linux/arch/arm/kernel/entry-common.S

633 lines
14 KiB
ArmAsm
Raw Normal View History

/*
* linux/arch/arm/kernel/entry-common.S
*
* Copyright (C) 2000 Russell King
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*/
#include <asm/unistd.h>
#include <asm/ftrace.h>
#include <asm/unwind.h>
#ifdef CONFIG_NEED_RET_TO_USER
#include <mach/entry-macro.S>
#else
.macro arch_ret_to_user, tmp1, tmp2
.endm
#endif
#include "entry-header.S"
.align 5
/*
* This is the fast syscall return path. We do as little as
* possible here, and this includes saving r0 back into the SVC
* stack.
*/
ret_fast_syscall:
UNWIND(.fnstart )
UNWIND(.cantunwind )
disable_irq @ disable interrupts
ldr r1, [tsk, #TI_FLAGS]
tst r1, #_TIF_WORK_MASK
bne fast_work_pending
#if defined(CONFIG_IRQSOFF_TRACER)
asm_trace_hardirqs_on
#endif
/* perform architecture specific actions before user return */
arch_ret_to_user r1, lr
restore_user_regs fast = 1, offset = S_OFF
UNWIND(.fnend )
/*
* Ok, we need to do extra processing, enter the slow path.
*/
fast_work_pending:
str r0, [sp, #S_R0+S_OFF]! @ returned r0
work_pending:
tst r1, #_TIF_NEED_RESCHED
bne work_resched
/*
* TIF_SIGPENDING or TIF_NOTIFY_RESUME must've been set if we got here
*/
ldr r2, [sp, #S_PSR]
mov r0, sp @ 'regs'
tst r2, #15 @ are we returning to user mode?
bne no_work_pending @ no? just leave, then...
mov r2, why @ 'syscall'
tst r1, #_TIF_SIGPENDING @ delivering a signal?
movne why, #0 @ prevent further restarts
bl do_notify_resume
b ret_slow_syscall @ Check work again
work_resched:
bl schedule
/*
* "slow" syscall return path. "why" tells us if this was a real syscall.
*/
ENTRY(ret_to_user)
ret_slow_syscall:
disable_irq @ disable interrupts
ARM: 6952/1: fix lockdep warning of "unannotated irqs-off" This patch fixes the lockdep warning of "unannotated irqs-off"[1]. After entering __irq_usr, arm core will disable interrupt automatically, but __irq_usr does not annotate the irq disable, so lockdep may complain the warning if it has chance to check this in irq handler. This patch adds trace_hardirqs_off in __irq_usr before entering irq_handler to handle the irq, also calls ret_to_user_from_irq to avoid calling disable_irq again. This is also a fix for irq off tracer. [1], lockdep warning log of "unannotated irqs-off" [ 13.804687] ------------[ cut here ]------------ [ 13.809570] WARNING: at kernel/lockdep.c:3335 check_flags+0x78/0x1d0() [ 13.816467] Modules linked in: [ 13.819732] Backtrace: [ 13.822357] [<c01cb42c>] (dump_backtrace+0x0/0x100) from [<c06abb14>] (dump_stack+0x20/0x24) [ 13.831268] r6:c07d8c2c r5:00000d07 r4:00000000 r3:00000000 [ 13.837280] [<c06abaf4>] (dump_stack+0x0/0x24) from [<c01ffc04>] (warn_slowpath_common+0x5c/0x74) [ 13.846649] [<c01ffba8>] (warn_slowpath_common+0x0/0x74) from [<c01ffc48>] (warn_slowpath_null+0x2c/0x34) [ 13.856781] r8:00000000 r7:00000000 r6:c18b8194 r5:60000093 r4:ef182000 [ 13.863708] r3:00000009 [ 13.866485] [<c01ffc1c>] (warn_slowpath_null+0x0/0x34) from [<c0237d84>] (check_flags+0x78/0x1d0) [ 13.875823] [<c0237d0c>] (check_flags+0x0/0x1d0) from [<c023afc8>] (lock_acquire+0x4c/0x150) [ 13.884704] [<c023af7c>] (lock_acquire+0x0/0x150) from [<c06af638>] (_raw_spin_lock+0x4c/0x84) [ 13.893798] [<c06af5ec>] (_raw_spin_lock+0x0/0x84) from [<c01f9a44>] (sched_ttwu_pending+0x58/0x8c) [ 13.903320] r6:ef92d040 r5:00000003 r4:c18b8180 [ 13.908233] [<c01f99ec>] (sched_ttwu_pending+0x0/0x8c) from [<c01f9a90>] (scheduler_ipi+0x18/0x1c) [ 13.917663] r6:ef183fb0 r5:00000003 r4:00000000 r3:00000001 [ 13.923645] [<c01f9a78>] (scheduler_ipi+0x0/0x1c) from [<c01bc458>] (do_IPI+0x9c/0xfc) [ 13.932006] [<c01bc3bc>] (do_IPI+0x0/0xfc) from [<c06b0888>] (__irq_usr+0x48/0xe0) [ 13.939971] Exception stack(0xef183fb0 to 0xef183ff8) [ 13.945281] 3fa0: ffffffc3 0001500c 00000001 0001500c [ 13.953948] 3fc0: 00000050 400b45f0 400d9000 00000000 00000001 400d9600 6474e552 bea05b3c [ 13.962585] 3fe0: 400d96c0 bea059c0 400b6574 400b65d8 20000010 ffffffff [ 13.969573] r6:00000403 r5:fa240100 r4:ffffffff r3:20000010 [ 13.975585] ---[ end trace efc4896ab0fb62cb ]--- [ 13.980468] possible reason: unannotated irqs-off. [ 13.985534] irq event stamp: 1610 [ 13.989044] hardirqs last enabled at (1610): [<c01c703c>] no_work_pending+0x8/0x2c [ 13.997131] hardirqs last disabled at (1609): [<c01c7024>] ret_slow_syscall+0xc/0x1c [ 14.005371] softirqs last enabled at (0): [<c01fe5e4>] copy_process+0x2cc/0xa24 [ 14.013183] softirqs last disabled at (0): [< (null)>] (null) Signed-off-by: Ming Lei <ming.lei@canonical.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2011-06-05 09:24:58 +08:00
ENTRY(ret_to_user_from_irq)
ldr r1, [tsk, #TI_FLAGS]
tst r1, #_TIF_WORK_MASK
bne work_pending
no_work_pending:
#if defined(CONFIG_IRQSOFF_TRACER)
asm_trace_hardirqs_on
#endif
/* perform architecture specific actions before user return */
arch_ret_to_user r1, lr
restore_user_regs fast = 0, offset = 0
ARM: 6952/1: fix lockdep warning of "unannotated irqs-off" This patch fixes the lockdep warning of "unannotated irqs-off"[1]. After entering __irq_usr, arm core will disable interrupt automatically, but __irq_usr does not annotate the irq disable, so lockdep may complain the warning if it has chance to check this in irq handler. This patch adds trace_hardirqs_off in __irq_usr before entering irq_handler to handle the irq, also calls ret_to_user_from_irq to avoid calling disable_irq again. This is also a fix for irq off tracer. [1], lockdep warning log of "unannotated irqs-off" [ 13.804687] ------------[ cut here ]------------ [ 13.809570] WARNING: at kernel/lockdep.c:3335 check_flags+0x78/0x1d0() [ 13.816467] Modules linked in: [ 13.819732] Backtrace: [ 13.822357] [<c01cb42c>] (dump_backtrace+0x0/0x100) from [<c06abb14>] (dump_stack+0x20/0x24) [ 13.831268] r6:c07d8c2c r5:00000d07 r4:00000000 r3:00000000 [ 13.837280] [<c06abaf4>] (dump_stack+0x0/0x24) from [<c01ffc04>] (warn_slowpath_common+0x5c/0x74) [ 13.846649] [<c01ffba8>] (warn_slowpath_common+0x0/0x74) from [<c01ffc48>] (warn_slowpath_null+0x2c/0x34) [ 13.856781] r8:00000000 r7:00000000 r6:c18b8194 r5:60000093 r4:ef182000 [ 13.863708] r3:00000009 [ 13.866485] [<c01ffc1c>] (warn_slowpath_null+0x0/0x34) from [<c0237d84>] (check_flags+0x78/0x1d0) [ 13.875823] [<c0237d0c>] (check_flags+0x0/0x1d0) from [<c023afc8>] (lock_acquire+0x4c/0x150) [ 13.884704] [<c023af7c>] (lock_acquire+0x0/0x150) from [<c06af638>] (_raw_spin_lock+0x4c/0x84) [ 13.893798] [<c06af5ec>] (_raw_spin_lock+0x0/0x84) from [<c01f9a44>] (sched_ttwu_pending+0x58/0x8c) [ 13.903320] r6:ef92d040 r5:00000003 r4:c18b8180 [ 13.908233] [<c01f99ec>] (sched_ttwu_pending+0x0/0x8c) from [<c01f9a90>] (scheduler_ipi+0x18/0x1c) [ 13.917663] r6:ef183fb0 r5:00000003 r4:00000000 r3:00000001 [ 13.923645] [<c01f9a78>] (scheduler_ipi+0x0/0x1c) from [<c01bc458>] (do_IPI+0x9c/0xfc) [ 13.932006] [<c01bc3bc>] (do_IPI+0x0/0xfc) from [<c06b0888>] (__irq_usr+0x48/0xe0) [ 13.939971] Exception stack(0xef183fb0 to 0xef183ff8) [ 13.945281] 3fa0: ffffffc3 0001500c 00000001 0001500c [ 13.953948] 3fc0: 00000050 400b45f0 400d9000 00000000 00000001 400d9600 6474e552 bea05b3c [ 13.962585] 3fe0: 400d96c0 bea059c0 400b6574 400b65d8 20000010 ffffffff [ 13.969573] r6:00000403 r5:fa240100 r4:ffffffff r3:20000010 [ 13.975585] ---[ end trace efc4896ab0fb62cb ]--- [ 13.980468] possible reason: unannotated irqs-off. [ 13.985534] irq event stamp: 1610 [ 13.989044] hardirqs last enabled at (1610): [<c01c703c>] no_work_pending+0x8/0x2c [ 13.997131] hardirqs last disabled at (1609): [<c01c7024>] ret_slow_syscall+0xc/0x1c [ 14.005371] softirqs last enabled at (0): [<c01fe5e4>] copy_process+0x2cc/0xa24 [ 14.013183] softirqs last disabled at (0): [< (null)>] (null) Signed-off-by: Ming Lei <ming.lei@canonical.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2011-06-05 09:24:58 +08:00
ENDPROC(ret_to_user_from_irq)
ENDPROC(ret_to_user)
/*
* This is how we return from a fork.
*/
ENTRY(ret_from_fork)
bl schedule_tail
get_thread_info tsk
ldr r1, [tsk, #TI_FLAGS] @ check for syscall tracing
mov why, #1
tst r1, #_TIF_SYSCALL_WORK @ are we tracing syscalls?
beq ret_slow_syscall
mov r1, sp
mov r0, #1 @ trace exit [IP = 1]
bl syscall_trace
b ret_slow_syscall
ENDPROC(ret_from_fork)
.equ NR_syscalls,0
#define CALL(x) .equ NR_syscalls,NR_syscalls+1
#include "calls.S"
#undef CALL
#define CALL(x) .long x
#ifdef CONFIG_FUNCTION_TRACER
/*
* When compiling with -pg, gcc inserts a call to the mcount routine at the
* start of every function. In mcount, apart from the function's address (in
* lr), we need to get hold of the function's caller's address.
*
* Older GCCs (pre-4.4) inserted a call to a routine called mcount like this:
*
* bl mcount
*
* These versions have the limitation that in order for the mcount routine to
* be able to determine the function's caller's address, an APCS-style frame
* pointer (which is set up with something like the code below) is required.
*
* mov ip, sp
* push {fp, ip, lr, pc}
* sub fp, ip, #4
*
* With EABI, these frame pointers are not available unless -mapcs-frame is
* specified, and if building as Thumb-2, not even then.
*
* Newer GCCs (4.4+) solve this problem by introducing a new version of mcount,
* with call sites like:
*
* push {lr}
* bl __gnu_mcount_nc
*
* With these compilers, frame pointers are not necessary.
*
* mcount can be thought of as a function called in the middle of a subroutine
* call. As such, it needs to be transparent for both the caller and the
* callee: the original lr needs to be restored when leaving mcount, and no
* registers should be clobbered. (In the __gnu_mcount_nc implementation, we
* clobber the ip register. This is OK because the ARM calling convention
* allows it to be clobbered in subroutines and doesn't use it to hold
* parameters.)
*
* When using dynamic ftrace, we patch out the mcount call by a "mov r0, r0"
* for the mcount case, and a "pop {lr}" for the __gnu_mcount_nc case (see
* arch/arm/kernel/ftrace.c).
*/
#ifndef CONFIG_OLD_MCOUNT
#if (__GNUC__ < 4 || (__GNUC__ == 4 && __GNUC_MINOR__ < 4))
#error Ftrace requires CONFIG_FRAME_POINTER=y with GCC older than 4.4.0.
#endif
#endif
.macro mcount_adjust_addr rd, rn
bic \rd, \rn, #1 @ clear the Thumb bit if present
sub \rd, \rd, #MCOUNT_INSN_SIZE
.endm
.macro __mcount suffix
mcount_enter
ldr r0, =ftrace_trace_function
ldr r2, [r0]
adr r0, .Lftrace_stub
cmp r0, r2
bne 1f
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
ldr r1, =ftrace_graph_return
ldr r2, [r1]
cmp r0, r2
bne ftrace_graph_caller\suffix
ldr r1, =ftrace_graph_entry
ldr r2, [r1]
ldr r0, =ftrace_graph_entry_stub
cmp r0, r2
bne ftrace_graph_caller\suffix
#endif
mcount_exit
1: mcount_get_lr r1 @ lr of instrumented func
mcount_adjust_addr r0, lr @ instrumented function
adr lr, BSYM(2f)
mov pc, r2
2: mcount_exit
.endm
.macro __ftrace_caller suffix
mcount_enter
mcount_get_lr r1 @ lr of instrumented func
mcount_adjust_addr r0, lr @ instrumented function
.globl ftrace_call\suffix
ftrace_call\suffix:
bl ftrace_stub
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
.globl ftrace_graph_call\suffix
ftrace_graph_call\suffix:
mov r0, r0
#endif
mcount_exit
.endm
.macro __ftrace_graph_caller
sub r0, fp, #4 @ &lr of instrumented routine (&parent)
#ifdef CONFIG_DYNAMIC_FTRACE
@ called from __ftrace_caller, saved in mcount_enter
ldr r1, [sp, #16] @ instrumented routine (func)
mcount_adjust_addr r1, r1
#else
@ called from __mcount, untouched in lr
mcount_adjust_addr r1, lr @ instrumented routine (func)
#endif
mov r2, fp @ frame pointer
bl prepare_ftrace_return
mcount_exit
.endm
#ifdef CONFIG_OLD_MCOUNT
/*
* mcount
*/
.macro mcount_enter
stmdb sp!, {r0-r3, lr}
.endm
.macro mcount_get_lr reg
ldr \reg, [fp, #-4]
.endm
.macro mcount_exit
ldr lr, [fp, #-4]
ldmia sp!, {r0-r3, pc}
.endm
ENTRY(mcount)
#ifdef CONFIG_DYNAMIC_FTRACE
stmdb sp!, {lr}
ldr lr, [fp, #-4]
ldmia sp!, {pc}
#else
__mcount _old
#endif
ENDPROC(mcount)
#ifdef CONFIG_DYNAMIC_FTRACE
ENTRY(ftrace_caller_old)
__ftrace_caller _old
ENDPROC(ftrace_caller_old)
#endif
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
ENTRY(ftrace_graph_caller_old)
__ftrace_graph_caller
ENDPROC(ftrace_graph_caller_old)
#endif
.purgem mcount_enter
.purgem mcount_get_lr
.purgem mcount_exit
#endif
/*
* __gnu_mcount_nc
*/
.macro mcount_enter
stmdb sp!, {r0-r3, lr}
.endm
.macro mcount_get_lr reg
ldr \reg, [sp, #20]
.endm
.macro mcount_exit
ldmia sp!, {r0-r3, ip, lr}
mov pc, ip
.endm
ENTRY(__gnu_mcount_nc)
#ifdef CONFIG_DYNAMIC_FTRACE
mov ip, lr
ldmia sp!, {lr}
mov pc, ip
#else
__mcount
#endif
ENDPROC(__gnu_mcount_nc)
#ifdef CONFIG_DYNAMIC_FTRACE
ENTRY(ftrace_caller)
__ftrace_caller
ENDPROC(ftrace_caller)
#endif
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
ENTRY(ftrace_graph_caller)
__ftrace_graph_caller
ENDPROC(ftrace_graph_caller)
#endif
.purgem mcount_enter
.purgem mcount_get_lr
.purgem mcount_exit
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
.globl return_to_handler
return_to_handler:
stmdb sp!, {r0-r3}
mov r0, fp @ frame pointer
bl ftrace_return_to_handler
mov lr, r0 @ r0 has real ret addr
ldmia sp!, {r0-r3}
mov pc, lr
#endif
ENTRY(ftrace_stub)
.Lftrace_stub:
mov pc, lr
ENDPROC(ftrace_stub)
#endif /* CONFIG_FUNCTION_TRACER */
/*=============================================================================
* SWI handler
*-----------------------------------------------------------------------------
*/
.align 5
ENTRY(vector_swi)
sub sp, sp, #S_FRAME_SIZE
stmia sp, {r0 - r12} @ Calling r0 - r12
ARM( add r8, sp, #S_PC )
ARM( stmdb r8, {sp, lr}^ ) @ Calling sp, lr
THUMB( mov r8, sp )
THUMB( store_user_sp_lr r8, r10, S_SP ) @ calling sp, lr
mrs r8, spsr @ called from non-FIQ mode, so ok.
str lr, [sp, #S_PC] @ Save calling PC
str r8, [sp, #S_PSR] @ Save CPSR
str r0, [sp, #S_OLD_R0] @ Save OLD_R0
zero_fp
/*
* Get the system call number.
*/
#if defined(CONFIG_OABI_COMPAT)
/*
* If we have CONFIG_OABI_COMPAT then we need to look at the swi
* value to determine if it is an EABI or an old ABI call.
*/
#ifdef CONFIG_ARM_THUMB
tst r8, #PSR_T_BIT
movne r10, #0 @ no thumb OABI emulation
ldreq r10, [lr, #-4] @ get SWI instruction
#else
ldr r10, [lr, #-4] @ get SWI instruction
#endif
#ifdef CONFIG_CPU_ENDIAN_BE8
rev r10, r10 @ little endian instruction
#endif
#elif defined(CONFIG_AEABI)
/*
* Pure EABI user space always put syscall number into scno (r7).
*/
#elif defined(CONFIG_ARM_THUMB)
/* Legacy ABI only, possibly thumb mode. */
tst r8, #PSR_T_BIT @ this is SPSR from save_user_regs
addne scno, r7, #__NR_SYSCALL_BASE @ put OS number in
ldreq scno, [lr, #-4]
#else
/* Legacy ABI only. */
ldr scno, [lr, #-4] @ get SWI instruction
#endif
#ifdef CONFIG_ALIGNMENT_TRAP
ldr ip, __cr_alignment
ldr ip, [ip]
mcr p15, 0, ip, c1, c0 @ update control register
#endif
enable_irq
get_thread_info tsk
adr tbl, sys_call_table @ load syscall table pointer
#if defined(CONFIG_OABI_COMPAT)
/*
* If the swi argument is zero, this is an EABI call and we do nothing.
*
* If this is an old ABI call, get the syscall number into scno and
* get the old ABI syscall table address.
*/
bics r10, r10, #0xff000000
eorne scno, r10, #__NR_OABI_SYSCALL_BASE
ldrne tbl, =sys_oabi_call_table
#elif !defined(CONFIG_AEABI)
bic scno, scno, #0xff000000 @ mask off SWI op-code
eor scno, scno, #__NR_SYSCALL_BASE @ check OS number
#endif
ldr r10, [tsk, #TI_FLAGS] @ check for syscall tracing
stmdb sp!, {r4, r5} @ push fifth and sixth args
#ifdef CONFIG_SECCOMP
tst r10, #_TIF_SECCOMP
beq 1f
mov r0, scno
bl __secure_computing
add r0, sp, #S_R0 + S_OFF @ pointer to regs
ldmia r0, {r0 - r3} @ have to reload r0 - r3
1:
#endif
tst r10, #_TIF_SYSCALL_WORK @ are we tracing syscalls?
bne __sys_trace
cmp scno, #NR_syscalls @ check upper syscall limit
adr lr, BSYM(ret_fast_syscall) @ return address
ldrcc pc, [tbl, scno, lsl #2] @ call sys_* routine
add r1, sp, #S_OFF
2: mov why, #0 @ no longer a real syscall
cmp scno, #(__ARM_NR_BASE - __NR_SYSCALL_BASE)
eor r0, scno, #__NR_SYSCALL_BASE @ put OS number back
bcs arm_syscall
b sys_ni_syscall @ not private func
ENDPROC(vector_swi)
/*
* This is the really slow path. We're going to be doing
* context switches, and waiting for our parent to respond.
*/
__sys_trace:
mov r2, scno
add r1, sp, #S_OFF
mov r0, #0 @ trace entry [IP = 0]
bl syscall_trace
adr lr, BSYM(__sys_trace_return) @ return address
mov scno, r0 @ syscall number (possibly new)
add r1, sp, #S_R0 + S_OFF @ pointer to regs
cmp scno, #NR_syscalls @ check upper syscall limit
ldmccia r1, {r0 - r3} @ have to reload r0 - r3
ldrcc pc, [tbl, scno, lsl #2] @ call sys_* routine
b 2b
__sys_trace_return:
str r0, [sp, #S_R0 + S_OFF]! @ save returned r0
mov r2, scno
mov r1, sp
mov r0, #1 @ trace exit [IP = 1]
bl syscall_trace
b ret_slow_syscall
.align 5
#ifdef CONFIG_ALIGNMENT_TRAP
.type __cr_alignment, #object
__cr_alignment:
.word cr_alignment
#endif
.ltorg
/*
* This is the syscall table declaration for native ABI syscalls.
* With EABI a couple syscalls are obsolete and defined as sys_ni_syscall.
*/
#define ABI(native, compat) native
#ifdef CONFIG_AEABI
#define OBSOLETE(syscall) sys_ni_syscall
#else
#define OBSOLETE(syscall) syscall
#endif
.type sys_call_table, #object
ENTRY(sys_call_table)
#include "calls.S"
#undef ABI
#undef OBSOLETE
/*============================================================================
* Special system call wrappers
*/
@ r0 = syscall number
@ r8 = syscall table
sys_syscall:
bic scno, r0, #__NR_OABI_SYSCALL_BASE
cmp scno, #__NR_syscall - __NR_SYSCALL_BASE
cmpne scno, #NR_syscalls @ check range
stmloia sp, {r5, r6} @ shuffle args
movlo r0, r1
movlo r1, r2
movlo r2, r3
movlo r3, r4
ldrlo pc, [tbl, scno, lsl #2]
b sys_ni_syscall
ENDPROC(sys_syscall)
sys_fork_wrapper:
add r0, sp, #S_OFF
b sys_fork
ENDPROC(sys_fork_wrapper)
sys_vfork_wrapper:
add r0, sp, #S_OFF
b sys_vfork
ENDPROC(sys_vfork_wrapper)
sys_execve_wrapper:
add r3, sp, #S_OFF
b sys_execve
ENDPROC(sys_execve_wrapper)
sys_clone_wrapper:
add ip, sp, #S_OFF
str ip, [sp, #4]
b sys_clone
ENDPROC(sys_clone_wrapper)
sys_sigreturn_wrapper:
add r0, sp, #S_OFF
arm: fix really nasty sigreturn bug If a signal hits us outside of a syscall and another gets delivered when we are in sigreturn (e.g. because it had been in sa_mask for the first one and got sent to us while we'd been in the first handler), we have a chance of returning from the second handler to location one insn prior to where we ought to return. If r0 happens to contain -513 (-ERESTARTNOINTR), sigreturn will get confused into doing restart syscall song and dance. Incredible joy to debug, since it manifests as random, infrequent and very hard to reproduce double execution of instructions in userland code... The fix is simple - mark it "don't bother with restarts" in wrapper, i.e. set r8 to 0 in sys_sigreturn and sys_rt_sigreturn wrappers, suppressing the syscall restart handling on return from these guys. They can't legitimately return a restart-worthy error anyway. Testcase: #include <unistd.h> #include <signal.h> #include <stdlib.h> #include <sys/time.h> #include <errno.h> void f(int n) { __asm__ __volatile__( "ldr r0, [%0]\n" "b 1f\n" "b 2f\n" "1:b .\n" "2:\n" : : "r"(&n)); } void handler1(int sig) { } void handler2(int sig) { raise(1); } void handler3(int sig) { exit(0); } main() { struct sigaction s = {.sa_handler = handler2}; struct itimerval t1 = { .it_value = {1} }; struct itimerval t2 = { .it_value = {2} }; signal(1, handler1); sigemptyset(&s.sa_mask); sigaddset(&s.sa_mask, 1); sigaction(SIGALRM, &s, NULL); signal(SIGVTALRM, handler3); setitimer(ITIMER_REAL, &t1, NULL); setitimer(ITIMER_VIRTUAL, &t2, NULL); f(-513); /* -ERESTARTNOINTR */ write(1, "buggered\n", 9); return 1; } Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> Acked-by: Russell King <rmk+kernel@arm.linux.org.uk> Cc: stable@kernel.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-09-17 21:34:39 +08:00
mov why, #0 @ prevent syscall restart handling
b sys_sigreturn
ENDPROC(sys_sigreturn_wrapper)
sys_rt_sigreturn_wrapper:
add r0, sp, #S_OFF
arm: fix really nasty sigreturn bug If a signal hits us outside of a syscall and another gets delivered when we are in sigreturn (e.g. because it had been in sa_mask for the first one and got sent to us while we'd been in the first handler), we have a chance of returning from the second handler to location one insn prior to where we ought to return. If r0 happens to contain -513 (-ERESTARTNOINTR), sigreturn will get confused into doing restart syscall song and dance. Incredible joy to debug, since it manifests as random, infrequent and very hard to reproduce double execution of instructions in userland code... The fix is simple - mark it "don't bother with restarts" in wrapper, i.e. set r8 to 0 in sys_sigreturn and sys_rt_sigreturn wrappers, suppressing the syscall restart handling on return from these guys. They can't legitimately return a restart-worthy error anyway. Testcase: #include <unistd.h> #include <signal.h> #include <stdlib.h> #include <sys/time.h> #include <errno.h> void f(int n) { __asm__ __volatile__( "ldr r0, [%0]\n" "b 1f\n" "b 2f\n" "1:b .\n" "2:\n" : : "r"(&n)); } void handler1(int sig) { } void handler2(int sig) { raise(1); } void handler3(int sig) { exit(0); } main() { struct sigaction s = {.sa_handler = handler2}; struct itimerval t1 = { .it_value = {1} }; struct itimerval t2 = { .it_value = {2} }; signal(1, handler1); sigemptyset(&s.sa_mask); sigaddset(&s.sa_mask, 1); sigaction(SIGALRM, &s, NULL); signal(SIGVTALRM, handler3); setitimer(ITIMER_REAL, &t1, NULL); setitimer(ITIMER_VIRTUAL, &t2, NULL); f(-513); /* -ERESTARTNOINTR */ write(1, "buggered\n", 9); return 1; } Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> Acked-by: Russell King <rmk+kernel@arm.linux.org.uk> Cc: stable@kernel.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-09-17 21:34:39 +08:00
mov why, #0 @ prevent syscall restart handling
b sys_rt_sigreturn
ENDPROC(sys_rt_sigreturn_wrapper)
sys_sigaltstack_wrapper:
ldr r2, [sp, #S_OFF + S_SP]
b do_sigaltstack
ENDPROC(sys_sigaltstack_wrapper)
sys_statfs64_wrapper:
teq r1, #88
moveq r1, #84
b sys_statfs64
ENDPROC(sys_statfs64_wrapper)
sys_fstatfs64_wrapper:
teq r1, #88
moveq r1, #84
b sys_fstatfs64
ENDPROC(sys_fstatfs64_wrapper)
/*
* Note: off_4k (r5) is always units of 4K. If we can't do the requested
* offset, we return EINVAL.
*/
sys_mmap2:
#if PAGE_SHIFT > 12
tst r5, #PGOFF_MASK
moveq r5, r5, lsr #PAGE_SHIFT - 12
streq r5, [sp, #4]
beq sys_mmap_pgoff
mov r0, #-EINVAL
mov pc, lr
#else
str r5, [sp, #4]
b sys_mmap_pgoff
#endif
ENDPROC(sys_mmap2)
#ifdef CONFIG_OABI_COMPAT
/*
* These are syscalls with argument register differences
*/
sys_oabi_pread64:
stmia sp, {r3, r4}
b sys_pread64
ENDPROC(sys_oabi_pread64)
sys_oabi_pwrite64:
stmia sp, {r3, r4}
b sys_pwrite64
ENDPROC(sys_oabi_pwrite64)
sys_oabi_truncate64:
mov r3, r2
mov r2, r1
b sys_truncate64
ENDPROC(sys_oabi_truncate64)
sys_oabi_ftruncate64:
mov r3, r2
mov r2, r1
b sys_ftruncate64
ENDPROC(sys_oabi_ftruncate64)
sys_oabi_readahead:
str r3, [sp]
mov r3, r2
mov r2, r1
b sys_readahead
ENDPROC(sys_oabi_readahead)
/*
* Let's declare a second syscall table for old ABI binaries
* using the compatibility syscall entries.
*/
#define ABI(native, compat) compat
#define OBSOLETE(syscall) syscall
.type sys_oabi_call_table, #object
ENTRY(sys_oabi_call_table)
#include "calls.S"
#undef ABI
#undef OBSOLETE
#endif