diff options
233 files changed, 6554 insertions, 3201 deletions
diff --git a/arch/alpha/include/asm/spinlock_types.h b/arch/alpha/include/asm/spinlock_types.h index 1d5716bc060b..6883bc952d22 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 24804f11302d..4252af49eecb 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -32,6 +32,7 @@ config ARM select ARCH_OPTIONAL_KERNEL_RWX_DEFAULT if CPU_V7 select ARCH_SUPPORTS_ATOMIC_RMW select ARCH_SUPPORTS_HUGETLBFS if ARM_LPAE + select ARCH_SUPPORTS_RT if HAVE_POSIX_CPU_TIMERS_TASK_WORK select ARCH_USE_BUILTIN_BSWAP select ARCH_USE_CMPXCHG_LOCKREF select ARCH_USE_MEMTEST @@ -69,7 +70,7 @@ 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 @@ -110,6 +111,7 @@ 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 @@ -125,6 +127,7 @@ 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 5976958647fe..a37c0803954b 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 70d4cbc49ae1..b86418b4dfef 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 70993af22d80..024c65c3a0f2 100644 --- a/arch/arm/kernel/asm-offsets.c +++ b/arch/arm/kernel/asm-offsets.c @@ -43,6 +43,7 @@ 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 0ea8529a4872..fa0d155d21b3 100644 --- a/arch/arm/kernel/entry-armv.S +++ b/arch/arm/kernel/entry-armv.S @@ -206,11 +206,18 @@ __irq_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 @@ svc_preempt: 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 a3a38d0a4c85..f04ccf19ab1f 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 c7bb168b0d97..b943e2df9540 100644 --- a/arch/arm/kernel/smp.c +++ b/arch/arm/kernel/smp.c @@ -667,9 +667,7 @@ 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 da78740faf7b..07f79e533a29 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; @@ -479,6 +482,9 @@ 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 9f1d8566bbf9..4c36d75edb65 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -87,6 +87,7 @@ 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 @@ -192,6 +193,7 @@ 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 @@ -213,6 +215,7 @@ 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 e83f0982b99c..2545c17281e1 100644 --- a/arch/arm64/include/asm/preempt.h +++ b/arch/arm64/include/asm/preempt.h @@ -70,13 +70,36 @@ 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 diff --git a/arch/arm64/include/asm/spinlock_types.h b/arch/arm64/include/asm/spinlock_types.h index 18782f0c4721..6672b05350b4 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 <asm-generic/qspinlock_types.h> #include <asm-generic/qrwlock_types.h> diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h index 6623c99f0984..c55ccec33a5a 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 { @@ -67,6 +68,7 @@ int arch_dup_task_struct(struct task_struct *dst, #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 */ @@ -97,8 +99,10 @@ int arch_dup_task_struct(struct task_struct *dst, #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) @@ -107,6 +111,8 @@ int arch_dup_task_struct(struct task_struct *dst, _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 0cb34ccb6e73..fe19323aa44a 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 3513984a88bd..db926701ef59 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -572,9 +572,18 @@ 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 ad3dd34a83cf..9bf86cd7b605 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 @@ -1031,6 +1041,7 @@ 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; @@ -1043,7 +1054,7 @@ 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. @@ -1077,6 +1088,7 @@ 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 22899c86711a..eb7f8fa21e3f 100644 --- a/arch/arm64/kernel/signal.c +++ b/arch/arm64/kernel/signal.c @@ -916,7 +916,7 @@ 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 facf4d41d32a..58c8d904d609 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -750,7 +750,7 @@ 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); @@ -799,7 +799,7 @@ 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; } @@ -871,7 +871,7 @@ 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 19d233497ba5..de72fb23016d 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 6e345fefcdca..681408d6816f 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 088dd2afcfe4..95c4518680ca 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -152,6 +152,7 @@ config PPC select ARCH_STACKWALK 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_MEMTEST @@ -222,6 +223,7 @@ config PPC select HAVE_IOREMAP_PROT select HAVE_IRQ_EXIT_ON_IRQ_STACK select HAVE_IRQ_TIME_ACCOUNTING + select HAVE_POSIX_CPU_TIMERS_TASK_WORK if !KVM select HAVE_KERNEL_GZIP select HAVE_KERNEL_LZMA if DEFAULT_UIMAGE select HAVE_KERNEL_LZO if DEFAULT_UIMAGE @@ -238,6 +240,7 @@ config PPC select HAVE_PERF_EVENTS_NMI if PPC64 select HAVE_PERF_REGS select HAVE_PERF_USER_STACK_DUMP + select HAVE_PREEMPT_LAZY select HAVE_REGS_AND_STACK_ACCESS_API select HAVE_RELIABLE_STACKTRACE select HAVE_RSEQ diff --git a/arch/powerpc/include/asm/cmpxchg.h b/arch/powerpc/include/asm/cmpxchg.h index cf091c4c22e5..7371f7e23c35 100644 --- a/arch/powerpc/include/asm/cmpxchg.h +++ b/arch/powerpc/include/asm/cmpxchg.h @@ -5,7 +5,7 @@ #ifdef __KERNEL__ #include <linux/compiler.h> #include <asm/synch.h> -#include <linux/bug.h> +#include <linux/bits.h> #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 0f3cdd8faa95..d45561e9e6ba 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 03b3d010cbab..eec452e647b3 100644 --- a/arch/powerpc/include/asm/smp.h +++ b/arch/powerpc/include/asm/smp.h @@ -58,6 +58,7 @@ 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 c5d742f18021..cc6922a011ba 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 <asm-generic/qspinlock_types.h> #include <asm-generic/qrwlock_types.h> diff --git a/arch/powerpc/include/asm/stackprotector.h b/arch/powerpc/include/asm/stackprotector.h index 1c8460e23583..b1653c160bab 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 b4ec6c7dd72e..07df83231ec2 100644 --- a/arch/powerpc/include/asm/thread_info.h +++ b/arch/powerpc/include/asm/thread_info.h @@ -47,6 +47,8 @@ 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; @@ -93,6 +95,7 @@ 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 */ @@ -108,6 +111,7 @@ 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<<TIF_SYSCALL_TRACE) #define _TIF_SIGPENDING (1<<TIF_SIGPENDING) @@ -119,6 +123,7 @@ void arch_setup_new_exec(void); #define _TIF_PATCH_PENDING (1<<TIF_PATCH_PENDING) #define _TIF_SYSCALL_AUDIT (1<<TIF_SYSCALL_AUDIT) #define _TIF_SINGLESTEP (1<<TIF_SINGLESTEP) +#define _TIF_NEED_RESCHED_LAZY (1<<TIF_NEED_RESCHED_LAZY) #define _TIF_SECCOMP (1<<TIF_SECCOMP) #define _TIF_RESTOREALL (1<<TIF_RESTOREALL) #define _TIF_NOERROR (1<<TIF_NOERROR) @@ -132,10 +137,12 @@ void arch_setup_new_exec(void); _TIF_SYSCALL_EMU) #define _TIF_USER_WORK_MASK (_TIF_SIGPENDING | _TIF_NEED_RESCHED | \ + _TIF_NEED_RESCHED_LAZY | \ _TIF_NOTIFY_RESUME | _TIF_UPROBE | \ _TIF_RESTORE_TM | _TIF_PATCH_PENDING | \ _TIF_NOTIFY_SIGNAL) #define _TIF_PERSYSCALL_MASK (_TIF_RESTOREALL|_TIF_NOERROR) +#define _TIF_NEED_RESCHED_MASK (_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY) /* Bits in local_flags */ /* Don't move TLF_NAPPING without adjusting the code in entry_32.S */ diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index f633f09dc912..4d47c3fac81b 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -188,6 +188,7 @@ int main(void) OFFSET(TI_FLAGS, thread_info, flags); OFFSET(TI_LOCAL_FLAGS, thread_info, local_flags); OFFSET(TI_PREEMPT, thread_info, preempt_count); + OFFSET(TI_PREEMPT_LAZY, thread_info, preempt_lazy_count); #ifdef CONFIG_PPC64 OFFSET(DCACHEL1BLOCKSIZE, ppc64_caches, l1d.block_size); diff --git a/arch/powerpc/kernel/interrupt.c b/arch/powerpc/kernel/interrupt.c index e0938ba298f2..507dca866e1a 100644 --- a/arch/powerpc/kernel/interrupt.c +++ b/arch/powerpc/kernel/interrupt.c @@ -287,7 +287,7 @@ again: ti_flags = READ_ONCE(current_thread_info()->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 { /* @@ -376,7 +376,7 @@ again: 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) @@ -461,11 +461,15 @@ 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 ca58ad3b06da..024d5b8acf1b 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -588,6 +588,7 @@ static inline void check_stack_overflow(void) } } +#ifndef CONFIG_PREEMPT_RT static __always_inline void call_do_softirq(const void *sp) { /* Temporarily switch r1 to sp, call __do_softirq() then restore r1. */ @@ -606,6 +607,7 @@ static __always_inline void call_do_softirq(const void *sp) "r11", "r12" ); } +#endif static __always_inline void call_do_irq(struct pt_regs *regs, void *sp) { @@ -718,10 +720,12 @@ 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 7dd2ad3603ad..59402cc01eb9 100644 --- a/arch/powerpc/kernel/kgdb.c +++ b/arch/powerpc/kernel/kgdb.c @@ -20,6 +20,7 @@ #include <linux/signal.h> #include <linux/ptrace.h> #include <linux/kdebug.h> +#include <linux/console.h> #include <asm/current.h> #include <asm/processor.h> #include <asm/machdep.h> @@ -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/smp.c b/arch/powerpc/kernel/smp.c index df6b468976d5..35558e14dfb1 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 04090fde27c8..f4ec910aa585 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -170,7 +170,6 @@ 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(); @@ -260,12 +259,17 @@ 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 c9a8f4781a10..dc17d8903d4f 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 0196d0c211ac..899955be1cfe 100644 --- a/arch/powerpc/kexec/crash.c +++ b/arch/powerpc/kexec/crash.c @@ -312,9 +312,6 @@ 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 e45644657d49..b826174ce983 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/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index 0c55b991f665..b529370fb27a 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -24,6 +24,7 @@ #include <linux/of.h> #include <linux/iommu.h> #include <linux/rculist.h> +#include <linux/local_lock.h> #include <asm/io.h> #include <asm/prom.h> #include <asm/rtas.h> @@ -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/s390/include/asm/spinlock_types.h b/arch/s390/include/asm/spinlock_types.h index a2bbfd7df85f..f059d282e766 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; } arch_spinlock_t; diff --git a/arch/sh/include/asm/spinlock_types.h b/arch/sh/include/asm/spinlock_types.h index e82369f286a2..22ca9a98bbb8 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 ef0f0827cf57..2d3eca8fee01 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 c8848bb681a1..41fa1be980a3 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/x86/Kconfig b/arch/x86/Kconfig index 2db2bf999489..33c4ef85d71e 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -105,6 +105,7 @@ 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_MEMTEST select ARCH_USE_QUEUED_RWLOCKS @@ -229,6 +230,7 @@ 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 23bef08a8388..62cf3e4c06fb 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 562854c60808..ea0c5ab31da4 100644 --- a/arch/x86/include/asm/irq_stack.h +++ b/arch/x86/include/asm/irq_stack.h @@ -185,6 +185,7 @@ IRQ_CONSTRAINTS, regs, vector); \ } +#ifndef CONFIG_PREEMPT_RT #define ASM_CALL_SOFTIRQ \ "call %P[__func] \n" @@ -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 fe5efbcba824..ab8cb5fc2329 100644 --- a/arch/x86/include/asm/preempt.h +++ b/arch/x86/include/asm/preempt.h @@ -90,17 +90,48 @@ 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 diff --git a/arch/x86/include/asm/signal.h b/arch/x86/include/asm/signal.h index 6fd8410a3910..f3bf2f515edb 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 b6ffe58c70fa..e79e75ede951 100644 --- a/arch/x86/include/asm/stackprotector.h +++ b/arch/x86/include/asm/stackprotector.h @@ -50,7 +50,7 @@ */ static __always_inline void boot_init_stack_canary(void) { - u64 canary; + u64 canary = 0; u64 tsc; #ifdef CONFIG_X86_64 @@ -61,8 +61,14 @@ 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 de406d93b515..730d86e28f46 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 4fa0a4280895..6b59b0a7d7d8 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -80,11 +80,12 @@ EXPORT_SYMBOL_GPL(hv_remove_vmbus_handler); 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 571220ac8bea..d315d45b64fa 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 044902d5a3c4..e5dd6da78713 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 3a43a2dee658..55c446dc0d9b 100644 --- a/arch/x86/kernel/kgdb.c +++ b/arch/x86/kernel/kgdb.c @@ -32,6 +32,7 @@ #include <linux/kgdb.h> #include <linux/smp.h> #include <linux/nmi.h> +#include <linux/console.h> #include <linux/hw_breakpoint.h> #include <linux/uaccess.h> #include <linux/memory.h> @@ -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 1e11198f8993..b6c3394f2519 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -8193,6 +8193,14 @@ 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 64c9389254f1..dc846323b1cd 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 <asm-generic/qspinlock_types.h> #include <asm-generic/qrwlock_types.h> diff --git a/block/blk-mq.c b/block/blk-mq.c index 6dfa572ac1fc..3b63fb5b481f 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -1552,14 +1552,14 @@ 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 a1bea0f4baa8..5f8ca8c1f59c 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/base/node.c b/drivers/base/node.c index 2c36f61d30bc..9db297431b97 100644 --- a/drivers/base/node.c +++ b/drivers/base/node.c @@ -482,6 +482,7 @@ static DEVICE_ATTR(meminfo, 0444, node_read_meminfo, NULL); static ssize_t node_read_numastat(struct device *dev, struct device_attribute *attr, char *buf) { + fold_vm_numa_events(); return sysfs_emit(buf, "numa_hit %lu\n" "numa_miss %lu\n" @@ -489,12 +490,12 @@ static ssize_t node_read_numastat(struct device *dev, "interleave_hit %lu\n" "local_node %lu\n" "other_node %lu\n", - sum_zone_numa_state(dev->id, NUMA_HIT), - sum_zone_numa_state(dev->id, NUMA_MISS), - sum_zone_numa_state(dev->id, NUMA_FOREIGN), - sum_zone_numa_state(dev->id, NUMA_INTERLEAVE_HIT), - sum_zone_numa_state(dev->id, NUMA_LOCAL), - sum_zone_numa_state(dev->id, NUMA_OTHER)); + sum_zone_numa_event_state(dev->id, NUMA_HIT), + sum_zone_numa_event_state(dev->id, NUMA_MISS), + sum_zone_numa_event_state(dev->id, NUMA_FOREIGN), + sum_zone_numa_event_state(dev->id, NUMA_INTERLEAVE_HIT), + sum_zone_numa_event_state(dev->id, NUMA_LOCAL), + sum_zone_numa_event_state(dev->id, NUMA_OTHER)); } static DEVICE_ATTR(numastat, 0444, node_read_numastat, NULL); @@ -512,10 +513,11 @@ static ssize_t node_read_vmstat(struct device *dev, sum_zone_node_page_state(nid, i)); #ifdef CONFIG_NUMA - for (i = 0; i < NR_VM_NUMA_STAT_ITEMS; i++) + fold_vm_numa_events(); + for (i = 0; i < NR_VM_NUMA_EVENT_ITEMS; i++) len += sysfs_emit_at(buf, len, "%s %lu\n", numa_stat_name(i), - sum_zone_numa_state(nid, i)); + sum_zone_numa_event_state(nid, i)); #endif for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) { diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index cf8deecc39ef..5c7999ebc4e0 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 419a7e8281ee..561c7ba1421f 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 605969ed0f96..9bcaa6c99f69 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -1242,26 +1242,25 @@ 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 4ed6e660273a..c2bd0d40b5fc 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/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index 847f33ffc4ae..ae79c3300129 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_crtc.c b/drivers/gpu/drm/i915/display/intel_crtc.c index 39358076c05b..54d62d343f1a 100644 --- a/drivers/gpu/drm/i915/display/intel_crtc.c +++ b/drivers/gpu/drm/i915/display/intel_crtc.c @@ -425,7 +425,8 @@ void intel_pipe_update_start(const struct intel_crtc_state *new_crtc_state) */ intel_psr_wait_for_idle(new_crtc_state); - local_irq_disable(); + if (!IS_ENABLED(CONFIG_PREEMPT_RT)) + local_irq_disable(); crtc->debug.min_vbl = min; crtc->debug.max_vbl = max; @@ -450,11 +451,13 @@ 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); @@ -487,7 +490,8 @@ 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) @@ -566,7 +570,8 @@ 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 7c9af86fdb1e..4008080ebd9a 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_pm.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_pm.c @@ -84,9 +84,10 @@ 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; @@ -96,7 +97,8 @@ 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 783f25920d00..50478356591f 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -887,6 +887,7 @@ 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) @@ -951,6 +952,7 @@ 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 a4addcc64978..396b6598694d 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 <linux/stringify.h> #include <linux/types.h> #include <linux/tracepoint.h> @@ -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 1d03ec763604..c6f1cb30f94a 100644 --- a/drivers/gpu/drm/radeon/radeon_display.c +++ b/drivers/gpu/drm/radeon/radeon_display.c @@ -1814,6 +1814,7 @@ 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) @@ -1906,6 +1907,7 @@ 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 9416e09ebd58..4a5767a15544 100644 --- a/drivers/hv/hyperv_vmbus.h +++ b/drivers/hv/hyperv_vmbus.h @@ -18,6 +18,7 @@ #include <linux/atomic.h> #include <linux/hyperv.h> #include <linux/interrupt.h> +#include <linux/irq.h> #include "hv_trace.h" diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c index 92cb3f7d21d9..3fc06e5f2785 100644 --- a/drivers/hv/vmbus_drv.c +++ b/drivers/hv/vmbus_drv.c @@ -22,6 +22,7 @@ #include <linux/clockchips.h> #include <linux/cpu.h> #include <linux/sched/task_stack.h> +#include <linux/irq.h> #include <linux/delay.h> #include <linux/notifier.h> @@ -1339,6 +1340,8 @@ 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)) @@ -1383,7 +1386,7 @@ static void vmbus_isr(void) tasklet_schedule(&hv_cpu->msg_dpc); } - add_interrupt_randomness(vmbus_interrupt, 0); + add_interrupt_randomness(vmbus_interrupt, 0, ip); } static irqreturn_t vmbus_percpu_isr(int irq, void *dev_id) diff --git a/drivers/leds/trigger/Kconfig b/drivers/leds/trigger/Kconfig index b77a01bd27f4..aa74e2a05798 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 7d4ff8a5c55e..29055cdc9446 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -2217,8 +2217,9 @@ 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++; @@ -2277,7 +2278,8 @@ 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) @@ -7078,6 +7080,7 @@ 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 5c05acf20e1f..665fe138ab4f 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/scsi/fcoe/fcoe.c b/drivers/scsi/fcoe/fcoe.c index 89ec735929c3..9c1dc0767bb9 100644 --- a/drivers/scsi/fcoe/fcoe.c +++ b/drivers/scsi/fcoe/fcoe.c @@ -1452,11 +1452,11 @@ err2: 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 1756a0ac6f08..3a2cbf35ea3d 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 841000445b9a..26d661ddc950 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 6473361525d1..b52ba054a4da 100644 --- a/drivers/tty/serial/8250/8250.h +++ b/drivers/tty/serial/8250/8250.h @@ -132,12 +132,55 @@ 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; } @@ -146,7 +189,7 @@ 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 cae61d1ebec5..47dd23056271 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 fc65a2293ce9..d659e05c2e60 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 988bf6bcce42..bcd26d672539 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 fb65dc601b23..5bc734c70da4 100644 --- a/drivers/tty/serial/8250/8250_mtk.c +++ b/drivers/tty/serial/8250/8250_mtk.c @@ -218,12 +218,37 @@ 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 9422284bb3f3..253470fbd3c4 100644 --- a/drivers/tty/serial/8250/8250_port.c +++ b/drivers/tty/serial/8250/8250_port.c @@ -761,7 +761,7 @@ 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); @@ -1435,7 +1435,7 @@ 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); } @@ -1465,7 +1465,7 @@ 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); } @@ -2131,14 +2131,7 @@ 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); /* @@ -2151,7 +2144,7 @@ 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); } @@ -2454,7 +2447,7 @@ 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); @@ -2797,7 +2790,7 @@ 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; @@ -3263,7 +3256,7 @@ 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); @@ -3271,6 +3264,18 @@ 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 */ @@ -3292,6 +3297,32 @@ 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... @@ -3308,24 +3339,12 @@ 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); - - /* - * First save the IER then disable the interrupts - */ - ier = serial_port_in(port, UART_IER); + spin_lock_irqsave(&port->lock, flags); - 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))) { @@ -3339,7 +3358,9 @@ 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 @@ -3352,8 +3373,7 @@ 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 @@ -3365,8 +3385,7 @@ 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) @@ -3386,6 +3405,7 @@ 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'; @@ -3395,6 +3415,8 @@ 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 78682c12156a..401513bb0bb6 100644 --- a/drivers/tty/serial/amba-pl011.c +++ b/drivers/tty/serial/amba-pl011.c @@ -2199,18 +2199,24 @@ 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 @@ -2236,8 +2242,7 @@ 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 84e8158088cd..342005ed5ebf 100644 --- a/drivers/tty/serial/omap-serial.c +++ b/drivers/tty/serial/omap-serial.c @@ -1311,13 +1311,10 @@ 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 @@ -1346,8 +1343,7 @@ 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/fs/afs/dir_silly.c b/fs/afs/dir_silly.c index dae9a57d7ec0..9a6a0ec4d1fb 100644 --- a/fs/afs/dir_silly.c +++ b/fs/afs/dir_silly.c @@ -239,7 +239,7 @@ 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 63bfc533c9fb..a749570a3142 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 9508bd57a3bc..654b4c9d4f8b 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -2539,9 +2539,10 @@ 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(); } @@ -2549,26 +2550,30 @@ 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); @@ -2582,7 +2587,7 @@ 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)) { @@ -2610,7 +2615,7 @@ retry: } 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; @@ -2683,7 +2688,7 @@ 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 bc267832310c..3176913fae6c 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 78de5b5dc084..646fe09ba5ec 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -157,7 +157,7 @@ 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 79b0ff9b151e..4699d4a6038f 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -1605,7 +1605,7 @@ 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))) @@ -3127,7 +3127,7 @@ 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 670ba5250137..7336bb1037b8 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -14,6 +14,7 @@ #include <linux/mnt_namespace.h> #include <linux/user_namespace.h> #include <linux/namei.h> +#include <linux/hrtimer.h> #include <linux/security.h> #include <linux/cred.h> #include <linux/idr.h> @@ -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 1a6d2867fba4..2e67080475c5 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; @@ -1876,7 +1876,7 @@ 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 5fa11e1aca4c..984f26eb888c 100644 --- a/fs/nfs/unlink.c +++ b/fs/nfs/unlink.c @@ -13,7 +13,7 @@ #include <linux/sunrpc/clnt.h> #include <linux/nfs_fs.h> #include <linux/sched.h> -#include <linux/wait.h> +#include <linux/swait.h> #include <linux/namei.h> #include <linux/fsnotify.h> @@ -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 06150eb56a60..8c45129eca02 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -95,6 +95,7 @@ #include <linux/posix-timers.h> #include <linux/time_namespace.h> #include <linux/resctrl.h> +#include <linux/swait.h> #include <trace/events/oom.h> #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 dea0f5ee540c..8872fbf4803b 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -678,7 +678,7 @@ 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/include/asm-generic/softirq_stack.h b/include/asm-generic/softirq_stack.h index eceeecf6a5bd..d3e2d81656e0 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/console.h b/include/linux/console.h index 20874db50bc8..851daf13de0a 100644 --- a/include/linux/console.h +++ b/include/linux/console.h @@ -16,6 +16,19 @@ #include <linux/atomic.h> #include <linux/types.h> +#include <linux/printk.h> +#include <linux/seqlock.h> + +#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 9e23d33bb6f1..9f89d4887e35 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -108,7 +108,7 @@ 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 */ @@ -240,7 +240,7 @@ 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 edb5c186b0b7..3f49e65169c6 100644 --- a/include/linux/debug_locks.h +++ b/include/linux/debug_locks.h @@ -3,8 +3,7 @@ #define __LINUX_DEBUG_LOCKING_H #include <linux/atomic.h> -#include <linux/bug.h> -#include <linux/printk.h> +#include <linux/cache.h> struct task_struct; diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h index 2e2b8d6140ed..572fac3dd288 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 93eb43e002d9..a47dcfa53b83 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -699,7 +699,7 @@ 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 69bc86ea382c..76878b357ffa 100644 --- a/include/linux/hardirq.h +++ b/include/linux/hardirq.h @@ -116,7 +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) @@ -135,7 +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 7902c7d8b55f..4aa1031d3e4c 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 bb5e7b0a4274..7d4768c1ae3d 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -42,6 +42,7 @@ enum hrtimer_mode { HRTIMER_MODE_PINNED = 0x02, HRTIMER_MODE_SOFT = 0x04, HRTIMER_MODE_HARD = 0x08, + HRTIMER_MODE_CHILL = 0x10, HRTIMER_MODE_ABS_PINNED = HRTIMER_MODE_ABS | HRTIMER_MODE_PINNED, HRTIMER_MODE_REL_PINNED = HRTIMER_MODE_REL | HRTIMER_MODE_PINNED, @@ -124,6 +125,7 @@ struct hrtimer { u8 is_rel; u8 is_soft; u8 is_hard; + u8 is_chill; }; /** @@ -540,4 +542,10 @@ 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/irq_work.h b/include/linux/irq_work.h index ec2a47a81e42..dbbef9089789 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 df4651250785..aabd79e8e19a 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 600c10da321a..4b140938b03e 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/kgdb.h b/include/linux/kgdb.h index 392a3670944c..67197bbdcba8 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/local_lock_internal.h b/include/linux/local_lock_internal.h index ded90b097e6e..f39fb2806164 100644 --- a/include/linux/local_lock_internal.h +++ b/include/linux/local_lock_internal.h @@ -6,6 +6,8 @@ #include <linux/percpu-defs.h> #include <linux/lockdep.h> +#ifndef CONFIG_PREEMPT_RT + typedef struct { #ifdef CONFIG_DEBUG_LOCK_ALLOC struct lockdep_map dep_map; @@ -56,38 +58,98 @@ 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 */ +#define ll_preempt_disable() preempt_disable() +#define ll_preempt_enable() preempt_enable() +#define ll_local_irq_disable() local_irq_disable() +#define ll_local_irq_enable() local_irq_enable() +#define ll_local_irq_save(flags) local_irq_save(flags) +#define ll_local_irq_restore(flags) local_irq_restore(flags) + +#else /* !CONFIG_PREEMPT_RT */ + +/* + * The preempt RT mapping of local locks: a spinlock. + */ +typedef struct { + spinlock_t lock; +} local_lock_t; + +#define INIT_LOCAL_LOCK(lockname) { \ + __SPIN_LOCK_UNLOCKED((lockname).lock), \ + } + +#define __local_lock_init(l) \ +do { \ + spin_lock_init(&(l)->lock); \ +} while (0) + +static inline void local_lock_acquire(local_lock_t *l) +{ + spin_lock(&l->lock); +} + +static inline void local_lock_release(local_lock_t *l) +{ + spin_unlock(&l->lock); +} + +/* + * On RT enabled kernels the serialization is guaranteed by the spinlock in + * local_lock_t, so the only guarantee to make is to not leave the CPU. + */ +#define ll_preempt_disable() migrate_disable() +#define ll_preempt_enable() migrate_enable() +#define ll_local_irq_disable() migrate_disable() +#define ll_local_irq_enable() migrate_enable() + +#define ll_local_irq_save(flags) \ + do { \ + typecheck(unsigned long, flags); \ + flags = 0; \ + migrate_disable(); \ + } while (0) + +#define ll_local_irq_restore(flags) \ + do { \ + typecheck(unsigned long, flags); \ + (void)flags; \ + migrate_enable(); \ + } while (0) + +#endif /* CONFIG_PREEMPT_RT */ + #define __local_lock(lock) \ do { \ - preempt_disable(); \ + ll_preempt_disable(); \ local_lock_acquire(this_cpu_ptr(lock)); \ } while (0) #define __local_lock_irq(lock) \ do { \ - local_irq_disable(); \ + ll_local_irq_disable(); \ local_lock_acquire(this_cpu_ptr(lock)); \ } while (0) #define __local_lock_irqsave(lock, flags) \ do { \ - local_irq_save(flags); \ + ll_local_irq_save(flags); \ local_lock_acquire(this_cpu_ptr(lock)); \ } while (0) #define __local_unlock(lock) \ do { \ local_lock_release(this_cpu_ptr(lock)); \ - preempt_enable(); \ + ll_preempt_enable(); \ } while (0) #define __local_unlock_irq(lock) \ do { \ local_lock_release(this_cpu_ptr(lock)); \ - local_irq_enable(); \ + ll_local_irq_enable(); \ } while (0) #define __local_unlock_irqrestore(lock, flags) \ do { \ local_lock_release(this_cpu_ptr(lock)); \ - local_irq_restore(flags); \ + ll_local_irq_restore(flags); \ } while (0) diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 5043c0702c10..409376d4d7fa 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -12,6 +12,7 @@ #include <linux/completion.h> #include <linux/cpumask.h> #include <linux/uprobes.h> +#include <linux/rcupdate.h> #include <linux/page-flags-layout.h> #include <linux/workqueue.h> #include <linux/seqlock.h> @@ -569,6 +570,9 @@ 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/mmzone.h b/include/linux/mmzone.h index 0d53eba1c383..d7740c97b87e 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -20,6 +20,7 @@ #include <linux/atomic.h> #include <linux/mm_types.h> #include <linux/page-flags.h> +#include <linux/local_lock.h> #include <asm/page.h> /* Free memory management - zoned buddy allocator. */ @@ -134,10 +135,10 @@ enum numa_stat_item { NUMA_INTERLEAVE_HIT, /* interleaver preferred this zone */ NUMA_LOCAL, /* allocation from local node */ NUMA_OTHER, /* allocation from other node */ - NR_VM_NUMA_STAT_ITEMS + NR_VM_NUMA_EVENT_ITEMS }; #else -#define NR_VM_NUMA_STAT_ITEMS 0 +#define NR_VM_NUMA_EVENT_ITEMS 0 #endif enum zone_stat_item { @@ -337,24 +338,31 @@ enum zone_watermarks { #define high_wmark_pages(z) (z->_watermark[WMARK_HIGH] + z->watermark_boost) #define wmark_pages(z, i) (z->_watermark[i] + z->watermark_boost) +/* Fields and list protected by pagesets local_lock in page_alloc.c */ struct per_cpu_pages { int count; /* number of pages in the list */ int high; /* high watermark, emptying needed */ int batch; /* chunk size for buddy add/remove */ +#ifdef CONFIG_NUMA + int expire; /* When 0, remote pagesets are drained */ +#endif /* Lists of pages, one per migrate type stored on the pcp-lists */ struct list_head lists[MIGRATE_PCPTYPES]; }; -struct per_cpu_pageset { - struct per_cpu_pages pcp; -#ifdef CONFIG_NUMA - s8 expire; - u16 vm_numa_stat_diff[NR_VM_NUMA_STAT_ITEMS]; -#endif +struct per_cpu_zonestat { #ifdef CONFIG_SMP - s8 stat_threshold; s8 vm_stat_diff[NR_VM_ZONE_STAT_ITEMS]; + s8 stat_threshold; +#endif +#ifdef CONFIG_NUMA + /* + * Low priority inaccurate counters that are only folded + * on demand. Use a large type to avoid the overhead of + * folding during refresh_cpu_vm_stats. + */ + unsigned long vm_numa_event[NR_VM_NUMA_EVENT_ITEMS]; #endif }; @@ -484,7 +492,8 @@ struct zone { int node; #endif struct pglist_data *zone_pgdat; - struct per_cpu_pageset __percpu *pageset; + struct per_cpu_pages __percpu *per_cpu_pageset; + struct per_cpu_zonestat __percpu *per_cpu_zonestats; /* * the high and batch values are copied to individual pagesets for * faster access @@ -619,7 +628,7 @@ struct zone { ZONE_PADDING(_pad3_) /* Zone statistics */ atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS]; - atomic_long_t vm_numa_stat[NR_VM_NUMA_STAT_ITEMS]; + atomic_long_t vm_numa_event[NR_VM_NUMA_EVENT_ITEMS]; } ____cacheline_internodealigned_in_smp; enum pgdat_flags { diff --git a/include/linux/mutex.h b/include/linux/mutex.h index e19323521f9c..2cfc234a786d 100644 --- a/include/linux/mutex.h +++ b/include/linux/mutex.h @@ -20,9 +20,6 @@ #include <linux/osq_lock.h> #include <linux/debug_locks.h> -struct ww_class; -struct ww_acquire_ctx; - /* * Simple, straightforward mutexes with strict semantics: * @@ -51,9 +48,30 @@ struct ww_acquire_ctx; * - detects multi-task circular deadlocks and prints out all affected * locks and tasks (and only those tasks) */ -struct mutex { + +#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 + +/* + * Typedef _mutex_t for ww_mutex and core code to allow ww_mutex being + * built on the regular mutex code in RT kernels while mutex itself is + * substituted by a rt_mutex. + */ +#ifndef CONFIG_PREEMPT_RT +typedef struct mutex +#else +typedef struct __mutex +#endif +{ atomic_long_t owner; - spinlock_t wait_lock; + raw_spinlock_t wait_lock; #ifdef CONFIG_MUTEX_SPIN_ON_OWNER struct optimistic_spin_queue osq; /* Spinner MCS lock */ #endif @@ -64,44 +82,24 @@ struct mutex { #ifdef CONFIG_DEBUG_LOCK_ALLOC struct lockdep_map dep_map; #endif -}; +} _mutex_t; -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: - */ -struct mutex_waiter { - struct list_head list; - struct task_struct *task; - struct ww_acquire_ctx *ww_ctx; -#ifdef CONFIG_DEBUG_MUTEXES - void *magic; -#endif -}; +extern void __mutex_t_init(_mutex_t *lock, const char *name, + struct lock_class_key *key); +extern int _mutex_t_trylock(_mutex_t *lock); +extern bool _mutex_t_is_locked(_mutex_t *lock); #ifdef CONFIG_DEBUG_MUTEXES - -#define __DEBUG_MUTEX_INITIALIZER(lockname) \ +# define __DEBUG_MUTEX_INITIALIZER(lockname) \ , .magic = &lockname -extern void mutex_destroy(struct mutex *lock); - +extern void _mutex_t_destroy(_mutex_t *lock); #else - # define __DEBUG_MUTEX_INITIALIZER(lockname) - -static inline void mutex_destroy(struct mutex *lock) {} - +static inline void _mutex_t_destroy(_mutex_t *lock) {} #endif +#ifndef CONFIG_PREEMPT_RT /** * mutex_init - initialize the mutex * @mutex: the mutex to be initialized @@ -114,22 +112,17 @@ static inline void mutex_destroy(struct mutex *lock) {} do { \ static struct lock_class_key __key; \ \ - __mutex_init((mutex), #mutex, &__key); \ + __mutex_t_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_init(mutex, name, key) \ +do { \ + __mutex_t_init((mutex), name, key); \ +} while (0) #define __MUTEX_INITIALIZER(lockname) \ { .owner = ATOMIC_LONG_INIT(0) \ - , .wait_lock = __SPIN_LOCK_UNLOCKED(lockname.wait_lock) \ + , .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(lockname.wait_lock) \ , .wait_list = LIST_HEAD_INIT(lockname.wait_list) \ __DEBUG_MUTEX_INITIALIZER(lockname) \ __DEP_MAP_MUTEX_INITIALIZER(lockname) } @@ -137,8 +130,10 @@ do { \ #define DEFINE_MUTEX(mutexname) \ struct mutex mutexname = __MUTEX_INITIALIZER(mutexname) -extern void __mutex_init(struct mutex *lock, const char *name, - struct lock_class_key *key); +static __always_inline void mutex_destroy(struct mutex *lock) +{ + _mutex_t_destroy(lock); +} /** * mutex_is_locked - is the mutex locked @@ -146,7 +141,74 @@ extern void __mutex_init(struct mutex *lock, const char *name, * * Returns true if the mutex is locked, false if unlocked. */ -extern bool mutex_is_locked(struct mutex *lock); +static __always_inline bool mutex_is_locked(struct mutex *lock) +{ + return _mutex_t_is_locked(lock); +} + +/** + * mutex_trylock - try to acquire the mutex, without waiting + * @lock: the mutex to be acquired + * + * Try to acquire the mutex atomically. Returns 1 if the mutex + * has been acquired successfully, and 0 on contention. + * + * NOTE: this function follows the spin_trylock() convention, so + * it is negated from the down_trylock() return values! Be careful + * about this when converting semaphore users to mutexes. + * + * This function must not be used in interrupt context. The + * mutex must be released by the same task that acquired it. + */ +static __always_inline int mutex_trylock(struct mutex *lock) +{ + return _mutex_t_trylock(lock); +} + +#else /* !CONFIG_PREEMPT_RT */ +/* + * Preempt-RT variant based on rtmutexes. + */ +#include <linux/rtmutex.h> + +struct mutex { + struct rt_mutex rtmutex; +#ifdef CONFIG_DEBUG_LOCK_ALLOC + struct lockdep_map dep_map; +#endif +}; + +#define __MUTEX_INITIALIZER(mutexname) \ + { \ + .rtmutex = __RT_MUTEX_INITIALIZER(mutexname.rtmutex) \ + __DEP_MAP_MUTEX_INITIALIZER(mutexname) \ + } + +#define DEFINE_MUTEX(mutexname) \ + struct mutex mutexname = __MUTEX_INITIALIZER(mutexname) + +extern void __mutex_rt_init(struct mutex *lock, const char *name, + struct lock_class_key *key); +extern int mutex_trylock(struct mutex *lock); + +static inline void mutex_destroy(struct mutex *lock) { } + +#define mutex_is_locked(l) rt_mutex_is_locked(&(l)->rtmutex) + +#define mutex_init(mutex) \ +do { \ + static struct lock_class_key __key; \ + \ + rt_mutex_init(&(mutex)->rtmutex); \ + __mutex_rt_init((mutex), #mutex, &__key); \ +} while (0) + +#define __mutex_init(mutex, name, key) \ +do { \ + rt_mutex_init(&(mutex)->rtmutex); \ + __mutex_rt_init((mutex), name, key); \ +} while (0) +#endif /* CONFIG_PREEMPT_RT */ /* * See kernel/locking/mutex.c for detailed documentation of these APIs. @@ -186,13 +248,6 @@ extern void mutex_lock_io(struct mutex *lock); # define mutex_lock_io_nested(lock, subclass) mutex_lock_io(lock) #endif -/* - * NOTE: mutex_trylock() follows the spin_trylock() convention, - * not the down_trylock() convention! - * - * Returns 1 if the mutex has been acquired successfully, and 0 on contention. - */ -extern int mutex_trylock(struct mutex *lock); extern void mutex_unlock(struct mutex *lock); extern int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock); diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 5c73a91a8105..31d24f44acb5 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1691,7 +1691,7 @@ 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 2fb373a5c1ed..723bc2df6388 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 fa10acb8d6a4..2f86f84e9fc1 100644 --- a/include/linux/pid.h +++ b/include/linux/pid.h @@ -3,6 +3,7 @@ #define _LINUX_PID_H #include <linux/rculist.h> +#include <linux/atomic.h> #include <linux/wait.h> #include <linux/refcount.h> diff --git a/include/linux/preempt.h b/include/linux/preempt.h index 9881eac0698f..af39859f02ee 100644 --- a/include/linux/preempt.h +++ b/include/linux/preempt.h @@ -121,7 +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: @@ -170,6 +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() \ @@ -178,13 +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()) @@ -209,6 +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 { \ @@ -216,6 +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(); \ @@ -254,8 +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 @@ -274,10 +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; @@ -390,8 +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 fe7eb2351610..0cdd25b49fcc 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 f45b8be3e3c4..0e41d0527809 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 d31ecaf4fdd3..36a0e7226ec5 100644 --- a/include/linux/rbtree.h +++ b/include/linux/rbtree.h @@ -19,22 +19,11 @@ #include <linux/kernel.h> #include <linux/stddef.h> +#include <linux/rbtree_types.h> #include <linux/rcupdate.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; -}; - #define rb_parent(r) ((struct rb_node *)((r)->__rb_parent_color & ~3)) -#define RB_ROOT (struct rb_root) { NULL, } #define rb_entry(ptr, type, member) container_of(ptr, type, member) #define RB_EMPTY_ROOT(root) (READ_ONCE((root)->rb_node) == NULL) @@ -112,23 +101,6 @@ 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) */ #define rb_first_cached(root) (root)->rb_leftmost diff --git a/include/linux/rbtree_types.h b/include/linux/rbtree_types.h new file mode 100644 index 000000000000..45b6ecde3665 --- /dev/null +++ b/include/linux/rbtree_types.h @@ -0,0 +1,34 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef _LINUX_RBTREE_TYPES_H +#define _LINUX_RBTREE_TYPES_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; +}; + +#define RB_ROOT (struct rb_root) { NULL, } +#define RB_ROOT_CACHED (struct rb_root_cached) { {NULL, }, NULL } + +#endif diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 1199ffd305d1..a70da3f37df3 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 */ diff --git a/include/linux/rtmutex.h b/include/linux/rtmutex.h index d1672de9ca89..7bbee67720dc 100644 --- a/include/linux/rtmutex.h +++ b/include/linux/rtmutex.h @@ -14,8 +14,8 @@ #define __LINUX_RT_MUTEX_H #include <linux/linkage.h> -#include <linux/rbtree.h> -#include <linux/spinlock_types.h> +#include <linux/rbtree_types.h> +#include <linux/spinlock_types_raw.h> extern int max_lock_depth; /* for sysctl */ diff --git a/include/linux/rwbase_rt.h b/include/linux/rwbase_rt.h new file mode 100644 index 000000000000..78b62a01e301 --- /dev/null +++ b/include/linux/rwbase_rt.h @@ -0,0 +1,37 @@ +// SPDX-License-Identifier: GPL-2.0-only +#ifndef _LINUX_RW_BASE_RT_H +#define _LINUX_RW_BASE_RT_H + +#include <linux/rtmutex.h> +#include <linux/atomic.h> + +#define READER_BIAS (1U << 31) +#define WRITER_BIAS (1U << 30) + +struct rwbase_rt { + atomic_t readers; + struct rt_mutex rtmutex; +}; + +#define __RWBASE_INITIALIZER(name) \ +{ \ + .readers = ATOMIC_INIT(READER_BIAS), \ + .rtmutex = __RT_MUTEX_INITIALIZER(name.rtmutex), \ +} + +#define init_rwbase_rt(rwbase) \ + do { \ + rt_mutex_init(&(rwbase)->rtmutex); \ + atomic_set(&(rwbase)->readers, READER_BIAS); \ +} while (0) + +static __always_inline bool rw_base_is_locked(struct rwbase_rt *rwb) +{ + return atomic_read(&rwb->readers) != READER_BIAS; +} + +static __always_inline bool rw_base_is_contended(struct rwbase_rt *rwb) +{ + return atomic_read(&rwb->readers) > 0; +} +#endif diff --git a/include/linux/rwlock_rt.h b/include/linux/rwlock_rt.h new file mode 100644 index 000000000000..38048bf7d063 --- /dev/null +++ b/include/linux/rwlock_rt.h @@ -0,0 +1,140 @@ +// SPDX-License-Identifier: GPL-2.0-only +#ifndef __LINUX_RWLOCK_RT_H +#define __LINUX_RWLOCK_RT_H + +#ifndef __LINUX_SPINLOCK_RT_H +#error Do not include directly. Use spinlock.h +#endif + +#ifdef CONFIG_DEBUG_LOCK_ALLOC +extern void __rt_rwlock_init(rwlock_t *rwlock, const char *name, + struct lock_class_key *key); +#else +static inline void __rt_rwlock_init(rwlock_t *rwlock, char *name, + struct lock_class_key *key) +{ +} +#endif + +#define rwlock_init(rwl) \ +do { \ + static struct lock_class_key __key; \ + \ + init_rwbase_rt(&(rwl)->rwbase); \ + __rt_rwlock_init(rwl, #rwl, &__key); \ +} while (0) + +extern void rt_read_lock(rwlock_t *rwlock); +extern int rt_read_trylock(rwlock_t *rwlock); +extern void rt_read_unlock(rwlock_t *rwlock); +extern void rt_write_lock(rwlock_t *rwlock); +extern int rt_write_trylock(rwlock_t *rwlock); +extern void rt_write_unlock(rwlock_t *rwlock); + +static __always_inline void read_lock(rwlock_t *rwlock) +{ + rt_read_lock(rwlock); +} + +static __always_inline void read_lock_bh(rwlock_t *rwlock) +{ + local_bh_disable(); + rt_read_lock(rwlock); +} + +static __always_inline void read_lock_irq(rwlock_t *rwlock) +{ + rt_read_lock(rwlock); +} + +#define read_lock_irqsave(lock, flags) \ + do { \ + typecheck(unsigned long, flags); \ + rt_read_lock(lock); \ + flags = 0; \ + } while (0) + +#define read_trylock(lock) __cond_lock(lock, rt_read_trylock(lock)) + +static __always_inline void read_unlock(rwlock_t *rwlock) +{ + rt_read_unlock(rwlock); +} + +static __always_inline void read_unlock_bh(rwlock_t *rwlock) +{ + rt_read_unlock(rwlock); + local_bh_enable(); +} + +static __always_inline void read_unlock_irq(rwlock_t *rwlock) +{ + rt_read_unlock(rwlock); +} + +static __always_inline void read_unlock_irqrestore(rwlock_t *rwlock, + unsigned long flags) +{ + rt_read_unlock(rwlock); +} + +static __always_inline void write_lock(rwlock_t *rwlock) +{ + rt_write_lock(rwlock); +} + +static __always_inline void write_lock_bh(rwlock_t *rwlock) +{ + local_bh_disable(); + rt_write_lock(rwlock); +} + +static __always_inline void write_lock_irq(rwlock_t *rwlock) +{ + rt_write_lock(rwlock); +} + +#define write_lock_irqsave(lock, flags) \ + do { \ + typecheck(unsigned long, flags); \ + rt_write_lock(lock); \ + flags = 0; \ + } while (0) + +#define write_trylock(lock) __cond_lock(lock, rt_write_trylock(lock)) + +#define write_trylock_irqsave(lock, flags) \ +({ \ + int __locked; \ + \ + typecheck(unsigned long, flags); \ + flags = 0; \ + __locked = write_trylock(lock); \ + __locked; \ +}) + +static __always_inline void write_unlock(rwlock_t *rwlock) +{ + rt_write_unlock(rwlock); +} + +static __always_inline void write_unlock_bh(rwlock_t *rwlock) +{ + rt_write_unlock(rwlock); + local_bh_enable(); +} + +static __always_inline void write_unlock_irq(rwlock_t *rwlock) +{ + rt_write_unlock(rwlock); +} + +static __always_inline void write_unlock_irqrestore(rwlock_t *rwlock, + unsigned long flags) +{ + rt_write_unlock(rwlock); +} + +#define rwlock_is_contended(lock) (((void)(lock), 0)) + +#endif diff --git a/include/linux/rwlock_types.h b/include/linux/rwlock_types.h index 3bd03e18061c..243339e3e27c 100644 --- a/include/linux/rwlock_types.h +++ b/include/linux/rwlock_types.h @@ -1,9 +1,13 @@ #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 + +#ifndef CONFIG_PREEMPT_RT /* - * include/linux/rwlock_types.h - generic rwlock type definitions - * and initializers + * generic rwlock type definitions and initializers * * portions Copyright 2005, Red Hat, Inc., Ingo Molnar * Released under the General Public License (GPL). @@ -46,4 +50,35 @@ typedef struct { #define DEFINE_RWLOCK(x) rwlock_t x = __RW_LOCK_UNLOCKED(x) +#else /* !CONFIG_PREEMPT_RT */ + +#include <linux/rwbase_rt.h> + +typedef struct { + struct rwbase_rt rwbase; + atomic_t readers; +#ifdef CONFIG_DEBUG_LOCK_ALLOC + struct lockdep_map dep_map; +#endif +} rwlock_t; + +#ifdef CONFIG_DEBUG_LOCK_ALLOC +# define RW_DEP_MAP_INIT(lockname) .dep_map = { .name = #lockname } +#else +# define RW_DEP_MAP_INIT(lockname) +#endif + +#define __RW_LOCK_UNLOCKED(name) __RWLOCK_RT_INITIALIZER(name) + +#define DEFINE_RWLOCK(name) \ + rwlock_t name = __RW_LOCK_UNLOCKED(name) + +#define __RWLOCK_RT_INITIALIZER(name) \ +{ \ + .rwbase = __RWBASE_INITIALIZER(name), \ + RW_DEP_MAP_INIT(name) \ +} + +#endif /* CONFIG_PREEMPT_RT */ + #endif /* __LINUX_RWLOCK_TYPES_H */ diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h index a66038d88878..67a3face07b1 100644 --- a/include/linux/rwsem.h +++ b/include/linux/rwsem.h @@ -16,6 +16,9 @@ #include <linux/spinlock.h> #include <linux/atomic.h> #include <linux/err.h> + +#ifndef CONFIG_PREEMPT_RT + #ifdef CONFIG_RWSEM_SPIN_ON_OWNER #include <linux/osq_lock.h> #endif @@ -119,6 +122,61 @@ static inline int rwsem_is_contended(struct rw_semaphore *sem) return !list_empty(&sem->wait_list); } +#else /* !CONFIG_PREEMPT_RT */ + +#include <linux/rwbase_rt.h> + +struct rw_semaphore { + struct rwbase_rt rwbase; +#ifdef CONFIG_DEBUG_LOCK_ALLOC + struct lockdep_map dep_map; +#endif +}; + +#define __RWSEM_INITIALIZER(name) \ + { \ + .rwbase = __RWBASE_INITIALIZER(name), \ + RW_DEP_MAP_INIT(name) \ +} + +#define DECLARE_RWSEM(lockname) \ + struct rw_semaphore lockname = __RWSEM_INITIALIZER(lockname) + +#ifdef CONFIG_DEBUG_LOCK_ALLOC +extern void __rwsem_init(struct rw_semaphore *rwsem, const char *name, + struct lock_class_key *key); +#else +static inline void __rwsem_init(struct rw_semaphore *rwsem, const char *name, + struct lock_class_key *key) +{ +} +#endif + +#define init_rwsem(sem) \ +do { \ + static struct lock_class_key __key; \ + \ + init_rwbase_rt(&(sem)->rwbase); \ + __rwsem_init((sem), #sem, &__key); \ +} while (0) + +static __always_inline int rwsem_is_locked(struct rw_semaphore *sem) +{ + return rw_base_is_locked(&sem->rwbase); +} + +static __always_inline int rwsem_is_contended(struct rw_semaphore *sem) +{ + return rw_base_is_contended(&sem->rwbase); +} + +#endif /* CONFIG_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 32813c345115..efdbdf654876 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -95,7 +95,9 @@ struct task_group; #define TASK_WAKING 0x0200 #define TASK_NOLOAD 0x0400 #define TASK_NEW 0x0800 -#define TASK_STATE_MAX 0x1000 +/* RT specific auxilliary flag to mark RT lock waiters */ +#define TASK_RTLOCK_WAIT 0x1000 +#define TASK_STATE_MAX 0x2000 /* Convenience macros for the sake of set_current_state: */ #define TASK_KILLABLE (TASK_WAKEKILL | TASK_UNINTERRUPTIBLE) @@ -113,12 +115,8 @@ 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 /* @@ -151,6 +149,27 @@ struct task_group; current->state = (state_value); \ raw_spin_unlock_irqrestore(¤t->pi_lock, flags); \ } while (0) + + +#define current_save_and_set_rtlock_wait_state() \ + do { \ + raw_spin_lock(¤t->pi_lock); \ + current->saved_state = current->state; \ + current->saved_state_change = current->task_state_change;\ + current->task_state_change = _THIS_IP_; \ + current->state = TASK_RTLOCK_WAIT; \ + raw_spin_unlock(¤t->pi_lock); \ + } while (0); + +#define current_restore_rtlock_saved_state() \ + do { \ + raw_spin_lock(¤t->pi_lock); \ + current->task_state_change = current->saved_state_change;\ + current->state = current->saved_state; \ + current->saved_state = TASK_RUNNING; \ + raw_spin_unlock(¤t->pi_lock); \ + } while (0); + #else /* * set_current_state() includes a barrier so that the write of current->state @@ -209,6 +228,47 @@ struct task_group; raw_spin_unlock_irqrestore(¤t->pi_lock, flags); \ } while (0) +/* + * PREEMPT_RT specific variants for "sleeping" spin/rwlocks + * + * RT's spin/rwlock substitutions are state preserving. The state of the + * task when blocking on the lock is saved in task_struct::saved_state and + * restored after the lock has been acquired. These operations are + * serialized by task_struct::pi_lock against try_to_wake_up(). Any non RT + * lock related wakeups while the task is blocked on the lock are + * redirected to operate on task_struct::saved_state to ensure that these + * are not dropped. On restore task_struct::saved_state is set to + * TASK_RUNNING so any wakeup attempt redirected to saved_state will fail. + * + * The lock operation looks like this: + * + * current_save_and_set_rtlock_wait_state(); + * for (;;) { + * if (try_lock()) + * break; + * raw_spin_unlock_irq(&lock->wait_lock); + * schedule_rtlock(); + * raw_spin_lock_irq(&lock->wait_lock); + * set_current_state(TASK_RTLOCK_WAIT); + * } + * current_restore_rtlock_saved_state(); + */ +#define current_save_and_set_rtlock_wait_state() \ + do { \ + raw_spin_lock(¤t->pi_lock); \ + current->saved_state = current->state; \ + current->state = TASK_RTLOCK_WAIT; \ + raw_spin_unlock(¤t->pi_lock); \ + } while (0); + +#define current_restore_rtlock_saved_state() \ + do { \ + raw_spin_lock(¤t->pi_lock); \ + current->state = current->saved_state; \ + current->saved_state = TASK_RUNNING; \ + raw_spin_unlock(¤t->pi_lock); \ + } while (0); + #endif /* Task command name length: */ @@ -226,6 +286,9 @@ extern long schedule_timeout_idle(long timeout); asmlinkage void schedule(void); extern void schedule_preempt_disabled(void); asmlinkage void preempt_schedule_irq(void); +#ifdef CONFIG_PREEMPT_RT + extern void schedule_rtlock(void); +#endif extern int __must_check io_schedule_prepare(void); extern void io_schedule_finish(int token); @@ -665,6 +728,11 @@ struct task_struct { /* -1 unrunnable, 0 runnable, >0 stopped: */ volatile long state; +#ifdef CONFIG_PREEMPT_RT + /* saved state for "spinlock sleepers" */ + long saved_state; +#endif + /* * This begins the randomizable portion of task_struct. Only * scheduling-critical items should be added above here. @@ -1002,6 +1070,10 @@ struct task_struct { /* 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; @@ -1347,6 +1419,9 @@ struct task_struct { struct kmap_ctrl kmap_ctrl; #ifdef CONFIG_DEBUG_ATOMIC_SLEEP unsigned long task_state_change; +# ifdef CONFIG_PREEMPT_RT + unsigned long saved_state_change; +# endif #endif int pagefault_disabled; #ifdef CONFIG_MMU @@ -1887,6 +1962,118 @@ 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 + +#ifdef CONFIG_PREEMPT_RT +static inline bool task_match_saved_state(struct task_struct *p, long match_state) +{ + return p->saved_state == match_state; +} + +static inline bool task_is_traced(struct task_struct *task) +{ + bool traced = false; + + /* 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); + return traced; +} + +static inline bool task_is_stopped_or_traced(struct task_struct *task) +{ + bool traced_stopped = false; + unsigned long flags; + + raw_spin_lock_irqsave(&task->pi_lock, flags); + + if (task->state & (__TASK_STOPPED | __TASK_TRACED)) + traced_stopped = true; + else if (task->saved_state & (__TASK_STOPPED | __TASK_TRACED)) + traced_stopped = true; + + raw_spin_unlock_irqrestore(&task->pi_lock, flags); + return traced_stopped; +} + +#else + +static inline bool task_match_saved_state(struct task_struct *p, long match_state) +{ + return false; +} + +static inline bool task_is_traced(struct task_struct *task) +{ + return task->state & __TASK_TRACED; +} + +static inline bool task_is_stopped_or_traced(struct task_struct *task) +{ + return task->state & (__TASK_STOPPED | __TASK_TRACED); +} +#endif + +static inline bool task_match_state_or_saved(struct task_struct *p, + long match_state) +{ + if (p->state == match_state) + return true; + + return task_match_saved_state(p, match_state); +} + +static inline bool task_match_state_lock(struct task_struct *p, + long match_state) +{ + bool match; + + raw_spin_lock_irq(&p->pi_lock); + match = task_match_state_or_saved(p, match_state); + raw_spin_unlock_irq(&p->pi_lock); + + return match; +} + /* * 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 e24b1fe348e3..52ecb2c11c18 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/wake_q.h b/include/linux/sched/wake_q.h index 26a2013ac39c..06cd8fb2f409 100644 --- a/include/linux/sched/wake_q.h +++ b/include/linux/sched/wake_q.h @@ -42,8 +42,11 @@ struct wake_q_head { #define WAKE_Q_TAIL ((struct wake_q_node *) 0x01) -#define DEFINE_WAKE_Q(name) \ - struct wake_q_head name = { WAKE_Q_TAIL, &name.first } +#define WAKE_Q_HEAD_INITIALIZER(name) \ + { WAKE_Q_TAIL, &name.first } + +#define DEFINE_WAKE_Q(name) \ + struct wake_q_head name = WAKE_Q_HEAD_INITIALIZER(name) static inline void wake_q_init(struct wake_q_head *head) { diff --git a/include/linux/serial_8250.h b/include/linux/serial_8250.h index 9e655055112d..ffef674deda7 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 <linux/atomic.h> #include <linux/serial_core.h> #include <linux/serial_reg.h> #include <linux/platform_device.h> @@ -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 d82b6f396588..12b2e41d8f47 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/skbuff.h b/include/linux/skbuff.h index dbf820a50a39..7be803493474 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -296,6 +296,7 @@ struct sk_buff_head { __u32 qlen; spinlock_t lock; + raw_spinlock_t raw_lock; }; struct sk_buff; @@ -1906,6 +1907,12 @@ 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/slub_def.h b/include/linux/slub_def.h index dcde82a4434c..b5bcac29b979 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -10,6 +10,7 @@ #include <linux/kfence.h> #include <linux/kobject.h> #include <linux/reciprocal_div.h> +#include <linux/local_lock.h> enum stat_item { ALLOC_FASTPATH, /* Allocation from cpu slab */ @@ -41,6 +42,7 @@ enum stat_item { NR_SLUB_STAT_ITEMS }; struct kmem_cache_cpu { + local_lock_t lock; /* Protects the fields below except stat */ void **freelist; /* Pointer to next available object */ unsigned long tid; /* Globally unique transaction id */ struct page *page; /* The slab from which we are allocating */ diff --git a/include/linux/smp.h b/include/linux/smp.h index 510519e8a1eb..7ac9fdb5ad09 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -268,6 +268,9 @@ 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 79897841a2cc..23925a6c489b 100644 --- a/include/linux/spinlock.h +++ b/include/linux/spinlock.h @@ -12,6 +12,8 @@ * asm/spinlock_types.h: contains the arch_spinlock_t/arch_rwlock_t and the * initializers * + * linux/spinlock_types_raw: + * The raw types and initializers * linux/spinlock_types.h: * defines the generic type and initializers * @@ -31,6 +33,8 @@ * contains the generic, simplified UP spinlock type. * (which is an empty structure on non-debug builds) * + * linux/spinlock_types_raw: + * The raw RT types and initializers * linux/spinlock_types.h: * defines the generic type and initializers * @@ -308,8 +312,10 @@ static inline void do_raw_spin_unlock(raw_spinlock_t *lock) __releases(lock) 1 : ({ local_irq_restore(flags); 0; }); \ }) -/* Include rwlock functions */ +#ifndef CONFIG_PREEMPT_RT +/* Include rwlock functions for !RT */ #include <linux/rwlock.h> +#endif /* * Pull the _spin_*()/_read_*()/_write_*() functions/declarations: @@ -320,6 +326,9 @@ static inline void do_raw_spin_unlock(raw_spinlock_t *lock) __releases(lock) # include <linux/spinlock_api_up.h> #endif +/* Non PREEMPT_RT kernel map to raw spinlocks */ +#ifndef CONFIG_PREEMPT_RT + /* * Map the spin_lock functions to the raw variants for PREEMPT_RT=n */ @@ -454,6 +463,10 @@ static __always_inline int spin_is_contended(spinlock_t *lock) #define assert_spin_locked(lock) assert_raw_spin_locked(&(lock)->rlock) +#else /* !CONFIG_PREEMPT_RT */ +# include <linux/spinlock_rt.h> +#endif /* CONFIG_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 19a9be9d97ee..51bf88c84133 100644 --- a/include/linux/spinlock_api_smp.h +++ b/include/linux/spinlock_api_smp.h @@ -187,6 +187,9 @@ static inline int __raw_spin_trylock_bh(raw_spinlock_t *lock) return 0; } +/* PREEMPT_RT has it's own rwlock implementation */ +#ifndef CONFIG_PREEMPT_RT #include <linux/rwlock_api_smp.h> +#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 000000000000..8ce04c07e944 --- /dev/null +++ b/include/linux/spinlock_rt.h @@ -0,0 +1,151 @@ +// 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 + +#ifdef CONFIG_DEBUG_LOCK_ALLOC +extern void __rt_spin_lock_init(spinlock_t *lock, const char *name, + struct lock_class_key *key); +#else +static inline void __rt_spin_lock_init(spinlock_t *lock, const char *name, + struct lock_class_key *key) +{ +} +#endif + +#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 rt_spin_lock(spinlock_t *lock); +extern void rt_spin_lock_nested(spinlock_t *lock, int subclass); +extern void rt_spin_lock_nest_lock(spinlock_t *lock, struct lockdep_map *nest_lock); +extern void rt_spin_unlock(spinlock_t *lock); +extern void rt_spin_lock_unlock(spinlock_t *lock); +extern int rt_spin_trylock_bh(spinlock_t *lock); +extern int rt_spin_trylock(spinlock_t *lock); + +static __always_inline void spin_lock(spinlock_t *lock) +{ + rt_spin_lock(lock); +} + +#ifdef CONFIG_LOCKDEP +# define __spin_lock_nested(lock, subclass) \ + rt_spin_lock_nested(lock, subclass) + +# define __spin_lock_nest_lock(lock, nest_lock) \ + do { \ + typecheck(struct lockdep_map *, &(nest_lock)->dep_map); \ + rt_spin_lock_nest_lock(lock, &(nest_lock)->dep_map); \ + } while (0) +# define __spin_lock_irqsave_nested(lock, flags, subclass) \ + do { \ + typecheck(unsigned long, flags); \ + flags = 0; \ + __spin_lock_nested(lock, subclass); \ + } while (0) + +#else + /* + * Always evaluate the 'subclass' argument to avoid that the compiler + * warns about set-but-not-used variables when building with + * CONFIG_DEBUG_LOCK_ALLOC=n and with W=1. + */ +# 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_irqsave_nested(lock, flags, subclass) \ + spin_lock_irqsave(((void)(subclass), (lock)), flags) +#endif + +#define spin_lock_nested(lock, subclass) \ + __spin_lock_nested(lock, subclass) + +#define spin_lock_nest_lock(lock, nest_lock) \ + __spin_lock_nest_lock(lock, nest_lock) + +#define spin_lock_irqsave_nested(lock, flags, subclass) \ + __spin_lock_irqsave_nested(lock, flags, subclass) + +static __always_inline void spin_lock_bh(spinlock_t *lock) +{ + /* Investigate: Drop bh when blocking ? */ + local_bh_disable(); + rt_spin_lock(lock); +} + +static __always_inline void spin_lock_irq(spinlock_t *lock) +{ + rt_spin_lock(lock); +} + +#define spin_lock_irqsave(lock, flags) \ + do { \ + typecheck(unsigned long, flags); \ + flags = 0; \ + spin_lock(lock); \ + } while (0) + +static __always_inline void spin_unlock(spinlock_t *lock) +{ + rt_spin_unlock(lock); +} + +static __always_inline void spin_unlock_bh(spinlock_t *lock) +{ + rt_spin_unlock(lock); + local_bh_enable(); +} + +static __always_inline void spin_unlock_irq(spinlock_t *lock) +{ + rt_spin_unlock(lock); +} + +static __always_inline void spin_unlock_irqrestore(spinlock_t *lock, + unsigned long flags) +{ + spin_unlock(lock); +} + +#define spin_trylock(lock) \ + __cond_lock(lock, rt_spin_trylock(lock)) + +#define spin_trylock_bh(lock) \ + __cond_lock(lock, rt_spin_trylock_bh(lock)) + +#define spin_trylock_irq(lock) \ + __cond_lock(lock, rt_spin_trylock(lock)) + +#define __spin_trylock_irqsave(lock, flags) \ +({ \ + int __locked; \ + \ + typecheck(unsigned long, flags); \ + flags = 0; \ + __locked = spin_trylock(lock); \ + __locked; \ +}) + +#define spin_trylock_irqsave(lock, flags) \ + __cond_lock(lock, __spin_trylock_irqsave(lock, flags)) + +#define spin_is_contended(lock) (((void)(lock), 0)) + +static inline int spin_is_locked(spinlock_t *lock) +{ + return rt_mutex_is_locked(&lock->lock); +} + +#define assert_spin_locked(lock) BUG_ON(!spin_is_locked(lock)) + +#include <linux/rwlock_rt.h> + +#endif diff --git a/include/linux/spinlock_types.h b/include/linux/spinlock_types.h index b981caafe8bf..98d498f9e4fc 100644 --- a/include/linux/spinlock_types.h +++ b/include/linux/spinlock_types.h @@ -9,24 +9,7 @@ * Released under the General Public License (GPL). */ -#if defined(CONFIG_SMP) -# include <asm/spinlock_types.h> -#else -# include <linux/spinlock_types_up.h> -#endif - -#include <linux/lockdep_types.h> - -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; +#include <linux/spinlock_types_raw.h> #define SPINLOCK_MAGIC 0xdead4ead @@ -68,6 +51,9 @@ typedef struct raw_spinlock { #define DEFINE_RAW_SPINLOCK(x) raw_spinlock_t x = __RAW_SPIN_LOCK_UNLOCKED(x) +#ifndef CONFIG_PREEMPT_RT + +/* Non PREEMPT_RT kernels map spinlock to raw_spinlock */ typedef struct spinlock { union { struct raw_spinlock rlock; @@ -96,6 +82,29 @@ typedef struct spinlock { #define DEFINE_SPINLOCK(x) spinlock_t x = __SPIN_LOCK_UNLOCKED(x) +#else /* !CONFIG_PREEMPT_RT */ + +/* PREEMPT_RT kernels map spinlock to rt_mutex */ +#include <linux/rtmutex.h> + +typedef struct spinlock { + struct rt_mutex lock; +#ifdef CONFIG_DEBUG_LOCK_ALLOC + struct lockdep_map dep_map; +#endif +} spinlock_t; + +#define __SPIN_LOCK_UNLOCKED(name) \ + { \ + .lock = __RT_MUTEX_INITIALIZER(name.lock), \ + SPIN_DEP_MAP_INIT(name) \ + } + +#define DEFINE_SPINLOCK(name) \ + spinlock_t name = __SPIN_LOCK_UNLOCKED(name) + +#endif /* CONFIG_PREEMPT_RT */ + #include <linux/rwlock_types.h> #endif /* __LINUX_SPINLOCK_TYPES_H */ diff --git a/include/linux/spinlock_types_raw.h b/include/linux/spinlock_types_raw.h new file mode 100644 index 000000000000..1d4a180e983d --- /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 <linux/types.h> + +#if defined(CONFIG_SMP) +# include <asm/spinlock_types.h> +#else +# include <linux/spinlock_types_up.h> +#endif + +#include <linux/lockdep_types.h> + +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/thread_info.h b/include/linux/thread_info.h index 157762db9d4b..6cf0fcc3e126 100644 --- a/include/linux/thread_info.h +++ b/include/linux/thread_info.h @@ -162,7 +162,17 @@ 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 ad413b382a3c..415fb02dd13f 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 e81856c0ba13..66eb968a09d4 100644 --- a/include/linux/u64_stats_sync.h +++ b/include/linux/u64_stats_sync.h @@ -66,7 +66,7 @@ #include <linux/seqlock.h> 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 3299cd69e4ca..81f001e71a31 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) @@ -138,34 +142,27 @@ static inline void vm_events_fold_cpu(int cpu) * Zone and node-based page accounting with per cpu differentials. */ extern atomic_long_t vm_zone_stat[NR_VM_ZONE_STAT_ITEMS]; -extern atomic_long_t vm_numa_stat[NR_VM_NUMA_STAT_ITEMS]; extern atomic_long_t vm_node_stat[NR_VM_NODE_STAT_ITEMS]; +extern atomic_long_t vm_numa_event[NR_VM_NUMA_EVENT_ITEMS]; #ifdef CONFIG_NUMA -static inline void zone_numa_state_add(long x, struct zone *zone, - enum numa_stat_item item) +static inline void zone_numa_event_add(long x, struct zone *zone, + enum numa_stat_item item) { - atomic_long_add(x, &zone->vm_numa_stat[item]); - atomic_long_add(x, &vm_numa_stat[item]); + atomic_long_add(x, &zone->vm_numa_event[item]); + atomic_long_add(x, &vm_numa_event[item]); } -static inline unsigned long global_numa_state(enum numa_stat_item item) +static inline unsigned long zone_numa_event_state(struct zone *zone, + enum numa_stat_item item) { - long x = atomic_long_read(&vm_numa_stat[item]); - - return x; + return atomic_long_read(&zone->vm_numa_event[item]); } -static inline unsigned long zone_numa_state_snapshot(struct zone *zone, - enum numa_stat_item item) +static inline unsigned long +global_numa_event_state(enum numa_stat_item item) { - long x = atomic_long_read(&zone->vm_numa_stat[item]); - int cpu; - - for_each_online_cpu(cpu) - x += per_cpu_ptr(zone->pageset, cpu)->vm_numa_stat_diff[item]; - - return x; + return atomic_long_read(&vm_numa_event[item]); } #endif /* CONFIG_NUMA */ @@ -236,7 +233,7 @@ static inline unsigned long zone_page_state_snapshot(struct zone *zone, #ifdef CONFIG_SMP int cpu; for_each_online_cpu(cpu) - x += per_cpu_ptr(zone->pageset, cpu)->vm_stat_diff[item]; + x += per_cpu_ptr(zone->per_cpu_zonestats, cpu)->vm_stat_diff[item]; if (x < 0) x = 0; @@ -245,18 +242,38 @@ static inline unsigned long zone_page_state_snapshot(struct zone *zone, } #ifdef CONFIG_NUMA -extern void __inc_numa_state(struct zone *zone, enum numa_stat_item item); +/* See __count_vm_event comment on why raw_cpu_inc is used. */ +static inline void +__count_numa_event(struct zone *zone, enum numa_stat_item item) +{ + struct per_cpu_zonestat __percpu *pzstats = zone->per_cpu_zonestats; + + raw_cpu_inc(pzstats->vm_numa_event[item]); +} + +static inline void +__count_numa_events(struct zone *zone, enum numa_stat_item item, long delta) +{ + struct per_cpu_zonestat __percpu *pzstats = zone->per_cpu_zonestats; + + raw_cpu_add(pzstats->vm_numa_event[item], delta); +} + extern unsigned long sum_zone_node_page_state(int node, enum zone_stat_item item); -extern unsigned long sum_zone_numa_state(int node, enum numa_stat_item item); +extern unsigned long sum_zone_numa_event_state(int node, enum numa_stat_item item); extern unsigned long node_page_state(struct pglist_data *pgdat, enum node_stat_item item); extern unsigned long node_page_state_pages(struct pglist_data *pgdat, enum node_stat_item item); +extern void fold_vm_numa_events(void); #else #define sum_zone_node_page_state(node, item) global_zone_page_state(item) #define node_page_state(node, item) global_node_page_state(item) #define node_page_state_pages(node, item) global_node_page_state_pages(item) +static inline void fold_vm_numa_events(void) +{ +} #endif /* CONFIG_NUMA */ #ifdef CONFIG_SMP @@ -291,7 +308,7 @@ struct ctl_table; int vmstat_refresh(struct ctl_table *, int write, void *buffer, size_t *lenp, loff_t *ppos); -void drain_zonestat(struct zone *zone, struct per_cpu_pageset *); +void drain_zonestat(struct zone *zone, struct per_cpu_zonestat *); int calculate_pressure_threshold(struct zone *zone); int calculate_normal_threshold(struct zone *zone); @@ -399,7 +416,7 @@ static inline void cpu_vm_stats_fold(int cpu) { } static inline void quiet_vmstat(void) { } static inline void drain_zonestat(struct zone *zone, - struct per_cpu_pageset *pset) { } + struct per_cpu_zonestat *pzstats) { } #endif /* CONFIG_SMP */ static inline void __mod_zone_freepage_state(struct zone *zone, int nr_pages, @@ -428,7 +445,7 @@ static inline const char *numa_stat_name(enum numa_stat_item item) static inline const char *node_stat_name(enum node_stat_item item) { return vmstat_text[NR_VM_ZONE_STAT_ITEMS + - NR_VM_NUMA_STAT_ITEMS + + NR_VM_NUMA_EVENT_ITEMS + item]; } @@ -440,7 +457,7 @@ static inline const char *lru_list_name(enum lru_list lru) static inline const char *writeback_stat_name(enum writeback_stat_item item) { return vmstat_text[NR_VM_ZONE_STAT_ITEMS + - NR_VM_NUMA_STAT_ITEMS + + NR_VM_NUMA_EVENT_ITEMS + NR_VM_NODE_STAT_ITEMS + item]; } @@ -449,7 +466,7 @@ static inline const char *writeback_stat_name(enum writeback_stat_item item) static inline const char *vm_event_name(enum vm_event_item item) { return vmstat_text[NR_VM_ZONE_STAT_ITEMS + - NR_VM_NUMA_STAT_ITEMS + + NR_VM_NUMA_EVENT_ITEMS + NR_VM_NODE_STAT_ITEMS + NR_VM_WRITEBACK_STAT_ITEMS + item]; diff --git a/include/linux/wait.h b/include/linux/wait.h index 6598ae35e1b5..172efca327e9 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -10,6 +10,7 @@ #include <asm/current.h> #include <uapi/linux/wait.h> +#include <linux/atomic.h> typedef struct wait_queue_entry wait_queue_entry_t; diff --git a/include/linux/ww_mutex.h b/include/linux/ww_mutex.h index b77f39f319ad..4f56ec47c698 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 { + _mutex_t 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; @@ -74,7 +82,7 @@ struct ww_acquire_ctx { static inline void ww_mutex_init(struct ww_mutex *lock, struct ww_class *ww_class) { - __mutex_init(&lock->base, ww_class->mutex_name, &ww_class->mutex_key); + __mutex_t_init(&lock->base, ww_class->mutex_name, &ww_class->mutex_key); lock->ctx = NULL; #ifdef CONFIG_DEBUG_MUTEXES lock->ww_class = ww_class; @@ -322,7 +330,7 @@ extern void ww_mutex_unlock(struct ww_mutex *lock); */ static inline int __must_check ww_mutex_trylock(struct ww_mutex *lock) { - return mutex_trylock(&lock->base); + return _mutex_t_trylock(&lock->base); } /*** @@ -335,7 +343,7 @@ static inline int __must_check ww_mutex_trylock(struct ww_mutex *lock) */ static inline void ww_mutex_destroy(struct ww_mutex *lock) { - mutex_destroy(&lock->base); + _mutex_t_destroy(&lock->base); } /** @@ -346,7 +354,7 @@ static inline void ww_mutex_destroy(struct ww_mutex *lock) */ static inline bool ww_mutex_is_locked(struct ww_mutex *lock) { - return mutex_is_locked(&lock->base); + return _mutex_t_is_locked(&lock->base); } #endif diff --git a/include/net/gen_stats.h b/include/net/gen_stats.h index 1424e02cef90..163f8415e5db 100644 --- a/include/net/gen_stats.h +++ b/include/net/gen_stats.h @@ -6,6 +6,7 @@ #include <linux/socket.h> #include <linux/rtnetlink.h> #include <linux/pkt_sched.h> +#include <net/net_seq_lock.h> /* 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 000000000000..67710bace741 --- /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 57710303908c..c6fec32c661d 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -10,6 +10,7 @@ #include <linux/percpu.h> #include <linux/dynamic_queue_limits.h> #include <linux/list.h> +#include <net/net_seq_lock.h> #include <linux/refcount.h> #include <linux/workqueue.h> #include <linux/mutex.h> @@ -101,7 +102,7 @@ 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; @@ -142,7 +143,11 @@ 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) @@ -203,17 +208,35 @@ nolock_empty: } 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_); +#endif return true; } 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); @@ -585,7 +608,7 @@ 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 a61c92066c2e..6ca28e2268ba 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -977,6 +977,7 @@ 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 @@ -1870,6 +1871,7 @@ 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 @@ -1890,6 +1892,7 @@ 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 @@ -1955,7 +1958,7 @@ 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 a1cbc0ffe9e1..bdc5545570cd 100644 --- a/init/main.c +++ b/init/main.c @@ -1531,6 +1531,12 @@ 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) { /* @@ -1556,6 +1562,7 @@ 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 3de8fd11873b..4198f0273ecd 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 416017301660..c3ccb459ed97 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 diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index adb5190c4429..920ff974f662 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 03527f518dfb..a04c91b91cf5 100644 --- a/kernel/cgroup/rstat.c +++ b/kernel/cgroup/rstat.c @@ -156,8 +156,9 @@ 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; @@ -169,7 +170,7 @@ 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 4708aec492df..8a073198c4e8 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 6735ac36b718..539a2f0dc89d 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/entry/common.c b/kernel/entry/common.c index bf16395b9e13..d8bedab935b2 100644 --- a/kernel/entry/common.c +++ b/kernel/entry/common.c @@ -159,9 +159,17 @@ 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); @@ -389,7 +397,7 @@ 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/fork.c b/kernel/fork.c index 5ffbfa7ddcfa..e8fd80d51564 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -42,6 +42,7 @@ #include <linux/mmu_notifier.h> #include <linux/fs.h> #include <linux/mm.h> +#include <linux/kprobes.h> #include <linux/vmacache.h> #include <linux/nsproxy.h> #include <linux/capability.h> @@ -289,7 +290,7 @@ static inline void free_thread_stack(struct task_struct *tsk) return; } - vfree_atomic(tsk->stack); + vfree(tsk->stack); return; } #endif @@ -693,6 +694,19 @@ 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; @@ -734,6 +748,15 @@ 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); diff --git a/kernel/futex.c b/kernel/futex.c index 408cad5e8968..c2565c3dddcd 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -197,6 +197,8 @@ struct futex_pi_state { * @rt_waiter: rt_waiter storage for use with requeue_pi * @requeue_pi_key: the requeue_pi target futex key * @bitset: bitset for the optional bitmasked wakeup + * @requeue_state: State field for futex_requeue_pi() + * @requeue_wait: RCU wait for futex_requeue_pi() (RT only) * * We use this hashed waitqueue, instead of a normal wait_queue_entry_t, so * we can wake only the relevant ones (hashed queues may be shared). @@ -219,6 +221,10 @@ struct futex_q { struct rt_mutex_waiter *rt_waiter; union futex_key *requeue_pi_key; u32 bitset; + atomic_t requeue_state; +#ifdef CONFIG_PREEMPT_RT + struct rcuwait requeue_wait; +#endif } __randomize_layout; static const struct futex_q futex_q_init = { @@ -1354,7 +1360,7 @@ static int lock_pi_update_atomic(u32 __user *uaddr, u32 uval, u32 newval) * - 1 - acquired the lock; * - <0 - error * - * The hb->lock and futex_key refs shall be held by the caller. + * The hb->lock must be held by the caller. * * @exiting is only set when the return value is -EBUSY. If so, this holds * a refcount on the exiting task on return and the caller needs to drop it @@ -1493,11 +1499,11 @@ static void mark_wake_futex(struct wake_q_head *wake_q, struct futex_q *q) */ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_pi_state *pi_state) { + DEFINE_RT_MUTEX_WAKE_Q_HEAD(wqh); u32 curval, newval; struct rt_mutex_waiter *top_waiter; struct task_struct *new_owner; bool postunlock = false; - DEFINE_WAKE_Q(wake_q); int ret = 0; top_waiter = rt_mutex_top_waiter(&pi_state->pi_mutex); @@ -1549,14 +1555,14 @@ 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, &wqh); } out_unlock: raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock); if (postunlock) - rt_mutex_postunlock(&wake_q); + rt_mutex_postunlock(&wqh); return ret; } @@ -1796,6 +1802,158 @@ void requeue_futex(struct futex_q *q, struct futex_hash_bucket *hb1, q->key = *key2; } +/* + * On PREEMPT_RT, the hash bucket lock is a 'sleeping' spinlock with an + * underlying rtmutex. The task which is about to be requeued could have + * just woken up (timeout, signal). After the wake up the task has to + * acquire hash bucket lock, which is held by the requeue code. As a task + * can only be blocked on _ONE_ rtmutex at a time, the proxy lock blocking + * and the hash bucket lock blocking would collide and corrupt state. + * + * On !PREEMPT_RT this is not a problem and everything could be serialized + * on hash bucket lock, but aside of having the benefit of common code, + * this allows to avoid doing the requeue when the task is already on the + * way out and taking the hash bucket lock of the original uaddr1 when the + * requeue has been completed. + * + * The following state transitions are valid: + * + * On the waiter side: + * Q_REQUEUE_PI_NONE -> Q_REQUEUE_PI_IGNORE + * Q_REQUEUE_PI_IN_PROGRESS -> Q_REQUEUE_PI_WAIT + * + * On the requeue side: + * Q_REQUEUE_PI_NONE -> Q_REQUEUE_PI_INPROGRESS + * Q_REQUEUE_PI_IN_PROGRESS -> Q_REQUEUE_PI_DONE/LOCKED + * Q_REQUEUE_PI_IN_PROGRESS -> Q_REQUEUE_PI_NONE (requeue failed) + * Q_REQUEUE_PI_WAIT -> Q_REQUEUE_PI_DONE/LOCKED + * Q_REQUEUE_PI_WAIT -> Q_REQUEUE_PI_IGNORE (requeue failed) + * + * The requeue side ignores a waiter with state Q_REQUEUE_PI_IGNORE as this + * signals that the waiter is already on the way out. It also means that + * the waiter is still on the 'wait' futex, i.e. uaddr1. + * + * The waiter side signals early wakeup to the requeue side either through + * setting state to Q_REQUEUE_PI_IGNORE or to Q_REQUEUE_PI_WAIT depending + * on the current state. In case of Q_REQUEUE_PI_IGNORE it can immediately + * proceed to take the hash bucket lock of uaddr1. If it set state to WAIT, + * which means the wakeup is interleaving with a requeue in progress it has + * to wait for the requeue side to change the state. Either to DONE/LOCKED + * or to IGNORE. DONE/LOCKED means the waiter q is now on the uaddr2 futex + * and either blocked (DONE) or has acquired it (LOCKED). IGNORE is set by + * the requeue side when the requeue attempt failed via deadlock detection + * and therefore the waiter q is still on the uaddr1 futex. + */ +enum { + Q_REQUEUE_PI_NONE = 0, + Q_REQUEUE_PI_IGNORE, + Q_REQUEUE_PI_IN_PROGRESS, + Q_REQUEUE_PI_WAIT, + Q_REQUEUE_PI_DONE, + Q_REQUEUE_PI_LOCKED, +}; + +static inline bool futex_requeue_pi_prepare(struct futex_q *q, + struct futex_pi_state *pi_state) +{ + int cur, res, new; + + /* + * Set state to Q_REQUEUE_PI_IN_PROGRESS unless an early wakeup has + * already set Q_REQUEUE_PI_IGNORE to signal that requeue should + * ignore the waiter. + */ + for (cur = atomic_read(&q->requeue_state);; cur = res) { + if (cur == Q_REQUEUE_PI_IGNORE) + return false; + + /* + * futex_proxy_trylock_atomic() might have set it to + * IN_PROGRESS and a interleaved early wake to WAIT. + * + * It was considered to have an extra state for that + * trylock, but that would just add more conditionals + * all over the place for a dubious value. + */ + if (cur != Q_REQUEUE_PI_NONE) + break; + + new = Q_REQUEUE_PI_IN_PROGRESS; + res = atomic_cmpxchg(&q->requeue_state, cur, new); + if (likely(cur == res)) + break; + } + q->pi_state = pi_state; + return true; +} + +static inline void futex_requeue_pi_complete(struct futex_q *q, int locked) +{ + int cur, res, new; + + for (cur = atomic_read(&q->requeue_state);; cur = res) { + if (locked >= 0) { + /* Requeue succeeded. Set DONE or LOCKED */ + new = Q_REQUEUE_PI_DONE + locked; + } else if (cur == Q_REQUEUE_PI_IN_PROGRESS) { + /* Deadlock, no early wakeup interleave */ + new = Q_REQUEUE_PI_NONE; + } else { + /* Deadlock, early wakeup interleave. */ + new = Q_REQUEUE_PI_IGNORE; + } + + res = atomic_cmpxchg(&q->requeue_state, cur, new); + if (likely(cur == res)) + break; + } + +#ifdef CONFIG_PREEMPT_RT + /* If the waiter interleaved with the requeue let it know */ + if (unlikely(cur == Q_REQUEUE_PI_WAIT)) + rcuwait_wake_up(&q->requeue_wait); +#endif +} + +static inline int futex_requeue_pi_wakeup_sync(struct futex_q *q) +{ + int cur, new, res; + + for (cur = atomic_read(&q->requeue_state);; cur = res) { + /* Is requeue done already? */ + if (cur >= Q_REQUEUE_PI_DONE) + break; + + /* + * If not done, then tell the requeue code to either ignore + * the waiter or to wake it up once the requeue is done. + */ + new = !cur ? Q_REQUEUE_PI_IGNORE : Q_REQUEUE_PI_WAIT; + res = atomic_cmpxchg(&q->requeue_state, cur, new); + if (likely(cur == res)) + break; + } + + /* If the requeue was in progress, wait for it to complete */ + if (cur == Q_REQUEUE_PI_IN_PROGRESS) { +#ifdef CONFIG_PREEMPT_RT + rcuwait_wait_event(&q->requeue_wait, + atomic_read(&q->requeue_state) != Q_REQUEUE_PI_WAIT, + TASK_UNINTERRUPTIBLE); +#else + while (atomic_read(&q->requeue_state) == Q_REQUEUE_PI_WAIT) + cpu_relax(); +#endif + } + + /* + * Requeue is now either prohibited or complete. Reread state + * because during the wait above it might have changed. Nothing + * will modify q->requeue_state after this point. + */ + return atomic_read(&q->requeue_state); +} + /** * requeue_pi_wake_futex() - Wake a task that acquired the lock during requeue * @q: the futex_q @@ -1823,6 +1981,8 @@ void requeue_pi_wake_futex(struct futex_q *q, union futex_key *key, q->lock_ptr = &hb->lock; + /* Signal locked state to the waiter */ + futex_requeue_pi_complete(q, 1); wake_up_state(q->task, TASK_NORMAL); } @@ -1882,10 +2042,18 @@ futex_proxy_trylock_atomic(u32 __user *pifutex, struct futex_hash_bucket *hb1, if (!top_waiter) return 0; + /* Ensure that this is a waiter sitting in futex_wait_requeue_pi() */ + if (!top_waiter->rt_waiter || top_waiter->pi_state) + ret = -EINVAL; + /* Ensure we requeue to the expected futex. */ if (!match_futex(top_waiter->requeue_pi_key, key2)) return -EINVAL; + /* Ensure that this does not race against an early wakeup */ + if (!futex_requeue_pi_prepare(top_waiter, NULL)) + return -EAGAIN; + /* * Try to take the lock for top_waiter. Set the FUTEX_WAITERS bit in * the contended case or if set_waiters is 1. The pi_state is returned @@ -1895,8 +2063,22 @@ futex_proxy_trylock_atomic(u32 __user *pifutex, struct futex_hash_bucket *hb1, ret = futex_lock_pi_atomic(pifutex, hb2, key2, ps, top_waiter->task, exiting, set_waiters); if (ret == 1) { + /* Dequeue, wake up and update top_waiter::requeue_state */ requeue_pi_wake_futex(top_waiter, key2, hb2); return vpid; + } else if (ret < 0) { + /* Rewind top_waiter::requeue_state */ + futex_requeue_pi_complete(top_waiter, ret); + } else { + /* + * futex_lock_pi_atomic() did not acquire the user space + * futex, but managed to establish the proxy lock and pi + * state. top_waiter::requeue_state cannot be fixed up here + * because the waiter is not enqueued on the rtmutex + * yet. This is handled at the callsite depending on the + * result of rt_mutex_start_proxy_lock() which is + * guaranteed to be reached with this function returning 0. + */ } return ret; } @@ -1956,15 +2138,27 @@ static int futex_requeue(u32 __user *uaddr1, unsigned int flags, */ if (refill_pi_state_cache()) return -ENOMEM; + /* - * requeue_pi must wake as many tasks as it can, up to nr_wake - * + nr_requeue, since it acquires the rt_mutex prior to - * returning to userspace, so as to not leave the rt_mutex with - * waiters and no owner. However, second and third wake-ups - * cannot be predicted as they involve race conditions with the - * first wake and a fault while looking up the pi_state. Both - * pthread_cond_signal() and pthread_cond_broadcast() should - * use nr_wake=1. + * futex_requeue() allows the caller to define the number + * of waiters to wake up via the @nr_wake argument. With + * REQUEUE_PI waking up more than one waiter is creating + * more problems than it solves. Waking up a waiter makes + * only sense if the PI futex @uaddr2 is uncontended as + * this allows the requeue code to acquire the futex + * @uaddr2 before waking the waiter. The waiter can then + * return to user space without further action. A secondary + * wakeup would just make the futex_wait_requeue_pi() + * handling more complex because that code would have to + * look up pi_state and do more or less all the handling + * which the requeue code has to do for the to be requeued + * waiters. So restrict the number of waiters to wake to + * one and only wake it up when the PI futex is + * uncontended. Otherwise requeue it and let the unlock of + * the PI futex handle the wakeup. + * + * All REQUEUE_PI users, e.g. pthread_cond_signal() and + * pthread_cond_broadcast() must use nr_wake=1. */ if (nr_wake != 1) return -EINVAL; @@ -2025,6 +2219,8 @@ retry_private: * intend to requeue waiters, force setting the FUTEX_WAITERS * bit. We force this here where we are able to easily handle * faults rather in the requeue loop below. + * + * Updates topwaiter::requeue_state if a top waiter exists. */ ret = futex_proxy_trylock_atomic(uaddr2, hb1, hb2, &key1, &key2, &pi_state, @@ -2038,6 +2234,27 @@ retry_private: * vpid of the top waiter task. * If the lock was not taken, we have pi_state and an initial * refcount on it. In case of an error we have nothing. + * + * The top waiter's requeue_state is up to date: + * + * - If the lock was acquired atomically (ret > 0), then + * the state is Q_REQUEUE_PI_LOCKED. No matter whether + * the below lookup_pi_state() fails or not requeue_state + * is correct because that waiter is dequeued and woken + * up and nothing can hold it up. + * + * - If the trylock failed with an error (ret < 0) then + * the state is either Q_REQUEUE_PI_NONE, i.e. "nothing + * happened", or Q_REQUEUE_PI_IGNORE when there was an + * interleaved early wakeup. + * + * - If the trylock did not succeed (ret == 0) then the + * state is either Q_REQUEUE_PI_IN_PROGRESS or + * Q_REQUEUE_PI_WAIT if an early wakeup interleaved. + * This will be cleaned up in the loop below, which + * cannot fail because futex_proxy_trylock_atomic() did + * the same sanity checks for requeue_pi as the loop + * below does. */ if (ret > 0) { WARN_ON(pi_state); @@ -2063,7 +2280,10 @@ retry_private: /* We hold a reference on the pi state. */ break; - /* If the above failed, then pi_state is NULL */ + /* + * If the above failed, then pi_state is NULL and + * waiter::requeue_state is correct. + */ case -EFAULT: double_unlock_hb(hb1, hb2); hb_waiters_dec(hb2); @@ -2115,18 +2335,17 @@ retry_private: break; } - /* - * Wake nr_wake waiters. For requeue_pi, if we acquired the - * lock, we already woke the top_waiter. If not, it will be - * woken by futex_unlock_pi(). - */ - if (++task_count <= nr_wake && !requeue_pi) { - mark_wake_futex(&wake_q, this); + /* Plain futexes just wake or requeue and are done */ + if (!requeue_pi) { + if (++task_count <= nr_wake) + mark_wake_futex(&wake_q, this); + else + requeue_futex(this, hb1, hb2, &key2); continue; } /* Ensure we requeue to the expected futex for requeue_pi. */ - if (requeue_pi && !match_futex(this->requeue_pi_key, &key2)) { + if (!match_futex(this->requeue_pi_key, &key2)) { ret = -EINVAL; break; } @@ -2134,48 +2353,61 @@ retry_private: /* * Requeue nr_requeue waiters and possibly one more in the case * of requeue_pi if we couldn't acquire the lock atomically. + * + * Prepare the waiter to take the rt_mutex. Take a refcount + * on the pi_state and store the pointer in the futex_q + * object of the waiter. */ - if (requeue_pi) { + get_pi_state(pi_state); + + /* Don't requeue when the waiter is already on the way out. */ + if (!futex_requeue_pi_prepare(this, pi_state)) { /* - * Prepare the waiter to take the rt_mutex. Take a - * refcount on the pi_state and store the pointer in - * the futex_q object of the waiter. + * Early woken waiter signaled that it is on the + * way out. Drop the pi_state reference and try the + * next waiter. @this->pi_state is still NULL. */ - get_pi_state(pi_state); - this->pi_state = pi_state; - ret = rt_mutex_start_proxy_lock(&pi_state->pi_mutex, - this->rt_waiter, - this->task); - if (ret == 1) { - /* - * We got the lock. We do neither drop the - * refcount on pi_state nor clear - * this->pi_state because the waiter needs the - * pi_state for cleaning up the user space - * value. It will drop the refcount after - * doing so. - */ - requeue_pi_wake_futex(this, &key2, hb2); - continue; - } else if (ret) { - /* - * rt_mutex_start_proxy_lock() detected a - * potential deadlock when we tried to queue - * that waiter. Drop the pi_state reference - * which we took above and remove the pointer - * to the state from the waiters futex_q - * object. - */ - this->pi_state = NULL; - put_pi_state(pi_state); - /* - * We stop queueing more waiters and let user - * space deal with the mess. - */ - break; - } + put_pi_state(pi_state); + continue; + } + + ret = rt_mutex_start_proxy_lock(&pi_state->pi_mutex, + this->rt_waiter, + this->task); + + if (ret == 1) { + /* + * We got the lock. We do neither drop the refcount + * on pi_state nor clear this->pi_state because the + * waiter needs the pi_state for cleaning up the + * user space value. It will drop the refcount + * after doing so. this::requeue_state is updated + * in the wakeup as well. + */ + requeue_pi_wake_futex(this, &key2, hb2); + task_count++; + } else if (!ret) { + /* Waiter is queued, move it to hb2 */ + requeue_futex(this, hb1, hb2, &key2); + futex_requeue_pi_complete(this, 0); + task_count++; + } else { + /* + * rt_mutex_start_proxy_lock() detected a potential + * deadlock when we tried to queue that waiter. + * Drop the pi_state reference which we took above + * and remove the pointer to the state from the + * waiters futex_q object. + */ + this->pi_state = NULL; + put_pi_state(pi_state); + futex_requeue_pi_complete(this, ret); + /* + * We stop queueing more waiters and let user space + * deal with the mess. + */ + break; } - requeue_futex(this, hb1, hb2, &key2); } /* @@ -2617,8 +2849,7 @@ static void futex_wait_queue_me(struct futex_hash_bucket *hb, struct futex_q *q, * * Setup the futex_q and locate the hash_bucket. Get the futex value and * compare it with the expected value. Handle atomic faults internally. - * Return with the hb lock held and a q.key reference on success, and unlocked - * with no q.key reference on failure. + * Return with the hb lock held on success, and unlocked on failure. * * Return: * - 0 - uaddr contains val and hb has been locked; @@ -3075,27 +3306,22 @@ pi_faulted: } /** - * handle_early_requeue_pi_wakeup() - Detect early wakeup on the initial futex + * handle_early_requeue_pi_wakeup() - Handle early wakeup on the initial futex * @hb: the hash_bucket futex_q was original enqueued on * @q: the futex_q woken while waiting to be requeued - * @key2: the futex_key of the requeue target futex * @timeout: the timeout associated with the wait (NULL if none) * - * Detect if the task was woken on the initial futex as opposed to the requeue - * target futex. If so, determine if it was a timeout or a signal that caused - * the wakeup and return the appropriate error code to the caller. Must be - * called with the hb lock held. + * Determine the cause for the early wakeup. * * Return: - * - 0 = no early wakeup detected; - * - <0 = -ETIMEDOUT or -ERESTARTNOINTR + * -EWOULDBLOCK or -ETIMEDOUT or -ERESTARTNOINTR */ static inline int handle_early_requeue_pi_wakeup(struct futex_hash_bucket *hb, - struct futex_q *q, union futex_key *key2, + struct futex_q *q, struct hrtimer_sleeper *timeout) { - int ret = 0; + int ret; /* * With the hb lock held, we avoid races while we process the wakeup. @@ -3104,22 +3330,21 @@ int handle_early_requeue_pi_wakeup(struct futex_hash_bucket *hb, * It can't be requeued from uaddr2 to something else since we don't * support a PI aware source futex for requeue. */ - if (!match_futex(&q->key, key2)) { - WARN_ON(q->lock_ptr && (&hb->lock != q->lock_ptr)); - /* - * We were woken prior to requeue by a timeout or a signal. - * Unqueue the futex_q and determine which it was. - */ - plist_del(&q->list, &hb->chain); - hb_waiters_dec(hb); + WARN_ON_ONCE(&hb->lock != q->lock_ptr); - /* Handle spurious wakeups gracefully */ - ret = -EWOULDBLOCK; - if (timeout && !timeout->task) - ret = -ETIMEDOUT; - else if (signal_pending(current)) - ret = -ERESTARTNOINTR; - } + /* + * We were woken prior to requeue by a timeout or a signal. + * Unqueue the futex_q and determine which it was. + */ + plist_del(&q->list, &hb->chain); + hb_waiters_dec(hb); + + /* Handle spurious wakeups gracefully */ + ret = -EWOULDBLOCK; + if (timeout && !timeout->task) + ret = -ETIMEDOUT; + else if (signal_pending(current)) + ret = -ERESTARTNOINTR; return ret; } @@ -3172,6 +3397,7 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, struct futex_hash_bucket *hb; union futex_key key2 = FUTEX_KEY_INIT; struct futex_q q = futex_q_init; + struct rt_mutex *pi_mutex; int res, ret; if (!IS_ENABLED(CONFIG_FUTEX_PI)) @@ -3221,32 +3447,22 @@ 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; - - /* - * 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. - */ + switch (futex_requeue_pi_wakeup_sync(&q)) { + case Q_REQUEUE_PI_IGNORE: + /* The waiter is still on uaddr1 */ + spin_lock(&hb->lock); + ret = handle_early_requeue_pi_wakeup(hb, &q, to); + spin_unlock(&hb->lock); + break; - /* - * Check if the requeue code acquired the second futex for us and do - * any pertinent fixup. - */ - if (!q.rt_waiter) { + case Q_REQUEUE_PI_LOCKED: + /* The requeue acquired the lock */ if (q.pi_state && (q.pi_state->owner != current)) { spin_lock(q.lock_ptr); ret = fixup_owner(uaddr2, &q, true); /* - * Drop the reference to the pi state which - * the requeue_pi() code acquired for us. + * 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); @@ -3256,18 +3472,14 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, */ ret = ret < 0 ? ret : 0; } - } else { - struct rt_mutex *pi_mutex; + break; - /* - * We have been woken up by futex_unlock_pi(), a timeout, or a - * signal. futex_unlock_pi() will not destroy the lock_ptr nor - * the pi_state. - */ - WARN_ON(!q.pi_state); + case Q_REQUEUE_PI_DONE: + /* Requeue completed. Current is 'pi_blocked_on' the rtmutex */ pi_mutex = &q.pi_state->pi_mutex; ret = rt_mutex_wait_proxy_lock(pi_mutex, to, &rt_waiter); + /* Current is not longer pi_blocked_on */ spin_lock(q.lock_ptr); if (ret && !rt_mutex_cleanup_proxy_lock(pi_mutex, &rt_waiter)) ret = 0; @@ -3287,17 +3499,21 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, unqueue_me_pi(&q); spin_unlock(q.lock_ptr); - } - if (ret == -EINTR) { - /* - * We've already been requeued, but cannot restart by calling - * futex_lock_pi() directly. We could restart this syscall, but - * it would detect that the user space "val" changed and return - * -EWOULDBLOCK. Save the overhead of the restart and return - * -EWOULDBLOCK directly. - */ - ret = -EWOULDBLOCK; + if (ret == -EINTR) { + /* + * We've already been requeued, but cannot restart + * by calling futex_lock_pi() directly. We could + * restart this syscall, but it would detect that + * the user space "val" changed and return + * -EWOULDBLOCK. Save the overhead of the restart + * and return -EWOULDBLOCK directly. + */ + ret = -EWOULDBLOCK; + } + break; + default: + BUG(); } out: diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c index 762a928e18f9..7929fcdb7817 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 4c14356543d9..5770a50ced1e 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -1229,6 +1229,8 @@ 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; @@ -1249,6 +1251,12 @@ 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); } @@ -1394,8 +1402,6 @@ 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 @@ -2792,7 +2798,7 @@ 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 c481d8458325..ca4bdc53d6c7 100644 --- a/kernel/irq/spurious.c +++ b/kernel/irq/spurious.c @@ -447,6 +447,10 @@ 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"); @@ -459,6 +463,10 @@ 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 db8c248ebc8c..0ec825dbe9f0 100644 --- a/kernel/irq_work.c +++ b/kernel/irq_work.c @@ -18,6 +18,7 @@ #include <linux/cpu.h> #include <linux/notifier.h> #include <linux/smp.h> +#include <linux/interrupt.h> #include <asm/processor.h> #include <linux/kasan.h> @@ -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(); } } @@ -104,7 +119,14 @@ 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); } @@ -122,9 +144,8 @@ 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())); @@ -167,8 +188,12 @@ 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; @@ -184,7 +209,16 @@ 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); @@ -194,8 +228,17 @@ 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 f099baee3578..69c6e9b7761c 100644 --- a/kernel/kexec_core.c +++ b/kernel/kexec_core.c @@ -978,7 +978,6 @@ 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 35859da8bd4f..dfff31ed644a 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) @@ -229,6 +238,9 @@ static struct attribute * kernel_attrs[] = { &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 08931e525dd9..424d5c34b9ff 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -270,6 +270,7 @@ 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; @@ -300,6 +301,13 @@ 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; @@ -397,7 +405,6 @@ 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]; /* @@ -406,13 +413,6 @@ 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 3572808223e4..683f0b7fbacc 100644 --- a/kernel/locking/Makefile +++ b/kernel/locking/Makefile @@ -24,7 +24,8 @@ 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_RT_MUTEXES) += rtmutex_api.o +obj-$(CONFIG_PREEMPT_RT) += spinlock_rt.o obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock.o obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock_debug.o obj-$(CONFIG_QUEUED_RWLOCKS) += qrwlock.o diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 38b2a5a512eb..f48b1a374f26 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -5478,6 +5478,7 @@ 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 @@ -5492,6 +5493,7 @@ 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-debug.c b/kernel/locking/mutex-debug.c index db9301591e3f..fa61e6b24513 100644 --- a/kernel/locking/mutex-debug.c +++ b/kernel/locking/mutex-debug.c @@ -1,6 +1,4 @@ /* - * kernel/mutex-debug.c - * * Debugging code for mutexes * * Started by Ingo Molnar: @@ -22,19 +20,19 @@ #include <linux/interrupt.h> #include <linux/debug_locks.h> -#include "mutex-debug.h" +#include "mutex.h" /* * Must be called with lock->wait_lock held. */ -void debug_mutex_lock_common(struct mutex *lock, struct mutex_waiter *waiter) +void debug_mutex_lock_common(_mutex_t *lock, struct mutex_waiter *waiter) { memset(waiter, MUTEX_DEBUG_INIT, sizeof(*waiter)); waiter->magic = waiter; INIT_LIST_HEAD(&waiter->list); } -void debug_mutex_wake_waiter(struct mutex *lock, struct mutex_waiter *waiter) +void debug_mutex_wake_waiter(_mutex_t *lock, struct mutex_waiter *waiter) { lockdep_assert_held(&lock->wait_lock); DEBUG_LOCKS_WARN_ON(list_empty(&lock->wait_list)); @@ -48,7 +46,7 @@ void debug_mutex_free_waiter(struct mutex_waiter *waiter) memset(waiter, MUTEX_DEBUG_FREE, sizeof(*waiter)); } -void debug_mutex_add_waiter(struct mutex *lock, struct mutex_waiter *waiter, +void debug_mutex_add_waiter(_mutex_t *lock, struct mutex_waiter *waiter, struct task_struct *task) { lockdep_assert_held(&lock->wait_lock); @@ -57,7 +55,7 @@ void debug_mutex_add_waiter(struct mutex *lock, struct mutex_waiter *waiter, task->blocked_on = waiter; } -void debug_mutex_remove_waiter(struct mutex *lock, struct mutex_waiter *waiter, +void debug_mutex_remove_waiter(_mutex_t *lock, struct mutex_waiter *waiter, struct task_struct *task) { DEBUG_LOCKS_WARN_ON(list_empty(&waiter->list)); @@ -69,7 +67,7 @@ void debug_mutex_remove_waiter(struct mutex *lock, struct mutex_waiter *waiter, waiter->task = NULL; } -void debug_mutex_unlock(struct mutex *lock) +void debug_mutex_unlock(_mutex_t *lock) { if (likely(debug_locks)) { DEBUG_LOCKS_WARN_ON(lock->magic != lock); @@ -77,7 +75,7 @@ void debug_mutex_unlock(struct mutex *lock) } } -void debug_mutex_init(struct mutex *lock, const char *name, +void debug_mutex_init(_mutex_t *lock, const char *name, struct lock_class_key *key) { #ifdef CONFIG_DEBUG_LOCK_ALLOC @@ -91,17 +89,16 @@ void debug_mutex_init(struct mutex *lock, const char *name, } /*** - * mutex_destroy - mark a mutex unusable + * _mutex_t_destroy - mark a mutex unusable * @lock: the mutex to be destroyed * * This function marks the mutex uninitialized, and any subsequent * use of the mutex is forbidden. The mutex must not be locked when * this function is called. */ -void mutex_destroy(struct mutex *lock) +void _mutex_t_destroy(_mutex_t *lock) { - DEBUG_LOCKS_WARN_ON(mutex_is_locked(lock)); + DEBUG_LOCKS_WARN_ON(_mutex_t_is_locked(lock)); lock->magic = NULL; } - -EXPORT_SYMBOL_GPL(mutex_destroy); +EXPORT_SYMBOL_GPL(_mutex_t_destroy); diff --git a/kernel/locking/mutex-debug.h b/kernel/locking/mutex-debug.h deleted file mode 100644 index 53e631e1d76d..000000000000 --- a/kernel/locking/mutex-debug.h +++ /dev/null @@ -1,29 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Mutexes: blocking mutual exclusion locks - * - * started by Ingo Molnar: - * - * Copyright (C) 2004, 2005, 2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com> - * - * This file contains mutex debugging related internal declarations, - * prototypes and inline functions, for the CONFIG_DEBUG_MUTEXES case. - * More details are in kernel/mutex-debug.c. - */ - -/* - * This must be called with lock->wait_lock held. - */ -extern void debug_mutex_lock_common(struct mutex *lock, - struct mutex_waiter *waiter); -extern void debug_mutex_wake_waiter(struct mutex *lock, - struct mutex_waiter *waiter); -extern void debug_mutex_free_waiter(struct mutex_waiter *waiter); -extern void debug_mutex_add_waiter(struct mutex *lock, - struct mutex_waiter *waiter, - struct task_struct *task); -extern void debug_mutex_remove_waiter(struct mutex *lock, struct mutex_waiter *waiter, - struct task_struct *task); -extern void debug_mutex_unlock(struct mutex *lock); -extern void debug_mutex_init(struct mutex *lock, const char *name, - struct lock_class_key *key); diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c index 013e1b08a1bf..3f4359154267 100644 --- a/kernel/locking/mutex.c +++ b/kernel/locking/mutex.c @@ -30,17 +30,13 @@ #include <linux/debug_locks.h> #include <linux/osq_lock.h> -#ifdef CONFIG_DEBUG_MUTEXES -# include "mutex-debug.h" -#else -# include "mutex.h" -#endif +#include "mutex.h" void -__mutex_init(struct mutex *lock, const char *name, struct lock_class_key *key) +__mutex_t_init(_mutex_t *lock, const char *name, struct lock_class_key *key) { atomic_long_set(&lock->owner, 0); - spin_lock_init(&lock->wait_lock); + raw_spin_lock_init(&lock->wait_lock); INIT_LIST_HEAD(&lock->wait_list); #ifdef CONFIG_MUTEX_SPIN_ON_OWNER osq_lock_init(&lock->osq); @@ -48,7 +44,7 @@ __mutex_init(struct mutex *lock, const char *name, struct lock_class_key *key) debug_mutex_init(lock, name, key); } -EXPORT_SYMBOL(__mutex_init); +EXPORT_SYMBOL(__mutex_t_init); /* * @owner: contains: 'struct task_struct *' to the current lock owner, @@ -70,7 +66,7 @@ EXPORT_SYMBOL(__mutex_init); * * DO NOT USE (outside of mutex code). */ -static inline struct task_struct *__mutex_owner(struct mutex *lock) +static inline struct task_struct *__mutex_owner(_mutex_t *lock) { return (struct task_struct *)(atomic_long_read(&lock->owner) & ~MUTEX_FLAGS); } @@ -80,11 +76,11 @@ static inline struct task_struct *__owner_task(unsigned long owner) return (struct task_struct *)(owner & ~MUTEX_FLAGS); } -bool mutex_is_locked(struct mutex *lock) +bool _mutex_t_is_locked(_mutex_t *lock) { return __mutex_owner(lock) != NULL; } -EXPORT_SYMBOL(mutex_is_locked); +EXPORT_SYMBOL(_mutex_t_is_locked); static inline unsigned long __owner_flags(unsigned long owner) { @@ -94,7 +90,7 @@ static inline unsigned long __owner_flags(unsigned long owner) /* * Trylock variant that returns the owning task on failure. */ -static inline struct task_struct *__mutex_trylock_or_owner(struct mutex *lock) +static inline struct task_struct *__mutex_trylock_or_owner(_mutex_t *lock) { unsigned long owner, curr = (unsigned long)current; @@ -137,7 +133,7 @@ static inline struct task_struct *__mutex_trylock_or_owner(struct mutex *lock) /* * Actual trylock that will work on any unlocked state. */ -static inline bool __mutex_trylock(struct mutex *lock) +static inline bool __mutex_trylock(_mutex_t *lock) { return !__mutex_trylock_or_owner(lock); } @@ -153,7 +149,7 @@ static inline bool __mutex_trylock(struct mutex *lock) * Optimistic trylock that only works in the uncontended case. Make sure to * follow with a __mutex_trylock() before failing. */ -static __always_inline bool __mutex_trylock_fast(struct mutex *lock) +static __always_inline bool __mutex_trylock_fast(_mutex_t *lock) { unsigned long curr = (unsigned long)current; unsigned long zero = 0UL; @@ -164,7 +160,7 @@ static __always_inline bool __mutex_trylock_fast(struct mutex *lock) return false; } -static __always_inline bool __mutex_unlock_fast(struct mutex *lock) +static __always_inline bool __mutex_unlock_fast(_mutex_t *lock) { unsigned long curr = (unsigned long)current; @@ -175,17 +171,17 @@ static __always_inline bool __mutex_unlock_fast(struct mutex *lock) } #endif -static inline void __mutex_set_flag(struct mutex *lock, unsigned long flag) +static inline void __mutex_set_flag(_mutex_t *lock, unsigned long flag) { atomic_long_or(flag, &lock->owner); } -static inline void __mutex_clear_flag(struct mutex *lock, unsigned long flag) +static inline void __mutex_clear_flag(_mutex_t *lock, unsigned long flag) { atomic_long_andnot(flag, &lock->owner); } -static inline bool __mutex_waiter_is_first(struct mutex *lock, struct mutex_waiter *waiter) +static inline bool __mutex_waiter_is_first(_mutex_t *lock, struct mutex_waiter *waiter) { return list_first_entry(&lock->wait_list, struct mutex_waiter, list) == waiter; } @@ -195,7 +191,7 @@ static inline bool __mutex_waiter_is_first(struct mutex *lock, struct mutex_wait * FLAG_WAITERS flag if it's the first waiter. */ static void -__mutex_add_waiter(struct mutex *lock, struct mutex_waiter *waiter, +__mutex_add_waiter(_mutex_t *lock, struct mutex_waiter *waiter, struct list_head *list) { debug_mutex_add_waiter(lock, waiter, current); @@ -206,7 +202,7 @@ __mutex_add_waiter(struct mutex *lock, struct mutex_waiter *waiter, } static void -__mutex_remove_waiter(struct mutex *lock, struct mutex_waiter *waiter) +__mutex_remove_waiter(_mutex_t *lock, struct mutex_waiter *waiter) { list_del(&waiter->list); if (likely(list_empty(&lock->wait_list))) @@ -221,7 +217,7 @@ __mutex_remove_waiter(struct mutex *lock, struct mutex_waiter *waiter) * WAITERS. Provides RELEASE semantics like a regular unlock, the * __mutex_trylock() provides a matching ACQUIRE semantics for the handoff. */ -static void __mutex_handoff(struct mutex *lock, struct task_struct *task) +static void __mutex_handoff(_mutex_t *lock, struct task_struct *task) { unsigned long owner = atomic_long_read(&lock->owner); @@ -246,7 +242,7 @@ static void __mutex_handoff(struct mutex *lock, struct task_struct *task) } } -#ifndef CONFIG_DEBUG_LOCK_ALLOC +#if !defined(CONFIG_DEBUG_LOCK_ALLOC) && !defined(CONFIG_PREEMPT_RT) /* * We split the mutex lock/unlock logic into separate fastpath and * slowpath functions, to reduce the register pressure on the fastpath. @@ -284,7 +280,7 @@ void __sched mutex_lock(struct mutex *lock) __mutex_lock_slowpath(lock); } EXPORT_SYMBOL(mutex_lock); -#endif +#endif /* !CONFIG_DEBUG_LOCK_ALLOC && !CONFIG_PREEMPT_RT */ /* * Wait-Die: @@ -364,7 +360,7 @@ __ww_ctx_stamp_after(struct ww_acquire_ctx *a, struct ww_acquire_ctx *b) * __ww_mutex_check_kill() wake any but the earliest context. */ static bool __sched -__ww_mutex_die(struct mutex *lock, struct mutex_waiter *waiter, +__ww_mutex_die(_mutex_t *lock, struct mutex_waiter *waiter, struct ww_acquire_ctx *ww_ctx) { if (!ww_ctx->is_wait_die) @@ -386,7 +382,7 @@ __ww_mutex_die(struct mutex *lock, struct mutex_waiter *waiter, * the lock holders. Even if multiple waiters may wound the lock holder, * it's sufficient that only one does. */ -static bool __ww_mutex_wound(struct mutex *lock, +static bool __ww_mutex_wound(_mutex_t *lock, struct ww_acquire_ctx *ww_ctx, struct ww_acquire_ctx *hold_ctx) { @@ -441,7 +437,7 @@ static bool __ww_mutex_wound(struct mutex *lock, * The current task must not be on the wait list. */ static void __sched -__ww_mutex_check_waiters(struct mutex *lock, struct ww_acquire_ctx *ww_ctx) +__ww_mutex_check_waiters(_mutex_t *lock, struct ww_acquire_ctx *ww_ctx) { struct mutex_waiter *cur; @@ -491,15 +487,15 @@ ww_mutex_set_context_fastpath(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) * Uh oh, we raced in fastpath, check if any of the waiters need to * die or wound us. */ - spin_lock(&lock->base.wait_lock); + raw_spin_lock(&lock->base.wait_lock); __ww_mutex_check_waiters(&lock->base, ctx); - spin_unlock(&lock->base.wait_lock); + raw_spin_unlock(&lock->base.wait_lock); } #ifdef CONFIG_MUTEX_SPIN_ON_OWNER static inline -bool ww_mutex_spin_on_owner(struct mutex *lock, struct ww_acquire_ctx *ww_ctx, +bool ww_mutex_spin_on_owner(_mutex_t *lock, struct ww_acquire_ctx *ww_ctx, struct mutex_waiter *waiter) { struct ww_mutex *ww; @@ -547,7 +543,7 @@ bool ww_mutex_spin_on_owner(struct mutex *lock, struct ww_acquire_ctx *ww_ctx, * "noinline" so that this function shows up on perf profiles. */ static noinline -bool mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner, +bool mutex_spin_on_owner(_mutex_t *lock, struct task_struct *owner, struct ww_acquire_ctx *ww_ctx, struct mutex_waiter *waiter) { bool ret = true; @@ -586,7 +582,7 @@ bool mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner, /* * Initial check for entering the mutex spinning loop */ -static inline int mutex_can_spin_on_owner(struct mutex *lock) +static inline int mutex_can_spin_on_owner(_mutex_t *lock) { struct task_struct *owner; int retval = 1; @@ -635,7 +631,7 @@ static inline int mutex_can_spin_on_owner(struct mutex *lock) * changed to itself. */ static __always_inline bool -mutex_optimistic_spin(struct mutex *lock, struct ww_acquire_ctx *ww_ctx, +mutex_optimistic_spin(_mutex_t *lock, struct ww_acquire_ctx *ww_ctx, struct mutex_waiter *waiter) { if (!waiter) { @@ -709,17 +705,27 @@ fail: return false; } -#else +#else /* CONFIG_MUTEX_SPIN_ON_OWNER */ static __always_inline bool -mutex_optimistic_spin(struct mutex *lock, struct ww_acquire_ctx *ww_ctx, +mutex_optimistic_spin(_mutex_t *lock, struct ww_acquire_ctx *ww_ctx, struct mutex_waiter *waiter) { return false; } -#endif +#endif /* !CONFIG_MUTEX_SPIN_ON_OWNER */ + +static noinline void __sched __mutex_unlock_slowpath(_mutex_t *lock, unsigned long ip); -static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigned long ip); +static __always_inline void __mutex_unlock(_mutex_t *lock) +{ +#ifndef CONFIG_DEBUG_LOCK_ALLOC + if (__mutex_unlock_fast(lock)) + return; +#endif + __mutex_unlock_slowpath(lock, _RET_IP_); +} +#ifndef CONFIG_PREEMPT_RT /** * mutex_unlock - release the mutex * @lock: the mutex to be released @@ -733,13 +739,10 @@ static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigne */ void __sched mutex_unlock(struct mutex *lock) { -#ifndef CONFIG_DEBUG_LOCK_ALLOC - if (__mutex_unlock_fast(lock)) - return; -#endif - __mutex_unlock_slowpath(lock, _RET_IP_); + __mutex_unlock(lock); } EXPORT_SYMBOL(mutex_unlock); +#endif /* !CONFIG_PREEMPT_RT */ /** * ww_mutex_unlock - release the w/w mutex @@ -767,13 +770,13 @@ void __sched ww_mutex_unlock(struct ww_mutex *lock) lock->ctx = NULL; } - mutex_unlock(&lock->base); + __mutex_unlock(&lock->base); } EXPORT_SYMBOL(ww_mutex_unlock); static __always_inline int __sched -__ww_mutex_kill(struct mutex *lock, struct ww_acquire_ctx *ww_ctx) +__ww_mutex_kill(_mutex_t *lock, struct ww_acquire_ctx *ww_ctx) { if (ww_ctx->acquired > 0) { #ifdef CONFIG_DEBUG_MUTEXES @@ -802,7 +805,7 @@ __ww_mutex_kill(struct mutex *lock, struct ww_acquire_ctx *ww_ctx) * look at waiters before us in the wait-list. */ static inline int __sched -__ww_mutex_check_kill(struct mutex *lock, struct mutex_waiter *waiter, +__ww_mutex_check_kill(_mutex_t *lock, struct mutex_waiter *waiter, struct ww_acquire_ctx *ctx) { struct ww_mutex *ww = container_of(lock, struct ww_mutex, base); @@ -850,7 +853,7 @@ __ww_mutex_check_kill(struct mutex *lock, struct mutex_waiter *waiter, */ static inline int __sched __ww_mutex_add_waiter(struct mutex_waiter *waiter, - struct mutex *lock, + _mutex_t *lock, struct ww_acquire_ctx *ww_ctx) { struct mutex_waiter *cur; @@ -923,7 +926,7 @@ __ww_mutex_add_waiter(struct mutex_waiter *waiter, * Lock a mutex (possibly interruptible), slowpath: */ static __always_inline int __sched -__mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, +__mutex_lock_common(_mutex_t *lock, long state, unsigned int subclass, struct lockdep_map *nest_lock, unsigned long ip, struct ww_acquire_ctx *ww_ctx, const bool use_ww_ctx) { @@ -968,7 +971,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, return 0; } - spin_lock(&lock->wait_lock); + raw_spin_lock(&lock->wait_lock); /* * After waiting to acquire the wait_lock, try again. */ @@ -1032,7 +1035,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, goto err; } - spin_unlock(&lock->wait_lock); + raw_spin_unlock(&lock->wait_lock); schedule_preempt_disabled(); /* @@ -1055,9 +1058,9 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, (first && mutex_optimistic_spin(lock, ww_ctx, &waiter))) break; - spin_lock(&lock->wait_lock); + raw_spin_lock(&lock->wait_lock); } - spin_lock(&lock->wait_lock); + raw_spin_lock(&lock->wait_lock); acquired: __set_current_state(TASK_RUNNING); @@ -1082,7 +1085,7 @@ skip_wait: if (ww_ctx) ww_mutex_lock_acquired(ww, ww_ctx); - spin_unlock(&lock->wait_lock); + raw_spin_unlock(&lock->wait_lock); preempt_enable(); return 0; @@ -1090,22 +1093,24 @@ err: __set_current_state(TASK_RUNNING); __mutex_remove_waiter(lock, &waiter); err_early_kill: - spin_unlock(&lock->wait_lock); + raw_spin_unlock(&lock->wait_lock); debug_mutex_free_waiter(&waiter); mutex_release(&lock->dep_map, ip); preempt_enable(); return ret; } +#ifndef CONFIG_PREEMPT_RT static int __sched __mutex_lock(struct mutex *lock, long state, unsigned int subclass, struct lockdep_map *nest_lock, unsigned long ip) { return __mutex_lock_common(lock, state, subclass, nest_lock, ip, NULL, false); } +#endif /* !CONFIG_PREEMPT_RT */ static int __sched -__ww_mutex_lock(struct mutex *lock, long state, unsigned int subclass, +__ww_mutex_lock(_mutex_t *lock, long state, unsigned int subclass, struct lockdep_map *nest_lock, unsigned long ip, struct ww_acquire_ctx *ww_ctx) { @@ -1113,6 +1118,7 @@ __ww_mutex_lock(struct mutex *lock, long state, unsigned int subclass, } #ifdef CONFIG_DEBUG_LOCK_ALLOC +# ifndef CONFIG_PREEMPT_RT void __sched mutex_lock_nested(struct mutex *lock, unsigned int subclass) { @@ -1155,6 +1161,7 @@ mutex_lock_io_nested(struct mutex *lock, unsigned int subclass) io_schedule_finish(token); } EXPORT_SYMBOL_GPL(mutex_lock_io_nested); +# endif /* !CONFIG_PREEMPT_RT */ static inline int ww_mutex_deadlock_injection(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) @@ -1220,7 +1227,7 @@ EXPORT_SYMBOL_GPL(ww_mutex_lock_interruptible); /* * Release the lock, slowpath: */ -static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigned long ip) +static noinline void __sched __mutex_unlock_slowpath(_mutex_t *lock, unsigned long ip) { struct task_struct *next = NULL; DEFINE_WAKE_Q(wake_q); @@ -1259,7 +1266,7 @@ static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigne owner = old; } - spin_lock(&lock->wait_lock); + raw_spin_lock(&lock->wait_lock); debug_mutex_unlock(lock); if (!list_empty(&lock->wait_list)) { /* get the first entry from the wait-list: */ @@ -1276,12 +1283,13 @@ static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigne if (owner & MUTEX_FLAG_HANDOFF) __mutex_handoff(lock, next); - spin_unlock(&lock->wait_lock); + raw_spin_unlock(&lock->wait_lock); wake_up_q(&wake_q); } #ifndef CONFIG_DEBUG_LOCK_ALLOC +#ifndef CONFIG_PREEMPT_RT /* * Here come the less common (and hence less performance-critical) APIs: * mutex_lock_interruptible() and mutex_trylock(). @@ -1376,6 +1384,7 @@ __mutex_lock_interruptible_slowpath(struct mutex *lock) { return __mutex_lock(lock, TASK_INTERRUPTIBLE, 0, NULL, _RET_IP_); } +#endif /* !CONFIG_PREEMPT_RT */ static noinline int __sched __ww_mutex_lock_slowpath(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) @@ -1394,21 +1403,7 @@ __ww_mutex_lock_interruptible_slowpath(struct ww_mutex *lock, #endif -/** - * mutex_trylock - try to acquire the mutex, without waiting - * @lock: the mutex to be acquired - * - * Try to acquire the mutex atomically. Returns 1 if the mutex - * has been acquired successfully, and 0 on contention. - * - * NOTE: this function follows the spin_trylock() convention, so - * it is negated from the down_trylock() return values! Be careful - * about this when converting semaphore users to mutexes. - * - * This function must not be used in interrupt context. The - * mutex must be released by the same task that acquired it. - */ -int __sched mutex_trylock(struct mutex *lock) +int __sched _mutex_t_trylock(_mutex_t *lock) { bool locked; @@ -1422,7 +1417,7 @@ int __sched mutex_trylock(struct mutex *lock) return locked; } -EXPORT_SYMBOL(mutex_trylock); +EXPORT_SYMBOL(_mutex_t_trylock); #ifndef CONFIG_DEBUG_LOCK_ALLOC int __sched diff --git a/kernel/locking/mutex.h b/kernel/locking/mutex.h index f0c710b1d192..226e5c4f2a51 100644 --- a/kernel/locking/mutex.h +++ b/kernel/locking/mutex.h @@ -5,11 +5,37 @@ * started by Ingo Molnar: * * Copyright (C) 2004, 2005, 2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com> - * - * This file contains mutex debugging related internal prototypes, for the - * !CONFIG_DEBUG_MUTEXES case. Most of them are NOPs: */ +/* + * This is the control structure for tasks blocked on mutex, which resides + * on the blocked task's kernel stack: + */ +struct mutex_waiter { + struct list_head list; + struct task_struct *task; + struct ww_acquire_ctx *ww_ctx; +#ifdef CONFIG_DEBUG_MUTEXES + void *magic; +#endif +}; + +#ifdef CONFIG_DEBUG_MUTEXES +extern void debug_mutex_lock_common(_mutex_t *lock, + struct mutex_waiter *waiter); +extern void debug_mutex_wake_waiter(_mutex_t *lock, + struct mutex_waiter *waiter); +extern void debug_mutex_free_waiter(struct mutex_waiter *waiter); +extern void debug_mutex_add_waiter(_mutex_t *lock, + struct mutex_waiter *waiter, + struct task_struct *task); +extern void debug_mutex_remove_waiter(_mutex_t *lock, struct mutex_waiter *waiter, + struct task_struct *task); +extern void debug_mutex_unlock(_mutex_t *lock); +extern void debug_mutex_init(_mutex_t *lock, const char *name, + struct lock_class_key *key); +#else /* CONFIG_DEBUG_MUTEXES */ + #define debug_mutex_wake_waiter(lock, waiter) do { } while (0) #define debug_mutex_free_waiter(waiter) do { } while (0) #define debug_mutex_add_waiter(lock, waiter, ti) do { } while (0) @@ -18,6 +44,7 @@ #define debug_mutex_init(lock, name, key) do { } while (0) static inline void -debug_mutex_lock_common(struct mutex *lock, struct mutex_waiter *waiter) +debug_mutex_lock_common(_mutex_t *lock, struct mutex_waiter *waiter) { } +#endif /* !CONFIG_DEBUG_MUTEXES */ diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index 3c20afbc19e1..f7bb9f6fae93 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -8,17 +8,20 @@ * Copyright (C) 2005-2006 Timesys Corp., Thomas Gleixner <tglx@timesys.com> * 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 <srostedt@redhat.com> * * See Documentation/locking/rt-mutex-design.rst for details. */ -#include <linux/spinlock.h> -#include <linux/export.h> +#include <linux/sched.h> +#include <linux/sched/debug.h> +#include <linux/sched/deadline.h> #include <linux/sched/signal.h> #include <linux/sched/rt.h> -#include <linux/sched/deadline.h> #include <linux/sched/wake_q.h> -#include <linux/sched/debug.h> -#include <linux/timer.h> #include "rtmutex_common.h" @@ -141,8 +144,19 @@ static __always_inline void fixup_rt_mutex_waiters(struct rt_mutex *lock) * set up. */ #ifndef CONFIG_DEBUG_RT_MUTEXES -# define rt_mutex_cmpxchg_acquire(l,c,n) (cmpxchg_acquire(&l->owner, c, n) == c) -# define rt_mutex_cmpxchg_release(l,c,n) (cmpxchg_release(&l->owner, c, n) == c) +static __always_inline bool rt_mutex_cmpxchg_acquire(struct rt_mutex *lock, + struct task_struct *old, + struct task_struct *new) +{ + return cmpxchg_acquire(&lock->owner, old, new) == old; +} + +static __always_inline bool rt_mutex_cmpxchg_release(struct rt_mutex *lock, + struct task_struct *old, + struct task_struct *new) +{ + return cmpxchg_release(&lock->owner, old, new) == old; +} /* * Callers must hold the ->wait_lock -- which is the whole purpose as we force @@ -201,8 +215,20 @@ static __always_inline bool unlock_rt_mutex_safe(struct rt_mutex *lock, } #else -# define rt_mutex_cmpxchg_acquire(l,c,n) (0) -# define rt_mutex_cmpxchg_release(l,c,n) (0) +static __always_inline bool rt_mutex_cmpxchg_acquire(struct rt_mutex *lock, + struct task_struct *old, + struct task_struct *new) +{ + return false; + +} + +static __always_inline bool rt_mutex_cmpxchg_release(struct rt_mutex *lock, + struct task_struct *old, + struct task_struct *new) +{ + return false; +} static __always_inline void mark_rt_mutex_waiters(struct rt_mutex *lock) { @@ -265,6 +291,26 @@ static __always_inline int rt_mutex_waiter_equal(struct rt_mutex_waiter *left, return 1; } +static inline bool rt_mutex_steal(struct rt_mutex_waiter *waiter, + struct rt_mutex_waiter *top_waiter) +{ + if (rt_mutex_waiter_less(waiter, top_waiter)) + return true; + +#ifdef RT_MUTEX_BUILD_SPINLOCKS + /* + * Note that RT tasks are excluded from same priority (lateral) + * steals to prevent the introduction of an unbounded latency. + */ + if (rt_prio(waiter->prio) || dl_prio(waiter->prio)) + return false; + + return rt_mutex_waiter_equal(waiter, top_waiter); +#else + return false; +#endif +} + #define __node_2_waiter(node) \ rb_entry((node), struct rt_mutex_waiter, tree_entry) @@ -326,6 +372,33 @@ static __always_inline void rt_mutex_adjust_prio(struct task_struct *p) rt_mutex_setprio(p, pi_task); } +/* RT mutex specific wake_q wrappers */ +static __always_inline void rt_mutex_wake_q_add(struct rt_mutex_wake_q_head *wqh, + struct rt_mutex_waiter *w) +{ + if (IS_ENABLED(CONFIG_PREEMPT_RT) && w->wake_state != TASK_NORMAL) { + get_task_struct(w->task); + wqh->rtlock_task = w->task; + } else { + wake_q_add(&wqh->head, w->task); + } +} + +static __always_inline void rt_mutex_wake_up_q(struct rt_mutex_wake_q_head *wqh) +{ + if (IS_ENABLED(CONFIG_PREEMPT_RT) && wqh->rtlock_task) { + wake_up_state(wqh->rtlock_task, TASK_RTLOCK_WAIT); + put_task_struct(wqh->rtlock_task); + wqh->rtlock_task = NULL; + } + + if (!wake_q_empty(&wqh->head)) + wake_up_q(&wqh->head); + + /* Pairs with preempt_disable() in mark_wakeup_next_waiter() */ + preempt_enable(); +} + /* * Deadlock detection is conditional: * @@ -348,11 +421,6 @@ rt_mutex_cond_detect_deadlock(struct rt_mutex_waiter *waiter, return chwalk == RT_MUTEX_FULL_CHAINWALK; } -/* - * Max number of times we'll walk the boosting chain: - */ -int max_lock_depth = 1024; - static __always_inline struct rt_mutex *task_blocked_on_lock(struct task_struct *p) { return p->pi_blocked_on ? p->pi_blocked_on->lock : NULL; @@ -676,7 +744,7 @@ static int __sched rt_mutex_adjust_prio_chain(struct task_struct *task, * to get the lock. */ if (prerequeue_top_waiter != rt_mutex_top_waiter(lock)) - wake_up_process(rt_mutex_top_waiter(lock)->task); + wake_up_state(waiter->task, waiter->wake_state); raw_spin_unlock_irq(&lock->wait_lock); return 0; } @@ -815,19 +883,21 @@ try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task, * trylock attempt. */ if (waiter) { - /* - * If waiter is not the highest priority waiter of - * @lock, give up. - */ - if (waiter != rt_mutex_top_waiter(lock)) - return 0; + struct rt_mutex_waiter *top_waiter = rt_mutex_top_waiter(lock); /* - * We can acquire the lock. Remove the waiter from the - * lock waiters tree. + * If waiter is the highest priority waiter of @lock, + * or allowed to steal it, take it over. */ - rt_mutex_dequeue(lock, waiter); - + if (waiter == top_waiter || rt_mutex_steal(waiter, top_waiter)) { + /* + * We can acquire the lock. Remove the waiter from the + * lock waiters tree. + */ + rt_mutex_dequeue(lock, waiter); + } else { + return 0; + } } else { /* * If the lock has waiters already we check whether @task is @@ -838,13 +908,9 @@ try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task, * not need to be dequeued. */ if (rt_mutex_has_waiters(lock)) { - /* - * If @task->prio is greater than or equal to - * the top waiter priority (kernel view), - * @task lost. - */ - if (!rt_mutex_waiter_less(task_to_waiter(task), - rt_mutex_top_waiter(lock))) + /* Check whether the trylock can steal it. */ + if (!rt_mutex_steal(task_to_waiter(task), + rt_mutex_top_waiter(lock))) return 0; /* @@ -986,7 +1052,7 @@ static int __sched task_blocks_on_rt_mutex(struct rt_mutex *lock, * * Called with lock->wait_lock held and interrupts disabled. */ -static void __sched mark_wakeup_next_waiter(struct wake_q_head *wake_q, +static void __sched mark_wakeup_next_waiter(struct rt_mutex_wake_q_head *wqh, struct rt_mutex *lock) { struct rt_mutex_waiter *waiter; @@ -1023,17 +1089,146 @@ static void __sched mark_wakeup_next_waiter(struct wake_q_head *wake_q, * deboost but before waking our donor task, hence the preempt_disable() * before unlock. * - * Pairs with preempt_enable() in rt_mutex_postunlock(); + * Pairs with preempt_enable() in rt_mutex_wake_up_q(); */ preempt_disable(); - wake_q_add(wake_q, waiter->task); + rt_mutex_wake_q_add(wqh, waiter); raw_spin_unlock(¤t->pi_lock); } +static int __sched __rt_mutex_slowtrylock(struct rt_mutex *lock) +{ + int ret = try_to_take_rt_mutex(lock, current, NULL); + + /* + * try_to_take_rt_mutex() sets the lock waiters bit + * unconditionally. Clean this up. + */ + fixup_rt_mutex_waiters(lock); + + return ret; +} + +/* + * Slow path try-lock function: + */ +static int __sched rt_mutex_slowtrylock(struct rt_mutex *lock) +{ + unsigned long flags; + int ret; + + /* + * If the lock already has an owner we fail to get the lock. + * This can be done without taking the @lock->wait_lock as + * it is only being read, and this is a trylock anyway. + */ + if (rt_mutex_owner(lock)) + return 0; + + /* + * The mutex has currently no owner. Lock the wait lock and try to + * acquire the lock. We use irqsave here to support early boot calls. + */ + raw_spin_lock_irqsave(&lock->wait_lock, flags); + + ret = __rt_mutex_slowtrylock(lock); + + raw_spin_unlock_irqrestore(&lock->wait_lock, flags); + + return ret; +} + +static __always_inline int __rt_mutex_trylock(struct rt_mutex *lock) +{ + if (likely(rt_mutex_cmpxchg_acquire(lock, NULL, current))) + return 1; + + return rt_mutex_slowtrylock(lock); +} + +/* + * Slow path to release a rt-mutex. + */ +static void __sched rt_mutex_slowunlock(struct rt_mutex *lock) +{ + DEFINE_RT_MUTEX_WAKE_Q_HEAD(wqh); + unsigned long flags; + + /* irqsave required to support early boot calls */ + raw_spin_lock_irqsave(&lock->wait_lock, flags); + + debug_rt_mutex_unlock(lock); + + /* + * We must be careful here if the fast path is enabled. If we + * have no waiters queued we cannot set owner to NULL here + * because of: + * + * foo->lock->owner = NULL; + * rtmutex_lock(foo->lock); <- fast path + * free = atomic_dec_and_test(foo->refcnt); + * rtmutex_unlock(foo->lock); <- fast path + * if (free) + * kfree(foo); + * raw_spin_unlock(foo->lock->wait_lock); + * + * So for the fastpath enabled kernel: + * + * Nothing can set the waiters bit as long as we hold + * lock->wait_lock. So we do the following sequence: + * + * owner = rt_mutex_owner(lock); + * clear_rt_mutex_waiters(lock); + * raw_spin_unlock(&lock->wait_lock); + * if (cmpxchg(&lock->owner, owner, 0) == owner) + * return; + * goto retry; + * + * The fastpath disabled variant is simple as all access to + * lock->owner is serialized by lock->wait_lock: + * + * lock->owner = NULL; + * raw_spin_unlock(&lock->wait_lock); + */ + while (!rt_mutex_has_waiters(lock)) { + /* Drops lock->wait_lock ! */ + if (unlock_rt_mutex_safe(lock, flags) == true) + return; + /* Relock the rtmutex and try again */ + raw_spin_lock_irqsave(&lock->wait_lock, flags); + } + + /* + * The wakeup next waiter path does not suffer from the above + * race. See the comments there. + * + * Queue the next waiter for wakeup once we release the wait_lock. + */ + mark_wakeup_next_waiter(&wqh, lock); + raw_spin_unlock_irqrestore(&lock->wait_lock, flags); + + rt_mutex_wake_up_q(&wqh); +} + +static __always_inline void __rt_mutex_unlock(struct rt_mutex *lock) +{ + if (likely(rt_mutex_cmpxchg_release(lock, current, NULL))) + return; + + rt_mutex_slowunlock(lock); +} + +#ifdef RT_MUTEX_BUILD_MUTEX +/* + * Functions required for: + * - rtmutex, futex on all kernels + * - mutex and rwsem substitutions on RT kernels + */ + /* * Remove a waiter from a lock and give up * - * Must be called with lock->wait_lock held and interrupts disabled. I must + * Must be called with lock->wait_lock held and interrupts disabled. It must * have just failed to try_to_take_rt_mutex(). */ static void __sched remove_waiter(struct rt_mutex *lock, @@ -1089,44 +1284,8 @@ static void __sched remove_waiter(struct rt_mutex *lock, raw_spin_lock_irq(&lock->wait_lock); } -/* - * Recheck the pi chain, in case we got a priority setting - * - * Called from sched_setscheduler - */ -void __sched rt_mutex_adjust_pi(struct task_struct *task) -{ - struct rt_mutex_waiter *waiter; - struct rt_mutex *next_lock; - unsigned long flags; - - raw_spin_lock_irqsave(&task->pi_lock, flags); - - waiter = task->pi_blocked_on; - if (!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); - - rt_mutex_adjust_prio_chain(task, RT_MUTEX_MIN_CHAINWALK, NULL, - next_lock, NULL, task); -} - -void __sched rt_mutex_init_waiter(struct rt_mutex_waiter *waiter) -{ - debug_rt_mutex_init_waiter(waiter); - RB_CLEAR_NODE(&waiter->pi_tree_entry); - RB_CLEAR_NODE(&waiter->tree_entry); - waiter->task = NULL; -} - /** - * __rt_mutex_slowlock() - Perform the wait-wake-try-to-take loop + * rt_mutex_slowlock_block() - Perform the wait-wake-try-to-take loop * @lock: the rt_mutex to take * @state: the state the task should block in (TASK_INTERRUPTIBLE * or TASK_UNINTERRUPTIBLE) @@ -1135,9 +1294,10 @@ void __sched rt_mutex_init_waiter(struct rt_mutex_waiter *waiter) * * Must be called with lock->wait_lock held and interrupts disabled */ -static int __sched __rt_mutex_slowlock(struct rt_mutex *lock, int state, - struct hrtimer_sleeper *timeout, - struct rt_mutex_waiter *waiter) +static int __sched rt_mutex_slowlock_block(struct rt_mutex *lock, + unsigned int state, + struct hrtimer_sleeper *timeout, + struct rt_mutex_waiter *waiter) { int ret = 0; @@ -1187,51 +1347,37 @@ static void __sched rt_mutex_handle_deadlock(int res, int detect_deadlock, } } -/* - * Slow path lock function: +/** + * __rt_mutex_slowlock - Locking slowpath invoked with lock::wait_lock held + * @lock: The rtmutex to block lock + * @state: The task state for sleeping + * @chwalk: Indicator whether full or partial chainwalk is requested + * @waiter: Initializer waiter for blocking */ -static int __sched rt_mutex_slowlock(struct rt_mutex *lock, int state, - struct hrtimer_sleeper *timeout, - enum rtmutex_chainwalk chwalk) +static int __sched __rt_mutex_slowlock(struct rt_mutex *lock, + unsigned int state, + enum rtmutex_chainwalk chwalk, + struct rt_mutex_waiter *waiter) { - struct rt_mutex_waiter waiter; - unsigned long flags; - int ret = 0; - - rt_mutex_init_waiter(&waiter); + int ret; - /* - * Technically we could use raw_spin_[un]lock_irq() here, but this can - * be called in early boot if the cmpxchg() fast path is disabled - * (debug, no architecture support). In this case we will acquire the - * rtmutex with lock->wait_lock held. But we cannot unconditionally - * enable interrupts in that early boot case. So we need to use the - * irqsave/restore variants. - */ - raw_spin_lock_irqsave(&lock->wait_lock, flags); + lockdep_assert_held(&lock->wait_lock); /* Try to acquire the lock again: */ - if (try_to_take_rt_mutex(lock, current, NULL)) { - raw_spin_unlock_irqrestore(&lock->wait_lock, flags); + if (try_to_take_rt_mutex(lock, current, NULL)) 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); + 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); + ret = rt_mutex_slowlock_block(lock, state, NULL, waiter); if (unlikely(ret)) { __set_current_state(TASK_RUNNING); - remove_waiter(lock, &waiter); - rt_mutex_handle_deadlock(ret, chwalk, &waiter); + remove_waiter(lock, waiter); + rt_mutex_handle_deadlock(ret, chwalk, waiter); } /* @@ -1239,547 +1385,153 @@ static int __sched rt_mutex_slowlock(struct rt_mutex *lock, int state, * unconditionally. We might have to fix that up. */ fixup_rt_mutex_waiters(lock); - - raw_spin_unlock_irqrestore(&lock->wait_lock, flags); - - /* Remove pending timer: */ - if (unlikely(timeout)) - hrtimer_cancel(&timeout->timer); - - debug_rt_mutex_free_waiter(&waiter); - return ret; } -static int __sched __rt_mutex_slowtrylock(struct rt_mutex *lock) +static inline int __rt_mutex_slowlock_locked(struct rt_mutex *lock, + unsigned int state) { - int ret = try_to_take_rt_mutex(lock, current, NULL); + struct rt_mutex_waiter waiter; - /* - * try_to_take_rt_mutex() sets the lock waiters bit - * unconditionally. Clean this up. - */ - fixup_rt_mutex_waiters(lock); + rt_mutex_init_waiter(&waiter); - return ret; + return __rt_mutex_slowlock(lock, state, RT_MUTEX_MIN_CHAINWALK, &waiter); } /* - * Slow path try-lock function: + * rt_mutex_slowlock - Locking slowpath invoked when fast path fails + * @lock: The rtmutex to block lock + * @state: The task state for sleeping */ -static int __sched rt_mutex_slowtrylock(struct rt_mutex *lock) +static int __sched rt_mutex_slowlock(struct rt_mutex *lock, unsigned int state) { unsigned long flags; int ret; /* - * If the lock already has an owner we fail to get the lock. - * This can be done without taking the @lock->wait_lock as - * it is only being read, and this is a trylock anyway. - */ - if (rt_mutex_owner(lock)) - return 0; - - /* - * The mutex has currently no owner. Lock the wait lock and try to - * acquire the lock. We use irqsave here to support early boot calls. + * Technically we could use raw_spin_[un]lock_irq() here, but this can + * be called in early boot if the cmpxchg() fast path is disabled + * (debug, no architecture support). In this case we will acquire the + * rtmutex with lock->wait_lock held. But we cannot unconditionally + * enable interrupts in that early boot case. So we need to use the + * irqsave/restore variants. */ raw_spin_lock_irqsave(&lock->wait_lock, flags); - - ret = __rt_mutex_slowtrylock(lock); - + ret = __rt_mutex_slowlock_locked(lock, state); raw_spin_unlock_irqrestore(&lock->wait_lock, flags); return ret; } -/* - * Performs the wakeup of the top-waiter and re-enables preemption. - */ -void __sched rt_mutex_postunlock(struct wake_q_head *wake_q) +static __always_inline int __rt_mutex_lock(struct rt_mutex *lock, + unsigned int state) { - wake_up_q(wake_q); + if (likely(rt_mutex_cmpxchg_acquire(lock, NULL, current))) + return 0; - /* Pairs with preempt_disable() in mark_wakeup_next_waiter() */ - preempt_enable(); + return rt_mutex_slowlock(lock, state); } +#endif /* RT_MUTEX_BUILD_MUTEX */ +#ifdef RT_MUTEX_BUILD_SPINLOCKS /* - * Slow path to release a rt-mutex. - * - * Return whether the current task needs to call rt_mutex_postunlock(). + * Functions required for spin/rw_lock substitution on RT kernels */ -static void __sched rt_mutex_slowunlock(struct rt_mutex *lock) -{ - DEFINE_WAKE_Q(wake_q); - unsigned long flags; - - /* irqsave required to support early boot calls */ - raw_spin_lock_irqsave(&lock->wait_lock, flags); - - debug_rt_mutex_unlock(lock); - - /* - * We must be careful here if the fast path is enabled. If we - * have no waiters queued we cannot set owner to NULL here - * because of: - * - * foo->lock->owner = NULL; - * rtmutex_lock(foo->lock); <- fast path - * free = atomic_dec_and_test(foo->refcnt); - * rtmutex_unlock(foo->lock); <- fast path - * if (free) - * kfree(foo); - * raw_spin_unlock(foo->lock->wait_lock); - * - * So for the fastpath enabled kernel: - * - * Nothing can set the waiters bit as long as we hold - * lock->wait_lock. So we do the following sequence: - * - * owner = rt_mutex_owner(lock); - * clear_rt_mutex_waiters(lock); - * raw_spin_unlock(&lock->wait_lock); - * if (cmpxchg(&lock->owner, owner, 0) == owner) - * return; - * goto retry; - * - * The fastpath disabled variant is simple as all access to - * lock->owner is serialized by lock->wait_lock: - * - * lock->owner = NULL; - * raw_spin_unlock(&lock->wait_lock); - */ - while (!rt_mutex_has_waiters(lock)) { - /* Drops lock->wait_lock ! */ - if (unlock_rt_mutex_safe(lock, flags) == true) - return; - /* Relock the rtmutex and try again */ - raw_spin_lock_irqsave(&lock->wait_lock, flags); - } - - /* - * The wakeup next waiter path does not suffer from the above - * race. See the comments there. - * - * Queue the next waiter for wakeup once we release the wait_lock. - */ - mark_wakeup_next_waiter(&wake_q, lock); - raw_spin_unlock_irqrestore(&lock->wait_lock, flags); - - rt_mutex_postunlock(&wake_q); -} +#ifdef CONFIG_SMP /* - * debug aware fast / slowpath lock,trylock,unlock - * - * The atomic acquire/release ops are compiled away, when either the - * architecture does not support cmpxchg or when debugging is enabled. + * Note that owner is a speculative pointer and dereferencing relies + * on rcu_read_lock() and the check against the lock owner. */ -static __always_inline int __rt_mutex_lock(struct rt_mutex *lock, long state, - unsigned int subclass) +static bool rtlock_adaptive_spinwait(struct rt_mutex *lock, + struct task_struct *owner) { - int ret; - - might_sleep(); - mutex_acquire(&lock->dep_map, subclass, 0, _RET_IP_); - - if (likely(rt_mutex_cmpxchg_acquire(lock, NULL, current))) - return 0; - - ret = rt_mutex_slowlock(lock, state, NULL, RT_MUTEX_MIN_CHAINWALK); - if (ret) - mutex_release(&lock->dep_map, _RET_IP_); - return ret; -} + bool res = true; -#ifdef CONFIG_DEBUG_LOCK_ALLOC -/** - * rt_mutex_lock_nested - lock a rt_mutex - * - * @lock: the rt_mutex to be locked - * @subclass: the lockdep subclass - */ -void __sched rt_mutex_lock_nested(struct rt_mutex *lock, unsigned int subclass) -{ - __rt_mutex_lock(lock, TASK_UNINTERRUPTIBLE, subclass); + rcu_read_lock(); + for (;;) { + /* Owner changed. Trylock again */ + 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 = false; + break; + } + cpu_relax(); + } + rcu_read_unlock(); + return res; } -EXPORT_SYMBOL_GPL(rt_mutex_lock_nested); - -#else /* !CONFIG_DEBUG_LOCK_ALLOC */ - -/** - * rt_mutex_lock - lock a rt_mutex - * - * @lock: the rt_mutex to be locked - */ -void __sched rt_mutex_lock(struct rt_mutex *lock) +#else +static bool rtlock_adaptive_spinwait(struct rt_mutex *lock, + struct task_struct *owner) { - __rt_mutex_lock(lock, TASK_UNINTERRUPTIBLE, 0); + return false; } -EXPORT_SYMBOL_GPL(rt_mutex_lock); #endif /** - * rt_mutex_lock_interruptible - lock a rt_mutex interruptible - * - * @lock: the rt_mutex to be locked - * - * Returns: - * 0 on success - * -EINTR when interrupted by a signal + * rtlock_slowlock_locked - Slow path lock acquisition for RT locks + * @lock: The underlying rt mutex */ -int __sched rt_mutex_lock_interruptible(struct rt_mutex *lock) +static void __sched rtlock_slowlock_locked(struct rt_mutex *lock) { - return __rt_mutex_lock(lock, TASK_INTERRUPTIBLE, 0); -} -EXPORT_SYMBOL_GPL(rt_mutex_lock_interruptible); - -/** - * rt_mutex_trylock - try to lock a rt_mutex - * - * @lock: the rt_mutex to be locked - * - * This function can only be called in thread context. It's safe to call it - * from atomic regions, but not from hard or soft interrupt context. - * - * Returns: - * 1 on success - * 0 on contention - */ -int __sched rt_mutex_trylock(struct rt_mutex *lock) -{ - int ret; - - if (IS_ENABLED(CONFIG_DEBUG_RT_MUTEXES) && WARN_ON_ONCE(!in_task())) - return 0; - - /* - * No lockdep annotation required because lockdep disables the fast - * path. - */ - if (likely(rt_mutex_cmpxchg_acquire(lock, NULL, current))) - return 1; - - ret = rt_mutex_slowtrylock(lock); - if (ret) - mutex_acquire(&lock->dep_map, 0, 1, _RET_IP_); - - return ret; -} -EXPORT_SYMBOL_GPL(rt_mutex_trylock); - -/** - * rt_mutex_unlock - unlock a rt_mutex - * - * @lock: the rt_mutex to be unlocked - */ -void __sched rt_mutex_unlock(struct rt_mutex *lock) -{ - mutex_release(&lock->dep_map, _RET_IP_); - if (likely(rt_mutex_cmpxchg_release(lock, current, NULL))) - return; - - rt_mutex_slowunlock(lock); -} -EXPORT_SYMBOL_GPL(rt_mutex_unlock); - -/* - * Futex variants, must not use fastpath. - */ -int __sched rt_mutex_futex_trylock(struct rt_mutex *lock) -{ - return rt_mutex_slowtrylock(lock); -} - -int __sched __rt_mutex_futex_trylock(struct rt_mutex *lock) -{ - return __rt_mutex_slowtrylock(lock); -} + struct rt_mutex_waiter waiter; + struct task_struct *owner; -/** - * __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) -{ lockdep_assert_held(&lock->wait_lock); - debug_rt_mutex_unlock(lock); - - if (!rt_mutex_has_waiters(lock)) { - lock->owner = NULL; - return false; /* done */ - } - - /* - * We've already deboosted, mark_wakeup_next_waiter() will - * retain preempt_disabled when we drop the wait_lock, to - * avoid inversion prior to the wakeup. preempt_disable() - * therein pairs with rt_mutex_postunlock(). - */ - mark_wakeup_next_waiter(wake_q, lock); - - return true; /* call postunlock() */ -} - -void __sched rt_mutex_futex_unlock(struct rt_mutex *lock) -{ - DEFINE_WAKE_Q(wake_q); - unsigned long flags; - bool postunlock; - - raw_spin_lock_irqsave(&lock->wait_lock, flags); - postunlock = __rt_mutex_futex_unlock(lock, &wake_q); - raw_spin_unlock_irqrestore(&lock->wait_lock, flags); - - if (postunlock) - rt_mutex_postunlock(&wake_q); -} - -/** - * __rt_mutex_init - initialize the rt_mutex - * - * @lock: The rt_mutex to be initialized - * @name: The lock name used for debugging - * @key: The lock class key used for debugging - * - * Initialize the rt_mutex to unlocked state. - * - * Initializing of a locked rt_mutex is not allowed - */ -void __sched __rt_mutex_init(struct rt_mutex *lock, const char *name, - struct lock_class_key *key) -{ - debug_check_no_locks_freed((void *)lock, sizeof(*lock)); - lockdep_init_map(&lock->dep_map, name, key, 0); + if (try_to_take_rt_mutex(lock, current, NULL)) + return; - __rt_mutex_basic_init(lock); -} -EXPORT_SYMBOL_GPL(__rt_mutex_init); + rt_mutex_init_rtlock_waiter(&waiter); -/** - * rt_mutex_init_proxy_locked - initialize and lock a rt_mutex on behalf of a - * proxy owner - * - * @lock: the rt_mutex to be locked - * @proxy_owner:the task to set as owner - * - * No locking. Caller has to do serializing itself - * - * Special API call for PI-futex support. This initializes the rtmutex and - * assigns it to @proxy_owner. Concurrent operations on the rtmutex are not - * possible at this point because the pi_state which contains the rtmutex - * is not yet visible to other tasks. - */ -void __sched rt_mutex_init_proxy_locked(struct rt_mutex *lock, - struct task_struct *proxy_owner) -{ - __rt_mutex_basic_init(lock); - rt_mutex_set_owner(lock, proxy_owner); -} + /* Save current state and set state to TASK_RTLOCK_WAIT */ + current_save_and_set_rtlock_wait_state(); -/** - * rt_mutex_proxy_unlock - release a lock on behalf of owner - * - * @lock: the rt_mutex to be locked - * - * No locking. Caller has to do serializing itself - * - * Special API call for PI-futex support. This merrily cleans up the rtmutex - * (debugging) state. Concurrent operations on this rt_mutex are not - * possible because it belongs to the pi_state which is about to be freed - * and it is not longer visible to other tasks. - */ -void __sched rt_mutex_proxy_unlock(struct rt_mutex *lock) -{ - debug_rt_mutex_proxy_unlock(lock); - rt_mutex_set_owner(lock, NULL); -} + task_blocks_on_rt_mutex(lock, &waiter, current, RT_MUTEX_MIN_CHAINWALK); -/** - * __rt_mutex_start_proxy_lock() - Start lock acquisition for another task - * @lock: the rt_mutex to take - * @waiter: the pre-initialized rt_mutex_waiter - * @task: the task to prepare - * - * Starts the rt_mutex acquire; it enqueues the @waiter and does deadlock - * detection. It does not wait, see rt_mutex_wait_proxy_lock() for that. - * - * NOTE: does _NOT_ remove the @waiter on failure; must either call - * rt_mutex_wait_proxy_lock() or rt_mutex_cleanup_proxy_lock() after this. - * - * Returns: - * 0 - task blocked on lock - * 1 - acquired the lock for task, caller should wake it up - * <0 - error - * - * Special API call for PI-futex support. - */ -int __sched __rt_mutex_start_proxy_lock(struct rt_mutex *lock, - struct rt_mutex_waiter *waiter, - struct task_struct *task) -{ - int ret; - - lockdep_assert_held(&lock->wait_lock); + for (;;) { + /* Try to acquire the lock again. */ + if (try_to_take_rt_mutex(lock, current, &waiter)) + break; - if (try_to_take_rt_mutex(lock, task, NULL)) - return 1; + if (&waiter == rt_mutex_top_waiter(lock)) + owner = rt_mutex_owner(lock); + else + owner = NULL; + raw_spin_unlock_irq(&lock->wait_lock); - /* We enforce deadlock detection for futexes */ - ret = task_blocks_on_rt_mutex(lock, waiter, task, - RT_MUTEX_FULL_CHAINWALK); + if (!owner || !rtlock_adaptive_spinwait(lock, owner)) + schedule_rtlock(); - if (ret && !rt_mutex_owner(lock)) { - /* - * Reset the return value. We might have - * returned with -EDEADLK and the owner - * released the lock while we were walking the - * pi chain. Let the waiter sort it out. - */ - ret = 0; + raw_spin_lock_irq(&lock->wait_lock); + set_current_state(TASK_RTLOCK_WAIT); } - return ret; -} - -/** - * rt_mutex_start_proxy_lock() - Start lock acquisition for another task - * @lock: the rt_mutex to take - * @waiter: the pre-initialized rt_mutex_waiter - * @task: the task to prepare - * - * Starts the rt_mutex acquire; it enqueues the @waiter and does deadlock - * detection. It does not wait, see rt_mutex_wait_proxy_lock() for that. - * - * NOTE: unlike __rt_mutex_start_proxy_lock this _DOES_ remove the @waiter - * on failure. - * - * Returns: - * 0 - task blocked on lock - * 1 - acquired the lock for task, caller should wake it up - * <0 - error - * - * Special API call for PI-futex support. - */ -int __sched rt_mutex_start_proxy_lock(struct rt_mutex *lock, - struct rt_mutex_waiter *waiter, - struct task_struct *task) -{ - int ret; - - raw_spin_lock_irq(&lock->wait_lock); - ret = __rt_mutex_start_proxy_lock(lock, waiter, task); - if (unlikely(ret)) - remove_waiter(lock, waiter); - raw_spin_unlock_irq(&lock->wait_lock); - - return ret; -} - -/** - * rt_mutex_wait_proxy_lock() - Wait for lock acquisition - * @lock: the rt_mutex we were woken on - * @to: the timeout, null if none. hrtimer should already have - * been started. - * @waiter: the pre-initialized rt_mutex_waiter - * - * Wait for the lock acquisition started on our behalf by - * rt_mutex_start_proxy_lock(). Upon failure, the caller must call - * rt_mutex_cleanup_proxy_lock(). - * - * Returns: - * 0 - success - * <0 - error, one of -EINTR, -ETIMEDOUT - * - * Special API call for PI-futex support - */ -int __sched rt_mutex_wait_proxy_lock(struct rt_mutex *lock, - struct hrtimer_sleeper *to, - struct rt_mutex_waiter *waiter) -{ - int ret; + /* Restore the task state */ + current_restore_rtlock_saved_state(); - 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); /* - * try_to_take_rt_mutex() sets the waiter bit unconditionally. We might - * have to fix that up. + * try_to_take_rt_mutex() sets the waiter bit unconditionally. We + * might have to fix that up: */ fixup_rt_mutex_waiters(lock); - raw_spin_unlock_irq(&lock->wait_lock); - - return ret; + debug_rt_mutex_free_waiter(&waiter); } -/** - * rt_mutex_cleanup_proxy_lock() - Cleanup failed lock acquisition - * @lock: the rt_mutex we were woken on - * @waiter: the pre-initialized rt_mutex_waiter - * - * Attempt to clean up after a failed __rt_mutex_start_proxy_lock() or - * rt_mutex_wait_proxy_lock(). - * - * Unless we acquired the lock; we're still enqueued on the wait-list and can - * in fact still be granted ownership until we're removed. Therefore we can - * find we are in fact the owner and must disregard the - * rt_mutex_wait_proxy_lock() failure. - * - * Returns: - * true - did the cleanup, we done. - * false - we acquired the lock after rt_mutex_wait_proxy_lock() returned, - * caller should disregards its return value. - * - * Special API call for PI-futex support - */ -bool __sched rt_mutex_cleanup_proxy_lock(struct rt_mutex *lock, - struct rt_mutex_waiter *waiter) +static __always_inline void __sched rtlock_slowlock(struct rt_mutex *lock) { - bool cleanup = false; - - raw_spin_lock_irq(&lock->wait_lock); - /* - * Do an unconditional try-lock, this deals with the lock stealing - * state where __rt_mutex_futex_unlock() -> mark_wakeup_next_waiter() - * sets a NULL owner. - * - * We're not interested in the return value, because the subsequent - * test on rt_mutex_owner() will infer that. If the trylock succeeded, - * we will own the lock and it will have removed the waiter. If we - * failed the trylock, we're still not owner and we need to remove - * ourselves. - */ - try_to_take_rt_mutex(lock, current, waiter); - /* - * Unless we're the owner; we're still enqueued on the wait_list. - * So check if we became owner, if not, take us off the wait_list. - */ - if (rt_mutex_owner(lock) != current) { - remove_waiter(lock, waiter); - cleanup = true; - } - /* - * try_to_take_rt_mutex() sets the waiter bit unconditionally. We might - * have to fix that up. - */ - fixup_rt_mutex_waiters(lock); - - raw_spin_unlock_irq(&lock->wait_lock); + unsigned long flags; - return cleanup; + raw_spin_lock_irqsave(&lock->wait_lock, flags); + rtlock_slowlock_locked(lock); + raw_spin_unlock_irqrestore(&lock->wait_lock, flags); } -#ifdef CONFIG_DEBUG_RT_MUTEXES -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); -} -#endif +#endif /* RT_MUTEX_BUILD_SPINLOCKS */ diff --git a/kernel/locking/rtmutex_api.c b/kernel/locking/rtmutex_api.c new file mode 100644 index 000000000000..e4eed067873c --- /dev/null +++ b/kernel/locking/rtmutex_api.c @@ -0,0 +1,647 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * rtmutex API + */ +#include <linux/spinlock.h> +#include <linux/export.h> + +#define RT_MUTEX_BUILD_MUTEX +#include "rtmutex.c" + +/* + * Max number of times we'll walk the boosting chain: + */ +int max_lock_depth = 1024; + +/* + * Debug aware fast / slowpath lock,trylock,unlock + * + * The atomic acquire/release ops are compiled away, when either the + * architecture does not support cmpxchg or when debugging is enabled. + */ +static __always_inline int __rt_mutex_lock_common(struct rt_mutex *lock, + unsigned int state, + unsigned int subclass) +{ + int ret; + + might_sleep(); + mutex_acquire(&lock->dep_map, subclass, 0, _RET_IP_); + ret = __rt_mutex_lock(lock, state); + if (ret) + mutex_release(&lock->dep_map, _RET_IP_); + return ret; +} + +#ifdef CONFIG_DEBUG_LOCK_ALLOC +/** + * rt_mutex_lock_nested - lock a rt_mutex + * + * @lock: the rt_mutex to be locked + * @subclass: the lockdep subclass + */ +void __sched rt_mutex_lock_nested(struct rt_mutex *lock, unsigned int subclass) +{ + __rt_mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, subclass); +} +EXPORT_SYMBOL_GPL(rt_mutex_lock_nested); + +#else /* !CONFIG_DEBUG_LOCK_ALLOC */ + +/** + * rt_mutex_lock - lock a rt_mutex + * + * @lock: the rt_mutex to be locked + */ +void __sched rt_mutex_lock(struct rt_mutex *lock) +{ + __rt_mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, 0); +} +EXPORT_SYMBOL_GPL(rt_mutex_lock); +#endif + +/** + * rt_mutex_lock_interruptible - lock a rt_mutex interruptible + * + * @lock: the rt_mutex to be locked + * + * Returns: + * 0 on success + * -EINTR when interrupted by a signal + */ +int __sched rt_mutex_lock_interruptible(struct rt_mutex *lock) +{ + return __rt_mutex_lock_common(lock, TASK_INTERRUPTIBLE, 0); +} +EXPORT_SYMBOL_GPL(rt_mutex_lock_interruptible); + +/** + * rt_mutex_trylock - try to lock a rt_mutex + * + * @lock: the rt_mutex to be locked + * + * This function can only be called in thread context. It's safe to call it + * from atomic regions, but not from hard or soft interrupt context. + * + * Returns: + * 1 on success + * 0 on contention + */ +int __sched rt_mutex_trylock(struct rt_mutex *lock) +{ + int ret; + + if (IS_ENABLED(CONFIG_DEBUG_RT_MUTEXES) && WARN_ON_ONCE(!in_task())) + return 0; + + ret = __rt_mutex_trylock(lock); + if (ret) + mutex_acquire(&lock->dep_map, 0, 1, _RET_IP_); + + return ret; +} +EXPORT_SYMBOL_GPL(rt_mutex_trylock); + +/** + * rt_mutex_unlock - unlock a rt_mutex + * + * @lock: the rt_mutex to be unlocked + */ +void __sched rt_mutex_unlock(struct rt_mutex *lock) +{ + mutex_release(&lock->dep_map, _RET_IP_); + __rt_mutex_unlock(lock); +} +EXPORT_SYMBOL_GPL(rt_mutex_unlock); + +/* + * Futex variants, must not use fastpath. + */ +int __sched rt_mutex_futex_trylock(struct rt_mutex *lock) +{ + return rt_mutex_slowtrylock(lock); +} + +int __sched __rt_mutex_futex_trylock(struct rt_mutex *lock) +{ + return __rt_mutex_slowtrylock(lock); +} + +/** + * __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 + * @wqh: The wake queue head from which to get the next lock waiter + */ +bool __sched __rt_mutex_futex_unlock(struct rt_mutex *lock, + struct rt_mutex_wake_q_head *wqh) +{ + lockdep_assert_held(&lock->wait_lock); + + debug_rt_mutex_unlock(lock); + + if (!rt_mutex_has_waiters(lock)) { + lock->owner = NULL; + return false; /* done */ + } + + /* + * We've already deboosted, mark_wakeup_next_waiter() will + * retain preempt_disabled when we drop the wait_lock, to + * avoid inversion prior to the wakeup. preempt_disable() + * therein pairs with rt_mutex_postunlock(). + */ + mark_wakeup_next_waiter(wqh, lock); + + return true; /* call postunlock() */ +} + +void __sched rt_mutex_futex_unlock(struct rt_mutex *lock) +{ + DEFINE_RT_MUTEX_WAKE_Q_HEAD(wqh); + unsigned long flags; + bool postunlock; + + raw_spin_lock_irqsave(&lock->wait_lock, flags); + postunlock = __rt_mutex_futex_unlock(lock, &wqh); + raw_spin_unlock_irqrestore(&lock->wait_lock, flags); + + if (postunlock) + rt_mutex_postunlock(&wqh); +} + +/** + * __rt_mutex_init - initialize the rt_mutex + * + * @lock: The rt_mutex to be initialized + * @name: The lock name used for debugging + * @key: The lock class key used for debugging + * + * Initialize the rt_mutex to unlocked state. + * + * Initializing of a locked rt_mutex is not allowed + */ +void __sched __rt_mutex_init(struct rt_mutex *lock, const char *name, + struct lock_class_key *key) +{ + debug_check_no_locks_freed((void *)lock, sizeof(*lock)); + lockdep_init_map(&lock->dep_map, name, key, 0); + + __rt_mutex_basic_init(lock); +} +EXPORT_SYMBOL_GPL(__rt_mutex_init); + +/** + * rt_mutex_init_proxy_locked - initialize and lock a rt_mutex on behalf of a + * proxy owner + * + * @lock: the rt_mutex to be locked + * @proxy_owner:the task to set as owner + * + * No locking. Caller has to do serializing itself + * + * Special API call for PI-futex support. This initializes the rtmutex and + * assigns it to @proxy_owner. Concurrent operations on the rtmutex are not + * possible at this point because the pi_state which contains the rtmutex + * is not yet visible to other tasks. + */ +void __sched rt_mutex_init_proxy_locked(struct rt_mutex *lock, + struct task_struct *proxy_owner) +{ + static struct lock_class_key pi_futex_key; + + __rt_mutex_basic_init(lock); + /* + * On PREEMPT_RT the futex hashbucket spinlock becomes 'sleeping' + * and rtmutex based. That causes a lockdep false positive because + * some of the futex functions invoke spin_unlock(&hb->lock) with + * the wait_lock of the rtmutex associated to the pi_futex held. + * spin_unlock() in turn takes wait_lock of the rtmutex on which + * the spinlock is based which makes lockdep notice a lock + * recursion. Give the futex/rtmutex wait_lock a seperate key. + */ + lockdep_set_class(&lock->wait_lock, &pi_futex_key); + rt_mutex_set_owner(lock, proxy_owner); +} + +/** + * rt_mutex_proxy_unlock - release a lock on behalf of owner + * + * @lock: the rt_mutex to be locked + * + * No locking. Caller has to do serializing itself + * + * Special API call for PI-futex support. This just cleans up the rtmutex + * (debugging) state. Concurrent operations on this rt_mutex are not + * possible because it belongs to the pi_state which is about to be freed + * and it is not longer visible to other tasks. + */ +void __sched rt_mutex_proxy_unlock(struct rt_mutex *lock) +{ + debug_rt_mutex_proxy_unlock(lock); + rt_mutex_set_owner(lock, NULL); +} + +/** + * __rt_mutex_start_proxy_lock() - Start lock acquisition for another task + * @lock: the rt_mutex to take + * @waiter: the pre-initialized rt_mutex_waiter + * @task: the task to prepare + * + * Starts the rt_mutex acquire; it enqueues the @waiter and does deadlock + * detection. It does not wait, see rt_mutex_wait_proxy_lock() for that. + * + * NOTE: does _NOT_ remove the @waiter on failure; must either call + * rt_mutex_wait_proxy_lock() or rt_mutex_cleanup_proxy_lock() after this. + * + * Returns: + * 0 - task blocked on lock + * 1 - acquired the lock for task, caller should wake it up + * <0 - error + * + * Special API call for PI-futex support. + */ +int __sched __rt_mutex_start_proxy_lock(struct rt_mutex *lock, + struct rt_mutex_waiter *waiter, + struct task_struct *task) +{ + int ret; + + lockdep_assert_held(&lock->wait_lock); + + if (try_to_take_rt_mutex(lock, task, NULL)) + return 1; + + /* We enforce deadlock detection for futexes */ + ret = task_blocks_on_rt_mutex(lock, waiter, task, + RT_MUTEX_FULL_CHAINWALK); + + if (ret && !rt_mutex_owner(lock)) { + /* + * Reset the return value. We might have + * returned with -EDEADLK and the owner + * released the lock while we were walking the + * pi chain. Let the waiter sort it out. + */ + ret = 0; + } + + return ret; +} + +/** + * rt_mutex_start_proxy_lock() - Start lock acquisition for another task + * @lock: the rt_mutex to take + * @waiter: the pre-initialized rt_mutex_waiter + * @task: the task to prepare + * + * Starts the rt_mutex acquire; it enqueues the @waiter and does deadlock + * detection. It does not wait, see rt_mutex_wait_proxy_lock() for that. + * + * NOTE: unlike __rt_mutex_start_proxy_lock this _DOES_ remove the @waiter + * on failure. + * + * Returns: + * 0 - task blocked on lock + * 1 - acquired the lock for task, caller should wake it up + * <0 - error + * + * Special API call for PI-futex support. + */ +int __sched rt_mutex_start_proxy_lock(struct rt_mutex *lock, + struct rt_mutex_waiter *waiter, + struct task_struct *task) +{ + int ret; + + raw_spin_lock_irq(&lock->wait_lock); + ret = __rt_mutex_start_proxy_lock(lock, waiter, task); + if (unlikely(ret)) + remove_waiter(lock, waiter); + raw_spin_unlock_irq(&lock->wait_lock); + + return ret; +} + +/** + * rt_mutex_wait_proxy_lock() - Wait for lock acquisition + * @lock: the rt_mutex we were woken on + * @to: the timeout, null if none. hrtimer should already have + * been started. + * @waiter: the pre-initialized rt_mutex_waiter + * + * Wait for the lock acquisition started on our behalf by + * rt_mutex_start_proxy_lock(). Upon failure, the caller must call + * rt_mutex_cleanup_proxy_lock(). + * + * Returns: + * 0 - success + * <0 - error, one of -EINTR, -ETIMEDOUT + * + * Special API call for PI-futex support + */ +int __sched rt_mutex_wait_proxy_lock(struct rt_mutex *lock, + struct hrtimer_sleeper *to, + struct rt_mutex_waiter *waiter) +{ + int ret; + + raw_spin_lock_irq(&lock->wait_lock); + /* sleep on the mutex */ + set_current_state(TASK_INTERRUPTIBLE); + ret = rt_mutex_slowlock_block(lock, TASK_INTERRUPTIBLE, to, waiter); + /* + * try_to_take_rt_mutex() sets the waiter bit unconditionally. We might + * have to fix that up. + */ + fixup_rt_mutex_waiters(lock); + raw_spin_unlock_irq(&lock->wait_lock); + + return ret; +} + +/** + * rt_mutex_cleanup_proxy_lock() - Cleanup failed lock acquisition + * @lock: the rt_mutex we were woken on + * @waiter: the pre-initialized rt_mutex_waiter + * + * Attempt to clean up after a failed __rt_mutex_start_proxy_lock() or + * rt_mutex_wait_proxy_lock(). + * + * Unless we acquired the lock; we're still enqueued on the wait-list and can + * in fact still be granted ownership until we're removed. Therefore we can + * find we are in fact the owner and must disregard the + * rt_mutex_wait_proxy_lock() failure. + * + * Returns: + * true - did the cleanup, we done. + * false - we acquired the lock after rt_mutex_wait_proxy_lock() returned, + * caller should disregards its return value. + * + * Special API call for PI-futex support + */ +bool __sched rt_mutex_cleanup_proxy_lock(struct rt_mutex *lock, + struct rt_mutex_waiter *waiter) +{ + bool cleanup = false; + + raw_spin_lock_irq(&lock->wait_lock); + /* + * Do an unconditional try-lock, this deals with the lock stealing + * state where __rt_mutex_futex_unlock() -> mark_wakeup_next_waiter() + * sets a NULL owner. + * + * We're not interested in the return value, because the subsequent + * test on rt_mutex_owner() will infer that. If the trylock succeeded, + * we will own the lock and it will have removed the waiter. If we + * failed the trylock, we're still not owner and we need to remove + * ourselves. + */ + try_to_take_rt_mutex(lock, current, waiter); + /* + * Unless we're the owner; we're still enqueued on the wait_list. + * So check if we became owner, if not, take us off the wait_list. + */ + if (rt_mutex_owner(lock) != current) { + remove_waiter(lock, waiter); + cleanup = true; + } + /* + * try_to_take_rt_mutex() sets the waiter bit unconditionally. We might + * have to fix that up. + */ + fixup_rt_mutex_waiters(lock); + + raw_spin_unlock_irq(&lock->wait_lock); + + return cleanup; +} + +/* + * Recheck the pi chain, in case we got a priority setting + * + * Called from sched_setscheduler + */ +void __sched rt_mutex_adjust_pi(struct task_struct *task) +{ + struct rt_mutex_waiter *waiter; + struct rt_mutex *next_lock; + unsigned long flags; + + raw_spin_lock_irqsave(&task->pi_lock, flags); + + waiter = task->pi_blocked_on; + if (!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); + + rt_mutex_adjust_prio_chain(task, RT_MUTEX_MIN_CHAINWALK, NULL, + next_lock, NULL, task); +} + +/* + * Performs the wakeup of the top-waiter and re-enables preemption. + */ +void __sched rt_mutex_postunlock(struct rt_mutex_wake_q_head *wqh) +{ + rt_mutex_wake_up_q(wqh); +} + +#ifdef CONFIG_DEBUG_RT_MUTEXES +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); +} +#endif + +/* Interfaces for PREEMPT_RT lock substitutions */ +#ifdef CONFIG_PREEMPT_RT +/** + * rwsem_rt_mutex_slowlock_locked - Lock slowpath invoked with @lock::wait_lock held + * @lock: The rtmutex to acquire + * @state: The task state for blocking + */ +int __sched rwsem_rt_mutex_slowlock_locked(struct rt_mutex *lock, + unsigned int state) +{ + return __rt_mutex_slowlock_locked(lock, state); +} + +/** + * rwsem_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 + * + * The function does no lockdep operations on @lock. The lockdep state + * changes have to be done on the callsite related to the locking primitive + * which embeds the rtmutex. Otherwise lockdep has double tracking. + */ +int __sched rwsem_rt_mutex_lock_state(struct rt_mutex *lock, unsigned int state) +{ + return __rt_mutex_lock(lock, state); +} + +/** + * rwsem_rt_mutex_try_lock_nolockdep - Try to lock a rt_mutex + * @lock: The rt_mutex to be locked + * + * The function does no lockdep operations on @lock. The lockdep state + * changes have to be done on the callsite related to the locking primitive + * which embeds the rtmutex. Otherwise lockdep has double tracking. + */ +int __sched rwsem_rt_mutex_trylock(struct rt_mutex *lock) +{ + if (IS_ENABLED(CONFIG_DEBUG_RT_MUTEXES) && + WARN_ON_ONCE(in_nmi() | in_hardirq())) + return 0; + + if (likely(rt_mutex_cmpxchg_acquire(lock, NULL, current))) + return 1; + + return rt_mutex_slowtrylock(lock); +} + +/** + * rwsem_rt_mutex_unlock - Unlock a rt_mutex + * @lock: The rt_mutex to be unlocked + * + * The function does no lockdep operations on @lock. The lockdep state + * changes have to be done on the callsite related to the locking primitive + * which embeds the rtmutex. Otherwise lockdep has double tracking. + */ +void rwsem_rt_mutex_unlock(struct rt_mutex *lock) +{ + if (likely(rt_mutex_cmpxchg_acquire(lock, current, NULL))) + return; + + rt_mutex_slowunlock(lock); +} + +/* Mutexes */ +void __mutex_rt_init(struct mutex *mutex, const char *name, + struct lock_class_key *key) +{ + debug_check_no_locks_freed((void *)mutex, sizeof(*mutex)); + lockdep_init_map(&mutex->dep_map, name, key, 0); +} +EXPORT_SYMBOL(__mutex_rt_init); + +static __always_inline int __mutex_lock_common(struct mutex *lock, + unsigned int state, + unsigned int subclass, + struct lockdep_map *nest_lock, + unsigned long ip) +{ + int ret; + + might_sleep(); + mutex_acquire_nest(&lock->dep_map, subclass, 0, nest_lock, ip); + ret = __rt_mutex_lock(&lock->rtmutex, state); + if (ret) + mutex_release(&lock->dep_map, ip); + else + lock_acquired(&lock->dep_map, ip); + return ret; +} + +#ifdef CONFIG_DEBUG_LOCK_ALLOC +void __sched mutex_lock_nested(struct mutex *lock, unsigned int subclass) +{ + __mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, subclass, NULL, _RET_IP_); +} +EXPORT_SYMBOL_GPL(mutex_lock_nested); + +void __sched _mutex_lock_nest_lock(struct mutex *lock, + struct lockdep_map *nest_lock) +{ + __mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, 0, nest_lock, _RET_IP_); +} +EXPORT_SYMBOL_GPL(_mutex_lock_nest_lock); + +int __sched mutex_lock_interruptible_nested(struct mutex *lock, + unsigned int subclass) +{ + return __mutex_lock_common(lock, TASK_INTERRUPTIBLE, subclass, NULL, _RET_IP_); +} +EXPORT_SYMBOL_GPL(mutex_lock_interruptible_nested); + +int __sched mutex_lock_killable_nested(struct mutex *lock, + unsigned int subclass) +{ + return __mutex_lock_common(lock, TASK_KILLABLE, subclass, NULL, _RET_IP_); +} +EXPORT_SYMBOL_GPL(mutex_lock_killable_nested); + +void __sched mutex_lock_io_nested(struct mutex *lock, unsigned int subclass) +{ + int token; + + might_sleep(); + + token = io_schedule_prepare(); + __mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, subclass, NULL, _RET_IP_); + io_schedule_finish(token); +} +EXPORT_SYMBOL_GPL(mutex_lock_io_nested); + +#else /* CONFIG_DEBUG_LOCK_ALLOC */ + +void __sched mutex_lock(struct mutex *lock) +{ + __mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, 0, NULL, _RET_IP_); +} +EXPORT_SYMBOL(mutex_lock); + +int __sched mutex_lock_interruptible(struct mutex *lock) +{ + return __mutex_lock_common(lock, TASK_INTERRUPTIBLE, 0, NULL, _RET_IP_); +} +EXPORT_SYMBOL(mutex_lock_interruptible); + +int __sched mutex_lock_killable(struct mutex *lock) +{ + return __mutex_lock_common(lock, TASK_KILLABLE, 0, NULL, _RET_IP_); +} +EXPORT_SYMBOL(mutex_lock_killable); + +void __sched mutex_lock_io(struct mutex *lock) +{ + int token = io_schedule_prepare(); + + __mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, 0, NULL, _RET_IP_); + io_schedule_finish(token); +} +EXPORT_SYMBOL(mutex_lock_io); +#endif /* !CONFIG_DEBUG_LOCK_ALLOC */ + +int __sched mutex_trylock(struct mutex *lock) +{ + int ret; + + if (IS_ENABLED(CONFIG_DEBUG_RT_MUTEXES) && WARN_ON_ONCE(!in_task())) + return 0; + + ret = __rt_mutex_trylock(&lock->rtmutex); + if (ret) + mutex_acquire(&lock->dep_map, 0, 1, _RET_IP_); + + return ret; +} +EXPORT_SYMBOL(mutex_trylock); + +void __sched mutex_unlock(struct mutex *lock) +{ + mutex_release(&lock->dep_map, _RET_IP_); + __rt_mutex_unlock(&lock->rtmutex); +} +EXPORT_SYMBOL(mutex_unlock); + +#endif /* CONFIG_PREEMPT_RT */ diff --git a/kernel/locking/rtmutex_common.h b/kernel/locking/rtmutex_common.h index a90c22abdbca..fecc839cf082 100644 --- a/kernel/locking/rtmutex_common.h +++ b/kernel/locking/rtmutex_common.h @@ -25,6 +25,7 @@ * @pi_tree_entry: pi node to enqueue into the mutex owner waiters tree * @task: task reference to the blocked task * @lock: Pointer to the rt_mutex on which the waiter blocks + * @wake_state: Wakeup state to use (TASK_NORMAL or TASK_RTLOCK_WAIT) * @prio: Priority of the waiter * @deadline: Deadline of the waiter if applicable */ @@ -33,10 +34,61 @@ struct rt_mutex_waiter { struct rb_node pi_tree_entry; struct task_struct *task; struct rt_mutex *lock; + int wake_state; int prio; u64 deadline; }; +/** + * rt_mutex_wake_q_head - Wrapper around regular wake_q_head to support + * "sleeping" spinlocks on RT + * @head: The regular wake_q_head for sleeping lock variants + * @rtlock_task: Task pointer for RT lock (spin/rwlock) wakeups + */ +struct rt_mutex_wake_q_head { + struct wake_q_head head; + struct task_struct *rtlock_task; +}; + +#define DEFINE_RT_MUTEX_WAKE_Q_HEAD(name) \ + struct rt_mutex_wake_q_head name = { \ + .head = WAKE_Q_HEAD_INITIALIZER(name.head), \ + .rtlock_task = NULL, \ + } + +/* + * PI-futex support (proxy locking functions, etc.): + */ +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 int __rt_mutex_start_proxy_lock(struct rt_mutex *lock, + struct rt_mutex_waiter *waiter, + struct task_struct *task); +extern int rt_mutex_start_proxy_lock(struct rt_mutex *lock, + struct rt_mutex_waiter *waiter, + struct task_struct *task); +extern int rt_mutex_wait_proxy_lock(struct rt_mutex *lock, + struct hrtimer_sleeper *to, + struct rt_mutex_waiter *waiter); +extern bool rt_mutex_cleanup_proxy_lock(struct rt_mutex *lock, + struct rt_mutex_waiter *waiter); + +extern int rt_mutex_futex_trylock(struct rt_mutex *l); +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 rt_mutex_wake_q_head *wqh); + +extern void rt_mutex_postunlock(struct rt_mutex_wake_q_head *wqh); + +/* Special interfaces for RT lock substitutions */ +int rwsem_rt_mutex_slowlock_locked(struct rt_mutex *lock, unsigned int state); +int rwsem_rt_mutex_lock_state(struct rt_mutex *lock, unsigned int state); +int rwsem_rt_mutex_trylock(struct rt_mutex *lock); +void rwsem_rt_mutex_unlock(struct rt_mutex *lock); + /* * Must be guarded because this header is included from rcu/tree_plugin.h * unconditionally. @@ -78,13 +130,6 @@ static inline struct task_struct *rt_mutex_owner(struct rt_mutex *lock) return (struct task_struct *) (owner & ~RT_MUTEX_HAS_WAITERS); } -#else /* CONFIG_RT_MUTEXES */ -/* Used in rcu/tree_plugin.h */ -static inline struct task_struct *rt_mutex_owner(struct rt_mutex *lock) -{ - return NULL; -} -#endif /* !CONFIG_RT_MUTEXES */ /* * Constants for rt mutex functions which have a selectable deadlock @@ -108,34 +153,6 @@ static inline void __rt_mutex_basic_init(struct rt_mutex *lock) lock->waiters = RB_ROOT_CACHED; } -/* - * PI-futex support (proxy locking functions, etc.): - */ -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 int __rt_mutex_start_proxy_lock(struct rt_mutex *lock, - struct rt_mutex_waiter *waiter, - struct task_struct *task); -extern int rt_mutex_start_proxy_lock(struct rt_mutex *lock, - struct rt_mutex_waiter *waiter, - struct task_struct *task); -extern int rt_mutex_wait_proxy_lock(struct rt_mutex *lock, - struct hrtimer_sleeper *to, - struct rt_mutex_waiter *waiter); -extern bool rt_mutex_cleanup_proxy_lock(struct rt_mutex *lock, - struct rt_mutex_waiter *waiter); - -extern int rt_mutex_futex_trylock(struct rt_mutex *l); -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); - -extern void rt_mutex_postunlock(struct wake_q_head *wake_q); - /* Debug functions */ static inline void debug_rt_mutex_unlock(struct rt_mutex *lock) { @@ -161,4 +178,27 @@ static inline void debug_rt_mutex_free_waiter(struct rt_mutex_waiter *waiter) memset(waiter, 0x22, sizeof(*waiter)); } +static inline void rt_mutex_init_waiter(struct rt_mutex_waiter *waiter) +{ + debug_rt_mutex_init_waiter(waiter); + RB_CLEAR_NODE(&waiter->pi_tree_entry); + RB_CLEAR_NODE(&waiter->tree_entry); + waiter->wake_state = TASK_NORMAL; + waiter->task = NULL; +} + +static inline void rt_mutex_init_rtlock_waiter(struct rt_mutex_waiter *waiter) +{ + rt_mutex_init_waiter(waiter); + waiter->wake_state = TASK_RTLOCK_WAIT; +} + +#else /* CONFIG_RT_MUTEXES */ +/* Used in rcu/tree_plugin.h */ +static inline struct task_struct *rt_mutex_owner(struct rt_mutex *lock) +{ + return NULL; +} +#endif /* !CONFIG_RT_MUTEXES */ + #endif diff --git a/kernel/locking/rwbase_rt.c b/kernel/locking/rwbase_rt.c new file mode 100644 index 000000000000..c8d5c77954c4 --- /dev/null +++ b/kernel/locking/rwbase_rt.c @@ -0,0 +1,266 @@ +// SPDX-License-Identifier: GPL-2.0-only + +/* + * RT-specific reader/writer semaphores and reader/writer locks + * + * down_write/write_lock() + * 1) 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 + * + * up_write/write_unlock() + * 1) Remove the write locked marker + * 2) Set the reader BIAS so readers can use the fast path again + * 3) Unlock rtmutex to release blocked readers + * + * down_read/read_lock() + * 1) Try fast path acquisition (reader BIAS is set) + * 2) Take tmutex::wait_lock which protects the writelocked flag + * 3) If !writelocked, acquire it for read + * 4) If writelocked, block on tmutex + * 5) unlock rtmutex, goto 1) + * + * up_read/read_unlock() + * 1) Try fast path release (reader count != 1) + * 2) Wake the writer waiting in down_write()/write_lock() #3 + * + * down_read/read_lock()#3 has the consequence, that rw semaphores and rw + * locks 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 primitives 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. + * + * Common code shared between RT rw_semaphore and rwlock + */ + +static __always_inline int rwbase_read_trylock(struct rwbase_rt *rwb) +{ + int r, old; + + /* + * Increment reader count, if sem->readers < 0, i.e. READER_BIAS is + * set. + */ + for (r = atomic_read(&rwb->readers); r < 0;) { + old = atomic_cmpxchg(&rwb->readers, r, r + 1); + if (likely(old == r)) + return 1; + r = old; + } + return 0; +} + +static int __sched __rwbase_read_lock(struct rwbase_rt *rwb, + unsigned int state) +{ + struct rt_mutex *rtm = &rwb->rtmutex; + int ret; + + raw_spin_lock_irq(&rtm->wait_lock); + /* + * Allow readers as long as the writer has not completely + * acquired the semaphore for write. + */ + if (atomic_read(&rwb->readers) != WRITER_BIAS) { + atomic_inc(&rwb->readers); + raw_spin_unlock_irq(&rtm->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) + * wait() + * down_read() + * unlock(m->wait_lock) + * up_read() + * wake(Writer) + * 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) + * wait() + * rtmutex_lock(m) + * + * That would put Reader1 behind the writer waiting on + * Reader2 to call up_read() which might be unbound. + */ + + /* + * For rwlocks this returns 0 unconditionally, so the below + * !ret conditionals are optimized out. + */ + ret = rwbase_rtmutex_slowlock_locked(rtm, state); + + /* + * On success the rtmutex is held, so there can't be a writer + * active. Increment the reader count and immediately drop the + * rtmutex again. + * + * rtmutex->wait_lock has to be unlocked in any case of course. + */ + if (!ret) + atomic_inc(&rwb->readers); + raw_spin_unlock_irq(&rtm->wait_lock); + if (!ret) + rwbase_rtmutex_unlock(rtm); + return ret; +} + +static __always_inline int rwbase_read_lock(struct rwbase_rt *rwb, + unsigned int state) +{ + if (rwbase_read_trylock(rwb)) + return 0; + + return __rwbase_read_lock(rwb, state); +} + +static void __sched __rwbase_read_unlock(struct rwbase_rt *rwb, + unsigned int state) +{ + struct rt_mutex *rtm = &rwb->rtmutex; + struct task_struct *owner; + + raw_spin_lock_irq(&rtm->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 rwb->readers it needs to acquire rtm->wait_lock. The + * worst case which can happen is a spurious wakeup. + */ + owner = rt_mutex_owner(rtm); + if (owner) + wake_up_state(owner, state); + + raw_spin_unlock_irq(&rtm->wait_lock); +} + +static __always_inline void rwbase_read_unlock(struct rwbase_rt *rwb, + unsigned int state) +{ + /* + * rwb->readers can only hit 0 when a writer is waiting for the + * active readers to leave the critical region. + */ + if (unlikely(atomic_dec_and_test(&rwb->readers))) + __rwbase_read_unlock(rwb, state); +} + +static inline void __rwbase_write_unlock(struct rwbase_rt *rwb, int bias, + unsigned long flags) +{ + struct rt_mutex *rtm = &rwb->rtmutex; + + atomic_add(READER_BIAS - bias, &rwb->readers); + raw_spin_unlock_irqrestore(&rtm->wait_lock, flags); + rwbase_rtmutex_unlock(rtm); +} + +static inline void rwbase_write_unlock(struct rwbase_rt *rwb) +{ + struct rt_mutex *rtm = &rwb->rtmutex; + unsigned long flags; + + raw_spin_lock_irqsave(&rtm->wait_lock, flags); + __rwbase_write_unlock(rwb, WRITER_BIAS, flags); +} + +static inline void rwbase_write_downgrade(struct rwbase_rt *rwb) +{ + struct rt_mutex *rtm = &rwb->rtmutex; + unsigned long flags; + + raw_spin_lock_irqsave(&rtm->wait_lock, flags); + /* Release it and account current as reader */ + __rwbase_write_unlock(rwb, WRITER_BIAS - 1, flags); + +} + +static int __sched rwbase_write_lock(struct rwbase_rt *rwb, + unsigned int state) +{ + struct rt_mutex *rtm = &rwb->rtmutex; + unsigned long flags; + + /* Take the rtmutex as a first step */ + if (rwbase_rtmutex_lock_state(rtm, state)) + return -EINTR; + + /* Force readers into slow path */ + atomic_sub(READER_BIAS, &rwb->readers); + + raw_spin_lock_irqsave(&rtm->wait_lock, flags); + /* + * set_current_state() for rw_semaphore + * current_save_and_set_rtlock_wait_state() for rwlock + */ + rwbase_set_and_save_current_state(state); + + /* Block until all readers have left the critical region. */ + for (; atomic_read(&rwb->readers);) { + /* Optimized out for rwlocks */ + if (rwbase_signal_pending_state(state, current)) { + __set_current_state(TASK_RUNNING); + __rwbase_write_unlock(rwb, 0, flags); + return -EINTR; + } + raw_spin_unlock_irqrestore(&rtm->wait_lock, flags); + + /* + * Schedule and wait for the readers to leave the critical + * section. The last reader leaving it wakes the waiter. + */ + if (atomic_read(&rwb->readers) != 0) + rwbase_schedule(); + set_current_state(state); + raw_spin_lock_irqsave(&rtm->wait_lock, flags); + } + + atomic_set(&rwb->readers, WRITER_BIAS); + rwbase_restore_current_state(); + raw_spin_unlock_irqrestore(&rtm->wait_lock, flags); + return 0; +} + +static inline int rwbase_write_trylock(struct rwbase_rt *rwb) +{ + struct rt_mutex *rtm = &rwb->rtmutex; + unsigned long flags; + + if (!rwbase_rtmutex_trylock(rtm)) + return 0; + + atomic_sub(READER_BIAS, &rwb->readers); + + raw_spin_lock_irqsave(&rtm->wait_lock, flags); + if (!atomic_read(&rwb->readers)) { + atomic_set(&rwb->readers, WRITER_BIAS); + raw_spin_unlock_irqrestore(&rtm->wait_lock, flags); + return 1; + } + __rwbase_write_unlock(rwb, 0, flags); + return 0; +} diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c index 809b0016d344..5870cddddb62 100644 --- a/kernel/locking/rwsem.c +++ b/kernel/locking/rwsem.c @@ -28,6 +28,7 @@ #include <linux/rwsem.h> #include <linux/atomic.h> +#ifndef CONFIG_PREEMPT_RT #include "lock_events.h" /* @@ -1344,6 +1345,113 @@ static inline void __downgrade_write(struct rw_semaphore *sem) rwsem_downgrade_wake(sem); } +#else /* !CONFIG_PREEMPT_RT */ + +#include "rtmutex_common.h" + +#define rwbase_set_and_save_current_state(state) \ + set_current_state(state) + +#define rwbase_restore_current_state() \ + __set_current_state(TASK_RUNNING) + +#define rwbase_rtmutex_lock_state(rtm, state) \ + rwsem_rt_mutex_lock_state(rtm, state) + +#define rwbase_rtmutex_slowlock_locked(rtm, state) \ + rwsem_rt_mutex_slowlock_locked(rtm, state) + +#define rwbase_rtmutex_unlock(rtm) \ + rwsem_rt_mutex_unlock(rtm) + +#define rwbase_rtmutex_trylock(rtm) \ + rwsem_rt_mutex_trylock(rtm) + +#define rwbase_signal_pending_state(state, current) \ + signal_pending_state(state, current) + +#define rwbase_schedule() \ + schedule() + +#include "rwbase_rt.c" + +#ifdef CONFIG_DEBUG_LOCK_ALLOC +void __rwsem_init(struct rw_semaphore *sem, const char *name, + struct lock_class_key *key) +{ + debug_check_no_locks_freed((void *)sem, sizeof(*sem)); + lockdep_init_map(&sem->dep_map, name, key, 0); +} +EXPORT_SYMBOL(__rwsem_init); +#endif + +static inline void __down_read(struct rw_semaphore *sem) +{ + rwbase_read_lock(&sem->rwbase, TASK_UNINTERRUPTIBLE); +} + +static inline int __down_read_interruptible(struct rw_semaphore *sem) +{ + return rwbase_read_lock(&sem->rwbase, TASK_INTERRUPTIBLE); +} + +static inline int __down_read_killable(struct rw_semaphore *sem) +{ + return rwbase_read_lock(&sem->rwbase, TASK_KILLABLE); +} + +static inline int __down_read_trylock(struct rw_semaphore *sem) +{ + return rwbase_read_trylock(&sem->rwbase); +} + +static inline void __up_read(struct rw_semaphore *sem) +{ + rwbase_read_unlock(&sem->rwbase, TASK_NORMAL); +} + +static inline void __sched __down_write(struct rw_semaphore *sem) +{ + rwbase_write_lock(&sem->rwbase, TASK_UNINTERRUPTIBLE); +} + +static inline int __sched __down_write_killable(struct rw_semaphore *sem) +{ + return rwbase_write_lock(&sem->rwbase, TASK_KILLABLE); +} + +static inline int __down_write_trylock(struct rw_semaphore *sem) +{ + return rwbase_write_trylock(&sem->rwbase); +} + +static inline void __up_write(struct rw_semaphore *sem) +{ + rwbase_write_unlock(&sem->rwbase); +} + +static inline void __downgrade_write(struct rw_semaphore *sem) +{ + rwbase_write_downgrade(&sem->rwbase); +} + +/* Debug stubs for the common API */ +#define DEBUG_RWSEMS_WARN_ON(c, sem) + +static inline void __rwsem_set_reader_owned(struct rw_semaphore *sem, + struct task_struct *owner) +{ +} + +static inline bool is_rwsem_reader_owned(struct rw_semaphore *sem) +{ + int count = atomic_read(&sem->rwbase.readers); + + return count < 0 && count != READER_BIAS; +} + +#endif /* CONFIG_PREEMPT_RT */ + /* * lock for reading */ diff --git a/kernel/locking/spinlock.c b/kernel/locking/spinlock.c index c8d7ad9fb9b2..c5830cfa379a 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 /* !CONFIG_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 b9d93087ee66..14235671a1a7 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 /* !CONFIG_PREEMPT_RT */ diff --git a/kernel/locking/spinlock_rt.c b/kernel/locking/spinlock_rt.c new file mode 100644 index 000000000000..85b19e41e26d --- /dev/null +++ b/kernel/locking/spinlock_rt.c @@ -0,0 +1,258 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * PREEMPT_RT substitution for spin/rw_locks + * + * spin_lock and rw_lock on RT are based on rtmutex with a few twists to + * resemble the non RT semantics + * + * - Contrary to a plain rtmutex, spin_lock and rw_lock are state + * preserving. The task state is saved before blocking on the underlying + * rtmutex and restored when the lock has been acquired. Regular wakeups + * during that time are redirected to the saved state so no wake up is + * missed. + * + * - Non RT spin/rw_locks disable preemption and evtl. interrupts. + * Disabling preemption has the side effect of disabling migration and + * preventing RCU grace periods. + * + * The RT substitutions explicitly disable migration and take + * rcu_read_lock() across the lock held section. + */ +#include <linux/spinlock.h> +#include <linux/export.h> + +#define RT_MUTEX_BUILD_SPINLOCKS +#include "rtmutex.c" + +static __always_inline void rtlock_lock(struct rt_mutex *rtm) +{ + if (unlikely(!rt_mutex_cmpxchg_acquire(rtm, NULL, current))) + rtlock_slowlock(rtm); +} + +static __always_inline void __rt_spin_lock(spinlock_t *lock) +{ + ___might_sleep(__FILE__, __LINE__, 0); + rtlock_lock(&lock->lock); + rcu_read_lock(); + migrate_disable(); +} + +void __sched rt_spin_lock(spinlock_t *lock) +{ + spin_acquire(&lock->dep_map, 0, 0, _RET_IP_); + __rt_spin_lock(lock); +} +EXPORT_SYMBOL(rt_spin_lock); + +#ifdef CONFIG_DEBUG_LOCK_ALLOC +void __sched rt_spin_lock_nested(spinlock_t *lock, int subclass) +{ + spin_acquire(&lock->dep_map, subclass, 0, _RET_IP_); + __rt_spin_lock(lock); +} +EXPORT_SYMBOL(rt_spin_lock_nested); + +void __sched 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(lock); +} +EXPORT_SYMBOL(rt_spin_lock_nest_lock); +#endif + +void __sched rt_spin_unlock(spinlock_t *lock) +{ + spin_release(&lock->dep_map, _RET_IP_); + migrate_enable(); + rcu_read_unlock(); + + if (unlikely(!rt_mutex_cmpxchg_release(&lock->lock, current, NULL))) + rt_mutex_slowunlock(&lock->lock); +} +EXPORT_SYMBOL(rt_spin_unlock); + +/* + * Wait for the lock to get unlocked: instead of polling for an unlock + * (like raw spinlocks do), lock and unlock, to force the kernel to + * schedule if there's contention: + */ +void __sched rt_spin_lock_unlock(spinlock_t *lock) +{ + spin_lock(lock); + spin_unlock(lock); +} +EXPORT_SYMBOL(rt_spin_lock_unlock); + +static __always_inline int __rt_spin_trylock(spinlock_t *lock) +{ + int ret = 1; + + if (unlikely(!rt_mutex_cmpxchg_acquire(&lock->lock, NULL, current))) + ret = rt_mutex_slowtrylock(&lock->lock); + + if (ret) { + spin_acquire(&lock->dep_map, 0, 1, _RET_IP_); + rcu_read_lock(); + migrate_disable(); + } + return ret; +} + +int __sched rt_spin_trylock(spinlock_t *lock) +{ + return __rt_spin_trylock(lock); +} +EXPORT_SYMBOL(rt_spin_trylock); + +int __sched rt_spin_trylock_bh(spinlock_t *lock) +{ + int ret; + + local_bh_disable(); + ret = __rt_spin_trylock(lock); + if (!ret) + local_bh_enable(); + return ret; +} +EXPORT_SYMBOL(rt_spin_trylock_bh); + +#ifdef CONFIG_DEBUG_LOCK_ALLOC +void __rt_spin_lock_init(spinlock_t *lock, const char *name, + struct lock_class_key *key) +{ + debug_check_no_locks_freed((void *)lock, sizeof(*lock)); + lockdep_init_map(&lock->dep_map, name, key, 0); +} +EXPORT_SYMBOL(__rt_spin_lock_init); +#endif + +/* + * RT-specific reader/writer locks + */ +#define rwbase_set_and_save_current_state(state) \ + current_save_and_set_rtlock_wait_state() + +#define rwbase_restore_current_state() \ + current_restore_rtlock_saved_state() + +static __always_inline int rwbase_rtmutex_lock_state(struct rt_mutex *rtm, + unsigned int state) +{ + if (unlikely(!rt_mutex_cmpxchg_acquire(rtm, NULL, current))) + rtlock_slowlock(rtm); + return 0; +} + +static __always_inline int rwbase_rtmutex_slowlock_locked(struct rt_mutex *rtm, + unsigned int state) +{ + rtlock_slowlock_locked(rtm); + return 0; +} + +static __always_inline void rwbase_rtmutex_unlock(struct rt_mutex *rtm) +{ + if (likely(rt_mutex_cmpxchg_acquire(rtm, current, NULL))) + return; + + rt_mutex_slowunlock(rtm); +} + +static __always_inline int rwbase_rtmutex_trylock(struct rt_mutex *rtm) +{ + if (likely(rt_mutex_cmpxchg_acquire(rtm, NULL, current))) + return 1; + + return rt_mutex_slowtrylock(rtm); +} + +#define rwbase_signal_pending_state(state, current) (0) + +#define rwbase_schedule() \ + schedule_rtlock() + +#include "rwbase_rt.c" +/* + * The common functions which get wrapped into the rwlock API. + */ +int __sched rt_read_trylock(rwlock_t *rwlock) +{ + int ret; + + ret = rwbase_read_trylock(&rwlock->rwbase); + 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 __sched rt_write_trylock(rwlock_t *rwlock) +{ + int ret; + + ret = rwbase_write_trylock(&rwlock->rwbase); + if (ret) { + rwlock_acquire(&rwlock->dep_map, 0, 1, _RET_IP_); + rcu_read_lock(); + migrate_disable(); + } + return ret; +} +EXPORT_SYMBOL(rt_write_trylock); + +void __sched rt_read_lock(rwlock_t *rwlock) +{ + rwlock_acquire_read(&rwlock->dep_map, 0, 0, _RET_IP_); + rwbase_read_lock(&rwlock->rwbase, TASK_RTLOCK_WAIT); + rcu_read_lock(); + migrate_disable(); +} +EXPORT_SYMBOL(rt_read_lock); + +void __sched rt_write_lock(rwlock_t *rwlock) +{ + rwlock_acquire(&rwlock->dep_map, 0, 0, _RET_IP_); + rwbase_write_lock(&rwlock->rwbase, TASK_RTLOCK_WAIT); + rcu_read_lock(); + migrate_disable(); +} +EXPORT_SYMBOL(rt_write_lock); + +void __sched rt_read_unlock(rwlock_t *rwlock) +{ + rwlock_release(&rwlock->dep_map, _RET_IP_); + migrate_enable(); + rcu_read_unlock(); + rwbase_read_unlock(&rwlock->rwbase, TASK_RTLOCK_WAIT); +} +EXPORT_SYMBOL(rt_read_unlock); + +void __sched rt_write_unlock(rwlock_t *rwlock) +{ + rwlock_release(&rwlock->dep_map, _RET_IP_); + rcu_read_unlock(); + migrate_enable(); + rwbase_write_unlock(&rwlock->rwbase); +} +EXPORT_SYMBOL(rt_write_unlock); + +int __sched rt_rwlock_is_contended(rwlock_t *rwlock) +{ + return rw_base_is_contended(&rwlock->rwbase); +} +EXPORT_SYMBOL(rt_rwlock_is_contended); + +#ifdef CONFIG_DEBUG_LOCK_ALLOC +void __rt_rwlock_init(rwlock_t *rwlock, const char *name, + struct lock_class_key *key) +{ + debug_check_no_locks_freed((void *)rwlock, sizeof(*rwlock)); + lockdep_init_map(&rwlock->dep_map, name, key, 0); +} +EXPORT_SYMBOL(__rt_rwlock_init); +#endif diff --git a/kernel/notifier.c b/kernel/notifier.c index 1b019cbca594..c20782f07643 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 21d59a508272..14017d1b77b0 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 eee3dc9b60a9..59cb24e25f00 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 51615c909b2f..000000000000 --- a/kernel/printk/internal.h +++ /dev/null @@ -1,69 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * internal.h - printk internal definitions - */ -#include <linux/percpu.h> - -#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 - -__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); -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 - -/* - * In !PRINTK builds we still export 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 421c35571797..209d2392f0d8 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -44,6 +44,10 @@ #include <linux/irq_work.h> #include <linux/ctype.h> #include <linux/uio.h> +#include <linux/kdb.h> +#include <linux/kgdb.h> +#include <linux/kthread.h> +#include <linux/clocksource.h> #include <linux/sched/clock.h> #include <linux/sched/debug.h> #include <linux/sched/task_stack.h> @@ -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_) @@ -267,11 +254,6 @@ 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=) */ @@ -355,10 +337,13 @@ enum log_flags { LOG_CONT = 8, /* text is a fragment of a continuation line */ }; +#ifdef CONFIG_PRINTK /* syslog_lock protects syslog_* variables and write access to clear_seq. */ -static DEFINE_RAW_SPINLOCK(syslog_lock); +static DEFINE_SPINLOCK(syslog_lock); + +/* Set to enable sync mode. Once set, it is never cleared. */ +static bool sync_mode; -#ifdef CONFIG_PRINTK DECLARE_WAIT_QUEUE_HEAD(log_wait); /* All 3 protected by @syslog_lock. */ /* the next printk record to read by syslog(READ) or /proc/kmsg */ @@ -366,17 +351,6 @@ static u64 syslog_seq; static size_t syslog_partial; static bool syslog_time; -/* All 3 protected by @console_sem. */ -/* the next printk record to write to the console */ -static u64 console_seq; -static u64 exclusive_console_stop_seq; -static unsigned long console_dropped; - -struct latched_seq { - seqcount_latch_t latch; - u64 val[2]; -}; - /* * The next printk record to read after the last 'clear' command. There are * two copies (updated with seqcount_latch) so that reads can locklessly @@ -394,9 +368,6 @@ static struct latched_seq clear_seq = { #define PREFIX_MAX 32 #endif -/* the maximum size of a formatted record (i.e. with prefix added per line) */ -#define CONSOLE_LOG_MAX 1024 - /* the maximum size allowed to be reserved for a record */ #define LOG_LINE_MAX (CONSOLE_LOG_MAX - PREFIX_MAX) @@ -435,12 +406,12 @@ 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 syslog_lock. */ +/* 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); @@ -732,27 +703,22 @@ static ssize_t devkmsg_read(struct file *file, char __user *buf, if (ret) return ret; - printk_safe_enter_irq(); if (!prb_read_valid(prb, atomic64_read(&user->seq), r)) { if (file->f_flags & O_NONBLOCK) { ret = -EAGAIN; - printk_safe_exit_irq(); goto out; } - printk_safe_exit_irq(); ret = wait_event_interruptible(log_wait, prb_read_valid(prb, atomic64_read(&user->seq), r)); if (ret) goto out; - printk_safe_enter_irq(); } if (r->info->seq != atomic64_read(&user->seq)) { /* our last seen message is gone, return error and reset */ atomic64_set(&user->seq, r->info->seq); ret = -EPIPE; - printk_safe_exit_irq(); goto out; } @@ -762,7 +728,6 @@ static ssize_t devkmsg_read(struct file *file, char __user *buf, &r->info->dev_info); atomic64_set(&user->seq, r->info->seq + 1); - printk_safe_exit_irq(); if (len > count) { ret = -EINVAL; @@ -797,7 +762,6 @@ static loff_t devkmsg_llseek(struct file *file, loff_t offset, int whence) if (offset) return -ESPIPE; - printk_safe_enter_irq(); switch (whence) { case SEEK_SET: /* the first record */ @@ -818,7 +782,6 @@ static loff_t devkmsg_llseek(struct file *file, loff_t offset, int whence) default: ret = -EINVAL; } - printk_safe_exit_irq(); return ret; } @@ -833,7 +796,6 @@ static __poll_t devkmsg_poll(struct file *file, poll_table *wait) poll_wait(file, &log_wait, wait); - printk_safe_enter_irq(); if (prb_read_valid_info(prb, atomic64_read(&user->seq), &info, NULL)) { /* return error when data has vanished underneath us */ if (info.seq != atomic64_read(&user->seq)) @@ -841,7 +803,6 @@ static __poll_t devkmsg_poll(struct file *file, poll_table *wait) else ret = EPOLLIN|EPOLLRDNORM; } - printk_safe_exit_irq(); return ret; } @@ -874,9 +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)); - printk_safe_enter_irq(); atomic64_set(&user->seq, prb_first_valid_seq(prb)); - printk_safe_exit_irq(); file->private_data = user; return 0; @@ -1042,9 +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; } @@ -1084,7 +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; @@ -1142,8 +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; @@ -1159,8 +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); @@ -1498,11 +1449,9 @@ static int syslog_print(char __user *buf, int size) size_t n; size_t skip; - printk_safe_enter_irq(); - raw_spin_lock(&syslog_lock); + spin_lock_irq(&syslog_lock); if (!prb_read_valid(prb, syslog_seq, &r)) { - raw_spin_unlock(&syslog_lock); - printk_safe_exit_irq(); + spin_unlock_irq(&syslog_lock); break; } if (r.info->seq != syslog_seq) { @@ -1531,8 +1480,7 @@ static int syslog_print(char __user *buf, int size) syslog_partial += n; } else n = 0; - raw_spin_unlock(&syslog_lock); - printk_safe_exit_irq(); + spin_unlock_irq(&syslog_lock); if (!n) break; @@ -1566,7 +1514,6 @@ static int syslog_print_all(char __user *buf, int size, bool clear) return -ENOMEM; time = printk_time; - printk_safe_enter_irq(); /* * Find first record that fits, including all following records, * into the user-provided buffer for this dump. @@ -1587,23 +1534,20 @@ static int syslog_print_all(char __user *buf, int size, bool clear) break; } - printk_safe_exit_irq(); if (copy_to_user(buf + len, text, textlen)) len = -EFAULT; else len += textlen; - printk_safe_enter_irq(); if (len < 0) break; } if (clear) { - raw_spin_lock(&syslog_lock); + spin_lock_irq(&syslog_lock); latched_seq_write(&clear_seq, seq); - raw_spin_unlock(&syslog_lock); + spin_unlock_irq(&syslog_lock); } - printk_safe_exit_irq(); kfree(text); return len; @@ -1611,11 +1555,9 @@ static int syslog_print_all(char __user *buf, int size, bool clear) static void syslog_clear(void) { - printk_safe_enter_irq(); - raw_spin_lock(&syslog_lock); + spin_lock_irq(&syslog_lock); latched_seq_write(&clear_seq, prb_next_seq(prb)); - raw_spin_unlock(&syslog_lock); - printk_safe_exit_irq(); + spin_unlock_irq(&syslog_lock); } /* Return a consistent copy of @syslog_seq. */ @@ -1623,9 +1565,9 @@ static u64 read_syslog_seq_irq(void) { u64 seq; - raw_spin_lock_irq(&syslog_lock); + spin_lock_irq(&syslog_lock); seq = syslog_seq; - raw_spin_unlock_irq(&syslog_lock); + spin_unlock_irq(&syslog_lock); return seq; } @@ -1703,12 +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: - printk_safe_enter_irq(); - raw_spin_lock(&syslog_lock); + spin_lock_irq(&syslog_lock); if (!prb_read_valid_info(prb, syslog_seq, &info, NULL)) { /* No unread messages. */ - raw_spin_unlock(&syslog_lock); - printk_safe_exit_irq(); + spin_unlock_irq(&syslog_lock); return 0; } if (info.seq != syslog_seq) { @@ -1736,8 +1676,7 @@ int do_syslog(int type, char __user *buf, int len, int source) } error -= syslog_partial; } - raw_spin_unlock(&syslog_lock); - printk_safe_exit_irq(); + spin_unlock_irq(&syslog_lock); break; /* Size of the log buffer */ case SYSLOG_ACTION_SIZE_BUFFER: @@ -1756,202 +1695,213 @@ 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. - */ +int printk_delay_msec __read_mostly; -#ifdef CONFIG_LOCKDEP -static struct lockdep_map console_owner_dep_map = { - .name = "console_owner" -}; -#endif +static inline void printk_delay(int level) +{ + boot_delay_msec(level); -static DEFINE_RAW_SPINLOCK(console_owner_lock); -static struct task_struct *console_owner; -static bool console_waiter; + if (unlikely(printk_delay_msec)) { + int m = printk_delay_msec; -/** - * 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) + while (m--) { + mdelay(1); + touch_nmi_watchdog(); + } + } +} + +static bool kernel_sync_mode(void) { - raw_spin_lock(&console_owner_lock); - console_owner = current; - raw_spin_unlock(&console_owner_lock); + return (oops_in_progress || sync_mode); +} - /* The waiter may spin on us after setting console_owner */ - spin_acquire(&console_owner_dep_map, 0, 0, _THIS_IP_); +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; } -/** - * 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) +static bool call_sync_console_driver(struct console *con, const char *text, size_t text_len) { - int waiter; + if (!(con->flags & CON_ENABLED)) + return false; + + if (con->write_atomic && kernel_sync_mode()) { + con->write_atomic(con, text, text_len); + return true; + } - raw_spin_lock(&console_owner_lock); - waiter = READ_ONCE(console_waiter); - console_owner = NULL; - raw_spin_unlock(&console_owner_lock); + if (con->write_atomic && (con->flags & CON_HANDOVER) && !con->thread) { + if (console_trylock()) { + con->write_atomic(con, text, text_len); + console_unlock(); + return true; + } - if (!waiter) { - spin_release(&console_owner_dep_map, _THIS_IP_); - return 0; + } else if (con->write && (con->flags & CON_BOOT) && !con->thread) { + if (console_trylock()) { + con->write(con, text, text_len); + console_unlock(); + return true; + } } - /* The waiter is now free to continue */ - WRITE_ONCE(console_waiter, false); + return false; +} - spin_release(&console_owner_dep_map, _THIS_IP_); +static bool have_atomic_console(void) +{ + struct console *con; - /* - * 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; + for_each_console(con) { + if (!(con->flags & CON_ENABLED)) + continue; + if (con->write_atomic) + return true; + } + return false; } -/** - * 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) +static bool print_sync(struct console *con, u64 *seq) { - struct task_struct *owner = NULL; - bool waiter; - bool spin = false; - unsigned long flags; + struct printk_info info; + struct printk_record r; + size_t text_len; - if (console_trylock()) - return 1; + prb_rec_init_rd(&r, &info, &con->sync_buf[0], sizeof(con->sync_buf)); - printk_safe_enter_irqsave(flags); + if (!prb_read_valid(prb, *seq, &r)) + return false; - 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); + text_len = record_print_text(&r, console_msg_format & MSG_FORMAT_SYSLOG, printk_time); - /* - * 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; - } + if (!call_sync_console_driver(con, &con->sync_buf[0], text_len)) + return false; - /* 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_); + *seq = r.info->seq; - 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_); + touch_softlockup_watchdog_sync(); + clocksource_touch_watchdog(); + rcu_cpu_stall_reset(); + touch_nmi_watchdog(); - return 1; + if (text_len) + printk_delay(r.info->level); + + return true; } -/* - * 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 u64 read_console_seq(struct console *con) { - static char dropped_text[64]; - size_t dropped_len = 0; - struct console *con; + u64 seq2; + u64 seq; - trace_console_rcuidle(text, len); + 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; +} - if (!console_drivers) - return; +static void print_sync_until(struct console *con, u64 seq, bool is_locked) +{ + unsigned int flags; + u64 printk_seq; - if (console_dropped) { - dropped_len = snprintf(dropped_text, sizeof(dropped_text), - "** %lu printk messages dropped **\n", - console_dropped); - console_dropped = 0; - } + console_atomic_lock(&flags); + for (;;) { + printk_seq = read_console_seq(con); + if (printk_seq >= seq) + break; + if (!print_sync(con, &printk_seq)) + break; - 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); + 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); } -int printk_delay_msec __read_mostly; +/* + * 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]; -static inline void printk_delay(void) +/* + * 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) { - if (unlikely(printk_delay_msec)) { - int m = printk_delay_msec; + int ctx = 0; - while (m--) { - mdelay(1); - touch_nmi_watchdog(); - } +#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) @@ -2032,20 +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 @@ -2055,6 +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 @@ -2081,6 +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; @@ -2088,11 +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; } } @@ -2108,9 +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) @@ -2125,12 +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; + } + + 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); + } + } - return (text_len + trunc_msg_len); + printk_exit_irqrestore(irqflags); + return ret; } asmlinkage int vprintk_emit(int facility, int level, @@ -2138,53 +2115,43 @@ 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); -int vprintk_default(const char *fmt, va_list args) +__printf(1, 0) +static int vprintk_default(const char *fmt, va_list args) { return vprintk_emit(0, LOGLEVEL_DEFAULT, NULL, fmt, args); } -EXPORT_SYMBOL_GPL(vprintk_default); + +__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); /** * printk - print a kernel message @@ -2220,37 +2187,164 @@ asmlinkage __visible int printk(const char *fmt, ...) } EXPORT_SYMBOL(printk); -#else /* CONFIG_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; -#define CONSOLE_LOG_MAX 0 -#define printk_time false + 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; -#define prb_read_valid(rb, seq, r) false -#define prb_first_valid_seq(rb) 0 + if (con->flags & CON_EXTENDED) + write_text = ext_text; + else + write_text = text; -static u64 syslog_seq; -static u64 console_seq; -static u64 exclusive_console_stop_seq; -static unsigned long console_dropped; + 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; +} -static size_t record_print_text(const struct printk_record *r, - bool syslog, bool time) +/* Must be called within console_lock(). */ +static void start_printk_kthread(struct console *con) { - return 0; + 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); } -static ssize_t info_print_ext_header(char *buf, size_t size, - struct printk_info *info) + +/* protected by console_lock */ +static bool kthreads_started; + +/* Must be called within console_lock(). */ +static void console_try_thread(struct console *con) { - return 0; + 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); } -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; } + +#else /* CONFIG_PRINTK */ + +#define prb_first_valid_seq(rb) 0 +#define prb_next_seq(rb) 0 + +#define console_try_thread(con) #endif /* CONFIG_PRINTK */ @@ -2495,34 +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 * @@ -2539,136 +2605,14 @@ static inline int can_use_console(void) */ void console_unlock(void) { - static char ext_text[CONSOLE_EXT_LOG_MAX]; - static char text[CONSOLE_LOG_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); -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++; - - /* - * 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; 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. - */ - retry = prb_read_valid(prb, console_seq, NULL); - printk_safe_exit_irqrestore(flags); - - if (retry && console_trylock()) - goto again; } EXPORT_SYMBOL(console_unlock); @@ -2718,23 +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 (mode == CONSOLE_REPLAY_ALL) { - unsigned long flags; + if (!console_trylock()) + return; - printk_safe_enter_irqsave(flags); - console_seq = prb_first_valid_seq(prb); - printk_safe_exit_irqrestore(flags); + if (mode == CONSOLE_REPLAY_ALL) { + seq = prb_first_valid_seq(prb); + for_each_console(c) + latched_seq_write(&c->printk_seq, seq); } + console_unlock(); } @@ -2869,8 +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) { @@ -2893,6 +2832,8 @@ void register_console(struct console *newcon) } } + newcon->thread = NULL; + if (console_drivers && console_drivers->flags & CON_BOOT) bcon = console_drivers; @@ -2934,8 +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 @@ -2957,27 +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. - * - * 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; + if (!(newcon->flags & CON_PRINTBUFFER)) + seq = prb_next_seq(prb); - /* Get a consistent copy of @syslog_seq. */ - raw_spin_lock_irqsave(&syslog_lock, flags); - console_seq = syslog_seq; - raw_spin_unlock_irqrestore(&syslog_lock, flags); - } + 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(); @@ -3051,6 +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); @@ -3133,6 +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); @@ -3148,7 +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); @@ -3156,14 +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) = @@ -3182,25 +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, ...) @@ -3341,6 +3266,24 @@ void kmsg_dump(enum kmsg_dump_reason reason) { struct kmsg_dumper *dumper; + 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) { enum kmsg_dump_reason max_reason = dumper->max_reason; @@ -3386,14 +3329,12 @@ bool kmsg_dump_get_line(struct kmsg_dump_iter *iter, bool syslog, struct printk_info info; unsigned int line_count; struct printk_record r; - unsigned long flags; size_t l = 0; bool ret = false; if (iter->cur_seq < min_seq) iter->cur_seq = min_seq; - printk_safe_enter_irqsave(flags); prb_rec_init_rd(&r, &info, line, size); /* Read text or count text lines? */ @@ -3414,7 +3355,6 @@ bool kmsg_dump_get_line(struct kmsg_dump_iter *iter, bool syslog, iter->cur_seq = r.info->seq + 1; ret = true; out: - printk_safe_exit_irqrestore(flags); if (len) *len = l; return ret; @@ -3446,7 +3386,6 @@ bool kmsg_dump_get_buffer(struct kmsg_dump_iter *iter, bool syslog, u64 min_seq = latched_seq_read_nolock(&clear_seq); struct printk_info info; struct printk_record r; - unsigned long flags; u64 seq; u64 next_seq; size_t len = 0; @@ -3459,7 +3398,6 @@ bool kmsg_dump_get_buffer(struct kmsg_dump_iter *iter, bool syslog, if (iter->cur_seq < min_seq) iter->cur_seq = min_seq; - printk_safe_enter_irqsave(flags); 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 */ @@ -3468,10 +3406,8 @@ bool kmsg_dump_get_buffer(struct kmsg_dump_iter *iter, bool syslog, } /* last entry */ - if (iter->cur_seq >= iter->next_seq) { - printk_safe_exit_irqrestore(flags); + if (iter->cur_seq >= iter->next_seq) goto out; - } /* * Find first record that fits, including all following records, @@ -3503,7 +3439,6 @@ bool kmsg_dump_get_buffer(struct kmsg_dump_iter *iter, bool syslog, iter->next_seq = next_seq; ret = true; - printk_safe_exit_irqrestore(flags); out: if (len_out) *len_out = len; @@ -3521,13 +3456,204 @@ EXPORT_SYMBOL_GPL(kmsg_dump_get_buffer); */ void kmsg_dump_rewind(struct kmsg_dump_iter *iter) { - unsigned long flags; - - printk_safe_enter_irqsave(flags); iter->cur_seq = latched_seq_read_nolock(&clear_seq); iter->next_seq = prb_next_seq(prb); - printk_safe_exit_irqrestore(flags); } 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 94232186fccb..000000000000 --- a/kernel/printk/printk_safe.c +++ /dev/null @@ -1,414 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * printk_safe.c - Safe printk for printk-deadlock-prone contexts - */ - -#include <linux/preempt.h> -#include <linux/spinlock.h> -#include <linux/debug_locks.h> -#include <linux/kdb.h> -#include <linux/smp.h> -#include <linux/cpumask.h> -#include <linux/irq_work.h> -#include <linux/printk.h> -#include <linux/kprobes.h> - -#include "internal.h" - -/* - * In NMI and safe mode, printk() avoids taking locks. 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 safe buffers. - * Do not risk a double release when more CPUs are up. - */ - 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 store the messages into the main logbuf directly. - */ -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); -} - -asmlinkage int vprintk(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 - - /* - * 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)) { - unsigned long flags; - int len; - - printk_safe_enter_irqsave(flags); - len = vprintk_store(0, LOGLEVEL_DEFAULT, NULL, fmt, args); - printk_safe_exit_irqrestore(flags); - defer_console_output(); - return len; - } - - /* Use extra buffer in NMI. */ - 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); -} -EXPORT_SYMBOL(vprintk); - -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 2997ca600d18..3ed6598357ce 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -197,7 +197,18 @@ static bool ptrace_freeze_traced(struct task_struct *task) spin_lock_irq(&task->sighand->siglock); if (task_is_traced(task) && !looks_like_a_spurious_pid(task) && !__fatal_signal_pending(task)) { +#ifdef CONFIG_PREEMPT_RT + 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); +#else task->state = __TASK_TRACED; +#endif ret = true; } spin_unlock_irq(&task->sighand->siglock); @@ -207,8 +218,8 @@ 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); @@ -217,12 +228,21 @@ 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; +#ifdef CONFIG_PREEMPT_RT + else if (task->saved_state == __TASK_TRACED) + task->saved_state = TASK_TRACED; +#endif + 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 29d2f4c647d3..6096a7d14342 100644 --- a/kernel/rcu/rcutorture.c +++ b/kernel/rcu/rcutorture.c @@ -61,10 +61,13 @@ MODULE_AUTHOR("Paul E. McKenney <paulmck@linux.ibm.com> and Josh Triplett <josh@ #define RCUTORTURE_RDR_RBH 0x08 /* ... rcu_read_lock_bh(). */ #define RCUTORTURE_RDR_SCHED 0x10 /* ... rcu_read_lock_sched(). */ #define RCUTORTURE_RDR_RCU 0x20 /* ... entering another RCU reader. */ -#define RCUTORTURE_RDR_NBITS 6 /* Number of bits defined above. */ +#define RCUTORTURE_RDR_ATOM_BH 0x40 /* ... disabling bh while atomic */ +#define RCUTORTURE_RDR_ATOM_RBH 0x80 /* ... RBH while atomic */ +#define RCUTORTURE_RDR_NBITS 8 /* Number of bits defined above. */ #define RCUTORTURE_MAX_EXTEND \ (RCUTORTURE_RDR_BH | RCUTORTURE_RDR_IRQ | RCUTORTURE_RDR_PREEMPT | \ - RCUTORTURE_RDR_RBH | RCUTORTURE_RDR_SCHED) + RCUTORTURE_RDR_RBH | RCUTORTURE_RDR_SCHED | \ + RCUTORTURE_RDR_ATOM_BH | RCUTORTURE_RDR_ATOM_RBH) #define RCUTORTURE_RDR_MAX_LOOPS 0x7 /* Maximum reader extensions. */ /* Must be power of two minus one. */ #define RCUTORTURE_RDR_MAX_SEGS (RCUTORTURE_RDR_MAX_LOOPS + 3) @@ -1418,31 +1421,53 @@ static void rcutorture_one_extend(int *readstate, int newstate, WARN_ON_ONCE((idxold >> 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 fcef5f0c60b8..d212815f99a9 100644 --- a/kernel/rcu/tasks.h +++ b/kernel/rcu/tasks.h @@ -1293,7 +1293,7 @@ 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 @@ -1330,9 +1330,7 @@ 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) { @@ -1347,9 +1345,6 @@ 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 15b4d2fb6be3..c58c517e1197 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -74,7 +74,11 @@ __read_mostly int sysctl_resched_latency_warn_once = 1; * 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. @@ -630,6 +634,48 @@ 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); @@ -1759,6 +1805,7 @@ void migrate_disable(void) preempt_disable(); this_rq()->nr_pinned++; p->migration_disabled = 1; + preempt_lazy_disable(); preempt_enable(); } EXPORT_SYMBOL_GPL(migrate_disable); @@ -1787,6 +1834,7 @@ void migrate_enable(void) barrier(); p->migration_disabled = 0; this_rq()->nr_pinned--; + preempt_lazy_enable(); preempt_enable(); } EXPORT_SYMBOL_GPL(migrate_enable); @@ -2634,7 +2682,7 @@ 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 && !task_match_state_lock(p, match_state)) return 0; cpu_relax(); } @@ -2649,7 +2697,7 @@ 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 || task_match_state_or_saved(p, match_state)) ncsw = p->nvcsw | LONG_MIN; /* sets MSB */ task_rq_unlock(rq, p, &rf); @@ -3209,6 +3257,54 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags) } /* + * Invoked from try_to_wake_up() to check whether the task can be woken up. + * + * The caller holds p::pi_lock if p != current or has preemption + * disabled when p == current. + * + * The rules of PREEMPT_RT saved_state: + * + * The related locking code always holds p::pi_lock when updating + * p::saved_state, which means the code is fully serialized in both cases. + * + * The lock wait and lock wakeups happen via TASK_RTLOCK_WAIT. No other + * bits set. This allows to distinguish all wakeup scenarios. + */ +static __always_inline +bool ttwu_state_match(struct task_struct *p, unsigned int state, int *success) +{ + if (IS_ENABLED(CONFIG_DEBUG_PREEMPT)) + WARN_ON_ONCE((state & TASK_RTLOCK_WAIT) && + (state & TASK_RTLOCK_WAIT) != TASK_RTLOCK_WAIT); + + if (p->state & state) { + *success = 1; + return true; + } + +#ifdef CONFIG_PREEMPT_RT + /* + * Saved state preserves the task state accross blocking on + * a RT lock. If the state matches, set p::saved_state to + * TASK_RUNNING, but do not wake the task because it waits + * for a lock wakeup. Also indicate success because from + * the regular waker's point of view this has succeeded. + * + * After acquiring the lock the task will restore p::state + * from p::saved_state which ensures that the regular + * wakeup is not lost. The restore will also set + * p::saved_state to TASK_RUNNING so any further tests will + * not result in false positives vs. @success + */ + if (p->saved_state & state) { + p->saved_state = TASK_RUNNING; + *success = 1; + } +#endif + return false; +} + +/* * Notes on Program-Order guarantees on SMP systems. * * MIGRATION @@ -3347,10 +3443,9 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) * - we're serialized against set_special_state() by virtue of * it disabling IRQs (this allows not taking ->pi_lock). */ - if (!(p->state & state)) + if (!ttwu_state_match(p, state, &success)) goto out; - success = 1; trace_sched_waking(p); p->state = TASK_RUNNING; trace_sched_wakeup(p); @@ -3365,14 +3460,12 @@ 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 (!ttwu_state_match(p, state, &success)) goto unlock; trace_sched_waking(p); - /* We're going to change ->state: */ - success = 1; - /* * Ensure we load p->on_rq _after_ p->state, otherwise it would * be possible to, falsely, observe p->on_rq == 0 and get stuck @@ -3802,6 +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); @@ -4234,23 +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); } @@ -4986,6 +5077,26 @@ restart: } /* + * Constants for the sched_mode argument of __schedule(). + * + * The mode argument allows RT enabled kernels to differentiate a + * preemption from blocking on an 'sleeping' spin/rwlock by having seperate + * mask values for SM_MASK_PREEMPT and SM_MASK_STATE while on a non RT + * enabled kernel the masks have all bits set which allows the compiler to + * optimize the AND operation out. + */ +#define SM_NONE 0x0 +#define SM_PREEMPT 0x1 +#ifndef CONFIG_PREEMPT_RT +# define SM_MASK_PREEMPT UINT_MAX +# define SM_MASK_STATE SM_MASK_PREEMPT +#else +# define SM_RTLOCK_WAIT 0x2 +# define SM_MASK_PREEMPT SM_PREEMPT +# define SM_MASK_STATE (SM_PREEMPT | SM_RTLOCK_WAIT) +#endif + +/* * __schedule() is the main scheduler function. * * The main means of driving the scheduler and thus entering this function are: @@ -5024,7 +5135,7 @@ restart: * * WARNING: must be called with preemption disabled! */ -static void __sched notrace __schedule(bool preempt) +static void __sched notrace __schedule(unsigned int sched_mode) { struct task_struct *prev, *next; unsigned long *switch_count; @@ -5037,13 +5148,13 @@ static void __sched notrace __schedule(bool preempt) rq = cpu_rq(cpu); prev = rq->curr; - schedule_debug(prev, preempt); + schedule_debug(prev, sched_mode & SM_MASK_STATE); if (sched_feat(HRTICK) || sched_feat(HRTICK_DL)) hrtick_clear(rq); local_irq_disable(); - rcu_note_context_switch(preempt); + rcu_note_context_switch(sched_mode & SM_MASK_STATE); /* * Make sure that signal_pending_state()->signal_pending() below @@ -5077,7 +5188,7 @@ 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 (!(sched_mode & SM_MASK_PREEMPT) && prev_state) { if (signal_pending_state(prev_state, prev)) { prev->state = TASK_RUNNING; } else { @@ -5112,6 +5223,7 @@ 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(); #ifdef CONFIG_SCHED_DEBUG rq->last_seen_need_resched_ns = 0; @@ -5143,7 +5255,7 @@ static void __sched notrace __schedule(bool preempt) migrate_disable_switch(rq, prev); psi_sched_switch(prev, next, !task_on_rq_queued(prev)); - trace_sched_switch(preempt, prev, next); + trace_sched_switch(sched_mode & SM_MASK_PREEMPT, prev, next); /* Also unlocks the rq: */ rq = context_switch(rq, prev, next, &rf); @@ -5164,7 +5276,7 @@ void __noreturn do_task_dead(void) /* Tell freezer to ignore us: */ current->flags |= PF_NOFREEZE; - __schedule(false); + __schedule(SM_NONE); BUG(); /* Avoid "noreturn function does return" - but don't continue if BUG() is a NOP: */ @@ -5225,7 +5337,7 @@ asmlinkage __visible void __sched schedule(void) sched_submit_work(tsk); do { preempt_disable(); - __schedule(false); + __schedule(SM_NONE); sched_preempt_enable_no_resched(); } while (need_resched()); sched_update_worker(tsk); @@ -5253,7 +5365,7 @@ void __sched schedule_idle(void) */ WARN_ON_ONCE(current->state); do { - __schedule(false); + __schedule(SM_NONE); } while (need_resched()); } @@ -5288,6 +5400,18 @@ void __sched schedule_preempt_disabled(void) preempt_disable(); } +#ifdef CONFIG_PREEMPT_RT +void __sched notrace schedule_rtlock(void) +{ + do { + preempt_disable(); + __schedule(SM_RTLOCK_WAIT); + sched_preempt_enable_no_resched(); + } while (need_resched()); +} +NOKPROBE_SYMBOL(schedule_rtlock); +#endif + static void __sched notrace preempt_schedule_common(void) { do { @@ -5306,7 +5430,7 @@ static void __sched notrace preempt_schedule_common(void) */ preempt_disable_notrace(); preempt_latency_start(1); - __schedule(true); + __schedule(SM_PREEMPT); preempt_latency_stop(1); preempt_enable_no_resched_notrace(); @@ -5317,6 +5441,30 @@ 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 @@ -5330,7 +5478,8 @@ asmlinkage __visible void __sched notrace preempt_schedule(void) */ if (likely(!preemptible())) return; - + if (!preemptible_lazy()) + return; preempt_schedule_common(); } NOKPROBE_SYMBOL(preempt_schedule); @@ -5363,6 +5512,9 @@ 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() @@ -5385,7 +5537,7 @@ asmlinkage __visible void __sched notrace preempt_schedule_notrace(void) * an infinite recursion. */ prev_ctx = exception_enter(); - __schedule(true); + __schedule(SM_PREEMPT); exception_exit(prev_ctx); preempt_latency_stop(1); @@ -5534,7 +5686,7 @@ asmlinkage __visible void __sched preempt_schedule_irq(void) do { preempt_disable(); local_irq_enable(); - __schedule(true); + __schedule(SM_PREEMPT); local_irq_disable(); sched_preempt_enable_no_resched(); } while (need_resched()); @@ -7481,7 +7633,9 @@ void __init 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: */ @@ -7586,6 +7740,7 @@ 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. @@ -8262,7 +8417,7 @@ 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/fair.c b/kernel/sched/fair.c index f60ef0b4ec33..4541a379a0f3 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -4446,7 +4446,7 @@ 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. @@ -4470,7 +4470,7 @@ 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 @@ -4613,7 +4613,7 @@ 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; } /* @@ -4750,7 +4750,7 @@ 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 @@ -5494,7 +5494,7 @@ 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); @@ -7123,7 +7123,7 @@ 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 @@ -10854,7 +10854,7 @@ 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; @@ -10881,7 +10881,7 @@ 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 7f8dace0964c..d5cee51819bf 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 f2bc99ca01e5..9bfcf75ad240 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -2028,6 +2028,15 @@ 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 e1c655f928c7..f230b1ac7f91 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 55a0a243e871..3e2e6238ee8b 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 30a0bee5ff9b..f722dea57a12 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1316,6 +1316,34 @@ 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; @@ -2215,16 +2243,8 @@ 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 52bf159ec400..86955bacbae6 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -690,10 +690,21 @@ void flush_smp_call_function_from_idle(void) cfd_seq_store(this_cpu_ptr(&cfd_seq_local)->idle, CFD_SEQ_NOCPU, smp_processor_id(), CFD_SEQ_IDLE); + 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/time/hrtimer.c b/kernel/time/hrtimer.c index 4a66725b1d4a..b0ad29f80711 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -1422,6 +1422,7 @@ static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id, base += hrtimer_clockid_to_base(clock_id); timer->is_soft = softtimer; timer->is_hard = !!(mode & HRTIMER_MODE_HARD); + timer->is_chill = !!(mode & HRTIMER_MODE_CHILL); timer->base = &cpu_base->clock_base[base]; timerqueue_init(&timer->node); } @@ -1788,7 +1789,7 @@ static enum hrtimer_restart hrtimer_wakeup(struct hrtimer *timer) t->task = NULL; if (task) - wake_up_process(task); + wake_up_state(task, timer->is_chill ? TASK_RTLOCK_WAIT : TASK_NORMAL); return HRTIMER_NORESTART; } @@ -2006,6 +2007,34 @@ 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; + ktime_t chill_time; + + local_irq_disable(); + current_save_and_set_rtlock_wait_state(); + local_irq_enable(); + + chill_time = ktime_set(0, NSEC_PER_MSEC); + + current->flags |= PF_NOFREEZE; + schedule_hrtimeout(&chill_time, + HRTIMER_MODE_REL_HARD| HRTIMER_MODE_CHILL); + if (!freeze_flag) + current->flags &= ~PF_NOFREEZE; + + local_irq_disable(); + current_restore_rtlock_saved_state(); + local_irq_enable(); +} +EXPORT_SYMBOL(cpu_chill); +#endif + /* * Functions related to boot-time initialization: */ diff --git a/kernel/time/timer.c b/kernel/time/timer.c index 2870a7a51638..9c0f56ae3927 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -1758,6 +1758,8 @@ 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 fa617a0a9eed..20696524214b 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -2595,6 +2595,15 @@ 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; @@ -2613,7 +2622,16 @@ 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 * @@ -4140,14 +4158,17 @@ 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) @@ -4181,13 +4202,16 @@ 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 @@ -9684,7 +9708,6 @@ 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); @@ -9766,7 +9789,6 @@ 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 80e96989770e..0e6704248425 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 d0368a569bfa..321e18fb6907 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 1e1bd6f4a13d..10c15a68588c 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1440,7 +1440,7 @@ 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 45a0584f6541..03a87df69ed2 100644 --- a/lib/bug.c +++ b/lib/bug.c @@ -206,6 +206,7 @@ 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 9e14ae02306b..083882a3cf2f 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 2f17b488d58e..7557bf7ecf1f 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 0f6b262e0964..2b70ae9f90d3 100644 --- a/lib/locking-selftest.c +++ b/lib/locking-selftest.c @@ -795,6 +795,8 @@ 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) @@ -810,9 +812,12 @@ 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: */ @@ -845,6 +850,8 @@ GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2A_rlock) #undef E1 #undef E2 +#endif + /* * Enabling irqs with an irq-safe lock held: */ @@ -868,6 +875,8 @@ 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) @@ -883,6 +892,8 @@ 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 @@ -914,6 +925,8 @@ 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) @@ -929,6 +942,8 @@ 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 @@ -962,6 +977,8 @@ 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) @@ -977,10 +994,14 @@ 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. * @@ -1170,6 +1191,11 @@ 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. */ @@ -1216,6 +1242,8 @@ GENERATE_PERMUTATIONS_3_EVENTS(irq_read_recursion_soft_wlock) #undef E2 #undef E3 +#endif + /* * read-lock / write-lock recursion that is unsafe. */ @@ -2842,6 +2870,7 @@ void locking_selftest(void) printk(" --------------------------------------------------------------------------\n"); +#ifndef CONFIG_PREEMPT_RT /* * irq-context testcases: */ @@ -2856,6 +2885,28 @@ 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 8abe1870dba4..b09a490f5f70 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 a59778946404..907f59045998 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/lib/test_lockup.c b/lib/test_lockup.c index 864554e76973..906b598740a7 100644 --- a/lib/test_lockup.c +++ b/lib/test_lockup.c @@ -485,13 +485,13 @@ static int __init test_lockup_init(void) offsetof(spinlock_t, lock.wait_lock.magic), SPINLOCK_MAGIC) || test_magic(lock_rwlock_ptr, - offsetof(rwlock_t, rtmutex.wait_lock.magic), + offsetof(rwlock_t, rwbase.rtmutex.wait_lock.magic), SPINLOCK_MAGIC) || test_magic(lock_mutex_ptr, - offsetof(struct mutex, lock.wait_lock.magic), + offsetof(struct mutex, rtmutex.wait_lock.magic), SPINLOCK_MAGIC) || test_magic(lock_rwsem_ptr, - offsetof(struct rw_semaphore, rtmutex.wait_lock.magic), + offsetof(struct rw_semaphore, rwbase.rtmutex.wait_lock.magic), SPINLOCK_MAGIC)) return -EINVAL; #else @@ -502,7 +502,7 @@ static int __init test_lockup_init(void) offsetof(rwlock_t, magic), RWLOCK_MAGIC) || test_magic(lock_mutex_ptr, - offsetof(struct mutex, wait_lock.rlock.magic), + offsetof(struct mutex, wait_lock.magic), SPINLOCK_MAGIC) || test_magic(lock_rwsem_ptr, offsetof(struct rw_semaphore, wait_lock.magic), diff --git a/localversion-rt b/localversion-rt new file mode 100644 index 000000000000..6f206be67cd2 --- /dev/null +++ b/localversion-rt @@ -0,0 +1 @@ +-rt1 diff --git a/mm/Kconfig b/mm/Kconfig index 02d44e3420f5..453ce5f4811f 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -403,7 +403,7 @@ 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 946d84815693..a9b294463487 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -66,6 +66,7 @@ #include <net/sock.h> #include <net/ip.h> #include "slab.h" +#include <linux/local_lock.h> #include <linux/uaccess.h> @@ -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) { @@ -256,7 +264,8 @@ struct cgroup_subsys_state *vmpressure_to_css(struct vmpressure *vmpr) extern spinlock_t css_set_lock; static void obj_cgroup_uncharge_pages(struct obj_cgroup *objcg, - unsigned int nr_pages); + unsigned int nr_pages, + bool lock_memcg_stock); static void obj_cgroup_release(struct percpu_ref *ref) { @@ -293,7 +302,7 @@ static void obj_cgroup_release(struct percpu_ref *ref) spin_lock_irqsave(&css_set_lock, flags); memcg = obj_cgroup_memcg(objcg); if (nr_pages) - obj_cgroup_uncharge_pages(objcg, nr_pages); + obj_cgroup_uncharge_pages(objcg, nr_pages, false); list_del(&objcg->list); mem_cgroup_put(memcg); spin_unlock_irqrestore(&css_set_lock, flags); @@ -693,6 +702,7 @@ 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); @@ -712,6 +722,7 @@ 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(); } /** @@ -2041,6 +2052,7 @@ 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; @@ -2092,7 +2104,7 @@ 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) { @@ -2100,7 +2112,7 @@ 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; } @@ -2135,26 +2147,28 @@ 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); } /* * Cache charges(val) to local per_cpu area. * This will be consumed by consume_stock() function, later. */ -static void refill_stock(struct mem_cgroup *memcg, unsigned int nr_pages) +static void refill_stock(struct mem_cgroup *memcg, unsigned int nr_pages, + bool lock_memcg_stock) { struct memcg_stock_pcp *stock; unsigned long flags; - local_irq_save(flags); + if (lock_memcg_stock) + local_lock_irqsave(&memcg_stock.lock, flags); stock = this_cpu_ptr(&memcg_stock); if (stock->cached != memcg) { /* reset if necessary */ @@ -2167,7 +2181,8 @@ 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); + if (lock_memcg_stock) + local_unlock_irqrestore(&memcg_stock.lock, flags); } /* @@ -2187,7 +2202,7 @@ 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; @@ -2210,7 +2225,7 @@ 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); } @@ -2651,7 +2666,7 @@ force: done_restock: if (batch > nr_pages) - refill_stock(memcg, batch - nr_pages); + refill_stock(memcg, batch - nr_pages, true); /* * If the hierarchy is above the normal consumption range, schedule @@ -2903,7 +2918,8 @@ static void memcg_free_cache_id(int id) * @nr_pages: number of pages to uncharge */ static void obj_cgroup_uncharge_pages(struct obj_cgroup *objcg, - unsigned int nr_pages) + unsigned int nr_pages, + bool lock_memcg_stock) { struct mem_cgroup *memcg; @@ -2911,7 +2927,7 @@ static void obj_cgroup_uncharge_pages(struct obj_cgroup *objcg, if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) page_counter_uncharge(&memcg->kmem, nr_pages); - refill_stock(memcg, nr_pages); + refill_stock(memcg, nr_pages, lock_memcg_stock); css_put(&memcg->css); } @@ -2998,7 +3014,7 @@ void __memcg_kmem_uncharge_page(struct page *page, int order) return; objcg = __page_objcg(page); - obj_cgroup_uncharge_pages(objcg, nr_pages); + obj_cgroup_uncharge_pages(objcg, nr_pages, true); page->memcg_data = 0; obj_cgroup_put(objcg); } @@ -3009,7 +3025,7 @@ 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) { @@ -3017,7 +3033,7 @@ 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; } @@ -3034,7 +3050,7 @@ static void drain_obj_stock(struct memcg_stock_pcp *stock) unsigned int nr_bytes = stock->nr_bytes & (PAGE_SIZE - 1); if (nr_pages) - obj_cgroup_uncharge_pages(old, nr_pages); + obj_cgroup_uncharge_pages(old, nr_pages, false); /* * The leftover is flushed to the centralized per-memcg value. @@ -3073,7 +3089,7 @@ 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 */ @@ -3087,7 +3103,7 @@ 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) @@ -5512,12 +5528,12 @@ 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: @@ -6535,10 +6551,10 @@ static int __mem_cgroup_charge(struct page *page, struct mem_cgroup *memcg, 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); out: return ret; } @@ -6665,11 +6681,11 @@ 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_memory); 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); @@ -6822,10 +6838,10 @@ 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); @@ -6911,7 +6927,7 @@ void mem_cgroup_uncharge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages) mod_memcg_state(memcg, MEMCG_SOCK, -nr_pages); - refill_stock(memcg, nr_pages); + refill_stock(memcg, nr_pages, true); } static int __init cgroup_memory(char *s) @@ -6953,9 +6969,13 @@ 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; @@ -7004,6 +7024,7 @@ 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); @@ -7052,9 +7073,13 @@ 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/mempolicy.c b/mm/mempolicy.c index d79fa299b70c..9e4b406c79f8 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -2150,7 +2150,7 @@ static struct page *alloc_page_interleave(gfp_t gfp, unsigned order, return page; if (page && page_to_nid(page) == nid) { preempt_disable(); - __inc_numa_state(page_zone(page), NUMA_INTERLEAVE_HIT); + __count_numa_event(page_zone(page), NUMA_INTERLEAVE_HIT); preempt_enable(); } return page; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index de392908bf64..a379dcdfa7de 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -122,6 +122,13 @@ typedef int __bitwise fpi_t; static DEFINE_MUTEX(pcp_batch_high_lock); #define MIN_PERCPU_PAGELIST_FRACTION (8) +struct pagesets { + local_lock_t lock; +}; +static DEFINE_PER_CPU(struct pagesets, pagesets) = { + .lock = INIT_LOCAL_LOCK(lock), +}; + #ifdef CONFIG_USE_PERCPU_NUMA_NODE_ID DEFINE_PER_CPU(int, numa_node); EXPORT_PER_CPU_SYMBOL(numa_node); @@ -1456,6 +1463,10 @@ static void free_pcppages_bulk(struct zone *zone, int count, } while (--count && --batch_free && !list_empty(list)); } + /* + * local_lock_irq held so equivalent to spin_lock_irqsave for + * both PREEMPT_RT and non-PREEMPT_RT configurations. + */ spin_lock(&zone->lock); isolated_pageblocks = has_isolate_pageblock(zone); @@ -1482,13 +1493,15 @@ static void free_one_page(struct zone *zone, unsigned int order, int migratetype, fpi_t fpi_flags) { - spin_lock(&zone->lock); + unsigned long flags; + + spin_lock_irqsave(&zone->lock, flags); if (unlikely(has_isolate_pageblock(zone) || is_migrate_isolate(migratetype))) { migratetype = get_pfnblock_migratetype(page, pfn); } __free_one_page(page, pfn, zone, order, migratetype, fpi_flags); - spin_unlock(&zone->lock); + spin_unlock_irqrestore(&zone->lock, flags); } static void __meminit __init_single_page(struct page *page, unsigned long pfn, @@ -1571,16 +1584,22 @@ static void __free_pages_ok(struct page *page, unsigned int order, unsigned long flags; int migratetype; unsigned long pfn = page_to_pfn(page); + struct zone *zone = page_zone(page); if (!free_pages_prepare(page, order, true, fpi_flags)) return; migratetype = get_pfnblock_migratetype(page, pfn); - local_irq_save(flags); + + spin_lock_irqsave(&zone->lock, flags); + if (unlikely(has_isolate_pageblock(zone) || + is_migrate_isolate(migratetype))) { + migratetype = get_pfnblock_migratetype(page, pfn); + } + __free_one_page(page, pfn, zone, order, migratetype, fpi_flags); + spin_unlock_irqrestore(&zone->lock, flags); + __count_vm_events(PGFREE, 1 << order); - free_one_page(page_zone(page), page, pfn, order, migratetype, - fpi_flags); - local_irq_restore(flags); } void __free_pages_core(struct page *page, unsigned int order) @@ -2958,6 +2977,10 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order, { int i, allocated = 0; + /* + * local_lock_irq held so equivalent to spin_lock_irqsave for + * both PREEMPT_RT and non-PREEMPT_RT configurations. + */ spin_lock(&zone->lock); for (i = 0; i < count; ++i) { struct page *page = __rmqueue(zone, order, migratetype, @@ -3010,12 +3033,12 @@ 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(&pagesets.lock, 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(&pagesets.lock, flags); } #endif @@ -3029,16 +3052,15 @@ void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp) static void drain_pages_zone(unsigned int cpu, struct zone *zone) { unsigned long flags; - struct per_cpu_pageset *pset; struct per_cpu_pages *pcp; - local_irq_save(flags); - pset = per_cpu_ptr(zone->pageset, cpu); + local_lock_irqsave(&pagesets.lock, flags); - pcp = &pset->pcp; + pcp = per_cpu_ptr(zone->per_cpu_pageset, cpu); if (pcp->count) free_pcppages_bulk(zone, pcp->count, pcp); - local_irq_restore(flags); + + local_unlock_irqrestore(&pagesets.lock, flags); } /* @@ -3086,9 +3108,9 @@ static void drain_local_pages_wq(struct work_struct *work) * cpu which is alright 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(); } /* @@ -3136,7 +3158,7 @@ static void __drain_all_pages(struct zone *zone, bool force_all_cpus) * disables preemption as part of its processing */ for_each_online_cpu(cpu) { - struct per_cpu_pageset *pcp; + struct per_cpu_pages *pcp; struct zone *z; bool has_pcps = false; @@ -3147,13 +3169,13 @@ static void __drain_all_pages(struct zone *zone, bool force_all_cpus) */ has_pcps = true; } else if (zone) { - pcp = per_cpu_ptr(zone->pageset, cpu); - if (pcp->pcp.count) + pcp = per_cpu_ptr(zone->per_cpu_pageset, cpu); + if (pcp->count) has_pcps = true; } else { for_each_populated_zone(z) { - pcp = per_cpu_ptr(z->pageset, cpu); - if (pcp->pcp.count) { + pcp = per_cpu_ptr(z->per_cpu_pageset, cpu); + if (pcp->count) { has_pcps = true; break; } @@ -3258,32 +3280,14 @@ static bool free_unref_page_prepare(struct page *page, unsigned long pfn) return true; } -static void free_unref_page_commit(struct page *page, unsigned long pfn) +static void free_unref_page_commit(struct page *page, unsigned long pfn, + int migratetype) { struct zone *zone = page_zone(page); struct per_cpu_pages *pcp; - int migratetype; - migratetype = get_pcppage_migratetype(page); __count_vm_event(PGFREE); - - /* - * We only track unmovable, reclaimable and movable on pcp lists. - * Free ISOLATE pages back to the allocator because they are being - * offlined but treat HIGHATOMIC as movable pages so we can get those - * areas back if necessary. Otherwise, we may have to free - * excessively into the page allocator - */ - if (migratetype >= MIGRATE_PCPTYPES) { - if (unlikely(is_migrate_isolate(migratetype))) { - free_one_page(zone, page, pfn, 0, migratetype, - FPI_NONE); - return; - } - migratetype = MIGRATE_MOVABLE; - } - - pcp = &this_cpu_ptr(zone->pageset)->pcp; + pcp = this_cpu_ptr(zone->per_cpu_pageset); list_add(&page->lru, &pcp->lists[migratetype]); pcp->count++; if (pcp->count >= READ_ONCE(pcp->high)) @@ -3297,13 +3301,30 @@ void free_unref_page(struct page *page) { unsigned long flags; unsigned long pfn = page_to_pfn(page); + int migratetype; if (!free_unref_page_prepare(page, pfn)) return; - local_irq_save(flags); - free_unref_page_commit(page, pfn); - local_irq_restore(flags); + /* + * We only track unmovable, reclaimable and movable on pcp lists. + * Place ISOLATE pages on the isolated list because they are being + * offlined but treat HIGHATOMIC as movable pages so we can get those + * areas back if necessary. Otherwise, we may have to free + * excessively into the page allocator + */ + migratetype = get_pcppage_migratetype(page); + if (unlikely(migratetype >= MIGRATE_PCPTYPES)) { + if (unlikely(is_migrate_isolate(migratetype))) { + free_one_page(page_zone(page), page, pfn, 0, migratetype, FPI_NONE); + return; + } + migratetype = MIGRATE_MOVABLE; + } + + local_lock_irqsave(&pagesets.lock, flags); + free_unref_page_commit(page, pfn, migratetype); + local_unlock_irqrestore(&pagesets.lock, flags); } /* @@ -3314,34 +3335,56 @@ void free_unref_page_list(struct list_head *list) struct page *page, *next; unsigned long flags, pfn; int batch_count = 0; + int migratetype; /* Prepare pages for freeing */ list_for_each_entry_safe(page, next, list, lru) { pfn = page_to_pfn(page); if (!free_unref_page_prepare(page, pfn)) list_del(&page->lru); + + /* + * Free isolated pages directly to the allocator, see + * comment in free_unref_page. + */ + migratetype = get_pcppage_migratetype(page); + if (unlikely(migratetype >= MIGRATE_PCPTYPES)) { + if (unlikely(is_migrate_isolate(migratetype))) { + list_del(&page->lru); + free_one_page(page_zone(page), page, pfn, 0, + migratetype, FPI_NONE); + continue; + } + + /* + * Non-isolated types over MIGRATE_PCPTYPES get added + * to the MIGRATE_MOVABLE pcp list. + */ + set_pcppage_migratetype(page, MIGRATE_MOVABLE); + } + set_page_private(page, pfn); } - local_irq_save(flags); + local_lock_irqsave(&pagesets.lock, flags); list_for_each_entry_safe(page, next, list, lru) { - unsigned long pfn = page_private(page); - + pfn = page_private(page); set_page_private(page, 0); + migratetype = get_pcppage_migratetype(page); trace_mm_page_free_batched(page); - free_unref_page_commit(page, pfn); + free_unref_page_commit(page, pfn, migratetype); /* * Guard against excessive IRQ disabled times when we get * a large list of pages to free. */ if (++batch_count == SWAP_CLUSTER_MAX) { - local_irq_restore(flags); + local_unlock_irqrestore(&pagesets.lock, flags); batch_count = 0; - local_irq_save(flags); + local_lock_irqsave(&pagesets.lock, flags); } } - local_irq_restore(flags); + local_unlock_irqrestore(&pagesets.lock, flags); } /* @@ -3440,7 +3483,8 @@ void __putback_isolated_page(struct page *page, unsigned int order, int mt) * * Must be called with interrupts disabled. */ -static inline void zone_statistics(struct zone *preferred_zone, struct zone *z) +static inline void zone_statistics(struct zone *preferred_zone, struct zone *z, + long nr_account) { #ifdef CONFIG_NUMA enum numa_stat_item local_stat = NUMA_LOCAL; @@ -3453,12 +3497,12 @@ static inline void zone_statistics(struct zone *preferred_zone, struct zone *z) local_stat = NUMA_OTHER; if (zone_to_nid(z) == zone_to_nid(preferred_zone)) - __inc_numa_state(z, NUMA_HIT); + __count_numa_events(z, NUMA_HIT, nr_account); else { - __inc_numa_state(z, NUMA_MISS); - __inc_numa_state(preferred_zone, NUMA_FOREIGN); + __count_numa_events(z, NUMA_MISS, nr_account); + __count_numa_events(preferred_zone, NUMA_FOREIGN, nr_account); } - __inc_numa_state(z, local_stat); + __count_numa_events(z, local_stat, nr_account); #endif } @@ -3498,15 +3542,15 @@ static struct page *rmqueue_pcplist(struct zone *preferred_zone, struct page *page; unsigned long flags; - local_irq_save(flags); - pcp = &this_cpu_ptr(zone->pageset)->pcp; + local_lock_irqsave(&pagesets.lock, flags); + pcp = this_cpu_ptr(zone->per_cpu_pageset); list = &pcp->lists[migratetype]; page = __rmqueue_pcplist(zone, migratetype, alloc_flags, pcp, list); + local_unlock_irqrestore(&pagesets.lock, flags); if (page) { __count_zid_vm_events(PGALLOC, page_zonenum(page), 1); - zone_statistics(preferred_zone, zone); + zone_statistics(preferred_zone, zone, 1); } - local_irq_restore(flags); return page; } @@ -3558,15 +3602,15 @@ struct page *rmqueue(struct zone *preferred_zone, if (!page) page = __rmqueue(zone, order, migratetype, alloc_flags); } while (page && check_new_pages(page, order)); - spin_unlock(&zone->lock); if (!page) goto failed; + __mod_zone_freepage_state(zone, -(1 << order), get_pcppage_migratetype(page)); + spin_unlock_irqrestore(&zone->lock, flags); __count_zid_vm_events(PGALLOC, page_zonenum(page), 1 << order); - zone_statistics(preferred_zone, zone); - local_irq_restore(flags); + zone_statistics(preferred_zone, zone, 1); out: /* Separate test+clear to avoid unnecessary atomics */ @@ -3579,7 +3623,7 @@ out: return page; failed: - local_irq_restore(flags); + spin_unlock_irqrestore(&zone->lock, flags); return NULL; } @@ -5047,7 +5091,7 @@ unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid, struct alloc_context ac; gfp_t alloc_gfp; unsigned int alloc_flags = ALLOC_WMARK_LOW; - int nr_populated = 0; + int nr_populated = 0, nr_account = 0; if (unlikely(nr_pages <= 0)) return 0; @@ -5104,8 +5148,8 @@ unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid, goto failed; /* Attempt the batch allocation */ - local_irq_save(flags); - pcp = &this_cpu_ptr(zone->pageset)->pcp; + local_lock_irqsave(&pagesets.lock, flags); + pcp = this_cpu_ptr(zone->per_cpu_pageset); pcp_list = &pcp->lists[ac.migratetype]; while (nr_populated < nr_pages) { @@ -5124,15 +5168,7 @@ unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid, goto failed_irq; break; } - - /* - * Ideally this would be batched but the best way to do - * that cheaply is to first convert zone_statistics to - * be inaccurate per-cpu counter like vm_events to avoid - * a RMW cycle then do the accounting with IRQs enabled. - */ - __count_zid_vm_events(PGALLOC, zone_idx(zone), 1); - zone_statistics(ac.preferred_zoneref->zone, zone); + nr_account++; prep_new_page(page, 0, gfp, 0); if (page_list) @@ -5142,12 +5178,15 @@ unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid, nr_populated++; } - local_irq_restore(flags); + local_unlock_irqrestore(&pagesets.lock, flags); + + __count_zid_vm_events(PGALLOC, zone_idx(zone), nr_account); + zone_statistics(ac.preferred_zoneref->zone, zone, nr_account); return nr_populated; failed_irq: - local_irq_restore(flags); + local_unlock_irqrestore(&pagesets.lock, flags); failed: page = __alloc_pages(gfp, 0, preferred_nid, nodemask); @@ -5720,7 +5759,7 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask) continue; for_each_online_cpu(cpu) - free_pcp += per_cpu_ptr(zone->pageset, cpu)->pcp.count; + free_pcp += per_cpu_ptr(zone->per_cpu_pageset, cpu)->count; } printk("active_anon:%lu inactive_anon:%lu isolated_anon:%lu\n" @@ -5812,7 +5851,7 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask) free_pcp = 0; for_each_online_cpu(cpu) - free_pcp += per_cpu_ptr(zone->pageset, cpu)->pcp.count; + free_pcp += per_cpu_ptr(zone->per_cpu_pageset, cpu)->count; show_node(zone); printk(KERN_CONT @@ -5853,7 +5892,7 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask) K(zone_page_state(zone, NR_MLOCK)), K(zone_page_state(zone, NR_BOUNCE)), K(free_pcp), - K(this_cpu_read(zone->pageset->pcp.count)), + K(this_cpu_read(zone->per_cpu_pageset->count)), K(zone_page_state(zone, NR_FREE_CMA_PAGES))); printk("lowmem_reserve[]:"); for (i = 0; i < MAX_NR_ZONES; i++) @@ -6180,11 +6219,12 @@ static void build_zonelists(pg_data_t *pgdat) * not check if the processor is online before following the pageset pointer. * Other parts of the kernel may not check if the zone is available. */ -static void pageset_init(struct per_cpu_pageset *p); +static void per_cpu_pages_init(struct per_cpu_pages *pcp, struct per_cpu_zonestat *pzstats); /* These effectively disable the pcplists in the boot pageset completely */ #define BOOT_PAGESET_HIGH 0 #define BOOT_PAGESET_BATCH 1 -static DEFINE_PER_CPU(struct per_cpu_pageset, boot_pageset); +static DEFINE_PER_CPU(struct per_cpu_pages, boot_pageset); +static DEFINE_PER_CPU(struct per_cpu_zonestat, boot_zonestats); static DEFINE_PER_CPU(struct per_cpu_nodestat, boot_nodestats); static void __build_all_zonelists(void *data) @@ -6251,7 +6291,7 @@ build_all_zonelists_init(void) * (a chicken-egg dilemma). */ for_each_possible_cpu(cpu) - pageset_init(&per_cpu(boot_pageset, cpu)); + per_cpu_pages_init(&per_cpu(boot_pageset, cpu), &per_cpu(boot_zonestats, cpu)); mminit_verify_zonelist(); cpuset_init_current_mems_allowed(); @@ -6650,14 +6690,13 @@ static void pageset_update(struct per_cpu_pages *pcp, unsigned long high, WRITE_ONCE(pcp->high, high); } -static void pageset_init(struct per_cpu_pageset *p) +static void per_cpu_pages_init(struct per_cpu_pages *pcp, struct per_cpu_zonestat *pzstats) { - struct per_cpu_pages *pcp; int migratetype; - memset(p, 0, sizeof(*p)); + memset(pcp, 0, sizeof(*pcp)); + memset(pzstats, 0, sizeof(*pzstats)); - pcp = &p->pcp; for (migratetype = 0; migratetype < MIGRATE_PCPTYPES; migratetype++) INIT_LIST_HEAD(&pcp->lists[migratetype]); @@ -6674,12 +6713,12 @@ static void pageset_init(struct per_cpu_pageset *p) static void __zone_set_pageset_high_and_batch(struct zone *zone, unsigned long high, unsigned long batch) { - struct per_cpu_pageset *p; + struct per_cpu_pages *pcp; int cpu; for_each_possible_cpu(cpu) { - p = per_cpu_ptr(zone->pageset, cpu); - pageset_update(&p->pcp, high, batch); + pcp = per_cpu_ptr(zone->per_cpu_pageset, cpu); + pageset_update(pcp, high, batch); } } @@ -6714,13 +6753,20 @@ static void zone_set_pageset_high_and_batch(struct zone *zone) void __meminit setup_zone_pageset(struct zone *zone) { - struct per_cpu_pageset *p; int cpu; - zone->pageset = alloc_percpu(struct per_cpu_pageset); + /* Size may be 0 on !SMP && !NUMA */ + if (sizeof(struct per_cpu_zonestat) > 0) + zone->per_cpu_zonestats = alloc_percpu(struct per_cpu_zonestat); + + zone->per_cpu_pageset = alloc_percpu(struct per_cpu_pages); for_each_possible_cpu(cpu) { - p = per_cpu_ptr(zone->pageset, cpu); - pageset_init(p); + struct per_cpu_pages *pcp; + struct per_cpu_zonestat *pzstats; + + pcp = per_cpu_ptr(zone->per_cpu_pageset, cpu); + pzstats = per_cpu_ptr(zone->per_cpu_zonestats, cpu); + per_cpu_pages_init(pcp, pzstats); } zone_set_pageset_high_and_batch(zone); @@ -6747,9 +6793,9 @@ void __init setup_per_cpu_pageset(void) * the nodes these zones are associated with. */ for_each_possible_cpu(cpu) { - struct per_cpu_pageset *pcp = &per_cpu(boot_pageset, cpu); - memset(pcp->vm_numa_stat_diff, 0, - sizeof(pcp->vm_numa_stat_diff)); + struct per_cpu_zonestat *pzstats = &per_cpu(boot_zonestats, cpu); + memset(pzstats->vm_numa_event, 0, + sizeof(pzstats->vm_numa_event)); } #endif @@ -6765,7 +6811,8 @@ static __meminit void zone_pcp_init(struct zone *zone) * relies on the ability of the linker to provide the * offset of a (static) per cpu variable into the per cpu area. */ - zone->pageset = &boot_pageset; + zone->per_cpu_pageset = &boot_pageset; + zone->per_cpu_zonestats = &boot_zonestats; zone->pageset_high = BOOT_PAGESET_HIGH; zone->pageset_batch = BOOT_PAGESET_BATCH; @@ -9050,15 +9097,17 @@ void zone_pcp_enable(struct zone *zone) void zone_pcp_reset(struct zone *zone) { int cpu; - struct per_cpu_pageset *pset; + struct per_cpu_zonestat *pzstats; - if (zone->pageset != &boot_pageset) { + if (zone->per_cpu_pageset != &boot_pageset) { for_each_online_cpu(cpu) { - pset = per_cpu_ptr(zone->pageset, cpu); - drain_zonestat(zone, pset); + pzstats = per_cpu_ptr(zone->per_cpu_zonestats, cpu); + drain_zonestat(zone, pzstats); } - free_percpu(zone->pageset); - zone->pageset = &boot_pageset; + free_percpu(zone->per_cpu_pageset); + free_percpu(zone->per_cpu_zonestats); + zone->per_cpu_pageset = &boot_pageset; + zone->per_cpu_zonestats = &boot_zonestats; } } diff --git a/mm/shmem.c b/mm/shmem.c index 680d83cab077..2d2296786db3 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; } @@ -3532,9 +3533,10 @@ 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) { @@ -3579,14 +3581,15 @@ 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); } @@ -3703,7 +3706,7 @@ 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/slub.c b/mm/slub.c index e32ded30506e..27660a93d456 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -44,13 +44,22 @@ /* * Lock order: * 1. slab_mutex (Global Mutex) - * 2. node->list_lock - * 3. slab_lock(page) (Only on some arches and for debugging) + * 2. node->list_lock (Spinlock) + * OR + * kmem_cache->cpu_slab->lock (Local lock) + * 3. slab_lock(page) (Only on some arches or for debugging) + * 4. object_map_lock (Only for debugging) * * slab_mutex * * The role of the slab_mutex is to protect the list of all the slabs * and to synchronize major metadata changes to slab cache structures. + * Also synchronizes memory hotplug callbacks. + * + * slab_lock + * + * The slab_lock is a wrapper around the page lock, thus it is a bit + * spinlock. * * The slab_lock is only used for debugging and on arches that do not * have the ability to do a cmpxchg_double. It only protects: @@ -59,6 +68,8 @@ * C. page->objects -> Number of objects in page * D. page->frozen -> frozen state * + * Frozen slabs + * * If a slab is frozen then it is exempt from list management. It is not * on any list except per cpu partial list. The processor that froze the * slab is the one who can perform list operations on the page. Other @@ -66,6 +77,8 @@ * froze the slab is the only one that can retrieve the objects from the * page's freelist. * + * list_lock + * * The list_lock protects the partial and full list on each node and * the partial slab counter. If taken then no new slabs may be added or * removed from the lists nor make the number of partial slabs be modified. @@ -77,10 +90,36 @@ * slabs, operations can continue without any centralized lock. F.e. * allocating a long series of objects that fill up slabs does not require * the list lock. - * Interrupts are disabled during allocation and deallocation in order to - * make the slab allocator safe to use in the context of an irq. In addition - * interrupts are disabled to ensure that the processor does not change - * while handling per_cpu slabs, due to kernel preemption. + * + * cpu_slab->lock local lock + * + * This locks protect slowpath manipulation of all kmem_cache_cpu fields + * except the stat counters. This is a percpu structure manipulated only by + * the local cpu, so the lock protects against being preempted or interrupted + * by an irq. Fast path operations rely on lockless operations instead. + * On PREEMPT_RT, the local lock does not actually disable irqs (and thus + * prevent the lockless operations), so fastpath operations also need to take + * the lock and are no longer lockless. + * + * lockless fastpaths + * + * The fast path allocation (slab_alloc_node()) and freeing (do_slab_free()) + * are fully lockless when satisfied from the percpu slab (and when + * cmpxchg_double is possible to use, otherwise slab_lock is taken). + * They also don't disable preemption or migration or irqs. They rely on + * the transaction id (tid) field to detect being preempted or moved to + * another cpu. + * + * irq, preemption, migration considerations + * + * Interrupts are disabled as part of list_lock or local_lock operations, or + * around the slab_lock operation, in order to make the slab allocator safe + * to use in the context of an irq. + * + * In addition, preemption (or migration on PREEMPT_RT) is disabled in the + * allocation slowpath, bulk allocation, and put_cpu_partial(), so that the + * local cpu doesn't change in the process and e.g. the kmem_cache_cpu pointer + * doesn't have to be revalidated in each section protected by the local lock. * * SLUB assigns one slab for allocation to each processor. * Allocations only occur from these slabs called cpu slabs. @@ -116,6 +155,26 @@ * the fast path and disables lockless freelists. */ +/* + * We could simply use migrate_disable()/enable() but as long as it's a + * function call even on !PREEMPT_RT, use inline preempt_disable() there. + */ +#ifndef CONFIG_PREEMPT_RT +#define slub_get_cpu_ptr(var) get_cpu_ptr(var) +#define slub_put_cpu_ptr(var) put_cpu_ptr(var) +#else +#define slub_get_cpu_ptr(var) \ +({ \ + migrate_disable(); \ + this_cpu_ptr(var); \ +}) +#define slub_put_cpu_ptr(var) \ +do { \ + (void)(var); \ + migrate_enable(); \ +} while (0) +#endif + #ifdef CONFIG_SLUB_DEBUG #ifdef CONFIG_SLUB_DEBUG_ON DEFINE_STATIC_KEY_TRUE(slub_debug_enabled); @@ -354,25 +413,42 @@ static inline unsigned int oo_objects(struct kmem_cache_order_objects x) /* * Per slab locking using the pagelock */ -static __always_inline void slab_lock(struct page *page) +static __always_inline void +__slab_lock(struct page *page, unsigned long *flags, bool disable_irqs) { VM_BUG_ON_PAGE(PageTail(page), page); + if (disable_irqs) + local_irq_save(*flags); bit_spin_lock(PG_locked, &page->flags); } -static __always_inline void slab_unlock(struct page *page) +static __always_inline void +__slab_unlock(struct page *page, unsigned long *flags, bool disable_irqs) { VM_BUG_ON_PAGE(PageTail(page), page); __bit_spin_unlock(PG_locked, &page->flags); + if (disable_irqs) + local_irq_restore(*flags); } -/* Interrupts must be disabled (for the fallback code to work right) */ -static inline bool __cmpxchg_double_slab(struct kmem_cache *s, struct page *page, +static __always_inline void +slab_lock(struct page *page, unsigned long *flags) +{ + __slab_lock(page, flags, IS_ENABLED(CONFIG_PREEMPT_RT)); +} + +static __always_inline void slab_unlock(struct page *page, unsigned long *flags) +{ + __slab_unlock(page, flags, IS_ENABLED(CONFIG_PREEMPT_RT)); +} + +static inline bool ___cmpxchg_double_slab(struct kmem_cache *s, struct page *page, void *freelist_old, unsigned long counters_old, void *freelist_new, unsigned long counters_new, - const char *n) + const char *n, bool disable_irqs) { - VM_BUG_ON(!irqs_disabled()); + if (!disable_irqs) + lockdep_assert_irqs_disabled(); #if defined(CONFIG_HAVE_CMPXCHG_DOUBLE) && \ defined(CONFIG_HAVE_ALIGNED_STRUCT_PAGE) if (s->flags & __CMPXCHG_DOUBLE) { @@ -383,15 +459,17 @@ static inline bool __cmpxchg_double_slab(struct kmem_cache *s, struct page *page } else #endif { - slab_lock(page); + unsigned long flags; + + __slab_lock(page, &flags, disable_irqs); if (page->freelist == freelist_old && page->counters == counters_old) { page->freelist = freelist_new; page->counters = counters_new; - slab_unlock(page); + __slab_unlock(page, &flags, disable_irqs); return true; } - slab_unlock(page); + __slab_unlock(page, &flags, disable_irqs); } cpu_relax(); @@ -404,51 +482,46 @@ static inline bool __cmpxchg_double_slab(struct kmem_cache *s, struct page *page return false; } +/* + * Interrupts must be disabled (for the fallback code to work right), typically + * by an _irqsave() lock variant. Except on PREEMPT_RT where locks are different + * so we disable interrupts explicitly here. + */ +static inline bool __cmpxchg_double_slab(struct kmem_cache *s, struct page *page, + void *freelist_old, unsigned long counters_old, + void *freelist_new, unsigned long counters_new, + const char *n) +{ + return ___cmpxchg_double_slab(s, page, freelist_old, counters_old, + freelist_new, counters_new, n, + IS_ENABLED(CONFIG_PREEMPT_RT)); +} + static inline bool cmpxchg_double_slab(struct kmem_cache *s, struct page *page, void *freelist_old, unsigned long counters_old, void *freelist_new, unsigned long counters_new, const char *n) { -#if defined(CONFIG_HAVE_CMPXCHG_DOUBLE) && \ - defined(CONFIG_HAVE_ALIGNED_STRUCT_PAGE) - if (s->flags & __CMPXCHG_DOUBLE) { - if (cmpxchg_double(&page->freelist, &page->counters, - freelist_old, counters_old, - freelist_new, counters_new)) - return true; - } else -#endif - { - unsigned long flags; + return ___cmpxchg_double_slab(s, page, freelist_old, counters_old, + freelist_new, counters_new, n, true); +} - local_irq_save(flags); - slab_lock(page); - if (page->freelist == freelist_old && - page->counters == counters_old) { - page->freelist = freelist_new; - page->counters = counters_new; - slab_unlock(page); - local_irq_restore(flags); - return true; - } - slab_unlock(page); - local_irq_restore(flags); - } +#ifdef CONFIG_SLUB_DEBUG +static unsigned long object_map[BITS_TO_LONGS(MAX_OBJS_PER_PAGE)]; +static DEFINE_RAW_SPINLOCK(object_map_lock); - cpu_relax(); - stat(s, CMPXCHG_DOUBLE_FAIL); +static void __fill_map(unsigned long *obj_map, struct kmem_cache *s, + struct page *page) +{ + void *addr = page_address(page); + void *p; -#ifdef SLUB_DEBUG_CMPXCHG - pr_info("%s %s: cmpxchg double redo ", n, s->name); -#endif + bitmap_zero(obj_map, page->objects); - return false; + for (p = page->freelist; p; p = get_freepointer(s, p)) + set_bit(__obj_to_index(s, addr, p), obj_map); } -#ifdef CONFIG_SLUB_DEBUG -static unsigned long object_map[BITS_TO_LONGS(MAX_OBJS_PER_PAGE)]; -static DEFINE_SPINLOCK(object_map_lock); - /* * Determine a map of object in use on a page. * @@ -458,17 +531,11 @@ static DEFINE_SPINLOCK(object_map_lock); static unsigned long *get_map(struct kmem_cache *s, struct page *page) __acquires(&object_map_lock) { - void *p; - void *addr = page_address(page); - VM_BUG_ON(!irqs_disabled()); - spin_lock(&object_map_lock); + raw_spin_lock(&object_map_lock); - bitmap_zero(object_map, page->objects); - - for (p = page->freelist; p; p = get_freepointer(s, p)) - set_bit(__obj_to_index(s, addr, p), object_map); + __fill_map(object_map, s, page); return object_map; } @@ -476,7 +543,7 @@ 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) @@ -963,8 +1030,6 @@ static int check_slab(struct kmem_cache *s, struct page *page) { int maxobj; - VM_BUG_ON(!irqs_disabled()); - if (!PageSlab(page)) { slab_err(s, page, "Not a valid slab page"); return 0; @@ -1225,11 +1290,11 @@ static noinline int free_debug_processing( struct kmem_cache_node *n = get_node(s, page_to_nid(page)); void *object = head; int cnt = 0; - unsigned long flags; + unsigned long flags, flags2; int ret = 0; spin_lock_irqsave(&n->list_lock, flags); - slab_lock(page); + slab_lock(page, &flags2); if (s->flags & SLAB_CONSISTENCY_CHECKS) { if (!check_slab(s, page)) @@ -1262,7 +1327,7 @@ out: slab_err(s, page, "Bulk freelist count(%d) invalid(%d)\n", bulk_cnt, cnt); - slab_unlock(page); + slab_unlock(page, &flags2); spin_unlock_irqrestore(&n->list_lock, flags); if (!ret) slab_fix(s, "Object at 0x%p not freed", object); @@ -1540,20 +1605,8 @@ static __always_inline bool slab_free_hook(struct kmem_cache *s, { kmemleak_free_recursive(x, s->flags); - /* - * Trouble is that we may no longer disable interrupts in the fast path - * So in order to make the debug calls that expect irqs to be - * disabled we need to disable interrupts temporarily. - */ -#ifdef CONFIG_LOCKDEP - { - unsigned long flags; + debug_check_no_locks_freed(x, s->object_size); - local_irq_save(flags); - debug_check_no_locks_freed(x, s->object_size); - local_irq_restore(flags); - } -#endif if (!(s->flags & SLAB_DEBUG_OBJECTS)) debug_check_no_obj_freed(x, s->object_size); @@ -1770,9 +1823,6 @@ static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node) flags &= gfp_allowed_mask; - if (gfpflags_allow_blocking(flags)) - local_irq_enable(); - flags |= s->allocflags; /* @@ -1831,8 +1881,6 @@ static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node) page->frozen = 1; out: - if (gfpflags_allow_blocking(flags)) - local_irq_disable(); if (!page) return NULL; @@ -1846,6 +1894,8 @@ static struct page *new_slab(struct kmem_cache *s, gfp_t flags, int node) if (unlikely(flags & GFP_SLAB_BUG_MASK)) flags = kmalloc_fix_flags(flags); + WARN_ON_ONCE(s->ctor && (flags & __GFP_ZERO)); + return allocate_slab(s, flags & (GFP_RECLAIM_MASK | GFP_CONSTRAINT_MASK), node); } @@ -1976,11 +2026,12 @@ 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 page **ret_page, gfp_t gfpflags) { struct page *page, *page2; void *object = NULL; unsigned int available = 0; + unsigned long flags; int objects; /* @@ -1992,11 +2043,11 @@ 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); + spin_lock_irqsave(&n->list_lock, flags); list_for_each_entry_safe(page, page2, &n->partial, slab_list) { void *t; - if (!pfmemalloc_match(page, flags)) + if (!pfmemalloc_match(page, gfpflags)) continue; t = acquire_slab(s, n, page, object == NULL, &objects); @@ -2005,7 +2056,7 @@ static void *get_partial_node(struct kmem_cache *s, struct kmem_cache_node *n, available += objects; if (!object) { - c->page = page; + *ret_page = page; stat(s, ALLOC_FROM_PARTIAL); object = t; } else { @@ -2017,7 +2068,7 @@ static void *get_partial_node(struct kmem_cache *s, struct kmem_cache_node *n, break; } - spin_unlock(&n->list_lock); + spin_unlock_irqrestore(&n->list_lock, flags); return object; } @@ -2025,7 +2076,7 @@ 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 page **ret_page) { #ifdef CONFIG_NUMA struct zonelist *zonelist; @@ -2067,7 +2118,7 @@ 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, ret_page, flags); if (object) { /* * Don't check read_mems_allowed_retry() @@ -2089,7 +2140,7 @@ 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 page **ret_page) { void *object; int searchnode = node; @@ -2097,11 +2148,11 @@ 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), ret_page, flags); if (object || node != NUMA_NO_NODE) return object; - return get_any_partial(s, flags, c); + return get_any_partial(s, flags, ret_page); } #ifdef CONFIG_PREEMPTION @@ -2168,16 +2219,23 @@ static inline void note_cmpxchg_failure(const char *n, static void init_kmem_cache_cpus(struct kmem_cache *s) { int cpu; + struct kmem_cache_cpu *c; - for_each_possible_cpu(cpu) - per_cpu_ptr(s->cpu_slab, cpu)->tid = init_tid(cpu); + for_each_possible_cpu(cpu) { + c = per_cpu_ptr(s->cpu_slab, cpu); + local_lock_init(&c->lock); + c->tid = init_tid(cpu); + } } /* - * Remove the cpu slab + * Finishes removing the cpu slab. Merges cpu's freelist with page's freelist, + * unfreezes the slabs and puts it on the proper list. + * Assumes the slab has been already safely taken away from kmem_cache_cpu + * by the caller. */ static void deactivate_slab(struct kmem_cache *s, struct page *page, - void *freelist, struct kmem_cache_cpu *c) + void *freelist) { enum slab_modes { M_NONE, M_PARTIAL, M_FULL, M_FREE }; struct kmem_cache_node *n = get_node(s, page_to_nid(page)); @@ -2185,6 +2243,7 @@ static void deactivate_slab(struct kmem_cache *s, struct page *page, enum slab_modes l = M_NONE, m = M_NONE; void *nextfree, *freelist_iter, *freelist_tail; int tail = DEACTIVATE_TO_HEAD; + unsigned long flags = 0; struct page new; struct page old; @@ -2260,7 +2319,7 @@ redo: * that acquire_slab() will see a slab page that * is frozen */ - spin_lock(&n->list_lock); + spin_lock_irqsave(&n->list_lock, flags); } } else { m = M_FULL; @@ -2271,7 +2330,7 @@ redo: * slabs from diagnostic functions will not see * any frozen slabs. */ - spin_lock(&n->list_lock); + spin_lock_irqsave(&n->list_lock, flags); } } @@ -2288,14 +2347,14 @@ redo: } l = m; - if (!__cmpxchg_double_slab(s, page, + if (!cmpxchg_double_slab(s, page, old.freelist, old.counters, new.freelist, new.counters, "unfreezing slab")) goto redo; if (lock) - spin_unlock(&n->list_lock); + spin_unlock_irqrestore(&n->list_lock, flags); if (m == M_PARTIAL) stat(s, tail); @@ -2306,38 +2365,29 @@ redo: discard_slab(s, page); stat(s, FREE_SLAB); } - - c->page = NULL; - c->freelist = NULL; } -/* - * Unfreeze all the cpu partial slabs. - * - * This function must be called with interrupts disabled - * 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) -{ #ifdef CONFIG_SLUB_CPU_PARTIAL +static void __unfreeze_partials(struct kmem_cache *s, struct page *partial_page) +{ struct kmem_cache_node *n = NULL, *n2 = NULL; struct page *page, *discard_page = NULL; + unsigned long flags = 0; - while ((page = slub_percpu_partial(c))) { + while (partial_page) { struct page new; struct page old; - slub_set_percpu_partial(c, page); + page = partial_page; + partial_page = page->next; n2 = get_node(s, page_to_nid(page)); if (n != n2) { if (n) - spin_unlock(&n->list_lock); + spin_unlock_irqrestore(&n->list_lock, flags); n = n2; - spin_lock(&n->list_lock); + spin_lock_irqsave(&n->list_lock, flags); } do { @@ -2366,7 +2416,7 @@ static void unfreeze_partials(struct kmem_cache *s, } if (n) - spin_unlock(&n->list_lock); + spin_unlock_irqrestore(&n->list_lock, flags); while (discard_page) { page = discard_page; @@ -2376,10 +2426,50 @@ static void unfreeze_partials(struct kmem_cache *s, discard_slab(s, page); stat(s, FREE_SLAB); } -#endif /* CONFIG_SLUB_CPU_PARTIAL */ } /* + * Unfreeze all the cpu partial slabs. + * + * This function must be called with preemption or migration + * disabled. + */ +static void unfreeze_partials(struct kmem_cache *s) +{ + struct page *partial_page; + + do { + partial_page = this_cpu_read(s->cpu_slab->partial); + + } while (partial_page && + this_cpu_cmpxchg(s->cpu_slab->partial, partial_page, NULL) + != partial_page); + + if (partial_page) + __unfreeze_partials(s, partial_page); +} + +static void unfreeze_partials_cpu(struct kmem_cache *s, + struct kmem_cache_cpu *c) +{ + struct page *partial_page; + + partial_page = slub_percpu_partial(c); + c->partial = NULL; + + if (partial_page) + __unfreeze_partials(s, partial_page); +} + +#else /* CONFIG_SLUB_CPU_PARTIAL */ + +static void unfreeze_partials(struct kmem_cache *s) { } +static void unfreeze_partials_cpu(struct kmem_cache *s, + struct kmem_cache_cpu *c) { } + +#endif /* CONFIG_SLUB_CPU_PARTIAL */ + +/* * Put a page that was just frozen (in __slab_free|get_partial_node) into a * partial page slot if available. * @@ -2393,7 +2483,7 @@ static void put_cpu_partial(struct kmem_cache *s, struct page *page, int drain) int pages; int pobjects; - preempt_disable(); + slub_get_cpu_ptr(s->cpu_slab); do { pages = 0; pobjects = 0; @@ -2403,14 +2493,11 @@ static void put_cpu_partial(struct kmem_cache *s, struct page *page, int drain) pobjects = oldpage->pobjects; pages = oldpage->pages; if (drain && pobjects > slub_cpu_partial(s)) { - unsigned long flags; /* * partial array is full. Move the existing * set to the per node partial list. */ - local_irq_save(flags); - unfreeze_partials(s, this_cpu_ptr(s->cpu_slab)); - local_irq_restore(flags); + unfreeze_partials(s); oldpage = NULL; pobjects = 0; pages = 0; @@ -2427,58 +2514,113 @@ static void put_cpu_partial(struct kmem_cache *s, struct page *page, int drain) } while (this_cpu_cmpxchg(s->cpu_slab->partial, oldpage, page) != oldpage); - if (unlikely(!slub_cpu_partial(s))) { - unsigned long flags; - - local_irq_save(flags); - unfreeze_partials(s, this_cpu_ptr(s->cpu_slab)); - local_irq_restore(flags); - } - preempt_enable(); + slub_put_cpu_ptr(s->cpu_slab); #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, + bool lock) { - stat(s, CPUSLAB_FLUSH); - deactivate_slab(s, c->page, c->freelist, c); + unsigned long flags; + void *freelist; + struct page *page; + + if (lock) + local_lock_irqsave(&s->cpu_slab->lock, flags); + + freelist = c->freelist; + page = c->page; + c->page = NULL; + c->freelist = NULL; c->tid = next_tid(c->tid); + + if (lock) + local_unlock_irqrestore(&s->cpu_slab->lock, flags); + + if (page) + deactivate_slab(s, page, freelist); + + stat(s, CPUSLAB_FLUSH); } -/* - * Flush cpu slab. - * - * Called from IPI handler with interrupts disabled. - */ static inline void __flush_cpu_slab(struct kmem_cache *s, int cpu) { struct kmem_cache_cpu *c = per_cpu_ptr(s->cpu_slab, cpu); if (c->page) - flush_slab(s, c); + flush_slab(s, c, false); - unfreeze_partials(s, c); + unfreeze_partials_cpu(s, c); } -static void flush_cpu_slab(void *d) +struct slub_flush_work { + struct work_struct work; + struct kmem_cache *s; + bool skip; +}; + +/* + * Flush cpu slab. + * + * Called from CPU work handler with migration disabled. + */ +static void flush_cpu_slab(struct work_struct *w) { - struct kmem_cache *s = d; + struct kmem_cache *s; + struct kmem_cache_cpu *c; + struct slub_flush_work *sfw; - __flush_cpu_slab(s, smp_processor_id()); + sfw = container_of(w, struct slub_flush_work, work); + + s = sfw->s; + c = this_cpu_ptr(s->cpu_slab); + + if (c->page) + flush_slab(s, c, true); + + unfreeze_partials(s); } -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(struct kmem_cache *s) { - on_each_cpu_cond(has_cpu_slab, flush_cpu_slab, s, 1); + struct slub_flush_work *sfw; + unsigned int cpu; + + cpus_read_lock(); + 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); + cpus_read_unlock(); } /* @@ -2488,14 +2630,10 @@ static void flush_all(struct kmem_cache *s) static int slub_cpu_dead(unsigned int cpu) { struct kmem_cache *s; - unsigned long flags; mutex_lock(&slab_mutex); - list_for_each_entry(s, &slab_caches, list) { - local_irq_save(flags); + list_for_each_entry(s, &slab_caches, list) __flush_cpu_slab(s, cpu); - local_irq_restore(flags); - } mutex_unlock(&slab_mutex); return 0; } @@ -2578,41 +2716,6 @@ slab_out_of_memory(struct kmem_cache *s, gfp_t gfpflags, int nid) #endif } -static inline void *new_slab_objects(struct kmem_cache *s, gfp_t flags, - int node, struct kmem_cache_cpu **pc) -{ - void *freelist; - struct kmem_cache_cpu *c = *pc; - struct page *page; - - WARN_ON_ONCE(s->ctor && (flags & __GFP_ZERO)); - - freelist = get_partial(s, flags, node, c); - - if (freelist) - return freelist; - - page = new_slab(s, flags, node); - if (page) { - c = raw_cpu_ptr(s->cpu_slab); - if (c->page) - flush_slab(s, c); - - /* - * No other reference to the page yet so we can - * muck around with it freely without cmpxchg - */ - freelist = page->freelist; - page->freelist = NULL; - - stat(s, ALLOC_SLAB); - c->page = page; - *pc = c; - } - - return freelist; -} - static inline bool pfmemalloc_match(struct page *page, gfp_t gfpflags) { if (unlikely(PageSlabPfmemalloc(page))) @@ -2671,7 +2774,7 @@ static inline void *get_freelist(struct kmem_cache *s, struct page *page) * we need to allocate a new slab. This is the slowest path since it involves * a call to the page allocator and the setup of a new slab. * - * Version of __slab_alloc to use when we know that interrupts are + * Version of __slab_alloc to use when we know that preemption is * already disabled (which is the case for bulk allocation). */ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, @@ -2679,10 +2782,13 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, { void *freelist; struct page *page; + unsigned long flags; stat(s, ALLOC_SLOWPATH); - page = c->page; +reread_page: + + page = READ_ONCE(c->page); if (!page) { /* * if the node is not online or has no normal memory, just @@ -2705,8 +2811,7 @@ redo: goto redo; } else { stat(s, ALLOC_NODE_MISMATCH); - deactivate_slab(s, page, c->freelist, c); - goto new_slab; + goto deactivate_slab; } } @@ -2715,12 +2820,15 @@ redo: * PFMEMALLOC but right now, we are losing the pfmemalloc * information when the page leaves the per-cpu allocator */ - if (unlikely(!pfmemalloc_match(page, gfpflags))) { - deactivate_slab(s, page, c->freelist, c); - goto new_slab; + if (unlikely(!pfmemalloc_match(page, gfpflags))) + goto deactivate_slab; + + /* must check again c->page in case we got preempted and it changed */ + local_lock_irqsave(&s->cpu_slab->lock, flags); + if (unlikely(page != c->page)) { + local_unlock_irqrestore(&s->cpu_slab->lock, flags); + goto reread_page; } - - /* must check again c->freelist in case of cpu migration or IRQ */ freelist = c->freelist; if (freelist) goto load_freelist; @@ -2729,6 +2837,7 @@ redo: if (!freelist) { c->page = NULL; + local_unlock_irqrestore(&s->cpu_slab->lock, flags); stat(s, DEACTIVATE_BYPASS); goto new_slab; } @@ -2736,6 +2845,13 @@ redo: stat(s, ALLOC_REFILL); load_freelist: + +#ifdef CONFIG_PREEMPT_RT + lockdep_assert_held(this_cpu_ptr(&s->cpu_slab->lock.lock)); +#else + lockdep_assert_held(this_cpu_ptr(&s->cpu_slab->lock)); +#endif + /* * freelist is pointing to the list of objects to be used. * page is pointing to the page from which the objects are obtained. @@ -2744,59 +2860,141 @@ load_freelist: VM_BUG_ON(!c->page->frozen); c->freelist = get_freepointer(s, freelist); c->tid = next_tid(c->tid); + local_unlock_irqrestore(&s->cpu_slab->lock, flags); return freelist; +deactivate_slab: + + local_lock_irqsave(&s->cpu_slab->lock, flags); + if (page != c->page) { + local_unlock_irqrestore(&s->cpu_slab->lock, flags); + goto reread_page; + } + freelist = c->freelist; + c->page = NULL; + c->freelist = NULL; + local_unlock_irqrestore(&s->cpu_slab->lock, flags); + deactivate_slab(s, page, freelist); + new_slab: if (slub_percpu_partial(c)) { + local_lock_irqsave(&s->cpu_slab->lock, flags); + if (unlikely(c->page)) { + local_unlock_irqrestore(&s->cpu_slab->lock, flags); + goto reread_page; + } + if (unlikely(!slub_percpu_partial(c))) { + local_unlock_irqrestore(&s->cpu_slab->lock, flags); + /* we were preempted and partial list got empty */ + goto new_objects; + } + page = c->page = slub_percpu_partial(c); slub_set_percpu_partial(c, page); + local_unlock_irqrestore(&s->cpu_slab->lock, flags); stat(s, CPU_PARTIAL_ALLOC); goto redo; } - freelist = new_slab_objects(s, gfpflags, node, &c); +new_objects: + + freelist = get_partial(s, gfpflags, node, &page); + if (freelist) + goto check_new_page; - if (unlikely(!freelist)) { + slub_put_cpu_ptr(s->cpu_slab); + page = new_slab(s, gfpflags, node); + c = slub_get_cpu_ptr(s->cpu_slab); + + if (unlikely(!page)) { slab_out_of_memory(s, gfpflags, node); return NULL; } - page = c->page; - if (likely(!kmem_cache_debug(s) && pfmemalloc_match(page, gfpflags))) - goto load_freelist; + /* + * No other reference to the page yet so we can + * muck around with it freely without cmpxchg + */ + freelist = page->freelist; + page->freelist = NULL; - /* Only entered in the debug case */ - if (kmem_cache_debug(s) && - !alloc_debug_processing(s, page, freelist, addr)) - goto new_slab; /* Slab failed checks. Next slab needed */ + stat(s, ALLOC_SLAB); + +check_new_page: + + if (kmem_cache_debug(s)) { + if (!alloc_debug_processing(s, page, freelist, addr)) { + /* Slab failed checks. Next slab needed */ + goto new_slab; + } else { + /* + * For debug case, we don't load freelist so that all + * allocations go through alloc_debug_processing() + */ + goto return_single; + } + } + + if (unlikely(!pfmemalloc_match(page, gfpflags))) + /* + * For !pfmemalloc_match() case we don't load freelist so that + * we don't make further mismatched allocations easier. + */ + goto return_single; + +retry_load_page: + + local_lock_irqsave(&s->cpu_slab->lock, flags); + if (unlikely(c->page)) { + void *flush_freelist = c->freelist; + struct page *flush_page = c->page; + + c->page = NULL; + c->freelist = NULL; + c->tid = next_tid(c->tid); + + local_unlock_irqrestore(&s->cpu_slab->lock, flags); + + deactivate_slab(s, flush_page, flush_freelist); - deactivate_slab(s, page, get_freepointer(s, freelist), c); + stat(s, CPUSLAB_FLUSH); + + goto retry_load_page; + } + c->page = page; + + goto load_freelist; + +return_single: + + deactivate_slab(s, page, get_freepointer(s, freelist)); return freelist; } /* - * Another one that disabled interrupt and compensates for possible - * cpu changes by refetching the per cpu area pointer. + * A wrapper for ___slab_alloc() for contexts where preemption is not yet + * disabled. Compensates for possible cpu changes by refetching the per cpu area + * pointer. */ static void *__slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, unsigned long addr, struct kmem_cache_cpu *c) { void *p; - unsigned long flags; - local_irq_save(flags); -#ifdef CONFIG_PREEMPTION +#ifdef CONFIG_PREEMPT_COUNT /* * We may have been preempted and rescheduled on a different - * cpu before disabling interrupts. Need to reload cpu area + * cpu before disabling preemption. Need to reload cpu area * pointer. */ - c = this_cpu_ptr(s->cpu_slab); + c = slub_get_cpu_ptr(s->cpu_slab); #endif p = ___slab_alloc(s, gfpflags, node, addr, c); - local_irq_restore(flags); +#ifdef CONFIG_PREEMPT_COUNT + slub_put_cpu_ptr(s->cpu_slab); +#endif return p; } @@ -2847,15 +3045,14 @@ redo: * reading from one cpu area. That does not matter as long * as we end up on the original cpu again when doing the cmpxchg. * - * We should guarantee that tid and kmem_cache are retrieved on - * the same cpu. It could be different if CONFIG_PREEMPTION so we need - * to check if it is matched or not. + * We must guarantee that tid and kmem_cache_cpu are retrieved on the + * same cpu. We read first the kmem_cache_cpu pointer and use it to read + * the tid. If we are preempted and switched to another cpu between the + * two reads, it's OK as the two are still associated with the same cpu + * and cmpxchg later will validate the cpu. */ - do { - tid = this_cpu_read(s->cpu_slab->tid); - c = raw_cpu_ptr(s->cpu_slab); - } while (IS_ENABLED(CONFIG_PREEMPTION) && - unlikely(tid != READ_ONCE(c->tid))); + c = raw_cpu_ptr(s->cpu_slab); + tid = READ_ONCE(c->tid); /* * Irqless object alloc/free algorithm used here depends on sequence @@ -2876,7 +3073,15 @@ redo: object = c->freelist; page = c->page; - if (unlikely(!object || !page || !node_match(page, node))) { + /* + * We cannot use the lockless fastpath on PREEMPT_RT because if a + * slowpath has taken the local_lock_irqsave(), it is not protected + * against a fast path operation in an irq handler. So we need to take + * the slow path which uses local_lock. It is still relatively fast if + * there is a suitable cpu freelist. + */ + if (IS_ENABLED(CONFIG_PREEMPT_RT) || + unlikely(!object || !page || !node_match(page, node))) { object = __slab_alloc(s, gfpflags, node, addr, c); } else { void *next_object = get_freepointer_safe(s, object); @@ -3129,16 +3334,14 @@ redo: * data is retrieved via this pointer. If we are on the same cpu * during the cmpxchg then the free will succeed. */ - do { - tid = this_cpu_read(s->cpu_slab->tid); - c = raw_cpu_ptr(s->cpu_slab); - } while (IS_ENABLED(CONFIG_PREEMPTION) && - unlikely(tid != READ_ONCE(c->tid))); + c = raw_cpu_ptr(s->cpu_slab); + tid = READ_ONCE(c->tid); /* Same with comment on barrier() in slab_alloc_node() */ barrier(); if (likely(page == c->page)) { +#ifndef CONFIG_PREEMPT_RT void **freelist = READ_ONCE(c->freelist); set_freepointer(s, tail_obj, freelist); @@ -3151,6 +3354,32 @@ redo: note_cmpxchg_failure("slab_free", s, tid); goto redo; } +#else /* CONFIG_PREEMPT_RT */ + /* + * We cannot use the lockless fastpath on PREEMPT_RT because if + * a slowpath has taken the local_lock_irqsave(), it is not + * protected against a fast path operation in an irq handler. So + * we need to take the local_lock. We shouldn't simply defer to + * __slab_free() as that wouldn't use the cpu freelist at all. + */ + unsigned long flags; + void **freelist; + + local_lock_irqsave(&s->cpu_slab->lock, flags); + c = this_cpu_ptr(s->cpu_slab); + if (unlikely(page != c->page)) { + local_unlock_irqrestore(&s->cpu_slab->lock, flags); + goto redo; + } + tid = c->tid; + freelist = c->freelist; + + set_freepointer(s, tail_obj, freelist); + c->freelist = head; + c->tid = next_tid(tid); + + local_unlock_irqrestore(&s->cpu_slab->lock, flags); +#endif stat(s, FREE_FASTPATH); } else __slab_free(s, page, head, tail_obj, cnt, addr); @@ -3320,8 +3549,8 @@ int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size, * IRQs, which protects against PREEMPT and interrupts * handlers invoking normal fastpath. */ - local_irq_disable(); - c = this_cpu_ptr(s->cpu_slab); + c = slub_get_cpu_ptr(s->cpu_slab); + local_lock_irq(&s->cpu_slab->lock); for (i = 0; i < size; i++) { void *object = kfence_alloc(s, s->object_size, flags); @@ -3342,6 +3571,8 @@ int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size, */ c->tid = next_tid(c->tid); + local_unlock_irq(&s->cpu_slab->lock); + /* * Invoking slow path likely have side-effect * of re-populating per CPU c->freelist @@ -3354,6 +3585,8 @@ int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size, c = this_cpu_ptr(s->cpu_slab); maybe_wipe_obj_freeptr(s, p[i]); + local_lock_irq(&s->cpu_slab->lock); + continue; /* goto for-loop */ } c->freelist = get_freepointer(s, object); @@ -3361,7 +3594,8 @@ int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size, maybe_wipe_obj_freeptr(s, p[i]); } c->tid = next_tid(c->tid); - local_irq_enable(); + local_unlock_irq(&s->cpu_slab->lock); + slub_put_cpu_ptr(s->cpu_slab); /* * memcg and kmem_cache debug support and memory initialization. @@ -3371,7 +3605,7 @@ int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size, slab_want_init_on_alloc(flags, s)); return i; error: - local_irq_enable(); + local_unlock_irq(&s->cpu_slab->lock); slab_post_alloc_hook(s, objcg, flags, i, p, false); __kmem_cache_free_bulk(s, i, p); return 0; @@ -3887,9 +4121,10 @@ static void list_slab_objects(struct kmem_cache *s, struct page *page, void *addr = page_address(page); unsigned long *map; void *p; + unsigned long flags; slab_err(s, page, text, s->name); - slab_lock(page); + slab_lock(page, &flags); map = get_map(s, page); for_each_object(p, s, addr, page->objects) { @@ -3900,7 +4135,7 @@ static void list_slab_objects(struct kmem_cache *s, struct page *page, } } put_map(map); - slab_unlock(page); + slab_unlock(page, &flags); #endif } @@ -4611,33 +4846,33 @@ static int count_total(struct page *page) #endif #ifdef CONFIG_SLUB_DEBUG -static void validate_slab(struct kmem_cache *s, struct page *page) +static void validate_slab(struct kmem_cache *s, struct page *page, + unsigned long *obj_map) { void *p; void *addr = page_address(page); - unsigned long *map; + unsigned long flags; - slab_lock(page); + slab_lock(page, &flags); if (!check_slab(s, page) || !on_freelist(s, page, NULL)) goto unlock; /* Now we know that a valid freelist exists */ - map = get_map(s, page); + __fill_map(obj_map, s, page); for_each_object(p, s, addr, page->objects) { - u8 val = test_bit(__obj_to_index(s, addr, p), map) ? + u8 val = test_bit(__obj_to_index(s, addr, p), obj_map) ? SLUB_RED_INACTIVE : SLUB_RED_ACTIVE; if (!check_object(s, page, p, val)) break; } - put_map(map); unlock: - slab_unlock(page); + slab_unlock(page, &flags); } static int validate_slab_node(struct kmem_cache *s, - struct kmem_cache_node *n) + struct kmem_cache_node *n, unsigned long *obj_map) { unsigned long count = 0; struct page *page; @@ -4646,7 +4881,7 @@ static int validate_slab_node(struct kmem_cache *s, spin_lock_irqsave(&n->list_lock, flags); list_for_each_entry(page, &n->partial, slab_list) { - validate_slab(s, page); + validate_slab(s, page, obj_map); count++; } if (count != n->nr_partial) @@ -4657,7 +4892,7 @@ static int validate_slab_node(struct kmem_cache *s, goto out; list_for_each_entry(page, &n->full, slab_list) { - validate_slab(s, page); + validate_slab(s, page, obj_map); count++; } if (count != atomic_long_read(&n->nr_slabs)) @@ -4674,10 +4909,17 @@ static long validate_slab_cache(struct kmem_cache *s) int node; unsigned long count = 0; struct kmem_cache_node *n; + unsigned long *obj_map; + + obj_map = bitmap_alloc(oo_objects(s->oo), GFP_KERNEL); + if (!obj_map) + return -ENOMEM; flush_all(s); for_each_kmem_cache_node(s, node, n) - count += validate_slab_node(s, n); + count += validate_slab_node(s, n, obj_map); + + bitmap_free(obj_map); return count; } @@ -4808,17 +5050,17 @@ static int add_location(struct loc_track *t, struct kmem_cache *s, } static void process_slab(struct loc_track *t, struct kmem_cache *s, - struct page *page, enum track_item alloc) + struct page *page, enum track_item alloc, + unsigned long *obj_map) { void *addr = page_address(page); void *p; - unsigned long *map; - map = get_map(s, page); + __fill_map(obj_map, s, page); + for_each_object(p, s, addr, page->objects) - if (!test_bit(__obj_to_index(s, addr, p), map)) + if (!test_bit(__obj_to_index(s, addr, p), obj_map)) add_location(t, s, get_track(s, p, alloc)); - put_map(map); } static int list_locations(struct kmem_cache *s, char *buf, @@ -4829,13 +5071,17 @@ static int list_locations(struct kmem_cache *s, char *buf, struct loc_track t = { 0, 0, NULL }; int node; struct kmem_cache_node *n; + unsigned long *obj_map; + + obj_map = bitmap_alloc(oo_objects(s->oo), GFP_KERNEL); + if (!obj_map) + return sysfs_emit(buf, "Out of memory\n"); if (!alloc_loc_track(&t, PAGE_SIZE / sizeof(struct location), GFP_KERNEL)) { + bitmap_free(obj_map); return sysfs_emit(buf, "Out of memory\n"); } - /* Push back cpu slabs */ - flush_all(s); for_each_kmem_cache_node(s, node, n) { unsigned long flags; @@ -4846,12 +5092,14 @@ static int list_locations(struct kmem_cache *s, char *buf, spin_lock_irqsave(&n->list_lock, flags); list_for_each_entry(page, &n->partial, slab_list) - process_slab(&t, s, page, alloc); + process_slab(&t, s, page, alloc, obj_map); list_for_each_entry(page, &n->full, slab_list) - process_slab(&t, s, page, alloc); + process_slab(&t, s, page, alloc, obj_map); spin_unlock_irqrestore(&n->list_lock, flags); } + bitmap_free(obj_map); + for (i = 0; i < t.count; i++) { struct location *l = &t.loc[i]; diff --git a/mm/vmalloc.c b/mm/vmalloc.c index d0a7d89be091..62f73c4ada41 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -1829,7 +1829,7 @@ 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(); @@ -1866,11 +1866,12 @@ 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; } @@ -1935,6 +1936,7 @@ 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); @@ -1949,7 +1951,8 @@ 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; @@ -1972,7 +1975,7 @@ 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 cccee36b289c..d06332c221b1 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -31,8 +31,6 @@ #include "internal.h" -#define NUMA_STATS_THRESHOLD (U16_MAX - 2) - #ifdef CONFIG_NUMA int sysctl_vm_numa_stat = ENABLE_NUMA_STAT; @@ -41,11 +39,12 @@ static void zero_zone_numa_counters(struct zone *zone) { int item, cpu; - for (item = 0; item < NR_VM_NUMA_STAT_ITEMS; item++) { - atomic_long_set(&zone->vm_numa_stat[item], 0); - for_each_online_cpu(cpu) - per_cpu_ptr(zone->pageset, cpu)->vm_numa_stat_diff[item] + for (item = 0; item < NR_VM_NUMA_EVENT_ITEMS; item++) { + atomic_long_set(&zone->vm_numa_event[item], 0); + for_each_online_cpu(cpu) { + per_cpu_ptr(zone->per_cpu_zonestats, cpu)->vm_numa_event[item] = 0; + } } } @@ -63,8 +62,8 @@ static void zero_global_numa_counters(void) { int item; - for (item = 0; item < NR_VM_NUMA_STAT_ITEMS; item++) - atomic_long_set(&vm_numa_stat[item], 0); + for (item = 0; item < NR_VM_NUMA_EVENT_ITEMS; item++) + atomic_long_set(&vm_numa_event[item], 0); } static void invalid_numa_statistics(void) @@ -161,10 +160,9 @@ void vm_events_fold_cpu(int cpu) * vm_stat contains the global counters */ atomic_long_t vm_zone_stat[NR_VM_ZONE_STAT_ITEMS] __cacheline_aligned_in_smp; -atomic_long_t vm_numa_stat[NR_VM_NUMA_STAT_ITEMS] __cacheline_aligned_in_smp; atomic_long_t vm_node_stat[NR_VM_NODE_STAT_ITEMS] __cacheline_aligned_in_smp; +atomic_long_t vm_numa_event[NR_VM_NUMA_EVENT_ITEMS] __cacheline_aligned_in_smp; EXPORT_SYMBOL(vm_zone_stat); -EXPORT_SYMBOL(vm_numa_stat); EXPORT_SYMBOL(vm_node_stat); #ifdef CONFIG_SMP @@ -266,7 +264,7 @@ void refresh_zone_stat_thresholds(void) for_each_online_cpu(cpu) { int pgdat_threshold; - per_cpu_ptr(zone->pageset, cpu)->stat_threshold + per_cpu_ptr(zone->per_cpu_zonestats, cpu)->stat_threshold = threshold; /* Base nodestat threshold on the largest populated zone. */ @@ -303,7 +301,7 @@ void set_pgdat_percpu_threshold(pg_data_t *pgdat, threshold = (*calculate_pressure)(zone); for_each_online_cpu(cpu) - per_cpu_ptr(zone->pageset, cpu)->stat_threshold + per_cpu_ptr(zone->per_cpu_zonestats, cpu)->stat_threshold = threshold; } } @@ -316,11 +314,12 @@ void set_pgdat_percpu_threshold(pg_data_t *pgdat, void __mod_zone_page_state(struct zone *zone, enum zone_stat_item item, long delta) { - struct per_cpu_pageset __percpu *pcp = zone->pageset; + struct per_cpu_zonestat __percpu *pcp = zone->per_cpu_zonestats; s8 __percpu *p = pcp->vm_stat_diff + item; long x; long t; + preempt_disable_rt(); x = delta + __this_cpu_read(*p); t = __this_cpu_read(pcp->stat_threshold); @@ -330,6 +329,7 @@ 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 +352,7 @@ 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 +362,7 @@ 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); @@ -389,10 +391,11 @@ EXPORT_SYMBOL(__mod_node_page_state); */ void __inc_zone_state(struct zone *zone, enum zone_stat_item item) { - struct per_cpu_pageset __percpu *pcp = zone->pageset; + struct per_cpu_zonestat __percpu *pcp = zone->per_cpu_zonestats; 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 +404,7 @@ 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 +415,7 @@ 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 +424,7 @@ 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) @@ -435,10 +441,11 @@ EXPORT_SYMBOL(__inc_node_page_state); void __dec_zone_state(struct zone *zone, enum zone_stat_item item) { - struct per_cpu_pageset __percpu *pcp = zone->pageset; + struct per_cpu_zonestat __percpu *pcp = zone->per_cpu_zonestats; 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 +454,7 @@ 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 +465,7 @@ 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 +474,7 @@ 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) @@ -495,7 +505,7 @@ EXPORT_SYMBOL(__dec_node_page_state); static inline void mod_zone_state(struct zone *zone, enum zone_stat_item item, long delta, int overstep_mode) { - struct per_cpu_pageset __percpu *pcp = zone->pageset; + struct per_cpu_zonestat __percpu *pcp = zone->per_cpu_zonestats; s8 __percpu *p = pcp->vm_stat_diff + item; long o, n, t, z; @@ -706,8 +716,7 @@ EXPORT_SYMBOL(dec_node_page_state); * Fold a differential into the global counters. * Returns the number of counters updated. */ -#ifdef CONFIG_NUMA -static int fold_diff(int *zone_diff, int *numa_diff, int *node_diff) +static int fold_diff(int *zone_diff, int *node_diff) { int i; int changes = 0; @@ -718,12 +727,6 @@ static int fold_diff(int *zone_diff, int *numa_diff, int *node_diff) changes++; } - for (i = 0; i < NR_VM_NUMA_STAT_ITEMS; i++) - if (numa_diff[i]) { - atomic_long_add(numa_diff[i], &vm_numa_stat[i]); - changes++; - } - for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) if (node_diff[i]) { atomic_long_add(node_diff[i], &vm_node_stat[i]); @@ -731,26 +734,34 @@ static int fold_diff(int *zone_diff, int *numa_diff, int *node_diff) } return changes; } -#else -static int fold_diff(int *zone_diff, int *node_diff) + +#ifdef CONFIG_NUMA +static void fold_vm_zone_numa_events(struct zone *zone) { - int i; - int changes = 0; + unsigned long zone_numa_events[NR_VM_NUMA_EVENT_ITEMS] = { 0, }; + int cpu; + enum numa_stat_item item; - for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) - if (zone_diff[i]) { - atomic_long_add(zone_diff[i], &vm_zone_stat[i]); - changes++; - } + for_each_online_cpu(cpu) { + struct per_cpu_zonestat *pzstats; - for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) - if (node_diff[i]) { - atomic_long_add(node_diff[i], &vm_node_stat[i]); - changes++; + pzstats = per_cpu_ptr(zone->per_cpu_zonestats, cpu); + for (item = 0; item < NR_VM_NUMA_EVENT_ITEMS; item++) + zone_numa_events[item] += xchg(&pzstats->vm_numa_event[item], 0); } - return changes; + + for (item = 0; item < NR_VM_NUMA_EVENT_ITEMS; item++) + zone_numa_event_add(zone_numa_events[item], zone, item); +} + +void fold_vm_numa_events(void) +{ + struct zone *zone; + + for_each_populated_zone(zone) + fold_vm_zone_numa_events(zone); } -#endif /* CONFIG_NUMA */ +#endif /* * Update the zone counters for the current cpu. @@ -774,41 +785,30 @@ static int refresh_cpu_vm_stats(bool do_pagesets) struct zone *zone; int i; int global_zone_diff[NR_VM_ZONE_STAT_ITEMS] = { 0, }; -#ifdef CONFIG_NUMA - int global_numa_diff[NR_VM_NUMA_STAT_ITEMS] = { 0, }; -#endif int global_node_diff[NR_VM_NODE_STAT_ITEMS] = { 0, }; int changes = 0; for_each_populated_zone(zone) { - struct per_cpu_pageset __percpu *p = zone->pageset; + struct per_cpu_zonestat __percpu *pzstats = zone->per_cpu_zonestats; +#ifdef CONFIG_NUMA + struct per_cpu_pages __percpu *pcp = zone->per_cpu_pageset; +#endif for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) { int v; - v = this_cpu_xchg(p->vm_stat_diff[i], 0); + v = this_cpu_xchg(pzstats->vm_stat_diff[i], 0); if (v) { atomic_long_add(v, &zone->vm_stat[i]); global_zone_diff[i] += v; #ifdef CONFIG_NUMA /* 3 seconds idle till flush */ - __this_cpu_write(p->expire, 3); + __this_cpu_write(pcp->expire, 3); #endif } } #ifdef CONFIG_NUMA - for (i = 0; i < NR_VM_NUMA_STAT_ITEMS; i++) { - int v; - - v = this_cpu_xchg(p->vm_numa_stat_diff[i], 0); - if (v) { - - atomic_long_add(v, &zone->vm_numa_stat[i]); - global_numa_diff[i] += v; - __this_cpu_write(p->expire, 3); - } - } if (do_pagesets) { cond_resched(); @@ -819,23 +819,23 @@ static int refresh_cpu_vm_stats(bool do_pagesets) * Check if there are pages remaining in this pageset * if not then there is nothing to expire. */ - if (!__this_cpu_read(p->expire) || - !__this_cpu_read(p->pcp.count)) + if (!__this_cpu_read(pcp->expire) || + !__this_cpu_read(pcp->count)) continue; /* * We never drain zones local to this processor. */ if (zone_to_nid(zone) == numa_node_id()) { - __this_cpu_write(p->expire, 0); + __this_cpu_write(pcp->expire, 0); continue; } - if (__this_cpu_dec_return(p->expire)) + if (__this_cpu_dec_return(pcp->expire)) continue; - if (__this_cpu_read(p->pcp.count)) { - drain_zone_pages(zone, this_cpu_ptr(&p->pcp)); + if (__this_cpu_read(pcp->count)) { + drain_zone_pages(zone, this_cpu_ptr(pcp)); changes++; } } @@ -856,12 +856,7 @@ static int refresh_cpu_vm_stats(bool do_pagesets) } } -#ifdef CONFIG_NUMA - changes += fold_diff(global_zone_diff, global_numa_diff, - global_node_diff); -#else changes += fold_diff(global_zone_diff, global_node_diff); -#endif return changes; } @@ -876,36 +871,33 @@ void cpu_vm_stats_fold(int cpu) struct zone *zone; int i; int global_zone_diff[NR_VM_ZONE_STAT_ITEMS] = { 0, }; -#ifdef CONFIG_NUMA - int global_numa_diff[NR_VM_NUMA_STAT_ITEMS] = { 0, }; -#endif int global_node_diff[NR_VM_NODE_STAT_ITEMS] = { 0, }; for_each_populated_zone(zone) { - struct per_cpu_pageset *p; + struct per_cpu_zonestat *pzstats; - p = per_cpu_ptr(zone->pageset, cpu); + pzstats = per_cpu_ptr(zone->per_cpu_zonestats, cpu); - for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) - if (p->vm_stat_diff[i]) { + for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) { + if (pzstats->vm_stat_diff[i]) { int v; - v = p->vm_stat_diff[i]; - p->vm_stat_diff[i] = 0; + v = pzstats->vm_stat_diff[i]; + pzstats->vm_stat_diff[i] = 0; atomic_long_add(v, &zone->vm_stat[i]); global_zone_diff[i] += v; } - + } #ifdef CONFIG_NUMA - for (i = 0; i < NR_VM_NUMA_STAT_ITEMS; i++) - if (p->vm_numa_stat_diff[i]) { - int v; + for (i = 0; i < NR_VM_NUMA_EVENT_ITEMS; i++) { + if (pzstats->vm_numa_event[i]) { + unsigned long v; - v = p->vm_numa_stat_diff[i]; - p->vm_numa_stat_diff[i] = 0; - atomic_long_add(v, &zone->vm_numa_stat[i]); - global_numa_diff[i] += v; + v = pzstats->vm_numa_event[i]; + pzstats->vm_numa_event[i] = 0; + zone_numa_event_add(v, zone, i); } + } #endif } @@ -925,58 +917,39 @@ void cpu_vm_stats_fold(int cpu) } } -#ifdef CONFIG_NUMA - fold_diff(global_zone_diff, global_numa_diff, global_node_diff); -#else fold_diff(global_zone_diff, global_node_diff); -#endif } /* * this is only called if !populated_zone(zone), which implies no other users of * pset->vm_stat_diff[] exist. */ -void drain_zonestat(struct zone *zone, struct per_cpu_pageset *pset) +void drain_zonestat(struct zone *zone, struct per_cpu_zonestat *pzstats) { + unsigned long v; int i; - for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) - if (pset->vm_stat_diff[i]) { - int v = pset->vm_stat_diff[i]; - pset->vm_stat_diff[i] = 0; - atomic_long_add(v, &zone->vm_stat[i]); - atomic_long_add(v, &vm_zone_stat[i]); + for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) { + if (pzstats->vm_stat_diff[i]) { + v = pzstats->vm_stat_diff[i]; + pzstats->vm_stat_diff[i] = 0; + zone_page_state_add(v, zone, i); } + } #ifdef CONFIG_NUMA - for (i = 0; i < NR_VM_NUMA_STAT_ITEMS; i++) - if (pset->vm_numa_stat_diff[i]) { - int v = pset->vm_numa_stat_diff[i]; - - pset->vm_numa_stat_diff[i] = 0; - atomic_long_add(v, &zone->vm_numa_stat[i]); - atomic_long_add(v, &vm_numa_stat[i]); + for (i = 0; i < NR_VM_NUMA_EVENT_ITEMS; i++) { + if (pzstats->vm_numa_event[i]) { + v = pzstats->vm_numa_event[i]; + pzstats->vm_numa_event[i] = 0; + zone_numa_event_add(v, zone, i); } + } #endif } #endif #ifdef CONFIG_NUMA -void __inc_numa_state(struct zone *zone, - enum numa_stat_item item) -{ - struct per_cpu_pageset __percpu *pcp = zone->pageset; - u16 __percpu *p = pcp->vm_numa_stat_diff + item; - u16 v; - - v = __this_cpu_inc_return(*p); - - if (unlikely(v > NUMA_STATS_THRESHOLD)) { - zone_numa_state_add(v, zone, item); - __this_cpu_write(*p, 0); - } -} - /* * Determine the per node value of a stat item. This function * is called frequently in a NUMA machine, so try to be as @@ -995,19 +968,16 @@ unsigned long sum_zone_node_page_state(int node, return count; } -/* - * Determine the per node value of a numa stat item. To avoid deviation, - * the per cpu stat number in vm_numa_stat_diff[] is also included. - */ -unsigned long sum_zone_numa_state(int node, +/* Determine the per node value of a numa stat item. */ +unsigned long sum_zone_numa_event_state(int node, enum numa_stat_item item) { struct zone *zones = NODE_DATA(node)->node_zones; - int i; unsigned long count = 0; + int i; for (i = 0; i < MAX_NR_ZONES; i++) - count += zone_numa_state_snapshot(zones + i, item); + count += zone_numa_event_state(zones + i, item); return count; } @@ -1686,28 +1656,30 @@ static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat, zone_page_state(zone, i)); #ifdef CONFIG_NUMA - for (i = 0; i < NR_VM_NUMA_STAT_ITEMS; i++) + for (i = 0; i < NR_VM_NUMA_EVENT_ITEMS; i++) seq_printf(m, "\n %-12s %lu", numa_stat_name(i), - zone_numa_state_snapshot(zone, i)); + zone_numa_event_state(zone, i)); #endif seq_printf(m, "\n pagesets"); for_each_online_cpu(i) { - struct per_cpu_pageset *pageset; + struct per_cpu_pages *pcp; + struct per_cpu_zonestat __maybe_unused *pzstats; - pageset = per_cpu_ptr(zone->pageset, i); + pcp = per_cpu_ptr(zone->per_cpu_pageset, i); seq_printf(m, "\n cpu: %i" "\n count: %i" "\n high: %i" "\n batch: %i", i, - pageset->pcp.count, - pageset->pcp.high, - pageset->pcp.batch); + pcp->count, + pcp->high, + pcp->batch); #ifdef CONFIG_SMP + pzstats = per_cpu_ptr(zone->per_cpu_zonestats, i); seq_printf(m, "\n vm stats threshold: %d", - pageset->stat_threshold); + pzstats->stat_threshold); #endif } seq_printf(m, @@ -1740,7 +1712,7 @@ static const struct seq_operations zoneinfo_op = { }; #define NR_VMSTAT_ITEMS (NR_VM_ZONE_STAT_ITEMS + \ - NR_VM_NUMA_STAT_ITEMS + \ + NR_VM_NUMA_EVENT_ITEMS + \ NR_VM_NODE_STAT_ITEMS + \ NR_VM_WRITEBACK_STAT_ITEMS + \ (IS_ENABLED(CONFIG_VM_EVENT_COUNTERS) ? \ @@ -1755,6 +1727,7 @@ static void *vmstat_start(struct seq_file *m, loff_t *pos) return NULL; BUILD_BUG_ON(ARRAY_SIZE(vmstat_text) < NR_VMSTAT_ITEMS); + fold_vm_numa_events(); v = kmalloc_array(NR_VMSTAT_ITEMS, sizeof(unsigned long), GFP_KERNEL); m->private = v; if (!v) @@ -1764,9 +1737,9 @@ static void *vmstat_start(struct seq_file *m, loff_t *pos) v += NR_VM_ZONE_STAT_ITEMS; #ifdef CONFIG_NUMA - for (i = 0; i < NR_VM_NUMA_STAT_ITEMS; i++) - v[i] = global_numa_state(i); - v += NR_VM_NUMA_STAT_ITEMS; + for (i = 0; i < NR_VM_NUMA_EVENT_ITEMS; i++) + v[i] = global_numa_event_state(i); + v += NR_VM_NUMA_EVENT_ITEMS; #endif for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) { @@ -1927,19 +1900,16 @@ static bool need_update(int cpu) struct zone *zone; for_each_populated_zone(zone) { - struct per_cpu_pageset *p = per_cpu_ptr(zone->pageset, cpu); + struct per_cpu_zonestat *pzstats = per_cpu_ptr(zone->per_cpu_zonestats, cpu); struct per_cpu_nodestat *n; + /* * The fast way of checking if there are any vmstat diffs. */ - if (memchr_inv(p->vm_stat_diff, 0, NR_VM_ZONE_STAT_ITEMS * - sizeof(p->vm_stat_diff[0]))) - return true; -#ifdef CONFIG_NUMA - if (memchr_inv(p->vm_numa_stat_diff, 0, NR_VM_NUMA_STAT_ITEMS * - sizeof(p->vm_numa_stat_diff[0]))) + if (memchr_inv(pzstats->vm_stat_diff, 0, NR_VM_ZONE_STAT_ITEMS * + sizeof(pzstats->vm_stat_diff[0]))) return true; -#endif + if (last_pgdat == zone->zone_pgdat) continue; last_pgdat = zone->zone_pgdat; diff --git a/mm/workingset.c b/mm/workingset.c index b7cdeca5a76d..47bbc0a7b153 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 19b563bc6c48..4ebdb55841f0 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -57,6 +57,7 @@ #include <linux/wait.h> #include <linux/pagemap.h> #include <linux/fs.h> +#include <linux/local_lock.h> #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 (<PFN>, <obj_idx>) 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; @@ -346,9 +362,26 @@ 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) { @@ -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 c7392c449b25..d254b5143761 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -294,7 +294,7 @@ 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 04c4e236952f..acc0d4a801b1 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 } @@ -3121,6 +3121,7 @@ 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) @@ -3183,6 +3184,7 @@ 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); @@ -3867,7 +3869,11 @@ 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); @@ -4688,6 +4694,7 @@ drop: rps_unlock(sd); local_irq_restore(flags); + preempt_check_resched_rt(); atomic_long_inc(&skb->dev->rx_dropped); kfree_skb(skb); @@ -4905,7 +4912,7 @@ 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); @@ -4915,14 +4922,14 @@ 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; } @@ -4961,11 +4968,9 @@ 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; @@ -6413,12 +6418,14 @@ 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) @@ -6496,6 +6503,7 @@ 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); @@ -11303,6 +11311,7 @@ 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; @@ -11316,7 +11325,7 @@ 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); } @@ -11632,7 +11641,7 @@ 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 8e582e29a41e..e51f4854d8b2 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 e491b083b348..ef432cea2e10 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/sock.c b/net/core/sock.c index 37d732fe3fcf..f67ca9b54875 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -3073,12 +3073,11 @@ 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); @@ -3127,13 +3126,12 @@ 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 c96866a53a66..388e3ebb7f57 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 55c290d55605..9bad345cba9a 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/sched/sch_api.c b/net/sched/sch_api.c index f87d07736a14..7a627b208393 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 1ee96a5c5ee0..f7bf683c3fc9 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -578,7 +578,11 @@ 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, @@ -889,9 +893,15 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, lockdep_set_class(&sch->seqlock, 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 dbb41821b1b8..558a45c0f7cb 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -441,7 +441,7 @@ 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); @@ -465,7 +465,7 @@ 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/samples/kfifo/bytestream-example.c b/samples/kfifo/bytestream-example.c index 5a90aa527877..642d0748c169 100644 --- a/samples/kfifo/bytestream-example.c +++ b/samples/kfifo/bytestream-example.c @@ -22,10 +22,10 @@ #define PROC_FIFO "bytestream-fifo" /* lock for procfs read access */ -static DEFINE_MUTEX(read_lock); +static DEFINE_MUTEX(read_access); /* lock for procfs write access */ -static DEFINE_MUTEX(write_lock); +static DEFINE_MUTEX(write_access); /* * define DYNAMIC in this example for a dynamically allocated fifo. @@ -116,12 +116,12 @@ static ssize_t fifo_write(struct file *file, const char __user *buf, int ret; unsigned int copied; - if (mutex_lock_interruptible(&write_lock)) + if (mutex_lock_interruptible(&write_access)) return -ERESTARTSYS; ret = kfifo_from_user(&test, buf, count, &copied); - mutex_unlock(&write_lock); + mutex_unlock(&write_access); if (ret) return ret; @@ -134,12 +134,12 @@ static ssize_t fifo_read(struct file *file, char __user *buf, int ret; unsigned int copied; - if (mutex_lock_interruptible(&read_lock)) + if (mutex_lock_interruptible(&read_access)) return -ERESTARTSYS; ret = kfifo_to_user(&test, buf, count, &copied); - mutex_unlock(&read_lock); + mutex_unlock(&read_access); if (ret) return ret; diff --git a/samples/kfifo/inttype-example.c b/samples/kfifo/inttype-example.c index e5403d8c971a..c61482ba94f4 100644 --- a/samples/kfifo/inttype-example.c +++ b/samples/kfifo/inttype-example.c @@ -22,10 +22,10 @@ #define PROC_FIFO "int-fifo" /* lock for procfs read access */ -static DEFINE_MUTEX(read_lock); +static DEFINE_MUTEX(read_access); /* lock for procfs write access */ -static DEFINE_MUTEX(write_lock); +static DEFINE_MUTEX(write_access); /* * define DYNAMIC in this example for a dynamically allocated fifo. @@ -109,12 +109,12 @@ static ssize_t fifo_write(struct file *file, const char __user *buf, int ret; unsigned int copied; - if (mutex_lock_interruptible(&write_lock)) + if (mutex_lock_interruptible(&write_access)) return -ERESTARTSYS; ret = kfifo_from_user(&test, buf, count, &copied); - mutex_unlock(&write_lock); + mutex_unlock(&write_access); if (ret) return ret; @@ -127,12 +127,12 @@ static ssize_t fifo_read(struct file *file, char __user *buf, int ret; unsigned int copied; - if (mutex_lock_interruptible(&read_lock)) + if (mutex_lock_interruptible(&read_access)) return -ERESTARTSYS; ret = kfifo_to_user(&test, buf, count, &copied); - mutex_unlock(&read_lock); + mutex_unlock(&read_access); if (ret) return ret; diff --git a/samples/kfifo/record-example.c b/samples/kfifo/record-example.c index f64f3d62d6c2..e4087b2d3fc4 100644 --- a/samples/kfifo/record-example.c +++ b/samples/kfifo/record-example.c @@ -22,10 +22,10 @@ #define PROC_FIFO "record-fifo" /* lock for procfs read access */ -static DEFINE_MUTEX(read_lock); +static DEFINE_MUTEX(read_access); /* lock for procfs write access */ -static DEFINE_MUTEX(write_lock); +static DEFINE_MUTEX(write_access); /* * define DYNAMIC in this example for a dynamically allocated fifo. @@ -123,12 +123,12 @@ static ssize_t fifo_write(struct file *file, const char __user *buf, int ret; unsigned int copied; - if (mutex_lock_interruptible(&write_lock)) + if (mutex_lock_interruptible(&write_access)) return -ERESTARTSYS; ret = kfifo_from_user(&test, buf, count, &copied); - mutex_unlock(&write_lock); + mutex_unlock(&write_access); if (ret) return ret; @@ -141,12 +141,12 @@ static ssize_t fifo_read(struct file *file, char __user *buf, int ret; unsigned int copied; - if (mutex_lock_interruptible(&read_lock)) + if (mutex_lock_interruptible(&read_access)) return -ERESTARTSYS; ret = kfifo_to_user(&test, buf, count, &copied); - mutex_unlock(&read_lock); + mutex_unlock(&read_access); if (ret) return ret; |