0xdead4ead + +#define SPINLOCK_OWNER_INIT ((void *)-1L) + +#ifdef CONFIG_DEBUG_LOCK_ALLOC +# define RAW_SPIN_DEP_MAP_INIT(lockname) \ + .dep_map = { \ + .name = #lockname, \ + .wait_type_inner = LD_WAIT_SPIN, \ + } +# define SPIN_DEP_MAP_INIT(lockname) \ + .dep_map = { \ + .name = #lockname, \ + .wait_type_inner = LD_WAIT_CONFIG, \ + } +#else +# define RAW_SPIN_DEP_MAP_INIT(lockname) +# define SPIN_DEP_MAP_INIT(lockname) +#endif + +#ifdef CONFIG_DEBUG_SPINLOCK +# define SPIN_DEBUG_INIT(lockname) \ + .magic = SPINLOCK_MAGIC, \ + .owner_cpu = -1, \ + .owner = SPINLOCK_OWNER_INIT, +#else +# define SPIN_DEBUG_INIT(lockname) +#endif + +#define __RAW_SPIN_LOCK_INITIALIZER(lockname) \ +{ \ + .raw_lock = __ARCH_SPIN_LOCK_UNLOCKED, \ + SPIN_DEBUG_INIT(lockname) \ + RAW_SPIN_DEP_MAP_INIT(lockname) } + +#define __RAW_SPIN_LOCK_UNLOCKED(lockname) \ + (raw_spinlock_t) __RAW_SPIN_LOCK_INITIALIZER(lockname) + +#define DEFINE_RAW_SPINLOCK(x) raw_spinlock_t x = __RAW_SPIN_LOCK_UNLOCKED(x) + +#endif diff --git a/include/linux/spinlock_types_rt.h b/include/linux/spinlock_types_rt.h new file mode 100644 index 0000000000000..446da786e5d5c --- /dev/null +++ b/include/linux/spinlock_types_rt.h @@ -0,0 +1,38 @@ +// SPDX-License-Identifier: GPL-2.0-only +#ifndef __LINUX_SPINLOCK_TYPES_RT_H +#define __LINUX_SPINLOCK_TYPES_RT_H + +#ifndef __LINUX_SPINLOCK_TYPES_H +#error "Do not include directly. Include spinlock_types.h instead" +#endif + +#include + +/* + * PREEMPT_RT: spinlocks - an RT mutex plus lock-break field: + */ +typedef struct spinlock { + struct rt_mutex lock; + unsigned int break_lock; +#ifdef CONFIG_DEBUG_LOCK_ALLOC + struct lockdep_map dep_map; +#endif +} spinlock_t; + +#define __RT_SPIN_INITIALIZER(name) \ + { \ + .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(name.wait_lock), \ + .save_state = 1, \ + } +/* +.wait_list = PLIST_HEAD_INIT_RAW((name).lock.wait_list, (name).lock.wait_lock) +*/ + +#define __SPIN_LOCK_UNLOCKED(name) \ + { .lock = __RT_SPIN_INITIALIZER(name.lock), \ + SPIN_DEP_MAP_INIT(name) } + +#define DEFINE_SPINLOCK(name) \ + spinlock_t name = __SPIN_LOCK_UNLOCKED(name) + +#endif diff --git a/include/linux/spinlock_types_up.h b/include/linux/spinlock_types_up.h index c09b6407ae1b3..d9b371fa13e09 100644 --- a/include/linux/spinlock_types_up.h +++ b/include/linux/spinlock_types_up.h @@ -1,7 +1,7 @@ #ifndef __LINUX_SPINLOCK_TYPES_UP_H #define __LINUX_SPINLOCK_TYPES_UP_H -#ifndef __LINUX_SPINLOCK_TYPES_H +#if !defined(__LINUX_SPINLOCK_TYPES_H) && !defined(__LINUX_RT_MUTEX_H) # error "please don't include this file directly" #endif diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h index 9b2158c69275e..8d1cac4052f20 100644 --- a/include/linux/thread_info.h +++ b/include/linux/thread_info.h @@ -149,7 +149,17 @@ static inline int test_ti_thread_flag(struct thread_info *ti, int flag) clear_ti_thread_flag(task_thread_info(t), TIF_##fl) #endif /* !CONFIG_GENERIC_ENTRY */ -#define tif_need_resched() test_thread_flag(TIF_NEED_RESCHED) +#ifdef CONFIG_PREEMPT_LAZY +#define tif_need_resched() (test_thread_flag(TIF_NEED_RESCHED) || \ + test_thread_flag(TIF_NEED_RESCHED_LAZY)) +#define tif_need_resched_now() (test_thread_flag(TIF_NEED_RESCHED)) +#define tif_need_resched_lazy() test_thread_flag(TIF_NEED_RESCHED_LAZY) + +#else +#define tif_need_resched() test_thread_flag(TIF_NEED_RESCHED) +#define tif_need_resched_now() test_thread_flag(TIF_NEED_RESCHED) +#define tif_need_resched_lazy() 0 +#endif #ifndef CONFIG_HAVE_ARCH_WITHIN_STACK_FRAMES static inline int arch_within_stack_frames(const void * const stack, diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 28e7af1406f28..9e4bc12bb8265 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -69,6 +69,8 @@ struct trace_entry { unsigned char flags; unsigned char preempt_count; int pid; + unsigned char migrate_disable; + unsigned char preempt_lazy_count; }; #define TRACE_EVENT_TYPE_MAX \ @@ -157,9 +159,11 @@ static inline void tracing_generic_entry_update(struct trace_entry *entry, unsigned int trace_ctx) { entry->preempt_count = trace_ctx & 0xff; + entry->migrate_disable = (trace_ctx >> 8) & 0xff; + entry->preempt_lazy_count = (trace_ctx >> 16) & 0xff; entry->pid = current->pid; entry->type = type; - entry->flags = trace_ctx >> 16; + entry->flags = trace_ctx >> 24; } unsigned int tracing_gen_ctx_irq_test(unsigned int irqs_status); @@ -172,6 +176,7 @@ enum trace_flag_type { TRACE_FLAG_SOFTIRQ = 0x10, TRACE_FLAG_PREEMPT_RESCHED = 0x20, TRACE_FLAG_NMI = 0x40, + TRACE_FLAG_NEED_RESCHED_LAZY = 0x80, }; #ifdef CONFIG_TRACE_IRQFLAGS_SUPPORT diff --git a/include/linux/u64_stats_sync.h b/include/linux/u64_stats_sync.h index e81856c0ba134..66eb968a09d49 100644 --- a/include/linux/u64_stats_sync.h +++ b/include/linux/u64_stats_sync.h @@ -66,7 +66,7 @@ #include struct u64_stats_sync { -#if BITS_PER_LONG==32 && defined(CONFIG_SMP) +#if BITS_PER_LONG==32 && (defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT)) seqcount_t seq; #endif }; @@ -115,7 +115,7 @@ static inline void u64_stats_inc(u64_stats_t *p) } #endif -#if BITS_PER_LONG == 32 && defined(CONFIG_SMP) +#if BITS_PER_LONG == 32 && (defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT)) #define u64_stats_init(syncp) seqcount_init(&(syncp)->seq) #else static inline void u64_stats_init(struct u64_stats_sync *syncp) @@ -125,15 +125,19 @@ static inline void u64_stats_init(struct u64_stats_sync *syncp) static inline void u64_stats_update_begin(struct u64_stats_sync *syncp) { -#if BITS_PER_LONG==32 && defined(CONFIG_SMP) +#if BITS_PER_LONG == 32 && (defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT)) + if (IS_ENABLED(CONFIG_PREEMPT_RT)) + preempt_disable(); write_seqcount_begin(&syncp->seq); #endif } static inline void u64_stats_update_end(struct u64_stats_sync *syncp) { -#if BITS_PER_LONG==32 && defined(CONFIG_SMP) +#if BITS_PER_LONG == 32 && (defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT)) write_seqcount_end(&syncp->seq); + if (IS_ENABLED(CONFIG_PREEMPT_RT)) + preempt_enable(); #endif } @@ -142,8 +146,11 @@ u64_stats_update_begin_irqsave(struct u64_stats_sync *syncp) { unsigned long flags = 0; -#if BITS_PER_LONG==32 && defined(CONFIG_SMP) - local_irq_save(flags); +#if BITS_PER_LONG == 32 && (defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT)) + if (IS_ENABLED(CONFIG_PREEMPT_RT)) + preempt_disable(); + else + local_irq_save(flags); write_seqcount_begin(&syncp->seq); #endif return flags; @@ -153,15 +160,18 @@ static inline void u64_stats_update_end_irqrestore(struct u64_stats_sync *syncp, unsigned long flags) { -#if BITS_PER_LONG==32 && defined(CONFIG_SMP) +#if BITS_PER_LONG == 32 && (defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT)) write_seqcount_end(&syncp->seq); - local_irq_restore(flags); + if (IS_ENABLED(CONFIG_PREEMPT_RT)) + preempt_enable(); + else + local_irq_restore(flags); #endif } static inline unsigned int __u64_stats_fetch_begin(const struct u64_stats_sync *syncp) { -#if BITS_PER_LONG==32 && defined(CONFIG_SMP) +#if BITS_PER_LONG == 32 && (defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT)) return read_seqcount_begin(&syncp->seq); #else return 0; @@ -170,7 +180,7 @@ static inline unsigned int __u64_stats_fetch_begin(const struct u64_stats_sync * static inline unsigned int u64_stats_fetch_begin(const struct u64_stats_sync *syncp) { -#if BITS_PER_LONG==32 && !defined(CONFIG_SMP) +#if BITS_PER_LONG == 32 && (!defined(CONFIG_SMP) && !defined(CONFIG_PREEMPT_RT)) preempt_disable(); #endif return __u64_stats_fetch_begin(syncp); @@ -179,7 +189,7 @@ static inline unsigned int u64_stats_fetch_begin(const struct u64_stats_sync *sy static inline bool __u64_stats_fetch_retry(const struct u64_stats_sync *syncp, unsigned int start) { -#if BITS_PER_LONG==32 && defined(CONFIG_SMP) +#if BITS_PER_LONG == 32 && (defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT)) return read_seqcount_retry(&syncp->seq, start); #else return false; @@ -189,7 +199,7 @@ static inline bool __u64_stats_fetch_retry(const struct u64_stats_sync *syncp, static inline bool u64_stats_fetch_retry(const struct u64_stats_sync *syncp, unsigned int start) { -#if BITS_PER_LONG==32 && !defined(CONFIG_SMP) +#if BITS_PER_LONG == 32 && (!defined(CONFIG_SMP) && !defined(CONFIG_PREEMPT_RT)) preempt_enable(); #endif return __u64_stats_fetch_retry(syncp, start); @@ -203,7 +213,9 @@ static inline bool u64_stats_fetch_retry(const struct u64_stats_sync *syncp, */ static inline unsigned int u64_stats_fetch_begin_irq(const struct u64_stats_sync *syncp) { -#if BITS_PER_LONG==32 && !defined(CONFIG_SMP) +#if BITS_PER_LONG == 32 && defined(CONFIG_PREEMPT_RT) + preempt_disable(); +#elif BITS_PER_LONG == 32 && !defined(CONFIG_SMP) local_irq_disable(); #endif return __u64_stats_fetch_begin(syncp); @@ -212,7 +224,9 @@ static inline unsigned int u64_stats_fetch_begin_irq(const struct u64_stats_sync static inline bool u64_stats_fetch_retry_irq(const struct u64_stats_sync *syncp, unsigned int start) { -#if BITS_PER_LONG==32 && !defined(CONFIG_SMP) +#if BITS_PER_LONG == 32 && defined(CONFIG_PREEMPT_RT) + preempt_enable(); +#elif BITS_PER_LONG == 32 && !defined(CONFIG_SMP) local_irq_enable(); #endif return __u64_stats_fetch_retry(syncp, start); diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index 506d625163a11..09a7e4c714b8c 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -63,7 +63,9 @@ DECLARE_PER_CPU(struct vm_event_state, vm_event_states); */ static inline void __count_vm_event(enum vm_event_item item) { + preempt_disable_rt(); raw_cpu_inc(vm_event_states.event[item]); + preempt_enable_rt(); } static inline void count_vm_event(enum vm_event_item item) @@ -73,7 +75,9 @@ static inline void count_vm_event(enum vm_event_item item) static inline void __count_vm_events(enum vm_event_item item, long delta) { + preempt_disable_rt(); raw_cpu_add(vm_event_states.event[item], delta); + preempt_enable_rt(); } static inline void count_vm_events(enum vm_event_item item, long delta) diff --git a/include/linux/wait.h b/include/linux/wait.h index fe10e8570a522..e9ce878a49069 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -10,6 +10,7 @@ #include #include +#include typedef struct wait_queue_entry wait_queue_entry_t; diff --git a/include/linux/ww_mutex.h b/include/linux/ww_mutex.h index 850424e5d0306..8ef2feb0d8fef 100644 --- a/include/linux/ww_mutex.h +++ b/include/linux/ww_mutex.h @@ -28,6 +28,14 @@ struct ww_class { unsigned int is_wait_die; }; +struct ww_mutex { + struct mutex base; + struct ww_acquire_ctx *ctx; +#ifdef CONFIG_DEBUG_MUTEXES + struct ww_class *ww_class; +#endif +}; + struct ww_acquire_ctx { struct task_struct *task; unsigned long stamp; diff --git a/include/net/gen_stats.h b/include/net/gen_stats.h index 1424e02cef90c..163f8415e5db5 100644 --- a/include/net/gen_stats.h +++ b/include/net/gen_stats.h @@ -6,6 +6,7 @@ #include #include #include +#include /* Note: this used to be in include/uapi/linux/gen_stats.h */ struct gnet_stats_basic_packed { @@ -42,15 +43,15 @@ int gnet_stats_start_copy_compat(struct sk_buff *skb, int type, spinlock_t *lock, struct gnet_dump *d, int padattr); -int gnet_stats_copy_basic(const seqcount_t *running, +int gnet_stats_copy_basic(net_seqlock_t *running, struct gnet_dump *d, struct gnet_stats_basic_cpu __percpu *cpu, struct gnet_stats_basic_packed *b); -void __gnet_stats_copy_basic(const seqcount_t *running, +void __gnet_stats_copy_basic(net_seqlock_t *running, struct gnet_stats_basic_packed *bstats, struct gnet_stats_basic_cpu __percpu *cpu, struct gnet_stats_basic_packed *b); -int gnet_stats_copy_basic_hw(const seqcount_t *running, +int gnet_stats_copy_basic_hw(net_seqlock_t *running, struct gnet_dump *d, struct gnet_stats_basic_cpu __percpu *cpu, struct gnet_stats_basic_packed *b); @@ -70,13 +71,13 @@ int gen_new_estimator(struct gnet_stats_basic_packed *bstats, struct gnet_stats_basic_cpu __percpu *cpu_bstats, struct net_rate_estimator __rcu **rate_est, spinlock_t *lock, - seqcount_t *running, struct nlattr *opt); + net_seqlock_t *running, struct nlattr *opt); void gen_kill_estimator(struct net_rate_estimator __rcu **ptr); int gen_replace_estimator(struct gnet_stats_basic_packed *bstats, struct gnet_stats_basic_cpu __percpu *cpu_bstats, struct net_rate_estimator __rcu **ptr, spinlock_t *lock, - seqcount_t *running, struct nlattr *opt); + net_seqlock_t *running, struct nlattr *opt); bool gen_estimator_active(struct net_rate_estimator __rcu **ptr); bool gen_estimator_read(struct net_rate_estimator __rcu **ptr, struct gnet_stats_rate_est64 *sample); diff --git a/include/net/net_seq_lock.h b/include/net/net_seq_lock.h new file mode 100644 index 0000000000000..67710bace7418 --- /dev/null +++ b/include/net/net_seq_lock.h @@ -0,0 +1,15 @@ +#ifndef __NET_NET_SEQ_LOCK_H__ +#define __NET_NET_SEQ_LOCK_H__ + +#ifdef CONFIG_PREEMPT_RT +# define net_seqlock_t seqlock_t +# define net_seq_begin(__r) read_seqbegin(__r) +# define net_seq_retry(__r, __s) read_seqretry(__r, __s) + +#else +# define net_seqlock_t seqcount_t +# define net_seq_begin(__r) read_seqcount_begin(__r) +# define net_seq_retry(__r, __s) read_seqcount_retry(__r, __s) +#endif + +#endif diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 2d6eb60c58c81..bf0865d642f54 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -10,6 +10,7 @@ #include #include #include +#include #include #include #include @@ -100,7 +101,7 @@ struct Qdisc { struct sk_buff_head gso_skb ____cacheline_aligned_in_smp; struct qdisc_skb_head q; struct gnet_stats_basic_packed bstats; - seqcount_t running; + net_seqlock_t running; struct gnet_stats_queue qstats; unsigned long state; struct Qdisc *next_sched; @@ -141,7 +142,11 @@ static inline bool qdisc_is_running(struct Qdisc *qdisc) { if (qdisc->flags & TCQ_F_NOLOCK) return spin_is_locked(&qdisc->seqlock); +#ifdef CONFIG_PREEMPT_RT + return spin_is_locked(&qdisc->running.lock) ? true : false; +#else return (raw_read_seqcount(&qdisc->running) & 1) ? true : false; +#endif } static inline bool qdisc_is_percpu_stats(const struct Qdisc *q) @@ -165,17 +170,35 @@ static inline bool qdisc_run_begin(struct Qdisc *qdisc) } else if (qdisc_is_running(qdisc)) { return false; } +#ifdef CONFIG_PREEMPT_RT + if (spin_trylock(&qdisc->running.lock)) { + seqcount_t *s = &qdisc->running.seqcount.seqcount; + /* + * Variant of write_seqcount_t_begin() telling lockdep that a + * trylock was attempted. + */ + do_raw_write_seqcount_begin(s); + seqcount_acquire(&s->dep_map, 0, 1, _RET_IP_); + return true; + } + return false; +#else /* Variant of write_seqcount_begin() telling lockdep a trylock * was attempted. */ raw_write_seqcount_begin(&qdisc->running); seqcount_acquire(&qdisc->running.dep_map, 0, 1, _RET_IP_); return true; +#endif } static inline void qdisc_run_end(struct Qdisc *qdisc) { +#ifdef CONFIG_PREEMPT_RT + write_sequnlock(&qdisc->running); +#else write_seqcount_end(&qdisc->running); +#endif if (qdisc->flags & TCQ_F_NOLOCK) spin_unlock(&qdisc->seqlock); } @@ -540,7 +563,7 @@ static inline spinlock_t *qdisc_root_sleeping_lock(const struct Qdisc *qdisc) return qdisc_lock(root); } -static inline seqcount_t *qdisc_root_sleeping_running(const struct Qdisc *qdisc) +static inline net_seqlock_t *qdisc_root_sleeping_running(const struct Qdisc *qdisc) { struct Qdisc *root = qdisc_root_sleeping(qdisc); diff --git a/init/Kconfig b/init/Kconfig index 5f5c776ef1921..45f2231c71319 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -973,6 +973,7 @@ config CFS_BANDWIDTH config RT_GROUP_SCHED bool "Group scheduling for SCHED_RR/FIFO" depends on CGROUP_SCHED + depends on !PREEMPT_RT default n help This feature lets you explicitly allocate real CPU bandwidth @@ -1886,6 +1887,7 @@ choice config SLAB bool "SLAB" + depends on !PREEMPT_RT select HAVE_HARDENED_USERCOPY_ALLOCATOR help The regular slab allocator that is established and known to work @@ -1906,6 +1908,7 @@ config SLUB config SLOB depends on EXPERT bool "SLOB (Simple Allocator)" + depends on !PREEMPT_RT help SLOB replaces the stock allocator with a drastically simpler allocator. SLOB is generally more space efficient but @@ -1971,7 +1974,7 @@ config SHUFFLE_PAGE_ALLOCATOR Say Y if unsure. config SLUB_CPU_PARTIAL - default y + default y if !PREEMPT_RT depends on SLUB && SMP bool "SLUB per cpu partial cache" help diff --git a/init/main.c b/init/main.c index 53b278845b886..ff77379e2316e 100644 --- a/init/main.c +++ b/init/main.c @@ -1499,6 +1499,12 @@ void __init console_on_rootfs(void) fput(file); } +#ifdef CONFIG_PROVE_RCU +void rcu_tasks_initiate_self_tests(void); +#else +static inline void rcu_tasks_initiate_self_tests(void) {} +#endif + static noinline void __init kernel_init_freeable(void) { /* @@ -1524,6 +1530,7 @@ static noinline void __init kernel_init_freeable(void) rcu_init_tasks_generic(); do_pre_smp_initcalls(); + rcu_tasks_initiate_self_tests(); lockup_detector_init(); smp_init(); diff --git a/kernel/Kconfig.locks b/kernel/Kconfig.locks index 3de8fd11873b4..4198f0273ecdc 100644 --- a/kernel/Kconfig.locks +++ b/kernel/Kconfig.locks @@ -251,7 +251,7 @@ config ARCH_USE_QUEUED_RWLOCKS config QUEUED_RWLOCKS def_bool y if ARCH_USE_QUEUED_RWLOCKS - depends on SMP + depends on SMP && !PREEMPT_RT config ARCH_HAS_MMIOWB bool diff --git a/kernel/Kconfig.preempt b/kernel/Kconfig.preempt index 4160173016605..90837a6cb2e8a 100644 --- a/kernel/Kconfig.preempt +++ b/kernel/Kconfig.preempt @@ -1,5 +1,11 @@ # SPDX-License-Identifier: GPL-2.0-only +config HAVE_PREEMPT_LAZY + bool + +config PREEMPT_LAZY + def_bool y if HAVE_PREEMPT_LAZY && PREEMPT_RT + choice prompt "Preemption Model" default PREEMPT_NONE @@ -60,6 +66,7 @@ config PREEMPT_RT bool "Fully Preemptible Kernel (Real-Time)" depends on EXPERT && ARCH_SUPPORTS_RT select PREEMPTION + select RT_MUTEXES help This option turns the kernel into a real-time kernel by replacing various locking primitives (spinlocks, rwlocks, etc.) with diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 5258b68153e03..fb8715c1edfcc 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -345,7 +345,7 @@ void cpuset_read_unlock(void) percpu_up_read(&cpuset_rwsem); } -static DEFINE_SPINLOCK(callback_lock); +static DEFINE_RAW_SPINLOCK(callback_lock); static struct workqueue_struct *cpuset_migrate_mm_wq; @@ -1280,7 +1280,7 @@ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd, * Newly added CPUs will be removed from effective_cpus and * newly deleted ones will be added back to effective_cpus. */ - spin_lock_irq(&callback_lock); + raw_spin_lock_irq(&callback_lock); if (adding) { cpumask_or(parent->subparts_cpus, parent->subparts_cpus, tmp->addmask); @@ -1299,7 +1299,7 @@ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd, } parent->nr_subparts_cpus = cpumask_weight(parent->subparts_cpus); - spin_unlock_irq(&callback_lock); + raw_spin_unlock_irq(&callback_lock); return cmd == partcmd_update; } @@ -1404,7 +1404,7 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp) continue; rcu_read_unlock(); - spin_lock_irq(&callback_lock); + raw_spin_lock_irq(&callback_lock); cpumask_copy(cp->effective_cpus, tmp->new_cpus); if (cp->nr_subparts_cpus && @@ -1435,7 +1435,7 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp) = cpumask_weight(cp->subparts_cpus); } } - spin_unlock_irq(&callback_lock); + raw_spin_unlock_irq(&callback_lock); WARN_ON(!is_in_v2_mode() && !cpumask_equal(cp->cpus_allowed, cp->effective_cpus)); @@ -1553,7 +1553,7 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs, return -EINVAL; } - spin_lock_irq(&callback_lock); + raw_spin_lock_irq(&callback_lock); cpumask_copy(cs->cpus_allowed, trialcs->cpus_allowed); /* @@ -1564,7 +1564,7 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs, cs->cpus_allowed); cs->nr_subparts_cpus = cpumask_weight(cs->subparts_cpus); } - spin_unlock_irq(&callback_lock); + raw_spin_unlock_irq(&callback_lock); update_cpumasks_hier(cs, &tmp); @@ -1758,9 +1758,9 @@ static void update_nodemasks_hier(struct cpuset *cs, nodemask_t *new_mems) continue; rcu_read_unlock(); - spin_lock_irq(&callback_lock); + raw_spin_lock_irq(&callback_lock); cp->effective_mems = *new_mems; - spin_unlock_irq(&callback_lock); + raw_spin_unlock_irq(&callback_lock); WARN_ON(!is_in_v2_mode() && !nodes_equal(cp->mems_allowed, cp->effective_mems)); @@ -1828,9 +1828,9 @@ static int update_nodemask(struct cpuset *cs, struct cpuset *trialcs, if (retval < 0) goto done; - spin_lock_irq(&callback_lock); + raw_spin_lock_irq(&callback_lock); cs->mems_allowed = trialcs->mems_allowed; - spin_unlock_irq(&callback_lock); + raw_spin_unlock_irq(&callback_lock); /* use trialcs->mems_allowed as a temp variable */ update_nodemasks_hier(cs, &trialcs->mems_allowed); @@ -1921,9 +1921,9 @@ static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs, spread_flag_changed = ((is_spread_slab(cs) != is_spread_slab(trialcs)) || (is_spread_page(cs) != is_spread_page(trialcs))); - spin_lock_irq(&callback_lock); + raw_spin_lock_irq(&callback_lock); cs->flags = trialcs->flags; - spin_unlock_irq(&callback_lock); + raw_spin_unlock_irq(&callback_lock); if (!cpumask_empty(trialcs->cpus_allowed) && balance_flag_changed) rebuild_sched_domains_locked(); @@ -2432,7 +2432,7 @@ static int cpuset_common_seq_show(struct seq_file *sf, void *v) cpuset_filetype_t type = seq_cft(sf)->private; int ret = 0; - spin_lock_irq(&callback_lock); + raw_spin_lock_irq(&callback_lock); switch (type) { case FILE_CPULIST: @@ -2454,7 +2454,7 @@ static int cpuset_common_seq_show(struct seq_file *sf, void *v) ret = -EINVAL; } - spin_unlock_irq(&callback_lock); + raw_spin_unlock_irq(&callback_lock); return ret; } @@ -2767,14 +2767,14 @@ static int cpuset_css_online(struct cgroup_subsys_state *css) cpuset_inc(); - spin_lock_irq(&callback_lock); + raw_spin_lock_irq(&callback_lock); if (is_in_v2_mode()) { cpumask_copy(cs->effective_cpus, parent->effective_cpus); cs->effective_mems = parent->effective_mems; cs->use_parent_ecpus = true; parent->child_ecpus_count++; } - spin_unlock_irq(&callback_lock); + raw_spin_unlock_irq(&callback_lock); if (!test_bit(CGRP_CPUSET_CLONE_CHILDREN, &css->cgroup->flags)) goto out_unlock; @@ -2801,12 +2801,12 @@ static int cpuset_css_online(struct cgroup_subsys_state *css) } rcu_read_unlock(); - spin_lock_irq(&callback_lock); + raw_spin_lock_irq(&callback_lock); cs->mems_allowed = parent->mems_allowed; cs->effective_mems = parent->mems_allowed; cpumask_copy(cs->cpus_allowed, parent->cpus_allowed); cpumask_copy(cs->effective_cpus, parent->cpus_allowed); - spin_unlock_irq(&callback_lock); + raw_spin_unlock_irq(&callback_lock); out_unlock: percpu_up_write(&cpuset_rwsem); put_online_cpus(); @@ -2862,7 +2862,7 @@ static void cpuset_css_free(struct cgroup_subsys_state *css) static void cpuset_bind(struct cgroup_subsys_state *root_css) { percpu_down_write(&cpuset_rwsem); - spin_lock_irq(&callback_lock); + raw_spin_lock_irq(&callback_lock); if (is_in_v2_mode()) { cpumask_copy(top_cpuset.cpus_allowed, cpu_possible_mask); @@ -2873,7 +2873,7 @@ static void cpuset_bind(struct cgroup_subsys_state *root_css) top_cpuset.mems_allowed = top_cpuset.effective_mems; } - spin_unlock_irq(&callback_lock); + raw_spin_unlock_irq(&callback_lock); percpu_up_write(&cpuset_rwsem); } @@ -2970,12 +2970,12 @@ hotplug_update_tasks_legacy(struct cpuset *cs, { bool is_empty; - spin_lock_irq(&callback_lock); + raw_spin_lock_irq(&callback_lock); cpumask_copy(cs->cpus_allowed, new_cpus); cpumask_copy(cs->effective_cpus, new_cpus); cs->mems_allowed = *new_mems; cs->effective_mems = *new_mems; - spin_unlock_irq(&callback_lock); + raw_spin_unlock_irq(&callback_lock); /* * Don't call update_tasks_cpumask() if the cpuset becomes empty, @@ -3012,10 +3012,10 @@ hotplug_update_tasks(struct cpuset *cs, if (nodes_empty(*new_mems)) *new_mems = parent_cs(cs)->effective_mems; - spin_lock_irq(&callback_lock); + raw_spin_lock_irq(&callback_lock); cpumask_copy(cs->effective_cpus, new_cpus); cs->effective_mems = *new_mems; - spin_unlock_irq(&callback_lock); + raw_spin_unlock_irq(&callback_lock); if (cpus_updated) update_tasks_cpumask(cs); @@ -3170,7 +3170,7 @@ static void cpuset_hotplug_workfn(struct work_struct *work) /* synchronize cpus_allowed to cpu_active_mask */ if (cpus_updated) { - spin_lock_irq(&callback_lock); + raw_spin_lock_irq(&callback_lock); if (!on_dfl) cpumask_copy(top_cpuset.cpus_allowed, &new_cpus); /* @@ -3190,17 +3190,17 @@ static void cpuset_hotplug_workfn(struct work_struct *work) } } cpumask_copy(top_cpuset.effective_cpus, &new_cpus); - spin_unlock_irq(&callback_lock); + raw_spin_unlock_irq(&callback_lock); /* we don't mess with cpumasks of tasks in top_cpuset */ } /* synchronize mems_allowed to N_MEMORY */ if (mems_updated) { - spin_lock_irq(&callback_lock); + raw_spin_lock_irq(&callback_lock); if (!on_dfl) top_cpuset.mems_allowed = new_mems; top_cpuset.effective_mems = new_mems; - spin_unlock_irq(&callback_lock); + raw_spin_unlock_irq(&callback_lock); update_tasks_nodemask(&top_cpuset); } @@ -3301,11 +3301,11 @@ void cpuset_cpus_allowed(struct task_struct *tsk, struct cpumask *pmask) { unsigned long flags; - spin_lock_irqsave(&callback_lock, flags); + raw_spin_lock_irqsave(&callback_lock, flags); rcu_read_lock(); guarantee_online_cpus(task_cs(tsk), pmask); rcu_read_unlock(); - spin_unlock_irqrestore(&callback_lock, flags); + raw_spin_unlock_irqrestore(&callback_lock, flags); } /** @@ -3366,11 +3366,11 @@ nodemask_t cpuset_mems_allowed(struct task_struct *tsk) nodemask_t mask; unsigned long flags; - spin_lock_irqsave(&callback_lock, flags); + raw_spin_lock_irqsave(&callback_lock, flags); rcu_read_lock(); guarantee_online_mems(task_cs(tsk), &mask); rcu_read_unlock(); - spin_unlock_irqrestore(&callback_lock, flags); + raw_spin_unlock_irqrestore(&callback_lock, flags); return mask; } @@ -3462,14 +3462,14 @@ bool __cpuset_node_allowed(int node, gfp_t gfp_mask) return true; /* Not hardwall and node outside mems_allowed: scan up cpusets */ - spin_lock_irqsave(&callback_lock, flags); + raw_spin_lock_irqsave(&callback_lock, flags); rcu_read_lock(); cs = nearest_hardwall_ancestor(task_cs(current)); allowed = node_isset(node, cs->mems_allowed); rcu_read_unlock(); - spin_unlock_irqrestore(&callback_lock, flags); + raw_spin_unlock_irqrestore(&callback_lock, flags); return allowed; } diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c index d51175cedfca4..b424f3157b345 100644 --- a/kernel/cgroup/rstat.c +++ b/kernel/cgroup/rstat.c @@ -149,8 +149,9 @@ static void cgroup_rstat_flush_locked(struct cgroup *cgrp, bool may_sleep) raw_spinlock_t *cpu_lock = per_cpu_ptr(&cgroup_rstat_cpu_lock, cpu); struct cgroup *pos = NULL; + unsigned long flags; - raw_spin_lock(cpu_lock); + raw_spin_lock_irqsave(cpu_lock, flags); while ((pos = cgroup_rstat_cpu_pop_updated(pos, cgrp, cpu))) { struct cgroup_subsys_state *css; @@ -162,7 +163,7 @@ static void cgroup_rstat_flush_locked(struct cgroup *cgrp, bool may_sleep) css->ss->css_rstat_flush(css, cpu); rcu_read_unlock(); } - raw_spin_unlock(cpu_lock); + raw_spin_unlock_irqrestore(cpu_lock, flags); /* if @may_sleep, play nice and yield if necessary */ if (may_sleep && (need_resched() || diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c index 4708aec492df9..8a073198c4e80 100644 --- a/kernel/debug/debug_core.c +++ b/kernel/debug/debug_core.c @@ -241,35 +241,42 @@ NOKPROBE_SYMBOL(kgdb_call_nmi_hook); static DEFINE_PER_CPU(call_single_data_t, kgdb_roundup_csd) = CSD_INIT(kgdb_call_nmi_hook, NULL); -void __weak kgdb_roundup_cpus(void) +void __weak kgdb_roundup_cpu(unsigned int cpu) { call_single_data_t *csd; + int ret; + + csd = &per_cpu(kgdb_roundup_csd, cpu); + + /* + * If it didn't round up last time, don't try again + * since smp_call_function_single_async() will block. + * + * If rounding_up is false then we know that the + * previous call must have at least started and that + * means smp_call_function_single_async() won't block. + */ + if (kgdb_info[cpu].rounding_up) + return; + kgdb_info[cpu].rounding_up = true; + + ret = smp_call_function_single_async(cpu, csd); + if (ret) + kgdb_info[cpu].rounding_up = false; +} +NOKPROBE_SYMBOL(kgdb_roundup_cpu); + +void __weak kgdb_roundup_cpus(void) +{ int this_cpu = raw_smp_processor_id(); int cpu; - int ret; for_each_online_cpu(cpu) { /* No need to roundup ourselves */ if (cpu == this_cpu) continue; - csd = &per_cpu(kgdb_roundup_csd, cpu); - - /* - * If it didn't round up last time, don't try again - * since smp_call_function_single_async() will block. - * - * If rounding_up is false then we know that the - * previous call must have at least started and that - * means smp_call_function_single_async() won't block. - */ - if (kgdb_info[cpu].rounding_up) - continue; - kgdb_info[cpu].rounding_up = true; - - ret = smp_call_function_single_async(cpu, csd); - if (ret) - kgdb_info[cpu].rounding_up = false; + kgdb_roundup_cpu(cpu); } } NOKPROBE_SYMBOL(kgdb_roundup_cpus); diff --git a/kernel/debug/kdb/kdb_io.c b/kernel/debug/kdb/kdb_io.c index 6735ac36b7187..539a2f0dc89d9 100644 --- a/kernel/debug/kdb/kdb_io.c +++ b/kernel/debug/kdb/kdb_io.c @@ -559,23 +559,17 @@ static void kdb_msg_write(const char *msg, int msg_len) cp++; } + /* mirror output on atomic consoles */ for_each_console(c) { if (!(c->flags & CON_ENABLED)) continue; if (c == dbg_io_ops->cons) continue; - /* - * Set oops_in_progress to encourage the console drivers to - * disregard their internal spin locks: in the current calling - * context the risk of deadlock is a bigger problem than risks - * due to re-entering the console driver. We operate directly on - * oops_in_progress rather than using bust_spinlocks() because - * the calls bust_spinlocks() makes on exit are not appropriate - * for this calling context. - */ - ++oops_in_progress; - c->write(c, msg, msg_len); - --oops_in_progress; + + if (!c->write_atomic) + continue; + c->write_atomic(c, msg, msg_len); + touch_nmi_watchdog(); } } diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c index 930ac1b25ec7c..67d9f2403b52f 100644 --- a/kernel/debug/kdb/kdb_main.c +++ b/kernel/debug/kdb/kdb_main.c @@ -2101,7 +2101,7 @@ static int kdb_dmesg(int argc, const char **argv) int adjust = 0; int n = 0; int skip = 0; - struct kmsg_dumper dumper = { .active = 1 }; + struct kmsg_dump_iter iter; size_t len; char buf[201]; @@ -2126,8 +2126,8 @@ static int kdb_dmesg(int argc, const char **argv) kdb_set(2, setargs); } - kmsg_dump_rewind_nolock(&dumper); - while (kmsg_dump_get_line_nolock(&dumper, 1, NULL, 0, NULL)) + kmsg_dump_rewind(&iter); + while (kmsg_dump_get_line(&iter, 1, NULL, 0, NULL)) n++; if (lines < 0) { @@ -2159,8 +2159,8 @@ static int kdb_dmesg(int argc, const char **argv) if (skip >= n || skip < 0) return 0; - kmsg_dump_rewind_nolock(&dumper); - while (kmsg_dump_get_line_nolock(&dumper, 1, buf, sizeof(buf), &len)) { + kmsg_dump_rewind(&iter); + while (kmsg_dump_get_line(&iter, 1, buf, sizeof(buf), &len)) { if (skip) { skip--; continue; diff --git a/kernel/entry/common.c b/kernel/entry/common.c index 8442e5c9cfa26..16b4356494bca 100644 --- a/kernel/entry/common.c +++ b/kernel/entry/common.c @@ -158,9 +158,17 @@ static 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_MASK) schedule(); +#ifdef ARCH_RT_DELAYS_SIGNAL_SEND + if (unlikely(current->forced_info.si_signo)) { + struct task_struct *t = current; + force_sig_info(&t->forced_info); + t->forced_info.si_signo = 0; + } +#endif + if (ti_work & _TIF_UPROBE) uprobe_notify_resume(regs); @@ -388,7 +396,7 @@ void irqentry_exit_cond_resched(void) rcu_irq_exit_check_preempt(); if (IS_ENABLED(CONFIG_DEBUG_ENTRY)) WARN_ON_ONCE(!on_thread_stack()); - if (need_resched()) + if (should_resched(0)) preempt_schedule_irq(); } } diff --git a/kernel/exit.c b/kernel/exit.c index 04029e35e69af..346f7b76cecaa 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -152,7 +152,7 @@ static void __exit_signal(struct task_struct *tsk) * Do this under ->siglock, we can race with another thread * doing sigqueue_free() if we have SIGQUEUE_PREALLOC signals. */ - flush_sigqueue(&tsk->pending); + flush_task_sigqueue(tsk); tsk->sighand = NULL; spin_unlock(&sighand->siglock); diff --git a/kernel/fork.c b/kernel/fork.c index 0acc8ed1076b7..1b1a5cf4089d8 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -42,6 +42,7 @@ #include #include #include +#include #include #include #include @@ -288,7 +289,7 @@ static inline void free_thread_stack(struct task_struct *tsk) return; } - vfree_atomic(tsk->stack); + vfree(tsk->stack); return; } #endif @@ -689,6 +690,19 @@ void __mmdrop(struct mm_struct *mm) } EXPORT_SYMBOL_GPL(__mmdrop); +#ifdef CONFIG_PREEMPT_RT +/* + * RCU callback for delayed mm drop. Not strictly rcu, but we don't + * want another facility to make this work. + */ +void __mmdrop_delayed(struct rcu_head *rhp) +{ + struct mm_struct *mm = container_of(rhp, struct mm_struct, delayed_drop); + + __mmdrop(mm); +} +#endif + static void mmdrop_async_fn(struct work_struct *work) { struct mm_struct *mm; @@ -730,6 +744,15 @@ void __put_task_struct(struct task_struct *tsk) WARN_ON(refcount_read(&tsk->usage)); WARN_ON(tsk == current); + /* + * Remove function-return probe instances associated with this + * task and put them back on the free list. + */ + kprobe_flush_task(tsk); + + /* Task is done with its stack. */ + put_task_stack(tsk); + io_uring_free(tsk); cgroup_free(tsk); task_numa_free(tsk, true); @@ -927,6 +950,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node) tsk->splice_pipe = NULL; tsk->task_frag.page = NULL; tsk->wake_q.next = NULL; + tsk->wake_q_sleeper.next = NULL; account_kernel_stack(tsk, 1); @@ -2003,6 +2027,7 @@ static __latent_entropy struct task_struct *copy_process( spin_lock_init(&p->alloc_lock); init_sigpending(&p->pending); + p->sigqueue_cache = NULL; p->utime = p->stime = p->gtime = 0; #ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME diff --git a/kernel/futex.c b/kernel/futex.c index e68db77450392..93961549dc4cc 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -1497,6 +1497,7 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_pi_state *pi_ struct task_struct *new_owner; bool postunlock = false; DEFINE_WAKE_Q(wake_q); + DEFINE_WAKE_Q(wake_sleeper_q); int ret = 0; new_owner = rt_mutex_next_owner(&pi_state->pi_mutex); @@ -1546,14 +1547,15 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_pi_state *pi_ * not fail. */ pi_state_update_owner(pi_state, new_owner); - postunlock = __rt_mutex_futex_unlock(&pi_state->pi_mutex, &wake_q); + postunlock = __rt_mutex_futex_unlock(&pi_state->pi_mutex, &wake_q, + &wake_sleeper_q); } out_unlock: raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock); if (postunlock) - rt_mutex_postunlock(&wake_q); + rt_mutex_postunlock(&wake_q, &wake_sleeper_q); return ret; } @@ -2154,6 +2156,16 @@ static int futex_requeue(u32 __user *uaddr1, unsigned int flags, */ requeue_pi_wake_futex(this, &key2, hb2); continue; + } else if (ret == -EAGAIN) { + /* + * Waiter was woken by timeout or + * signal and has set pi_blocked_on to + * PI_WAKEUP_INPROGRESS before we + * tried to enqueue it on the rtmutex. + */ + this->pi_state = NULL; + put_pi_state(pi_state); + continue; } else if (ret) { /* * rt_mutex_start_proxy_lock() detected a @@ -2847,7 +2859,7 @@ static int futex_lock_pi(u32 __user *uaddr, unsigned int flags, goto no_block; } - rt_mutex_init_waiter(&rt_waiter); + rt_mutex_init_waiter(&rt_waiter, false); /* * On PREEMPT_RT_FULL, when hb->lock becomes an rt_mutex, we must not @@ -3171,7 +3183,7 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, { struct hrtimer_sleeper timeout, *to; struct rt_mutex_waiter rt_waiter; - struct futex_hash_bucket *hb; + struct futex_hash_bucket *hb, *hb2; union futex_key key2 = FUTEX_KEY_INIT; struct futex_q q = futex_q_init; int res, ret; @@ -3192,7 +3204,7 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, * The waiter is allocated on our stack, manipulated by the requeue * code while we sleep on uaddr. */ - rt_mutex_init_waiter(&rt_waiter); + rt_mutex_init_waiter(&rt_waiter, false); ret = get_futex_key(uaddr2, flags & FLAGS_SHARED, &key2, FUTEX_WRITE); if (unlikely(ret != 0)) @@ -3223,20 +3235,55 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, /* Queue the futex_q, drop the hb lock, wait for wakeup. */ futex_wait_queue_me(hb, &q, to); - spin_lock(&hb->lock); - ret = handle_early_requeue_pi_wakeup(hb, &q, &key2, to); - spin_unlock(&hb->lock); - if (ret) - goto out; + /* + * On RT we must avoid races with requeue and trying to block + * on two mutexes (hb->lock and uaddr2's rtmutex) by + * serializing access to pi_blocked_on with pi_lock. + */ + raw_spin_lock_irq(¤t->pi_lock); + if (current->pi_blocked_on) { + /* + * We have been requeued or are in the process of + * being requeued. + */ + raw_spin_unlock_irq(¤t->pi_lock); + } else { + /* + * Setting pi_blocked_on to PI_WAKEUP_INPROGRESS + * prevents a concurrent requeue from moving us to the + * uaddr2 rtmutex. After that we can safely acquire + * (and possibly block on) hb->lock. + */ + current->pi_blocked_on = PI_WAKEUP_INPROGRESS; + raw_spin_unlock_irq(¤t->pi_lock); + + spin_lock(&hb->lock); + + /* + * Clean up pi_blocked_on. We might leak it otherwise + * when we succeeded with the hb->lock in the fast + * path. + */ + raw_spin_lock_irq(¤t->pi_lock); + current->pi_blocked_on = NULL; + raw_spin_unlock_irq(¤t->pi_lock); + + ret = handle_early_requeue_pi_wakeup(hb, &q, &key2, to); + spin_unlock(&hb->lock); + if (ret) + goto out; + } /* - * In order for us to be here, we know our q.key == key2, and since - * we took the hb->lock above, we also know that futex_requeue() has - * completed and we no longer have to concern ourselves with a wakeup - * race with the atomic proxy lock acquisition by the requeue code. The - * futex_requeue dropped our key1 reference and incremented our key2 - * reference count. + * In order to be here, we have either been requeued, are in + * the process of being requeued, or requeue successfully + * acquired uaddr2 on our behalf. If pi_blocked_on was + * non-null above, we may be racing with a requeue. Do not + * rely on q->lock_ptr to be hb2->lock until after blocking on + * hb->lock or hb2->lock. The futex_requeue dropped our key1 + * reference and incremented our key2 reference count. */ + hb2 = hash_futex(&key2); /* Check if the requeue code acquired the second futex for us. */ if (!q.rt_waiter) { @@ -3245,14 +3292,16 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, * did a lock-steal - fix up the PI-state in that case. */ if (q.pi_state && (q.pi_state->owner != current)) { - spin_lock(q.lock_ptr); + spin_lock(&hb2->lock); + BUG_ON(&hb2->lock != q.lock_ptr); ret = fixup_pi_state_owner(uaddr2, &q, current); /* * Drop the reference to the pi state which * the requeue_pi() code acquired for us. */ put_pi_state(q.pi_state); - spin_unlock(q.lock_ptr); + spin_unlock(&hb2->lock); + /* * Adjust the return value. It's either -EFAULT or * success (1) but the caller expects 0 for success. @@ -3271,7 +3320,8 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, pi_mutex = &q.pi_state->pi_mutex; ret = rt_mutex_wait_proxy_lock(pi_mutex, to, &rt_waiter); - spin_lock(q.lock_ptr); + spin_lock(&hb2->lock); + BUG_ON(&hb2->lock != q.lock_ptr); if (ret && !rt_mutex_cleanup_proxy_lock(pi_mutex, &rt_waiter)) ret = 0; diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c index 762a928e18f92..7929fcdb78174 100644 --- a/kernel/irq/handle.c +++ b/kernel/irq/handle.c @@ -192,10 +192,16 @@ irqreturn_t handle_irq_event_percpu(struct irq_desc *desc) { irqreturn_t retval; unsigned int flags = 0; + struct pt_regs *regs = get_irq_regs(); + u64 ip = regs ? instruction_pointer(regs) : 0; retval = __handle_irq_event_percpu(desc, &flags); - add_interrupt_randomness(desc->irq_data.irq, flags); +#ifdef CONFIG_PREEMPT_RT + desc->random_ip = ip; +#else + add_interrupt_randomness(desc->irq_data.irq, flags, ip); +#endif if (!noirqdebug) note_interrupt(desc, retval); diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index dec3f73e8db92..b279a8683c385 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -1225,6 +1225,8 @@ static int irq_thread(void *data) irqreturn_t (*handler_fn)(struct irq_desc *desc, struct irqaction *action); + sched_set_fifo(current); + if (force_irqthreads && test_bit(IRQTF_FORCED_THREAD, &action->thread_flags)) handler_fn = irq_forced_thread_fn; @@ -1245,6 +1247,12 @@ static int irq_thread(void *data) if (action_ret == IRQ_WAKE_THREAD) irq_wake_secondary(desc, action); + if (IS_ENABLED(CONFIG_PREEMPT_RT)) { + migrate_disable(); + add_interrupt_randomness(action->irq, 0, + desc->random_ip ^ (unsigned long) action); + migrate_enable(); + } wake_threads_waitq(desc); } @@ -1390,8 +1398,6 @@ setup_irq_thread(struct irqaction *new, unsigned int irq, bool secondary) if (IS_ERR(t)) return PTR_ERR(t); - sched_set_fifo(t); - /* * We keep the reference to the task struct even if * the thread dies to avoid that the interrupt code @@ -2781,7 +2787,7 @@ EXPORT_SYMBOL_GPL(irq_get_irqchip_state); * This call sets the internal irqchip state of an interrupt, * depending on the value of @which. * - * This function should be called with preemption disabled if the + * This function should be called with migration disabled if the * interrupt controller has per-cpu registers. */ int irq_set_irqchip_state(unsigned int irq, enum irqchip_irq_state which, diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c index f865e5f4d3825..dc7311dd74b11 100644 --- a/kernel/irq/spurious.c +++ b/kernel/irq/spurious.c @@ -443,6 +443,10 @@ MODULE_PARM_DESC(noirqdebug, "Disable irq lockup detection when true"); static int __init irqfixup_setup(char *str) { +#ifdef CONFIG_PREEMPT_RT + pr_warn("irqfixup boot option not supported w/ CONFIG_PREEMPT_RT\n"); + return 1; +#endif irqfixup = 1; printk(KERN_WARNING "Misrouted IRQ fixup support enabled.\n"); printk(KERN_WARNING "This may impact system performance.\n"); @@ -455,6 +459,10 @@ module_param(irqfixup, int, 0644); static int __init irqpoll_setup(char *str) { +#ifdef CONFIG_PREEMPT_RT + pr_warn("irqpoll boot option not supported w/ CONFIG_PREEMPT_RT\n"); + return 1; +#endif irqfixup = 2; printk(KERN_WARNING "Misrouted IRQ fixup and polling support " "enabled\n"); diff --git a/kernel/irq_work.c b/kernel/irq_work.c index e8da1e71583a1..c3455910196f6 100644 --- a/kernel/irq_work.c +++ b/kernel/irq_work.c @@ -18,6 +18,7 @@ #include #include #include +#include #include @@ -52,13 +53,27 @@ void __weak arch_irq_work_raise(void) /* Enqueue on current CPU, work must already be claimed and preempt disabled */ static void __irq_work_queue_local(struct irq_work *work) { - /* If the work is "lazy", handle it from next tick if any */ - if (atomic_read(&work->node.a_flags) & IRQ_WORK_LAZY) { - if (llist_add(&work->node.llist, this_cpu_ptr(&lazy_list)) && - tick_nohz_tick_stopped()) - arch_irq_work_raise(); - } else { - if (llist_add(&work->node.llist, this_cpu_ptr(&raised_list))) + struct llist_head *list; + bool lazy_work; + int work_flags; + + work_flags = atomic_read(&work->node.a_flags); + if (work_flags & IRQ_WORK_LAZY) + lazy_work = true; + else if (IS_ENABLED(CONFIG_PREEMPT_RT) && + !(work_flags & IRQ_WORK_HARD_IRQ)) + lazy_work = true; + else + lazy_work = false; + + if (lazy_work) + list = this_cpu_ptr(&lazy_list); + else + list = this_cpu_ptr(&raised_list); + + if (llist_add(&work->node.llist, list)) { + /* If the work is "lazy", handle it from next tick if any */ + if (!lazy_work || tick_nohz_tick_stopped()) arch_irq_work_raise(); } } @@ -102,7 +117,14 @@ bool irq_work_queue_on(struct irq_work *work, int cpu) if (cpu != smp_processor_id()) { /* Arch remote IPI send/receive backend aren't NMI safe */ WARN_ON_ONCE(in_nmi()); - __smp_call_single_queue(cpu, &work->node.llist); + + if (IS_ENABLED(CONFIG_PREEMPT_RT) && !(atomic_read(&work->node.a_flags) & IRQ_WORK_HARD_IRQ)) { + if (llist_add(&work->node.llist, &per_cpu(lazy_list, cpu))) + /* && tick_nohz_tick_stopped_cpu(cpu) */ + arch_send_call_function_single_ipi(cpu); + } else { + __smp_call_single_queue(cpu, &work->node.llist); + } } else { __irq_work_queue_local(work); } @@ -120,9 +142,8 @@ bool irq_work_needs_cpu(void) raised = this_cpu_ptr(&raised_list); lazy = this_cpu_ptr(&lazy_list); - if (llist_empty(raised) || arch_irq_work_has_interrupt()) - if (llist_empty(lazy)) - return false; + if (llist_empty(raised) && llist_empty(lazy)) + return false; /* All work should have been flushed before going offline */ WARN_ON_ONCE(cpu_is_offline(smp_processor_id())); @@ -165,8 +186,12 @@ static void irq_work_run_list(struct llist_head *list) struct irq_work *work, *tmp; struct llist_node *llnode; +#ifndef CONFIG_PREEMPT_RT + /* + * nort: On RT IRQ-work may run in SOFTIRQ context. + */ BUG_ON(!irqs_disabled()); - +#endif if (llist_empty(list)) return; @@ -182,7 +207,16 @@ static void irq_work_run_list(struct llist_head *list) void irq_work_run(void) { irq_work_run_list(this_cpu_ptr(&raised_list)); - irq_work_run_list(this_cpu_ptr(&lazy_list)); + if (IS_ENABLED(CONFIG_PREEMPT_RT)) { + /* + * NOTE: we raise softirq via IPI for safety, + * and execute in irq_work_tick() to move the + * overhead from hard to soft irq context. + */ + if (!llist_empty(this_cpu_ptr(&lazy_list))) + raise_softirq(TIMER_SOFTIRQ); + } else + irq_work_run_list(this_cpu_ptr(&lazy_list)); } EXPORT_SYMBOL_GPL(irq_work_run); @@ -192,8 +226,17 @@ void irq_work_tick(void) if (!llist_empty(raised) && !arch_irq_work_has_interrupt()) irq_work_run_list(raised); + + if (!IS_ENABLED(CONFIG_PREEMPT_RT)) + irq_work_run_list(this_cpu_ptr(&lazy_list)); +} + +#if defined(CONFIG_IRQ_WORK) && defined(CONFIG_PREEMPT_RT) +void irq_work_tick_soft(void) +{ irq_work_run_list(this_cpu_ptr(&lazy_list)); } +#endif /* * Synchronize against the irq_work @entry, ensures the entry is not diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c index a0b6780740c8a..480d5f77ef4f6 100644 --- a/kernel/kexec_core.c +++ b/kernel/kexec_core.c @@ -977,7 +977,6 @@ void crash_kexec(struct pt_regs *regs) old_cpu = atomic_cmpxchg(&panic_cpu, PANIC_CPU_INVALID, this_cpu); if (old_cpu == PANIC_CPU_INVALID) { /* This is the 1st CPU which comes here, so go ahead. */ - printk_safe_flush_on_panic(); __crash_kexec(regs); /* diff --git a/kernel/ksysfs.c b/kernel/ksysfs.c index 35859da8bd4f7..dfff31ed644a6 100644 --- a/kernel/ksysfs.c +++ b/kernel/ksysfs.c @@ -138,6 +138,15 @@ KERNEL_ATTR_RO(vmcoreinfo); #endif /* CONFIG_CRASH_CORE */ +#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) @@ -228,6 +237,9 @@ 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 }; diff --git a/kernel/kthread.c b/kernel/kthread.c index 1578973c57409..bb0602597ffd0 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -243,6 +243,7 @@ EXPORT_SYMBOL_GPL(kthread_parkme); static int kthread(void *_create) { + static const struct sched_param param = { .sched_priority = 0 }; /* Copy data: it's on kthread's stack */ struct kthread_create_info *create = _create; int (*threadfn)(void *data) = create->threadfn; @@ -273,6 +274,13 @@ static int kthread(void *_create) init_completion(&self->parked); current->vfork_done = &self->exited; + /* + * The new thread inherited kthreadd's priority and CPU mask. Reset + * back to default in case they have been changed. + */ + sched_setscheduler_nocheck(current, SCHED_NORMAL, ¶m); + set_cpus_allowed_ptr(current, housekeeping_cpumask(HK_FLAG_KTHREAD)); + /* OK, tell user we're spawned, wait for stop or wakeup */ __set_current_state(TASK_UNINTERRUPTIBLE); create->result = current; @@ -370,7 +378,6 @@ struct task_struct *__kthread_create_on_node(int (*threadfn)(void *data), } task = create->result; if (!IS_ERR(task)) { - static const struct sched_param param = { .sched_priority = 0 }; char name[TASK_COMM_LEN]; /* @@ -379,13 +386,6 @@ struct task_struct *__kthread_create_on_node(int (*threadfn)(void *data), */ vsnprintf(name, sizeof(name), namefmt, args); set_task_comm(task, name); - /* - * root may have changed our (kthreadd's) priority or CPU mask. - * The kernel thread should not inherit these properties. - */ - sched_setscheduler_nocheck(task, SCHED_NORMAL, ¶m); - set_cpus_allowed_ptr(task, - housekeeping_cpumask(HK_FLAG_KTHREAD)); } kfree(create); return task; diff --git a/kernel/locking/Makefile b/kernel/locking/Makefile index 8838f1d7c4a2e..b4bdab93e2fc9 100644 --- a/kernel/locking/Makefile +++ b/kernel/locking/Makefile @@ -3,7 +3,7 @@ # and is generally not a function of system call inputs. KCOV_INSTRUMENT := n -obj-y += mutex.o semaphore.o rwsem.o percpu-rwsem.o +obj-y += semaphore.o rwsem.o percpu-rwsem.o # Avoid recursion lockdep -> KCSAN -> ... -> lockdep. KCSAN_SANITIZE_lockdep.o := n @@ -16,19 +16,23 @@ CFLAGS_REMOVE_rtmutex-debug.o = $(CC_FLAGS_FTRACE) endif obj-$(CONFIG_DEBUG_IRQFLAGS) += irqflag-debug.o -obj-$(CONFIG_DEBUG_MUTEXES) += mutex-debug.o obj-$(CONFIG_LOCKDEP) += lockdep.o ifeq ($(CONFIG_PROC_FS),y) obj-$(CONFIG_LOCKDEP) += lockdep_proc.o endif obj-$(CONFIG_SMP) += spinlock.o -obj-$(CONFIG_LOCK_SPIN_ON_OWNER) += osq_lock.o obj-$(CONFIG_PROVE_LOCKING) += spinlock.o obj-$(CONFIG_QUEUED_SPINLOCKS) += qspinlock.o obj-$(CONFIG_RT_MUTEXES) += rtmutex.o obj-$(CONFIG_DEBUG_RT_MUTEXES) += rtmutex-debug.o obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock.o obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock_debug.o +ifneq ($(CONFIG_PREEMPT_RT),y) +obj-y += mutex.o +obj-$(CONFIG_LOCK_SPIN_ON_OWNER) += osq_lock.o +obj-$(CONFIG_DEBUG_MUTEXES) += mutex-debug.o +endif +obj-$(CONFIG_PREEMPT_RT) += mutex-rt.o rwsem-rt.o rwlock-rt.o obj-$(CONFIG_QUEUED_RWLOCKS) += qrwlock.o obj-$(CONFIG_LOCK_TORTURE_TEST) += locktorture.o obj-$(CONFIG_WW_MUTEX_SELFTEST) += test-ww_mutex.o diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index c6d0c1dc62532..1cc1c962bc280 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -5358,6 +5358,7 @@ static noinstr void check_flags(unsigned long flags) } } +#ifndef CONFIG_PREEMPT_RT /* * We dont accurately track softirq state in e.g. * hardirq contexts (such as on 4KSTACKS), so only @@ -5372,6 +5373,7 @@ static noinstr void check_flags(unsigned long flags) DEBUG_LOCKS_WARN_ON(!current->softirqs_enabled); } } +#endif if (!debug_locks) print_irqtrace_events(current); diff --git a/kernel/locking/mutex-rt.c b/kernel/locking/mutex-rt.c new file mode 100644 index 0000000000000..2b849e6b9b4ae --- /dev/null +++ b/kernel/locking/mutex-rt.c @@ -0,0 +1,224 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Real-Time Preemption Support + * + * started by Ingo Molnar: + * + * Copyright (C) 2004-2006 Red Hat, Inc., Ingo Molnar + * Copyright (C) 2006, Timesys Corp., Thomas Gleixner + * + * historic credit for proving that Linux spinlocks can be implemented via + * RT-aware mutexes goes to many people: The Pmutex project (Dirk Grambow + * and others) who prototyped it on 2.4 and did lots of comparative + * research and analysis; TimeSys, for proving that you can implement a + * fully preemptible kernel via the use of IRQ threading and mutexes; + * Bill Huey for persuasively arguing on lkml that the mutex model is the + * right one; and to MontaVista, who ported pmutexes to 2.6. + * + * This code is a from-scratch implementation and is not based on pmutexes, + * but the idea of converting spinlocks to mutexes is used here too. + * + * lock debugging, locking tree, deadlock detection: + * + * Copyright (C) 2004, LynuxWorks, Inc., Igor Manyilov, Bill Huey + * Released under the General Public License (GPL). + * + * Includes portions of the generic R/W semaphore implementation from: + * + * Copyright (c) 2001 David Howells (dhowells@redhat.com). + * - Derived partially from idea by Andrea Arcangeli + * - Derived also from comments by Linus + * + * Pending ownership of locks and ownership stealing: + * + * Copyright (C) 2005, Kihon Technologies Inc., Steven Rostedt + * + * (also by Steven Rostedt) + * - Converted single pi_lock to individual task locks. + * + * By Esben Nielsen: + * Doing priority inheritance with help of the scheduler. + * + * Copyright (C) 2006, Timesys Corp., Thomas Gleixner + * - major rework based on Esben Nielsens initial patch + * - replaced thread_info references by task_struct refs + * - removed task->pending_owner dependency + * - BKL drop/reacquire for semaphore style locks to avoid deadlocks + * in the scheduler return path as discussed with Steven Rostedt + * + * Copyright (C) 2006, Kihon Technologies Inc. + * Steven Rostedt + * - debugged and patched Thomas Gleixner's rework. + * - added back the cmpxchg to the rework. + * - turned atomic require back on for SMP. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "rtmutex_common.h" + +/* + * struct mutex functions + */ +void __mutex_do_init(struct mutex *mutex, const char *name, + struct lock_class_key *key) +{ +#ifdef CONFIG_DEBUG_LOCK_ALLOC + /* + * Make sure we are not reinitializing a held lock: + */ + debug_check_no_locks_freed((void *)mutex, sizeof(*mutex)); + lockdep_init_map(&mutex->dep_map, name, key, 0); +#endif + mutex->lock.save_state = 0; +} +EXPORT_SYMBOL(__mutex_do_init); + +static int _mutex_lock_blk_flush(struct mutex *lock, int state) +{ + /* + * Flush blk before ->pi_blocked_on is set. At schedule() time it is too + * late if one of the callbacks needs to acquire a sleeping lock. + */ + if (blk_needs_flush_plug(current)) + blk_schedule_flush_plug(current); + return __rt_mutex_lock_state(&lock->lock, state); +} + +void __lockfunc _mutex_lock(struct mutex *lock) +{ + mutex_acquire(&lock->dep_map, 0, 0, _RET_IP_); + _mutex_lock_blk_flush(lock, TASK_UNINTERRUPTIBLE); +} +EXPORT_SYMBOL(_mutex_lock); + +void __lockfunc _mutex_lock_io_nested(struct mutex *lock, int subclass) +{ + int token; + + token = io_schedule_prepare(); + + mutex_acquire_nest(&lock->dep_map, subclass, 0, NULL, _RET_IP_); + __rt_mutex_lock_state(&lock->lock, TASK_UNINTERRUPTIBLE); + + io_schedule_finish(token); +} +EXPORT_SYMBOL_GPL(_mutex_lock_io_nested); + +int __lockfunc _mutex_lock_interruptible(struct mutex *lock) +{ + int ret; + + mutex_acquire(&lock->dep_map, 0, 0, _RET_IP_); + ret = _mutex_lock_blk_flush(lock, TASK_INTERRUPTIBLE); + if (ret) + mutex_release(&lock->dep_map, _RET_IP_); + return ret; +} +EXPORT_SYMBOL(_mutex_lock_interruptible); + +int __lockfunc _mutex_lock_killable(struct mutex *lock) +{ + int ret; + + mutex_acquire(&lock->dep_map, 0, 0, _RET_IP_); + ret = _mutex_lock_blk_flush(lock, TASK_KILLABLE); + if (ret) + mutex_release(&lock->dep_map, _RET_IP_); + return ret; +} +EXPORT_SYMBOL(_mutex_lock_killable); + +#ifdef CONFIG_DEBUG_LOCK_ALLOC +void __lockfunc _mutex_lock_nested(struct mutex *lock, int subclass) +{ + mutex_acquire_nest(&lock->dep_map, subclass, 0, NULL, _RET_IP_); + _mutex_lock_blk_flush(lock, TASK_UNINTERRUPTIBLE); +} +EXPORT_SYMBOL(_mutex_lock_nested); + +void __lockfunc _mutex_lock_nest_lock(struct mutex *lock, struct lockdep_map *nest) +{ + mutex_acquire_nest(&lock->dep_map, 0, 0, nest, _RET_IP_); + _mutex_lock_blk_flush(lock, TASK_UNINTERRUPTIBLE); +} +EXPORT_SYMBOL(_mutex_lock_nest_lock); + +int __lockfunc _mutex_lock_interruptible_nested(struct mutex *lock, int subclass) +{ + int ret; + + mutex_acquire_nest(&lock->dep_map, subclass, 0, NULL, _RET_IP_); + ret = _mutex_lock_blk_flush(lock, TASK_INTERRUPTIBLE); + if (ret) + mutex_release(&lock->dep_map, _RET_IP_); + return ret; +} +EXPORT_SYMBOL(_mutex_lock_interruptible_nested); + +int __lockfunc _mutex_lock_killable_nested(struct mutex *lock, int subclass) +{ + int ret; + + mutex_acquire(&lock->dep_map, subclass, 0, _RET_IP_); + ret = _mutex_lock_blk_flush(lock, TASK_KILLABLE); + if (ret) + mutex_release(&lock->dep_map, _RET_IP_); + return ret; +} +EXPORT_SYMBOL(_mutex_lock_killable_nested); +#endif + +int __lockfunc _mutex_trylock(struct mutex *lock) +{ + int ret = __rt_mutex_trylock(&lock->lock); + + if (ret) + mutex_acquire(&lock->dep_map, 0, 1, _RET_IP_); + + return ret; +} +EXPORT_SYMBOL(_mutex_trylock); + +void __lockfunc _mutex_unlock(struct mutex *lock) +{ + mutex_release(&lock->dep_map, _RET_IP_); + __rt_mutex_unlock(&lock->lock); +} +EXPORT_SYMBOL(_mutex_unlock); + +/** + * atomic_dec_and_mutex_lock - return holding mutex if we dec to 0 + * @cnt: the atomic which we are to dec + * @lock: the mutex to return holding if we dec to 0 + * + * return true and hold lock if we dec to 0, return false otherwise + */ +int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock) +{ + /* dec if we can't possibly hit 0 */ + if (atomic_add_unless(cnt, -1, 1)) + return 0; + /* we might hit 0, so take the lock */ + mutex_lock(lock); + if (!atomic_dec_and_test(cnt)) { + /* when we actually did the dec, we didn't hit 0 */ + mutex_unlock(lock); + return 0; + } + /* we hit 0, and we hold the lock */ + return 1; +} +EXPORT_SYMBOL(atomic_dec_and_mutex_lock); diff --git a/kernel/locking/rtmutex-debug.c b/kernel/locking/rtmutex-debug.c index 36e69100e8e06..fb150100335fc 100644 --- a/kernel/locking/rtmutex-debug.c +++ b/kernel/locking/rtmutex-debug.c @@ -32,110 +32,12 @@ #include "rtmutex_common.h" -static void printk_task(struct task_struct *p) -{ - if (p) - printk("%16s:%5d [%p, %3d]", p->comm, task_pid_nr(p), p, p->prio); - else - printk(""); -} - -static void printk_lock(struct rt_mutex *lock, int print_owner) -{ - if (lock->name) - printk(" [%p] {%s}\n", - lock, lock->name); - else - printk(" [%p] {%s:%d}\n", - lock, lock->file, lock->line); - - if (print_owner && rt_mutex_owner(lock)) { - printk(".. ->owner: %p\n", lock->owner); - printk(".. held by: "); - printk_task(rt_mutex_owner(lock)); - printk("\n"); - } -} - void rt_mutex_debug_task_free(struct task_struct *task) { DEBUG_LOCKS_WARN_ON(!RB_EMPTY_ROOT(&task->pi_waiters.rb_root)); DEBUG_LOCKS_WARN_ON(task->pi_blocked_on); } -/* - * We fill out the fields in the waiter to store the information about - * the deadlock. We print when we return. act_waiter can be NULL in - * case of a remove waiter operation. - */ -void debug_rt_mutex_deadlock(enum rtmutex_chainwalk chwalk, - struct rt_mutex_waiter *act_waiter, - struct rt_mutex *lock) -{ - struct task_struct *task; - - if (!debug_locks || chwalk == RT_MUTEX_FULL_CHAINWALK || !act_waiter) - return; - - task = rt_mutex_owner(act_waiter->lock); - if (task && task != current) { - act_waiter->deadlock_task_pid = get_pid(task_pid(task)); - act_waiter->deadlock_lock = lock; - } -} - -void debug_rt_mutex_print_deadlock(struct rt_mutex_waiter *waiter) -{ - struct task_struct *task; - - if (!waiter->deadlock_lock || !debug_locks) - return; - - rcu_read_lock(); - task = pid_task(waiter->deadlock_task_pid, PIDTYPE_PID); - if (!task) { - rcu_read_unlock(); - return; - } - - if (!debug_locks_off()) { - rcu_read_unlock(); - return; - } - - pr_warn("\n"); - pr_warn("============================================\n"); - pr_warn("WARNING: circular locking deadlock detected!\n"); - pr_warn("%s\n", print_tainted()); - pr_warn("--------------------------------------------\n"); - printk("%s/%d is deadlocking current task %s/%d\n\n", - task->comm, task_pid_nr(task), - current->comm, task_pid_nr(current)); - - printk("\n1) %s/%d is trying to acquire this lock:\n", - current->comm, task_pid_nr(current)); - printk_lock(waiter->lock, 1); - - printk("\n2) %s/%d is blocked on this lock:\n", - task->comm, task_pid_nr(task)); - printk_lock(waiter->deadlock_lock, 1); - - debug_show_held_locks(current); - debug_show_held_locks(task); - - printk("\n%s/%d's [blocked] stackdump:\n\n", - task->comm, task_pid_nr(task)); - show_stack(task, NULL, KERN_DEFAULT); - printk("\n%s/%d's [current] stackdump:\n\n", - current->comm, task_pid_nr(current)); - dump_stack(); - debug_show_all_locks(); - rcu_read_unlock(); - - printk("[ turning off deadlock detection." - "Please report this trace. ]\n\n"); -} - void debug_rt_mutex_lock(struct rt_mutex *lock) { } @@ -158,12 +60,10 @@ void debug_rt_mutex_proxy_unlock(struct rt_mutex *lock) void debug_rt_mutex_init_waiter(struct rt_mutex_waiter *waiter) { memset(waiter, 0x11, sizeof(*waiter)); - waiter->deadlock_task_pid = NULL; } void debug_rt_mutex_free_waiter(struct rt_mutex_waiter *waiter) { - put_pid(waiter->deadlock_task_pid); memset(waiter, 0x22, sizeof(*waiter)); } @@ -173,10 +73,8 @@ void debug_rt_mutex_init(struct rt_mutex *lock, const char *name, struct lock_cl * Make sure we are not reinitializing a held lock: */ debug_check_no_locks_freed((void *)lock, sizeof(*lock)); - lock->name = name; #ifdef CONFIG_DEBUG_LOCK_ALLOC lockdep_init_map(&lock->dep_map, name, key, 0); #endif } - diff --git a/kernel/locking/rtmutex-debug.h b/kernel/locking/rtmutex-debug.h index fc549713bba3f..659e93e256c67 100644 --- a/kernel/locking/rtmutex-debug.h +++ b/kernel/locking/rtmutex-debug.h @@ -18,20 +18,9 @@ extern void debug_rt_mutex_unlock(struct rt_mutex *lock); extern void debug_rt_mutex_proxy_lock(struct rt_mutex *lock, struct task_struct *powner); extern void debug_rt_mutex_proxy_unlock(struct rt_mutex *lock); -extern void debug_rt_mutex_deadlock(enum rtmutex_chainwalk chwalk, - struct rt_mutex_waiter *waiter, - struct rt_mutex *lock); -extern void debug_rt_mutex_print_deadlock(struct rt_mutex_waiter *waiter); -# define debug_rt_mutex_reset_waiter(w) \ - do { (w)->deadlock_lock = NULL; } while (0) static inline bool debug_rt_mutex_detect_deadlock(struct rt_mutex_waiter *waiter, enum rtmutex_chainwalk walk) { return (waiter != NULL); } - -static inline void rt_mutex_print_deadlock(struct rt_mutex_waiter *w) -{ - debug_rt_mutex_print_deadlock(w); -} diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index 48fff64379014..d4da971759fb4 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -8,6 +8,11 @@ * Copyright (C) 2005-2006 Timesys Corp., Thomas Gleixner * Copyright (C) 2005 Kihon Technologies Inc., Steven Rostedt * Copyright (C) 2006 Esben Nielsen + * Adaptive Spinlocks: + * Copyright (C) 2008 Novell, Inc., Gregory Haskins, Sven Dietrich, + * and Peter Morreale, + * Adaptive Spinlocks simplification: + * Copyright (C) 2008 Red Hat, Inc., Steven Rostedt * * See Documentation/locking/rt-mutex-design.rst for details. */ @@ -19,6 +24,7 @@ #include #include #include +#include #include "rtmutex_common.h" @@ -136,6 +142,12 @@ static void fixup_rt_mutex_waiters(struct rt_mutex *lock) WRITE_ONCE(*p, owner & ~RT_MUTEX_HAS_WAITERS); } +static int rt_mutex_real_waiter(struct rt_mutex_waiter *waiter) +{ + return waiter && waiter != PI_WAKEUP_INPROGRESS && + waiter != PI_REQUEUE_INPROGRESS; +} + /* * We can speed up the acquire/release, if there's no debugging state to be * set up. @@ -227,7 +239,7 @@ static inline bool unlock_rt_mutex_safe(struct rt_mutex *lock, * Only use with rt_mutex_waiter_{less,equal}() */ #define task_to_waiter(p) \ - &(struct rt_mutex_waiter){ .prio = (p)->prio, .deadline = (p)->dl.deadline } + &(struct rt_mutex_waiter){ .prio = (p)->prio, .deadline = (p)->dl.deadline, .task = (p) } static inline int rt_mutex_waiter_less(struct rt_mutex_waiter *left, @@ -267,6 +279,27 @@ rt_mutex_waiter_equal(struct rt_mutex_waiter *left, return 1; } +#define STEAL_NORMAL 0 +#define STEAL_LATERAL 1 + +static inline int +rt_mutex_steal(struct rt_mutex *lock, struct rt_mutex_waiter *waiter, int mode) +{ + struct rt_mutex_waiter *top_waiter = rt_mutex_top_waiter(lock); + + if (waiter == top_waiter || rt_mutex_waiter_less(waiter, top_waiter)) + return 1; + + /* + * Note that RT tasks are excluded from lateral-steals + * to prevent the introduction of an unbounded latency. + */ + if (mode == STEAL_NORMAL || rt_task(waiter->task)) + return 0; + + return rt_mutex_waiter_equal(waiter, top_waiter); +} + #define __node_2_waiter(node) \ rb_entry((node), struct rt_mutex_waiter, tree_entry) @@ -353,6 +386,14 @@ static bool rt_mutex_cond_detect_deadlock(struct rt_mutex_waiter *waiter, return debug_rt_mutex_detect_deadlock(waiter, chwalk); } +static void rt_mutex_wake_waiter(struct rt_mutex_waiter *waiter) +{ + if (waiter->savestate) + wake_up_lock_sleeper(waiter->task); + else + wake_up_process(waiter->task); +} + /* * Max number of times we'll walk the boosting chain: */ @@ -360,7 +401,8 @@ int max_lock_depth = 1024; static inline struct rt_mutex *task_blocked_on_lock(struct task_struct *p) { - return p->pi_blocked_on ? p->pi_blocked_on->lock : NULL; + return rt_mutex_real_waiter(p->pi_blocked_on) ? + p->pi_blocked_on->lock : NULL; } /* @@ -496,7 +538,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task, * reached or the state of the chain has changed while we * dropped the locks. */ - if (!waiter) + if (!rt_mutex_real_waiter(waiter)) goto out_unlock_pi; /* @@ -579,7 +621,6 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task, * walk, we detected a deadlock. */ if (lock == orig_lock || rt_mutex_owner(lock) == top_task) { - debug_rt_mutex_deadlock(chwalk, orig_waiter, lock); raw_spin_unlock(&lock->wait_lock); ret = -EDEADLK; goto out_unlock_pi; @@ -676,13 +717,16 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task, * follow here. This is the end of the chain we are walking. */ if (!rt_mutex_owner(lock)) { + struct rt_mutex_waiter *lock_top_waiter; + /* * If the requeue [7] above changed the top waiter, * then we need to wake the new top waiter up to try * to get the lock. */ - if (prerequeue_top_waiter != rt_mutex_top_waiter(lock)) - wake_up_process(rt_mutex_top_waiter(lock)->task); + lock_top_waiter = rt_mutex_top_waiter(lock); + if (prerequeue_top_waiter != lock_top_waiter) + rt_mutex_wake_waiter(lock_top_waiter); raw_spin_unlock_irq(&lock->wait_lock); return 0; } @@ -783,9 +827,11 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task, * @task: The task which wants to acquire the lock * @waiter: The waiter that is queued to the lock's wait tree if the * callsite called task_blocked_on_lock(), otherwise NULL + * @mode: Lock steal mode (STEAL_NORMAL, STEAL_LATERAL) */ -static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task, - struct rt_mutex_waiter *waiter) +static int __try_to_take_rt_mutex(struct rt_mutex *lock, + struct task_struct *task, + struct rt_mutex_waiter *waiter, int mode) { lockdep_assert_held(&lock->wait_lock); @@ -821,12 +867,11 @@ static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task, */ if (waiter) { /* - * If waiter is not the highest priority waiter of - * @lock, give up. + * If waiter is not the highest priority waiter of @lock, + * or its peer when lateral steal is allowed, give up. */ - if (waiter != rt_mutex_top_waiter(lock)) + if (!rt_mutex_steal(lock, waiter, mode)) return 0; - /* * We can acquire the lock. Remove the waiter from the * lock waiters tree. @@ -844,14 +889,12 @@ static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task, */ if (rt_mutex_has_waiters(lock)) { /* - * If @task->prio is greater than or equal to - * the top waiter priority (kernel view), - * @task lost. + * If @task->prio is greater than the top waiter + * priority (kernel view), or equal to it when a + * lateral steal is forbidden, @task lost. */ - if (!rt_mutex_waiter_less(task_to_waiter(task), - rt_mutex_top_waiter(lock))) + if (!rt_mutex_steal(lock, task_to_waiter(task), mode)) return 0; - /* * The current top waiter stays enqueued. We * don't have to change anything in the lock @@ -898,6 +941,329 @@ static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task, return 1; } +#ifdef CONFIG_PREEMPT_RT +/* + * preemptible spin_lock functions: + */ +static inline void rt_spin_lock_fastlock(struct rt_mutex *lock, + void (*slowfn)(struct rt_mutex *lock)) +{ + might_sleep_no_state_check(); + + if (likely(rt_mutex_cmpxchg_acquire(lock, NULL, current))) + return; + else + slowfn(lock); +} + +static inline void rt_spin_lock_fastunlock(struct rt_mutex *lock, + void (*slowfn)(struct rt_mutex *lock)) +{ + if (likely(rt_mutex_cmpxchg_release(lock, current, NULL))) + return; + else + slowfn(lock); +} +#ifdef CONFIG_SMP +/* + * Note that owner is a speculative pointer and dereferencing relies + * on rcu_read_lock() and the check against the lock owner. + */ +static int adaptive_wait(struct rt_mutex *lock, + struct task_struct *owner) +{ + int res = 0; + + rcu_read_lock(); + for (;;) { + if (owner != rt_mutex_owner(lock)) + break; + /* + * Ensure that owner->on_cpu is dereferenced _after_ + * checking the above to be valid. + */ + barrier(); + if (!owner->on_cpu) { + res = 1; + break; + } + cpu_relax(); + } + rcu_read_unlock(); + return res; +} +#else +static int adaptive_wait(struct rt_mutex *lock, + struct task_struct *orig_owner) +{ + return 1; +} +#endif + +static int task_blocks_on_rt_mutex(struct rt_mutex *lock, + struct rt_mutex_waiter *waiter, + struct task_struct *task, + enum rtmutex_chainwalk chwalk); +/* + * Slow path lock function spin_lock style: this variant is very + * careful not to miss any non-lock wakeups. + * + * We store the current state under p->pi_lock in p->saved_state and + * the try_to_wake_up() code handles this accordingly. + */ +void __sched rt_spin_lock_slowlock_locked(struct rt_mutex *lock, + struct rt_mutex_waiter *waiter, + unsigned long flags) +{ + struct task_struct *lock_owner, *self = current; + struct rt_mutex_waiter *top_waiter; + int ret; + + if (__try_to_take_rt_mutex(lock, self, NULL, STEAL_LATERAL)) + return; + + BUG_ON(rt_mutex_owner(lock) == self); + + /* + * We save whatever state the task is in and we'll restore it + * after acquiring the lock taking real wakeups into account + * as well. We are serialized via pi_lock against wakeups. See + * try_to_wake_up(). + */ + raw_spin_lock(&self->pi_lock); + self->saved_state = self->state; + __set_current_state_no_track(TASK_UNINTERRUPTIBLE); + raw_spin_unlock(&self->pi_lock); + + ret = task_blocks_on_rt_mutex(lock, waiter, self, RT_MUTEX_MIN_CHAINWALK); + BUG_ON(ret); + + for (;;) { + /* Try to acquire the lock again. */ + if (__try_to_take_rt_mutex(lock, self, waiter, STEAL_LATERAL)) + break; + + top_waiter = rt_mutex_top_waiter(lock); + lock_owner = rt_mutex_owner(lock); + + raw_spin_unlock_irqrestore(&lock->wait_lock, flags); + + if (top_waiter != waiter || adaptive_wait(lock, lock_owner)) + preempt_schedule_lock(); + + raw_spin_lock_irqsave(&lock->wait_lock, flags); + + raw_spin_lock(&self->pi_lock); + __set_current_state_no_track(TASK_UNINTERRUPTIBLE); + raw_spin_unlock(&self->pi_lock); + } + + /* + * Restore the task state to current->saved_state. We set it + * to the original state above and the try_to_wake_up() code + * has possibly updated it when a real (non-rtmutex) wakeup + * happened while we were blocked. Clear saved_state so + * try_to_wakeup() does not get confused. + */ + raw_spin_lock(&self->pi_lock); + __set_current_state_no_track(self->saved_state); + self->saved_state = TASK_RUNNING; + raw_spin_unlock(&self->pi_lock); + + /* + * try_to_take_rt_mutex() sets the waiter bit + * unconditionally. We might have to fix that up: + */ + fixup_rt_mutex_waiters(lock); + + BUG_ON(rt_mutex_has_waiters(lock) && waiter == rt_mutex_top_waiter(lock)); + BUG_ON(!RB_EMPTY_NODE(&waiter->tree_entry)); +} + +static void noinline __sched rt_spin_lock_slowlock(struct rt_mutex *lock) +{ + struct rt_mutex_waiter waiter; + unsigned long flags; + + rt_mutex_init_waiter(&waiter, true); + + raw_spin_lock_irqsave(&lock->wait_lock, flags); + rt_spin_lock_slowlock_locked(lock, &waiter, flags); + raw_spin_unlock_irqrestore(&lock->wait_lock, flags); + debug_rt_mutex_free_waiter(&waiter); +} + +static bool __sched __rt_mutex_unlock_common(struct rt_mutex *lock, + struct wake_q_head *wake_q, + struct wake_q_head *wq_sleeper); +/* + * Slow path to release a rt_mutex spin_lock style + */ +void __sched rt_spin_lock_slowunlock(struct rt_mutex *lock) +{ + unsigned long flags; + DEFINE_WAKE_Q(wake_q); + DEFINE_WAKE_Q(wake_sleeper_q); + bool postunlock; + + raw_spin_lock_irqsave(&lock->wait_lock, flags); + postunlock = __rt_mutex_unlock_common(lock, &wake_q, &wake_sleeper_q); + raw_spin_unlock_irqrestore(&lock->wait_lock, flags); + + if (postunlock) + rt_mutex_postunlock(&wake_q, &wake_sleeper_q); +} + +void __lockfunc rt_spin_lock(spinlock_t *lock) +{ + spin_acquire(&lock->dep_map, 0, 0, _RET_IP_); + rt_spin_lock_fastlock(&lock->lock, rt_spin_lock_slowlock); + rcu_read_lock(); + migrate_disable(); +} +EXPORT_SYMBOL(rt_spin_lock); + +void __lockfunc __rt_spin_lock(struct rt_mutex *lock) +{ + rt_spin_lock_fastlock(lock, rt_spin_lock_slowlock); +} + +#ifdef CONFIG_DEBUG_LOCK_ALLOC +void __lockfunc rt_spin_lock_nested(spinlock_t *lock, int subclass) +{ + spin_acquire(&lock->dep_map, subclass, 0, _RET_IP_); + rt_spin_lock_fastlock(&lock->lock, rt_spin_lock_slowlock); + rcu_read_lock(); + migrate_disable(); +} +EXPORT_SYMBOL(rt_spin_lock_nested); + +void __lockfunc rt_spin_lock_nest_lock(spinlock_t *lock, + struct lockdep_map *nest_lock) +{ + spin_acquire_nest(&lock->dep_map, 0, 0, nest_lock, _RET_IP_); + rt_spin_lock_fastlock(&lock->lock, rt_spin_lock_slowlock); + rcu_read_lock(); + migrate_disable(); +} +EXPORT_SYMBOL(rt_spin_lock_nest_lock); +#endif + +void __lockfunc rt_spin_unlock(spinlock_t *lock) +{ + /* NOTE: we always pass in '1' for nested, for simplicity */ + spin_release(&lock->dep_map, _RET_IP_); + migrate_enable(); + rcu_read_unlock(); + rt_spin_lock_fastunlock(&lock->lock, rt_spin_lock_slowunlock); +} +EXPORT_SYMBOL(rt_spin_unlock); + +void __lockfunc __rt_spin_unlock(struct rt_mutex *lock) +{ + rt_spin_lock_fastunlock(lock, rt_spin_lock_slowunlock); +} +EXPORT_SYMBOL(__rt_spin_unlock); + +/* + * Wait for the lock to get unlocked: instead of polling for an unlock + * (like raw spinlocks do), we lock and unlock, to force the kernel to + * schedule if there's contention: + */ +void __lockfunc rt_spin_lock_unlock(spinlock_t *lock) +{ + spin_lock(lock); + spin_unlock(lock); +} +EXPORT_SYMBOL(rt_spin_lock_unlock); + +int __lockfunc rt_spin_trylock(spinlock_t *lock) +{ + int ret; + + ret = __rt_mutex_trylock(&lock->lock); + if (ret) { + spin_acquire(&lock->dep_map, 0, 1, _RET_IP_); + rcu_read_lock(); + migrate_disable(); + } + return ret; +} +EXPORT_SYMBOL(rt_spin_trylock); + +int __lockfunc rt_spin_trylock_bh(spinlock_t *lock) +{ + int ret; + + local_bh_disable(); + ret = __rt_mutex_trylock(&lock->lock); + if (ret) { + spin_acquire(&lock->dep_map, 0, 1, _RET_IP_); + rcu_read_lock(); + migrate_disable(); + } else { + local_bh_enable(); + } + return ret; +} +EXPORT_SYMBOL(rt_spin_trylock_bh); + +void +__rt_spin_lock_init(spinlock_t *lock, const char *name, struct lock_class_key *key) +{ +#ifdef CONFIG_DEBUG_LOCK_ALLOC + /* + * Make sure we are not reinitializing a held lock: + */ + debug_check_no_locks_freed((void *)lock, sizeof(*lock)); + lockdep_init_map(&lock->dep_map, name, key, 0); +#endif +} +EXPORT_SYMBOL(__rt_spin_lock_init); + +#endif /* PREEMPT_RT */ + +#ifdef CONFIG_PREEMPT_RT + static inline int __sched +__mutex_lock_check_stamp(struct rt_mutex *lock, struct ww_acquire_ctx *ctx) +{ + struct ww_mutex *ww = container_of(lock, struct ww_mutex, base.lock); + struct ww_acquire_ctx *hold_ctx = READ_ONCE(ww->ctx); + + if (!hold_ctx) + return 0; + + if (unlikely(ctx == hold_ctx)) + return -EALREADY; + + if (ctx->stamp - hold_ctx->stamp <= LONG_MAX && + (ctx->stamp != hold_ctx->stamp || ctx > hold_ctx)) { +#ifdef CONFIG_DEBUG_MUTEXES + DEBUG_LOCKS_WARN_ON(ctx->contending_lock); + ctx->contending_lock = ww; +#endif + return -EDEADLK; + } + + return 0; +} +#else + static inline int __sched +__mutex_lock_check_stamp(struct rt_mutex *lock, struct ww_acquire_ctx *ctx) +{ + BUG(); + return 0; +} + +#endif + +static inline int +try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task, + struct rt_mutex_waiter *waiter) +{ + return __try_to_take_rt_mutex(lock, task, waiter, STEAL_NORMAL); +} + /* * Task blocks on lock. * @@ -930,6 +1296,22 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock, return -EDEADLK; raw_spin_lock(&task->pi_lock); + /* + * In the case of futex requeue PI, this will be a proxy + * lock. The task will wake unaware that it is enqueueed on + * this lock. Avoid blocking on two locks and corrupting + * pi_blocked_on via the PI_WAKEUP_INPROGRESS + * flag. futex_wait_requeue_pi() sets this when it wakes up + * before requeue (due to a signal or timeout). Do not enqueue + * the task if PI_WAKEUP_INPROGRESS is set. + */ + if (task != current && task->pi_blocked_on == PI_WAKEUP_INPROGRESS) { + raw_spin_unlock(&task->pi_lock); + return -EAGAIN; + } + + BUG_ON(rt_mutex_real_waiter(task->pi_blocked_on)); + waiter->task = task; waiter->lock = lock; waiter->prio = task->prio; @@ -953,7 +1335,7 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock, rt_mutex_enqueue_pi(owner, waiter); rt_mutex_adjust_prio(owner); - if (owner->pi_blocked_on) + if (rt_mutex_real_waiter(owner->pi_blocked_on)) chain_walk = 1; } else if (rt_mutex_cond_detect_deadlock(waiter, chwalk)) { chain_walk = 1; @@ -995,6 +1377,7 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock, * Called with lock->wait_lock held and interrupts disabled. */ static void mark_wakeup_next_waiter(struct wake_q_head *wake_q, + struct wake_q_head *wake_sleeper_q, struct rt_mutex *lock) { struct rt_mutex_waiter *waiter; @@ -1034,7 +1417,10 @@ static void mark_wakeup_next_waiter(struct wake_q_head *wake_q, * Pairs with preempt_enable() in rt_mutex_postunlock(); */ preempt_disable(); - wake_q_add(wake_q, waiter->task); + if (waiter->savestate) + wake_q_add_sleeper(wake_sleeper_q, waiter->task); + else + wake_q_add(wake_q, waiter->task); raw_spin_unlock(¤t->pi_lock); } @@ -1049,7 +1435,7 @@ static void remove_waiter(struct rt_mutex *lock, { bool is_top_waiter = (waiter == rt_mutex_top_waiter(lock)); struct task_struct *owner = rt_mutex_owner(lock); - struct rt_mutex *next_lock; + struct rt_mutex *next_lock = NULL; lockdep_assert_held(&lock->wait_lock); @@ -1075,7 +1461,8 @@ static void remove_waiter(struct rt_mutex *lock, rt_mutex_adjust_prio(owner); /* Store the lock on which owner is blocked or NULL */ - next_lock = task_blocked_on_lock(owner); + if (rt_mutex_real_waiter(owner->pi_blocked_on)) + next_lock = task_blocked_on_lock(owner); raw_spin_unlock(&owner->pi_lock); @@ -1111,26 +1498,28 @@ void rt_mutex_adjust_pi(struct task_struct *task) raw_spin_lock_irqsave(&task->pi_lock, flags); waiter = task->pi_blocked_on; - if (!waiter || rt_mutex_waiter_equal(waiter, task_to_waiter(task))) { + if (!rt_mutex_real_waiter(waiter) || + rt_mutex_waiter_equal(waiter, task_to_waiter(task))) { raw_spin_unlock_irqrestore(&task->pi_lock, flags); return; } next_lock = waiter->lock; - raw_spin_unlock_irqrestore(&task->pi_lock, flags); /* gets dropped in rt_mutex_adjust_prio_chain()! */ get_task_struct(task); + raw_spin_unlock_irqrestore(&task->pi_lock, flags); rt_mutex_adjust_prio_chain(task, RT_MUTEX_MIN_CHAINWALK, NULL, next_lock, NULL, task); } -void rt_mutex_init_waiter(struct rt_mutex_waiter *waiter) +void rt_mutex_init_waiter(struct rt_mutex_waiter *waiter, bool savestate) { debug_rt_mutex_init_waiter(waiter); RB_CLEAR_NODE(&waiter->pi_tree_entry); RB_CLEAR_NODE(&waiter->tree_entry); waiter->task = NULL; + waiter->savestate = savestate; } /** @@ -1146,7 +1535,8 @@ void rt_mutex_init_waiter(struct rt_mutex_waiter *waiter) static int __sched __rt_mutex_slowlock(struct rt_mutex *lock, int state, struct hrtimer_sleeper *timeout, - struct rt_mutex_waiter *waiter) + struct rt_mutex_waiter *waiter, + struct ww_acquire_ctx *ww_ctx) { int ret = 0; @@ -1155,24 +1545,23 @@ __rt_mutex_slowlock(struct rt_mutex *lock, int state, if (try_to_take_rt_mutex(lock, current, waiter)) break; - /* - * TASK_INTERRUPTIBLE checks for signals and - * timeout. Ignored otherwise. - */ - if (likely(state == TASK_INTERRUPTIBLE)) { - /* Signal pending? */ - if (signal_pending(current)) - ret = -EINTR; - if (timeout && !timeout->task) - ret = -ETIMEDOUT; + if (timeout && !timeout->task) { + ret = -ETIMEDOUT; + break; + } + if (signal_pending_state(state, current)) { + ret = -EINTR; + break; + } + + if (ww_ctx && ww_ctx->acquired > 0) { + ret = __mutex_lock_check_stamp(lock, ww_ctx); if (ret) break; } raw_spin_unlock_irq(&lock->wait_lock); - debug_rt_mutex_print_deadlock(waiter); - schedule(); raw_spin_lock_irq(&lock->wait_lock); @@ -1193,29 +1582,163 @@ static void rt_mutex_handle_deadlock(int res, int detect_deadlock, if (res != -EDEADLOCK || detect_deadlock) return; - /* - * Yell lowdly and stop the task right here. - */ - rt_mutex_print_deadlock(w); while (1) { set_current_state(TASK_INTERRUPTIBLE); schedule(); } } +static __always_inline void ww_mutex_lock_acquired(struct ww_mutex *ww, + struct ww_acquire_ctx *ww_ctx) +{ +#ifdef CONFIG_DEBUG_MUTEXES + /* + * If this WARN_ON triggers, you used ww_mutex_lock to acquire, + * but released with a normal mutex_unlock in this call. + * + * This should never happen, always use ww_mutex_unlock. + */ + DEBUG_LOCKS_WARN_ON(ww->ctx); + + /* + * Not quite done after calling ww_acquire_done() ? + */ + DEBUG_LOCKS_WARN_ON(ww_ctx->done_acquire); + + if (ww_ctx->contending_lock) { + /* + * After -EDEADLK you tried to + * acquire a different ww_mutex? Bad! + */ + DEBUG_LOCKS_WARN_ON(ww_ctx->contending_lock != ww); + + /* + * You called ww_mutex_lock after receiving -EDEADLK, + * but 'forgot' to unlock everything else first? + */ + DEBUG_LOCKS_WARN_ON(ww_ctx->acquired > 0); + ww_ctx->contending_lock = NULL; + } + + /* + * Naughty, using a different class will lead to undefined behavior! + */ + DEBUG_LOCKS_WARN_ON(ww_ctx->ww_class != ww->ww_class); +#endif + ww_ctx->acquired++; +} + +#ifdef CONFIG_PREEMPT_RT +static void ww_mutex_account_lock(struct rt_mutex *lock, + struct ww_acquire_ctx *ww_ctx) +{ + struct ww_mutex *ww = container_of(lock, struct ww_mutex, base.lock); + struct rt_mutex_waiter *waiter, *n; + + /* + * This branch gets optimized out for the common case, + * and is only important for ww_mutex_lock. + */ + ww_mutex_lock_acquired(ww, ww_ctx); + ww->ctx = ww_ctx; + + /* + * Give any possible sleeping processes the chance to wake up, + * so they can recheck if they have to back off. + */ + rbtree_postorder_for_each_entry_safe(waiter, n, &lock->waiters.rb_root, + tree_entry) { + /* XXX debug rt mutex waiter wakeup */ + + BUG_ON(waiter->lock != lock); + rt_mutex_wake_waiter(waiter); + } +} + +#else + +static void ww_mutex_account_lock(struct rt_mutex *lock, + struct ww_acquire_ctx *ww_ctx) +{ + BUG(); +} +#endif + +int __sched rt_mutex_slowlock_locked(struct rt_mutex *lock, int state, + struct hrtimer_sleeper *timeout, + enum rtmutex_chainwalk chwalk, + struct ww_acquire_ctx *ww_ctx, + struct rt_mutex_waiter *waiter) +{ + int ret; + +#ifdef CONFIG_PREEMPT_RT + if (ww_ctx) { + struct ww_mutex *ww; + + ww = container_of(lock, struct ww_mutex, base.lock); + if (unlikely(ww_ctx == READ_ONCE(ww->ctx))) + return -EALREADY; + } +#endif + + /* Try to acquire the lock again: */ + if (try_to_take_rt_mutex(lock, current, NULL)) { + if (ww_ctx) + ww_mutex_account_lock(lock, ww_ctx); + return 0; + } + + set_current_state(state); + + /* Setup the timer, when timeout != NULL */ + if (unlikely(timeout)) + hrtimer_start_expires(&timeout->timer, HRTIMER_MODE_ABS); + + ret = task_blocks_on_rt_mutex(lock, waiter, current, chwalk); + + if (likely(!ret)) { + /* sleep on the mutex */ + ret = __rt_mutex_slowlock(lock, state, timeout, waiter, + ww_ctx); + } else if (ww_ctx) { + /* ww_mutex received EDEADLK, let it become EALREADY */ + ret = __mutex_lock_check_stamp(lock, ww_ctx); + BUG_ON(!ret); + } + + if (unlikely(ret)) { + __set_current_state(TASK_RUNNING); + remove_waiter(lock, waiter); + /* ww_mutex wants to report EDEADLK/EALREADY, let it */ + if (!ww_ctx) + rt_mutex_handle_deadlock(ret, chwalk, waiter); + } else if (ww_ctx) { + ww_mutex_account_lock(lock, ww_ctx); + } + + /* + * try_to_take_rt_mutex() sets the waiter bit + * unconditionally. We might have to fix that up. + */ + fixup_rt_mutex_waiters(lock); + return ret; +} + /* * Slow path lock function: */ static int __sched rt_mutex_slowlock(struct rt_mutex *lock, int state, struct hrtimer_sleeper *timeout, - enum rtmutex_chainwalk chwalk) + enum rtmutex_chainwalk chwalk, + struct ww_acquire_ctx *ww_ctx) { struct rt_mutex_waiter waiter; unsigned long flags; int ret = 0; - rt_mutex_init_waiter(&waiter); + rt_mutex_init_waiter(&waiter, false); /* * Technically we could use raw_spin_[un]lock_irq() here, but this can @@ -1227,35 +1750,8 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state, */ raw_spin_lock_irqsave(&lock->wait_lock, flags); - /* Try to acquire the lock again: */ - if (try_to_take_rt_mutex(lock, current, NULL)) { - raw_spin_unlock_irqrestore(&lock->wait_lock, flags); - return 0; - } - - set_current_state(state); - - /* Setup the timer, when timeout != NULL */ - if (unlikely(timeout)) - hrtimer_start_expires(&timeout->timer, HRTIMER_MODE_ABS); - - ret = task_blocks_on_rt_mutex(lock, &waiter, current, chwalk); - - if (likely(!ret)) - /* sleep on the mutex */ - ret = __rt_mutex_slowlock(lock, state, timeout, &waiter); - - if (unlikely(ret)) { - __set_current_state(TASK_RUNNING); - remove_waiter(lock, &waiter); - rt_mutex_handle_deadlock(ret, chwalk, &waiter); - } - - /* - * try_to_take_rt_mutex() sets the waiter bit - * unconditionally. We might have to fix that up. - */ - fixup_rt_mutex_waiters(lock); + ret = rt_mutex_slowlock_locked(lock, state, timeout, chwalk, ww_ctx, + &waiter); raw_spin_unlock_irqrestore(&lock->wait_lock, flags); @@ -1316,7 +1812,8 @@ static inline int rt_mutex_slowtrylock(struct rt_mutex *lock) * Return whether the current task needs to call rt_mutex_postunlock(). */ static bool __sched rt_mutex_slowunlock(struct rt_mutex *lock, - struct wake_q_head *wake_q) + struct wake_q_head *wake_q, + struct wake_q_head *wake_sleeper_q) { unsigned long flags; @@ -1370,7 +1867,7 @@ static bool __sched rt_mutex_slowunlock(struct rt_mutex *lock, * * Queue the next waiter for wakeup once we release the wait_lock. */ - mark_wakeup_next_waiter(wake_q, lock); + mark_wakeup_next_waiter(wake_q, wake_sleeper_q, lock); raw_spin_unlock_irqrestore(&lock->wait_lock, flags); return true; /* call rt_mutex_postunlock() */ @@ -1384,29 +1881,16 @@ static bool __sched rt_mutex_slowunlock(struct rt_mutex *lock, */ static inline int rt_mutex_fastlock(struct rt_mutex *lock, int state, + struct ww_acquire_ctx *ww_ctx, int (*slowfn)(struct rt_mutex *lock, int state, struct hrtimer_sleeper *timeout, - enum rtmutex_chainwalk chwalk)) + enum rtmutex_chainwalk chwalk, + struct ww_acquire_ctx *ww_ctx)) { if (likely(rt_mutex_cmpxchg_acquire(lock, NULL, current))) return 0; - return slowfn(lock, state, NULL, RT_MUTEX_MIN_CHAINWALK); -} - -static inline int -rt_mutex_timed_fastlock(struct rt_mutex *lock, int state, - struct hrtimer_sleeper *timeout, - enum rtmutex_chainwalk chwalk, - int (*slowfn)(struct rt_mutex *lock, int state, - struct hrtimer_sleeper *timeout, - enum rtmutex_chainwalk chwalk)) -{ - if (chwalk == RT_MUTEX_MIN_CHAINWALK && - likely(rt_mutex_cmpxchg_acquire(lock, NULL, current))) - return 0; - - return slowfn(lock, state, timeout, chwalk); + return slowfn(lock, state, NULL, RT_MUTEX_MIN_CHAINWALK, ww_ctx); } static inline int @@ -1422,9 +1906,11 @@ rt_mutex_fasttrylock(struct rt_mutex *lock, /* * Performs the wakeup of the top-waiter and re-enables preemption. */ -void rt_mutex_postunlock(struct wake_q_head *wake_q) +void rt_mutex_postunlock(struct wake_q_head *wake_q, + struct wake_q_head *wake_sleeper_q) { wake_up_q(wake_q); + wake_up_q_sleeper(wake_sleeper_q); /* Pairs with preempt_disable() in rt_mutex_slowunlock() */ preempt_enable(); @@ -1433,23 +1919,46 @@ void rt_mutex_postunlock(struct wake_q_head *wake_q) static inline void rt_mutex_fastunlock(struct rt_mutex *lock, bool (*slowfn)(struct rt_mutex *lock, - struct wake_q_head *wqh)) + struct wake_q_head *wqh, + struct wake_q_head *wq_sleeper)) { DEFINE_WAKE_Q(wake_q); + DEFINE_WAKE_Q(wake_sleeper_q); if (likely(rt_mutex_cmpxchg_release(lock, current, NULL))) return; - if (slowfn(lock, &wake_q)) - rt_mutex_postunlock(&wake_q); + if (slowfn(lock, &wake_q, &wake_sleeper_q)) + rt_mutex_postunlock(&wake_q, &wake_sleeper_q); +} + +int __sched __rt_mutex_lock_state(struct rt_mutex *lock, int state) +{ + might_sleep(); + return rt_mutex_fastlock(lock, state, NULL, rt_mutex_slowlock); +} + +/** + * rt_mutex_lock_state - lock a rt_mutex with a given state + * + * @lock: The rt_mutex to be locked + * @state: The state to set when blocking on the rt_mutex + */ +static inline int __sched rt_mutex_lock_state(struct rt_mutex *lock, + unsigned int subclass, int state) +{ + int ret; + + mutex_acquire(&lock->dep_map, subclass, 0, _RET_IP_); + ret = __rt_mutex_lock_state(lock, state); + if (ret) + mutex_release(&lock->dep_map, _RET_IP_); + return ret; } static inline void __rt_mutex_lock(struct rt_mutex *lock, unsigned int subclass) { - might_sleep(); - - mutex_acquire(&lock->dep_map, subclass, 0, _RET_IP_); - rt_mutex_fastlock(lock, TASK_UNINTERRUPTIBLE, rt_mutex_slowlock); + rt_mutex_lock_state(lock, subclass, TASK_UNINTERRUPTIBLE); } #ifdef CONFIG_DEBUG_LOCK_ALLOC @@ -1490,16 +1999,7 @@ EXPORT_SYMBOL_GPL(rt_mutex_lock); */ int __sched rt_mutex_lock_interruptible(struct rt_mutex *lock) { - int ret; - - might_sleep(); - - mutex_acquire(&lock->dep_map, 0, 0, _RET_IP_); - ret = rt_mutex_fastlock(lock, TASK_INTERRUPTIBLE, rt_mutex_slowlock); - if (ret) - mutex_release(&lock->dep_map, _RET_IP_); - - return ret; + return rt_mutex_lock_state(lock, 0, TASK_INTERRUPTIBLE); } EXPORT_SYMBOL_GPL(rt_mutex_lock_interruptible); @@ -1516,36 +2016,17 @@ int __sched __rt_mutex_futex_trylock(struct rt_mutex *lock) return __rt_mutex_slowtrylock(lock); } -/** - * rt_mutex_timed_lock - lock a rt_mutex interruptible - * the timeout structure is provided - * by the caller - * - * @lock: the rt_mutex to be locked - * @timeout: timeout structure or NULL (no timeout) - * - * Returns: - * 0 on success - * -EINTR when interrupted by a signal - * -ETIMEDOUT when the timeout expired - */ -int -rt_mutex_timed_lock(struct rt_mutex *lock, struct hrtimer_sleeper *timeout) +int __sched __rt_mutex_trylock(struct rt_mutex *lock) { - int ret; +#ifdef CONFIG_PREEMPT_RT + if (WARN_ON_ONCE(in_irq() || in_nmi())) +#else + if (WARN_ON_ONCE(in_irq() || in_nmi() || in_serving_softirq())) +#endif + return 0; - might_sleep(); - - mutex_acquire(&lock->dep_map, 0, 0, _RET_IP_); - ret = rt_mutex_timed_fastlock(lock, TASK_INTERRUPTIBLE, timeout, - RT_MUTEX_MIN_CHAINWALK, - rt_mutex_slowlock); - if (ret) - mutex_release(&lock->dep_map, _RET_IP_); - - return ret; + return rt_mutex_fasttrylock(lock, rt_mutex_slowtrylock); } -EXPORT_SYMBOL_GPL(rt_mutex_timed_lock); /** * rt_mutex_trylock - try to lock a rt_mutex @@ -1562,10 +2043,7 @@ int __sched rt_mutex_trylock(struct rt_mutex *lock) { int ret; - if (WARN_ON_ONCE(in_irq() || in_nmi() || in_serving_softirq())) - return 0; - - ret = rt_mutex_fasttrylock(lock, rt_mutex_slowtrylock); + ret = __rt_mutex_trylock(lock); if (ret) mutex_acquire(&lock->dep_map, 0, 1, _RET_IP_); @@ -1573,6 +2051,11 @@ int __sched rt_mutex_trylock(struct rt_mutex *lock) } EXPORT_SYMBOL_GPL(rt_mutex_trylock); +void __sched __rt_mutex_unlock(struct rt_mutex *lock) +{ + rt_mutex_fastunlock(lock, rt_mutex_slowunlock); +} + /** * rt_mutex_unlock - unlock a rt_mutex * @@ -1581,19 +2064,13 @@ EXPORT_SYMBOL_GPL(rt_mutex_trylock); void __sched rt_mutex_unlock(struct rt_mutex *lock) { mutex_release(&lock->dep_map, _RET_IP_); - rt_mutex_fastunlock(lock, rt_mutex_slowunlock); + __rt_mutex_unlock(lock); } EXPORT_SYMBOL_GPL(rt_mutex_unlock); -/** - * __rt_mutex_futex_unlock - Futex variant, that since futex variants - * do not use the fast-path, can be simple and will not need to retry. - * - * @lock: The rt_mutex to be unlocked - * @wake_q: The wake queue head from which to get the next lock waiter - */ -bool __sched __rt_mutex_futex_unlock(struct rt_mutex *lock, - struct wake_q_head *wake_q) +static bool __sched __rt_mutex_unlock_common(struct rt_mutex *lock, + struct wake_q_head *wake_q, + struct wake_q_head *wq_sleeper) { lockdep_assert_held(&lock->wait_lock); @@ -1610,23 +2087,39 @@ bool __sched __rt_mutex_futex_unlock(struct rt_mutex *lock, * avoid inversion prior to the wakeup. preempt_disable() * therein pairs with rt_mutex_postunlock(). */ - mark_wakeup_next_waiter(wake_q, lock); + mark_wakeup_next_waiter(wake_q, wq_sleeper, lock); return true; /* call postunlock() */ } +/** + * __rt_mutex_futex_unlock - Futex variant, that since futex variants + * do not use the fast-path, can be simple and will not need to retry. + * + * @lock: The rt_mutex to be unlocked + * @wake_q: The wake queue head from which to get the next lock waiter + * @wq_sleeper: The sleeper wake queue head from which to get the next lock waiter + */ +bool __sched __rt_mutex_futex_unlock(struct rt_mutex *lock, + struct wake_q_head *wake_q, + struct wake_q_head *wq_sleeper) +{ + return __rt_mutex_unlock_common(lock, wake_q, wq_sleeper); +} + void __sched rt_mutex_futex_unlock(struct rt_mutex *lock) { DEFINE_WAKE_Q(wake_q); + DEFINE_WAKE_Q(wake_sleeper_q); unsigned long flags; bool postunlock; raw_spin_lock_irqsave(&lock->wait_lock, flags); - postunlock = __rt_mutex_futex_unlock(lock, &wake_q); + postunlock = __rt_mutex_futex_unlock(lock, &wake_q, &wake_sleeper_q); raw_spin_unlock_irqrestore(&lock->wait_lock, flags); if (postunlock) - rt_mutex_postunlock(&wake_q); + rt_mutex_postunlock(&wake_q, &wake_sleeper_q); } /** @@ -1640,9 +2133,6 @@ void __sched rt_mutex_futex_unlock(struct rt_mutex *lock) void rt_mutex_destroy(struct rt_mutex *lock) { WARN_ON(rt_mutex_is_locked(lock)); -#ifdef CONFIG_DEBUG_RT_MUTEXES - lock->magic = NULL; -#endif } EXPORT_SYMBOL_GPL(rt_mutex_destroy); @@ -1667,7 +2157,7 @@ void __rt_mutex_init(struct rt_mutex *lock, const char *name, if (name && key) debug_rt_mutex_init(lock, name, key); } -EXPORT_SYMBOL_GPL(__rt_mutex_init); +EXPORT_SYMBOL(__rt_mutex_init); /** * rt_mutex_init_proxy_locked - initialize and lock a rt_mutex on behalf of a @@ -1687,6 +2177,14 @@ void rt_mutex_init_proxy_locked(struct rt_mutex *lock, struct task_struct *proxy_owner) { __rt_mutex_init(lock, NULL, NULL); +#ifdef CONFIG_DEBUG_SPINLOCK + /* + * get another key class for the wait_lock. LOCK_PI and UNLOCK_PI is + * holding the ->wait_lock of the proxy_lock while unlocking a sleeping + * lock. + */ + raw_spin_lock_init(&lock->wait_lock); +#endif debug_rt_mutex_proxy_lock(lock, proxy_owner); rt_mutex_set_owner(lock, proxy_owner); } @@ -1709,6 +2207,26 @@ void rt_mutex_proxy_unlock(struct rt_mutex *lock) rt_mutex_set_owner(lock, NULL); } +static void fixup_rt_mutex_blocked(struct rt_mutex *lock) +{ + struct task_struct *tsk = current; + /* + * RT has a problem here when the wait got interrupted by a timeout + * or a signal. task->pi_blocked_on is still set. The task must + * acquire the hash bucket lock when returning from this function. + * + * If the hash bucket lock is contended then the + * BUG_ON(rt_mutex_real_waiter(task->pi_blocked_on)) in + * task_blocks_on_rt_mutex() will trigger. This can be avoided by + * clearing task->pi_blocked_on which removes the task from the + * boosting chain of the rtmutex. That's correct because the task + * is not longer blocked on it. + */ + raw_spin_lock(&tsk->pi_lock); + tsk->pi_blocked_on = NULL; + raw_spin_unlock(&tsk->pi_lock); +} + /** * __rt_mutex_start_proxy_lock() - Start lock acquisition for another task * @lock: the rt_mutex to take @@ -1739,6 +2257,34 @@ int __rt_mutex_start_proxy_lock(struct rt_mutex *lock, if (try_to_take_rt_mutex(lock, task, NULL)) return 1; +#ifdef CONFIG_PREEMPT_RT + /* + * In PREEMPT_RT there's an added race. + * If the task, that we are about to requeue, times out, + * it can set the PI_WAKEUP_INPROGRESS. This tells the requeue + * to skip this task. But right after the task sets + * its pi_blocked_on to PI_WAKEUP_INPROGRESS it can then + * block on the spin_lock(&hb->lock), which in RT is an rtmutex. + * This will replace the PI_WAKEUP_INPROGRESS with the actual + * lock that it blocks on. We *must not* place this task + * on this proxy lock in that case. + * + * To prevent this race, we first take the task's pi_lock + * and check if it has updated its pi_blocked_on. If it has, + * we assume that it woke up and we return -EAGAIN. + * Otherwise, we set the task's pi_blocked_on to + * PI_REQUEUE_INPROGRESS, so that if the task is waking up + * it will know that we are in the process of requeuing it. + */ + raw_spin_lock(&task->pi_lock); + if (task->pi_blocked_on) { + raw_spin_unlock(&task->pi_lock); + return -EAGAIN; + } + task->pi_blocked_on = PI_REQUEUE_INPROGRESS; + raw_spin_unlock(&task->pi_lock); +#endif + /* We enforce deadlock detection for futexes */ ret = task_blocks_on_rt_mutex(lock, waiter, task, RT_MUTEX_FULL_CHAINWALK); @@ -1753,7 +2299,8 @@ int __rt_mutex_start_proxy_lock(struct rt_mutex *lock, ret = 0; } - debug_rt_mutex_print_deadlock(waiter); + if (ret) + fixup_rt_mutex_blocked(lock); return ret; } @@ -1838,12 +2385,15 @@ int rt_mutex_wait_proxy_lock(struct rt_mutex *lock, raw_spin_lock_irq(&lock->wait_lock); /* sleep on the mutex */ set_current_state(TASK_INTERRUPTIBLE); - ret = __rt_mutex_slowlock(lock, TASK_INTERRUPTIBLE, to, waiter); + ret = __rt_mutex_slowlock(lock, TASK_INTERRUPTIBLE, to, waiter, NULL); /* * try_to_take_rt_mutex() sets the waiter bit unconditionally. We might * have to fix that up. */ fixup_rt_mutex_waiters(lock); + if (ret) + fixup_rt_mutex_blocked(lock); + raw_spin_unlock_irq(&lock->wait_lock); return ret; @@ -1905,3 +2455,97 @@ bool rt_mutex_cleanup_proxy_lock(struct rt_mutex *lock, return cleanup; } + +static inline int +ww_mutex_deadlock_injection(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) +{ +#ifdef CONFIG_DEBUG_WW_MUTEX_SLOWPATH + unsigned int tmp; + + if (ctx->deadlock_inject_countdown-- == 0) { + tmp = ctx->deadlock_inject_interval; + if (tmp > UINT_MAX/4) + tmp = UINT_MAX; + else + tmp = tmp*2 + tmp + tmp/2; + + ctx->deadlock_inject_interval = tmp; + ctx->deadlock_inject_countdown = tmp; + ctx->contending_lock = lock; + + ww_mutex_unlock(lock); + + return -EDEADLK; + } +#endif + + return 0; +} + +#ifdef CONFIG_PREEMPT_RT +int __sched +ww_mutex_lock_interruptible(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) +{ + int ret; + + might_sleep(); + + mutex_acquire_nest(&lock->base.dep_map, 0, 0, + ctx ? &ctx->dep_map : NULL, _RET_IP_); + ret = rt_mutex_slowlock(&lock->base.lock, TASK_INTERRUPTIBLE, NULL, 0, + ctx); + if (ret) + mutex_release(&lock->base.dep_map, _RET_IP_); + else if (!ret && ctx && ctx->acquired > 1) + return ww_mutex_deadlock_injection(lock, ctx); + + return ret; +} +EXPORT_SYMBOL_GPL(ww_mutex_lock_interruptible); + +int __sched +ww_mutex_lock(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) +{ + int ret; + + might_sleep(); + + mutex_acquire_nest(&lock->base.dep_map, 0, 0, + ctx ? &ctx->dep_map : NULL, _RET_IP_); + ret = rt_mutex_slowlock(&lock->base.lock, TASK_UNINTERRUPTIBLE, NULL, 0, + ctx); + if (ret) + mutex_release(&lock->base.dep_map, _RET_IP_); + else if (!ret && ctx && ctx->acquired > 1) + return ww_mutex_deadlock_injection(lock, ctx); + + return ret; +} +EXPORT_SYMBOL_GPL(ww_mutex_lock); + +void __sched ww_mutex_unlock(struct ww_mutex *lock) +{ + /* + * The unlocking fastpath is the 0->1 transition from 'locked' + * into 'unlocked' state: + */ + if (lock->ctx) { +#ifdef CONFIG_DEBUG_MUTEXES + DEBUG_LOCKS_WARN_ON(!lock->ctx->acquired); +#endif + if (lock->ctx->acquired > 0) + lock->ctx->acquired--; + lock->ctx = NULL; + } + + mutex_release(&lock->base.dep_map, _RET_IP_); + __rt_mutex_unlock(&lock->base.lock); +} +EXPORT_SYMBOL(ww_mutex_unlock); + +int __rt_mutex_owner_current(struct rt_mutex *lock) +{ + return rt_mutex_owner(lock) == current; +} +EXPORT_SYMBOL(__rt_mutex_owner_current); +#endif diff --git a/kernel/locking/rtmutex.h b/kernel/locking/rtmutex.h index 732f96abf4623..338ccd29119a1 100644 --- a/kernel/locking/rtmutex.h +++ b/kernel/locking/rtmutex.h @@ -19,15 +19,8 @@ #define debug_rt_mutex_proxy_unlock(l) do { } while (0) #define debug_rt_mutex_unlock(l) do { } while (0) #define debug_rt_mutex_init(m, n, k) do { } while (0) -#define debug_rt_mutex_deadlock(d, a ,l) do { } while (0) -#define debug_rt_mutex_print_deadlock(w) do { } while (0) #define debug_rt_mutex_reset_waiter(w) do { } while (0) -static inline void rt_mutex_print_deadlock(struct rt_mutex_waiter *w) -{ - WARN(1, "rtmutex deadlock detected\n"); -} - static inline bool debug_rt_mutex_detect_deadlock(struct rt_mutex_waiter *w, enum rtmutex_chainwalk walk) { diff --git a/kernel/locking/rtmutex_common.h b/kernel/locking/rtmutex_common.h index ca6fb489007b6..248a7d91583be 100644 --- a/kernel/locking/rtmutex_common.h +++ b/kernel/locking/rtmutex_common.h @@ -15,6 +15,7 @@ #include #include +#include /* * This is the control structure for tasks blocked on a rt_mutex, @@ -29,12 +30,8 @@ struct rt_mutex_waiter { struct rb_node pi_tree_entry; struct task_struct *task; struct rt_mutex *lock; -#ifdef CONFIG_DEBUG_RT_MUTEXES - unsigned long ip; - struct pid *deadlock_task_pid; - struct rt_mutex *deadlock_lock; -#endif int prio; + bool savestate; u64 deadline; }; @@ -130,11 +127,14 @@ enum rtmutex_chainwalk { /* * PI-futex support (proxy locking functions, etc.): */ +#define PI_WAKEUP_INPROGRESS ((struct rt_mutex_waiter *) 1) +#define PI_REQUEUE_INPROGRESS ((struct rt_mutex_waiter *) 2) + extern struct task_struct *rt_mutex_next_owner(struct rt_mutex *lock); extern void rt_mutex_init_proxy_locked(struct rt_mutex *lock, struct task_struct *proxy_owner); extern void rt_mutex_proxy_unlock(struct rt_mutex *lock); -extern void rt_mutex_init_waiter(struct rt_mutex_waiter *waiter); +extern void rt_mutex_init_waiter(struct rt_mutex_waiter *waiter, bool savetate); extern int __rt_mutex_start_proxy_lock(struct rt_mutex *lock, struct rt_mutex_waiter *waiter, struct task_struct *task); @@ -152,9 +152,27 @@ extern int __rt_mutex_futex_trylock(struct rt_mutex *l); extern void rt_mutex_futex_unlock(struct rt_mutex *lock); extern bool __rt_mutex_futex_unlock(struct rt_mutex *lock, - struct wake_q_head *wqh); + struct wake_q_head *wqh, + struct wake_q_head *wq_sleeper); -extern void rt_mutex_postunlock(struct wake_q_head *wake_q); +extern void rt_mutex_postunlock(struct wake_q_head *wake_q, + struct wake_q_head *wake_sleeper_q); + +/* RW semaphore special interface */ +struct ww_acquire_ctx; + +extern int __rt_mutex_lock_state(struct rt_mutex *lock, int state); +extern int __rt_mutex_trylock(struct rt_mutex *lock); +extern void __rt_mutex_unlock(struct rt_mutex *lock); +int __sched rt_mutex_slowlock_locked(struct rt_mutex *lock, int state, + struct hrtimer_sleeper *timeout, + enum rtmutex_chainwalk chwalk, + struct ww_acquire_ctx *ww_ctx, + struct rt_mutex_waiter *waiter); +void __sched rt_spin_lock_slowlock_locked(struct rt_mutex *lock, + struct rt_mutex_waiter *waiter, + unsigned long flags); +void __sched rt_spin_lock_slowunlock(struct rt_mutex *lock); #ifdef CONFIG_DEBUG_RT_MUTEXES # include "rtmutex-debug.h" diff --git a/kernel/locking/rwlock-rt.c b/kernel/locking/rwlock-rt.c new file mode 100644 index 0000000000000..cc8bc2ef4ba2d --- /dev/null +++ b/kernel/locking/rwlock-rt.c @@ -0,0 +1,340 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include +#include + +#include "rtmutex_common.h" +#include + +/* + * RT-specific reader/writer locks + * + * write_lock() + * 1) Lock lock->rtmutex + * 2) Remove the reader BIAS to force readers into the slow path + * 3) Wait until all readers have left the critical region + * 4) Mark it write locked + * + * write_unlock() + * 1) Remove the write locked marker + * 2) Set the reader BIAS so readers can use the fast path again + * 3) Unlock lock->rtmutex to release blocked readers + * + * read_lock() + * 1) Try fast path acquisition (reader BIAS is set) + * 2) Take lock->rtmutex.wait_lock which protects the writelocked flag + * 3) If !writelocked, acquire it for read + * 4) If writelocked, block on lock->rtmutex + * 5) unlock lock->rtmutex, goto 1) + * + * read_unlock() + * 1) Try fast path release (reader count != 1) + * 2) Wake the writer waiting in write_lock()#3 + * + * read_lock()#3 has the consequence, that rw locks on RT are not writer + * fair, but writers, which should be avoided in RT tasks (think tasklist + * lock), are subject to the rtmutex priority/DL inheritance mechanism. + * + * It's possible to make the rw locks writer fair by keeping a list of + * active readers. A blocked writer would force all newly incoming readers + * to block on the rtmutex, but the rtmutex would have to be proxy locked + * for one reader after the other. We can't use multi-reader inheritance + * because there is no way to support that with + * SCHED_DEADLINE. Implementing the one by one reader boosting/handover + * mechanism is a major surgery for a very dubious value. + * + * The risk of writer starvation is there, but the pathological use cases + * which trigger it are not necessarily the typical RT workloads. + */ + +void __rwlock_biased_rt_init(struct rt_rw_lock *lock, const char *name, + struct lock_class_key *key) +{ +#ifdef CONFIG_DEBUG_LOCK_ALLOC + /* + * Make sure we are not reinitializing a held semaphore: + */ + debug_check_no_locks_freed((void *)lock, sizeof(*lock)); + lockdep_init_map(&lock->dep_map, name, key, 0); +#endif + atomic_set(&lock->readers, READER_BIAS); + rt_mutex_init(&lock->rtmutex); + lock->rtmutex.save_state = 1; +} + +static int __read_rt_trylock(struct rt_rw_lock *lock) +{ + int r, old; + + /* + * Increment reader count, if lock->readers < 0, i.e. READER_BIAS is + * set. + */ + for (r = atomic_read(&lock->readers); r < 0;) { + old = atomic_cmpxchg(&lock->readers, r, r + 1); + if (likely(old == r)) + return 1; + r = old; + } + return 0; +} + +static void __read_rt_lock(struct rt_rw_lock *lock) +{ + struct rt_mutex *m = &lock->rtmutex; + struct rt_mutex_waiter waiter; + unsigned long flags; + + if (__read_rt_trylock(lock)) + return; + + raw_spin_lock_irqsave(&m->wait_lock, flags); + /* + * Allow readers as long as the writer has not completely + * acquired the semaphore for write. + */ + if (atomic_read(&lock->readers) != WRITER_BIAS) { + atomic_inc(&lock->readers); + raw_spin_unlock_irqrestore(&m->wait_lock, flags); + return; + } + + /* + * Call into the slow lock path with the rtmutex->wait_lock + * held, so this can't result in the following race: + * + * Reader1 Reader2 Writer + * read_lock() + * write_lock() + * rtmutex_lock(m) + * swait() + * read_lock() + * unlock(m->wait_lock) + * read_unlock() + * swake() + * lock(m->wait_lock) + * lock->writelocked=true + * unlock(m->wait_lock) + * + * write_unlock() + * lock->writelocked=false + * rtmutex_unlock(m) + * read_lock() + * write_lock() + * rtmutex_lock(m) + * swait() + * rtmutex_lock(m) + * + * That would put Reader1 behind the writer waiting on + * Reader2 to call read_unlock() which might be unbound. + */ + rt_mutex_init_waiter(&waiter, true); + rt_spin_lock_slowlock_locked(m, &waiter, flags); + /* + * The slowlock() above is guaranteed to return with the rtmutex is + * now held, so there can't be a writer active. Increment the reader + * count and immediately drop the rtmutex again. + */ + atomic_inc(&lock->readers); + raw_spin_unlock_irqrestore(&m->wait_lock, flags); + rt_spin_lock_slowunlock(m); + + debug_rt_mutex_free_waiter(&waiter); +} + +static void __read_rt_unlock(struct rt_rw_lock *lock) +{ + struct rt_mutex *m = &lock->rtmutex; + struct task_struct *tsk; + + /* + * sem->readers can only hit 0 when a writer is waiting for the + * active readers to leave the critical region. + */ + if (!atomic_dec_and_test(&lock->readers)) + return; + + raw_spin_lock_irq(&m->wait_lock); + /* + * Wake the writer, i.e. the rtmutex owner. It might release the + * rtmutex concurrently in the fast path, but to clean up the rw + * lock it needs to acquire m->wait_lock. The worst case which can + * happen is a spurious wakeup. + */ + tsk = rt_mutex_owner(m); + if (tsk) + wake_up_process(tsk); + + raw_spin_unlock_irq(&m->wait_lock); +} + +static void __write_unlock_common(struct rt_rw_lock *lock, int bias, + unsigned long flags) +{ + struct rt_mutex *m = &lock->rtmutex; + + atomic_add(READER_BIAS - bias, &lock->readers); + raw_spin_unlock_irqrestore(&m->wait_lock, flags); + rt_spin_lock_slowunlock(m); +} + +static void __write_rt_lock(struct rt_rw_lock *lock) +{ + struct rt_mutex *m = &lock->rtmutex; + struct task_struct *self = current; + unsigned long flags; + + /* Take the rtmutex as a first step */ + __rt_spin_lock(m); + + /* Force readers into slow path */ + atomic_sub(READER_BIAS, &lock->readers); + + raw_spin_lock_irqsave(&m->wait_lock, flags); + + raw_spin_lock(&self->pi_lock); + self->saved_state = self->state; + __set_current_state_no_track(TASK_UNINTERRUPTIBLE); + raw_spin_unlock(&self->pi_lock); + + for (;;) { + /* Have all readers left the critical region? */ + if (!atomic_read(&lock->readers)) { + atomic_set(&lock->readers, WRITER_BIAS); + raw_spin_lock(&self->pi_lock); + __set_current_state_no_track(self->saved_state); + self->saved_state = TASK_RUNNING; + raw_spin_unlock(&self->pi_lock); + raw_spin_unlock_irqrestore(&m->wait_lock, flags); + return; + } + + raw_spin_unlock_irqrestore(&m->wait_lock, flags); + + if (atomic_read(&lock->readers) != 0) + preempt_schedule_lock(); + + raw_spin_lock_irqsave(&m->wait_lock, flags); + + raw_spin_lock(&self->pi_lock); + __set_current_state_no_track(TASK_UNINTERRUPTIBLE); + raw_spin_unlock(&self->pi_lock); + } +} + +static int __write_rt_trylock(struct rt_rw_lock *lock) +{ + struct rt_mutex *m = &lock->rtmutex; + unsigned long flags; + + if (!__rt_mutex_trylock(m)) + return 0; + + atomic_sub(READER_BIAS, &lock->readers); + + raw_spin_lock_irqsave(&m->wait_lock, flags); + if (!atomic_read(&lock->readers)) { + atomic_set(&lock->readers, WRITER_BIAS); + raw_spin_unlock_irqrestore(&m->wait_lock, flags); + return 1; + } + __write_unlock_common(lock, 0, flags); + return 0; +} + +static void __write_rt_unlock(struct rt_rw_lock *lock) +{ + struct rt_mutex *m = &lock->rtmutex; + unsigned long flags; + + raw_spin_lock_irqsave(&m->wait_lock, flags); + __write_unlock_common(lock, WRITER_BIAS, flags); +} + +int __lockfunc rt_read_can_lock(rwlock_t *rwlock) +{ + return atomic_read(&rwlock->readers) < 0; +} + +int __lockfunc rt_write_can_lock(rwlock_t *rwlock) +{ + return atomic_read(&rwlock->readers) == READER_BIAS; +} + +/* + * The common functions which get wrapped into the rwlock API. + */ +int __lockfunc rt_read_trylock(rwlock_t *rwlock) +{ + int ret; + + ret = __read_rt_trylock(rwlock); + if (ret) { + rwlock_acquire_read(&rwlock->dep_map, 0, 1, _RET_IP_); + rcu_read_lock(); + migrate_disable(); + } + return ret; +} +EXPORT_SYMBOL(rt_read_trylock); + +int __lockfunc rt_write_trylock(rwlock_t *rwlock) +{ + int ret; + + ret = __write_rt_trylock(rwlock); + if (ret) { + rwlock_acquire(&rwlock->dep_map, 0, 1, _RET_IP_); + rcu_read_lock(); + migrate_disable(); + } + return ret; +} +EXPORT_SYMBOL(rt_write_trylock); + +void __lockfunc rt_read_lock(rwlock_t *rwlock) +{ + rwlock_acquire_read(&rwlock->dep_map, 0, 0, _RET_IP_); + __read_rt_lock(rwlock); + rcu_read_lock(); + migrate_disable(); +} +EXPORT_SYMBOL(rt_read_lock); + +void __lockfunc rt_write_lock(rwlock_t *rwlock) +{ + rwlock_acquire(&rwlock->dep_map, 0, 0, _RET_IP_); + __write_rt_lock(rwlock); + rcu_read_lock(); + migrate_disable(); +} +EXPORT_SYMBOL(rt_write_lock); + +void __lockfunc rt_read_unlock(rwlock_t *rwlock) +{ + rwlock_release(&rwlock->dep_map, _RET_IP_); + migrate_enable(); + rcu_read_unlock(); + __read_rt_unlock(rwlock); +} +EXPORT_SYMBOL(rt_read_unlock); + +void __lockfunc rt_write_unlock(rwlock_t *rwlock) +{ + rwlock_release(&rwlock->dep_map, _RET_IP_); + migrate_enable(); + rcu_read_unlock(); + __write_rt_unlock(rwlock); +} +EXPORT_SYMBOL(rt_write_unlock); + +void __rt_rwlock_init(rwlock_t *rwlock, char *name, struct lock_class_key *key) +{ + __rwlock_biased_rt_init(rwlock, name, key); +} +EXPORT_SYMBOL(__rt_rwlock_init); + +int __lockfunc rt_rwlock_is_contended(rwlock_t *rwlock) +{ + return rt_mutex_has_waiters(&rwlock->rtmutex); +} +EXPORT_SYMBOL(rt_rwlock_is_contended); diff --git a/kernel/locking/rwsem-rt.c b/kernel/locking/rwsem-rt.c new file mode 100644 index 0000000000000..274172d5bb3a5 --- /dev/null +++ b/kernel/locking/rwsem-rt.c @@ -0,0 +1,318 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include +#include +#include +#include +#include + +#include "rtmutex_common.h" + +/* + * RT-specific reader/writer semaphores + * + * down_write() + * 1) Lock sem->rtmutex + * 2) Remove the reader BIAS to force readers into the slow path + * 3) Wait until all readers have left the critical region + * 4) Mark it write locked + * + * up_write() + * 1) Remove the write locked marker + * 2) Set the reader BIAS so readers can use the fast path again + * 3) Unlock sem->rtmutex to release blocked readers + * + * down_read() + * 1) Try fast path acquisition (reader BIAS is set) + * 2) Take sem->rtmutex.wait_lock which protects the writelocked flag + * 3) If !writelocked, acquire it for read + * 4) If writelocked, block on sem->rtmutex + * 5) unlock sem->rtmutex, goto 1) + * + * up_read() + * 1) Try fast path release (reader count != 1) + * 2) Wake the writer waiting in down_write()#3 + * + * down_read()#3 has the consequence, that rw semaphores on RT are not writer + * fair, but writers, which should be avoided in RT tasks (think mmap_sem), + * are subject to the rtmutex priority/DL inheritance mechanism. + * + * It's possible to make the rw semaphores writer fair by keeping a list of + * active readers. A blocked writer would force all newly incoming readers to + * block on the rtmutex, but the rtmutex would have to be proxy locked for one + * reader after the other. We can't use multi-reader inheritance because there + * is no way to support that with SCHED_DEADLINE. Implementing the one by one + * reader boosting/handover mechanism is a major surgery for a very dubious + * value. + * + * The risk of writer starvation is there, but the pathological use cases + * which trigger it are not necessarily the typical RT workloads. + */ + +void __rwsem_init(struct rw_semaphore *sem, const char *name, + struct lock_class_key *key) +{ +#ifdef CONFIG_DEBUG_LOCK_ALLOC + /* + * Make sure we are not reinitializing a held semaphore: + */ + debug_check_no_locks_freed((void *)sem, sizeof(*sem)); + lockdep_init_map(&sem->dep_map, name, key, 0); +#endif + atomic_set(&sem->readers, READER_BIAS); +} +EXPORT_SYMBOL(__rwsem_init); + +int __down_read_trylock(struct rw_semaphore *sem) +{ + int r, old; + + /* + * Increment reader count, if sem->readers < 0, i.e. READER_BIAS is + * set. + */ + for (r = atomic_read(&sem->readers); r < 0;) { + old = atomic_cmpxchg(&sem->readers, r, r + 1); + if (likely(old == r)) + return 1; + r = old; + } + return 0; +} + +static int __sched __down_read_common(struct rw_semaphore *sem, int state) +{ + struct rt_mutex *m = &sem->rtmutex; + struct rt_mutex_waiter waiter; + int ret; + + if (__down_read_trylock(sem)) + return 0; + + /* + * Flush blk before ->pi_blocked_on is set. At schedule() time it is too + * late if one of the callbacks needs to acquire a sleeping lock. + */ + if (blk_needs_flush_plug(current)) + blk_schedule_flush_plug(current); + + might_sleep(); + raw_spin_lock_irq(&m->wait_lock); + /* + * Allow readers as long as the writer has not completely + * acquired the semaphore for write. + */ + if (atomic_read(&sem->readers) != WRITER_BIAS) { + atomic_inc(&sem->readers); + raw_spin_unlock_irq(&m->wait_lock); + return 0; + } + + /* + * Call into the slow lock path with the rtmutex->wait_lock + * held, so this can't result in the following race: + * + * Reader1 Reader2 Writer + * down_read() + * down_write() + * rtmutex_lock(m) + * swait() + * down_read() + * unlock(m->wait_lock) + * up_read() + * swake() + * lock(m->wait_lock) + * sem->writelocked=true + * unlock(m->wait_lock) + * + * up_write() + * sem->writelocked=false + * rtmutex_unlock(m) + * down_read() + * down_write() + * rtmutex_lock(m) + * swait() + * rtmutex_lock(m) + * + * That would put Reader1 behind the writer waiting on + * Reader2 to call up_read() which might be unbound. + */ + rt_mutex_init_waiter(&waiter, false); + ret = rt_mutex_slowlock_locked(m, state, NULL, RT_MUTEX_MIN_CHAINWALK, + NULL, &waiter); + /* + * The slowlock() above is guaranteed to return with the rtmutex (for + * ret = 0) is now held, so there can't be a writer active. Increment + * the reader count and immediately drop the rtmutex again. + * For ret != 0 we don't hold the rtmutex and need unlock the wait_lock. + * We don't own the lock then. + */ + if (!ret) + atomic_inc(&sem->readers); + raw_spin_unlock_irq(&m->wait_lock); + if (!ret) + __rt_mutex_unlock(m); + + debug_rt_mutex_free_waiter(&waiter); + return ret; +} + +void __down_read(struct rw_semaphore *sem) +{ + int ret; + + ret = __down_read_common(sem, TASK_UNINTERRUPTIBLE); + WARN_ON_ONCE(ret); +} + +int __down_read_interruptible(struct rw_semaphore *sem) +{ + int ret; + + ret = __down_read_common(sem, TASK_INTERRUPTIBLE); + if (likely(!ret)) + return ret; + WARN_ONCE(ret != -EINTR, "Unexpected state: %d\n", ret); + return -EINTR; +} + +int __down_read_killable(struct rw_semaphore *sem) +{ + int ret; + + ret = __down_read_common(sem, TASK_KILLABLE); + if (likely(!ret)) + return ret; + WARN_ONCE(ret != -EINTR, "Unexpected state: %d\n", ret); + return -EINTR; +} + +void __up_read(struct rw_semaphore *sem) +{ + struct rt_mutex *m = &sem->rtmutex; + struct task_struct *tsk; + + /* + * sem->readers can only hit 0 when a writer is waiting for the + * active readers to leave the critical region. + */ + if (!atomic_dec_and_test(&sem->readers)) + return; + + might_sleep(); + raw_spin_lock_irq(&m->wait_lock); + /* + * Wake the writer, i.e. the rtmutex owner. It might release the + * rtmutex concurrently in the fast path (due to a signal), but to + * clean up the rwsem it needs to acquire m->wait_lock. The worst + * case which can happen is a spurious wakeup. + */ + tsk = rt_mutex_owner(m); + if (tsk) + wake_up_process(tsk); + + raw_spin_unlock_irq(&m->wait_lock); +} + +static void __up_write_unlock(struct rw_semaphore *sem, int bias, + unsigned long flags) +{ + struct rt_mutex *m = &sem->rtmutex; + + atomic_add(READER_BIAS - bias, &sem->readers); + raw_spin_unlock_irqrestore(&m->wait_lock, flags); + __rt_mutex_unlock(m); +} + +static int __sched __down_write_common(struct rw_semaphore *sem, int state) +{ + struct rt_mutex *m = &sem->rtmutex; + unsigned long flags; + + /* + * Flush blk before ->pi_blocked_on is set. At schedule() time it is too + * late if one of the callbacks needs to acquire a sleeping lock. + */ + if (blk_needs_flush_plug(current)) + blk_schedule_flush_plug(current); + + /* Take the rtmutex as a first step */ + if (__rt_mutex_lock_state(m, state)) + return -EINTR; + + /* Force readers into slow path */ + atomic_sub(READER_BIAS, &sem->readers); + might_sleep(); + + set_current_state(state); + for (;;) { + raw_spin_lock_irqsave(&m->wait_lock, flags); + /* Have all readers left the critical region? */ + if (!atomic_read(&sem->readers)) { + atomic_set(&sem->readers, WRITER_BIAS); + __set_current_state(TASK_RUNNING); + raw_spin_unlock_irqrestore(&m->wait_lock, flags); + return 0; + } + + if (signal_pending_state(state, current)) { + __set_current_state(TASK_RUNNING); + __up_write_unlock(sem, 0, flags); + return -EINTR; + } + raw_spin_unlock_irqrestore(&m->wait_lock, flags); + + if (atomic_read(&sem->readers) != 0) { + schedule(); + set_current_state(state); + } + } +} + +void __sched __down_write(struct rw_semaphore *sem) +{ + __down_write_common(sem, TASK_UNINTERRUPTIBLE); +} + +int __sched __down_write_killable(struct rw_semaphore *sem) +{ + return __down_write_common(sem, TASK_KILLABLE); +} + +int __down_write_trylock(struct rw_semaphore *sem) +{ + struct rt_mutex *m = &sem->rtmutex; + unsigned long flags; + + if (!__rt_mutex_trylock(m)) + return 0; + + atomic_sub(READER_BIAS, &sem->readers); + + raw_spin_lock_irqsave(&m->wait_lock, flags); + if (!atomic_read(&sem->readers)) { + atomic_set(&sem->readers, WRITER_BIAS); + raw_spin_unlock_irqrestore(&m->wait_lock, flags); + return 1; + } + __up_write_unlock(sem, 0, flags); + return 0; +} + +void __up_write(struct rw_semaphore *sem) +{ + struct rt_mutex *m = &sem->rtmutex; + unsigned long flags; + + raw_spin_lock_irqsave(&m->wait_lock, flags); + __up_write_unlock(sem, WRITER_BIAS, flags); +} + +void __downgrade_write(struct rw_semaphore *sem) +{ + struct rt_mutex *m = &sem->rtmutex; + unsigned long flags; + + raw_spin_lock_irqsave(&m->wait_lock, flags); + /* Release it and account current as reader */ + __up_write_unlock(sem, WRITER_BIAS - 1, flags); +} diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c index abba5df500060..bed9a5e32a16c 100644 --- a/kernel/locking/rwsem.c +++ b/kernel/locking/rwsem.c @@ -28,6 +28,7 @@ #include #include +#ifndef CONFIG_PREEMPT_RT #include "lock_events.h" /* @@ -1343,6 +1344,7 @@ static inline void __downgrade_write(struct rw_semaphore *sem) if (tmp & RWSEM_FLAG_WAITERS) rwsem_downgrade_wake(sem); } +#endif /* * lock for reading @@ -1506,7 +1508,9 @@ void down_read_non_owner(struct rw_semaphore *sem) { might_sleep(); __down_read(sem); +#ifndef CONFIG_PREEMPT_RT __rwsem_set_reader_owned(sem, NULL); +#endif } EXPORT_SYMBOL(down_read_non_owner); @@ -1535,7 +1539,9 @@ EXPORT_SYMBOL(down_write_killable_nested); void up_read_non_owner(struct rw_semaphore *sem) { +#ifndef CONFIG_PREEMPT_RT DEBUG_RWSEMS_WARN_ON(!is_rwsem_reader_owned(sem), sem); +#endif __up_read(sem); } EXPORT_SYMBOL(up_read_non_owner); diff --git a/kernel/locking/spinlock.c b/kernel/locking/spinlock.c index 0ff08380f5318..45445a2f1799a 100644 --- a/kernel/locking/spinlock.c +++ b/kernel/locking/spinlock.c @@ -124,8 +124,11 @@ void __lockfunc __raw_##op##_lock_bh(locktype##_t *lock) \ * __[spin|read|write]_lock_bh() */ BUILD_LOCK_OPS(spin, raw_spinlock); + +#ifndef CONFIG_PREEMPT_RT BUILD_LOCK_OPS(read, rwlock); BUILD_LOCK_OPS(write, rwlock); +#endif #endif @@ -209,6 +212,8 @@ void __lockfunc _raw_spin_unlock_bh(raw_spinlock_t *lock) EXPORT_SYMBOL(_raw_spin_unlock_bh); #endif +#ifndef CONFIG_PREEMPT_RT + #ifndef CONFIG_INLINE_READ_TRYLOCK int __lockfunc _raw_read_trylock(rwlock_t *lock) { @@ -353,6 +358,8 @@ void __lockfunc _raw_write_unlock_bh(rwlock_t *lock) EXPORT_SYMBOL(_raw_write_unlock_bh); #endif +#endif /* !PREEMPT_RT */ + #ifdef CONFIG_DEBUG_LOCK_ALLOC void __lockfunc _raw_spin_lock_nested(raw_spinlock_t *lock, int subclass) diff --git a/kernel/locking/spinlock_debug.c b/kernel/locking/spinlock_debug.c index b9d93087ee669..72e306e0e8a3b 100644 --- a/kernel/locking/spinlock_debug.c +++ b/kernel/locking/spinlock_debug.c @@ -31,6 +31,7 @@ void __raw_spin_lock_init(raw_spinlock_t *lock, const char *name, EXPORT_SYMBOL(__raw_spin_lock_init); +#ifndef CONFIG_PREEMPT_RT void __rwlock_init(rwlock_t *lock, const char *name, struct lock_class_key *key) { @@ -48,6 +49,7 @@ void __rwlock_init(rwlock_t *lock, const char *name, } EXPORT_SYMBOL(__rwlock_init); +#endif static void spin_dump(raw_spinlock_t *lock, const char *msg) { @@ -139,6 +141,7 @@ void do_raw_spin_unlock(raw_spinlock_t *lock) arch_spin_unlock(&lock->raw_lock); } +#ifndef CONFIG_PREEMPT_RT static void rwlock_bug(rwlock_t *lock, const char *msg) { if (!debug_locks_off()) @@ -228,3 +231,5 @@ void do_raw_write_unlock(rwlock_t *lock) debug_write_unlock(lock); arch_write_unlock(&lock->raw_lock); } + +#endif diff --git a/kernel/notifier.c b/kernel/notifier.c index 1b019cbca594a..c20782f076432 100644 --- a/kernel/notifier.c +++ b/kernel/notifier.c @@ -142,9 +142,9 @@ int atomic_notifier_chain_register(struct atomic_notifier_head *nh, unsigned long flags; int ret; - spin_lock_irqsave(&nh->lock, flags); + raw_spin_lock_irqsave(&nh->lock, flags); ret = notifier_chain_register(&nh->head, n); - spin_unlock_irqrestore(&nh->lock, flags); + raw_spin_unlock_irqrestore(&nh->lock, flags); return ret; } EXPORT_SYMBOL_GPL(atomic_notifier_chain_register); @@ -164,9 +164,9 @@ int atomic_notifier_chain_unregister(struct atomic_notifier_head *nh, unsigned long flags; int ret; - spin_lock_irqsave(&nh->lock, flags); + raw_spin_lock_irqsave(&nh->lock, flags); ret = notifier_chain_unregister(&nh->head, n); - spin_unlock_irqrestore(&nh->lock, flags); + raw_spin_unlock_irqrestore(&nh->lock, flags); synchronize_rcu(); return ret; } @@ -182,9 +182,9 @@ int atomic_notifier_call_chain_robust(struct atomic_notifier_head *nh, * Musn't use RCU; because then the notifier list can * change between the up and down traversal. */ - spin_lock_irqsave(&nh->lock, flags); + raw_spin_lock_irqsave(&nh->lock, flags); ret = notifier_call_chain_robust(&nh->head, val_up, val_down, v); - spin_unlock_irqrestore(&nh->lock, flags); + raw_spin_unlock_irqrestore(&nh->lock, flags); return ret; } diff --git a/kernel/panic.c b/kernel/panic.c index 332736a72a58e..a14e2f5a9f550 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -177,12 +177,28 @@ static void panic_print_sys_info(void) void panic(const char *fmt, ...) { static char buf[1024]; + va_list args2; va_list args; long i, i_next = 0, len; int state = 0; int old_cpu, this_cpu; bool _crash_kexec_post_notifiers = crash_kexec_post_notifiers; + console_verbose(); + pr_emerg("Kernel panic - not syncing:\n"); + va_start(args2, fmt); + va_copy(args, args2); + vprintk(fmt, args2); + va_end(args2); +#ifdef CONFIG_DEBUG_BUGVERBOSE + /* + * Avoid nested stack-dumping if a panic occurs during oops processing + */ + if (!test_taint(TAINT_DIE) && oops_in_progress <= 1) + dump_stack(); +#endif + pr_flush(1000, true); + /* * Disable local interrupts. This will prevent panic_smp_self_stop * from deadlocking the first cpu that invokes the panic, since @@ -213,24 +229,13 @@ void panic(const char *fmt, ...) if (old_cpu != PANIC_CPU_INVALID && old_cpu != this_cpu) panic_smp_self_stop(); - console_verbose(); bust_spinlocks(1); - va_start(args, fmt); len = vscnprintf(buf, sizeof(buf), fmt, args); va_end(args); if (len && buf[len - 1] == '\n') buf[len - 1] = '\0'; - pr_emerg("Kernel panic - not syncing: %s\n", buf); -#ifdef CONFIG_DEBUG_BUGVERBOSE - /* - * Avoid nested stack-dumping if a panic occurs during oops processing - */ - if (!test_taint(TAINT_DIE) && oops_in_progress <= 1) - dump_stack(); -#endif - /* * If kgdb is enabled, give it a chance to run before we stop all * the other CPUs or else we won't be able to debug processes left @@ -247,7 +252,6 @@ void panic(const char *fmt, ...) * Bypass the panic_cpu check and call __crash_kexec directly. */ if (!_crash_kexec_post_notifiers) { - printk_safe_flush_on_panic(); __crash_kexec(NULL); /* @@ -271,8 +275,6 @@ void panic(const char *fmt, ...) */ atomic_notifier_call_chain(&panic_notifier_list, 0, buf); - /* Call flush even twice. It tries harder with a single online CPU */ - printk_safe_flush_on_panic(); kmsg_dump(KMSG_DUMP_PANIC); /* @@ -542,9 +544,11 @@ static u64 oops_id; static int init_oops_id(void) { +#ifndef CONFIG_PREEMPT_RT if (!oops_id) get_random_bytes(&oops_id, sizeof(oops_id)); else +#endif oops_id++; return 0; @@ -555,6 +559,7 @@ static void print_oops_end_marker(void) { init_oops_id(); pr_warn("---[ end trace %016llx ]---\n", (unsigned long long)oops_id); + pr_flush(1000, true); } /* diff --git a/kernel/printk/Makefile b/kernel/printk/Makefile index eee3dc9b60a9a..59cb24e25f004 100644 --- a/kernel/printk/Makefile +++ b/kernel/printk/Makefile @@ -1,5 +1,4 @@ # SPDX-License-Identifier: GPL-2.0-only obj-y = printk.o -obj-$(CONFIG_PRINTK) += printk_safe.o obj-$(CONFIG_A11Y_BRAILLE_CONSOLE) += braille.o obj-$(CONFIG_PRINTK) += printk_ringbuffer.o diff --git a/kernel/printk/internal.h b/kernel/printk/internal.h deleted file mode 100644 index 3a8fd491758cf..0000000000000 --- a/kernel/printk/internal.h +++ /dev/null @@ -1,74 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * internal.h - printk internal definitions - */ -#include - -#ifdef CONFIG_PRINTK - -#define PRINTK_SAFE_CONTEXT_MASK 0x007ffffff -#define PRINTK_NMI_DIRECT_CONTEXT_MASK 0x008000000 -#define PRINTK_NMI_CONTEXT_MASK 0xff0000000 - -#define PRINTK_NMI_CONTEXT_OFFSET 0x010000000 - -extern raw_spinlock_t logbuf_lock; - -__printf(4, 0) -int vprintk_store(int facility, int level, - const struct dev_printk_info *dev_info, - const char *fmt, va_list args); - -__printf(1, 0) int vprintk_default(const char *fmt, va_list args); -__printf(1, 0) int vprintk_deferred(const char *fmt, va_list args); -__printf(1, 0) int vprintk_func(const char *fmt, va_list args); -void __printk_safe_enter(void); -void __printk_safe_exit(void); - -void printk_safe_init(void); -bool printk_percpu_data_ready(void); - -#define printk_safe_enter_irqsave(flags) \ - do { \ - local_irq_save(flags); \ - __printk_safe_enter(); \ - } while (0) - -#define printk_safe_exit_irqrestore(flags) \ - do { \ - __printk_safe_exit(); \ - local_irq_restore(flags); \ - } while (0) - -#define printk_safe_enter_irq() \ - do { \ - local_irq_disable(); \ - __printk_safe_enter(); \ - } while (0) - -#define printk_safe_exit_irq() \ - do { \ - __printk_safe_exit(); \ - local_irq_enable(); \ - } while (0) - -void defer_console_output(void); - -#else - -__printf(1, 0) int vprintk_func(const char *fmt, va_list args) { return 0; } - -/* - * In !PRINTK builds we still export logbuf_lock spin_lock, console_sem - * semaphore and some of console functions (console_unlock()/etc.), so - * printk-safe must preserve the existing local IRQ guarantees. - */ -#define printk_safe_enter_irqsave(flags) local_irq_save(flags) -#define printk_safe_exit_irqrestore(flags) local_irq_restore(flags) - -#define printk_safe_enter_irq() local_irq_disable() -#define printk_safe_exit_irq() local_irq_enable() - -static inline void printk_safe_init(void) { } -static inline bool printk_percpu_data_ready(void) { return false; } -#endif /* CONFIG_PRINTK */ diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 575a34b88936f..c2ef8089bfd2f 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -44,6 +44,10 @@ #include #include #include +#include +#include +#include +#include #include #include #include @@ -58,7 +62,6 @@ #include "printk_ringbuffer.h" #include "console_cmdline.h" #include "braille.h" -#include "internal.h" int console_printk[4] = { CONSOLE_LOGLEVEL_DEFAULT, /* console_loglevel */ @@ -225,19 +228,7 @@ static int nr_ext_console_drivers; static int __down_trylock_console_sem(unsigned long ip) { - int lock_failed; - unsigned long flags; - - /* - * Here and in __up_console_sem() we need to be in safe mode, - * because spindump/WARN/etc from under console ->lock will - * deadlock in printk()->down_trylock_console_sem() otherwise. - */ - printk_safe_enter_irqsave(flags); - lock_failed = down_trylock(&console_sem); - printk_safe_exit_irqrestore(flags); - - if (lock_failed) + if (down_trylock(&console_sem)) return 1; mutex_acquire(&console_lock_dep_map, 0, 1, ip); return 0; @@ -246,13 +237,9 @@ static int __down_trylock_console_sem(unsigned long ip) static void __up_console_sem(unsigned long ip) { - unsigned long flags; - mutex_release(&console_lock_dep_map, ip); - printk_safe_enter_irqsave(flags); up(&console_sem); - printk_safe_exit_irqrestore(flags); } #define up_console_sem() __up_console_sem(_RET_IP_) @@ -266,11 +253,6 @@ static void __up_console_sem(unsigned long ip) */ static int console_locked, console_suspended; -/* - * If exclusive_console is non-NULL then only this console is to be printed to. - */ -static struct console *exclusive_console; - /* * Array of consoles built from command line options (console=) */ @@ -355,62 +337,39 @@ enum log_flags { LOG_CONT = 8, /* text is a fragment of a continuation line */ }; -/* - * The logbuf_lock protects kmsg buffer, indices, counters. This can be taken - * within the scheduler's rq lock. It must be released before calling - * console_unlock() or anything else that might wake up a process. - */ -DEFINE_RAW_SPINLOCK(logbuf_lock); - -/* - * Helper macros to lock/unlock logbuf_lock and switch between - * printk-safe/unsafe modes. - */ -#define logbuf_lock_irq() \ - do { \ - printk_safe_enter_irq(); \ - raw_spin_lock(&logbuf_lock); \ - } while (0) - -#define logbuf_unlock_irq() \ - do { \ - raw_spin_unlock(&logbuf_lock); \ - printk_safe_exit_irq(); \ - } while (0) - -#define logbuf_lock_irqsave(flags) \ - do { \ - printk_safe_enter_irqsave(flags); \ - raw_spin_lock(&logbuf_lock); \ - } while (0) - -#define logbuf_unlock_irqrestore(flags) \ - do { \ - raw_spin_unlock(&logbuf_lock); \ - printk_safe_exit_irqrestore(flags); \ - } while (0) - #ifdef CONFIG_PRINTK +/* syslog_lock protects syslog_* variables and write access to clear_seq. */ +static DEFINE_SPINLOCK(syslog_lock); + +/* Set to enable sync mode. Once set, it is never cleared. */ +static bool sync_mode; + DECLARE_WAIT_QUEUE_HEAD(log_wait); +/* All 3 protected by @syslog_lock. */ /* the next printk record to read by syslog(READ) or /proc/kmsg */ static u64 syslog_seq; static size_t syslog_partial; static bool syslog_time; -/* the next printk record to write to the console */ -static u64 console_seq; -static u64 exclusive_console_stop_seq; -static unsigned long console_dropped; - -/* the next printk record to read after the last 'clear' command */ -static u64 clear_seq; +/* + * The next printk record to read after the last 'clear' command. There are + * two copies (updated with seqcount_latch) so that reads can locklessly + * access a valid value. Writers are synchronized by @syslog_lock. + */ +static struct latched_seq clear_seq = { + .latch = SEQCNT_LATCH_ZERO(clear_seq.latch), + .val[0] = 0, + .val[1] = 0, +}; #ifdef CONFIG_PRINTK_CALLER #define PREFIX_MAX 48 #else #define PREFIX_MAX 32 #endif -#define LOG_LINE_MAX (1024 - PREFIX_MAX) + +/* the maximum size allowed to be reserved for a record */ +#define LOG_LINE_MAX (CONSOLE_LOG_MAX - PREFIX_MAX) #define LOG_LEVEL(v) ((v) & 0x07) #define LOG_FACILITY(v) ((v) >> 3 & 0xff) @@ -447,11 +406,36 @@ static struct printk_ringbuffer *prb = &printk_rb_static; */ static bool __printk_percpu_data_ready __read_mostly; -bool printk_percpu_data_ready(void) +static bool printk_percpu_data_ready(void) { return __printk_percpu_data_ready; } +/* Must be called under associated write-protection lock. */ +static void latched_seq_write(struct latched_seq *ls, u64 val) +{ + raw_write_seqcount_latch(&ls->latch); + ls->val[0] = val; + raw_write_seqcount_latch(&ls->latch); + ls->val[1] = val; +} + +/* Can be called from any context. */ +static u64 latched_seq_read_nolock(struct latched_seq *ls) +{ + unsigned int seq; + unsigned int idx; + u64 val; + + do { + seq = raw_read_seqcount_latch(&ls->latch); + idx = seq & 0x1; + val = ls->val[idx]; + } while (read_seqcount_latch_retry(&ls->latch, seq)); + + return val; +} + /* Return log buffer address */ char *log_buf_addr_get(void) { @@ -619,7 +603,7 @@ static ssize_t msg_print_ext_body(char *buf, size_t size, /* /dev/kmsg - userspace message inject/listen interface */ struct devkmsg_user { - u64 seq; + atomic64_t seq; struct ratelimit_state rs; struct mutex lock; char buf[CONSOLE_EXT_LOG_MAX]; @@ -719,27 +703,22 @@ static ssize_t devkmsg_read(struct file *file, char __user *buf, if (ret) return ret; - logbuf_lock_irq(); - if (!prb_read_valid(prb, user->seq, r)) { + if (!prb_read_valid(prb, atomic64_read(&user->seq), r)) { if (file->f_flags & O_NONBLOCK) { ret = -EAGAIN; - logbuf_unlock_irq(); goto out; } - logbuf_unlock_irq(); ret = wait_event_interruptible(log_wait, - prb_read_valid(prb, user->seq, r)); + prb_read_valid(prb, atomic64_read(&user->seq), r)); if (ret) goto out; - logbuf_lock_irq(); } - if (r->info->seq != user->seq) { + if (r->info->seq != atomic64_read(&user->seq)) { /* our last seen message is gone, return error and reset */ - user->seq = r->info->seq; + atomic64_set(&user->seq, r->info->seq); ret = -EPIPE; - logbuf_unlock_irq(); goto out; } @@ -748,8 +727,7 @@ static ssize_t devkmsg_read(struct file *file, char __user *buf, &r->text_buf[0], r->info->text_len, &r->info->dev_info); - user->seq = r->info->seq + 1; - logbuf_unlock_irq(); + atomic64_set(&user->seq, r->info->seq + 1); if (len > count) { ret = -EINVAL; @@ -784,11 +762,10 @@ static loff_t devkmsg_llseek(struct file *file, loff_t offset, int whence) if (offset) return -ESPIPE; - logbuf_lock_irq(); switch (whence) { case SEEK_SET: /* the first record */ - user->seq = prb_first_valid_seq(prb); + atomic64_set(&user->seq, prb_first_valid_seq(prb)); break; case SEEK_DATA: /* @@ -796,16 +773,15 @@ static loff_t devkmsg_llseek(struct file *file, loff_t offset, int whence) * like issued by 'dmesg -c'. Reading /dev/kmsg itself * changes no global state, and does not clear anything. */ - user->seq = clear_seq; + atomic64_set(&user->seq, latched_seq_read_nolock(&clear_seq)); break; case SEEK_END: /* after the last record */ - user->seq = prb_next_seq(prb); + atomic64_set(&user->seq, prb_next_seq(prb)); break; default: ret = -EINVAL; } - logbuf_unlock_irq(); return ret; } @@ -820,15 +796,13 @@ static __poll_t devkmsg_poll(struct file *file, poll_table *wait) poll_wait(file, &log_wait, wait); - logbuf_lock_irq(); - if (prb_read_valid_info(prb, user->seq, &info, NULL)) { + if (prb_read_valid_info(prb, atomic64_read(&user->seq), &info, NULL)) { /* return error when data has vanished underneath us */ - if (info.seq != user->seq) + if (info.seq != atomic64_read(&user->seq)) ret = EPOLLIN|EPOLLRDNORM|EPOLLERR|EPOLLPRI; else ret = EPOLLIN|EPOLLRDNORM; } - logbuf_unlock_irq(); return ret; } @@ -861,9 +835,7 @@ static int devkmsg_open(struct inode *inode, struct file *file) prb_rec_init_rd(&user->record, &user->info, &user->text_buf[0], sizeof(user->text_buf)); - logbuf_lock_irq(); - user->seq = prb_first_valid_seq(prb); - logbuf_unlock_irq(); + atomic64_set(&user->seq, prb_first_valid_seq(prb)); file->private_data = user; return 0; @@ -955,6 +927,9 @@ void log_buf_vmcoreinfo_setup(void) VMCOREINFO_SIZE(atomic_long_t); VMCOREINFO_TYPE_OFFSET(atomic_long_t, counter); + + VMCOREINFO_STRUCT_SIZE(latched_seq); + VMCOREINFO_OFFSET(latched_seq, val); } #endif @@ -1026,9 +1001,6 @@ static inline void log_buf_add_cpu(void) {} static void __init set_percpu_data_ready(void) { - printk_safe_init(); - /* Make sure we set this flag only after printk_safe() init is done */ - barrier(); __printk_percpu_data_ready = true; } @@ -1068,7 +1040,6 @@ void __init setup_log_buf(int early) struct printk_record r; size_t new_descs_size; size_t new_infos_size; - unsigned long flags; char *new_log_buf; unsigned int free; u64 seq; @@ -1126,8 +1097,6 @@ void __init setup_log_buf(int early) new_descs, ilog2(new_descs_count), new_infos); - printk_safe_enter_irqsave(flags); - log_buf_len = new_log_buf_len; log_buf = new_log_buf; new_log_buf_len = 0; @@ -1143,8 +1112,6 @@ void __init setup_log_buf(int early) */ prb = &printk_rb_dynamic; - printk_safe_exit_irqrestore(flags); - if (seq != prb_next_seq(&printk_rb_static)) { pr_err("dropped %llu messages\n", prb_next_seq(&printk_rb_static) - seq); @@ -1421,6 +1388,50 @@ static size_t get_record_print_text_size(struct printk_info *info, return ((prefix_len * line_count) + info->text_len + 1); } +/* + * Beginning with @start_seq, find the first record where it and all following + * records up to (but not including) @max_seq fit into @size. + * + * @max_seq is simply an upper bound and does not need to exist. If the caller + * does not require an upper bound, -1 can be used for @max_seq. + */ +static u64 find_first_fitting_seq(u64 start_seq, u64 max_seq, size_t size, + bool syslog, bool time) +{ + struct printk_info info; + unsigned int line_count; + size_t len = 0; + u64 seq; + + /* Determine the size of the records up to @max_seq. */ + prb_for_each_info(start_seq, prb, seq, &info, &line_count) { + if (info.seq >= max_seq) + break; + len += get_record_print_text_size(&info, line_count, syslog, time); + } + + /* + * Adjust the upper bound for the next loop to avoid subtracting + * lengths that were never added. + */ + if (seq < max_seq) + max_seq = seq; + + /* + * Move first record forward until length fits into the buffer. Ignore + * newest messages that were not counted in the above cycle. Messages + * might appear and get lost in the meantime. This is a best effort + * that prevents an infinite loop that could occur with a retry. + */ + prb_for_each_info(start_seq, prb, seq, &info, &line_count) { + if (len <= size || info.seq >= max_seq) + break; + len -= get_record_print_text_size(&info, line_count, syslog, time); + } + + return seq; +} + static int syslog_print(char __user *buf, int size) { struct printk_info info; @@ -1428,19 +1439,19 @@ static int syslog_print(char __user *buf, int size) char *text; int len = 0; - text = kmalloc(LOG_LINE_MAX + PREFIX_MAX, GFP_KERNEL); + text = kmalloc(CONSOLE_LOG_MAX, GFP_KERNEL); if (!text) return -ENOMEM; - prb_rec_init_rd(&r, &info, text, LOG_LINE_MAX + PREFIX_MAX); + prb_rec_init_rd(&r, &info, text, CONSOLE_LOG_MAX); while (size > 0) { size_t n; size_t skip; - logbuf_lock_irq(); + spin_lock_irq(&syslog_lock); if (!prb_read_valid(prb, syslog_seq, &r)) { - logbuf_unlock_irq(); + spin_unlock_irq(&syslog_lock); break; } if (r.info->seq != syslog_seq) { @@ -1469,7 +1480,7 @@ static int syslog_print(char __user *buf, int size) syslog_partial += n; } else n = 0; - logbuf_unlock_irq(); + spin_unlock_irq(&syslog_lock); if (!n) break; @@ -1492,34 +1503,25 @@ static int syslog_print(char __user *buf, int size) static int syslog_print_all(char __user *buf, int size, bool clear) { struct printk_info info; - unsigned int line_count; struct printk_record r; char *text; int len = 0; u64 seq; bool time; - text = kmalloc(LOG_LINE_MAX + PREFIX_MAX, GFP_KERNEL); + text = kmalloc(CONSOLE_LOG_MAX, GFP_KERNEL); if (!text) return -ENOMEM; time = printk_time; - logbuf_lock_irq(); /* * Find first record that fits, including all following records, * into the user-provided buffer for this dump. */ - prb_for_each_info(clear_seq, prb, seq, &info, &line_count) - len += get_record_print_text_size(&info, line_count, true, time); + seq = find_first_fitting_seq(latched_seq_read_nolock(&clear_seq), -1, + size, true, time); - /* move first record forward until length fits into the buffer */ - prb_for_each_info(clear_seq, prb, seq, &info, &line_count) { - if (len <= size) - break; - len -= get_record_print_text_size(&info, line_count, true, time); - } - - prb_rec_init_rd(&r, &info, text, LOG_LINE_MAX + PREFIX_MAX); + prb_rec_init_rd(&r, &info, text, CONSOLE_LOG_MAX); len = 0; prb_for_each_record(seq, prb, seq, &r) { @@ -1532,20 +1534,20 @@ static int syslog_print_all(char __user *buf, int size, bool clear) break; } - logbuf_unlock_irq(); if (copy_to_user(buf + len, text, textlen)) len = -EFAULT; else len += textlen; - logbuf_lock_irq(); if (len < 0) break; } - if (clear) - clear_seq = seq; - logbuf_unlock_irq(); + if (clear) { + spin_lock_irq(&syslog_lock); + latched_seq_write(&clear_seq, seq); + spin_unlock_irq(&syslog_lock); + } kfree(text); return len; @@ -1553,9 +1555,21 @@ static int syslog_print_all(char __user *buf, int size, bool clear) static void syslog_clear(void) { - logbuf_lock_irq(); - clear_seq = prb_next_seq(prb); - logbuf_unlock_irq(); + spin_lock_irq(&syslog_lock); + latched_seq_write(&clear_seq, prb_next_seq(prb)); + spin_unlock_irq(&syslog_lock); +} + +/* Return a consistent copy of @syslog_seq. */ +static u64 read_syslog_seq_irq(void) +{ + u64 seq; + + spin_lock_irq(&syslog_lock); + seq = syslog_seq; + spin_unlock_irq(&syslog_lock); + + return seq; } int do_syslog(int type, char __user *buf, int len, int source) @@ -1581,8 +1595,9 @@ int do_syslog(int type, char __user *buf, int len, int source) return 0; if (!access_ok(buf, len)) return -EFAULT; + error = wait_event_interruptible(log_wait, - prb_read_valid(prb, syslog_seq, NULL)); + prb_read_valid(prb, read_syslog_seq_irq(), NULL)); if (error) return error; error = syslog_print(buf, len); @@ -1630,10 +1645,10 @@ int do_syslog(int type, char __user *buf, int len, int source) break; /* Number of chars in the log buffer */ case SYSLOG_ACTION_SIZE_UNREAD: - logbuf_lock_irq(); + spin_lock_irq(&syslog_lock); if (!prb_read_valid_info(prb, syslog_seq, &info, NULL)) { /* No unread messages. */ - logbuf_unlock_irq(); + spin_unlock_irq(&syslog_lock); return 0; } if (info.seq != syslog_seq) { @@ -1661,7 +1676,7 @@ int do_syslog(int type, char __user *buf, int len, int source) } error -= syslog_partial; } - logbuf_unlock_irq(); + spin_unlock_irq(&syslog_lock); break; /* Size of the log buffer */ case SYSLOG_ACTION_SIZE_BUFFER: @@ -1680,194 +1695,12 @@ SYSCALL_DEFINE3(syslog, int, type, char __user *, buf, int, len) return do_syslog(type, buf, len, SYSLOG_FROM_READER); } -/* - * Special console_lock variants that help to reduce the risk of soft-lockups. - * They allow to pass console_lock to another printk() call using a busy wait. - */ - -#ifdef CONFIG_LOCKDEP -static struct lockdep_map console_owner_dep_map = { - .name = "console_owner" -}; -#endif - -static DEFINE_RAW_SPINLOCK(console_owner_lock); -static struct task_struct *console_owner; -static bool console_waiter; - -/** - * console_lock_spinning_enable - mark beginning of code where another - * thread might safely busy wait - * - * This basically converts console_lock into a spinlock. This marks - * the section where the console_lock owner can not sleep, because - * there may be a waiter spinning (like a spinlock). Also it must be - * ready to hand over the lock at the end of the section. - */ -static void console_lock_spinning_enable(void) -{ - raw_spin_lock(&console_owner_lock); - console_owner = current; - raw_spin_unlock(&console_owner_lock); - - /* The waiter may spin on us after setting console_owner */ - spin_acquire(&console_owner_dep_map, 0, 0, _THIS_IP_); -} - -/** - * console_lock_spinning_disable_and_check - mark end of code where another - * thread was able to busy wait and check if there is a waiter - * - * This is called at the end of the section where spinning is allowed. - * It has two functions. First, it is a signal that it is no longer - * safe to start busy waiting for the lock. Second, it checks if - * there is a busy waiter and passes the lock rights to her. - * - * Important: Callers lose the lock if there was a busy waiter. - * They must not touch items synchronized by console_lock - * in this case. - * - * Return: 1 if the lock rights were passed, 0 otherwise. - */ -static int console_lock_spinning_disable_and_check(void) -{ - int waiter; - - raw_spin_lock(&console_owner_lock); - waiter = READ_ONCE(console_waiter); - console_owner = NULL; - raw_spin_unlock(&console_owner_lock); - - if (!waiter) { - spin_release(&console_owner_dep_map, _THIS_IP_); - return 0; - } - - /* The waiter is now free to continue */ - WRITE_ONCE(console_waiter, false); - - spin_release(&console_owner_dep_map, _THIS_IP_); - - /* - * Hand off console_lock to waiter. The waiter will perform - * the up(). After this, the waiter is the console_lock owner. - */ - mutex_release(&console_lock_dep_map, _THIS_IP_); - return 1; -} - -/** - * console_trylock_spinning - try to get console_lock by busy waiting - * - * This allows to busy wait for the console_lock when the current - * owner is running in specially marked sections. It means that - * the current owner is running and cannot reschedule until it - * is ready to lose the lock. - * - * Return: 1 if we got the lock, 0 othrewise - */ -static int console_trylock_spinning(void) -{ - struct task_struct *owner = NULL; - bool waiter; - bool spin = false; - unsigned long flags; - - if (console_trylock()) - return 1; - - printk_safe_enter_irqsave(flags); - - raw_spin_lock(&console_owner_lock); - owner = READ_ONCE(console_owner); - waiter = READ_ONCE(console_waiter); - if (!waiter && owner && owner != current) { - WRITE_ONCE(console_waiter, true); - spin = true; - } - raw_spin_unlock(&console_owner_lock); - - /* - * If there is an active printk() writing to the - * consoles, instead of having it write our data too, - * see if we can offload that load from the active - * printer, and do some printing ourselves. - * Go into a spin only if there isn't already a waiter - * spinning, and there is an active printer, and - * that active printer isn't us (recursive printk?). - */ - if (!spin) { - printk_safe_exit_irqrestore(flags); - return 0; - } - - /* We spin waiting for the owner to release us */ - spin_acquire(&console_owner_dep_map, 0, 0, _THIS_IP_); - /* Owner will clear console_waiter on hand off */ - while (READ_ONCE(console_waiter)) - cpu_relax(); - spin_release(&console_owner_dep_map, _THIS_IP_); - - printk_safe_exit_irqrestore(flags); - /* - * The owner passed the console lock to us. - * Since we did not spin on console lock, annotate - * this as a trylock. Otherwise lockdep will - * complain. - */ - mutex_acquire(&console_lock_dep_map, 0, 1, _THIS_IP_); - - return 1; -} - -/* - * Call the console drivers, asking them to write out - * log_buf[start] to log_buf[end - 1]. - * The console_lock must be held. - */ -static void call_console_drivers(const char *ext_text, size_t ext_len, - const char *text, size_t len) -{ - static char dropped_text[64]; - size_t dropped_len = 0; - struct console *con; - - trace_console_rcuidle(text, len); - - if (!console_drivers) - return; - - if (console_dropped) { - dropped_len = snprintf(dropped_text, sizeof(dropped_text), - "** %lu printk messages dropped **\n", - console_dropped); - console_dropped = 0; - } - - for_each_console(con) { - if (exclusive_console && con != exclusive_console) - continue; - if (!(con->flags & CON_ENABLED)) - continue; - if (!con->write) - continue; - if (!cpu_online(smp_processor_id()) && - !(con->flags & CON_ANYTIME)) - continue; - if (con->flags & CON_EXTENDED) - con->write(con, ext_text, ext_len); - else { - if (dropped_len) - con->write(con, dropped_text, dropped_len); - con->write(con, text, len); - } - } -} - int printk_delay_msec __read_mostly; -static inline void printk_delay(void) +static inline void printk_delay(int level) { + boot_delay_msec(level); + if (unlikely(printk_delay_msec)) { int m = printk_delay_msec; @@ -1878,6 +1711,199 @@ static inline void printk_delay(void) } } +static bool kernel_sync_mode(void) +{ + return (oops_in_progress || sync_mode); +} + +static bool console_may_sync(struct console *con) +{ + if (!(con->flags & CON_ENABLED)) + return false; + if (con->write_atomic && kernel_sync_mode()) + return true; + if (con->write_atomic && (con->flags & CON_HANDOVER) && !con->thread) + return true; + if (con->write && (con->flags & CON_BOOT) && !con->thread) + return true; + return false; +} + +static bool call_sync_console_driver(struct console *con, const char *text, size_t text_len) +{ + if (!(con->flags & CON_ENABLED)) + return false; + + if (con->write_atomic && kernel_sync_mode()) { + con->write_atomic(con, text, text_len); + return true; + } + + if (con->write_atomic && (con->flags & CON_HANDOVER) && !con->thread) { + if (console_trylock()) { + con->write_atomic(con, text, text_len); + console_unlock(); + return true; + } + + } else if (con->write && (con->flags & CON_BOOT) && !con->thread) { + if (console_trylock()) { + con->write(con, text, text_len); + console_unlock(); + return true; + } + } + + return false; +} + +static bool have_atomic_console(void) +{ + struct console *con; + + for_each_console(con) { + if (!(con->flags & CON_ENABLED)) + continue; + if (con->write_atomic) + return true; + } + return false; +} + +static bool print_sync(struct console *con, u64 *seq) +{ + struct printk_info info; + struct printk_record r; + size_t text_len; + + prb_rec_init_rd(&r, &info, &con->sync_buf[0], sizeof(con->sync_buf)); + + if (!prb_read_valid(prb, *seq, &r)) + return false; + + text_len = record_print_text(&r, console_msg_format & MSG_FORMAT_SYSLOG, printk_time); + + if (!call_sync_console_driver(con, &con->sync_buf[0], text_len)) + return false; + + *seq = r.info->seq; + + touch_softlockup_watchdog_sync(); + clocksource_touch_watchdog(); + rcu_cpu_stall_reset(); + touch_nmi_watchdog(); + + if (text_len) + printk_delay(r.info->level); + + return true; +} + +static u64 read_console_seq(struct console *con) +{ + u64 seq2; + u64 seq; + + seq = latched_seq_read_nolock(&con->printk_seq); + seq2 = latched_seq_read_nolock(&con->printk_sync_seq[0]); + if (seq2 > seq) + seq = seq2; +#if PRINTK_CTX_NUM > 1 + seq2 = latched_seq_read_nolock(&con->printk_sync_seq[1]); + if (seq2 > seq) + seq = seq2; +#endif + return seq; +} + +static void print_sync_until(struct console *con, u64 seq, bool is_locked) +{ + unsigned int flags; + u64 printk_seq; + + console_atomic_lock(&flags); + for (;;) { + printk_seq = read_console_seq(con); + if (printk_seq >= seq) + break; + if (!print_sync(con, &printk_seq)) + break; + + if (is_locked) { + latched_seq_write(&con->printk_seq, printk_seq + 1); + } else { + int ctx = 0; + +#ifdef CONFIG_PRINTK_NMI + if (in_nmi()) + ctx = 1; +#endif + latched_seq_write(&con->printk_sync_seq[ctx], printk_seq + 1); + } + } + console_atomic_unlock(flags); +} + +/* + * Recursion is tracked separately on each CPU. If NMIs are supported, an + * additional NMI context per CPU is also separately tracked. Until per-CPU + * is available, a separate "early tracking" is performed. + */ +static DEFINE_PER_CPU(char [PRINTK_CTX_NUM], printk_count); +static char printk_count_early[PRINTK_CTX_NUM]; + +/* + * Recursion is limited to keep the output sane. printk() should not require + * more than 1 level of recursion (allowing, for example, printk() to trigger + * a WARN), but a higher value is used in case some printk-internal errors + * exist, such as the ringbuffer validation checks failing. + */ +#define PRINTK_MAX_RECURSION 3 + +/* Return a pointer to the dedicated counter for the CPU+context of the caller. */ +static char *printk_recursion_counter(void) +{ + int ctx = 0; + +#ifdef CONFIG_PRINTK_NMI + if (in_nmi()) + ctx = 1; +#endif + if (!printk_percpu_data_ready()) + return &printk_count_early[ctx]; + return &((*this_cpu_ptr(&printk_count))[ctx]); +} + +/* + * Enter recursion tracking. Interrupts are disabled to simplify tracking. + * The caller must check the return value to see if the recursion is allowed. + * On failure, interrupts are not disabled. + */ +static bool printk_enter_irqsave(unsigned long *flags) +{ + char *count; + + local_irq_save(*flags); + count = printk_recursion_counter(); + if (*count > PRINTK_MAX_RECURSION) { + local_irq_restore(*flags); + return false; + } + (*count)++; + + return true; +} + +/* Exit recursion tracking, restoring interrupts. */ +static void printk_exit_irqrestore(unsigned long flags) +{ + char *count; + + count = printk_recursion_counter(); + (*count)--; + local_irq_restore(flags); +} + static inline u32 printk_caller_id(void) { return in_task() ? task_pid_nr(current) : @@ -1956,20 +1982,24 @@ static u16 printk_sprint(char *text, u16 size, int facility, enum log_flags *lfl } __printf(4, 0) -int vprintk_store(int facility, int level, - const struct dev_printk_info *dev_info, - const char *fmt, va_list args) +static int vprintk_store(int facility, int level, + const struct dev_printk_info *dev_info, + const char *fmt, va_list args) { const u32 caller_id = printk_caller_id(); struct prb_reserved_entry e; enum log_flags lflags = 0; + bool final_commit = false; struct printk_record r; + unsigned long irqflags; u16 trunc_msg_len = 0; char prefix_buf[8]; u16 reserve_size; va_list args2; u16 text_len; + int ret = 0; u64 ts_nsec; + u64 seq; /* * Since the duration of printk() can vary depending on the message @@ -1979,6 +2009,9 @@ int vprintk_store(int facility, int level, */ ts_nsec = local_clock(); + if (!printk_enter_irqsave(&irqflags)) + return 0; + /* * The sprintf needs to come first since the syslog prefix might be * passed in as a parameter. An extra byte must be reserved so that @@ -2005,6 +2038,7 @@ int vprintk_store(int facility, int level, if (lflags & LOG_CONT) { prb_rec_init_wr(&r, reserve_size); if (prb_reserve_in_last(&e, prb, &r, caller_id, LOG_LINE_MAX)) { + seq = r.info->seq; text_len = printk_sprint(&r.text_buf[r.info->text_len], reserve_size, facility, &lflags, fmt, args); r.info->text_len += text_len; @@ -2012,11 +2046,13 @@ int vprintk_store(int facility, int level, if (lflags & LOG_NEWLINE) { r.info->flags |= LOG_NEWLINE; prb_final_commit(&e); + final_commit = true; } else { prb_commit(&e); } - return text_len; + ret = text_len; + goto out; } } @@ -2032,9 +2068,11 @@ int vprintk_store(int facility, int level, prb_rec_init_wr(&r, reserve_size + trunc_msg_len); if (!prb_reserve(&e, prb, &r)) - return 0; + goto out; } + seq = r.info->seq; + /* fill message */ text_len = printk_sprint(&r.text_buf[0], reserve_size, facility, &lflags, fmt, args); if (trunc_msg_len) @@ -2049,12 +2087,27 @@ int vprintk_store(int facility, int level, memcpy(&r.info->dev_info, dev_info, sizeof(r.info->dev_info)); /* A message without a trailing newline can be continued. */ - if (!(lflags & LOG_NEWLINE)) + if (!(lflags & LOG_NEWLINE)) { prb_commit(&e); - else + } else { prb_final_commit(&e); + final_commit = true; + } - return (text_len + trunc_msg_len); + ret = text_len + trunc_msg_len; +out: + /* only the kernel may perform synchronous printing */ + if (facility == 0 && final_commit) { + struct console *con; + + for_each_console(con) { + if (console_may_sync(con)) + print_sync_until(con, seq + 1, false); + } + } + + printk_exit_irqrestore(irqflags); + return ret; } asmlinkage int vprintk_emit(int facility, int level, @@ -2062,60 +2115,44 @@ asmlinkage int vprintk_emit(int facility, int level, const char *fmt, va_list args) { int printed_len; - bool in_sched = false; - unsigned long flags; /* Suppress unimportant messages after panic happens */ if (unlikely(suppress_printk)) return 0; - if (level == LOGLEVEL_SCHED) { + if (level == LOGLEVEL_SCHED) level = LOGLEVEL_DEFAULT; - in_sched = true; - } - boot_delay_msec(level); - printk_delay(); - - printk_safe_enter_irqsave(flags); printed_len = vprintk_store(facility, level, dev_info, fmt, args); - printk_safe_exit_irqrestore(flags); - - /* If called from the scheduler, we can not call up(). */ - if (!in_sched) { - /* - * Disable preemption to avoid being preempted while holding - * console_sem which would prevent anyone from printing to - * console - */ - preempt_disable(); - /* - * Try to acquire and then immediately release the console - * semaphore. The release will print out buffers and wake up - * /dev/kmsg and syslog() users. - */ - if (console_trylock_spinning()) - console_unlock(); - preempt_enable(); - } wake_up_klogd(); return printed_len; } EXPORT_SYMBOL(vprintk_emit); +__printf(1, 0) +static int vprintk_default(const char *fmt, va_list args) +{ + return vprintk_emit(0, LOGLEVEL_DEFAULT, NULL, fmt, args); +} + +__printf(1, 0) +static int vprintk_func(const char *fmt, va_list args) +{ +#ifdef CONFIG_KGDB_KDB + /* Allow to pass printk() to kdb but avoid a recursion. */ + if (unlikely(kdb_trap_printk && kdb_printf_cpu < 0)) + return vkdb_printf(KDB_MSGSRC_PRINTK, fmt, args); +#endif + return vprintk_default(fmt, args); +} + asmlinkage int vprintk(const char *fmt, va_list args) { return vprintk_func(fmt, args); } EXPORT_SYMBOL(vprintk); -int vprintk_default(const char *fmt, va_list args) -{ - return vprintk_emit(0, LOGLEVEL_DEFAULT, NULL, fmt, args); -} -EXPORT_SYMBOL_GPL(vprintk_default); - /** * printk - print a kernel message * @fmt: format string @@ -2150,38 +2187,164 @@ asmlinkage __visible int printk(const char *fmt, ...) } EXPORT_SYMBOL(printk); +static int printk_kthread_func(void *data) +{ + struct console *con = data; + unsigned long dropped = 0; + char *dropped_text = NULL; + struct printk_info info; + struct printk_record r; + char *ext_text = NULL; + size_t dropped_len; + int ret = -ENOMEM; + char *text = NULL; + char *write_text; + size_t len; + int error; + u64 seq; + + if (con->flags & CON_EXTENDED) { + ext_text = kmalloc(CONSOLE_EXT_LOG_MAX, GFP_KERNEL); + if (!ext_text) + goto out; + } + text = kmalloc(LOG_LINE_MAX + PREFIX_MAX, GFP_KERNEL); + dropped_text = kmalloc(64, GFP_KERNEL); + if (!text || !dropped_text) + goto out; + + if (con->flags & CON_EXTENDED) + write_text = ext_text; + else + write_text = text; + + seq = read_console_seq(con); + + prb_rec_init_rd(&r, &info, text, LOG_LINE_MAX + PREFIX_MAX); + + for (;;) { + error = wait_event_interruptible(log_wait, + prb_read_valid(prb, seq, &r) || kthread_should_stop()); + + if (kthread_should_stop()) + break; + + if (error) + continue; + + if (seq != r.info->seq) { + dropped += r.info->seq - seq; + seq = r.info->seq; + } + + seq++; + + if (!(con->flags & CON_ENABLED)) + continue; + + if (suppress_message_printing(r.info->level)) + continue; + + if (con->flags & CON_EXTENDED) { + len = info_print_ext_header(ext_text, + CONSOLE_EXT_LOG_MAX, + r.info); + len += msg_print_ext_body(ext_text + len, + CONSOLE_EXT_LOG_MAX - len, + &r.text_buf[0], r.info->text_len, + &r.info->dev_info); + } else { + len = record_print_text(&r, + console_msg_format & MSG_FORMAT_SYSLOG, + printk_time); + } + + console_lock(); + + /* + * Even though the printk kthread is always preemptible, it is + * still not allowed to call cond_resched() from within + * console drivers. The task may become non-preemptible in the + * console driver call chain. For example, vt_console_print() + * takes a spinlock and then can call into fbcon_redraw(), + * which can conditionally invoke cond_resched(). + */ + console_may_schedule = 0; + + if (kernel_sync_mode() && con->write_atomic) { + console_unlock(); + break; + } + + if (!(con->flags & CON_EXTENDED) && dropped) { + dropped_len = snprintf(dropped_text, 64, + "** %lu printk messages dropped **\n", + dropped); + dropped = 0; + + con->write(con, dropped_text, dropped_len); + printk_delay(r.info->level); + } + + con->write(con, write_text, len); + if (len) + printk_delay(r.info->level); + + latched_seq_write(&con->printk_seq, seq); + + console_unlock(); + } +out: + kfree(dropped_text); + kfree(text); + kfree(ext_text); + pr_info("%sconsole [%s%d]: printing thread stopped\n", + (con->flags & CON_BOOT) ? "boot" : "", + con->name, con->index); + return ret; +} + +/* Must be called within console_lock(). */ +static void start_printk_kthread(struct console *con) +{ + con->thread = kthread_run(printk_kthread_func, con, + "pr/%s%d", con->name, con->index); + if (IS_ERR(con->thread)) { + pr_err("%sconsole [%s%d]: unable to start printing thread\n", + (con->flags & CON_BOOT) ? "boot" : "", + con->name, con->index); + return; + } + pr_info("%sconsole [%s%d]: printing thread started\n", + (con->flags & CON_BOOT) ? "boot" : "", + con->name, con->index); +} + +/* protected by console_lock */ +static bool kthreads_started; + +/* Must be called within console_lock(). */ +static void console_try_thread(struct console *con) +{ + if (kthreads_started) { + start_printk_kthread(con); + return; + } + + /* + * The printing threads have not been started yet. If this console + * can print synchronously, print all unprinted messages. + */ + if (console_may_sync(con)) + print_sync_until(con, prb_next_seq(prb), true); +} + #else /* CONFIG_PRINTK */ -#define LOG_LINE_MAX 0 -#define PREFIX_MAX 0 -#define printk_time false - -#define prb_read_valid(rb, seq, r) false #define prb_first_valid_seq(rb) 0 +#define prb_next_seq(rb) 0 -static u64 syslog_seq; -static u64 console_seq; -static u64 exclusive_console_stop_seq; -static unsigned long console_dropped; - -static size_t record_print_text(const struct printk_record *r, - bool syslog, bool time) -{ - return 0; -} -static ssize_t info_print_ext_header(char *buf, size_t size, - struct printk_info *info) -{ - return 0; -} -static ssize_t msg_print_ext_body(char *buf, size_t size, - char *text, size_t text_len, - struct dev_printk_info *dev_info) { return 0; } -static void console_lock_spinning_enable(void) { } -static int console_lock_spinning_disable_and_check(void) { return 0; } -static void call_console_drivers(const char *ext_text, size_t ext_len, - const char *text, size_t len) {} -static bool suppress_message_printing(int level) { return false; } +#define console_try_thread(con) #endif /* CONFIG_PRINTK */ @@ -2426,34 +2589,6 @@ int is_console_locked(void) } EXPORT_SYMBOL(is_console_locked); -/* - * Check if we have any console that is capable of printing while cpu is - * booting or shutting down. Requires console_sem. - */ -static int have_callable_console(void) -{ - struct console *con; - - for_each_console(con) - if ((con->flags & CON_ENABLED) && - (con->flags & CON_ANYTIME)) - return 1; - - return 0; -} - -/* - * Can we actually use the console at this time on this cpu? - * - * Console drivers may assume that per-cpu resources have been allocated. So - * unless they're explicitly marked as being able to cope (CON_ANYTIME) don't - * call them until this CPU is officially up. - */ -static inline int can_use_console(void) -{ - return cpu_online(raw_smp_processor_id()) || have_callable_console(); -} - /** * console_unlock - unlock the console system * @@ -2470,142 +2605,14 @@ static inline int can_use_console(void) */ void console_unlock(void) { - static char ext_text[CONSOLE_EXT_LOG_MAX]; - static char text[LOG_LINE_MAX + PREFIX_MAX]; - unsigned long flags; - bool do_cond_resched, retry; - struct printk_info info; - struct printk_record r; - if (console_suspended) { up_console_sem(); return; } - prb_rec_init_rd(&r, &info, text, sizeof(text)); - - /* - * Console drivers are called with interrupts disabled, so - * @console_may_schedule should be cleared before; however, we may - * end up dumping a lot of lines, for example, if called from - * console registration path, and should invoke cond_resched() - * between lines if allowable. Not doing so can cause a very long - * scheduling stall on a slow console leading to RCU stall and - * softlockup warnings which exacerbate the issue with more - * messages practically incapacitating the system. - * - * console_trylock() is not able to detect the preemptive - * context reliably. Therefore the value must be stored before - * and cleared after the "again" goto label. - */ - do_cond_resched = console_may_schedule; -again: - console_may_schedule = 0; - - /* - * We released the console_sem lock, so we need to recheck if - * cpu is online and (if not) is there at least one CON_ANYTIME - * console. - */ - if (!can_use_console()) { - console_locked = 0; - up_console_sem(); - return; - } - - for (;;) { - size_t ext_len = 0; - size_t len; - - printk_safe_enter_irqsave(flags); - raw_spin_lock(&logbuf_lock); -skip: - if (!prb_read_valid(prb, console_seq, &r)) - break; - - if (console_seq != r.info->seq) { - console_dropped += r.info->seq - console_seq; - console_seq = r.info->seq; - } - - if (suppress_message_printing(r.info->level)) { - /* - * Skip record we have buffered and already printed - * directly to the console when we received it, and - * record that has level above the console loglevel. - */ - console_seq++; - goto skip; - } - - /* Output to all consoles once old messages replayed. */ - if (unlikely(exclusive_console && - console_seq >= exclusive_console_stop_seq)) { - exclusive_console = NULL; - } - - /* - * Handle extended console text first because later - * record_print_text() will modify the record buffer in-place. - */ - if (nr_ext_console_drivers) { - ext_len = info_print_ext_header(ext_text, - sizeof(ext_text), - r.info); - ext_len += msg_print_ext_body(ext_text + ext_len, - sizeof(ext_text) - ext_len, - &r.text_buf[0], - r.info->text_len, - &r.info->dev_info); - } - len = record_print_text(&r, - console_msg_format & MSG_FORMAT_SYSLOG, - printk_time); - console_seq++; - raw_spin_unlock(&logbuf_lock); - - /* - * While actively printing out messages, if another printk() - * were to occur on another CPU, it may wait for this one to - * finish. This task can not be preempted if there is a - * waiter waiting to take over. - */ - console_lock_spinning_enable(); - - stop_critical_timings(); /* don't trace print latency */ - call_console_drivers(ext_text, ext_len, text, len); - start_critical_timings(); - - if (console_lock_spinning_disable_and_check()) { - printk_safe_exit_irqrestore(flags); - return; - } - - printk_safe_exit_irqrestore(flags); - - if (do_cond_resched) - cond_resched(); - } - console_locked = 0; - raw_spin_unlock(&logbuf_lock); - up_console_sem(); - - /* - * Someone could have filled up the buffer again, so re-check if there's - * something to flush. In case we cannot trylock the console_sem again, - * there's a new owner and the console_unlock() from them will do the - * flush, no worries. - */ - raw_spin_lock(&logbuf_lock); - retry = prb_read_valid(prb, console_seq, NULL); - raw_spin_unlock(&logbuf_lock); - printk_safe_exit_irqrestore(flags); - - if (retry && console_trylock()) - goto again; } EXPORT_SYMBOL(console_unlock); @@ -2655,23 +2662,18 @@ void console_unblank(void) */ void console_flush_on_panic(enum con_flush_mode mode) { - /* - * If someone else is holding the console lock, trylock will fail - * and may_schedule may be set. Ignore and proceed to unlock so - * that messages are flushed out. As this can be called from any - * context and we don't want to get preempted while flushing, - * ensure may_schedule is cleared. - */ - console_trylock(); - console_may_schedule = 0; + struct console *c; + u64 seq; + + if (!console_trylock()) + return; if (mode == CONSOLE_REPLAY_ALL) { - unsigned long flags; - - logbuf_lock_irqsave(flags); - console_seq = prb_first_valid_seq(prb); - logbuf_unlock_irqrestore(flags); + seq = prb_first_valid_seq(prb); + for_each_console(c) + latched_seq_write(&c->printk_seq, seq); } + console_unlock(); } @@ -2806,8 +2808,8 @@ static int try_enable_new_console(struct console *newcon, bool user_specified) */ void register_console(struct console *newcon) { - unsigned long flags; struct console *bcon = NULL; + u64 seq = 0; int err; for_each_console(bcon) { @@ -2830,6 +2832,8 @@ void register_console(struct console *newcon) } } + newcon->thread = NULL; + if (console_drivers && console_drivers->flags & CON_BOOT) bcon = console_drivers; @@ -2871,8 +2875,10 @@ void register_console(struct console *newcon) * the real console are the same physical device, it's annoying to * see the beginning boot messages twice */ - if (bcon && ((newcon->flags & (CON_CONSDEV | CON_BOOT)) == CON_CONSDEV)) + if (bcon && ((newcon->flags & (CON_CONSDEV | CON_BOOT)) == CON_CONSDEV)) { newcon->flags &= ~CON_PRINTBUFFER; + newcon->flags |= CON_HANDOVER; + } /* * Put this console in the list - keep the @@ -2894,26 +2900,19 @@ void register_console(struct console *newcon) if (newcon->flags & CON_EXTENDED) nr_ext_console_drivers++; - if (newcon->flags & CON_PRINTBUFFER) { - /* - * console_unlock(); will print out the buffered messages - * for us. - */ - logbuf_lock_irqsave(flags); - /* - * We're about to replay the log buffer. Only do this to the - * just-registered console to avoid excessive message spam to - * the already-registered consoles. - * - * Set exclusive_console with disabled interrupts to reduce - * race window with eventual console_flush_on_panic() that - * ignores console_lock. - */ - exclusive_console = newcon; - exclusive_console_stop_seq = console_seq; - console_seq = syslog_seq; - logbuf_unlock_irqrestore(flags); - } + if (!(newcon->flags & CON_PRINTBUFFER)) + seq = prb_next_seq(prb); + + seqcount_latch_init(&newcon->printk_seq.latch); + latched_seq_write(&newcon->printk_seq, seq); + seqcount_latch_init(&newcon->printk_sync_seq[0].latch); + latched_seq_write(&newcon->printk_sync_seq[0], seq); +#if PRINTK_CTX_NUM > 1 + seqcount_latch_init(&newcon->printk_sync_seq[1].latch); + latched_seq_write(&newcon->printk_sync_seq[1], seq); +#endif + + console_try_thread(newcon); console_unlock(); console_sysfs_notify(); @@ -2987,6 +2986,9 @@ int unregister_console(struct console *console) console_unlock(); console_sysfs_notify(); + if (console->thread && !IS_ERR(console->thread)) + kthread_stop(console->thread); + if (console->exit) res = console->exit(console); @@ -3069,6 +3071,15 @@ static int __init printk_late_init(void) unregister_console(con); } } + +#ifdef CONFIG_PRINTK + console_lock(); + for_each_console(con) + start_printk_kthread(con); + kthreads_started = true; + console_unlock(); +#endif + ret = cpuhp_setup_state_nocalls(CPUHP_PRINTK_DEAD, "printk:dead", NULL, console_cpu_notify); WARN_ON(ret < 0); @@ -3084,7 +3095,6 @@ late_initcall(printk_late_init); * Delayed printk version, for scheduler-internal messages: */ #define PRINTK_PENDING_WAKEUP 0x01 -#define PRINTK_PENDING_OUTPUT 0x02 static DEFINE_PER_CPU(int, printk_pending); @@ -3092,14 +3102,8 @@ static void wake_up_klogd_work_func(struct irq_work *irq_work) { int pending = __this_cpu_xchg(printk_pending, 0); - if (pending & PRINTK_PENDING_OUTPUT) { - /* If trylock fails, someone else is doing the printing */ - if (console_trylock()) - console_unlock(); - } - if (pending & PRINTK_PENDING_WAKEUP) - wake_up_interruptible(&log_wait); + wake_up_interruptible_all(&log_wait); } static DEFINE_PER_CPU(struct irq_work, wake_up_klogd_work) = @@ -3118,25 +3122,10 @@ void wake_up_klogd(void) preempt_enable(); } -void defer_console_output(void) +__printf(1, 0) +static int vprintk_deferred(const char *fmt, va_list args) { - if (!printk_percpu_data_ready()) - return; - - preempt_disable(); - __this_cpu_or(printk_pending, PRINTK_PENDING_OUTPUT); - irq_work_queue(this_cpu_ptr(&wake_up_klogd_work)); - preempt_enable(); -} - -int vprintk_deferred(const char *fmt, va_list args) -{ - int r; - - r = vprintk_emit(0, LOGLEVEL_SCHED, NULL, fmt, args); - defer_console_output(); - - return r; + return vprintk_emit(0, LOGLEVEL_DEFAULT, NULL, fmt, args); } int printk_deferred(const char *fmt, ...) @@ -3276,7 +3265,24 @@ EXPORT_SYMBOL_GPL(kmsg_dump_reason_str); void kmsg_dump(enum kmsg_dump_reason reason) { struct kmsg_dumper *dumper; - unsigned long flags; + + if (!oops_in_progress) { + /* + * If atomic consoles are available, activate kernel sync mode + * to make sure any final messages are visible. The trailing + * printk message is important to flush any pending messages. + */ + if (have_atomic_console()) { + sync_mode = true; + pr_info("enabled sync mode\n"); + } + + /* + * Give the printing threads time to flush, allowing up to + * 1s of no printing forward progress before giving up. + */ + pr_flush(1000, true); + } rcu_read_lock(); list_for_each_entry_rcu(dumper, &dump_list, list) { @@ -3293,26 +3299,15 @@ void kmsg_dump(enum kmsg_dump_reason reason) if (reason > max_reason) continue; - /* initialize iterator with data about the stored records */ - dumper->active = true; - - logbuf_lock_irqsave(flags); - dumper->cur_seq = clear_seq; - dumper->next_seq = prb_next_seq(prb); - logbuf_unlock_irqrestore(flags); - /* invoke dumper which will iterate over records */ dumper->dump(dumper, reason); - - /* reset iterator */ - dumper->active = false; } rcu_read_unlock(); } /** - * kmsg_dump_get_line_nolock - retrieve one kmsg log line (unlocked version) - * @dumper: registered kmsg dumper + * kmsg_dump_get_line - retrieve one kmsg log line + * @iter: kmsg dump iterator * @syslog: include the "<4>" prefixes * @line: buffer to copy the line to * @size: maximum size of the buffer @@ -3326,30 +3321,29 @@ void kmsg_dump(enum kmsg_dump_reason reason) * * A return value of FALSE indicates that there are no more records to * read. - * - * The function is similar to kmsg_dump_get_line(), but grabs no locks. */ -bool kmsg_dump_get_line_nolock(struct kmsg_dumper *dumper, bool syslog, - char *line, size_t size, size_t *len) +bool kmsg_dump_get_line(struct kmsg_dump_iter *iter, bool syslog, + char *line, size_t size, size_t *len) { + u64 min_seq = latched_seq_read_nolock(&clear_seq); struct printk_info info; unsigned int line_count; struct printk_record r; size_t l = 0; bool ret = false; - prb_rec_init_rd(&r, &info, line, size); + if (iter->cur_seq < min_seq) + iter->cur_seq = min_seq; - if (!dumper->active) - goto out; + prb_rec_init_rd(&r, &info, line, size); /* Read text or count text lines? */ if (line) { - if (!prb_read_valid(prb, dumper->cur_seq, &r)) + if (!prb_read_valid(prb, iter->cur_seq, &r)) goto out; l = record_print_text(&r, syslog, printk_time); } else { - if (!prb_read_valid_info(prb, dumper->cur_seq, + if (!prb_read_valid_info(prb, iter->cur_seq, &info, &line_count)) { goto out; } @@ -3358,52 +3352,22 @@ bool kmsg_dump_get_line_nolock(struct kmsg_dumper *dumper, bool syslog, } - dumper->cur_seq = r.info->seq + 1; + iter->cur_seq = r.info->seq + 1; ret = true; out: if (len) *len = l; return ret; } - -/** - * kmsg_dump_get_line - retrieve one kmsg log line - * @dumper: registered kmsg dumper - * @syslog: include the "<4>" prefixes - * @line: buffer to copy the line to - * @size: maximum size of the buffer - * @len: length of line placed into buffer - * - * Start at the beginning of the kmsg buffer, with the oldest kmsg - * record, and copy one record into the provided buffer. - * - * Consecutive calls will return the next available record moving - * towards the end of the buffer with the youngest messages. - * - * A return value of FALSE indicates that there are no more records to - * read. - */ -bool kmsg_dump_get_line(struct kmsg_dumper *dumper, bool syslog, - char *line, size_t size, size_t *len) -{ - unsigned long flags; - bool ret; - - logbuf_lock_irqsave(flags); - ret = kmsg_dump_get_line_nolock(dumper, syslog, line, size, len); - logbuf_unlock_irqrestore(flags); - - return ret; -} EXPORT_SYMBOL_GPL(kmsg_dump_get_line); /** * kmsg_dump_get_buffer - copy kmsg log lines - * @dumper: registered kmsg dumper + * @iter: kmsg dump iterator * @syslog: include the "<4>" prefixes * @buf: buffer to copy the line to * @size: maximum size of the buffer - * @len: length of line placed into buffer + * @len_out: length of line placed into buffer * * Start at the end of the kmsg buffer and fill the provided buffer * with as many of the *youngest* kmsg records that fit into it. @@ -3416,116 +3380,280 @@ EXPORT_SYMBOL_GPL(kmsg_dump_get_line); * A return value of FALSE indicates that there are no more records to * read. */ -bool kmsg_dump_get_buffer(struct kmsg_dumper *dumper, bool syslog, - char *buf, size_t size, size_t *len) +bool kmsg_dump_get_buffer(struct kmsg_dump_iter *iter, bool syslog, + char *buf, size_t size, size_t *len_out) { + u64 min_seq = latched_seq_read_nolock(&clear_seq); struct printk_info info; - unsigned int line_count; struct printk_record r; - unsigned long flags; u64 seq; u64 next_seq; - size_t l = 0; + size_t len = 0; bool ret = false; bool time = printk_time; - prb_rec_init_rd(&r, &info, buf, size); - - if (!dumper->active || !buf || !size) + if (!buf || !size) goto out; - logbuf_lock_irqsave(flags); - if (prb_read_valid_info(prb, dumper->cur_seq, &info, NULL)) { - if (info.seq != dumper->cur_seq) { + if (iter->cur_seq < min_seq) + iter->cur_seq = min_seq; + + if (prb_read_valid_info(prb, iter->cur_seq, &info, NULL)) { + if (info.seq != iter->cur_seq) { /* messages are gone, move to first available one */ - dumper->cur_seq = info.seq; + iter->cur_seq = info.seq; } } /* last entry */ - if (dumper->cur_seq >= dumper->next_seq) { - logbuf_unlock_irqrestore(flags); + if (iter->cur_seq >= iter->next_seq) goto out; - } - /* calculate length of entire buffer */ - seq = dumper->cur_seq; - while (prb_read_valid_info(prb, seq, &info, &line_count)) { - if (r.info->seq >= dumper->next_seq) - break; - l += get_record_print_text_size(&info, line_count, syslog, time); - seq = r.info->seq + 1; - } + /* + * Find first record that fits, including all following records, + * into the user-provided buffer for this dump. Pass in size-1 + * because this function (by way of record_print_text()) will + * not write more than size-1 bytes of text into @buf. + */ + seq = find_first_fitting_seq(iter->cur_seq, iter->next_seq, + size - 1, syslog, time); - /* move first record forward until length fits into the buffer */ - seq = dumper->cur_seq; - while (l >= size && prb_read_valid_info(prb, seq, - &info, &line_count)) { - if (r.info->seq >= dumper->next_seq) - break; - l -= get_record_print_text_size(&info, line_count, syslog, time); - seq = r.info->seq + 1; - } - - /* last message in next interation */ + /* + * Next kmsg_dump_get_buffer() invocation will dump block of + * older records stored right before this one. + */ next_seq = seq; - /* actually read text into the buffer now */ - l = 0; - while (prb_read_valid(prb, seq, &r)) { - if (r.info->seq >= dumper->next_seq) + prb_rec_init_rd(&r, &info, buf, size); + + len = 0; + prb_for_each_record(seq, prb, seq, &r) { + if (r.info->seq >= iter->next_seq) break; - l += record_print_text(&r, syslog, time); + len += record_print_text(&r, syslog, time); - /* adjust record to store to remaining buffer space */ - prb_rec_init_rd(&r, &info, buf + l, size - l); - - seq = r.info->seq + 1; + /* Adjust record to store to remaining buffer space. */ + prb_rec_init_rd(&r, &info, buf + len, size - len); } - dumper->next_seq = next_seq; + iter->next_seq = next_seq; ret = true; - logbuf_unlock_irqrestore(flags); out: - if (len) - *len = l; + if (len_out) + *len_out = len; return ret; } EXPORT_SYMBOL_GPL(kmsg_dump_get_buffer); -/** - * kmsg_dump_rewind_nolock - reset the iterator (unlocked version) - * @dumper: registered kmsg dumper - * - * Reset the dumper's iterator so that kmsg_dump_get_line() and - * kmsg_dump_get_buffer() can be called again and used multiple - * times within the same dumper.dump() callback. - * - * The function is similar to kmsg_dump_rewind(), but grabs no locks. - */ -void kmsg_dump_rewind_nolock(struct kmsg_dumper *dumper) -{ - dumper->cur_seq = clear_seq; - dumper->next_seq = prb_next_seq(prb); -} - /** * kmsg_dump_rewind - reset the iterator - * @dumper: registered kmsg dumper + * @iter: kmsg dump iterator * * Reset the dumper's iterator so that kmsg_dump_get_line() and * kmsg_dump_get_buffer() can be called again and used multiple * times within the same dumper.dump() callback. */ -void kmsg_dump_rewind(struct kmsg_dumper *dumper) +void kmsg_dump_rewind(struct kmsg_dump_iter *iter) { - unsigned long flags; - - logbuf_lock_irqsave(flags); - kmsg_dump_rewind_nolock(dumper); - logbuf_unlock_irqrestore(flags); + iter->cur_seq = latched_seq_read_nolock(&clear_seq); + iter->next_seq = prb_next_seq(prb); } EXPORT_SYMBOL_GPL(kmsg_dump_rewind); #endif + +struct prb_cpulock { + atomic_t owner; + unsigned long __percpu *irqflags; +}; + +#define DECLARE_STATIC_PRINTKRB_CPULOCK(name) \ +static DEFINE_PER_CPU(unsigned long, _##name##_percpu_irqflags); \ +static struct prb_cpulock name = { \ + .owner = ATOMIC_INIT(-1), \ + .irqflags = &_##name##_percpu_irqflags, \ +} + +static unsigned int kgdb_cpu = -1; + +static bool __prb_trylock(struct prb_cpulock *cpu_lock, + unsigned int *cpu_store) +{ + unsigned long *flags; + unsigned int cpu; + + cpu = get_cpu(); + + *cpu_store = atomic_read(&cpu_lock->owner); + /* memory barrier to ensure the current lock owner is visible */ + smp_rmb(); + if (*cpu_store == -1) { + flags = per_cpu_ptr(cpu_lock->irqflags, cpu); + local_irq_save(*flags); + if (atomic_try_cmpxchg_acquire(&cpu_lock->owner, + cpu_store, cpu)) { + return true; + } + local_irq_restore(*flags); + } else if (*cpu_store == cpu) { + return true; + } + + put_cpu(); + return false; +} + +/* + * prb_lock: Perform a processor-reentrant spin lock. + * @cpu_lock: A pointer to the lock object. + * @cpu_store: A "flags" pointer to store lock status information. + * + * If no processor has the lock, the calling processor takes the lock and + * becomes the owner. If the calling processor is already the owner of the + * lock, this function succeeds immediately. If lock is locked by another + * processor, this function spins until the calling processor becomes the + * owner. + * + * It is safe to call this function from any context and state. + */ +static void prb_lock(struct prb_cpulock *cpu_lock, unsigned int *cpu_store) +{ + for (;;) { + if (__prb_trylock(cpu_lock, cpu_store)) + break; + cpu_relax(); + } +} + +/* + * prb_unlock: Perform a processor-reentrant spin unlock. + * @cpu_lock: A pointer to the lock object. + * @cpu_store: A "flags" object storing lock status information. + * + * Release the lock. The calling processor must be the owner of the lock. + * + * It is safe to call this function from any context and state. + */ +static void prb_unlock(struct prb_cpulock *cpu_lock, unsigned int cpu_store) +{ + bool trigger_kgdb = false; + unsigned long *flags; + unsigned int cpu; + + cpu = atomic_read(&cpu_lock->owner); + if (cpu == kgdb_cpu && cpu_store == -1) { + trigger_kgdb = true; + kgdb_cpu = -1; + } + atomic_set_release(&cpu_lock->owner, cpu_store); + + if (cpu_store == -1) { + flags = per_cpu_ptr(cpu_lock->irqflags, cpu); + local_irq_restore(*flags); + } + + put_cpu(); + + if (trigger_kgdb) { + pr_warn("re-triggering kgdb roundup for CPU#%d\n", cpu); + kgdb_roundup_cpu(cpu); + } +} + +DECLARE_STATIC_PRINTKRB_CPULOCK(printk_cpulock); + +void console_atomic_lock(unsigned int *flags) +{ + prb_lock(&printk_cpulock, flags); +} +EXPORT_SYMBOL(console_atomic_lock); + +void console_atomic_unlock(unsigned int flags) +{ + prb_unlock(&printk_cpulock, flags); +} +EXPORT_SYMBOL(console_atomic_unlock); + +bool console_atomic_kgdb_cpu_delay(unsigned int cpu) +{ + if (cpu != atomic_read(&printk_cpulock.owner)) + return false; + + kgdb_cpu = cpu; + return true; +} +EXPORT_SYMBOL(console_atomic_kgdb_cpu_delay); + +static void pr_msleep(bool may_sleep, int ms) +{ + if (may_sleep) { + msleep(ms); + } else { + while (ms--) + udelay(1000); + } +} + +/** + * pr_flush() - Wait for printing threads to catch up. + * + * @timeout_ms: The maximum time (in ms) to wait. + * @reset_on_progress: Reset the timeout if forward progress is seen. + * + * A value of 0 for @timeout_ms means no waiting will occur. A value of -1 + * represents infinite waiting. + * + * If @reset_on_progress is true, the timeout will be reset whenever any + * printer has been seen to make some forward progress. + * + * Context: Any context. + * Return: true if all enabled printers are caught up. + */ +bool pr_flush(int timeout_ms, bool reset_on_progress) +{ + int remaining = timeout_ms; + struct console *con; + u64 last_diff = 0; + bool may_sleep; + u64 printk_seq; + u64 diff; + u64 seq; + + may_sleep = (preemptible() && !in_softirq()); + + seq = prb_next_seq(prb); + + for (;;) { + diff = 0; + + for_each_console(con) { + if (!(con->flags & CON_ENABLED)) + continue; + printk_seq = read_console_seq(con); + if (printk_seq < seq) + diff += seq - printk_seq; + } + + if (diff != last_diff && reset_on_progress) + remaining = timeout_ms; + + if (diff == 0 || remaining == 0) + break; + + if (remaining < 0) { + pr_msleep(may_sleep, 100); + } else if (remaining < 100) { + pr_msleep(may_sleep, remaining); + remaining = 0; + } else { + pr_msleep(may_sleep, 100); + remaining -= 100; + } + + last_diff = diff; + } + + return (diff == 0); +} +EXPORT_SYMBOL(pr_flush); diff --git a/kernel/printk/printk_safe.c b/kernel/printk/printk_safe.c deleted file mode 100644 index 2e9e3ed7d63ef..0000000000000 --- a/kernel/printk/printk_safe.c +++ /dev/null @@ -1,422 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * printk_safe.c - Safe printk for printk-deadlock-prone contexts - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include "internal.h" - -/* - * printk() could not take logbuf_lock in NMI context. Instead, - * it uses an alternative implementation that temporary stores - * the strings into a per-CPU buffer. The content of the buffer - * is later flushed into the main ring buffer via IRQ work. - * - * The alternative implementation is chosen transparently - * by examining current printk() context mask stored in @printk_context - * per-CPU variable. - * - * The implementation allows to flush the strings also from another CPU. - * There are situations when we want to make sure that all buffers - * were handled or when IRQs are blocked. - */ - -#define SAFE_LOG_BUF_LEN ((1 << CONFIG_PRINTK_SAFE_LOG_BUF_SHIFT) - \ - sizeof(atomic_t) - \ - sizeof(atomic_t) - \ - sizeof(struct irq_work)) - -struct printk_safe_seq_buf { - atomic_t len; /* length of written data */ - atomic_t message_lost; - struct irq_work work; /* IRQ work that flushes the buffer */ - unsigned char buffer[SAFE_LOG_BUF_LEN]; -}; - -static DEFINE_PER_CPU(struct printk_safe_seq_buf, safe_print_seq); -static DEFINE_PER_CPU(int, printk_context); - -static DEFINE_RAW_SPINLOCK(safe_read_lock); - -#ifdef CONFIG_PRINTK_NMI -static DEFINE_PER_CPU(struct printk_safe_seq_buf, nmi_print_seq); -#endif - -/* Get flushed in a more safe context. */ -static void queue_flush_work(struct printk_safe_seq_buf *s) -{ - if (printk_percpu_data_ready()) - irq_work_queue(&s->work); -} - -/* - * Add a message to per-CPU context-dependent buffer. NMI and printk-safe - * have dedicated buffers, because otherwise printk-safe preempted by - * NMI-printk would have overwritten the NMI messages. - * - * The messages are flushed from irq work (or from panic()), possibly, - * from other CPU, concurrently with printk_safe_log_store(). Should this - * happen, printk_safe_log_store() will notice the buffer->len mismatch - * and repeat the write. - */ -static __printf(2, 0) int printk_safe_log_store(struct printk_safe_seq_buf *s, - const char *fmt, va_list args) -{ - int add; - size_t len; - va_list ap; - -again: - len = atomic_read(&s->len); - - /* The trailing '\0' is not counted into len. */ - if (len >= sizeof(s->buffer) - 1) { - atomic_inc(&s->message_lost); - queue_flush_work(s); - return 0; - } - - /* - * Make sure that all old data have been read before the buffer - * was reset. This is not needed when we just append data. - */ - if (!len) - smp_rmb(); - - va_copy(ap, args); - add = vscnprintf(s->buffer + len, sizeof(s->buffer) - len, fmt, ap); - va_end(ap); - if (!add) - return 0; - - /* - * Do it once again if the buffer has been flushed in the meantime. - * Note that atomic_cmpxchg() is an implicit memory barrier that - * makes sure that the data were written before updating s->len. - */ - if (atomic_cmpxchg(&s->len, len, len + add) != len) - goto again; - - queue_flush_work(s); - return add; -} - -static inline void printk_safe_flush_line(const char *text, int len) -{ - /* - * Avoid any console drivers calls from here, because we may be - * in NMI or printk_safe context (when in panic). The messages - * must go only into the ring buffer at this stage. Consoles will - * get explicitly called later when a crashdump is not generated. - */ - printk_deferred("%.*s", len, text); -} - -/* printk part of the temporary buffer line by line */ -static int printk_safe_flush_buffer(const char *start, size_t len) -{ - const char *c, *end; - bool header; - - c = start; - end = start + len; - header = true; - - /* Print line by line. */ - while (c < end) { - if (*c == '\n') { - printk_safe_flush_line(start, c - start + 1); - start = ++c; - header = true; - continue; - } - - /* Handle continuous lines or missing new line. */ - if ((c + 1 < end) && printk_get_level(c)) { - if (header) { - c = printk_skip_level(c); - continue; - } - - printk_safe_flush_line(start, c - start); - start = c++; - header = true; - continue; - } - - header = false; - c++; - } - - /* Check if there was a partial line. Ignore pure header. */ - if (start < end && !header) { - static const char newline[] = KERN_CONT "\n"; - - printk_safe_flush_line(start, end - start); - printk_safe_flush_line(newline, strlen(newline)); - } - - return len; -} - -static void report_message_lost(struct printk_safe_seq_buf *s) -{ - int lost = atomic_xchg(&s->message_lost, 0); - - if (lost) - printk_deferred("Lost %d message(s)!\n", lost); -} - -/* - * Flush data from the associated per-CPU buffer. The function - * can be called either via IRQ work or independently. - */ -static void __printk_safe_flush(struct irq_work *work) -{ - struct printk_safe_seq_buf *s = - container_of(work, struct printk_safe_seq_buf, work); - unsigned long flags; - size_t len; - int i; - - /* - * The lock has two functions. First, one reader has to flush all - * available message to make the lockless synchronization with - * writers easier. Second, we do not want to mix messages from - * different CPUs. This is especially important when printing - * a backtrace. - */ - raw_spin_lock_irqsave(&safe_read_lock, flags); - - i = 0; -more: - len = atomic_read(&s->len); - - /* - * This is just a paranoid check that nobody has manipulated - * the buffer an unexpected way. If we printed something then - * @len must only increase. Also it should never overflow the - * buffer size. - */ - if ((i && i >= len) || len > sizeof(s->buffer)) { - const char *msg = "printk_safe_flush: internal error\n"; - - printk_safe_flush_line(msg, strlen(msg)); - len = 0; - } - - if (!len) - goto out; /* Someone else has already flushed the buffer. */ - - /* Make sure that data has been written up to the @len */ - smp_rmb(); - i += printk_safe_flush_buffer(s->buffer + i, len - i); - - /* - * Check that nothing has got added in the meantime and truncate - * the buffer. Note that atomic_cmpxchg() is an implicit memory - * barrier that makes sure that the data were copied before - * updating s->len. - */ - if (atomic_cmpxchg(&s->len, len, 0) != len) - goto more; - -out: - report_message_lost(s); - raw_spin_unlock_irqrestore(&safe_read_lock, flags); -} - -/** - * printk_safe_flush - flush all per-cpu nmi buffers. - * - * The buffers are flushed automatically via IRQ work. This function - * is useful only when someone wants to be sure that all buffers have - * been flushed at some point. - */ -void printk_safe_flush(void) -{ - int cpu; - - for_each_possible_cpu(cpu) { -#ifdef CONFIG_PRINTK_NMI - __printk_safe_flush(&per_cpu(nmi_print_seq, cpu).work); -#endif - __printk_safe_flush(&per_cpu(safe_print_seq, cpu).work); - } -} - -/** - * printk_safe_flush_on_panic - flush all per-cpu nmi buffers when the system - * goes down. - * - * Similar to printk_safe_flush() but it can be called even in NMI context when - * the system goes down. It does the best effort to get NMI messages into - * the main ring buffer. - * - * Note that it could try harder when there is only one CPU online. - */ -void printk_safe_flush_on_panic(void) -{ - /* - * Make sure that we could access the main ring buffer. - * Do not risk a double release when more CPUs are up. - */ - if (raw_spin_is_locked(&logbuf_lock)) { - if (num_online_cpus() > 1) - return; - - debug_locks_off(); - raw_spin_lock_init(&logbuf_lock); - } - - if (raw_spin_is_locked(&safe_read_lock)) { - if (num_online_cpus() > 1) - return; - - debug_locks_off(); - raw_spin_lock_init(&safe_read_lock); - } - - printk_safe_flush(); -} - -#ifdef CONFIG_PRINTK_NMI -/* - * Safe printk() for NMI context. It uses a per-CPU buffer to - * store the message. NMIs are not nested, so there is always only - * one writer running. But the buffer might get flushed from another - * CPU, so we need to be careful. - */ -static __printf(1, 0) int vprintk_nmi(const char *fmt, va_list args) -{ - struct printk_safe_seq_buf *s = this_cpu_ptr(&nmi_print_seq); - - return printk_safe_log_store(s, fmt, args); -} - -void noinstr printk_nmi_enter(void) -{ - this_cpu_add(printk_context, PRINTK_NMI_CONTEXT_OFFSET); -} - -void noinstr printk_nmi_exit(void) -{ - this_cpu_sub(printk_context, PRINTK_NMI_CONTEXT_OFFSET); -} - -/* - * Marks a code that might produce many messages in NMI context - * and the risk of losing them is more critical than eventual - * reordering. - * - * It has effect only when called in NMI context. Then printk() - * will try to store the messages into the main logbuf directly - * and use the per-CPU buffers only as a fallback when the lock - * is not available. - */ -void printk_nmi_direct_enter(void) -{ - if (this_cpu_read(printk_context) & PRINTK_NMI_CONTEXT_MASK) - this_cpu_or(printk_context, PRINTK_NMI_DIRECT_CONTEXT_MASK); -} - -void printk_nmi_direct_exit(void) -{ - this_cpu_and(printk_context, ~PRINTK_NMI_DIRECT_CONTEXT_MASK); -} - -#else - -static __printf(1, 0) int vprintk_nmi(const char *fmt, va_list args) -{ - return 0; -} - -#endif /* CONFIG_PRINTK_NMI */ - -/* - * Lock-less printk(), to avoid deadlocks should the printk() recurse - * into itself. It uses a per-CPU buffer to store the message, just like - * NMI. - */ -static __printf(1, 0) int vprintk_safe(const char *fmt, va_list args) -{ - struct printk_safe_seq_buf *s = this_cpu_ptr(&safe_print_seq); - - return printk_safe_log_store(s, fmt, args); -} - -/* Can be preempted by NMI. */ -void __printk_safe_enter(void) -{ - this_cpu_inc(printk_context); -} - -/* Can be preempted by NMI. */ -void __printk_safe_exit(void) -{ - this_cpu_dec(printk_context); -} - -__printf(1, 0) int vprintk_func(const char *fmt, va_list args) -{ -#ifdef CONFIG_KGDB_KDB - /* Allow to pass printk() to kdb but avoid a recursion. */ - if (unlikely(kdb_trap_printk && kdb_printf_cpu < 0)) - return vkdb_printf(KDB_MSGSRC_PRINTK, fmt, args); -#endif - - /* - * Try to use the main logbuf even in NMI. But avoid calling console - * drivers that might have their own locks. - */ - if ((this_cpu_read(printk_context) & PRINTK_NMI_DIRECT_CONTEXT_MASK) && - raw_spin_trylock(&logbuf_lock)) { - int len; - - len = vprintk_store(0, LOGLEVEL_DEFAULT, NULL, fmt, args); - raw_spin_unlock(&logbuf_lock); - defer_console_output(); - return len; - } - - /* Use extra buffer in NMI when logbuf_lock is taken or in safe mode. */ - if (this_cpu_read(printk_context) & PRINTK_NMI_CONTEXT_MASK) - return vprintk_nmi(fmt, args); - - /* Use extra buffer to prevent a recursion deadlock in safe mode. */ - if (this_cpu_read(printk_context) & PRINTK_SAFE_CONTEXT_MASK) - return vprintk_safe(fmt, args); - - /* No obstacles. */ - return vprintk_default(fmt, args); -} - -void __init printk_safe_init(void) -{ - int cpu; - - for_each_possible_cpu(cpu) { - struct printk_safe_seq_buf *s; - - s = &per_cpu(safe_print_seq, cpu); - init_irq_work(&s->work, __printk_safe_flush); - -#ifdef CONFIG_PRINTK_NMI - s = &per_cpu(nmi_print_seq, cpu); - init_irq_work(&s->work, __printk_safe_flush); -#endif - } - - /* Flush pending messages that did not have scheduled IRQ works. */ - printk_safe_flush(); -} diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 821cf17238147..95025b90810fd 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -180,7 +180,14 @@ static bool ptrace_freeze_traced(struct task_struct *task) spin_lock_irq(&task->sighand->siglock); if (task_is_traced(task) && !__fatal_signal_pending(task)) { - task->state = __TASK_TRACED; + unsigned long flags; + + raw_spin_lock_irqsave(&task->pi_lock, flags); + if (task->state & __TASK_TRACED) + task->state = __TASK_TRACED; + else + task->saved_state = __TASK_TRACED; + raw_spin_unlock_irqrestore(&task->pi_lock, flags); ret = true; } spin_unlock_irq(&task->sighand->siglock); @@ -190,8 +197,8 @@ static bool ptrace_freeze_traced(struct task_struct *task) static void ptrace_unfreeze_traced(struct task_struct *task) { - if (task->state != __TASK_TRACED) - return; + unsigned long flags; + bool frozen = true; WARN_ON(!task->ptrace || task->parent != current); @@ -200,12 +207,19 @@ static void ptrace_unfreeze_traced(struct task_struct *task) * Recheck state under the lock to close this race. */ spin_lock_irq(&task->sighand->siglock); - if (task->state == __TASK_TRACED) { - if (__fatal_signal_pending(task)) - wake_up_state(task, __TASK_TRACED); - else - task->state = TASK_TRACED; - } + + raw_spin_lock_irqsave(&task->pi_lock, flags); + if (task->state == __TASK_TRACED) + task->state = TASK_TRACED; + else if (task->saved_state == __TASK_TRACED) + task->saved_state = TASK_TRACED; + else + frozen = false; + raw_spin_unlock_irqrestore(&task->pi_lock, flags); + + if (frozen && __fatal_signal_pending(task)) + wake_up_state(task, __TASK_TRACED); + spin_unlock_irq(&task->sighand->siglock); } diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c index 99657ffa66887..d41a13e091856 100644 --- a/kernel/rcu/rcutorture.c +++ b/kernel/rcu/rcutorture.c @@ -61,10 +61,13 @@ MODULE_AUTHOR("Paul E. McKenney and Josh Triplett > RCUTORTURE_RDR_SHIFT) > 1); rtrsp->rt_readstate = newstate; - /* First, put new protection in place to avoid critical-section gap. */ + /* + * First, put new protection in place to avoid critical-section gap. + * Disable preemption around the ATOM disables to ensure that + * in_atomic() is true. + */ if (statesnew & RCUTORTURE_RDR_BH) local_bh_disable(); + if (statesnew & RCUTORTURE_RDR_RBH) + rcu_read_lock_bh(); if (statesnew & RCUTORTURE_RDR_IRQ) local_irq_disable(); if (statesnew & RCUTORTURE_RDR_PREEMPT) preempt_disable(); - if (statesnew & RCUTORTURE_RDR_RBH) - rcu_read_lock_bh(); if (statesnew & RCUTORTURE_RDR_SCHED) rcu_read_lock_sched(); + preempt_disable(); + if (statesnew & RCUTORTURE_RDR_ATOM_BH) + local_bh_disable(); + if (statesnew & RCUTORTURE_RDR_ATOM_RBH) + rcu_read_lock_bh(); + preempt_enable(); if (statesnew & RCUTORTURE_RDR_RCU) idxnew = cur_ops->readlock() << RCUTORTURE_RDR_SHIFT; - /* Next, remove old protection, irq first due to bh conflict. */ + /* + * Next, remove old protection, in decreasing order of strength + * to avoid unlock paths that aren't safe in the stronger + * context. Disable preemption around the ATOM enables in + * case the context was only atomic due to IRQ disabling. + */ + preempt_disable(); if (statesold & RCUTORTURE_RDR_IRQ) local_irq_enable(); - if (statesold & RCUTORTURE_RDR_BH) + if (statesold & RCUTORTURE_RDR_ATOM_BH) local_bh_enable(); + if (statesold & RCUTORTURE_RDR_ATOM_RBH) + rcu_read_unlock_bh(); + preempt_enable(); if (statesold & RCUTORTURE_RDR_PREEMPT) preempt_enable(); - if (statesold & RCUTORTURE_RDR_RBH) - rcu_read_unlock_bh(); if (statesold & RCUTORTURE_RDR_SCHED) rcu_read_unlock_sched(); + if (statesold & RCUTORTURE_RDR_BH) + local_bh_enable(); + if (statesold & RCUTORTURE_RDR_RBH) + rcu_read_unlock_bh(); + if (statesold & RCUTORTURE_RDR_RCU) { bool lockit = !statesnew && !(torture_random(trsp) & 0xffff); @@ -1485,6 +1510,12 @@ rcutorture_extend_mask(int oldmask, struct torture_random_state *trsp) int mask = rcutorture_extend_mask_max(); unsigned long randmask1 = torture_random(trsp) >> 8; unsigned long randmask2 = randmask1 >> 3; + unsigned long preempts = RCUTORTURE_RDR_PREEMPT | RCUTORTURE_RDR_SCHED; + unsigned long preempts_irq = preempts | RCUTORTURE_RDR_IRQ; + unsigned long nonatomic_bhs = RCUTORTURE_RDR_BH | RCUTORTURE_RDR_RBH; + unsigned long atomic_bhs = RCUTORTURE_RDR_ATOM_BH | + RCUTORTURE_RDR_ATOM_RBH; + unsigned long tmp; WARN_ON_ONCE(mask >> RCUTORTURE_RDR_SHIFT); /* Mostly only one bit (need preemption!), sometimes lots of bits. */ @@ -1492,11 +1523,49 @@ rcutorture_extend_mask(int oldmask, struct torture_random_state *trsp) mask = mask & randmask2; else mask = mask & (1 << (randmask2 % RCUTORTURE_RDR_NBITS)); - /* Can't enable bh w/irq disabled. */ - if ((mask & RCUTORTURE_RDR_IRQ) && - ((!(mask & RCUTORTURE_RDR_BH) && (oldmask & RCUTORTURE_RDR_BH)) || - (!(mask & RCUTORTURE_RDR_RBH) && (oldmask & RCUTORTURE_RDR_RBH)))) - mask |= RCUTORTURE_RDR_BH | RCUTORTURE_RDR_RBH; + + /* + * Can't enable bh w/irq disabled. + */ + tmp = atomic_bhs | nonatomic_bhs; + if (mask & RCUTORTURE_RDR_IRQ) + mask |= oldmask & tmp; + + /* + * Ideally these sequences would be detected in debug builds + * (regardless of RT), but until then don't stop testing + * them on non-RT. + */ + if (IS_ENABLED(CONFIG_PREEMPT_RT)) { + /* + * Can't release the outermost rcu lock in an irq disabled + * section without preemption also being disabled, if irqs + * had ever been enabled during this RCU critical section + * (could leak a special flag and delay reporting the qs). + */ + if ((oldmask & RCUTORTURE_RDR_RCU) && + (mask & RCUTORTURE_RDR_IRQ) && + !(mask & preempts)) + mask |= RCUTORTURE_RDR_RCU; + + /* Can't modify atomic bh in non-atomic context */ + if ((oldmask & atomic_bhs) && (mask & atomic_bhs) && + !(mask & preempts_irq)) { + mask |= oldmask & preempts_irq; + if (mask & RCUTORTURE_RDR_IRQ) + mask |= oldmask & tmp; + } + if ((mask & atomic_bhs) && !(mask & preempts_irq)) + mask |= RCUTORTURE_RDR_PREEMPT; + + /* Can't modify non-atomic bh in atomic context */ + tmp = nonatomic_bhs; + if (oldmask & preempts_irq) + mask &= ~tmp; + if ((oldmask | mask) & preempts_irq) + mask |= oldmask & tmp; + } + return mask ?: RCUTORTURE_RDR_RCU; } diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h index af7c19439f4ec..3384c0bc6b218 100644 --- a/kernel/rcu/tasks.h +++ b/kernel/rcu/tasks.h @@ -1259,7 +1259,7 @@ static void test_rcu_tasks_callback(struct rcu_head *rhp) rttd->notrun = true; } -static void rcu_tasks_initiate_self_tests(void) +void rcu_tasks_initiate_self_tests(void) { pr_info("Running RCU-tasks wait API self tests\n"); #ifdef CONFIG_TASKS_RCU @@ -1296,9 +1296,7 @@ static int rcu_tasks_verify_self_tests(void) return ret; } late_initcall(rcu_tasks_verify_self_tests); -#else /* #ifdef CONFIG_PROVE_RCU */ -static void rcu_tasks_initiate_self_tests(void) { } -#endif /* #else #ifdef CONFIG_PROVE_RCU */ +#endif /* #ifdef CONFIG_PROVE_RCU */ void __init rcu_init_tasks_generic(void) { @@ -1313,9 +1311,6 @@ void __init rcu_init_tasks_generic(void) #ifdef CONFIG_TASKS_TRACE_RCU rcu_spawn_tasks_trace_kthread(); #endif - - // Run the self-tests. - rcu_tasks_initiate_self_tests(); } #else /* #ifdef CONFIG_TASKS_RCU_GENERIC */ diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 98191218d891d..46f2d26a7108e 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -64,7 +64,11 @@ const_debug unsigned int sysctl_sched_features = * Number of tasks to iterate in a single balance run. * Limited because this is done with IRQs disabled. */ +#ifdef CONFIG_PREEMPT_RT +const_debug unsigned int sysctl_sched_nr_migrate = 8; +#else const_debug unsigned int sysctl_sched_nr_migrate = 32; +#endif /* * period over which we measure -rt task CPU usage in us. @@ -502,9 +506,15 @@ static bool set_nr_if_polling(struct task_struct *p) #endif #endif -static bool __wake_q_add(struct wake_q_head *head, struct task_struct *task) +static bool __wake_q_add(struct wake_q_head *head, struct task_struct *task, + bool sleeper) { - struct wake_q_node *node = &task->wake_q; + struct wake_q_node *node; + + if (sleeper) + node = &task->wake_q_sleeper; + else + node = &task->wake_q; /* * Atomically grab the task, if ->wake_q is !nil already it means @@ -540,7 +550,13 @@ static bool __wake_q_add(struct wake_q_head *head, struct task_struct *task) */ void wake_q_add(struct wake_q_head *head, struct task_struct *task) { - if (__wake_q_add(head, task)) + if (__wake_q_add(head, task, false)) + get_task_struct(task); +} + +void wake_q_add_sleeper(struct wake_q_head *head, struct task_struct *task) +{ + if (__wake_q_add(head, task, true)) get_task_struct(task); } @@ -563,28 +579,39 @@ void wake_q_add(struct wake_q_head *head, struct task_struct *task) */ void wake_q_add_safe(struct wake_q_head *head, struct task_struct *task) { - if (!__wake_q_add(head, task)) + if (!__wake_q_add(head, task, false)) put_task_struct(task); } -void wake_up_q(struct wake_q_head *head) +void __wake_up_q(struct wake_q_head *head, bool sleeper) { struct wake_q_node *node = head->first; while (node != WAKE_Q_TAIL) { struct task_struct *task; - task = container_of(node, struct task_struct, wake_q); + if (sleeper) + task = container_of(node, struct task_struct, wake_q_sleeper); + else + task = container_of(node, struct task_struct, wake_q); + BUG_ON(!task); /* Task can safely be re-inserted now: */ node = node->next; - task->wake_q.next = NULL; + if (sleeper) + task->wake_q_sleeper.next = NULL; + else + task->wake_q.next = NULL; /* * wake_up_process() executes a full barrier, which pairs with * the queueing in wake_q_add() so as not to miss wakeups. */ - wake_up_process(task); + if (sleeper) + wake_up_lock_sleeper(task); + else + wake_up_process(task); + put_task_struct(task); } } @@ -620,6 +647,48 @@ void resched_curr(struct rq *rq) trace_sched_wake_idle_without_ipi(cpu); } +#ifdef CONFIG_PREEMPT_LAZY + +static int tsk_is_polling(struct task_struct *p) +{ +#ifdef TIF_POLLING_NRFLAG + return test_tsk_thread_flag(p, TIF_POLLING_NRFLAG); +#else + return 0; +#endif +} + +void resched_curr_lazy(struct rq *rq) +{ + struct task_struct *curr = rq->curr; + int cpu; + + if (!sched_feat(PREEMPT_LAZY)) { + resched_curr(rq); + return; + } + + lockdep_assert_held(&rq->lock); + + if (test_tsk_need_resched(curr)) + return; + + if (test_tsk_need_resched_lazy(curr)) + return; + + set_tsk_need_resched_lazy(curr); + + cpu = cpu_of(rq); + if (cpu == smp_processor_id()) + return; + + /* NEED_RESCHED_LAZY must be visible before we test polling */ + smp_mb(); + if (!tsk_is_polling(curr)) + smp_send_reschedule(cpu); +} +#endif + void resched_cpu(int cpu) { struct rq *rq = cpu_rq(cpu); @@ -1751,6 +1820,7 @@ void migrate_disable(void) preempt_disable(); this_rq()->nr_pinned++; p->migration_disabled = 1; + preempt_lazy_disable(); preempt_enable(); } EXPORT_SYMBOL_GPL(migrate_disable); @@ -1779,6 +1849,7 @@ void migrate_enable(void) barrier(); p->migration_disabled = 0; this_rq()->nr_pinned--; + preempt_lazy_enable(); preempt_enable(); } EXPORT_SYMBOL_GPL(migrate_enable); @@ -2569,6 +2640,18 @@ int migrate_swap(struct task_struct *cur, struct task_struct *p, } #endif /* CONFIG_NUMA_BALANCING */ +static bool check_task_state(struct task_struct *p, long match_state) +{ + bool match = false; + + raw_spin_lock_irq(&p->pi_lock); + if (p->state == match_state || p->saved_state == match_state) + match = true; + raw_spin_unlock_irq(&p->pi_lock); + + return match; +} + /* * wait_task_inactive - wait for a thread to unschedule. * @@ -2613,7 +2696,7 @@ unsigned long wait_task_inactive(struct task_struct *p, long match_state) * is actually now running somewhere else! */ while (task_running(rq, p)) { - if (match_state && unlikely(p->state != match_state)) + if (match_state && !check_task_state(p, match_state)) return 0; cpu_relax(); } @@ -2628,7 +2711,8 @@ unsigned long wait_task_inactive(struct task_struct *p, long match_state) running = task_running(rq, p); queued = task_on_rq_queued(p); ncsw = 0; - if (!match_state || p->state == match_state) + if (!match_state || p->state == match_state || + p->saved_state == match_state) ncsw = p->nvcsw | LONG_MIN; /* sets MSB */ task_rq_unlock(rq, p, &rf); @@ -3314,7 +3398,7 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) int cpu, success = 0; preempt_disable(); - if (p == current) { + if (!IS_ENABLED(CONFIG_PREEMPT_RT) && p == current) { /* * We're waking current, this means 'p->on_rq' and 'task_cpu(p) * == smp_processor_id()'. Together this means we can special @@ -3344,8 +3428,26 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) */ raw_spin_lock_irqsave(&p->pi_lock, flags); smp_mb__after_spinlock(); - if (!(p->state & state)) + if (!(p->state & state)) { + /* + * The task might be running due to a spinlock sleeper + * wakeup. Check the saved state and set it to running + * if the wakeup condition is true. + */ + if (!(wake_flags & WF_LOCK_SLEEPER)) { + if (p->saved_state & state) { + p->saved_state = TASK_RUNNING; + success = 1; + } + } goto unlock; + } + /* + * If this is a regular wakeup, then we can unconditionally + * clear the saved state of a "lock sleeper". + */ + if (!(wake_flags & WF_LOCK_SLEEPER)) + p->saved_state = TASK_RUNNING; trace_sched_waking(p); @@ -3534,6 +3636,18 @@ int wake_up_process(struct task_struct *p) } EXPORT_SYMBOL(wake_up_process); +/** + * wake_up_lock_sleeper - Wake up a specific process blocked on a "sleeping lock" + * @p: The process to be woken up. + * + * Same as wake_up_process() above, but wake_flags=WF_LOCK_SLEEPER to indicate + * the nature of the wakeup. + */ +int wake_up_lock_sleeper(struct task_struct *p) +{ + return try_to_wake_up(p, TASK_UNINTERRUPTIBLE, WF_LOCK_SLEEPER); +} + int wake_up_state(struct task_struct *p, unsigned int state) { return try_to_wake_up(p, state, 0); @@ -3781,6 +3895,9 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p) p->on_cpu = 0; #endif init_task_preempt_count(p); +#ifdef CONFIG_HAVE_PREEMPT_LAZY + task_thread_info(p)->preempt_lazy_count = 0; +#endif #ifdef CONFIG_SMP plist_node_init(&p->pushable_tasks, MAX_PRIO); RB_CLEAR_NODE(&p->pushable_dl_tasks); @@ -4213,23 +4330,18 @@ static struct rq *finish_task_switch(struct task_struct *prev) * provided by mmdrop(), * - a sync_core for SYNC_CORE. */ + /* + * We use mmdrop_delayed() here so we don't have to do the + * full __mmdrop() when we are the last user. + */ if (mm) { membarrier_mm_sync_core_before_usermode(mm); - mmdrop(mm); + mmdrop_delayed(mm); } if (unlikely(prev_state == TASK_DEAD)) { if (prev->sched_class->task_dead) prev->sched_class->task_dead(prev); - /* - * Remove function-return probe instances associated with this - * task and put them back on the free list. - */ - kprobe_flush_task(prev); - - /* Task is done with its stack. */ - put_task_stack(prev); - put_task_struct_rcu_user(prev); } @@ -4951,7 +5063,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) * * WARNING: must be called with preemption disabled! */ -static void __sched notrace __schedule(bool preempt) +static void __sched notrace __schedule(bool preempt, bool spinning_lock) { struct task_struct *prev, *next; unsigned long *switch_count; @@ -5004,7 +5116,7 @@ static void __sched notrace __schedule(bool preempt) * - ptrace_{,un}freeze_traced() can change ->state underneath us. */ prev_state = prev->state; - if (!preempt && prev_state) { + if ((!preempt || spinning_lock) && prev_state) { if (signal_pending_state(prev_state, prev)) { prev->state = TASK_RUNNING; } else { @@ -5039,6 +5151,7 @@ static void __sched notrace __schedule(bool preempt) next = pick_next_task(rq, prev, &rf); clear_tsk_need_resched(prev); + clear_tsk_need_resched_lazy(prev); clear_preempt_need_resched(); if (likely(prev != next)) { @@ -5088,7 +5201,7 @@ void __noreturn do_task_dead(void) /* Tell freezer to ignore us: */ current->flags |= PF_NOFREEZE; - __schedule(false); + __schedule(false, false); BUG(); /* Avoid "noreturn function does return" - but don't continue if BUG() is a NOP: */ @@ -5121,9 +5234,6 @@ static inline void sched_submit_work(struct task_struct *tsk) preempt_enable_no_resched(); } - if (tsk_is_pi_blocked(tsk)) - return; - /* * If we are going to sleep and we have plugged IO queued, * make sure to submit it to avoid deadlocks. @@ -5149,7 +5259,7 @@ asmlinkage __visible void __sched schedule(void) sched_submit_work(tsk); do { preempt_disable(); - __schedule(false); + __schedule(false, false); sched_preempt_enable_no_resched(); } while (need_resched()); sched_update_worker(tsk); @@ -5177,7 +5287,7 @@ void __sched schedule_idle(void) */ WARN_ON_ONCE(current->state); do { - __schedule(false); + __schedule(false, false); } while (need_resched()); } @@ -5230,7 +5340,7 @@ static void __sched notrace preempt_schedule_common(void) */ preempt_disable_notrace(); preempt_latency_start(1); - __schedule(true); + __schedule(true, false); preempt_latency_stop(1); preempt_enable_no_resched_notrace(); @@ -5241,6 +5351,30 @@ static void __sched notrace preempt_schedule_common(void) } while (need_resched()); } +#ifdef CONFIG_PREEMPT_LAZY +/* + * If TIF_NEED_RESCHED is then we allow to be scheduled away since this is + * set by a RT task. Oterwise we try to avoid beeing scheduled out as long as + * preempt_lazy_count counter >0. + */ +static __always_inline int preemptible_lazy(void) +{ + if (test_thread_flag(TIF_NEED_RESCHED)) + return 1; + if (current_thread_info()->preempt_lazy_count) + return 0; + return 1; +} + +#else + +static inline int preemptible_lazy(void) +{ + return 1; +} + +#endif + #ifdef CONFIG_PREEMPTION /* * This is the entry point to schedule() from in-kernel preemption @@ -5254,12 +5388,26 @@ asmlinkage __visible void __sched notrace preempt_schedule(void) */ if (likely(!preemptible())) return; - + if (!preemptible_lazy()) + return; preempt_schedule_common(); } NOKPROBE_SYMBOL(preempt_schedule); EXPORT_SYMBOL(preempt_schedule); +#ifdef CONFIG_PREEMPT_RT +void __sched notrace preempt_schedule_lock(void) +{ + do { + preempt_disable(); + __schedule(true, true); + sched_preempt_enable_no_resched(); + } while (need_resched()); +} +NOKPROBE_SYMBOL(preempt_schedule_lock); +EXPORT_SYMBOL(preempt_schedule_lock); +#endif + #ifdef CONFIG_PREEMPT_DYNAMIC DEFINE_STATIC_CALL(preempt_schedule, __preempt_schedule_func); EXPORT_STATIC_CALL_TRAMP(preempt_schedule); @@ -5287,6 +5435,9 @@ asmlinkage __visible void __sched notrace preempt_schedule_notrace(void) if (likely(!preemptible())) return; + if (!preemptible_lazy()) + return; + do { /* * Because the function tracer can trace preempt_count_sub() @@ -5309,7 +5460,7 @@ asmlinkage __visible void __sched notrace preempt_schedule_notrace(void) * an infinite recursion. */ prev_ctx = exception_enter(); - __schedule(true); + __schedule(true, false); exception_exit(prev_ctx); preempt_latency_stop(1); @@ -5527,7 +5678,7 @@ asmlinkage __visible void __sched preempt_schedule_irq(void) do { preempt_disable(); local_irq_enable(); - __schedule(true); + __schedule(true, false); local_irq_disable(); sched_preempt_enable_no_resched(); } while (need_resched()); @@ -7479,7 +7630,9 @@ void init_idle(struct task_struct *idle, int cpu) /* Set the preempt count _outside_ the spinlocks! */ init_idle_preempt_count(idle, cpu); - +#ifdef CONFIG_HAVE_PREEMPT_LAZY + task_thread_info(idle)->preempt_lazy_count = 0; +#endif /* * The idle tasks have their own, simple scheduling class: */ @@ -7584,6 +7737,7 @@ void sched_setnuma(struct task_struct *p, int nid) #endif /* CONFIG_NUMA_BALANCING */ #ifdef CONFIG_HOTPLUG_CPU + /* * Ensure that the idle task is using init_mm right before its CPU goes * offline. @@ -8260,7 +8414,7 @@ void __init sched_init(void) #ifdef CONFIG_DEBUG_ATOMIC_SLEEP static inline int preempt_count_equals(int preempt_offset) { - int nested = preempt_count() + rcu_preempt_depth(); + int nested = preempt_count() + sched_rcu_preempt_depth(); return (nested == preempt_offset); } diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index 5f611658eeab1..2c36a5fad5891 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -60,7 +60,7 @@ void irqtime_account_irq(struct task_struct *curr, unsigned int offset) cpu = smp_processor_id(); delta = sched_clock_cpu(cpu) - irqtime->irq_start_time; irqtime->irq_start_time += delta; - pc = preempt_count() - offset; + pc = irq_count() - offset; /* * We do not account for softirq time from ksoftirqd here. @@ -421,7 +421,7 @@ void vtime_task_switch(struct task_struct *prev) void vtime_account_irq(struct task_struct *tsk, unsigned int offset) { - unsigned int pc = preempt_count() - offset; + unsigned int pc = irq_count() - offset; if (pc & HARDIRQ_OFFSET) { vtime_account_hardirq(tsk); diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 794c2cb945f8b..f354c6d370d72 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -4365,7 +4365,7 @@ check_preempt_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr) ideal_runtime = sched_slice(cfs_rq, curr); delta_exec = curr->sum_exec_runtime - curr->prev_sum_exec_runtime; if (delta_exec > ideal_runtime) { - resched_curr(rq_of(cfs_rq)); + resched_curr_lazy(rq_of(cfs_rq)); /* * The current task ran long enough, ensure it doesn't get * re-elected due to buddy favours. @@ -4389,7 +4389,7 @@ check_preempt_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr) return; if (delta > ideal_runtime) - resched_curr(rq_of(cfs_rq)); + resched_curr_lazy(rq_of(cfs_rq)); } static void @@ -4532,7 +4532,7 @@ 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; } /* @@ -4669,7 +4669,7 @@ static void __account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec) * hierarchy can be throttled */ if (!assign_cfs_rq_runtime(cfs_rq) && likely(cfs_rq->curr)) - resched_curr(rq_of(cfs_rq)); + resched_curr_lazy(rq_of(cfs_rq)); } static __always_inline @@ -5413,7 +5413,7 @@ static void hrtick_start_fair(struct rq *rq, struct task_struct *p) if (delta < 0) { if (task_current(rq, p)) - resched_curr(rq); + resched_curr_lazy(rq); return; } hrtick_start(rq, delta); @@ -6988,7 +6988,7 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_ return; preempt: - resched_curr(rq); + resched_curr_lazy(rq); /* * Only set the backward buddy when the current task is still * on the rq. This can happen when a wakeup gets interleaved @@ -10775,7 +10775,7 @@ static void task_fork_fair(struct task_struct *p) * 'current' within the tree based on its new key value. */ swap(curr->vruntime, se->vruntime); - resched_curr(rq); + resched_curr_lazy(rq); } se->vruntime -= cfs_rq->min_vruntime; @@ -10802,7 +10802,7 @@ prio_changed_fair(struct rq *rq, struct task_struct *p, int oldprio) */ if (task_current(rq, p)) { if (p->prio > oldprio) - resched_curr(rq); + resched_curr_lazy(rq); } else check_preempt_curr(rq, p, 0); } diff --git a/kernel/sched/features.h b/kernel/sched/features.h index 1bc2b158fc515..c490f2c902aed 100644 --- a/kernel/sched/features.h +++ b/kernel/sched/features.h @@ -46,11 +46,19 @@ SCHED_FEAT(DOUBLE_TICK, false) */ SCHED_FEAT(NONTASK_CAPACITY, true) +#ifdef CONFIG_PREEMPT_RT +SCHED_FEAT(TTWU_QUEUE, false) +# ifdef CONFIG_PREEMPT_LAZY +SCHED_FEAT(PREEMPT_LAZY, true) +# endif +#else + /* * Queue remote wakeups on the target CPU and process them * using the scheduler IPI. Reduces rq->lock contention/bounces. */ SCHED_FEAT(TTWU_QUEUE, true) +#endif /* * When doing wakeups, attempt to limit superfluous scans of the LLC domain. diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 10a1522b1e303..178fe64154e7f 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -1751,6 +1751,7 @@ static inline int task_on_rq_migrating(struct task_struct *p) #define WF_SYNC 0x10 /* Waker goes to sleep after wakeup */ #define WF_MIGRATED 0x20 /* Internal use, task got migrated */ #define WF_ON_CPU 0x40 /* Wakee is on_cpu */ +#define WF_LOCK_SLEEPER 0x80 /* Wakeup spinlock "sleeper" */ #ifdef CONFIG_SMP static_assert(WF_EXEC == SD_BALANCE_EXEC); @@ -2014,6 +2015,15 @@ extern void reweight_task(struct task_struct *p, int prio); extern void resched_curr(struct rq *rq); extern void resched_cpu(int cpu); +#ifdef CONFIG_PREEMPT_LAZY +extern void resched_curr_lazy(struct rq *rq); +#else +static inline void resched_curr_lazy(struct rq *rq) +{ + resched_curr(rq); +} +#endif + extern struct rt_bandwidth def_rt_bandwidth; extern void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime); diff --git a/kernel/sched/swait.c b/kernel/sched/swait.c index e1c655f928c74..f230b1ac7f910 100644 --- a/kernel/sched/swait.c +++ b/kernel/sched/swait.c @@ -64,6 +64,7 @@ void swake_up_all(struct swait_queue_head *q) struct swait_queue *curr; LIST_HEAD(tmp); + WARN_ON(irqs_disabled()); raw_spin_lock_irq(&q->lock); list_splice_init(&q->task_list, &tmp); while (!list_empty(&tmp)) { diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index 09d35044bd889..6f7c0f493be34 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -526,7 +526,8 @@ static int init_rootdomain(struct root_domain *rd) #ifdef HAVE_RT_PUSH_IPI rd->rto_cpu = -1; raw_spin_lock_init(&rd->rto_lock); - init_irq_work(&rd->rto_push_work, rto_push_irq_work_func); +// init_irq_work(&rd->rto_push_work, rto_push_irq_work_func); + rd->rto_push_work = IRQ_WORK_INIT_HARD(rto_push_irq_work_func); #endif rd->visit_gen = 0; diff --git a/kernel/signal.c b/kernel/signal.c index ba4d1ef39a9ea..5baac8c5d2e9c 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -20,6 +20,7 @@ #include #include #include +#include #include #include #include @@ -404,13 +405,30 @@ void task_join_group_stop(struct task_struct *task) task_set_jobctl_pending(task, mask | JOBCTL_STOP_PENDING); } +static struct sigqueue *sigqueue_from_cache(struct task_struct *t) +{ + struct sigqueue *q = t->sigqueue_cache; + + if (q && cmpxchg(&t->sigqueue_cache, q, NULL) == q) + return q; + return NULL; +} + +static bool sigqueue_add_cache(struct task_struct *t, struct sigqueue *q) +{ + if (!t->sigqueue_cache && cmpxchg(&t->sigqueue_cache, NULL, q) == NULL) + return true; + return false; +} + /* * allocate a new signal queue record * - this may be called without locks if and only if t == current, otherwise an * appropriate lock must be held to stop the target task from exiting */ static struct sigqueue * -__sigqueue_alloc(int sig, struct task_struct *t, gfp_t flags, int override_rlimit) +__sigqueue_do_alloc(int sig, struct task_struct *t, gfp_t flags, + int override_rlimit, bool fromslab) { struct sigqueue *q = NULL; struct user_struct *user; @@ -432,7 +450,10 @@ __sigqueue_alloc(int sig, struct task_struct *t, gfp_t flags, int override_rlimi rcu_read_unlock(); if (override_rlimit || likely(sigpending <= task_rlimit(t, RLIMIT_SIGPENDING))) { - q = kmem_cache_alloc(sigqueue_cachep, flags); + if (!fromslab) + q = sigqueue_from_cache(t); + if (!q) + q = kmem_cache_alloc(sigqueue_cachep, flags); } else { print_dropped_signal(sig); } @@ -449,6 +470,13 @@ __sigqueue_alloc(int sig, struct task_struct *t, gfp_t flags, int override_rlimi return q; } +static struct sigqueue * +__sigqueue_alloc(int sig, struct task_struct *t, gfp_t flags, + int override_rlimit) +{ + return __sigqueue_do_alloc(sig, t, flags, override_rlimit, false); +} + static void __sigqueue_free(struct sigqueue *q) { if (q->flags & SIGQUEUE_PREALLOC) @@ -458,6 +486,20 @@ static void __sigqueue_free(struct sigqueue *q) kmem_cache_free(sigqueue_cachep, q); } +static void __sigqueue_cache_or_free(struct sigqueue *q) +{ + struct user_struct *up; + + if (q->flags & SIGQUEUE_PREALLOC) + return; + + up = q->user; + if (atomic_dec_and_test(&up->sigpending)) + free_uid(up); + if (!task_is_realtime(current) || !sigqueue_add_cache(current, q)) + kmem_cache_free(sigqueue_cachep, q); +} + void flush_sigqueue(struct sigpending *queue) { struct sigqueue *q; @@ -470,6 +512,21 @@ void flush_sigqueue(struct sigpending *queue) } } +/* + * Called from __exit_signal. Flush tsk->pending and + * tsk->sigqueue_cache + */ +void flush_task_sigqueue(struct task_struct *tsk) +{ + struct sigqueue *q; + + flush_sigqueue(&tsk->pending); + + q = sigqueue_from_cache(tsk); + if (q) + kmem_cache_free(sigqueue_cachep, q); +} + /* * Flush all pending signals for this kthread. */ @@ -594,7 +651,7 @@ static void collect_signal(int sig, struct sigpending *list, kernel_siginfo_t *i (info->si_code == SI_TIMER) && (info->si_sys_private); - __sigqueue_free(first); + __sigqueue_cache_or_free(first); } else { /* * Ok, it wasn't in the queue. This must be @@ -631,6 +688,8 @@ int dequeue_signal(struct task_struct *tsk, sigset_t *mask, kernel_siginfo_t *in bool resched_timer = false; int signr; + WARN_ON_ONCE(tsk != current); + /* We only dequeue private signals from ourselves, we don't let * signalfd steal them */ @@ -1314,6 +1373,34 @@ force_sig_info_to_task(struct kernel_siginfo *info, struct task_struct *t) struct k_sigaction *action; int sig = info->si_signo; + /* + * On some archs, PREEMPT_RT has to delay sending a signal from a trap + * since it can not enable preemption, and the signal code's spin_locks + * turn into mutexes. Instead, it must set TIF_NOTIFY_RESUME which will + * send the signal on exit of the trap. + */ +#ifdef ARCH_RT_DELAYS_SIGNAL_SEND + if (in_atomic()) { + struct task_struct *t = current; + + if (WARN_ON_ONCE(t->forced_info.si_signo)) + return 0; + + if (is_si_special(info)) { + WARN_ON_ONCE(info != SEND_SIG_PRIV); + t->forced_info.si_signo = info->si_signo; + t->forced_info.si_errno = 0; + t->forced_info.si_code = SI_KERNEL; + t->forced_info.si_pid = 0; + t->forced_info.si_uid = 0; + } else { + t->forced_info = *info; + } + + set_tsk_thread_flag(t, TIF_NOTIFY_RESUME); + return 0; + } +#endif spin_lock_irqsave(&t->sighand->siglock, flags); action = &t->sighand->action[sig-1]; ignored = action->sa.sa_handler == SIG_IGN; @@ -1807,7 +1894,7 @@ EXPORT_SYMBOL(kill_pid); */ struct sigqueue *sigqueue_alloc(void) { - struct sigqueue *q = __sigqueue_alloc(-1, current, GFP_KERNEL, 0); + struct sigqueue *q = __sigqueue_do_alloc(-1, current, GFP_KERNEL, 0, true); if (q) q->flags |= SIGQUEUE_PREALLOC; @@ -2203,16 +2290,8 @@ static void ptrace_stop(int exit_code, int why, int clear_code, kernel_siginfo_t if (gstop_done && ptrace_reparented(current)) do_notify_parent_cldstop(current, false, why); - /* - * Don't want to allow preemption here, because - * sys_ptrace() needs this task to be inactive. - * - * XXX: implement read_unlock_no_resched(). - */ - preempt_disable(); read_unlock(&tasklist_lock); cgroup_enter_frozen(); - preempt_enable_no_resched(); freezable_schedule(); cgroup_leave_frozen(true); } else { diff --git a/kernel/smp.c b/kernel/smp.c index aeb0adfa06063..01e9d01d1866e 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -450,8 +450,18 @@ void flush_smp_call_function_from_idle(void) local_irq_save(flags); flush_smp_call_function_queue(true); - if (local_softirq_pending()) - do_softirq(); + + if (local_softirq_pending()) { + + if (!IS_ENABLED(CONFIG_PREEMPT_RT)) { + do_softirq(); + } else { + struct task_struct *ksoftirqd = this_cpu_ksoftirqd(); + + if (ksoftirqd && ksoftirqd->state != TASK_RUNNING) + wake_up_process(ksoftirqd); + } + } local_irq_restore(flags); } diff --git a/kernel/softirq.c b/kernel/softirq.c index 9908ec4a9bfed..e3d9ea8a05f0a 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include #include @@ -25,6 +26,7 @@ #include #include #include +#include #include @@ -102,20 +104,204 @@ EXPORT_PER_CPU_SYMBOL_GPL(hardirq_context); #endif /* - * preempt_count and SOFTIRQ_OFFSET usage: - * - preempt_count is changed by SOFTIRQ_OFFSET on entering or leaving - * softirq processing. - * - preempt_count is changed by SOFTIRQ_DISABLE_OFFSET (= 2 * SOFTIRQ_OFFSET) + * SOFTIRQ_OFFSET usage: + * + * On !RT kernels 'count' is the preempt counter, on RT kernels this applies + * to a per CPU counter and to task::softirqs_disabled_cnt. + * + * - count is changed by SOFTIRQ_OFFSET on entering or leaving softirq + * processing. + * + * - count is changed by SOFTIRQ_DISABLE_OFFSET (= 2 * SOFTIRQ_OFFSET) * on local_bh_disable or local_bh_enable. + * * This lets us distinguish between whether we are currently processing * softirq and whether we just have bh disabled. */ +#ifdef CONFIG_PREEMPT_RT -#ifdef CONFIG_TRACE_IRQFLAGS /* - * This is for softirq.c-internal use, where hardirqs are disabled + * RT accounts for BH disabled sections in task::softirqs_disabled_cnt and + * also in per CPU softirq_ctrl::cnt. This is necessary to allow tasks in a + * softirq disabled section to be preempted. + * + * The per task counter is used for softirq_count(), in_softirq() and + * in_serving_softirqs() because these counts are only valid when the task + * holding softirq_ctrl::lock is running. + * + * The per CPU counter prevents pointless wakeups of ksoftirqd in case that + * the task which is in a softirq disabled section is preempted or blocks. + */ +struct softirq_ctrl { + local_lock_t lock; + int cnt; +}; + +static DEFINE_PER_CPU(struct softirq_ctrl, softirq_ctrl) = { + .lock = INIT_LOCAL_LOCK(softirq_ctrl.lock), +}; + +/** + * local_bh_blocked() - Check for idle whether BH processing is blocked + * + * Returns false if the per CPU softirq::cnt is 0 otherwise true. + * + * This is invoked from the idle task to guard against false positive + * softirq pending warnings, which would happen when the task which holds + * softirq_ctrl::lock was the only running task on the CPU and blocks on + * some other lock. + */ +bool local_bh_blocked(void) +{ + return __this_cpu_read(softirq_ctrl.cnt) != 0; +} + +void __local_bh_disable_ip(unsigned long ip, unsigned int cnt) +{ + unsigned long flags; + int newcnt; + + WARN_ON_ONCE(in_hardirq()); + + /* First entry of a task into a BH disabled section? */ + if (!current->softirq_disable_cnt) { + if (preemptible()) { + local_lock(&softirq_ctrl.lock); + /* Required to meet the RCU bottomhalf requirements. */ + rcu_read_lock(); + } else { + DEBUG_LOCKS_WARN_ON(this_cpu_read(softirq_ctrl.cnt)); + } + } + + /* + * Track the per CPU softirq disabled state. On RT this is per CPU + * state to allow preemption of bottom half disabled sections. + */ + newcnt = __this_cpu_add_return(softirq_ctrl.cnt, cnt); + /* + * Reflect the result in the task state to prevent recursion on the + * local lock and to make softirq_count() & al work. + */ + current->softirq_disable_cnt = newcnt; + + if (IS_ENABLED(CONFIG_TRACE_IRQFLAGS) && newcnt == cnt) { + raw_local_irq_save(flags); + lockdep_softirqs_off(ip); + raw_local_irq_restore(flags); + } +} +EXPORT_SYMBOL(__local_bh_disable_ip); + +static void __local_bh_enable(unsigned int cnt, bool unlock) +{ + unsigned long flags; + int newcnt; + + DEBUG_LOCKS_WARN_ON(current->softirq_disable_cnt != + this_cpu_read(softirq_ctrl.cnt)); + + if (IS_ENABLED(CONFIG_TRACE_IRQFLAGS) && softirq_count() == cnt) { + raw_local_irq_save(flags); + lockdep_softirqs_on(_RET_IP_); + raw_local_irq_restore(flags); + } + + newcnt = __this_cpu_sub_return(softirq_ctrl.cnt, cnt); + current->softirq_disable_cnt = newcnt; + + if (!newcnt && unlock) { + rcu_read_unlock(); + local_unlock(&softirq_ctrl.lock); + } +} + +void __local_bh_enable_ip(unsigned long ip, unsigned int cnt) +{ + bool preempt_on = preemptible(); + unsigned long flags; + u32 pending; + int curcnt; + + WARN_ON_ONCE(in_irq()); + lockdep_assert_irqs_enabled(); + + local_irq_save(flags); + curcnt = __this_cpu_read(softirq_ctrl.cnt); + + /* + * If this is not reenabling soft interrupts, no point in trying to + * run pending ones. + */ + if (curcnt != cnt) + goto out; + + pending = local_softirq_pending(); + if (!pending || ksoftirqd_running(pending)) + goto out; + + /* + * If this was called from non preemptible context, wake up the + * softirq daemon. + */ + if (!preempt_on) { + wakeup_softirqd(); + goto out; + } + + /* + * Adjust softirq count to SOFTIRQ_OFFSET which makes + * in_serving_softirq() become true. + */ + cnt = SOFTIRQ_OFFSET; + __local_bh_enable(cnt, false); + __do_softirq(); + +out: + __local_bh_enable(cnt, preempt_on); + local_irq_restore(flags); +} +EXPORT_SYMBOL(__local_bh_enable_ip); + +/* + * Invoked from ksoftirqd_run() outside of the interrupt disabled section + * to acquire the per CPU local lock for reentrancy protection. + */ +static inline void ksoftirqd_run_begin(void) +{ + __local_bh_disable_ip(_RET_IP_, SOFTIRQ_OFFSET); + local_irq_disable(); +} + +/* Counterpart to ksoftirqd_run_begin() */ +static inline void ksoftirqd_run_end(void) +{ + __local_bh_enable(SOFTIRQ_OFFSET, true); + WARN_ON_ONCE(in_interrupt()); + local_irq_enable(); +} + +static inline void softirq_handle_begin(void) { } +static inline void softirq_handle_end(void) { } + +static inline bool should_wake_ksoftirqd(void) +{ + return !this_cpu_read(softirq_ctrl.cnt); +} + +static inline void invoke_softirq(void) +{ + if (should_wake_ksoftirqd()) + wakeup_softirqd(); +} + +#else /* CONFIG_PREEMPT_RT */ + +/* + * This one is for softirq.c-internal use, where hardirqs are disabled * legitimately: */ +#ifdef CONFIG_TRACE_IRQFLAGS void __local_bh_disable_ip(unsigned long ip, unsigned int cnt) { unsigned long flags; @@ -206,6 +392,32 @@ void __local_bh_enable_ip(unsigned long ip, unsigned int cnt) } EXPORT_SYMBOL(__local_bh_enable_ip); +static inline void softirq_handle_begin(void) +{ + __local_bh_disable_ip(_RET_IP_, SOFTIRQ_OFFSET); +} + +static inline void softirq_handle_end(void) +{ + __local_bh_enable(SOFTIRQ_OFFSET); + WARN_ON_ONCE(in_interrupt()); +} + +static inline void ksoftirqd_run_begin(void) +{ + local_irq_disable(); +} + +static inline void ksoftirqd_run_end(void) +{ + local_irq_enable(); +} + +static inline bool should_wake_ksoftirqd(void) +{ + return true; +} + static inline void invoke_softirq(void) { if (ksoftirqd_running(local_softirq_pending())) @@ -250,6 +462,8 @@ asmlinkage __visible void do_softirq(void) local_irq_restore(flags); } +#endif /* !CONFIG_PREEMPT_RT */ + /* * We restart softirq processing for at most MAX_SOFTIRQ_RESTART times, * but break the loop if need_resched() is set or after 2 ms. @@ -318,7 +532,7 @@ asmlinkage __visible void __softirq_entry __do_softirq(void) pending = local_softirq_pending(); - __local_bh_disable_ip(_RET_IP_, SOFTIRQ_OFFSET); + softirq_handle_begin(); in_hardirq = lockdep_softirq_start(); account_softirq_enter(current); @@ -354,8 +568,10 @@ asmlinkage __visible void __softirq_entry __do_softirq(void) pending >>= softirq_bit; } - if (__this_cpu_read(ksoftirqd) == current) + if (!IS_ENABLED(CONFIG_PREEMPT_RT) && + __this_cpu_read(ksoftirqd) == current) rcu_softirq_qs(); + local_irq_disable(); pending = local_softirq_pending(); @@ -369,8 +585,7 @@ asmlinkage __visible void __softirq_entry __do_softirq(void) account_softirq_exit(current); lockdep_softirq_end(in_hardirq); - __local_bh_enable(SOFTIRQ_OFFSET); - WARN_ON_ONCE(in_interrupt()); + softirq_handle_end(); current_restore_flags(old_flags, PF_MEMALLOC); } @@ -465,7 +680,7 @@ inline void raise_softirq_irqoff(unsigned int nr) * Otherwise we wake up ksoftirqd to make sure we * schedule the softirq soon. */ - if (!in_interrupt()) + if (!in_interrupt() && should_wake_ksoftirqd()) wakeup_softirqd(); } @@ -531,6 +746,16 @@ void __tasklet_hi_schedule(struct tasklet_struct *t) } EXPORT_SYMBOL(__tasklet_hi_schedule); +static inline bool tasklet_clear_sched(struct tasklet_struct *t) +{ + if (test_and_clear_bit(TASKLET_STATE_SCHED, &t->state)) { + wake_up_var(&t->state); + return true; + } + + return false; +} + static void tasklet_action_common(struct softirq_action *a, struct tasklet_head *tl_head, unsigned int softirq_nr) @@ -550,8 +775,7 @@ static void tasklet_action_common(struct softirq_action *a, if (tasklet_trylock(t)) { if (!atomic_read(&t->count)) { - if (!test_and_clear_bit(TASKLET_STATE_SCHED, - &t->state)) + if (!tasklet_clear_sched(t)) BUG(); if (t->use_callback) t->callback(t); @@ -606,21 +830,62 @@ void tasklet_init(struct tasklet_struct *t, } EXPORT_SYMBOL(tasklet_init); +#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT) +/* + * Do not use in new code. There is no real reason to invoke this from + * atomic contexts. + */ +void tasklet_unlock_spin_wait(struct tasklet_struct *t) +{ + while (test_bit(TASKLET_STATE_RUN, &(t)->state)) { + if (IS_ENABLED(CONFIG_PREEMPT_RT)) { + /* + * Prevent a live lock when current preempted soft + * interrupt processing or prevents ksoftirqd from + * running. If the tasklet runs on a different CPU + * then this has no effect other than doing the BH + * disable/enable dance for nothing. + */ + local_bh_disable(); + local_bh_enable(); + } else { + cpu_relax(); + } + } +} +EXPORT_SYMBOL(tasklet_unlock_spin_wait); +#endif + void tasklet_kill(struct tasklet_struct *t) { if (in_interrupt()) pr_notice("Attempt to kill tasklet from interrupt\n"); - while (test_and_set_bit(TASKLET_STATE_SCHED, &t->state)) { - do { - yield(); - } while (test_bit(TASKLET_STATE_SCHED, &t->state)); - } + while (test_and_set_bit(TASKLET_STATE_SCHED, &t->state)) + wait_var_event(&t->state, !test_bit(TASKLET_STATE_SCHED, &t->state)); + tasklet_unlock_wait(t); - clear_bit(TASKLET_STATE_SCHED, &t->state); + tasklet_clear_sched(t); } EXPORT_SYMBOL(tasklet_kill); +#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT) +void tasklet_unlock(struct tasklet_struct *t) +{ + smp_mb__before_atomic(); + clear_bit(TASKLET_STATE_RUN, &t->state); + smp_mb__after_atomic(); + wake_up_var(&t->state); +} +EXPORT_SYMBOL_GPL(tasklet_unlock); + +void tasklet_unlock_wait(struct tasklet_struct *t) +{ + wait_var_event(&t->state, !test_bit(TASKLET_STATE_RUN, &t->state)); +} +EXPORT_SYMBOL_GPL(tasklet_unlock_wait); +#endif + void __init softirq_init(void) { int cpu; @@ -643,18 +908,18 @@ static int ksoftirqd_should_run(unsigned int cpu) static void run_ksoftirqd(unsigned int cpu) { - local_irq_disable(); + ksoftirqd_run_begin(); if (local_softirq_pending()) { /* * We can safely run softirq on inline stack, as we are not deep * in the task stack here. */ __do_softirq(); - local_irq_enable(); + ksoftirqd_run_end(); cond_resched(); return; } - local_irq_enable(); + ksoftirqd_run_end(); } #ifdef CONFIG_HOTPLUG_CPU diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index 788b9d137de4c..3fa18a01f5b2e 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -2006,6 +2006,36 @@ SYSCALL_DEFINE2(nanosleep_time32, struct old_timespec32 __user *, rqtp, } #endif +#ifdef CONFIG_PREEMPT_RT +/* + * Sleep for 1 ms in hope whoever holds what we want will let it go. + */ +void cpu_chill(void) +{ + unsigned int freeze_flag = current->flags & PF_NOFREEZE; + struct task_struct *self = current; + ktime_t chill_time; + + raw_spin_lock_irq(&self->pi_lock); + self->saved_state = self->state; + __set_current_state_no_track(TASK_UNINTERRUPTIBLE); + raw_spin_unlock_irq(&self->pi_lock); + + chill_time = ktime_set(0, NSEC_PER_MSEC); + + current->flags |= PF_NOFREEZE; + schedule_hrtimeout(&chill_time, HRTIMER_MODE_REL_HARD); + if (!freeze_flag) + current->flags &= ~PF_NOFREEZE; + + raw_spin_lock_irq(&self->pi_lock); + __set_current_state_no_track(self->saved_state); + self->saved_state = TASK_RUNNING; + raw_spin_unlock_irq(&self->pi_lock); +} +EXPORT_SYMBOL(cpu_chill); +#endif + /* * Functions related to boot-time initialization: */ diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index e10a4af887373..0cc55791b2b61 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -973,7 +973,7 @@ static bool can_stop_idle_tick(int cpu, struct tick_sched *ts) if (unlikely(local_softirq_pending())) { static int ratelimit; - if (ratelimit < 10 && + if (ratelimit < 10 && !local_bh_blocked() && (local_softirq_pending() & SOFTIRQ_STOP_IDLE_MASK)) { pr_warn("NOHZ tick-stop error: Non-RCU local softirq work is pending, handler #%02x!!!\n", (unsigned int) local_softirq_pending()); diff --git a/kernel/time/timer.c b/kernel/time/timer.c index f475f1a027c8b..4f7602724f9af 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -1277,8 +1277,10 @@ static inline void timer_base_unlock_expiry(struct timer_base *base) static void timer_sync_wait_running(struct timer_base *base) { if (atomic_read(&base->timer_waiters)) { + raw_spin_unlock_irq(&base->lock); spin_unlock(&base->expiry_lock); spin_lock(&base->expiry_lock); + raw_spin_lock_irq(&base->lock); } } @@ -1469,14 +1471,14 @@ static void expire_timers(struct timer_base *base, struct hlist_head *head) if (timer->flags & TIMER_IRQSAFE) { raw_spin_unlock(&base->lock); call_timer_fn(timer, fn, baseclk); - base->running_timer = NULL; raw_spin_lock(&base->lock); + base->running_timer = NULL; } else { raw_spin_unlock_irq(&base->lock); call_timer_fn(timer, fn, baseclk); + raw_spin_lock_irq(&base->lock); base->running_timer = NULL; timer_sync_wait_running(base); - raw_spin_lock_irq(&base->lock); } } } @@ -1755,6 +1757,8 @@ static __latent_entropy void run_timer_softirq(struct softirq_action *h) { struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]); + irq_work_tick_soft(); + __run_timers(base); if (IS_ENABLED(CONFIG_NO_HZ_COMMON)) __run_timers(this_cpu_ptr(&timer_bases[BASE_DEF])); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index eccb4e1187cc7..9836ab9d22bb9 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -2587,6 +2587,15 @@ enum print_line_t trace_handle_return(struct trace_seq *s) } EXPORT_SYMBOL_GPL(trace_handle_return); +static unsigned short migration_disable_value(void) +{ +#if defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT) + return current->migration_disabled; +#else + return 0; +#endif +} + unsigned int tracing_gen_ctx_irq_test(unsigned int irqs_status) { unsigned int trace_flags = irqs_status; @@ -2605,7 +2614,16 @@ 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; - return (trace_flags << 16) | (pc & 0xff); + +#ifdef CONFIG_PREEMPT_LAZY + if (need_resched_lazy()) + trace_flags |= TRACE_FLAG_NEED_RESCHED_LAZY; +#endif + + return (pc & 0xff) | + (migration_disable_value() & 0xff) << 8 | + (preempt_lazy_count() & 0xff) << 16 | + (trace_flags << 24); } struct ring_buffer_event * @@ -3865,14 +3883,17 @@ unsigned long trace_total_entries(struct trace_array *tr) static void print_lat_help_header(struct seq_file *m) { - seq_puts(m, "# _------=> CPU# \n" - "# / _-----=> irqs-off \n" - "# | / _----=> need-resched \n" - "# || / _---=> hardirq/softirq \n" - "# ||| / _--=> preempt-depth \n" - "# |||| / delay \n" - "# cmd pid ||||| time | caller \n" - "# \\ / ||||| \\ | / \n"); + seq_puts(m, "# _--------=> CPU# \n" + "# / _-------=> irqs-off \n" + "# | / _------=> need-resched \n" + "# || / _-----=> need-resched-lazy\n" + "# ||| / _----=> hardirq/softirq \n" + "# |||| / _---=> preempt-depth \n" + "# ||||| / _--=> preempt-lazy-depth\n" + "# |||||| / _-=> migrate-disable \n" + "# ||||||| / delay \n" + "# cmd pid |||||||| time | caller \n" + "# \\ / |||||||| \\ | / \n"); } static void print_event_info(struct array_buffer *buf, struct seq_file *m) @@ -3906,13 +3927,16 @@ static void print_func_help_header_irq(struct array_buffer *buf, struct seq_file print_event_info(buf, m); - seq_printf(m, "# %.*s _-----=> irqs-off\n", prec, space); - seq_printf(m, "# %.*s / _----=> need-resched\n", prec, space); - seq_printf(m, "# %.*s| / _---=> hardirq/softirq\n", prec, space); - seq_printf(m, "# %.*s|| / _--=> preempt-depth\n", prec, space); - seq_printf(m, "# %.*s||| / delay\n", prec, space); - seq_printf(m, "# TASK-PID %.*s CPU# |||| TIMESTAMP FUNCTION\n", prec, " TGID "); - seq_printf(m, "# | | %.*s | |||| | |\n", prec, " | "); + seq_printf(m, "# %.*s _-------=> irqs-off\n", prec, space); + seq_printf(m, "# %.*s / _------=> need-resched\n", prec, space); + seq_printf(m, "# %.*s| / _-----=> need-resched-lazy\n", prec, space); + seq_printf(m, "# %.*s|| / _----=> hardirq/softirq\n", prec, space); + seq_printf(m, "# %.*s||| / _---=> preempt-depth\n", prec, space); + seq_printf(m, "# %.*s|||| / _--=> preempt-lazy-depth\n", prec, space); + seq_printf(m, "# %.*s||||| / _-=> migrate-disable\n", prec, space); + seq_printf(m, "# %.*s|||||| / delay\n", prec, space); + seq_printf(m, "# TASK-PID %.*s CPU# ||||||| TIMESTAMP FUNCTION\n", prec, " TGID "); + seq_printf(m, "# | | %.*s | ||||||| | |\n", prec, " | "); } void @@ -9404,7 +9428,6 @@ void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) tracing_off(); local_irq_save(flags); - printk_nmi_direct_enter(); /* Simulate the iterator */ trace_init_global_iter(&iter); @@ -9486,7 +9509,6 @@ void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) atomic_dec(&per_cpu_ptr(iter.array_buffer->data, cpu)->disabled); } atomic_dec(&dump_running); - printk_nmi_direct_exit(); local_irq_restore(flags); } EXPORT_SYMBOL_GPL(ftrace_dump); diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index a3563afd412dc..39fa2a7a8b03e 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -183,6 +183,8 @@ static int trace_define_common_fields(void) __common_field(unsigned char, flags); __common_field(unsigned char, preempt_count); __common_field(int, pid); + __common_field(unsigned char, migrate_disable); + __common_field(unsigned char, preempt_lazy_count); return ret; } diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index 61255bad7e01f..af85aec1e8871 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -451,6 +451,7 @@ int trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry) { char hardsoft_irq; char need_resched; + char need_resched_lazy; char irqs_off; int hardirq; int softirq; @@ -481,6 +482,9 @@ int trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry) break; } + need_resched_lazy = + (entry->flags & TRACE_FLAG_NEED_RESCHED_LAZY) ? 'L' : '.'; + hardsoft_irq = (nmi && hardirq) ? 'Z' : nmi ? 'z' : @@ -489,14 +493,25 @@ int trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry) softirq ? 's' : '.' ; - trace_seq_printf(s, "%c%c%c", - irqs_off, need_resched, hardsoft_irq); + trace_seq_printf(s, "%c%c%c%c", + irqs_off, need_resched, need_resched_lazy, + hardsoft_irq); if (entry->preempt_count) trace_seq_printf(s, "%x", entry->preempt_count); else trace_seq_putc(s, '.'); + if (entry->preempt_lazy_count) + trace_seq_printf(s, "%x", entry->preempt_lazy_count); + else + trace_seq_putc(s, '.'); + + if (entry->migrate_disable) + trace_seq_printf(s, "%x", entry->migrate_disable); + else + trace_seq_putc(s, '.'); + return !trace_seq_has_overflowed(s); } diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 2779c29d9981f..74a0a9e54fdb4 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1392,7 +1392,7 @@ config DEBUG_ATOMIC_SLEEP config DEBUG_LOCKING_API_SELFTESTS bool "Locking API boot-time self-tests" - depends on DEBUG_KERNEL + depends on DEBUG_KERNEL && !PREEMPT_RT help Say Y here if you want the kernel to run a short self-test during bootup. The self-test checks whether common types of locking bugs diff --git a/lib/bug.c b/lib/bug.c index 8f9d537bfb2a5..8696908372d24 100644 --- a/lib/bug.c +++ b/lib/bug.c @@ -202,6 +202,7 @@ enum bug_trap_type report_bug(unsigned long bugaddr, struct pt_regs *regs) else pr_crit("Kernel BUG at %pB [verbose debug info unavailable]\n", (void *)bugaddr); + pr_flush(1000, true); return BUG_TRAP_TYPE_BUG; } diff --git a/lib/debugobjects.c b/lib/debugobjects.c index 9e14ae02306bc..083882a3cf2f4 100644 --- a/lib/debugobjects.c +++ b/lib/debugobjects.c @@ -557,7 +557,10 @@ __debug_object_init(void *addr, const struct debug_obj_descr *descr, int onstack struct debug_obj *obj; unsigned long flags; - fill_pool(); +#ifdef CONFIG_PREEMPT_RT + if (preempt_count() == 0 && !irqs_disabled()) +#endif + fill_pool(); db = get_bucket((unsigned long) addr); diff --git a/lib/irq_poll.c b/lib/irq_poll.c index 2f17b488d58e1..7557bf7ecf1f1 100644 --- a/lib/irq_poll.c +++ b/lib/irq_poll.c @@ -37,6 +37,7 @@ void irq_poll_sched(struct irq_poll *iop) list_add_tail(&iop->list, this_cpu_ptr(&blk_cpu_iopoll)); raise_softirq_irqoff(IRQ_POLL_SOFTIRQ); local_irq_restore(flags); + preempt_check_resched_rt(); } EXPORT_SYMBOL(irq_poll_sched); @@ -72,6 +73,7 @@ void irq_poll_complete(struct irq_poll *iop) local_irq_save(flags); __irq_poll_complete(iop); local_irq_restore(flags); + preempt_check_resched_rt(); } EXPORT_SYMBOL(irq_poll_complete); @@ -96,6 +98,7 @@ static void __latent_entropy irq_poll_softirq(struct softirq_action *h) } local_irq_enable(); + preempt_check_resched_rt(); /* Even though interrupts have been re-enabled, this * access is safe because interrupts can only add new @@ -133,6 +136,7 @@ static void __latent_entropy irq_poll_softirq(struct softirq_action *h) __raise_softirq_irqoff(IRQ_POLL_SOFTIRQ); local_irq_enable(); + preempt_check_resched_rt(); } /** @@ -196,6 +200,7 @@ static int irq_poll_cpu_dead(unsigned int cpu) this_cpu_ptr(&blk_cpu_iopoll)); __raise_softirq_irqoff(IRQ_POLL_SOFTIRQ); local_irq_enable(); + preempt_check_resched_rt(); return 0; } diff --git a/lib/locking-selftest.c b/lib/locking-selftest.c index 2d85abac17448..3d2d99d8ed13e 100644 --- a/lib/locking-selftest.c +++ b/lib/locking-selftest.c @@ -794,6 +794,8 @@ GENERATE_TESTCASE(init_held_rtmutex); #include "locking-selftest-spin-hardirq.h" GENERATE_PERMUTATIONS_2_EVENTS(irqsafe1_hard_spin) +#ifndef CONFIG_PREEMPT_RT + #include "locking-selftest-rlock-hardirq.h" GENERATE_PERMUTATIONS_2_EVENTS(irqsafe1_hard_rlock) @@ -809,9 +811,12 @@ GENERATE_PERMUTATIONS_2_EVENTS(irqsafe1_soft_rlock) #include "locking-selftest-wlock-softirq.h" GENERATE_PERMUTATIONS_2_EVENTS(irqsafe1_soft_wlock) +#endif + #undef E1 #undef E2 +#ifndef CONFIG_PREEMPT_RT /* * Enabling hardirqs with a softirq-safe lock held: */ @@ -844,6 +849,8 @@ GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2A_rlock) #undef E1 #undef E2 +#endif + /* * Enabling irqs with an irq-safe lock held: */ @@ -867,6 +874,8 @@ GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2A_rlock) #include "locking-selftest-spin-hardirq.h" GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2B_hard_spin) +#ifndef CONFIG_PREEMPT_RT + #include "locking-selftest-rlock-hardirq.h" GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2B_hard_rlock) @@ -882,6 +891,8 @@ GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2B_soft_rlock) #include "locking-selftest-wlock-softirq.h" GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2B_soft_wlock) +#endif + #undef E1 #undef E2 @@ -913,6 +924,8 @@ GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2B_soft_wlock) #include "locking-selftest-spin-hardirq.h" GENERATE_PERMUTATIONS_3_EVENTS(irqsafe3_hard_spin) +#ifndef CONFIG_PREEMPT_RT + #include "locking-selftest-rlock-hardirq.h" GENERATE_PERMUTATIONS_3_EVENTS(irqsafe3_hard_rlock) @@ -928,6 +941,8 @@ GENERATE_PERMUTATIONS_3_EVENTS(irqsafe3_soft_rlock) #include "locking-selftest-wlock-softirq.h" GENERATE_PERMUTATIONS_3_EVENTS(irqsafe3_soft_wlock) +#endif + #undef E1 #undef E2 #undef E3 @@ -961,6 +976,8 @@ GENERATE_PERMUTATIONS_3_EVENTS(irqsafe3_soft_wlock) #include "locking-selftest-spin-hardirq.h" GENERATE_PERMUTATIONS_3_EVENTS(irqsafe4_hard_spin) +#ifndef CONFIG_PREEMPT_RT + #include "locking-selftest-rlock-hardirq.h" GENERATE_PERMUTATIONS_3_EVENTS(irqsafe4_hard_rlock) @@ -976,10 +993,14 @@ GENERATE_PERMUTATIONS_3_EVENTS(irqsafe4_soft_rlock) #include "locking-selftest-wlock-softirq.h" GENERATE_PERMUTATIONS_3_EVENTS(irqsafe4_soft_wlock) +#endif + #undef E1 #undef E2 #undef E3 +#ifndef CONFIG_PREEMPT_RT + /* * read-lock / write-lock irq inversion. * @@ -1169,6 +1190,11 @@ GENERATE_PERMUTATIONS_3_EVENTS(W1W2_R2R3_R3W1) #undef E1 #undef E2 #undef E3 + +#endif + +#ifndef CONFIG_PREEMPT_RT + /* * read-lock / write-lock recursion that is actually safe. */ @@ -1215,6 +1241,8 @@ GENERATE_PERMUTATIONS_3_EVENTS(irq_read_recursion_soft_wlock) #undef E2 #undef E3 +#endif + /* * read-lock / write-lock recursion that is unsafe. */ @@ -2841,6 +2869,7 @@ void locking_selftest(void) printk(" --------------------------------------------------------------------------\n"); +#ifndef CONFIG_PREEMPT_RT /* * irq-context testcases: */ @@ -2855,6 +2884,28 @@ void locking_selftest(void) DO_TESTCASE_6x2x2RW("irq read-recursion #2", irq_read_recursion2); DO_TESTCASE_6x2x2RW("irq read-recursion #3", irq_read_recursion3); +#else + /* On -rt, we only do hardirq context test for raw spinlock */ + DO_TESTCASE_1B("hard-irqs-on + irq-safe-A", irqsafe1_hard_spin, 12); + DO_TESTCASE_1B("hard-irqs-on + irq-safe-A", irqsafe1_hard_spin, 21); + + DO_TESTCASE_1B("hard-safe-A + irqs-on", irqsafe2B_hard_spin, 12); + DO_TESTCASE_1B("hard-safe-A + irqs-on", irqsafe2B_hard_spin, 21); + + DO_TESTCASE_1B("hard-safe-A + unsafe-B #1", irqsafe3_hard_spin, 123); + DO_TESTCASE_1B("hard-safe-A + unsafe-B #1", irqsafe3_hard_spin, 132); + DO_TESTCASE_1B("hard-safe-A + unsafe-B #1", irqsafe3_hard_spin, 213); + DO_TESTCASE_1B("hard-safe-A + unsafe-B #1", irqsafe3_hard_spin, 231); + DO_TESTCASE_1B("hard-safe-A + unsafe-B #1", irqsafe3_hard_spin, 312); + DO_TESTCASE_1B("hard-safe-A + unsafe-B #1", irqsafe3_hard_spin, 321); + + DO_TESTCASE_1B("hard-safe-A + unsafe-B #2", irqsafe4_hard_spin, 123); + DO_TESTCASE_1B("hard-safe-A + unsafe-B #2", irqsafe4_hard_spin, 132); + DO_TESTCASE_1B("hard-safe-A + unsafe-B #2", irqsafe4_hard_spin, 213); + DO_TESTCASE_1B("hard-safe-A + unsafe-B #2", irqsafe4_hard_spin, 231); + DO_TESTCASE_1B("hard-safe-A + unsafe-B #2", irqsafe4_hard_spin, 312); + DO_TESTCASE_1B("hard-safe-A + unsafe-B #2", irqsafe4_hard_spin, 321); +#endif ww_tests(); force_read_lock_recursive = 0; diff --git a/lib/nmi_backtrace.c b/lib/nmi_backtrace.c index 8abe1870dba4e..b09a490f5f706 100644 --- a/lib/nmi_backtrace.c +++ b/lib/nmi_backtrace.c @@ -75,12 +75,6 @@ void nmi_trigger_cpumask_backtrace(const cpumask_t *mask, touch_softlockup_watchdog(); } - /* - * Force flush any remote buffers that might be stuck in IRQ context - * and therefore could not run their irq_work. - */ - printk_safe_flush(); - clear_bit_unlock(0, &backtrace_flag); put_cpu(); } diff --git a/lib/scatterlist.c b/lib/scatterlist.c index a597789464043..907f590459983 100644 --- a/lib/scatterlist.c +++ b/lib/scatterlist.c @@ -892,7 +892,7 @@ void sg_miter_stop(struct sg_mapping_iter *miter) flush_kernel_dcache_page(miter->page); if (miter->__flags & SG_MITER_ATOMIC) { - WARN_ON_ONCE(preemptible()); + WARN_ON_ONCE(!pagefault_disabled()); kunmap_atomic(miter->addr); } else kunmap(miter->page); diff --git a/localversion-rt b/localversion-rt new file mode 100644 index 0000000000000..1445cd65885cd --- /dev/null +++ b/localversion-rt @@ -0,0 +1 @@ +-rt3 diff --git a/mm/Kconfig b/mm/Kconfig index 24c045b24b950..ec06984ec4acc 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -387,7 +387,7 @@ config NOMMU_INITIAL_TRIM_EXCESS config TRANSPARENT_HUGEPAGE bool "Transparent Hugepage Support" - depends on HAVE_ARCH_TRANSPARENT_HUGEPAGE + depends on HAVE_ARCH_TRANSPARENT_HUGEPAGE && !PREEMPT_RT select COMPACTION select XARRAY_MULTI help diff --git a/mm/memcontrol.c b/mm/memcontrol.c index e064ac0d850ac..ae52cebfecfcd 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -66,6 +66,7 @@ #include #include #include "slab.h" +#include #include @@ -96,6 +97,13 @@ bool cgroup_memory_noswap __read_mostly; static DECLARE_WAIT_QUEUE_HEAD(memcg_cgwb_frn_waitq); #endif +struct event_lock { + local_lock_t l; +}; +static DEFINE_PER_CPU(struct event_lock, event_lock) = { + .l = INIT_LOCAL_LOCK(l), +}; + /* Whether legacy memory+swap accounting is active */ static bool do_memsw_account(void) { @@ -809,6 +817,7 @@ void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec); memcg = pn->memcg; + preempt_disable_rt(); /* Update memcg */ __mod_memcg_state(memcg, idx, val); @@ -828,6 +837,7 @@ void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, x = 0; } __this_cpu_write(pn->lruvec_stat_cpu->count[idx], x); + preempt_enable_rt(); } /** @@ -2208,6 +2218,7 @@ void unlock_page_memcg(struct page *page) EXPORT_SYMBOL(unlock_page_memcg); struct memcg_stock_pcp { + local_lock_t lock; struct mem_cgroup *cached; /* this never be root cgroup */ unsigned int nr_pages; @@ -2259,7 +2270,7 @@ static bool consume_stock(struct mem_cgroup *memcg, unsigned int nr_pages) if (nr_pages > MEMCG_CHARGE_BATCH) return ret; - local_irq_save(flags); + local_lock_irqsave(&memcg_stock.lock, flags); stock = this_cpu_ptr(&memcg_stock); if (memcg == stock->cached && stock->nr_pages >= nr_pages) { @@ -2267,7 +2278,7 @@ static bool consume_stock(struct mem_cgroup *memcg, unsigned int nr_pages) ret = true; } - local_irq_restore(flags); + local_unlock_irqrestore(&memcg_stock.lock, flags); return ret; } @@ -2302,14 +2313,14 @@ static void drain_local_stock(struct work_struct *dummy) * The only protection from memory hotplug vs. drain_stock races is * that we always operate on local CPU stock here with IRQ disabled */ - local_irq_save(flags); + local_lock_irqsave(&memcg_stock.lock, flags); stock = this_cpu_ptr(&memcg_stock); drain_obj_stock(stock); drain_stock(stock); clear_bit(FLUSHING_CACHED_CHARGE, &stock->flags); - local_irq_restore(flags); + local_unlock_irqrestore(&memcg_stock.lock, flags); } /* @@ -2321,7 +2332,7 @@ static void refill_stock(struct mem_cgroup *memcg, unsigned int nr_pages) struct memcg_stock_pcp *stock; unsigned long flags; - local_irq_save(flags); + local_lock_irqsave(&memcg_stock.lock, flags); stock = this_cpu_ptr(&memcg_stock); if (stock->cached != memcg) { /* reset if necessary */ @@ -2334,7 +2345,7 @@ static void refill_stock(struct mem_cgroup *memcg, unsigned int nr_pages) if (stock->nr_pages > MEMCG_CHARGE_BATCH) drain_stock(stock); - local_irq_restore(flags); + local_unlock_irqrestore(&memcg_stock.lock, flags); } /* @@ -2354,7 +2365,7 @@ static void drain_all_stock(struct mem_cgroup *root_memcg) * as well as workers from this path always operate on the local * per-cpu data. CPU up doesn't touch memcg_stock at all. */ - curcpu = get_cpu(); + curcpu = get_cpu_light(); for_each_online_cpu(cpu) { struct memcg_stock_pcp *stock = &per_cpu(memcg_stock, cpu); struct mem_cgroup *memcg; @@ -2377,7 +2388,7 @@ static void drain_all_stock(struct mem_cgroup *root_memcg) schedule_work_on(cpu, &stock->work); } } - put_cpu(); + put_cpu_light(); mutex_unlock(&percpu_charge_mutex); } @@ -3156,7 +3167,7 @@ static bool consume_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes) unsigned long flags; bool ret = false; - local_irq_save(flags); + local_lock_irqsave(&memcg_stock.lock, flags); stock = this_cpu_ptr(&memcg_stock); if (objcg == stock->cached_objcg && stock->nr_bytes >= nr_bytes) { @@ -3164,7 +3175,7 @@ static bool consume_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes) ret = true; } - local_irq_restore(flags); + local_unlock_irqrestore(&memcg_stock.lock, flags); return ret; } @@ -3223,7 +3234,7 @@ static void refill_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes) struct memcg_stock_pcp *stock; unsigned long flags; - local_irq_save(flags); + local_lock_irqsave(&memcg_stock.lock, flags); stock = this_cpu_ptr(&memcg_stock); if (stock->cached_objcg != objcg) { /* reset if necessary */ @@ -3237,7 +3248,7 @@ static void refill_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes) if (stock->nr_bytes > PAGE_SIZE) drain_obj_stock(stock); - local_irq_restore(flags); + local_unlock_irqrestore(&memcg_stock.lock, flags); } int obj_cgroup_charge(struct obj_cgroup *objcg, gfp_t gfp, size_t size) @@ -5674,12 +5685,12 @@ static int mem_cgroup_move_account(struct page *page, ret = 0; - local_irq_disable(); + local_lock_irq(&event_lock.l); mem_cgroup_charge_statistics(to, page, nr_pages); memcg_check_events(to, page); mem_cgroup_charge_statistics(from, page, -nr_pages); memcg_check_events(from, page); - local_irq_enable(); + local_unlock_irq(&event_lock.l); out_unlock: unlock_page(page); out: @@ -6736,10 +6747,10 @@ int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask) css_get(&memcg->css); commit_charge(page, memcg); - local_irq_disable(); + local_lock_irq(&event_lock.l); mem_cgroup_charge_statistics(memcg, page, nr_pages); memcg_check_events(memcg, page); - local_irq_enable(); + local_unlock_irq(&event_lock.l); /* * Cgroup1's unified memory+swap counter has been charged with the @@ -6795,11 +6806,11 @@ static void uncharge_batch(const struct uncharge_gather *ug) memcg_oom_recover(ug->memcg); } - local_irq_save(flags); + local_lock_irqsave(&event_lock.l, flags); __count_memcg_events(ug->memcg, PGPGOUT, ug->pgpgout); __this_cpu_add(ug->memcg->vmstats_percpu->nr_page_events, ug->nr_pages); memcg_check_events(ug->memcg, ug->dummy_page); - local_irq_restore(flags); + local_unlock_irqrestore(&event_lock.l, flags); /* drop reference from uncharge_page */ css_put(&ug->memcg->css); @@ -6932,10 +6943,10 @@ void mem_cgroup_migrate(struct page *oldpage, struct page *newpage) css_get(&memcg->css); commit_charge(newpage, memcg); - local_irq_save(flags); + local_lock_irqsave(&event_lock.l, flags); mem_cgroup_charge_statistics(memcg, newpage, nr_pages); memcg_check_events(memcg, newpage); - local_irq_restore(flags); + local_unlock_irqrestore(&event_lock.l, flags); } DEFINE_STATIC_KEY_FALSE(memcg_sockets_enabled_key); @@ -7063,9 +7074,13 @@ static int __init mem_cgroup_init(void) cpuhp_setup_state_nocalls(CPUHP_MM_MEMCQ_DEAD, "mm/memctrl:dead", NULL, memcg_hotplug_cpu_dead); - for_each_possible_cpu(cpu) - INIT_WORK(&per_cpu_ptr(&memcg_stock, cpu)->work, - drain_local_stock); + for_each_possible_cpu(cpu) { + struct memcg_stock_pcp *stock; + + stock = per_cpu_ptr(&memcg_stock, cpu); + INIT_WORK(&stock->work, drain_local_stock); + local_lock_init(&stock->lock); + } for_each_node(node) { struct mem_cgroup_tree_per_node *rtpn; @@ -7114,6 +7129,7 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry) struct mem_cgroup *memcg, *swap_memcg; unsigned int nr_entries; unsigned short oldid; + unsigned long flags; VM_BUG_ON_PAGE(PageLRU(page), page); VM_BUG_ON_PAGE(page_count(page), page); @@ -7162,9 +7178,13 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry) * important here to have the interrupts disabled because it is the * only synchronisation we have for updating the per-CPU variables. */ + local_lock_irqsave(&event_lock.l, flags); +#ifndef CONFIG_PREEMPT_RT VM_BUG_ON(!irqs_disabled()); +#endif mem_cgroup_charge_statistics(memcg, page, -nr_entries); memcg_check_events(memcg, page); + local_unlock_irqrestore(&event_lock.l, flags); css_put(&memcg->css); } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index cfc72873961d9..72993fb19c990 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -62,6 +62,7 @@ #include #include #include +#include #include #include #include @@ -363,6 +364,13 @@ EXPORT_SYMBOL(nr_online_nodes); int page_group_by_mobility_disabled __read_mostly; +struct pa_lock { + local_lock_t l; +}; +static DEFINE_PER_CPU(struct pa_lock, pa_lock) = { + .l = INIT_LOCAL_LOCK(l), +}; + #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT /* * During boot we initialize deferred pages on-demand, as needed, but once @@ -1541,11 +1549,11 @@ static void __free_pages_ok(struct page *page, unsigned int order, return; migratetype = get_pfnblock_migratetype(page, pfn); - local_irq_save(flags); + local_lock_irqsave(&pa_lock.l, flags); __count_vm_events(PGFREE, 1 << order); free_one_page(page_zone(page), page, pfn, order, migratetype, fpi_flags); - local_irq_restore(flags); + local_unlock_irqrestore(&pa_lock.l, flags); } void __free_pages_core(struct page *page, unsigned int order) @@ -2962,12 +2970,12 @@ void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp) unsigned long flags; int to_drain, batch; - local_irq_save(flags); + local_lock_irqsave(&pa_lock.l, flags); batch = READ_ONCE(pcp->batch); to_drain = min(pcp->count, batch); if (to_drain > 0) free_pcppages_bulk(zone, to_drain, pcp); - local_irq_restore(flags); + local_unlock_irqrestore(&pa_lock.l, flags); } #endif @@ -2984,13 +2992,13 @@ static void drain_pages_zone(unsigned int cpu, struct zone *zone) struct per_cpu_pageset *pset; struct per_cpu_pages *pcp; - local_irq_save(flags); + local_lock_irqsave(&pa_lock.l, flags); pset = per_cpu_ptr(zone->pageset, cpu); pcp = &pset->pcp; if (pcp->count) free_pcppages_bulk(zone, pcp->count, pcp); - local_irq_restore(flags); + local_unlock_irqrestore(&pa_lock.l, flags); } /* @@ -3038,9 +3046,9 @@ static void drain_local_pages_wq(struct work_struct *work) * cpu which is allright but we also have to make sure to not move to * a different one. */ - preempt_disable(); + migrate_disable(); drain_local_pages(drain->zone); - preempt_enable(); + migrate_enable(); } /* @@ -3253,9 +3261,9 @@ void free_unref_page(struct page *page) if (!free_unref_page_prepare(page, pfn)) return; - local_irq_save(flags); + local_lock_irqsave(&pa_lock.l, flags); free_unref_page_commit(page, pfn); - local_irq_restore(flags); + local_unlock_irqrestore(&pa_lock.l, flags); } /* @@ -3275,7 +3283,7 @@ void free_unref_page_list(struct list_head *list) set_page_private(page, pfn); } - local_irq_save(flags); + local_lock_irqsave(&pa_lock.l, flags); list_for_each_entry_safe(page, next, list, lru) { unsigned long pfn = page_private(page); @@ -3288,12 +3296,12 @@ void free_unref_page_list(struct list_head *list) * a large list of pages to free. */ if (++batch_count == SWAP_CLUSTER_MAX) { - local_irq_restore(flags); + local_unlock_irqrestore(&pa_lock.l, flags); batch_count = 0; - local_irq_save(flags); + local_lock_irqsave(&pa_lock.l, flags); } } - local_irq_restore(flags); + local_unlock_irqrestore(&pa_lock.l, flags); } /* @@ -3449,7 +3457,7 @@ static struct page *rmqueue_pcplist(struct zone *preferred_zone, struct page *page; unsigned long flags; - local_irq_save(flags); + local_lock_irqsave(&pa_lock.l, flags); pcp = &this_cpu_ptr(zone->pageset)->pcp; list = &pcp->lists[migratetype]; page = __rmqueue_pcplist(zone, migratetype, alloc_flags, pcp, list); @@ -3457,7 +3465,7 @@ static struct page *rmqueue_pcplist(struct zone *preferred_zone, __count_zid_vm_events(PGALLOC, page_zonenum(page), 1); zone_statistics(preferred_zone, zone); } - local_irq_restore(flags); + local_unlock_irqrestore(&pa_lock.l, flags); return page; } @@ -3491,7 +3499,9 @@ struct page *rmqueue(struct zone *preferred_zone, * allocate greater than order-1 page units with __GFP_NOFAIL. */ WARN_ON_ONCE((gfp_flags & __GFP_NOFAIL) && (order > 1)); - spin_lock_irqsave(&zone->lock, flags); + + local_lock_irqsave(&pa_lock.l, flags); + spin_lock(&zone->lock); do { page = NULL; @@ -3512,12 +3522,13 @@ struct page *rmqueue(struct zone *preferred_zone, spin_unlock(&zone->lock); if (!page) goto failed; + __mod_zone_freepage_state(zone, -(1 << order), get_pcppage_migratetype(page)); __count_zid_vm_events(PGALLOC, page_zonenum(page), 1 << order); zone_statistics(preferred_zone, zone); - local_irq_restore(flags); + local_unlock_irqrestore(&pa_lock.l, flags); out: /* Separate test+clear to avoid unnecessary atomics */ @@ -3530,7 +3541,7 @@ struct page *rmqueue(struct zone *preferred_zone, return page; failed: - local_irq_restore(flags); + local_unlock_irqrestore(&pa_lock.l, flags); return NULL; } @@ -8810,7 +8821,7 @@ void zone_pcp_reset(struct zone *zone) struct per_cpu_pageset *pset; /* avoid races with drain_pages() */ - local_irq_save(flags); + local_lock_irqsave(&pa_lock.l, flags); if (zone->pageset != &boot_pageset) { for_each_online_cpu(cpu) { pset = per_cpu_ptr(zone->pageset, cpu); @@ -8819,7 +8830,7 @@ void zone_pcp_reset(struct zone *zone) free_percpu(zone->pageset); zone->pageset = &boot_pageset; } - local_irq_restore(flags); + local_unlock_irqrestore(&pa_lock.l, flags); } #ifdef CONFIG_MEMORY_HOTREMOVE diff --git a/mm/shmem.c b/mm/shmem.c index b2db4ed0fbc7c..b85dafef65295 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -278,10 +278,10 @@ static int shmem_reserve_inode(struct super_block *sb, ino_t *inop) ino_t ino; if (!(sb->s_flags & SB_KERNMOUNT)) { - spin_lock(&sbinfo->stat_lock); + raw_spin_lock(&sbinfo->stat_lock); if (sbinfo->max_inodes) { if (!sbinfo->free_inodes) { - spin_unlock(&sbinfo->stat_lock); + raw_spin_unlock(&sbinfo->stat_lock); return -ENOSPC; } sbinfo->free_inodes--; @@ -304,7 +304,7 @@ static int shmem_reserve_inode(struct super_block *sb, ino_t *inop) } *inop = ino; } - spin_unlock(&sbinfo->stat_lock); + raw_spin_unlock(&sbinfo->stat_lock); } else if (inop) { /* * __shmem_file_setup, one of our callers, is lock-free: it @@ -319,13 +319,14 @@ static int shmem_reserve_inode(struct super_block *sb, ino_t *inop) * to worry about things like glibc compatibility. */ ino_t *next_ino; + next_ino = per_cpu_ptr(sbinfo->ino_batch, get_cpu()); ino = *next_ino; if (unlikely(ino % SHMEM_INO_BATCH == 0)) { - spin_lock(&sbinfo->stat_lock); + raw_spin_lock(&sbinfo->stat_lock); ino = sbinfo->next_ino; sbinfo->next_ino += SHMEM_INO_BATCH; - spin_unlock(&sbinfo->stat_lock); + raw_spin_unlock(&sbinfo->stat_lock); if (unlikely(is_zero_ino(ino))) ino++; } @@ -341,9 +342,9 @@ static void shmem_free_inode(struct super_block *sb) { struct shmem_sb_info *sbinfo = SHMEM_SB(sb); if (sbinfo->max_inodes) { - spin_lock(&sbinfo->stat_lock); + raw_spin_lock(&sbinfo->stat_lock); sbinfo->free_inodes++; - spin_unlock(&sbinfo->stat_lock); + raw_spin_unlock(&sbinfo->stat_lock); } } @@ -1453,10 +1454,10 @@ static struct mempolicy *shmem_get_sbmpol(struct shmem_sb_info *sbinfo) { struct mempolicy *mpol = NULL; if (sbinfo->mpol) { - spin_lock(&sbinfo->stat_lock); /* prevent replace/use races */ + raw_spin_lock(&sbinfo->stat_lock); /* prevent replace/use races */ mpol = sbinfo->mpol; mpol_get(mpol); - spin_unlock(&sbinfo->stat_lock); + raw_spin_unlock(&sbinfo->stat_lock); } return mpol; } @@ -3533,9 +3534,10 @@ static int shmem_reconfigure(struct fs_context *fc) struct shmem_options *ctx = fc->fs_private; struct shmem_sb_info *sbinfo = SHMEM_SB(fc->root->d_sb); unsigned long inodes; + struct mempolicy *mpol = NULL; const char *err; - spin_lock(&sbinfo->stat_lock); + raw_spin_lock(&sbinfo->stat_lock); inodes = sbinfo->max_inodes - sbinfo->free_inodes; if ((ctx->seen & SHMEM_SEEN_BLOCKS) && ctx->blocks) { if (!sbinfo->max_blocks) { @@ -3580,14 +3582,15 @@ static int shmem_reconfigure(struct fs_context *fc) * Preserve previous mempolicy unless mpol remount option was specified. */ if (ctx->mpol) { - mpol_put(sbinfo->mpol); + mpol = sbinfo->mpol; sbinfo->mpol = ctx->mpol; /* transfers initial ref */ ctx->mpol = NULL; } - spin_unlock(&sbinfo->stat_lock); + raw_spin_unlock(&sbinfo->stat_lock); + mpol_put(mpol); return 0; out: - spin_unlock(&sbinfo->stat_lock); + raw_spin_unlock(&sbinfo->stat_lock); return invalfc(fc, "%s", err); } @@ -3704,7 +3707,7 @@ static int shmem_fill_super(struct super_block *sb, struct fs_context *fc) sbinfo->mpol = ctx->mpol; ctx->mpol = NULL; - spin_lock_init(&sbinfo->stat_lock); + raw_spin_lock_init(&sbinfo->stat_lock); if (percpu_counter_init(&sbinfo->used_blocks, 0, GFP_KERNEL)) goto failed; spin_lock_init(&sbinfo->shrinklist_lock); diff --git a/mm/slab.c b/mm/slab.c index ae651bf540b70..afe196fcf5790 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -234,7 +234,7 @@ static void kmem_cache_node_init(struct kmem_cache_node *parent) parent->shared = NULL; parent->alien = NULL; parent->colour_next = 0; - spin_lock_init(&parent->list_lock); + raw_spin_lock_init(&parent->list_lock); parent->free_objects = 0; parent->free_touched = 0; } @@ -559,9 +559,9 @@ static noinline void cache_free_pfmemalloc(struct kmem_cache *cachep, page_node = page_to_nid(page); n = get_node(cachep, page_node); - spin_lock(&n->list_lock); + raw_spin_lock(&n->list_lock); free_block(cachep, &objp, 1, page_node, &list); - spin_unlock(&n->list_lock); + raw_spin_unlock(&n->list_lock); slabs_destroy(cachep, &list); } @@ -699,7 +699,7 @@ static void __drain_alien_cache(struct kmem_cache *cachep, struct kmem_cache_node *n = get_node(cachep, node); if (ac->avail) { - spin_lock(&n->list_lock); + raw_spin_lock(&n->list_lock); /* * Stuff objects into the remote nodes shared array first. * That way we could avoid the overhead of putting the objects @@ -710,7 +710,7 @@ static void __drain_alien_cache(struct kmem_cache *cachep, free_block(cachep, ac->entry, ac->avail, node, list); ac->avail = 0; - spin_unlock(&n->list_lock); + raw_spin_unlock(&n->list_lock); } } @@ -783,9 +783,9 @@ static int __cache_free_alien(struct kmem_cache *cachep, void *objp, slabs_destroy(cachep, &list); } else { n = get_node(cachep, page_node); - spin_lock(&n->list_lock); + raw_spin_lock(&n->list_lock); free_block(cachep, &objp, 1, page_node, &list); - spin_unlock(&n->list_lock); + raw_spin_unlock(&n->list_lock); slabs_destroy(cachep, &list); } return 1; @@ -826,10 +826,10 @@ static int init_cache_node(struct kmem_cache *cachep, int node, gfp_t gfp) */ n = get_node(cachep, node); if (n) { - spin_lock_irq(&n->list_lock); + raw_spin_lock_irq(&n->list_lock); n->free_limit = (1 + nr_cpus_node(node)) * cachep->batchcount + cachep->num; - spin_unlock_irq(&n->list_lock); + raw_spin_unlock_irq(&n->list_lock); return 0; } @@ -908,7 +908,7 @@ static int setup_kmem_cache_node(struct kmem_cache *cachep, goto fail; n = get_node(cachep, node); - spin_lock_irq(&n->list_lock); + raw_spin_lock_irq(&n->list_lock); if (n->shared && force_change) { free_block(cachep, n->shared->entry, n->shared->avail, node, &list); @@ -926,7 +926,7 @@ static int setup_kmem_cache_node(struct kmem_cache *cachep, new_alien = NULL; } - spin_unlock_irq(&n->list_lock); + raw_spin_unlock_irq(&n->list_lock); slabs_destroy(cachep, &list); /* @@ -965,7 +965,7 @@ static void cpuup_canceled(long cpu) if (!n) continue; - spin_lock_irq(&n->list_lock); + raw_spin_lock_irq(&n->list_lock); /* Free limit for this kmem_cache_node */ n->free_limit -= cachep->batchcount; @@ -976,7 +976,7 @@ static void cpuup_canceled(long cpu) nc->avail = 0; if (!cpumask_empty(mask)) { - spin_unlock_irq(&n->list_lock); + raw_spin_unlock_irq(&n->list_lock); goto free_slab; } @@ -990,7 +990,7 @@ static void cpuup_canceled(long cpu) alien = n->alien; n->alien = NULL; - spin_unlock_irq(&n->list_lock); + raw_spin_unlock_irq(&n->list_lock); kfree(shared); if (alien) { @@ -1174,7 +1174,7 @@ static void __init init_list(struct kmem_cache *cachep, struct kmem_cache_node * /* * Do not assume that spinlocks can be initialized via memcpy: */ - spin_lock_init(&ptr->list_lock); + raw_spin_lock_init(&ptr->list_lock); MAKE_ALL_LISTS(cachep, ptr, nodeid); cachep->node[nodeid] = ptr; @@ -1345,11 +1345,11 @@ slab_out_of_memory(struct kmem_cache *cachep, gfp_t gfpflags, int nodeid) for_each_kmem_cache_node(cachep, node, n) { unsigned long total_slabs, free_slabs, free_objs; - spin_lock_irqsave(&n->list_lock, flags); + raw_spin_lock_irqsave(&n->list_lock, flags); total_slabs = n->total_slabs; free_slabs = n->free_slabs; free_objs = n->free_objects; - spin_unlock_irqrestore(&n->list_lock, flags); + raw_spin_unlock_irqrestore(&n->list_lock, flags); pr_warn(" node %d: slabs: %ld/%ld, objs: %ld/%ld\n", node, total_slabs - free_slabs, total_slabs, @@ -2107,7 +2107,7 @@ static void check_spinlock_acquired(struct kmem_cache *cachep) { #ifdef CONFIG_SMP check_irq_off(); - assert_spin_locked(&get_node(cachep, numa_mem_id())->list_lock); + assert_raw_spin_locked(&get_node(cachep, numa_mem_id())->list_lock); #endif } @@ -2115,7 +2115,7 @@ static void check_spinlock_acquired_node(struct kmem_cache *cachep, int node) { #ifdef CONFIG_SMP check_irq_off(); - assert_spin_locked(&get_node(cachep, node)->list_lock); + assert_raw_spin_locked(&get_node(cachep, node)->list_lock); #endif } @@ -2155,9 +2155,9 @@ static void do_drain(void *arg) check_irq_off(); ac = cpu_cache_get(cachep); n = get_node(cachep, node); - spin_lock(&n->list_lock); + raw_spin_lock(&n->list_lock); free_block(cachep, ac->entry, ac->avail, node, &list); - spin_unlock(&n->list_lock); + raw_spin_unlock(&n->list_lock); ac->avail = 0; slabs_destroy(cachep, &list); } @@ -2175,9 +2175,9 @@ static void drain_cpu_caches(struct kmem_cache *cachep) drain_alien_cache(cachep, n->alien); for_each_kmem_cache_node(cachep, node, n) { - spin_lock_irq(&n->list_lock); + raw_spin_lock_irq(&n->list_lock); drain_array_locked(cachep, n->shared, node, true, &list); - spin_unlock_irq(&n->list_lock); + raw_spin_unlock_irq(&n->list_lock); slabs_destroy(cachep, &list); } @@ -2199,10 +2199,10 @@ static int drain_freelist(struct kmem_cache *cache, nr_freed = 0; while (nr_freed < tofree && !list_empty(&n->slabs_free)) { - spin_lock_irq(&n->list_lock); + raw_spin_lock_irq(&n->list_lock); p = n->slabs_free.prev; if (p == &n->slabs_free) { - spin_unlock_irq(&n->list_lock); + raw_spin_unlock_irq(&n->list_lock); goto out; } @@ -2215,7 +2215,7 @@ static int drain_freelist(struct kmem_cache *cache, * to the cache. */ n->free_objects -= cache->num; - spin_unlock_irq(&n->list_lock); + raw_spin_unlock_irq(&n->list_lock); slab_destroy(cache, page); nr_freed++; } @@ -2651,7 +2651,7 @@ static void cache_grow_end(struct kmem_cache *cachep, struct page *page) INIT_LIST_HEAD(&page->slab_list); n = get_node(cachep, page_to_nid(page)); - spin_lock(&n->list_lock); + raw_spin_lock(&n->list_lock); n->total_slabs++; if (!page->active) { list_add_tail(&page->slab_list, &n->slabs_free); @@ -2661,7 +2661,7 @@ static void cache_grow_end(struct kmem_cache *cachep, struct page *page) STATS_INC_GROWN(cachep); n->free_objects += cachep->num - page->active; - spin_unlock(&n->list_lock); + raw_spin_unlock(&n->list_lock); fixup_objfreelist_debug(cachep, &list); } @@ -2827,7 +2827,7 @@ static struct page *get_first_slab(struct kmem_cache_node *n, bool pfmemalloc) { struct page *page; - assert_spin_locked(&n->list_lock); + assert_raw_spin_locked(&n->list_lock); page = list_first_entry_or_null(&n->slabs_partial, struct page, slab_list); if (!page) { @@ -2854,10 +2854,10 @@ static noinline void *cache_alloc_pfmemalloc(struct kmem_cache *cachep, if (!gfp_pfmemalloc_allowed(flags)) return NULL; - spin_lock(&n->list_lock); + raw_spin_lock(&n->list_lock); page = get_first_slab(n, true); if (!page) { - spin_unlock(&n->list_lock); + raw_spin_unlock(&n->list_lock); return NULL; } @@ -2866,7 +2866,7 @@ static noinline void *cache_alloc_pfmemalloc(struct kmem_cache *cachep, fixup_slab_list(cachep, n, page, &list); - spin_unlock(&n->list_lock); + raw_spin_unlock(&n->list_lock); fixup_objfreelist_debug(cachep, &list); return obj; @@ -2925,7 +2925,7 @@ static void *cache_alloc_refill(struct kmem_cache *cachep, gfp_t flags) if (!n->free_objects && (!shared || !shared->avail)) goto direct_grow; - spin_lock(&n->list_lock); + raw_spin_lock(&n->list_lock); shared = READ_ONCE(n->shared); /* See if we can refill from the shared array */ @@ -2949,7 +2949,7 @@ static void *cache_alloc_refill(struct kmem_cache *cachep, gfp_t flags) must_grow: n->free_objects -= ac->avail; alloc_done: - spin_unlock(&n->list_lock); + raw_spin_unlock(&n->list_lock); fixup_objfreelist_debug(cachep, &list); direct_grow: @@ -3174,7 +3174,7 @@ static void *____cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, BUG_ON(!n); check_irq_off(); - spin_lock(&n->list_lock); + raw_spin_lock(&n->list_lock); page = get_first_slab(n, false); if (!page) goto must_grow; @@ -3192,12 +3192,12 @@ static void *____cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, fixup_slab_list(cachep, n, page, &list); - spin_unlock(&n->list_lock); + raw_spin_unlock(&n->list_lock); fixup_objfreelist_debug(cachep, &list); return obj; must_grow: - spin_unlock(&n->list_lock); + raw_spin_unlock(&n->list_lock); page = cache_grow_begin(cachep, gfp_exact_node(flags), nodeid); if (page) { /* This slab isn't counted yet so don't update free_objects */ @@ -3385,7 +3385,7 @@ static void cache_flusharray(struct kmem_cache *cachep, struct array_cache *ac) check_irq_off(); n = get_node(cachep, node); - spin_lock(&n->list_lock); + raw_spin_lock(&n->list_lock); if (n->shared) { struct array_cache *shared_array = n->shared; int max = shared_array->limit - shared_array->avail; @@ -3414,7 +3414,7 @@ static void cache_flusharray(struct kmem_cache *cachep, struct array_cache *ac) STATS_SET_FREEABLE(cachep, i); } #endif - spin_unlock(&n->list_lock); + raw_spin_unlock(&n->list_lock); ac->avail -= batchcount; memmove(ac->entry, &(ac->entry[batchcount]), sizeof(void *)*ac->avail); slabs_destroy(cachep, &list); @@ -3870,9 +3870,9 @@ static int do_tune_cpucache(struct kmem_cache *cachep, int limit, node = cpu_to_mem(cpu); n = get_node(cachep, node); - spin_lock_irq(&n->list_lock); + raw_spin_lock_irq(&n->list_lock); free_block(cachep, ac->entry, ac->avail, node, &list); - spin_unlock_irq(&n->list_lock); + raw_spin_unlock_irq(&n->list_lock); slabs_destroy(cachep, &list); } free_percpu(prev); @@ -3967,9 +3967,9 @@ static void drain_array(struct kmem_cache *cachep, struct kmem_cache_node *n, return; } - spin_lock_irq(&n->list_lock); + raw_spin_lock_irq(&n->list_lock); drain_array_locked(cachep, ac, node, false, &list); - spin_unlock_irq(&n->list_lock); + raw_spin_unlock_irq(&n->list_lock); slabs_destroy(cachep, &list); } @@ -4053,7 +4053,7 @@ void get_slabinfo(struct kmem_cache *cachep, struct slabinfo *sinfo) for_each_kmem_cache_node(cachep, node, n) { check_irq_on(); - spin_lock_irq(&n->list_lock); + raw_spin_lock_irq(&n->list_lock); total_slabs += n->total_slabs; free_slabs += n->free_slabs; @@ -4062,7 +4062,7 @@ void get_slabinfo(struct kmem_cache *cachep, struct slabinfo *sinfo) if (n->shared) shared_avail += n->shared->avail; - spin_unlock_irq(&n->list_lock); + raw_spin_unlock_irq(&n->list_lock); } num_objs = total_slabs * cachep->num; active_slabs = total_slabs - free_slabs; diff --git a/mm/slab.h b/mm/slab.h index 076582f58f687..21c670da13ac1 100644 --- a/mm/slab.h +++ b/mm/slab.h @@ -527,7 +527,7 @@ static inline void slab_post_alloc_hook(struct kmem_cache *s, * The slab lists for all objects. */ struct kmem_cache_node { - spinlock_t list_lock; + raw_spinlock_t list_lock; #ifdef CONFIG_SLAB struct list_head slabs_partial; /* partial list first, better asm code */ diff --git a/mm/slub.c b/mm/slub.c index 3021ce9bf1b3d..87b1e5cf9348e 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -445,7 +445,7 @@ static inline bool cmpxchg_double_slab(struct kmem_cache *s, struct page *page, #ifdef CONFIG_SLUB_DEBUG static unsigned long object_map[BITS_TO_LONGS(MAX_OBJS_PER_PAGE)]; -static DEFINE_SPINLOCK(object_map_lock); +static DEFINE_RAW_SPINLOCK(object_map_lock); /* * Determine a map of object in use on a page. @@ -461,7 +461,7 @@ static unsigned long *get_map(struct kmem_cache *s, struct page *page) VM_BUG_ON(!irqs_disabled()); - spin_lock(&object_map_lock); + raw_spin_lock(&object_map_lock); bitmap_zero(object_map, page->objects); @@ -474,7 +474,7 @@ static unsigned long *get_map(struct kmem_cache *s, struct page *page) static void put_map(unsigned long *map) __releases(&object_map_lock) { VM_BUG_ON(map != object_map); - spin_unlock(&object_map_lock); + raw_spin_unlock(&object_map_lock); } static inline unsigned int size_from_object(struct kmem_cache *s) @@ -1225,7 +1225,7 @@ static noinline int free_debug_processing( unsigned long flags; int ret = 0; - spin_lock_irqsave(&n->list_lock, flags); + raw_spin_lock_irqsave(&n->list_lock, flags); slab_lock(page); if (s->flags & SLAB_CONSISTENCY_CHECKS) { @@ -1260,7 +1260,7 @@ static noinline int free_debug_processing( bulk_cnt, cnt); slab_unlock(page); - spin_unlock_irqrestore(&n->list_lock, flags); + raw_spin_unlock_irqrestore(&n->list_lock, flags); if (!ret) slab_fix(s, "Object at 0x%p not freed", object); return ret; @@ -1759,10 +1759,18 @@ static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node) void *start, *p, *next; int idx; bool shuffle; + bool enableirqs = false; flags &= gfp_allowed_mask; if (gfpflags_allow_blocking(flags)) + enableirqs = true; + +#ifdef CONFIG_PREEMPT_RT + if (system_state > SYSTEM_BOOTING && system_state < SYSTEM_SUSPEND) + enableirqs = true; +#endif + if (enableirqs) local_irq_enable(); flags |= s->allocflags; @@ -1823,7 +1831,7 @@ static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node) page->frozen = 1; out: - if (gfpflags_allow_blocking(flags)) + if (enableirqs) local_irq_disable(); if (!page) return NULL; @@ -1881,12 +1889,32 @@ static void free_slab(struct kmem_cache *s, struct page *page) __free_slab(s, page); } +static void discard_slab_delayed(struct kmem_cache *s, struct page *page, + struct list_head *delayed_free) +{ + dec_slabs_node(s, page_to_nid(page), page->objects); + if (unlikely(s->flags & SLAB_TYPESAFE_BY_RCU)) + call_rcu(&page->rcu_head, rcu_free_slab); + else + list_add(&page->lru, delayed_free); +} + static void discard_slab(struct kmem_cache *s, struct page *page) { dec_slabs_node(s, page_to_nid(page), page->objects); free_slab(s, page); } +static void discard_delayed(struct list_head *l) +{ + while (!list_empty(l)) { + struct page *page = list_first_entry(l, struct page, lru); + + list_del(&page->lru); + __free_slab(page->slab_cache, page); + } +} + /* * Management of partially allocated slabs. */ @@ -1960,15 +1988,16 @@ static inline void *acquire_slab(struct kmem_cache *s, WARN_ON(!freelist); return freelist; } - -static void put_cpu_partial(struct kmem_cache *s, struct page *page, int drain); +static void put_cpu_partial(struct kmem_cache *s, struct page *page, int drain, + struct list_head *delayed_free); static inline bool pfmemalloc_match(struct page *page, gfp_t gfpflags); /* * Try to allocate a partial slab from a specific node. */ static void *get_partial_node(struct kmem_cache *s, struct kmem_cache_node *n, - struct kmem_cache_cpu *c, gfp_t flags) + struct kmem_cache_cpu *c, gfp_t flags, + struct list_head *delayed_free) { struct page *page, *page2; void *object = NULL; @@ -1984,7 +2013,7 @@ static void *get_partial_node(struct kmem_cache *s, struct kmem_cache_node *n, if (!n || !n->nr_partial) return NULL; - spin_lock(&n->list_lock); + raw_spin_lock(&n->list_lock); list_for_each_entry_safe(page, page2, &n->partial, slab_list) { void *t; @@ -2001,7 +2030,7 @@ static void *get_partial_node(struct kmem_cache *s, struct kmem_cache_node *n, stat(s, ALLOC_FROM_PARTIAL); object = t; } else { - put_cpu_partial(s, page, 0); + put_cpu_partial(s, page, 0, delayed_free); stat(s, CPU_PARTIAL_NODE); } if (!kmem_cache_has_cpu_partial(s) @@ -2009,7 +2038,7 @@ static void *get_partial_node(struct kmem_cache *s, struct kmem_cache_node *n, break; } - spin_unlock(&n->list_lock); + raw_spin_unlock(&n->list_lock); return object; } @@ -2017,7 +2046,8 @@ static void *get_partial_node(struct kmem_cache *s, struct kmem_cache_node *n, * Get a page from somewhere. Search in increasing NUMA distances. */ static void *get_any_partial(struct kmem_cache *s, gfp_t flags, - struct kmem_cache_cpu *c) + struct kmem_cache_cpu *c, + struct list_head *delayed_free) { #ifdef CONFIG_NUMA struct zonelist *zonelist; @@ -2059,7 +2089,7 @@ static void *get_any_partial(struct kmem_cache *s, gfp_t flags, if (n && cpuset_zone_allowed(zone, flags) && n->nr_partial > s->min_partial) { - object = get_partial_node(s, n, c, flags); + object = get_partial_node(s, n, c, flags, delayed_free); if (object) { /* * Don't check read_mems_allowed_retry() @@ -2081,7 +2111,8 @@ static void *get_any_partial(struct kmem_cache *s, gfp_t flags, * Get a partial page, lock it and return it. */ static void *get_partial(struct kmem_cache *s, gfp_t flags, int node, - struct kmem_cache_cpu *c) + struct kmem_cache_cpu *c, + struct list_head *delayed_free) { void *object; int searchnode = node; @@ -2089,11 +2120,12 @@ static void *get_partial(struct kmem_cache *s, gfp_t flags, int node, if (node == NUMA_NO_NODE) searchnode = numa_mem_id(); - object = get_partial_node(s, get_node(s, searchnode), c, flags); + object = get_partial_node(s, get_node(s, searchnode), c, flags, + delayed_free); if (object || node != NUMA_NO_NODE) return object; - return get_any_partial(s, flags, c); + return get_any_partial(s, flags, c, delayed_free); } #ifdef CONFIG_PREEMPTION @@ -2169,7 +2201,8 @@ static void init_kmem_cache_cpus(struct kmem_cache *s) * Remove the cpu slab */ static void deactivate_slab(struct kmem_cache *s, struct page *page, - void *freelist, struct kmem_cache_cpu *c) + void *freelist, struct kmem_cache_cpu *c, + struct list_head *delayed_free) { enum slab_modes { M_NONE, M_PARTIAL, M_FULL, M_FREE }; struct kmem_cache_node *n = get_node(s, page_to_nid(page)); @@ -2252,7 +2285,7 @@ static void deactivate_slab(struct kmem_cache *s, struct page *page, * that acquire_slab() will see a slab page that * is frozen */ - spin_lock(&n->list_lock); + raw_spin_lock(&n->list_lock); } } else { m = M_FULL; @@ -2263,7 +2296,7 @@ static void deactivate_slab(struct kmem_cache *s, struct page *page, * slabs from diagnostic functions will not see * any frozen slabs. */ - spin_lock(&n->list_lock); + raw_spin_lock(&n->list_lock); } } @@ -2287,7 +2320,7 @@ static void deactivate_slab(struct kmem_cache *s, struct page *page, goto redo; if (lock) - spin_unlock(&n->list_lock); + raw_spin_unlock(&n->list_lock); if (m == M_PARTIAL) stat(s, tail); @@ -2295,7 +2328,7 @@ static void deactivate_slab(struct kmem_cache *s, struct page *page, stat(s, DEACTIVATE_FULL); else if (m == M_FREE) { stat(s, DEACTIVATE_EMPTY); - discard_slab(s, page); + discard_slab_delayed(s, page, delayed_free); stat(s, FREE_SLAB); } @@ -2310,8 +2343,8 @@ static void deactivate_slab(struct kmem_cache *s, struct page *page, * for the cpu using c (or some other guarantee must be there * to guarantee no concurrent accesses). */ -static void unfreeze_partials(struct kmem_cache *s, - struct kmem_cache_cpu *c) +static void unfreeze_partials(struct kmem_cache *s, struct kmem_cache_cpu *c, + struct list_head *delayed_free) { #ifdef CONFIG_SLUB_CPU_PARTIAL struct kmem_cache_node *n = NULL, *n2 = NULL; @@ -2326,10 +2359,10 @@ static void unfreeze_partials(struct kmem_cache *s, n2 = get_node(s, page_to_nid(page)); if (n != n2) { if (n) - spin_unlock(&n->list_lock); + raw_spin_unlock(&n->list_lock); n = n2; - spin_lock(&n->list_lock); + raw_spin_lock(&n->list_lock); } do { @@ -2358,14 +2391,14 @@ static void unfreeze_partials(struct kmem_cache *s, } if (n) - spin_unlock(&n->list_lock); + raw_spin_unlock(&n->list_lock); while (discard_page) { page = discard_page; discard_page = discard_page->next; stat(s, DEACTIVATE_EMPTY); - discard_slab(s, page); + discard_slab_delayed(s, page, delayed_free); stat(s, FREE_SLAB); } #endif /* CONFIG_SLUB_CPU_PARTIAL */ @@ -2378,7 +2411,8 @@ static void unfreeze_partials(struct kmem_cache *s, * If we did not find a slot then simply move all the partials to the * per node partial list. */ -static void put_cpu_partial(struct kmem_cache *s, struct page *page, int drain) +static void put_cpu_partial(struct kmem_cache *s, struct page *page, int drain, + struct list_head *delayed_free) { #ifdef CONFIG_SLUB_CPU_PARTIAL struct page *oldpage; @@ -2401,7 +2435,8 @@ static void put_cpu_partial(struct kmem_cache *s, struct page *page, int drain) * set to the per node partial list. */ local_irq_save(flags); - unfreeze_partials(s, this_cpu_ptr(s->cpu_slab)); + unfreeze_partials(s, this_cpu_ptr(s->cpu_slab), + delayed_free); local_irq_restore(flags); oldpage = NULL; pobjects = 0; @@ -2423,17 +2458,18 @@ static void put_cpu_partial(struct kmem_cache *s, struct page *page, int drain) unsigned long flags; local_irq_save(flags); - unfreeze_partials(s, this_cpu_ptr(s->cpu_slab)); + unfreeze_partials(s, this_cpu_ptr(s->cpu_slab), delayed_free); local_irq_restore(flags); } preempt_enable(); #endif /* CONFIG_SLUB_CPU_PARTIAL */ } -static inline void flush_slab(struct kmem_cache *s, struct kmem_cache_cpu *c) +static inline void flush_slab(struct kmem_cache *s, struct kmem_cache_cpu *c, + struct list_head *delayed_free) { stat(s, CPUSLAB_FLUSH); - deactivate_slab(s, c->page, c->freelist, c); + deactivate_slab(s, c->page, c->freelist, c, delayed_free); c->tid = next_tid(c->tid); } @@ -2443,34 +2479,81 @@ static inline void flush_slab(struct kmem_cache *s, struct kmem_cache_cpu *c) * * Called from IPI handler with interrupts disabled. */ -static inline void __flush_cpu_slab(struct kmem_cache *s, int cpu) +static inline void __flush_cpu_slab(struct kmem_cache *s, int cpu, + struct list_head *delayed_free) { struct kmem_cache_cpu *c = per_cpu_ptr(s->cpu_slab, cpu); if (c->page) - flush_slab(s, c); + flush_slab(s, c, delayed_free); - unfreeze_partials(s, c); + unfreeze_partials(s, c, delayed_free); } -static void flush_cpu_slab(void *d) -{ - struct kmem_cache *s = d; +struct slub_flush_work { + struct work_struct work; + struct kmem_cache *s; + bool skip; +}; - __flush_cpu_slab(s, smp_processor_id()); +static void flush_cpu_slab(struct work_struct *w) +{ + struct slub_flush_work *sfw; + LIST_HEAD(delayed_free); + + sfw = container_of(w, struct slub_flush_work, work); + + local_irq_disable(); + __flush_cpu_slab(sfw->s, smp_processor_id(), &delayed_free); + local_irq_enable(); + + discard_delayed(&delayed_free); } -static bool has_cpu_slab(int cpu, void *info) +static bool has_cpu_slab(int cpu, struct kmem_cache *s) { - struct kmem_cache *s = info; struct kmem_cache_cpu *c = per_cpu_ptr(s->cpu_slab, cpu); return c->page || slub_percpu_partial(c); } +static DEFINE_MUTEX(flush_lock); +static DEFINE_PER_CPU(struct slub_flush_work, slub_flush); + +static void flush_all_locked(struct kmem_cache *s) +{ + struct slub_flush_work *sfw; + unsigned int cpu; + + mutex_lock(&flush_lock); + + for_each_online_cpu(cpu) { + sfw = &per_cpu(slub_flush, cpu); + if (!has_cpu_slab(cpu, s)) { + sfw->skip = true; + continue; + } + INIT_WORK(&sfw->work, flush_cpu_slab); + sfw->skip = false; + sfw->s = s; + schedule_work_on(cpu, &sfw->work); + } + + for_each_online_cpu(cpu) { + sfw = &per_cpu(slub_flush, cpu); + if (sfw->skip) + continue; + flush_work(&sfw->work); + } + + mutex_unlock(&flush_lock); +} + static void flush_all(struct kmem_cache *s) { - on_each_cpu_cond(has_cpu_slab, flush_cpu_slab, s, 1); + cpus_read_lock(); + flush_all_locked(s); + cpus_read_unlock(); } /* @@ -2481,13 +2564,15 @@ static int slub_cpu_dead(unsigned int cpu) { struct kmem_cache *s; unsigned long flags; + LIST_HEAD(delayed_free); mutex_lock(&slab_mutex); list_for_each_entry(s, &slab_caches, list) { local_irq_save(flags); - __flush_cpu_slab(s, cpu); + __flush_cpu_slab(s, cpu, &delayed_free); local_irq_restore(flags); } + discard_delayed(&delayed_free); mutex_unlock(&slab_mutex); return 0; } @@ -2525,10 +2610,10 @@ static unsigned long count_partial(struct kmem_cache_node *n, unsigned long x = 0; struct page *page; - spin_lock_irqsave(&n->list_lock, flags); + raw_spin_lock_irqsave(&n->list_lock, flags); list_for_each_entry(page, &n->partial, slab_list) x += get_count(page); - spin_unlock_irqrestore(&n->list_lock, flags); + raw_spin_unlock_irqrestore(&n->list_lock, flags); return x; } #endif /* CONFIG_SLUB_DEBUG || CONFIG_SYSFS */ @@ -2571,7 +2656,8 @@ slab_out_of_memory(struct kmem_cache *s, gfp_t gfpflags, int nid) } static inline void *new_slab_objects(struct kmem_cache *s, gfp_t flags, - int node, struct kmem_cache_cpu **pc) + int node, struct kmem_cache_cpu **pc, + struct list_head *delayed_free) { void *freelist; struct kmem_cache_cpu *c = *pc; @@ -2579,7 +2665,7 @@ static inline void *new_slab_objects(struct kmem_cache *s, gfp_t flags, WARN_ON_ONCE(s->ctor && (flags & __GFP_ZERO)); - freelist = get_partial(s, flags, node, c); + freelist = get_partial(s, flags, node, c, delayed_free); if (freelist) return freelist; @@ -2588,7 +2674,7 @@ static inline void *new_slab_objects(struct kmem_cache *s, gfp_t flags, if (page) { c = raw_cpu_ptr(s->cpu_slab); if (c->page) - flush_slab(s, c); + flush_slab(s, c, delayed_free); /* * No other reference to the page yet so we can @@ -2667,7 +2753,8 @@ static inline void *get_freelist(struct kmem_cache *s, struct page *page) * already disabled (which is the case for bulk allocation). */ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, - unsigned long addr, struct kmem_cache_cpu *c) + unsigned long addr, struct kmem_cache_cpu *c, + struct list_head *delayed_free) { void *freelist; struct page *page; @@ -2697,7 +2784,7 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, goto redo; } else { stat(s, ALLOC_NODE_MISMATCH); - deactivate_slab(s, page, c->freelist, c); + deactivate_slab(s, page, c->freelist, c, delayed_free); goto new_slab; } } @@ -2708,7 +2795,7 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, * information when the page leaves the per-cpu allocator */ if (unlikely(!pfmemalloc_match(page, gfpflags))) { - deactivate_slab(s, page, c->freelist, c); + deactivate_slab(s, page, c->freelist, c, delayed_free); goto new_slab; } @@ -2747,7 +2834,7 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, goto redo; } - freelist = new_slab_objects(s, gfpflags, node, &c); + freelist = new_slab_objects(s, gfpflags, node, &c, delayed_free); if (unlikely(!freelist)) { slab_out_of_memory(s, gfpflags, node); @@ -2763,7 +2850,7 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, !alloc_debug_processing(s, page, freelist, addr)) goto new_slab; /* Slab failed checks. Next slab needed */ - deactivate_slab(s, page, get_freepointer(s, freelist), c); + deactivate_slab(s, page, get_freepointer(s, freelist), c, delayed_free); return freelist; } @@ -2776,6 +2863,7 @@ static void *__slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, { void *p; unsigned long flags; + LIST_HEAD(delayed_free); local_irq_save(flags); #ifdef CONFIG_PREEMPTION @@ -2787,8 +2875,9 @@ static void *__slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, c = this_cpu_ptr(s->cpu_slab); #endif - p = ___slab_alloc(s, gfpflags, node, addr, c); + p = ___slab_alloc(s, gfpflags, node, addr, c, &delayed_free); local_irq_restore(flags); + discard_delayed(&delayed_free); return p; } @@ -2823,6 +2912,10 @@ static __always_inline void *slab_alloc_node(struct kmem_cache *s, unsigned long tid; struct obj_cgroup *objcg = NULL; + if (IS_ENABLED(CONFIG_PREEMPT_RT) && IS_ENABLED(CONFIG_DEBUG_ATOMIC_SLEEP)) + WARN_ON_ONCE(!preemptible() && + (system_state > SYSTEM_BOOTING && system_state < SYSTEM_SUSPEND)); + s = slab_pre_alloc_hook(s, &objcg, 1, gfpflags); if (!s) return NULL; @@ -2997,7 +3090,7 @@ static void __slab_free(struct kmem_cache *s, struct page *page, do { if (unlikely(n)) { - spin_unlock_irqrestore(&n->list_lock, flags); + raw_spin_unlock_irqrestore(&n->list_lock, flags); n = NULL; } prior = page->freelist; @@ -3029,7 +3122,7 @@ static void __slab_free(struct kmem_cache *s, struct page *page, * Otherwise the list_lock will synchronize with * other processors updating the list of slabs. */ - spin_lock_irqsave(&n->list_lock, flags); + raw_spin_lock_irqsave(&n->list_lock, flags); } } @@ -3048,11 +3141,13 @@ static void __slab_free(struct kmem_cache *s, struct page *page, */ stat(s, FREE_FROZEN); } else if (new.frozen) { + LIST_HEAD(delayed_free); /* * If we just froze the page then put it onto the * per cpu partial list. */ - put_cpu_partial(s, page, 1); + put_cpu_partial(s, page, 1, &delayed_free); + discard_delayed(&delayed_free); stat(s, CPU_PARTIAL_FREE); } @@ -3071,7 +3166,7 @@ static void __slab_free(struct kmem_cache *s, struct page *page, add_partial(n, page, DEACTIVATE_TO_TAIL); stat(s, FREE_ADD_PARTIAL); } - spin_unlock_irqrestore(&n->list_lock, flags); + raw_spin_unlock_irqrestore(&n->list_lock, flags); return; slab_empty: @@ -3086,7 +3181,7 @@ static void __slab_free(struct kmem_cache *s, struct page *page, remove_full(s, n, page); } - spin_unlock_irqrestore(&n->list_lock, flags); + raw_spin_unlock_irqrestore(&n->list_lock, flags); stat(s, FREE_SLAB); discard_slab(s, page); } @@ -3303,6 +3398,11 @@ int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size, struct kmem_cache_cpu *c; int i; struct obj_cgroup *objcg = NULL; + LIST_HEAD(delayed_free); + + if (IS_ENABLED(CONFIG_PREEMPT_RT) && IS_ENABLED(CONFIG_DEBUG_ATOMIC_SLEEP)) + WARN_ON_ONCE(!preemptible() && + (system_state > SYSTEM_BOOTING && system_state < SYSTEM_SUSPEND)); /* memcg and kmem_cache debug support */ s = slab_pre_alloc_hook(s, &objcg, size, flags); @@ -3340,7 +3440,7 @@ int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size, * of re-populating per CPU c->freelist */ p[i] = ___slab_alloc(s, flags, NUMA_NO_NODE, - _RET_IP_, c); + _RET_IP_, c, &delayed_free); if (unlikely(!p[i])) goto error; @@ -3356,6 +3456,8 @@ int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size, c->tid = next_tid(c->tid); local_irq_enable(); + discard_delayed(&delayed_free); + /* Clear memory outside IRQ disabled fastpath loop */ if (unlikely(slab_want_init_on_alloc(flags, s))) { int j; @@ -3369,6 +3471,7 @@ int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size, return i; error: local_irq_enable(); + discard_delayed(&delayed_free); slab_post_alloc_hook(s, objcg, flags, i, p); __kmem_cache_free_bulk(s, i, p); return 0; @@ -3518,7 +3621,7 @@ static void init_kmem_cache_node(struct kmem_cache_node *n) { n->nr_partial = 0; - spin_lock_init(&n->list_lock); + raw_spin_lock_init(&n->list_lock); INIT_LIST_HEAD(&n->partial); #ifdef CONFIG_SLUB_DEBUG atomic_long_set(&n->nr_slabs, 0); @@ -3918,7 +4021,7 @@ static void free_partial(struct kmem_cache *s, struct kmem_cache_node *n) struct page *page, *h; BUG_ON(irqs_disabled()); - spin_lock_irq(&n->list_lock); + raw_spin_lock_irq(&n->list_lock); list_for_each_entry_safe(page, h, &n->partial, slab_list) { if (!page->inuse) { remove_partial(n, page); @@ -3928,7 +4031,7 @@ static void free_partial(struct kmem_cache *s, struct kmem_cache_node *n) "Objects remaining in %s on __kmem_cache_shutdown()"); } } - spin_unlock_irq(&n->list_lock); + raw_spin_unlock_irq(&n->list_lock); list_for_each_entry_safe(page, h, &discard, slab_list) discard_slab(s, page); @@ -3953,7 +4056,7 @@ int __kmem_cache_shutdown(struct kmem_cache *s) int node; struct kmem_cache_node *n; - flush_all(s); + flush_all_locked(s); /* Attempt to free all objects */ for_each_kmem_cache_node(s, node, n) { free_partial(s, n); @@ -4237,13 +4340,13 @@ int __kmem_cache_shrink(struct kmem_cache *s) unsigned long flags; int ret = 0; - flush_all(s); + flush_all_locked(s); for_each_kmem_cache_node(s, node, n) { INIT_LIST_HEAD(&discard); for (i = 0; i < SHRINK_PROMOTE_MAX; i++) INIT_LIST_HEAD(promote + i); - spin_lock_irqsave(&n->list_lock, flags); + raw_spin_lock_irqsave(&n->list_lock, flags); /* * Build lists of slabs to discard or promote. @@ -4274,7 +4377,7 @@ int __kmem_cache_shrink(struct kmem_cache *s) for (i = SHRINK_PROMOTE_MAX - 1; i >= 0; i--) list_splice(promote + i, &n->partial); - spin_unlock_irqrestore(&n->list_lock, flags); + raw_spin_unlock_irqrestore(&n->list_lock, flags); /* Release empty slabs */ list_for_each_entry_safe(page, t, &discard, slab_list) @@ -4421,6 +4524,7 @@ static struct kmem_cache * __init bootstrap(struct kmem_cache *static_cache) int node; struct kmem_cache *s = kmem_cache_zalloc(kmem_cache, GFP_NOWAIT); struct kmem_cache_node *n; + LIST_HEAD(delayed_free); memcpy(s, static_cache, kmem_cache->object_size); @@ -4429,7 +4533,8 @@ static struct kmem_cache * __init bootstrap(struct kmem_cache *static_cache) * up. Even if it weren't true, IRQs are not up so we couldn't fire * IPIs around. */ - __flush_cpu_slab(s, smp_processor_id()); + __flush_cpu_slab(s, smp_processor_id(), &delayed_free); + discard_delayed(&delayed_free); for_each_kmem_cache_node(s, node, n) { struct page *p; @@ -4644,7 +4749,7 @@ static int validate_slab_node(struct kmem_cache *s, struct page *page; unsigned long flags; - spin_lock_irqsave(&n->list_lock, flags); + raw_spin_lock_irqsave(&n->list_lock, flags); list_for_each_entry(page, &n->partial, slab_list) { validate_slab(s, page); @@ -4666,7 +4771,7 @@ static int validate_slab_node(struct kmem_cache *s, s->name, count, atomic_long_read(&n->nr_slabs)); out: - spin_unlock_irqrestore(&n->list_lock, flags); + raw_spin_unlock_irqrestore(&n->list_lock, flags); return count; } @@ -4717,6 +4822,9 @@ static int alloc_loc_track(struct loc_track *t, unsigned long max, gfp_t flags) struct location *l; int order; + if (IS_ENABLED(CONFIG_PREEMPT_RT) && flags == GFP_ATOMIC) + return 0; + order = get_order(sizeof(struct location) * max); l = (void *)__get_free_pages(flags, order); @@ -4845,12 +4953,12 @@ static int list_locations(struct kmem_cache *s, char *buf, if (!atomic_long_read(&n->nr_slabs)) continue; - spin_lock_irqsave(&n->list_lock, flags); + raw_spin_lock_irqsave(&n->list_lock, flags); list_for_each_entry(page, &n->partial, slab_list) process_slab(&t, s, page, alloc); list_for_each_entry(page, &n->full, slab_list) process_slab(&t, s, page, alloc); - spin_unlock_irqrestore(&n->list_lock, flags); + raw_spin_unlock_irqrestore(&n->list_lock, flags); } for (i = 0; i < t.count; i++) { diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 4f5f8c907897a..e6cd482a11b92 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -1558,7 +1558,7 @@ static void *new_vmap_block(unsigned int order, gfp_t gfp_mask) struct vmap_block *vb; struct vmap_area *va; unsigned long vb_idx; - int node, err; + int node, err, cpu; void *vaddr; node = numa_node_id(); @@ -1595,11 +1595,12 @@ static void *new_vmap_block(unsigned int order, gfp_t gfp_mask) return ERR_PTR(err); } - vbq = &get_cpu_var(vmap_block_queue); + cpu = get_cpu_light(); + vbq = this_cpu_ptr(&vmap_block_queue); spin_lock(&vbq->lock); list_add_tail_rcu(&vb->free_list, &vbq->free); spin_unlock(&vbq->lock); - put_cpu_var(vmap_block_queue); + put_cpu_light(); return vaddr; } @@ -1664,6 +1665,7 @@ static void *vb_alloc(unsigned long size, gfp_t gfp_mask) struct vmap_block *vb; void *vaddr = NULL; unsigned int order; + int cpu; BUG_ON(offset_in_page(size)); BUG_ON(size > PAGE_SIZE*VMAP_MAX_ALLOC); @@ -1678,7 +1680,8 @@ static void *vb_alloc(unsigned long size, gfp_t gfp_mask) order = get_order(size); rcu_read_lock(); - vbq = &get_cpu_var(vmap_block_queue); + cpu = get_cpu_light(); + vbq = this_cpu_ptr(&vmap_block_queue); list_for_each_entry_rcu(vb, &vbq->free, free_list) { unsigned long pages_off; @@ -1701,7 +1704,7 @@ static void *vb_alloc(unsigned long size, gfp_t gfp_mask) break; } - put_cpu_var(vmap_block_queue); + put_cpu_light(); rcu_read_unlock(); /* Allocate new block if nothing was found */ diff --git a/mm/vmstat.c b/mm/vmstat.c index 74b2c374b86c8..4ef7b8a8f5ce5 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -321,6 +321,7 @@ void __mod_zone_page_state(struct zone *zone, enum zone_stat_item item, long x; long t; + preempt_disable_rt(); x = delta + __this_cpu_read(*p); t = __this_cpu_read(pcp->stat_threshold); @@ -330,6 +331,7 @@ void __mod_zone_page_state(struct zone *zone, enum zone_stat_item item, x = 0; } __this_cpu_write(*p, x); + preempt_enable_rt(); } EXPORT_SYMBOL(__mod_zone_page_state); @@ -352,6 +354,7 @@ void __mod_node_page_state(struct pglist_data *pgdat, enum node_stat_item item, delta >>= PAGE_SHIFT; } + preempt_disable_rt(); x = delta + __this_cpu_read(*p); t = __this_cpu_read(pcp->stat_threshold); @@ -361,6 +364,7 @@ void __mod_node_page_state(struct pglist_data *pgdat, enum node_stat_item item, x = 0; } __this_cpu_write(*p, x); + preempt_enable_rt(); } EXPORT_SYMBOL(__mod_node_page_state); @@ -393,6 +397,7 @@ void __inc_zone_state(struct zone *zone, enum zone_stat_item item) s8 __percpu *p = pcp->vm_stat_diff + item; s8 v, t; + preempt_disable_rt(); v = __this_cpu_inc_return(*p); t = __this_cpu_read(pcp->stat_threshold); if (unlikely(v > t)) { @@ -401,6 +406,7 @@ void __inc_zone_state(struct zone *zone, enum zone_stat_item item) zone_page_state_add(v + overstep, zone, item); __this_cpu_write(*p, -overstep); } + preempt_enable_rt(); } void __inc_node_state(struct pglist_data *pgdat, enum node_stat_item item) @@ -411,6 +417,7 @@ void __inc_node_state(struct pglist_data *pgdat, enum node_stat_item item) VM_WARN_ON_ONCE(vmstat_item_in_bytes(item)); + preempt_disable_rt(); v = __this_cpu_inc_return(*p); t = __this_cpu_read(pcp->stat_threshold); if (unlikely(v > t)) { @@ -419,6 +426,7 @@ void __inc_node_state(struct pglist_data *pgdat, enum node_stat_item item) node_page_state_add(v + overstep, pgdat, item); __this_cpu_write(*p, -overstep); } + preempt_enable_rt(); } void __inc_zone_page_state(struct page *page, enum zone_stat_item item) @@ -439,6 +447,7 @@ void __dec_zone_state(struct zone *zone, enum zone_stat_item item) s8 __percpu *p = pcp->vm_stat_diff + item; s8 v, t; + preempt_disable_rt(); v = __this_cpu_dec_return(*p); t = __this_cpu_read(pcp->stat_threshold); if (unlikely(v < - t)) { @@ -447,6 +456,7 @@ void __dec_zone_state(struct zone *zone, enum zone_stat_item item) zone_page_state_add(v - overstep, zone, item); __this_cpu_write(*p, overstep); } + preempt_enable_rt(); } void __dec_node_state(struct pglist_data *pgdat, enum node_stat_item item) @@ -457,6 +467,7 @@ void __dec_node_state(struct pglist_data *pgdat, enum node_stat_item item) VM_WARN_ON_ONCE(vmstat_item_in_bytes(item)); + preempt_disable_rt(); v = __this_cpu_dec_return(*p); t = __this_cpu_read(pcp->stat_threshold); if (unlikely(v < - t)) { @@ -465,6 +476,7 @@ void __dec_node_state(struct pglist_data *pgdat, enum node_stat_item item) node_page_state_add(v - overstep, pgdat, item); __this_cpu_write(*p, overstep); } + preempt_enable_rt(); } void __dec_zone_page_state(struct page *page, enum zone_stat_item item) diff --git a/mm/workingset.c b/mm/workingset.c index cd39902c10629..3d34c1309f54c 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -430,6 +430,8 @@ static struct list_lru shadow_nodes; void workingset_update_node(struct xa_node *node) { + struct address_space *mapping; + /* * Track non-empty nodes that contain only shadow entries; * unlink those that contain pages or are being freed. @@ -438,7 +440,8 @@ void workingset_update_node(struct xa_node *node) * already where they should be. The list_empty() test is safe * as node->private_list is protected by the i_pages lock. */ - VM_WARN_ON_ONCE(!irqs_disabled()); /* For __inc_lruvec_page_state */ + mapping = container_of(node->array, struct address_space, i_pages); + lockdep_assert_held(&mapping->i_pages.xa_lock); if (node->count && node->count == node->nr_values) { if (list_empty(&node->private_list)) { diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index 30c358b720251..6177b736d0180 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -57,6 +57,7 @@ #include #include #include +#include #define ZSPAGE_MAGIC 0x58 @@ -77,6 +78,20 @@ #define ZS_HANDLE_SIZE (sizeof(unsigned long)) +#ifdef CONFIG_PREEMPT_RT + +struct zsmalloc_handle { + unsigned long addr; + struct mutex lock; +}; + +#define ZS_HANDLE_ALLOC_SIZE (sizeof(struct zsmalloc_handle)) + +#else + +#define ZS_HANDLE_ALLOC_SIZE (sizeof(unsigned long)) +#endif + /* * Object location (, ) is encoded as * a single (unsigned long) handle value. @@ -293,6 +308,7 @@ struct zspage { }; struct mapping_area { + local_lock_t lock; char *vm_buf; /* copy buffer for objects that span pages */ char *vm_addr; /* address of kmap_atomic()'ed pages */ enum zs_mapmode vm_mm; /* mapping mode */ @@ -322,7 +338,7 @@ static void SetZsPageMovable(struct zs_pool *pool, struct zspage *zspage) {} static int create_cache(struct zs_pool *pool) { - pool->handle_cachep = kmem_cache_create("zs_handle", ZS_HANDLE_SIZE, + pool->handle_cachep = kmem_cache_create("zs_handle", ZS_HANDLE_ALLOC_SIZE, 0, 0, NULL); if (!pool->handle_cachep) return 1; @@ -346,10 +362,27 @@ static void destroy_cache(struct zs_pool *pool) static unsigned long cache_alloc_handle(struct zs_pool *pool, gfp_t gfp) { - return (unsigned long)kmem_cache_alloc(pool->handle_cachep, - gfp & ~(__GFP_HIGHMEM|__GFP_MOVABLE)); + void *p; + + p = kmem_cache_alloc(pool->handle_cachep, + gfp & ~(__GFP_HIGHMEM|__GFP_MOVABLE)); +#ifdef CONFIG_PREEMPT_RT + if (p) { + struct zsmalloc_handle *zh = p; + + mutex_init(&zh->lock); + } +#endif + return (unsigned long)p; } +#ifdef CONFIG_PREEMPT_RT +static struct zsmalloc_handle *zs_get_pure_handle(unsigned long handle) +{ + return (void *)(handle &~((1 << OBJ_TAG_BITS) - 1)); +} +#endif + static void cache_free_handle(struct zs_pool *pool, unsigned long handle) { kmem_cache_free(pool->handle_cachep, (void *)handle); @@ -368,12 +401,18 @@ static void cache_free_zspage(struct zs_pool *pool, struct zspage *zspage) static void record_obj(unsigned long handle, unsigned long obj) { +#ifdef CONFIG_PREEMPT_RT + struct zsmalloc_handle *zh = zs_get_pure_handle(handle); + + WRITE_ONCE(zh->addr, obj); +#else /* * lsb of @obj represents handle lock while other bits * represent object value the handle is pointing so * updating shouldn't do store tearing. */ WRITE_ONCE(*(unsigned long *)handle, obj); +#endif } /* zpool driver */ @@ -455,7 +494,10 @@ MODULE_ALIAS("zpool-zsmalloc"); #endif /* CONFIG_ZPOOL */ /* per-cpu VM mapping areas for zspage accesses that cross page boundaries */ -static DEFINE_PER_CPU(struct mapping_area, zs_map_area); +static DEFINE_PER_CPU(struct mapping_area, zs_map_area) = { + /* XXX remove this and use a spin_lock_t in pin_tag() */ + .lock = INIT_LOCAL_LOCK(lock), +}; static bool is_zspage_isolated(struct zspage *zspage) { @@ -862,7 +904,13 @@ static unsigned long location_to_obj(struct page *page, unsigned int obj_idx) static unsigned long handle_to_obj(unsigned long handle) { +#ifdef CONFIG_PREEMPT_RT + struct zsmalloc_handle *zh = zs_get_pure_handle(handle); + + return zh->addr; +#else return *(unsigned long *)handle; +#endif } static unsigned long obj_to_head(struct page *page, void *obj) @@ -876,22 +924,46 @@ static unsigned long obj_to_head(struct page *page, void *obj) static inline int testpin_tag(unsigned long handle) { +#ifdef CONFIG_PREEMPT_RT + struct zsmalloc_handle *zh = zs_get_pure_handle(handle); + + return mutex_is_locked(&zh->lock); +#else return bit_spin_is_locked(HANDLE_PIN_BIT, (unsigned long *)handle); +#endif } static inline int trypin_tag(unsigned long handle) { +#ifdef CONFIG_PREEMPT_RT + struct zsmalloc_handle *zh = zs_get_pure_handle(handle); + + return mutex_trylock(&zh->lock); +#else return bit_spin_trylock(HANDLE_PIN_BIT, (unsigned long *)handle); +#endif } static void pin_tag(unsigned long handle) __acquires(bitlock) { +#ifdef CONFIG_PREEMPT_RT + struct zsmalloc_handle *zh = zs_get_pure_handle(handle); + + return mutex_lock(&zh->lock); +#else bit_spin_lock(HANDLE_PIN_BIT, (unsigned long *)handle); +#endif } static void unpin_tag(unsigned long handle) __releases(bitlock) { +#ifdef CONFIG_PREEMPT_RT + struct zsmalloc_handle *zh = zs_get_pure_handle(handle); + + return mutex_unlock(&zh->lock); +#else bit_spin_unlock(HANDLE_PIN_BIT, (unsigned long *)handle); +#endif } static void reset_page(struct page *page) @@ -1274,7 +1346,8 @@ void *zs_map_object(struct zs_pool *pool, unsigned long handle, class = pool->size_class[class_idx]; off = (class->size * obj_idx) & ~PAGE_MASK; - area = &get_cpu_var(zs_map_area); + local_lock(&zs_map_area.lock); + area = this_cpu_ptr(&zs_map_area); area->vm_mm = mm; if (off + class->size <= PAGE_SIZE) { /* this object is contained entirely within a page */ @@ -1328,7 +1401,7 @@ void zs_unmap_object(struct zs_pool *pool, unsigned long handle) __zs_unmap_object(area, pages, off, class->size); } - put_cpu_var(zs_map_area); + local_unlock(&zs_map_area.lock); migrate_read_unlock(zspage); unpin_tag(handle); diff --git a/net/Kconfig b/net/Kconfig index 8cea808ad9e8d..32f1011083616 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -286,7 +286,7 @@ config CGROUP_NET_CLASSID config NET_RX_BUSY_POLL bool - default y + default y if !PREEMPT_RT config BQL bool diff --git a/net/core/dev.c b/net/core/dev.c index 6c5967e801328..ca150f02eed13 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -223,14 +223,14 @@ static inline struct hlist_head *dev_index_hash(struct net *net, int ifindex) static inline void rps_lock(struct softnet_data *sd) { #ifdef CONFIG_RPS - spin_lock(&sd->input_pkt_queue.lock); + raw_spin_lock(&sd->input_pkt_queue.raw_lock); #endif } static inline void rps_unlock(struct softnet_data *sd) { #ifdef CONFIG_RPS - spin_unlock(&sd->input_pkt_queue.lock); + raw_spin_unlock(&sd->input_pkt_queue.raw_lock); #endif } @@ -3060,6 +3060,7 @@ static void __netif_reschedule(struct Qdisc *q) sd->output_queue_tailp = &q->next_sched; raise_softirq_irqoff(NET_TX_SOFTIRQ); local_irq_restore(flags); + preempt_check_resched_rt(); } void __netif_schedule(struct Qdisc *q) @@ -3122,6 +3123,7 @@ void __dev_kfree_skb_irq(struct sk_buff *skb, enum skb_free_reason reason) __this_cpu_write(softnet_data.completion_queue, skb); raise_softirq_irqoff(NET_TX_SOFTIRQ); local_irq_restore(flags); + preempt_check_resched_rt(); } EXPORT_SYMBOL(__dev_kfree_skb_irq); @@ -3805,7 +3807,11 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, * This permits qdisc->running owner to get the lock more * often and dequeue packets faster. */ +#ifdef CONFIG_PREEMPT_RT + contended = true; +#else contended = qdisc_is_running(q); +#endif if (unlikely(contended)) spin_lock(&q->busylock); @@ -4617,6 +4623,7 @@ static int enqueue_to_backlog(struct sk_buff *skb, int cpu, rps_unlock(sd); local_irq_restore(flags); + preempt_check_resched_rt(); atomic_long_inc(&skb->dev->rx_dropped); kfree_skb(skb); @@ -4830,7 +4837,7 @@ static int netif_rx_internal(struct sk_buff *skb) struct rps_dev_flow voidflow, *rflow = &voidflow; int cpu; - preempt_disable(); + migrate_disable(); rcu_read_lock(); cpu = get_rps_cpu(skb->dev, skb, &rflow); @@ -4840,14 +4847,14 @@ static int netif_rx_internal(struct sk_buff *skb) ret = enqueue_to_backlog(skb, cpu, &rflow->last_qtail); rcu_read_unlock(); - preempt_enable(); + migrate_enable(); } else #endif { unsigned int qtail; - ret = enqueue_to_backlog(skb, get_cpu(), &qtail); - put_cpu(); + ret = enqueue_to_backlog(skb, get_cpu_light(), &qtail); + put_cpu_light(); } return ret; } @@ -4886,11 +4893,9 @@ int netif_rx_ni(struct sk_buff *skb) trace_netif_rx_ni_entry(skb); - preempt_disable(); + local_bh_disable(); err = netif_rx_internal(skb); - if (local_softirq_pending()) - do_softirq(); - preempt_enable(); + local_bh_enable(); trace_netif_rx_ni_exit(err); return err; @@ -6306,12 +6311,14 @@ static void net_rps_action_and_irq_enable(struct softnet_data *sd) sd->rps_ipi_list = NULL; local_irq_enable(); + preempt_check_resched_rt(); /* Send pending IPI's to kick RPS processing on remote cpus. */ net_rps_send_ipi(remsd); } else #endif local_irq_enable(); + preempt_check_resched_rt(); } static bool sd_has_rps_ipi_waiting(struct softnet_data *sd) @@ -6389,6 +6396,7 @@ void __napi_schedule(struct napi_struct *n) local_irq_save(flags); ____napi_schedule(this_cpu_ptr(&softnet_data), n); local_irq_restore(flags); + preempt_check_resched_rt(); } EXPORT_SYMBOL(__napi_schedule); @@ -11144,6 +11152,7 @@ static int dev_cpu_dead(unsigned int oldcpu) raise_softirq_irqoff(NET_TX_SOFTIRQ); local_irq_enable(); + preempt_check_resched_rt(); #ifdef CONFIG_RPS remsd = oldsd->rps_ipi_list; @@ -11157,7 +11166,7 @@ static int dev_cpu_dead(unsigned int oldcpu) netif_rx_ni(skb); input_queue_head_incr(oldsd); } - while ((skb = skb_dequeue(&oldsd->input_pkt_queue))) { + while ((skb = __skb_dequeue(&oldsd->input_pkt_queue))) { netif_rx_ni(skb); input_queue_head_incr(oldsd); } @@ -11473,7 +11482,7 @@ static int __init net_dev_init(void) INIT_WORK(flush, flush_backlog); - skb_queue_head_init(&sd->input_pkt_queue); + skb_queue_head_init_raw(&sd->input_pkt_queue); skb_queue_head_init(&sd->process_queue); #ifdef CONFIG_XFRM_OFFLOAD skb_queue_head_init(&sd->xfrm_backlog); diff --git a/net/core/gen_estimator.c b/net/core/gen_estimator.c index 8e582e29a41e3..e51f4854d8b2f 100644 --- a/net/core/gen_estimator.c +++ b/net/core/gen_estimator.c @@ -42,7 +42,7 @@ struct net_rate_estimator { struct gnet_stats_basic_packed *bstats; spinlock_t *stats_lock; - seqcount_t *running; + net_seqlock_t *running; struct gnet_stats_basic_cpu __percpu *cpu_bstats; u8 ewma_log; u8 intvl_log; /* period : (250ms << intvl_log) */ @@ -125,7 +125,7 @@ int gen_new_estimator(struct gnet_stats_basic_packed *bstats, struct gnet_stats_basic_cpu __percpu *cpu_bstats, struct net_rate_estimator __rcu **rate_est, spinlock_t *lock, - seqcount_t *running, + net_seqlock_t *running, struct nlattr *opt) { struct gnet_estimator *parm = nla_data(opt); @@ -226,7 +226,7 @@ int gen_replace_estimator(struct gnet_stats_basic_packed *bstats, struct gnet_stats_basic_cpu __percpu *cpu_bstats, struct net_rate_estimator __rcu **rate_est, spinlock_t *lock, - seqcount_t *running, struct nlattr *opt) + net_seqlock_t *running, struct nlattr *opt) { return gen_new_estimator(bstats, cpu_bstats, rate_est, lock, running, opt); diff --git a/net/core/gen_stats.c b/net/core/gen_stats.c index e491b083b3485..ef432cea2e105 100644 --- a/net/core/gen_stats.c +++ b/net/core/gen_stats.c @@ -137,7 +137,7 @@ __gnet_stats_copy_basic_cpu(struct gnet_stats_basic_packed *bstats, } void -__gnet_stats_copy_basic(const seqcount_t *running, +__gnet_stats_copy_basic(net_seqlock_t *running, struct gnet_stats_basic_packed *bstats, struct gnet_stats_basic_cpu __percpu *cpu, struct gnet_stats_basic_packed *b) @@ -150,15 +150,15 @@ __gnet_stats_copy_basic(const seqcount_t *running, } do { if (running) - seq = read_seqcount_begin(running); + seq = net_seq_begin(running); bstats->bytes = b->bytes; bstats->packets = b->packets; - } while (running && read_seqcount_retry(running, seq)); + } while (running && net_seq_retry(running, seq)); } EXPORT_SYMBOL(__gnet_stats_copy_basic); static int -___gnet_stats_copy_basic(const seqcount_t *running, +___gnet_stats_copy_basic(net_seqlock_t *running, struct gnet_dump *d, struct gnet_stats_basic_cpu __percpu *cpu, struct gnet_stats_basic_packed *b, @@ -204,7 +204,7 @@ ___gnet_stats_copy_basic(const seqcount_t *running, * if the room in the socket buffer was not sufficient. */ int -gnet_stats_copy_basic(const seqcount_t *running, +gnet_stats_copy_basic(net_seqlock_t *running, struct gnet_dump *d, struct gnet_stats_basic_cpu __percpu *cpu, struct gnet_stats_basic_packed *b) @@ -228,7 +228,7 @@ EXPORT_SYMBOL(gnet_stats_copy_basic); * if the room in the socket buffer was not sufficient. */ int -gnet_stats_copy_basic_hw(const seqcount_t *running, +gnet_stats_copy_basic_hw(net_seqlock_t *running, struct gnet_dump *d, struct gnet_stats_basic_cpu __percpu *cpu, struct gnet_stats_basic_packed *b) diff --git a/net/core/skbuff.c b/net/core/skbuff.c index c421c8f809256..4275b88726f46 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -60,6 +60,7 @@ #include #include #include +#include #include #include diff --git a/net/core/sock.c b/net/core/sock.c index 0ed98f20448a2..f1d1cee0dddd5 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -3064,12 +3064,11 @@ void lock_sock_nested(struct sock *sk, int subclass) if (sk->sk_lock.owned) __lock_sock(sk); sk->sk_lock.owned = 1; - spin_unlock(&sk->sk_lock.slock); + spin_unlock_bh(&sk->sk_lock.slock); /* * The sk_lock has mutex_lock() semantics here: */ mutex_acquire(&sk->sk_lock.dep_map, subclass, 0, _RET_IP_); - local_bh_enable(); } EXPORT_SYMBOL(lock_sock_nested); @@ -3118,13 +3117,12 @@ bool lock_sock_fast(struct sock *sk) __acquires(&sk->sk_lock.slock) __lock_sock(sk); sk->sk_lock.owned = 1; - spin_unlock(&sk->sk_lock.slock); + spin_unlock_bh(&sk->sk_lock.slock); /* * The sk_lock has mutex_lock() semantics here: */ mutex_acquire(&sk->sk_lock.dep_map, 0, 0, _RET_IP_); __acquire(&sk->sk_lock.slock); - local_bh_enable(); return true; } EXPORT_SYMBOL(lock_sock_fast); diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index c96866a53a664..388e3ebb7f576 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -635,7 +635,9 @@ int __inet_hash(struct sock *sk, struct sock *osk) int err = 0; if (sk->sk_state != TCP_LISTEN) { + local_bh_disable(); inet_ehash_nolisten(sk, osk, NULL); + local_bh_enable(); return 0; } WARN_ON(!sk_unhashed(sk)); @@ -667,11 +669,8 @@ int inet_hash(struct sock *sk) { int err = 0; - if (sk->sk_state != TCP_CLOSE) { - local_bh_disable(); + if (sk->sk_state != TCP_CLOSE) err = __inet_hash(sk, NULL); - local_bh_enable(); - } return err; } @@ -682,17 +681,20 @@ void inet_unhash(struct sock *sk) struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo; struct inet_listen_hashbucket *ilb = NULL; spinlock_t *lock; + bool state_listen; if (sk_unhashed(sk)) return; if (sk->sk_state == TCP_LISTEN) { + state_listen = true; ilb = &hashinfo->listening_hash[inet_sk_listen_hashfn(sk)]; - lock = &ilb->lock; + spin_lock(&ilb->lock); } else { + state_listen = false; lock = inet_ehash_lockp(hashinfo, sk->sk_hash); + spin_lock_bh(lock); } - spin_lock_bh(lock); if (sk_unhashed(sk)) goto unlock; @@ -705,7 +707,10 @@ void inet_unhash(struct sock *sk) __sk_nulls_del_node_init_rcu(sk); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); unlock: - spin_unlock_bh(lock); + if (state_listen) + spin_unlock(&ilb->lock); + else + spin_unlock_bh(lock); } EXPORT_SYMBOL_GPL(inet_unhash); diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index 55c290d556059..9bad345cba9a0 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -333,11 +333,8 @@ int inet6_hash(struct sock *sk) { int err = 0; - if (sk->sk_state != TCP_CLOSE) { - local_bh_disable(); + if (sk->sk_state != TCP_CLOSE) err = __inet_hash(sk, NULL); - local_bh_enable(); - } return err; } diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index b80c9b016b2be..c127debdc12e9 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #include #include "ieee80211_i.h" diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index c1343c028b767..62047e93e217b 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #include #include diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index f87d07736a140..7a627b2083936 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1258,7 +1258,7 @@ static struct Qdisc *qdisc_create(struct net_device *dev, rcu_assign_pointer(sch->stab, stab); } if (tca[TCA_RATE]) { - seqcount_t *running; + net_seqlock_t *running; err = -EOPNOTSUPP; if (sch->flags & TCQ_F_MQROOT) { diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 49eae93d1489d..512a39d6edecc 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -553,7 +553,11 @@ struct Qdisc noop_qdisc = { .ops = &noop_qdisc_ops, .q.lock = __SPIN_LOCK_UNLOCKED(noop_qdisc.q.lock), .dev_queue = &noop_netdev_queue, +#ifdef CONFIG_PREEMPT_RT + .running = __SEQLOCK_UNLOCKED(noop_qdisc.running), +#else .running = SEQCNT_ZERO(noop_qdisc.running), +#endif .busylock = __SPIN_LOCK_UNLOCKED(noop_qdisc.busylock), .gso_skb = { .next = (struct sk_buff *)&noop_qdisc.gso_skb, @@ -845,9 +849,15 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, lockdep_set_class(&sch->busylock, dev->qdisc_tx_busylock ?: &qdisc_tx_busylock); +#ifdef CONFIG_PREEMPT_RT + seqlock_init(&sch->running); + lockdep_set_class(&sch->running.lock, + dev->qdisc_running_key ?: &qdisc_running_key); +#else seqcount_init(&sch->running); lockdep_set_class(&sch->running, dev->qdisc_running_key ?: &qdisc_running_key); +#endif sch->ops = ops; sch->flags = ops->static_flags; diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index dcc50ae545506..e4a0dc8f8e40b 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -422,7 +422,7 @@ void svc_xprt_do_enqueue(struct svc_xprt *xprt) if (test_and_set_bit(XPT_BUSY, &xprt->xpt_flags)) return; - cpu = get_cpu(); + cpu = get_cpu_light(); pool = svc_pool_for_cpu(xprt->xpt_server, cpu); atomic_long_inc(&pool->sp_stats.packets); @@ -446,7 +446,7 @@ void svc_xprt_do_enqueue(struct svc_xprt *xprt) rqstp = NULL; out_unlock: rcu_read_unlock(); - put_cpu(); + put_cpu_light(); trace_svc_xprt_do_enqueue(xprt, rqstp); } EXPORT_SYMBOL_GPL(svc_xprt_do_enqueue); diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index d01ca1a184189..14059a9051b88 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -44,7 +44,7 @@ static void xfrm_state_gc_task(struct work_struct *work); */ static unsigned int xfrm_state_hashmax __read_mostly = 1 * 1024 * 1024; -static __read_mostly seqcount_t xfrm_state_hash_generation = SEQCNT_ZERO(xfrm_state_hash_generation); +static __read_mostly seqcount_spinlock_t xfrm_state_hash_generation; static struct kmem_cache *xfrm_state_cache __ro_after_init; static DECLARE_WORK(xfrm_state_gc_work, xfrm_state_gc_task); @@ -139,6 +139,11 @@ static void xfrm_hash_resize(struct work_struct *work) return; } + /* XXX - the locking which protects the sequence counter appears + * to be broken here. The sequence counter is global, but the + * spinlock used for the sequence counter write serialization is + * per network namespace... + */ spin_lock_bh(&net->xfrm.xfrm_state_lock); write_seqcount_begin(&xfrm_state_hash_generation); @@ -2666,6 +2671,8 @@ int __net_init xfrm_state_init(struct net *net) net->xfrm.state_num = 0; INIT_WORK(&net->xfrm.state_hash_work, xfrm_hash_resize); spin_lock_init(&net->xfrm.xfrm_state_lock); + seqcount_spinlock_init(&xfrm_state_hash_generation, + &net->xfrm.xfrm_state_lock); return 0; out_byspi: