linux/arch/arc
Christian Ruppert 79e5f05edc ARC: Add implicit compiler barrier to raw_local_irq* functions
ARC irqsave/restore macros were missing the compiler barrier, causing a
stale load in irq-enabled region be used in irq-safe region, despite
being changed, because the register holding the value was still live.

The problem manifested as random crashes in timer code when stress
testing ARCLinux (3.9-rc3) on a !SMP && !PREEMPT_COUNT

Here's the exact sequence which caused this:
 (0). tv1[x] <----> t1 <---> t2
 (1). mod_timer(t1) interrupted after it calls timer_pending()
 (2). mod_timer(t2) completes
 (3). mod_timer(t1) resumes but messes up the list
 (4). __runt_timers( ) uses bogus timer_list entry / crashes in
      timer->function

Essentially mod_timer() was racing against itself and while the spinlock
serialized the tv1[] timer link list, timer_pending() called outside the
spinlock, cached timer link list element in a register.
With low register pressure (and a deep register file), lack of barrier
in raw_local_irqsave() as well as preempt_disable (!PREEMPT_COUNT
version), there was nothing to force gcc to reload across the spinlock,
causing a stale value in reg be used for link list manipulation - ensuing
a corruption.

ARcompact disassembly which shows the culprit generated code:

mod_timer:
    push_s blink
    mov_s r13,r0	# timer, timer
..
    ###### timer_pending( )
    ld_s r3,[r13]       # <------ <variable>.entry.next LOADED
    brne r3, 0, @.L163

.L163:
..
    ###### spin_lock_irq( )
    lr  r5, [status32]  # flags
    bic r4, r5, 6       # temp, flags,
    and.f 0, r5, 6      # flags,
    flag.nz r4

    ###### detach_if_pending( ) begins

    tst_s r3,r3  <--------------
			# timer_pending( ) checks timer->entry.next
                        # r3 is NOT reloaded by gcc, using stale value
    beq.d @.L169
    mov.eq r0,0

    #####  detach_timer( ): __list_del( )

    ld r4,[r13,4]    	# <variable>.entry.prev, D.31439
    st r4,[r3,4]     	# <variable>.prev, D.31439
    st r3,[r4]       	# <variable>.next, D.30246

We initially tried to fix this by adding barrier() to preempt_* macros
for !PREEMPT_COUNT but Linus clarified that it was anything but wrong.
http://www.spinics.net/lists/kernel/msg1512709.html

[vgupta: updated commitlog]

Reported-by/Signed-off-by: Christian Ruppert <christian.ruppert@abilis.com>
Cc: Christian Ruppert <christian.ruppert@abilis.com>
Cc: Pierrick Hascoet <pierrick.hascoet@abilis.com>
Debugged-by/Signed-off-by: Vineet Gupta <vgupta@synopsys.com>

Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-04-08 16:10:26 -07:00
..
boot ARC: [plat-arcfpga] DT arc-uart bindings change: "baud" => "current-speed" 2013-02-15 23:16:22 +05:30
configs ARC: [plat-arcfpga] defconfig for fully loaded ARC Linux 2013-02-15 23:16:17 +05:30
include ARC: Add implicit compiler barrier to raw_local_irq* functions 2013-04-08 16:10:26 -07:00
kernel ARC: Fix the typo in event identifier flags used by ptrace 2013-03-20 18:45:45 +05:30
lib ARC: String library 2013-02-11 20:00:35 +05:30
mm ARC: Don't fiddle with non-existent caches 2013-02-15 23:16:19 +05:30
oprofile ARC: OProfile support 2013-02-15 23:16:00 +05:30
plat-arcfpga ARC: [Review] Multi-platform image #8: platform registers SMP callbacks 2013-02-15 23:16:17 +05:30
Kbuild
Kconfig ARC: Kconfig cleanup tracking cross-arch Kconfig pruning in merge window 2013-02-26 14:25:22 +05:30
Kconfig.debug
Makefile ARC: [Review] Multi-platform image #4: Isolate platform headers 2013-02-15 23:16:14 +05:30