398aa66827
Currently, the 32-bit and 64-bit atomic operations on ARM do not include memory constraints in the inline assembly blocks. In the case of barrier-less operations [for example, atomic_add], this means that the compiler may constant fold values which have actually been modified by a call to an atomic operation. This issue can be observed in the atomic64_test routine in <kernel root>/lib/atomic64_test.c: 00000000 <test_atomic64>: 0: e1a0c00d mov ip, sp 4: e92dd830 push {r4, r5, fp, ip, lr, pc} 8: e24cb004 sub fp, ip, #4 c: e24dd008 sub sp, sp, #8 10: e24b3014 sub r3, fp, #20 14: e30d000d movw r0, #53261 ; 0xd00d 18: e3011337 movw r1, #4919 ; 0x1337 1c: e34c0001 movt r0, #49153 ; 0xc001 20: e34a1aa3 movt r1, #43683 ; 0xaaa3 24: e16300f8 strd r0, [r3, #-8]! 28: e30c0afe movw r0, #51966 ; 0xcafe 2c: e30b1eef movw r1, #48879 ; 0xbeef 30: e34d0eaf movt r0, #57007 ; 0xdeaf 34: e34d1ead movt r1, #57005 ; 0xdead 38: e1b34f9f ldrexd r4, [r3] 3c: e1a34f90 strexd r4, r0, [r3] 40: e3340000 teq r4, #0 44: 1afffffb bne 38 <test_atomic64+0x38> 48: e59f0004 ldr r0, [pc, #4] ; 54 <test_atomic64+0x54> 4c: e3a0101e mov r1, #30 50: ebfffffe bl 0 <__bug> 54: 00000000 .word 0x00000000 The atomic64_set (0x38-0x44) writes to the atomic64_t, but the compiler doesn't see this, assumes the test condition is always false and generates an unconditional branch to __bug. The rest of the test is optimised away. This patch adds suitable memory constraints to the atomic operations on ARM to ensure that the compiler is informed of the correct data hazards. We have to use the "Qo" constraints to avoid hitting the GCC anomaly described at http://gcc.gnu.org/bugzilla/show_bug.cgi?id=44492 , where the compiler makes assumptions about the writeback in the addressing mode used by the inline assembly. These constraints forbid the use of auto{inc,dec} addressing modes, so it doesn't matter if we don't use the operand exactly once. Cc: stable@kernel.org Reviewed-by: Nicolas Pitre <nicolas.pitre@linaro.org> Signed-off-by: Will Deacon <will.deacon@arm.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk> |
||
---|---|---|
.. | ||
hardware | ||
mach | ||
a.out-core.h | ||
a.out.h | ||
asm-offsets.h | ||
assembler.h | ||
atomic.h | ||
auxvec.h | ||
bitops.h | ||
bitsperlong.h | ||
bug.h | ||
bugs.h | ||
byteorder.h | ||
cache.h | ||
cacheflush.h | ||
cachetype.h | ||
checksum.h | ||
clkdev.h | ||
cpu-multi32.h | ||
cpu-single.h | ||
cpu.h | ||
cputime.h | ||
cputype.h | ||
current.h | ||
delay.h | ||
device.h | ||
div64.h | ||
dma-mapping.h | ||
dma.h | ||
domain.h | ||
ecard.h | ||
elf.h | ||
emergency-restart.h | ||
entry-macro-vic2.S | ||
errno.h | ||
fb.h | ||
fcntl.h | ||
fiq.h | ||
fixmap.h | ||
flat.h | ||
floppy.h | ||
fpstate.h | ||
ftrace.h | ||
futex.h | ||
glue.h | ||
gpio.h | ||
hardirq.h | ||
highmem.h | ||
hw_irq.h | ||
hwcap.h | ||
ide.h | ||
io.h | ||
ioctl.h | ||
ioctls.h | ||
ipcbuf.h | ||
irq_regs.h | ||
irq.h | ||
irqflags.h | ||
Kbuild | ||
kdebug.h | ||
kexec.h | ||
kgdb.h | ||
kmap_types.h | ||
kprobes.h | ||
leds.h | ||
limits.h | ||
linkage.h | ||
local.h | ||
localtimer.h | ||
locks.h | ||
mach-types.h | ||
mc146818rtc.h | ||
memory.h | ||
mman.h | ||
mmu_context.h | ||
mmu.h | ||
mmzone.h | ||
module.h | ||
msgbuf.h | ||
mtd-xip.h | ||
mutex.h | ||
nwflash.h | ||
outercache.h | ||
page-nommu.h | ||
page.h | ||
param.h | ||
parport.h | ||
pci.h | ||
percpu.h | ||
perf_event.h | ||
pgalloc.h | ||
pgtable-hwdef.h | ||
pgtable-nommu.h | ||
pgtable.h | ||
pmu.h | ||
poll.h | ||
posix_types.h | ||
proc-fns.h | ||
processor.h | ||
procinfo.h | ||
ptrace.h | ||
resource.h | ||
scatterlist.h | ||
sections.h | ||
segment.h | ||
sembuf.h | ||
serial.h | ||
setup.h | ||
shmbuf.h | ||
shmparam.h | ||
sigcontext.h | ||
siginfo.h | ||
signal.h | ||
sizes.h | ||
smp_plat.h | ||
smp_scu.h | ||
smp_twd.h | ||
smp.h | ||
socket.h | ||
sockios.h | ||
sparsemem.h | ||
spinlock_types.h | ||
spinlock.h | ||
stacktrace.h | ||
stat.h | ||
statfs.h | ||
string.h | ||
swab.h | ||
system.h | ||
tcm.h | ||
termbits.h | ||
termios.h | ||
therm.h | ||
thread_info.h | ||
thread_notify.h | ||
timex.h | ||
tlb.h | ||
tlbflush.h | ||
topology.h | ||
traps.h | ||
types.h | ||
uaccess.h | ||
ucontext.h | ||
unaligned.h | ||
unified.h | ||
unistd.h | ||
unwind.h | ||
user.h | ||
vfp.h | ||
vfpmacros.h | ||
vga.h | ||
xor.h |