From: Chris Metcalf Date: Sat, 8 Oct 2016 00:02:55 +0000 (-0700) Subject: nmi_backtrace: generate one-line reports for idle cpus X-Git-Tag: v4.1.12-107.0.20170801_2000~20 X-Git-Url: https://www.infradead.org/git/?a=commitdiff_plain;h=38eda2668a5b34149ee2ff07eba37585088656d6;p=users%2Fjedix%2Flinux-maple.git nmi_backtrace: generate one-line reports for idle cpus When doing an nmi backtrace of many cores, most of which are idle, the output is a little overwhelming and very uninformative. Suppress messages for cpus that are idling when they are interrupted and just emit one line, "NMI backtrace for N skipped: idling at pc 0xNNN". We do this by grouping all the cpuidle code together into a new .cpuidle.text section, and then checking the address of the interrupted PC to see if it lies within that section. This commit suitably tags x86 and tile idle routines, and only adds in the minimal framework for other architectures. Link: http://lkml.kernel.org/r/1472487169-14923-5-git-send-email-cmetcalf@mellanox.com Signed-off-by: Chris Metcalf Acked-by: Peter Zijlstra (Intel) Tested-by: Peter Zijlstra (Intel) Tested-by: Daniel Thompson [arm] Tested-by: Petr Mladek Cc: Aaron Tomlin Cc: Peter Zijlstra (Intel) Cc: "Rafael J. Wysocki" Cc: Russell King Cc: Thomas Gleixner Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds (cherry picked from commit 6727ad9e206cc08b80d8000a4d67f8417e53539d) Orabug: 25925689 Signed-off-by: Ethan Zhao Reviewed-by: Jack Vogel Conflicts: arch/arm/kernel/vmlinux-xip.lds.S arch/h8300/kernel/vmlinux.lds.S arch/x86/kernel/process.c drivers/acpi/processor_idle.c kernel/sched/idle.c lib/nmi_backtrace.c --- diff --git a/arch/alpha/kernel/vmlinux.lds.S b/arch/alpha/kernel/vmlinux.lds.S index 647b84c15382..cebecfb76fbf 100644 --- a/arch/alpha/kernel/vmlinux.lds.S +++ b/arch/alpha/kernel/vmlinux.lds.S @@ -22,6 +22,7 @@ SECTIONS HEAD_TEXT TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT *(.fixup) *(.gnu.warning) diff --git a/arch/arc/kernel/vmlinux.lds.S b/arch/arc/kernel/vmlinux.lds.S index dd35bde39f69..bb6d4fd4528c 100644 --- a/arch/arc/kernel/vmlinux.lds.S +++ b/arch/arc/kernel/vmlinux.lds.S @@ -97,6 +97,7 @@ SECTIONS _text = .; TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT KPROBES_TEXT *(.fixup) diff --git a/arch/arm/kernel/vmlinux-xip.lds.S b/arch/arm/kernel/vmlinux-xip.lds.S new file mode 100644 index 000000000000..7fa487ef7e2f --- /dev/null +++ b/arch/arm/kernel/vmlinux-xip.lds.S @@ -0,0 +1,317 @@ +/* ld script to make ARM Linux kernel + * taken from the i386 version by Russell King + * Written by Martin Mares + */ + +#include +#include +#include +#include +#include + +#define PROC_INFO \ + . = ALIGN(4); \ + VMLINUX_SYMBOL(__proc_info_begin) = .; \ + *(.proc.info.init) \ + VMLINUX_SYMBOL(__proc_info_end) = .; + +#define IDMAP_TEXT \ + ALIGN_FUNCTION(); \ + VMLINUX_SYMBOL(__idmap_text_start) = .; \ + *(.idmap.text) \ + VMLINUX_SYMBOL(__idmap_text_end) = .; \ + . = ALIGN(PAGE_SIZE); \ + VMLINUX_SYMBOL(__hyp_idmap_text_start) = .; \ + *(.hyp.idmap.text) \ + VMLINUX_SYMBOL(__hyp_idmap_text_end) = .; + +#ifdef CONFIG_HOTPLUG_CPU +#define ARM_CPU_DISCARD(x) +#define ARM_CPU_KEEP(x) x +#else +#define ARM_CPU_DISCARD(x) x +#define ARM_CPU_KEEP(x) +#endif + +#if (defined(CONFIG_SMP_ON_UP) && !defined(CONFIG_DEBUG_SPINLOCK)) || \ + defined(CONFIG_GENERIC_BUG) +#define ARM_EXIT_KEEP(x) x +#define ARM_EXIT_DISCARD(x) +#else +#define ARM_EXIT_KEEP(x) +#define ARM_EXIT_DISCARD(x) x +#endif + +OUTPUT_ARCH(arm) +ENTRY(stext) + +#ifndef __ARMEB__ +jiffies = jiffies_64; +#else +jiffies = jiffies_64 + 4; +#endif + +SECTIONS +{ + /* + * XXX: The linker does not define how output sections are + * assigned to input sections when there are multiple statements + * matching the same input section name. There is no documented + * order of matching. + * + * unwind exit sections must be discarded before the rest of the + * unwind sections get included. + */ + /DISCARD/ : { + *(.ARM.exidx.exit.text) + *(.ARM.extab.exit.text) + ARM_CPU_DISCARD(*(.ARM.exidx.cpuexit.text)) + ARM_CPU_DISCARD(*(.ARM.extab.cpuexit.text)) + ARM_EXIT_DISCARD(EXIT_TEXT) + ARM_EXIT_DISCARD(EXIT_DATA) + EXIT_CALL +#ifndef CONFIG_MMU + *(.text.fixup) + *(__ex_table) +#endif +#ifndef CONFIG_SMP_ON_UP + *(.alt.smp.init) +#endif + *(.discard) + *(.discard.*) + } + + . = XIP_VIRT_ADDR(CONFIG_XIP_PHYS_ADDR); + _xiprom = .; /* XIP ROM area to be mapped */ + + .head.text : { + _text = .; + HEAD_TEXT + } + + .text : { /* Real text segment */ + _stext = .; /* Text and read-only data */ + IDMAP_TEXT + __exception_text_start = .; + *(.exception.text) + __exception_text_end = .; + IRQENTRY_TEXT + TEXT_TEXT + SCHED_TEXT + CPUIDLE_TEXT + LOCK_TEXT + KPROBES_TEXT + *(.gnu.warning) + *(.glue_7) + *(.glue_7t) + . = ALIGN(4); + *(.got) /* Global offset table */ + ARM_CPU_KEEP(PROC_INFO) + } + + RO_DATA(PAGE_SIZE) + + . = ALIGN(4); + __ex_table : AT(ADDR(__ex_table) - LOAD_OFFSET) { + __start___ex_table = .; +#ifdef CONFIG_MMU + *(__ex_table) +#endif + __stop___ex_table = .; + } + +#ifdef CONFIG_ARM_UNWIND + /* + * Stack unwinding tables + */ + . = ALIGN(8); + .ARM.unwind_idx : { + __start_unwind_idx = .; + *(.ARM.exidx*) + __stop_unwind_idx = .; + } + .ARM.unwind_tab : { + __start_unwind_tab = .; + *(.ARM.extab*) + __stop_unwind_tab = .; + } +#endif + + NOTES + + _etext = .; /* End of text and rodata section */ + + /* + * The vectors and stubs are relocatable code, and the + * only thing that matters is their relative offsets + */ + __vectors_start = .; + .vectors 0xffff0000 : AT(__vectors_start) { + *(.vectors) + } + . = __vectors_start + SIZEOF(.vectors); + __vectors_end = .; + + __stubs_start = .; + .stubs ADDR(.vectors) + 0x1000 : AT(__stubs_start) { + *(.stubs) + } + . = __stubs_start + SIZEOF(.stubs); + __stubs_end = .; + + PROVIDE(vector_fiq_offset = vector_fiq - ADDR(.vectors)); + + INIT_TEXT_SECTION(8) + .exit.text : { + ARM_EXIT_KEEP(EXIT_TEXT) + } + .init.proc.info : { + ARM_CPU_DISCARD(PROC_INFO) + } + .init.arch.info : { + __arch_info_begin = .; + *(.arch.info.init) + __arch_info_end = .; + } + .init.tagtable : { + __tagtable_begin = .; + *(.taglist.init) + __tagtable_end = .; + } +#ifdef CONFIG_SMP_ON_UP + .init.smpalt : { + __smpalt_begin = .; + *(.alt.smp.init) + __smpalt_end = .; + } +#endif + .init.pv_table : { + __pv_table_begin = .; + *(.pv_table) + __pv_table_end = .; + } + .init.data : { + INIT_SETUP(16) + INIT_CALLS + CON_INITCALL + SECURITY_INITCALL + INIT_RAM_FS + } + +#ifdef CONFIG_SMP + PERCPU_SECTION(L1_CACHE_BYTES) +#endif + + _exiprom = .; /* End of XIP ROM area */ + __data_loc = ALIGN(4); /* location in binary */ + . = PAGE_OFFSET + TEXT_OFFSET; + + .data : AT(__data_loc) { + _data = .; /* address in memory */ + _sdata = .; + + /* + * first, the init task union, aligned + * to an 8192 byte boundary. + */ + INIT_TASK_DATA(THREAD_SIZE) + + . = ALIGN(PAGE_SIZE); + __init_begin = .; + INIT_DATA + ARM_EXIT_KEEP(EXIT_DATA) + . = ALIGN(PAGE_SIZE); + __init_end = .; + + NOSAVE_DATA + CACHELINE_ALIGNED_DATA(L1_CACHE_BYTES) + READ_MOSTLY_DATA(L1_CACHE_BYTES) + + /* + * and the usual data section + */ + DATA_DATA + CONSTRUCTORS + + _edata = .; + } + _edata_loc = __data_loc + SIZEOF(.data); + +#ifdef CONFIG_HAVE_TCM + /* + * We align everything to a page boundary so we can + * free it after init has commenced and TCM contents have + * been copied to its destination. + */ + .tcm_start : { + . = ALIGN(PAGE_SIZE); + __tcm_start = .; + __itcm_start = .; + } + + /* + * Link these to the ITCM RAM + * Put VMA to the TCM address and LMA to the common RAM + * and we'll upload the contents from RAM to TCM and free + * the used RAM after that. + */ + .text_itcm ITCM_OFFSET : AT(__itcm_start) + { + __sitcm_text = .; + *(.tcm.text) + *(.tcm.rodata) + . = ALIGN(4); + __eitcm_text = .; + } + + /* + * Reset the dot pointer, this is needed to create the + * relative __dtcm_start below (to be used as extern in code). + */ + . = ADDR(.tcm_start) + SIZEOF(.tcm_start) + SIZEOF(.text_itcm); + + .dtcm_start : { + __dtcm_start = .; + } + + /* TODO: add remainder of ITCM as well, that can be used for data! */ + .data_dtcm DTCM_OFFSET : AT(__dtcm_start) + { + . = ALIGN(4); + __sdtcm_data = .; + *(.tcm.data) + . = ALIGN(4); + __edtcm_data = .; + } + + /* Reset the dot pointer or the linker gets confused */ + . = ADDR(.dtcm_start) + SIZEOF(.data_dtcm); + + /* End marker for freeing TCM copy in linked object */ + .tcm_end : AT(ADDR(.dtcm_start) + SIZEOF(.data_dtcm)){ + . = ALIGN(PAGE_SIZE); + __tcm_end = .; + } +#endif + + BSS_SECTION(0, 0, 0) + _end = .; + + STABS_DEBUG +} + +/* + * These must never be empty + * If you have to comment these two assert statements out, your + * binutils is too old (for other reasons as well) + */ +ASSERT((__proc_info_end - __proc_info_begin), "missing CPU support") +ASSERT((__arch_info_end - __arch_info_begin), "no machine record defined") + +/* + * The HYP init code can't be more than a page long, + * and should not cross a page boundary. + * The above comment applies as well. + */ +ASSERT(__hyp_idmap_text_end - (__hyp_idmap_text_start & PAGE_MASK) <= PAGE_SIZE, + "HYP init code too big or misaligned") diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S index 8b60fde5ce48..6c13d570e9c9 100644 --- a/arch/arm/kernel/vmlinux.lds.S +++ b/arch/arm/kernel/vmlinux.lds.S @@ -107,6 +107,7 @@ SECTIONS IRQENTRY_TEXT TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT KPROBES_TEXT *(.gnu.warning) diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S index a2c29865c3fe..853f297b54f5 100644 --- a/arch/arm64/kernel/vmlinux.lds.S +++ b/arch/arm64/kernel/vmlinux.lds.S @@ -93,6 +93,7 @@ SECTIONS IRQENTRY_TEXT TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT HYPERVISOR_TEXT *(.fixup) diff --git a/arch/avr32/kernel/vmlinux.lds.S b/arch/avr32/kernel/vmlinux.lds.S index a4589176bed5..17f2730eb497 100644 --- a/arch/avr32/kernel/vmlinux.lds.S +++ b/arch/avr32/kernel/vmlinux.lds.S @@ -52,6 +52,7 @@ SECTIONS KPROBES_TEXT TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT *(.fixup) *(.gnu.warning) diff --git a/arch/blackfin/kernel/vmlinux.lds.S b/arch/blackfin/kernel/vmlinux.lds.S index c9eec84aa258..63a02c342830 100644 --- a/arch/blackfin/kernel/vmlinux.lds.S +++ b/arch/blackfin/kernel/vmlinux.lds.S @@ -33,6 +33,7 @@ SECTIONS #ifndef CONFIG_SCHEDULE_L1 SCHED_TEXT #endif + CPUIDLE_TEXT LOCK_TEXT IRQENTRY_TEXT KPROBES_TEXT diff --git a/arch/c6x/kernel/vmlinux.lds.S b/arch/c6x/kernel/vmlinux.lds.S index 5a6e141d1641..9cabd962ab36 100644 --- a/arch/c6x/kernel/vmlinux.lds.S +++ b/arch/c6x/kernel/vmlinux.lds.S @@ -70,6 +70,7 @@ SECTIONS _stext = .; TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT IRQENTRY_TEXT KPROBES_TEXT diff --git a/arch/cris/kernel/vmlinux.lds.S b/arch/cris/kernel/vmlinux.lds.S index a68b983dcea1..e8a8235d6e1c 100644 --- a/arch/cris/kernel/vmlinux.lds.S +++ b/arch/cris/kernel/vmlinux.lds.S @@ -42,6 +42,7 @@ SECTIONS .text : { TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT *(.fixup) *(.text.__*) diff --git a/arch/frv/kernel/vmlinux.lds.S b/arch/frv/kernel/vmlinux.lds.S index 7e958d829ec9..aa6e573d57da 100644 --- a/arch/frv/kernel/vmlinux.lds.S +++ b/arch/frv/kernel/vmlinux.lds.S @@ -63,6 +63,7 @@ SECTIONS *(.text..tlbmiss) TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT #ifdef CONFIG_DEBUG_INFO INIT_TEXT diff --git a/arch/h8300/kernel/vmlinux.lds.S b/arch/h8300/kernel/vmlinux.lds.S new file mode 100644 index 000000000000..7f11da1b895e --- /dev/null +++ b/arch/h8300/kernel/vmlinux.lds.S @@ -0,0 +1,68 @@ +#include +#include +#include + +#define ROMTOP 0x000000 +#define RAMTOP 0x400000 + +jiffies = jiffies_64 + 4; + +ENTRY(_start) + +SECTIONS +{ +#if defined(CONFIG_ROMKERNEL) + . = ROMTOP; + .vectors : + { + _vector = . ; + *(.vector*) + } +#else + . = RAMTOP; + _ramstart = .; + . = . + CONFIG_OFFSET; +#endif + _text = .; + HEAD_TEXT_SECTION + .text : { + _stext = . ; + TEXT_TEXT + SCHED_TEXT + CPUIDLE_TEXT + LOCK_TEXT +#if defined(CONFIG_ROMKERNEL) + *(.int_redirect) +#endif + _etext = . ; + } + EXCEPTION_TABLE(16) + NOTES + RO_DATA_SECTION(4) + ROMEND = .; +#if defined(CONFIG_ROMKERNEL) + . = RAMTOP; + _ramstart = .; +#define ADDR(x) ROMEND +#endif + _sdata = . ; + __data_start = . ; + RW_DATA_SECTION(0, PAGE_SIZE, THREAD_SIZE) +#if defined(CONFIG_ROMKERNEL) +#undef ADDR +#endif + . = ALIGN(0x4) ; + __init_begin = .; + INIT_TEXT_SECTION(4) + INIT_DATA_SECTION(4) + SECURITY_INIT + __init_end = .; + _edata = . ; + _begin_data = LOADADDR(.data); + _sbss =.; + BSS_SECTION(0, 0 ,0) + _ebss =.; + _ramend = .; + _end = .; + DISCARDS +} diff --git a/arch/hexagon/kernel/vmlinux.lds.S b/arch/hexagon/kernel/vmlinux.lds.S index 5f268c1071b3..ec87e67feb19 100644 --- a/arch/hexagon/kernel/vmlinux.lds.S +++ b/arch/hexagon/kernel/vmlinux.lds.S @@ -50,6 +50,7 @@ SECTIONS _text = .; TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT KPROBES_TEXT *(.fixup) diff --git a/arch/ia64/kernel/vmlinux.lds.S b/arch/ia64/kernel/vmlinux.lds.S index 84f8a52ac5ae..29c80056b2f6 100644 --- a/arch/ia64/kernel/vmlinux.lds.S +++ b/arch/ia64/kernel/vmlinux.lds.S @@ -46,6 +46,7 @@ SECTIONS { __end_ivt_text = .; TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT KPROBES_TEXT *(.gnu.linkonce.t*) diff --git a/arch/m32r/kernel/vmlinux.lds.S b/arch/m32r/kernel/vmlinux.lds.S index 018e4a711d79..ad1fe56455aa 100644 --- a/arch/m32r/kernel/vmlinux.lds.S +++ b/arch/m32r/kernel/vmlinux.lds.S @@ -31,6 +31,7 @@ SECTIONS HEAD_TEXT TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT *(.fixup) *(.gnu.warning) diff --git a/arch/m68k/kernel/vmlinux-nommu.lds b/arch/m68k/kernel/vmlinux-nommu.lds index 06a763f49fd3..d2c8abf1c8c4 100644 --- a/arch/m68k/kernel/vmlinux-nommu.lds +++ b/arch/m68k/kernel/vmlinux-nommu.lds @@ -45,6 +45,7 @@ SECTIONS { HEAD_TEXT TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT *(.fixup) . = ALIGN(16); diff --git a/arch/m68k/kernel/vmlinux-std.lds b/arch/m68k/kernel/vmlinux-std.lds index d0993594f558..5b5ce1e4d1ed 100644 --- a/arch/m68k/kernel/vmlinux-std.lds +++ b/arch/m68k/kernel/vmlinux-std.lds @@ -16,6 +16,7 @@ SECTIONS HEAD_TEXT TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT *(.fixup) *(.gnu.warning) diff --git a/arch/m68k/kernel/vmlinux-sun3.lds b/arch/m68k/kernel/vmlinux-sun3.lds index 8080469ee6c1..fe5ea1974b16 100644 --- a/arch/m68k/kernel/vmlinux-sun3.lds +++ b/arch/m68k/kernel/vmlinux-sun3.lds @@ -16,6 +16,7 @@ SECTIONS HEAD_TEXT TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT *(.fixup) *(.gnu.warning) diff --git a/arch/metag/kernel/vmlinux.lds.S b/arch/metag/kernel/vmlinux.lds.S index e12055e88bfe..9fc48354d519 100644 --- a/arch/metag/kernel/vmlinux.lds.S +++ b/arch/metag/kernel/vmlinux.lds.S @@ -21,6 +21,7 @@ SECTIONS .text : { TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT KPROBES_TEXT IRQENTRY_TEXT diff --git a/arch/microblaze/kernel/vmlinux.lds.S b/arch/microblaze/kernel/vmlinux.lds.S index be9488d69734..5913c7863067 100644 --- a/arch/microblaze/kernel/vmlinux.lds.S +++ b/arch/microblaze/kernel/vmlinux.lds.S @@ -33,6 +33,7 @@ SECTIONS { EXIT_TEXT EXIT_CALL SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT KPROBES_TEXT IRQENTRY_TEXT diff --git a/arch/mips/kernel/vmlinux.lds.S b/arch/mips/kernel/vmlinux.lds.S index 3b46f7ce9ca7..cffe97d1cf04 100644 --- a/arch/mips/kernel/vmlinux.lds.S +++ b/arch/mips/kernel/vmlinux.lds.S @@ -53,6 +53,7 @@ SECTIONS .text : { TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT KPROBES_TEXT IRQENTRY_TEXT diff --git a/arch/mn10300/kernel/vmlinux.lds.S b/arch/mn10300/kernel/vmlinux.lds.S index 13c4814c29f8..2d5f1c3f1afb 100644 --- a/arch/mn10300/kernel/vmlinux.lds.S +++ b/arch/mn10300/kernel/vmlinux.lds.S @@ -30,6 +30,7 @@ SECTIONS HEAD_TEXT TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT KPROBES_TEXT *(.fixup) diff --git a/arch/nios2/kernel/vmlinux.lds.S b/arch/nios2/kernel/vmlinux.lds.S index 326fab40a9de..340c7ab1d8b0 100644 --- a/arch/nios2/kernel/vmlinux.lds.S +++ b/arch/nios2/kernel/vmlinux.lds.S @@ -37,6 +37,7 @@ SECTIONS .text : { TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT IRQENTRY_TEXT KPROBES_TEXT diff --git a/arch/openrisc/kernel/vmlinux.lds.S b/arch/openrisc/kernel/vmlinux.lds.S index 2d69a853b742..6c3cf834b5d8 100644 --- a/arch/openrisc/kernel/vmlinux.lds.S +++ b/arch/openrisc/kernel/vmlinux.lds.S @@ -47,6 +47,7 @@ SECTIONS _stext = .; TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT KPROBES_TEXT IRQENTRY_TEXT diff --git a/arch/parisc/kernel/vmlinux.lds.S b/arch/parisc/kernel/vmlinux.lds.S index 0dacc5ca555a..1c91fc60cc07 100644 --- a/arch/parisc/kernel/vmlinux.lds.S +++ b/arch/parisc/kernel/vmlinux.lds.S @@ -69,6 +69,7 @@ SECTIONS .text ALIGN(PAGE_SIZE) : { TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT KPROBES_TEXT IRQENTRY_TEXT diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S index 1db685104ffc..ecba94a3f367 100644 --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -52,6 +52,7 @@ SECTIONS /* careful! __ftr_alt_* sections need to be close to .text */ *(.text .fixup __ftr_alt_* .ref.text) SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT KPROBES_TEXT IRQENTRY_TEXT diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S index 445657fe658c..cbc74fd4a6db 100644 --- a/arch/s390/kernel/vmlinux.lds.S +++ b/arch/s390/kernel/vmlinux.lds.S @@ -25,6 +25,7 @@ SECTIONS HEAD_TEXT TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT KPROBES_TEXT IRQENTRY_TEXT diff --git a/arch/score/kernel/vmlinux.lds.S b/arch/score/kernel/vmlinux.lds.S index 7274b5c4287e..4117890b1db1 100644 --- a/arch/score/kernel/vmlinux.lds.S +++ b/arch/score/kernel/vmlinux.lds.S @@ -40,6 +40,7 @@ SECTIONS _text = .; /* Text and read-only data */ TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT KPROBES_TEXT *(.text.*) diff --git a/arch/sh/kernel/vmlinux.lds.S b/arch/sh/kernel/vmlinux.lds.S index db88cbf9eafd..989500c17358 100644 --- a/arch/sh/kernel/vmlinux.lds.S +++ b/arch/sh/kernel/vmlinux.lds.S @@ -36,6 +36,7 @@ SECTIONS TEXT_TEXT EXTRA_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT KPROBES_TEXT IRQENTRY_TEXT diff --git a/arch/sparc/kernel/vmlinux.lds.S b/arch/sparc/kernel/vmlinux.lds.S index f0f4ea82ec78..40162cc0b4d7 100644 --- a/arch/sparc/kernel/vmlinux.lds.S +++ b/arch/sparc/kernel/vmlinux.lds.S @@ -45,6 +45,7 @@ SECTIONS HEAD_TEXT TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT KPROBES_TEXT IRQENTRY_TEXT diff --git a/arch/tile/kernel/entry.S b/arch/tile/kernel/entry.S index 3d9175992a20..4a3d930eec03 100644 --- a/arch/tile/kernel/entry.S +++ b/arch/tile/kernel/entry.S @@ -57,7 +57,7 @@ STD_ENTRY(smp_nap) * When interrupted at _cpu_idle_nap, we bump the PC forward 8, and * as a result return to the function that called _cpu_idle(). */ -STD_ENTRY(_cpu_idle) +STD_ENTRY_SECTION(_cpu_idle, .cpuidle.text) movei r1, 1 IRQ_ENABLE_LOAD(r2, r3) mtspr INTERRUPT_CRITICAL_SECTION, r1 diff --git a/arch/tile/kernel/vmlinux.lds.S b/arch/tile/kernel/vmlinux.lds.S index 0e059a0101ea..a92931e8c4f9 100644 --- a/arch/tile/kernel/vmlinux.lds.S +++ b/arch/tile/kernel/vmlinux.lds.S @@ -42,6 +42,7 @@ SECTIONS .text : AT (ADDR(.text) - LOAD_OFFSET) { HEAD_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT KPROBES_TEXT IRQENTRY_TEXT diff --git a/arch/um/kernel/dyn.lds.S b/arch/um/kernel/dyn.lds.S index adde088aeeff..4fdbcf958cd5 100644 --- a/arch/um/kernel/dyn.lds.S +++ b/arch/um/kernel/dyn.lds.S @@ -68,6 +68,7 @@ SECTIONS _stext = .; TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT *(.fixup) *(.stub .text.* .gnu.linkonce.t.*) diff --git a/arch/um/kernel/uml.lds.S b/arch/um/kernel/uml.lds.S index 6899195602b7..1840f55ed042 100644 --- a/arch/um/kernel/uml.lds.S +++ b/arch/um/kernel/uml.lds.S @@ -28,6 +28,7 @@ SECTIONS _stext = .; TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT *(.fixup) /* .gnu.warning sections are handled specially by elf32.em. */ diff --git a/arch/unicore32/kernel/vmlinux.lds.S b/arch/unicore32/kernel/vmlinux.lds.S index 77e407e49a63..56e788e8ee83 100644 --- a/arch/unicore32/kernel/vmlinux.lds.S +++ b/arch/unicore32/kernel/vmlinux.lds.S @@ -37,6 +37,7 @@ SECTIONS .text : { /* Real text segment */ TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT *(.fixup) diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h index b77f5edb03b0..ac7692dcfa2e 100644 --- a/arch/x86/include/asm/irqflags.h +++ b/arch/x86/include/asm/irqflags.h @@ -4,6 +4,10 @@ #include #ifndef __ASSEMBLY__ + +/* Provide __cpuidle; we can't safely include */ +#define __cpuidle __attribute__((__section__(".cpuidle.text"))) + /* * Interrupt control: */ @@ -44,12 +48,12 @@ static inline void native_irq_enable(void) asm volatile("sti": : :"memory"); } -static inline void native_safe_halt(void) +static inline __cpuidle void native_safe_halt(void) { asm volatile("sti; hlt": : :"memory"); } -static inline void native_halt(void) +static inline __cpuidle void native_halt(void) { asm volatile("hlt": : :"memory"); } @@ -86,7 +90,7 @@ static inline notrace void arch_local_irq_enable(void) * Used in the idle loop; sti takes one instruction cycle * to complete: */ -static inline void arch_safe_halt(void) +static inline __cpuidle void arch_safe_halt(void) { native_safe_halt(); } @@ -95,7 +99,7 @@ static inline void arch_safe_halt(void) * Used when interrupts are already enabled or to * shutdown the processor: */ -static inline void halt(void) +static inline __cpuidle void halt(void) { native_halt(); } diff --git a/arch/x86/kernel/acpi/cstate.c b/arch/x86/kernel/acpi/cstate.c index 4b28159e0421..7efbb4d19024 100644 --- a/arch/x86/kernel/acpi/cstate.c +++ b/arch/x86/kernel/acpi/cstate.c @@ -152,7 +152,7 @@ int acpi_processor_ffh_cstate_probe(unsigned int cpu, } EXPORT_SYMBOL_GPL(acpi_processor_ffh_cstate_probe); -void acpi_processor_ffh_cstate_enter(struct acpi_processor_cx *cx) +void __cpuidle acpi_processor_ffh_cstate_enter(struct acpi_processor_cx *cx) { unsigned int cpu = smp_processor_id(); struct cstate_entry *percpu_entry; diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 971743774248..57c24319fa53 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -335,7 +335,7 @@ void arch_cpu_idle(void) /* * We use this if we don't have any better idle routine.. */ -void default_idle(void) +void __cpuidle default_idle(void) { trace_cpu_idle_rcuidle(1, smp_processor_id()); safe_halt(); @@ -449,8 +449,7 @@ static int prefer_mwait_c1_over_halt(const struct cpuinfo_x86 *c) * This invokes MWAIT with interrutps enabled and no flags, * which is backwards compatible with the original MWAIT implementation. */ - -static void mwait_idle(void) +static __cpuidle void mwait_idle(void) { if (!current_set_polling_and_test()) { trace_cpu_idle_rcuidle(1, smp_processor_id()); diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index 5f08871673eb..aeb549f04bca 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -98,6 +98,7 @@ SECTIONS _stext = .; TEXT_TEXT SCHED_TEXT + CPUIDLE_TEXT LOCK_TEXT KPROBES_TEXT ENTRY_TEXT diff --git a/arch/xtensa/kernel/vmlinux.lds.S b/arch/xtensa/kernel/vmlinux.lds.S index fc1bc2ba8d5d..cfda0b425442 100644 --- a/arch/xtensa/kernel/vmlinux.lds.S +++ b/arch/xtensa/kernel/vmlinux.lds.S @@ -93,6 +93,9 @@ SECTIONS VMLINUX_SYMBOL(__sched_text_start) = .; *(.sched.literal .sched.text) VMLINUX_SYMBOL(__sched_text_end) = .; + VMLINUX_SYMBOL(__cpuidle_text_start) = .; + *(.cpuidle.literal .cpuidle.text) + VMLINUX_SYMBOL(__cpuidle_text_end) = .; VMLINUX_SYMBOL(__lock_text_start) = .; *(.spinlock.literal .spinlock.text) VMLINUX_SYMBOL(__lock_text_end) = .; diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c index 39e0c8e36244..f488026ad91c 100644 --- a/drivers/acpi/processor_idle.c +++ b/drivers/acpi/processor_idle.c @@ -35,6 +35,7 @@ #include #include #include +#include #include /* @@ -115,7 +116,7 @@ static struct dmi_system_id processor_power_dmi_table[] = { * Callers should disable interrupts before the call and enable * interrupts after return. */ -static void acpi_safe_halt(void) +static void __cpuidle acpi_safe_halt(void) { if (!tif_need_resched()) { safe_halt(); @@ -684,7 +685,7 @@ static int acpi_idle_bm_check(void) * * Caller disables interrupt before call and enables interrupt after return. */ -static void acpi_idle_do_entry(struct acpi_processor_cx *cx) +static void __cpuidle acpi_idle_do_entry(struct acpi_processor_cx *cx) { if (cx->entry_method == ACPI_CSTATE_FFH) { /* Call into architectural FFH based C-state */ diff --git a/drivers/cpuidle/driver.c b/drivers/cpuidle/driver.c index 5db147859b90..e99c8f17c0be 100644 --- a/drivers/cpuidle/driver.c +++ b/drivers/cpuidle/driver.c @@ -14,6 +14,7 @@ #include #include #include +#include #include "cpuidle.h" @@ -178,8 +179,8 @@ static void __cpuidle_driver_init(struct cpuidle_driver *drv) } #ifdef CONFIG_ARCH_HAS_CPU_RELAX -static int poll_idle(struct cpuidle_device *dev, - struct cpuidle_driver *drv, int index) +static int __cpuidle poll_idle(struct cpuidle_device *dev, + struct cpuidle_driver *drv, int index) { local_irq_enable(); if (!current_set_polling_and_test()) { diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c index 22473db328a1..85d27da83ebe 100644 --- a/drivers/idle/intel_idle.c +++ b/drivers/idle/intel_idle.c @@ -836,8 +836,8 @@ static struct cpuidle_state bxt_cstates[] = { * * Must be called under local_irq_disable(). */ -static int intel_idle(struct cpuidle_device *dev, - struct cpuidle_driver *drv, int index) +static __cpuidle int intel_idle(struct cpuidle_device *dev, + struct cpuidle_driver *drv, int index) { unsigned long ecx = 1; /* break on interrupt flag */ struct cpuidle_state *state = &drv->states[index]; diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 1839145b44a2..d11dd70b6dba 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -450,6 +450,12 @@ *(.spinlock.text) \ VMLINUX_SYMBOL(__lock_text_end) = .; +#define CPUIDLE_TEXT \ + ALIGN_FUNCTION(); \ + VMLINUX_SYMBOL(__cpuidle_text_start) = .; \ + *(.cpuidle.text) \ + VMLINUX_SYMBOL(__cpuidle_text_end) = .; + #define KPROBES_TEXT \ ALIGN_FUNCTION(); \ VMLINUX_SYMBOL(__kprobes_text_start) = .; \ diff --git a/include/linux/cpu.h b/include/linux/cpu.h index c0fb6b1b4712..d29d4c1052d4 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -275,6 +275,11 @@ void cpu_startup_entry(enum cpuhp_state state); void cpu_idle_poll_ctrl(bool enable); +/* Attach to any functions which should be considered cpuidle. */ +#define __cpuidle __attribute__((__section__(".cpuidle.text"))) + +bool cpu_in_idle(unsigned long pc); + void arch_cpu_idle(void); void arch_cpu_idle_prepare(void); void arch_cpu_idle_enter(void); diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index fefcb1fa5160..cfc504aa8d9c 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -15,6 +15,18 @@ #include "sched.h" +/* Linker adds these: start and end of __cpuidle functions */ +extern char __cpuidle_text_start[], __cpuidle_text_end[]; + +/** + * sched_idle_set_state - Record idle state for the current CPU. + * @idle_state: State to record. + */ +void sched_idle_set_state(struct cpuidle_state *idle_state) +{ + idle_set_state(this_rq(), idle_state); +} + static int __read_mostly cpu_idle_force_poll; void cpu_idle_poll_ctrl(bool enable) @@ -43,7 +55,7 @@ static int __init cpu_idle_nopoll_setup(char *__unused) __setup("hlt", cpu_idle_nopoll_setup); #endif -static inline int cpu_idle_poll(void) +static noinline int __cpuidle cpu_idle_poll(void) { rcu_idle_enter(); trace_cpu_idle_rcuidle(0, smp_processor_id()); @@ -67,6 +79,43 @@ void __weak arch_cpu_idle(void) local_irq_enable(); } +/** + * default_idle_call - Default CPU idle routine. + * + * To use when the cpuidle framework cannot be used. + */ +void __cpuidle default_idle_call(void) +{ + if (current_clr_polling_and_test()) { + local_irq_enable(); + } else { + stop_critical_timings(); + arch_cpu_idle(); + start_critical_timings(); + } +} + +static int call_cpuidle(struct cpuidle_driver *drv, struct cpuidle_device *dev, + int next_state) +{ + /* + * The idle task must be scheduled, it is pointless to go to idle, just + * update no idle residency and return. + */ + if (current_clr_polling_and_test()) { + dev->last_residency = 0; + local_irq_enable(); + return -EBUSY; + } + + /* + * Enter the idle state previously returned by the governor decision. + * This function will block until an interrupt occurs and will take + * care of re-enabling the local interrupts + */ + return cpuidle_enter(drv, dev, next_state); +} + /** * cpuidle_idle_call - the main idle function * @@ -276,6 +325,12 @@ static void cpu_idle_loop(void) } } +bool cpu_in_idle(unsigned long pc) +{ + return pc >= (unsigned long)__cpuidle_text_start && + pc < (unsigned long)__cpuidle_text_end; +} + void cpu_startup_entry(enum cpuhp_state state) { /* diff --git a/lib/nmi_backtrace.c b/lib/nmi_backtrace.c new file mode 100644 index 000000000000..75554754eadf --- /dev/null +++ b/lib/nmi_backtrace.c @@ -0,0 +1,108 @@ +/* + * NMI backtrace support + * + * Gratuitously copied from arch/x86/kernel/apic/hw_nmi.c by Russell King, + * with the following header: + * + * HW NMI watchdog support + * + * started by Don Zickus, Copyright (C) 2010 Red Hat, Inc. + * + * Arch specific calls to support NMI watchdog + * + * Bits copied from original nmi.c file + */ +#include +#include +#include +#include +#include + +#ifdef arch_trigger_cpumask_backtrace +/* For reliability, we're prepared to waste bits here. */ +static DECLARE_BITMAP(backtrace_mask, NR_CPUS) __read_mostly; + +/* "in progress" flag of arch_trigger_cpumask_backtrace */ +static unsigned long backtrace_flag; + +/* + * When raise() is called it will be passed a pointer to the + * backtrace_mask. Architectures that call nmi_cpu_backtrace() + * directly from their raise() functions may rely on the mask + * they are passed being updated as a side effect of this call. + */ +void nmi_trigger_cpumask_backtrace(const cpumask_t *mask, + bool exclude_self, + void (*raise)(cpumask_t *mask)) +{ + int i, this_cpu = get_cpu(); + + if (test_and_set_bit(0, &backtrace_flag)) { + /* + * If there is already a trigger_all_cpu_backtrace() in progress + * (backtrace_flag == 1), don't output double cpu dump infos. + */ + put_cpu(); + return; + } + + cpumask_copy(to_cpumask(backtrace_mask), mask); + if (exclude_self) + cpumask_clear_cpu(this_cpu, to_cpumask(backtrace_mask)); + + /* + * Don't try to send an NMI to this cpu; it may work on some + * architectures, but on others it may not, and we'll get + * information at least as useful just by doing a dump_stack() here. + * Note that nmi_cpu_backtrace(NULL) will clear the cpu bit. + */ + if (cpumask_test_cpu(this_cpu, to_cpumask(backtrace_mask))) + nmi_cpu_backtrace(NULL); + + if (!cpumask_empty(to_cpumask(backtrace_mask))) { + pr_info("Sending NMI from CPU %d to CPUs %*pbl:\n", + this_cpu, nr_cpumask_bits, to_cpumask(backtrace_mask)); + raise(to_cpumask(backtrace_mask)); + } + + /* Wait for up to 10 seconds for all CPUs to do the backtrace */ + for (i = 0; i < 10 * 1000; i++) { + if (cpumask_empty(to_cpumask(backtrace_mask))) + break; + mdelay(1); + touch_softlockup_watchdog(); + } + + /* + * Force flush any remote buffers that might be stuck in IRQ context + * and therefore could not run their irq_work. + */ + printk_nmi_flush(); + + clear_bit_unlock(0, &backtrace_flag); + put_cpu(); +} + +bool nmi_cpu_backtrace(struct pt_regs *regs) +{ + int cpu = smp_processor_id(); + + if (cpumask_test_cpu(cpu, to_cpumask(backtrace_mask))) { + if (regs && cpu_in_idle(instruction_pointer(regs))) { + pr_warn("NMI backtrace for cpu %d skipped: idling at pc %#lx\n", + cpu, instruction_pointer(regs)); + } else { + pr_warn("NMI backtrace for cpu %d\n", cpu); + if (regs) + show_regs(regs); + else + dump_stack(); + } + cpumask_clear_cpu(cpu, to_cpumask(backtrace_mask)); + return true; + } + + return false; +} +NOKPROBE_SYMBOL(nmi_cpu_backtrace); +#endif diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c index 03d798228a45..b4b9ba8b6e75 100644 --- a/scripts/mod/modpost.c +++ b/scripts/mod/modpost.c @@ -884,7 +884,7 @@ static void check_section(const char *modname, struct elf_info *elf, #define DATA_SECTIONS ".data", ".data.rel" #define TEXT_SECTIONS ".text", ".text.unlikely", ".sched.text", \ - ".kprobes.text" + ".kprobes.text", ".cpuidle.text" #define OTHER_TEXT_SECTIONS ".ref.text", ".head.text", ".spinlock.text", \ ".fixup", ".entry.text", ".exception.text", ".text.*" diff --git a/scripts/recordmcount.c b/scripts/recordmcount.c index 3d1984e59a30..6c1486428aa4 100644 --- a/scripts/recordmcount.c +++ b/scripts/recordmcount.c @@ -254,6 +254,7 @@ is_mcounted_section_name(char const *const txtname) strcmp(".spinlock.text", txtname) == 0 || strcmp(".irqentry.text", txtname) == 0 || strcmp(".kprobes.text", txtname) == 0 || + strcmp(".cpuidle.text", txtname) == 0 || strcmp(".text.unlikely", txtname) == 0; } diff --git a/scripts/recordmcount.pl b/scripts/recordmcount.pl index 826470d7f000..f8be31c30ee2 100755 --- a/scripts/recordmcount.pl +++ b/scripts/recordmcount.pl @@ -135,6 +135,7 @@ my %text_sections = ( ".spinlock.text" => 1, ".irqentry.text" => 1, ".kprobes.text" => 1, + ".cpuidle.text" => 1, ".text.unlikely" => 1, );