Hi Oleg,
Thanks for looking into this. Attached is the task_work.s for you.
> Fengguang, I do not think this will help, but just in case. Could you
> show the result of
>
> $ kernel/task_work.s
>
> ?
Sorry I lost some emails and found it back in LKML. Opened up too many
mutt clients..
Thanks,
Fengguang
.file "task_work.c"
# GNU C (Debian 4.6.3-1) version 4.6.3 (x86_64-linux-gnu)
# compiled by GNU C version 4.6.3, GMP version 5.0.4, MPFR version
3.1.0-p3, MPC version 0.9
# warning: GMP header version 5.0.4 differs from library version 5.0.2.
# warning: MPFR header version 3.1.0-p3 differs from library version 3.1.1-p2.
# GGC heuristics: --param ggc-min-expand=100 --param ggc-min-heapsize=131072
# options passed: -nostdinc -I /c/wfg/tip/arch/x86/include
# -I arch/x86/include/generated -I /c/wfg/tip/include -I include
# -I /c/wfg/tip/arch/x86/include/uapi -I arch/x86/include/generated/uapi
# -I /c/wfg/tip/include/uapi -I include/generated/uapi -I /c/wfg/tip/kernel
# -I kernel -imultilib 32 -imultiarch i386-linux-gnu -D __KERNEL__
# -D CONFIG_AS_CFI=1 -D CONFIG_AS_CFI_SIGNAL_FRAME=1
# -D CONFIG_AS_CFI_SECTIONS=1 -D CONFIG_AS_AVX=1 -D CONFIG_AS_AVX2=1
# -D CC_HAVE_ASM_GOTO -D KBUILD_STR(s)=#s
# -D KBUILD_BASENAME=KBUILD_STR(task_work)
# -D KBUILD_MODNAME=KBUILD_STR(task_work)
# -isystem /usr/lib/gcc/x86_64-linux-gnu/4.6/include
# -include /c/wfg/tip/include/linux/kconfig.h -MD kernel/.task_work.s.d
# /c/wfg/tip/kernel/task_work.c -m32 -msoft-float -mregparm=3
# -mpreferred-stack-boundary=2 -march=winchip2 -maccumulate-outgoing-args
# -mno-sse -mno-mmx -mno-sse2 -mno-3dnow -mno-avx
# -auxbase-strip kernel/task_work.s -O2 -Wall -Wundef -Wstrict-prototypes
# -Wno-trigraphs -Werror=implicit-function-declaration -Wno-format-security
# -Wno-sign-compare -Wframe-larger-than=1024 -Wno-unused-but-set-variable
# -Wdeclaration-after-statement -Wno-pointer-sign -p -fno-strict-aliasing
# -fno-common -fno-delete-null-pointer-checks -freg-struct-return -fno-pic
# -ffreestanding -fno-asynchronous-unwind-tables -fno-stack-protector
# -fno-omit-frame-pointer -fno-optimize-sibling-calls -fno-strict-overflow
# -fconserve-stack -fverbose-asm
# options enabled: -fauto-inc-dec -fbranch-count-reg -fcaller-saves
# -fcombine-stack-adjustments -fcompare-elim -fcprop-registers
# -fcrossjumping -fcse-follow-jumps -fdefer-pop -fdevirtualize
# -fdwarf2-cfi-asm -fearly-inlining -feliminate-unused-debug-types
# -fexpensive-optimizations -fforward-propagate -ffunction-cse -fgcse
# -fgcse-lm -fguess-branch-probability -fident -fif-conversion
# -fif-conversion2 -findirect-inlining -finline
# -finline-functions-called-once -finline-small-functions -fipa-cp
# -fipa-profile -fipa-pure-const -fipa-reference -fipa-sra
# -fira-share-save-slots -fira-share-spill-slots -fivopts
# -fkeep-static-consts -fleading-underscore -fmath-errno -fmerge-constants
# -fmerge-debug-strings -fmove-loop-invariants -foptimize-register-move
# -fpartial-inlining -fpeephole -fpeephole2 -fprefetch-loop-arrays
# -fprofile -freg-struct-return -fregmove -freorder-blocks
# -freorder-functions -frerun-cse-after-loop
# -fsched-critical-path-heuristic -fsched-dep-count-heuristic
# -fsched-group-heuristic -fsched-interblock -fsched-last-insn-heuristic
# -fsched-rank-heuristic -fsched-spec -fsched-spec-insn-heuristic
# -fsched-stalled-insns-dep -fshow-column -fsigned-zeros
# -fsplit-ivs-in-unroller -fsplit-wide-types -fstrict-volatile-bitfields
# -fthread-jumps -ftoplevel-reorder -ftrapping-math -ftree-bit-ccp
# -ftree-builtin-call-dce -ftree-ccp -ftree-ch -ftree-copy-prop
# -ftree-copyrename -ftree-cselim -ftree-dce -ftree-dominator-opts
# -ftree-dse -ftree-forwprop -ftree-fre -ftree-loop-if-convert
# -ftree-loop-im -ftree-loop-ivcanon -ftree-loop-optimize
# -ftree-parallelize-loops= -ftree-phiprop -ftree-pre -ftree-pta
# -ftree-reassoc -ftree-scev-cprop -ftree-sink -ftree-slp-vectorize
# -ftree-sra -ftree-switch-conversion -ftree-ter -ftree-vect-loop-version
# -ftree-vrp -funit-at-a-time -fvect-cost-model -fverbose-asm
# -fzero-initialized-in-bss -m32 -m96bit-long-double
# -maccumulate-outgoing-args -malign-stringops -mglibc -mieee-fp
# -mno-fancy-math-387 -mno-red-zone -mno-sse4 -mpush-args -msahf
# -mtls-direct-seg-refs
# Compiler executable checksum: aa5cb4c8e9c62c6cc9349213df314c34
.text
.p2align 4,,15
.globl task_work_add
.type task_work_add, @function
task_work_add:
pushl %ebp #
movl %esp, %ebp #,
pushl %edi #
pushl %esi #
pushl %ebx #
subl $12, %esp #,
call mcount
movl %eax, %edi # task, task
movl %edx, -16(%ebp) # work, %sfp
movb %cl, -21(%ebp) # notify, %sfp
.p2align 4,,15
.L3:
movl 904(%edi), %esi # task_3(D)->task_works, head
cmpl $work_exited, %esi #, head
sete %bl #, D.14145
andl $255, %ebx #, D.14145
xorl %ecx, %ecx #
movl %ebx, %edx # D.14145,
movl $______f.14042, %eax #,
call ftrace_likely_update #
testl %ebx, %ebx # D.14145
jne .L4 #,
movl -16(%ebp), %edx # %sfp,
movl %esi, (%edx) # head, work_13(D)->next
movl %esi, %eax # head, __ret
#APP
# 34 "/c/wfg/tip/kernel/task_work.c" 1
cmpxchgl %edx,904(%edi) #, *__ptr_16
# 0 "" 2
#NO_APP
cmpl %eax, %esi # __ret, head
jne .L3 #,
cmpb $0, -21(%ebp) #, %sfp
je .L5 #,
movl 4(%edi), %eax # task_3(D)->stack, task_3(D)->stack
#APP
# 208 "/c/wfg/tip/arch/x86/include/asm/bitops.h" 1
bts $1, 8(%eax); jc .L2 #, MEM[(volatile long unsigned int
*)D.14203_29],
# 0 "" 2
#NO_APP
.L5:
movl $0, -20(%ebp) #, %sfp
.L2:
movl -20(%ebp), %eax # %sfp,
addl $12, %esp #,
popl %ebx #
popl %esi #
popl %edi #
popl %ebp #
ret
.p2align 4,,15
.L4:
movl $-3, -20(%ebp) #, %sfp
movl -20(%ebp), %eax # %sfp,
addl $12, %esp #,
popl %ebx #
popl %esi #
popl %edi #
popl %ebp #
ret
.size task_work_add, .-task_work_add
.p2align 4,,15
.globl task_work_cancel
.type task_work_cancel, @function
task_work_cancel:
pushl %ebp #
movl %esp, %ebp #,
pushl %edi #
pushl %esi #
pushl %ebx #
pushl %ecx #
call mcount
movl %edx, %edi # func, func
leal 904(%eax), %esi #, pprev
addl $960, %eax #,
movl %eax, -16(%ebp) #, %sfp
call _raw_spin_lock_irqsave #
movl %eax, %ecx #, flags
jmp .L14 #
.p2align 4,,15
.L15:
movl %ebx, %esi # work, pprev
.L14:
movl (%esi), %ebx # MEM[(struct callback_head * volatile
*)pprev_1], work
testl %ebx, %ebx # work
je .L12 #,
cmpl %edi, 4(%ebx) # func, work_7->func
jne .L15 #,
movl (%ebx), %edx # work_7->next, __new
movl %ebx, %eax # work, __ret
#APP
# 69 "/c/wfg/tip/kernel/task_work.c" 1
cmpxchgl %edx,(%esi) # __new, MEM[(volatile u32 *)pprev_1]
# 0 "" 2
#NO_APP
cmpl %eax, %ebx # __ret, work
jne .L14 #,
.p2align 4,,15
.L12:
movl %ecx, %edx # flags,
movl -16(%ebp), %eax # %sfp,
call _raw_spin_unlock_irqrestore #
movl %ebx, %eax # work,
popl %edx #
popl %ebx #
popl %esi #
popl %edi #
popl %ebp #
ret
.size task_work_cancel, .-task_work_cancel
.section .rodata.str1.1,"aMS",@progbits,1
.LC0:
.string "/c/wfg/tip/kernel/task_work.c"
.text
.p2align 4,,15
.globl task_work_run
.type task_work_run, @function
task_work_run:
pushl %ebp #
movl %esp, %ebp #,
pushl %edi #
pushl %esi #
pushl %ebx #
call mcount
#APP
# 14 "/c/wfg/tip/arch/x86/include/asm/current.h" 1
movl current_task,%esi #, task
# 0 "" 2
#NO_APP
leal 904(%esi), %edi #, __ptr
.p2align 4,,15
.L31:
movl 904(%esi), %edx # task_39->task_works, work
testl %edx, %edx # work
je .L32 #,
.L24:
xorl %ecx, %ecx # head
.L17:
movl %edx, %eax # work, __ret
#APP
# 99 "/c/wfg/tip/kernel/task_work.c" 1
cmpxchgl %ecx,(%edi) # head, *__ptr_14
# 0 "" 2
#NO_APP
cmpl %eax, %edx # __ret, work
jne .L31 #,
testl %edx, %edx # work
je .L16 #,
.p2align 4,,15
.L28:
#APP
# 656 "/c/wfg/tip/arch/x86/include/asm/processor.h" 1
rep; nop
# 0 "" 2
#NO_APP
movl 960(%esi), %eax # task_39->pi_lock.raw_lock.slock, D.14132
testl %eax, %eax # D.14132
je .L28 #,
xorl %ebx, %ebx # head
jmp .L21 #
.p2align 4,,15
.L26:
movl %edx, %ebx # work, head
movl %eax, %edx # next, work
.L21:
movl (%edx), %eax # work_1->next, next
movl %ebx, (%edx) # head, work_1->next
testl %eax, %eax # next
jne .L26 #,
jmp .L23 #
.p2align 4,,15
.L32:
testb $4, 12(%esi) #, task_39->flags
je .L24 #,
movl $work_exited, %ecx #, head
jmp .L17 #
.p2align 4,,15
.L33:
movl %ebx, %edx # work, work
movl (%ebx), %ebx # work_5->next, work
.L23:
movl %edx, %eax # work,
call *4(%edx) # work_2->func
xorl %ecx, %ecx #
movl $125, %edx #,
movl $.LC0, %eax #,
call __might_sleep #
call _cond_resched #
testl %ebx, %ebx # work
jne .L33 #,
jmp .L31 #
.p2align 4,,15
.L16:
popl %ebx #
popl %esi #
popl %edi #
popl %ebp #
ret
.size task_work_run, .-task_work_run
.local work_exited
.comm work_exited,8,4
.section _ftrace_annotated_branch,"aw",@progbits
.align 4
.type ______f.14042, @object
.size ______f.14042, 20
______f.14042:
# func:
.long __func__.14043
# file:
.long .LC0
# line:
.long 31
.zero 8
.section .rodata
.type __func__.14043, @object
.size __func__.14043, 14
__func__.14043:
.string "task_work_add"
.ident "GCC: (Debian 4.6.3-1) 4.6.3"
.section .note.GNU-stack,"",@progbits
