mirror of
https://github.com/torvalds/linux.git
synced 2024-11-17 17:41:44 +00:00
26c191788f
When holding the mmap_sem for reading, pmd_offset_map_lock should only run on a pmd_t that has been read atomically from the pmdp pointer, otherwise we may read only half of it leading to this crash. PID: 11679 TASK: f06e8000 CPU: 3 COMMAND: "do_race_2_panic" #0 [f06a9dd8] crash_kexec at c049b5ec #1 [f06a9e2c] oops_end at c083d1c2 #2 [f06a9e40] no_context at c0433ded #3 [f06a9e64] bad_area_nosemaphore at c043401a #4 [f06a9e6c] __do_page_fault at c0434493 #5 [f06a9eec] do_page_fault at c083eb45 #6 [f06a9f04] error_code (via page_fault) at c083c5d5 EAX: 01fb470c EBX: fff35000 ECX: 00000003 EDX: 00000100 EBP: 00000000 DS: 007b ESI: 9e201000 ES: 007b EDI: 01fb4700 GS: 00e0 CS: 0060 EIP: c083bc14 ERR: ffffffff EFLAGS: 00010246 #7 [f06a9f38] _spin_lock at c083bc14 #8 [f06a9f44] sys_mincore at c0507b7d #9 [f06a9fb0] system_call at c083becd start len EAX: ffffffda EBX: 9e200000 ECX: 00001000 EDX: 6228537f DS: 007b ESI: 00000000 ES: 007b EDI: 003d0f00 SS: 007b ESP: 62285354 EBP: 62285388 GS: 0033 CS: 0073 EIP: 00291416 ERR: 000000da EFLAGS: 00000286 This should be a longstanding bug affecting x86 32bit PAE without THP. Only archs with 64bit large pmd_t and 32bit unsigned long should be affected. With THP enabled the barrier() in pmd_none_or_trans_huge_or_clear_bad() would partly hide the bug when the pmd transition from none to stable, by forcing a re-read of the *pmd in pmd_offset_map_lock, but when THP is enabled a new set of problem arises by the fact could then transition freely in any of the none, pmd_trans_huge or pmd_trans_stable states. So making the barrier in pmd_none_or_trans_huge_or_clear_bad() unconditional isn't good idea and it would be a flakey solution. This should be fully fixed by introducing a pmd_read_atomic that reads the pmd in order with THP disabled, or by reading the pmd atomically with cmpxchg8b with THP enabled. Luckily this new race condition only triggers in the places that must already be covered by pmd_none_or_trans_huge_or_clear_bad() so the fix is localized there but this bug is not related to THP. NOTE: this can trigger on x86 32bit systems with PAE enabled with more than 4G of ram, otherwise the high part of the pmd will never risk to be truncated because it would be zero at all times, in turn so hiding the SMP race. This bug was discovered and fully debugged by Ulrich, quote: ---- [..] pmd_none_or_trans_huge_or_clear_bad() loads the content of edx and eax. 496 static inline int pmd_none_or_trans_huge_or_clear_bad(pmd_t *pmd) 497 { 498 /* depend on compiler for an atomic pmd read */ 499 pmd_t pmdval = *pmd; // edi = pmd pointer 0xc0507a74 <sys_mincore+548>: mov 0x8(%esp),%edi ... // edx = PTE page table high address 0xc0507a84 <sys_mincore+564>: mov 0x4(%edi),%edx ... // eax = PTE page table low address 0xc0507a8e <sys_mincore+574>: mov (%edi),%eax [..] Please note that the PMD is not read atomically. These are two "mov" instructions where the high order bits of the PMD entry are fetched first. Hence, the above machine code is prone to the following race. - The PMD entry {high|low} is 0x0000000000000000. The "mov" at 0xc0507a84 loads 0x00000000 into edx. - A page fault (on another CPU) sneaks in between the two "mov" instructions and instantiates the PMD. - The PMD entry {high|low} is now 0x00000003fda38067. The "mov" at 0xc0507a8e loads 0xfda38067 into eax. ---- Reported-by: Ulrich Obergfell <uobergfe@redhat.com> Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Hugh Dickins <hughd@google.com> Cc: Larry Woodman <lwoodman@redhat.com> Cc: Petr Matousek <pmatouse@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> |
||
---|---|---|
.. | ||
bitops | ||
4level-fixup.h | ||
atomic64.h | ||
atomic-long.h | ||
atomic.h | ||
audit_change_attr.h | ||
audit_dir_write.h | ||
audit_read.h | ||
audit_signal.h | ||
audit_write.h | ||
auxvec.h | ||
barrier.h | ||
bitops.h | ||
bitsperlong.h | ||
bug.h | ||
bugs.h | ||
cache.h | ||
cacheflush.h | ||
checksum.h | ||
cmpxchg-local.h | ||
cmpxchg.h | ||
cputime.h | ||
current.h | ||
delay.h | ||
device.h | ||
div64.h | ||
dma-coherent.h | ||
dma-contiguous.h | ||
dma-mapping-broken.h | ||
dma-mapping-common.h | ||
dma.h | ||
emergency-restart.h | ||
errno-base.h | ||
errno.h | ||
exec.h | ||
fb.h | ||
fcntl.h | ||
ftrace.h | ||
futex.h | ||
getorder.h | ||
gpio.h | ||
hardirq.h | ||
hw_irq.h | ||
ide_iops.h | ||
int-l64.h | ||
int-ll64.h | ||
io-64-nonatomic-hi-lo.h | ||
io-64-nonatomic-lo-hi.h | ||
io.h | ||
ioctl.h | ||
ioctls.h | ||
iomap.h | ||
ipcbuf.h | ||
irq_regs.h | ||
irq.h | ||
irqflags.h | ||
Kbuild | ||
Kbuild.asm | ||
kdebug.h | ||
kmap_types.h | ||
kvm_para.h | ||
libata-portmap.h | ||
linkage.h | ||
local64.h | ||
local.h | ||
memory_model.h | ||
mm_hooks.h | ||
mman-common.h | ||
mman.h | ||
mmu_context.h | ||
mmu.h | ||
module.h | ||
msgbuf.h | ||
mutex-dec.h | ||
mutex-null.h | ||
mutex-xchg.h | ||
mutex.h | ||
page.h | ||
param.h | ||
parport.h | ||
pci_iomap.h | ||
pci-bridge.h | ||
pci-dma-compat.h | ||
pci.h | ||
percpu.h | ||
pgalloc.h | ||
pgtable-nopmd.h | ||
pgtable-nopud.h | ||
pgtable.h | ||
poll.h | ||
posix_types.h | ||
ptrace.h | ||
resource.h | ||
rtc.h | ||
rwsem.h | ||
scatterlist.h | ||
sections.h | ||
segment.h | ||
sembuf.h | ||
serial.h | ||
setup.h | ||
shmbuf.h | ||
shmparam.h | ||
siginfo.h | ||
signal-defs.h | ||
signal.h | ||
sizes.h | ||
socket.h | ||
sockios.h | ||
spinlock.h | ||
stat.h | ||
statfs.h | ||
string.h | ||
swab.h | ||
switch_to.h | ||
syscall.h | ||
syscalls.h | ||
termbits.h | ||
termios-base.h | ||
termios.h | ||
timex.h | ||
tlb.h | ||
tlbflush.h | ||
topology.h | ||
types.h | ||
uaccess-unaligned.h | ||
uaccess.h | ||
ucontext.h | ||
unaligned.h | ||
unistd.h | ||
user.h | ||
vga.h | ||
vmlinux.lds.h | ||
word-at-a-time.h | ||
xor.h |