From 0a855342d92f9b1b29ba2616d4d50637087cd955 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 1 Nov 2012 11:03:47 +0100 Subject: [PATCH 239/347] x86: Support for lazy preemption Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.246-rt110.tar.xz Implement the x86 pieces for lazy preempt. Signed-off-by: Thomas Gleixner --- arch/x86/Kconfig | 1 + arch/x86/entry/common.c | 4 ++-- arch/x86/entry/entry_32.S | 17 ++++++++++++++++ arch/x86/entry/entry_64.S | 16 +++++++++++++++ arch/x86/include/asm/preempt.h | 31 +++++++++++++++++++++++++++++- arch/x86/include/asm/thread_info.h | 11 +++++++++++ arch/x86/kernel/asm-offsets.c | 2 ++ 7 files changed, 79 insertions(+), 3 deletions(-) diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 6ee7220e7f47..7299aeaa7cbb 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -180,6 +180,7 @@ config X86 select HAVE_HARDLOCKUP_DETECTOR_PERF if PERF_EVENTS && HAVE_PERF_EVENTS_NMI select HAVE_PERF_REGS select HAVE_PERF_USER_STACK_DUMP + select HAVE_PREEMPT_LAZY select HAVE_RCU_TABLE_FREE if PARAVIRT select HAVE_RCU_TABLE_INVALIDATE if HAVE_RCU_TABLE_FREE select HAVE_REGS_AND_STACK_ACCESS_API diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c index 91676b0d2d4c..3b5e41d9b29d 100644 --- a/arch/x86/entry/common.c +++ b/arch/x86/entry/common.c @@ -134,7 +134,7 @@ static long syscall_trace_enter(struct pt_regs *regs) #define EXIT_TO_USERMODE_LOOP_FLAGS \ (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_UPROBE | \ - _TIF_NEED_RESCHED | _TIF_USER_RETURN_NOTIFY | _TIF_PATCH_PENDING) + _TIF_NEED_RESCHED_MASK | _TIF_USER_RETURN_NOTIFY | _TIF_PATCH_PENDING) static void exit_to_usermode_loop(struct pt_regs *regs, u32 cached_flags) { @@ -149,7 +149,7 @@ static void exit_to_usermode_loop(struct pt_regs *regs, u32 cached_flags) /* We have work to do. */ local_irq_enable(); - if (cached_flags & _TIF_NEED_RESCHED) + if (cached_flags & _TIF_NEED_RESCHED_MASK) schedule(); #ifdef ARCH_RT_DELAYS_SIGNAL_SEND diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index 37d9016d4768..324b7539eaab 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -750,8 +750,25 @@ END(ret_from_exception) ENTRY(resume_kernel) DISABLE_INTERRUPTS(CLBR_ANY) .Lneed_resched: + # preempt count == 0 + NEED_RS set? cmpl $0, PER_CPU_VAR(__preempt_count) +#ifndef CONFIG_PREEMPT_LAZY jnz restore_all_kernel +#else + jz test_int_off + + # atleast preempt count == 0 ? + cmpl $_PREEMPT_ENABLED,PER_CPU_VAR(__preempt_count) + jne restore_all + + movl PER_CPU_VAR(current_task), %ebp + cmpl $0,TASK_TI_preempt_lazy_count(%ebp) # non-zero preempt_lazy_count ? + jnz restore_all + + testl $_TIF_NEED_RESCHED_LAZY, TASK_TI_flags(%ebp) + jz restore_all + test_int_off: +#endif testl $X86_EFLAGS_IF, PT_EFLAGS(%esp) # interrupts off (exception path) ? jz restore_all_kernel call preempt_schedule_irq diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index f53d995b1370..94fccaa04bfa 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -733,7 +733,23 @@ GLOBAL(swapgs_restore_regs_and_return_to_usermode) btl $9, EFLAGS(%rsp) /* were interrupts off? */ jnc 1f 0: cmpl $0, PER_CPU_VAR(__preempt_count) +#ifndef CONFIG_PREEMPT_LAZY jnz 1f +#else + jz do_preempt_schedule_irq + + # atleast preempt count == 0 ? + cmpl $_PREEMPT_ENABLED,PER_CPU_VAR(__preempt_count) + jnz 1f + + movq PER_CPU_VAR(current_task), %rcx + cmpl $0, TASK_TI_preempt_lazy_count(%rcx) + jnz 1f + + btl $TIF_NEED_RESCHED_LAZY,TASK_TI_flags(%rcx) + jnc 1f +do_preempt_schedule_irq: +#endif call preempt_schedule_irq jmp 0b 1: diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h index 7f2dbd91fc74..22992c837795 100644 --- a/arch/x86/include/asm/preempt.h +++ b/arch/x86/include/asm/preempt.h @@ -86,17 +86,46 @@ 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) { GEN_UNARY_RMWcc("decl", __preempt_count, __percpu_arg(0), e); } +static __always_inline bool __preempt_count_dec_and_test(void) +{ + if (____preempt_count_dec_and_test()) + return true; +#ifdef CONFIG_PREEMPT_LAZY + 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) + return false; + 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_PREEMPT diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index b5e4c357523e..d311dc042ddd 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -56,17 +56,24 @@ struct task_struct; struct thread_info { unsigned long flags; /* low level 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__ */ #include +#define GET_THREAD_INFO(reg) \ + _ASM_MOV PER_CPU_VAR(cpu_current_top_of_stack),reg ; \ + _ASM_SUB $(THREAD_SIZE),reg ; + #endif /* @@ -91,6 +98,7 @@ struct thread_info { #define TIF_NOCPUID 15 /* CPUID is not accessible in userland */ #define TIF_NOTSC 16 /* TSC is not accessible in userland */ #define TIF_IA32 17 /* IA32 compatibility process */ +#define TIF_NEED_RESCHED_LAZY 18 /* lazy rescheduling necessary */ #define TIF_NOHZ 19 /* in adaptive nohz mode */ #define TIF_MEMDIE 20 /* is terminating due to OOM killer */ #define TIF_POLLING_NRFLAG 21 /* idle is polling for TIF_NEED_RESCHED */ @@ -120,6 +128,7 @@ struct thread_info { #define _TIF_NOCPUID (1 << TIF_NOCPUID) #define _TIF_NOTSC (1 << TIF_NOTSC) #define _TIF_IA32 (1 << TIF_IA32) +#define _TIF_NEED_RESCHED_LAZY (1 << TIF_NEED_RESCHED_LAZY) #define _TIF_NOHZ (1 << TIF_NOHZ) #define _TIF_POLLING_NRFLAG (1 << TIF_POLLING_NRFLAG) #define _TIF_IO_BITMAP (1 << TIF_IO_BITMAP) @@ -165,6 +174,8 @@ struct thread_info { #define _TIF_WORK_CTXSW_PREV (_TIF_WORK_CTXSW|_TIF_USER_RETURN_NOTIFY) #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/asm-offsets.c b/arch/x86/kernel/asm-offsets.c index 01de31db300d..ce1c5b9fbd8c 100644 --- a/arch/x86/kernel/asm-offsets.c +++ b/arch/x86/kernel/asm-offsets.c @@ -38,6 +38,7 @@ void common(void) { BLANK(); OFFSET(TASK_TI_flags, task_struct, thread_info.flags); + OFFSET(TASK_TI_preempt_lazy_count, task_struct, thread_info.preempt_lazy_count); OFFSET(TASK_addr_limit, task_struct, thread.addr_limit); BLANK(); @@ -94,6 +95,7 @@ void common(void) { BLANK(); DEFINE(PTREGS_SIZE, sizeof(struct pt_regs)); + DEFINE(_PREEMPT_ENABLED, PREEMPT_ENABLED); /* TLB state for the entry code */ OFFSET(TLB_STATE_user_pcid_flush_mask, tlb_state, user_pcid_flush_mask); -- 2.36.1