linux/arch
Steven Rostedt (Red Hat) 2b4bc78956 trace,x86: Do not call local_irq_save() in load_current_idt()
As load_current_idt() is now what is used to update the IDT for the
switches needed for NMI, lockdep debug, and for tracing, it must not
call local_irq_save(). This is because one of the users of this is
lockdep, which does tracing of local_irq_save() and when the debug
trap is hit, we need to update the IDT before tracing interrupts
being disabled. As load_current_idt() is used to do this, calling
local_irq_save() which lockdep traces, defeats the point of calling
load_current_idt().

As interrupts are already disabled when used by lockdep and NMI, the
only other user is tracing that can disable interrupts itself. Simply
have the tracing update disable interrupts before calling load_current_idt()
instead of breaking the other users.

Here's the dump that happened:

------------[ cut here ]------------
WARNING: at /work/autotest/nobackup/linux-test.git/kernel/fork.c:1196 copy_process+0x2c3/0x1398()
DEBUG_LOCKS_WARN_ON(!p->hardirqs_enabled)
Modules linked in:
CPU: 1 PID: 4570 Comm: gdm-simple-gree Not tainted 3.10.0-rc3-test+ #5
Hardware name:                  /DG965MQ, BIOS MQ96510J.86A.0372.2006.0605.1717 06/05/2006
 ffffffff81d2a7a5 ffff88006ed13d50 ffffffff8192822b ffff88006ed13d90
 ffffffff81035f25 ffff8800721c6000 ffff88006ed13da0 0000000001200011
 0000000000000000 ffff88006ed5e000 ffff8800721c6000 ffff88006ed13df0
Call Trace:
 [<ffffffff8192822b>] dump_stack+0x19/0x1b
 [<ffffffff81035f25>] warn_slowpath_common+0x67/0x80
 [<ffffffff81035fe1>] warn_slowpath_fmt+0x46/0x48
 [<ffffffff812bfc5d>] ? __raw_spin_lock_init+0x31/0x52
 [<ffffffff810341f7>] copy_process+0x2c3/0x1398
 [<ffffffff8103539d>] do_fork+0xa8/0x260
 [<ffffffff810ca7b1>] ? trace_preempt_on+0x2a/0x2f
 [<ffffffff812afb3e>] ? trace_hardirqs_on_thunk+0x3a/0x3f
 [<ffffffff81937fe7>] ? sysret_check+0x1b/0x56
 [<ffffffff81937fe7>] ? sysret_check+0x1b/0x56
 [<ffffffff810355cf>] SyS_clone+0x16/0x18
 [<ffffffff81938369>] stub_clone+0x69/0x90
 [<ffffffff81937fc2>] ? system_call_fastpath+0x16/0x1b
---[ end trace 8b157a9d20ca1aa2 ]---

in fork.c:

 #ifdef CONFIG_PROVE_LOCKING
	DEBUG_LOCKS_WARN_ON(!p->hardirqs_enabled); <-- bug here
	DEBUG_LOCKS_WARN_ON(!p->softirqs_enabled);
 #endif

Cc: Seiji Aguchi <seiji.aguchi@hds.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2013-06-22 13:16:19 -04:00
..
alpha Removal of GENERIC_GPIO for v3.10 2013-05-09 09:59:16 -07:00
arc ARC: lazy dcache flush broke gdb in non-aliasing configs 2013-05-25 14:15:55 +05:30
arm ARM: SoC fixes for 3.10-rc 2013-06-15 11:49:48 -10:00
arm64 arm64: don't kill the kernel on a bad esr from el0 2013-05-31 16:04:51 +01:00
avr32 Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/egtvedt/linux-avr32 2013-05-22 18:06:57 -07:00
blackfin blackfin updates for Linux 3.10 2013-05-10 07:21:16 -07:00
c6x dump_stack: unify debug information printed by show_regs() 2013-04-30 17:04:02 -07:00
cris - Lots of cleanups from Artem, including deletion of some obsolete drivers 2013-05-09 10:15:46 -07:00
frv Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next 2013-05-01 14:08:52 -07:00
h8300 We get rid of the general module prefix confusion with a binary config option, 2013-05-05 10:58:06 -07:00
hexagon Removal of GENERIC_GPIO for v3.10 2013-05-09 09:59:16 -07:00
ia64 arch, mm: Remove tlb_fast_mode() 2013-06-06 10:07:26 +09:00
m32r Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next 2013-05-01 14:08:52 -07:00
m68k Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/gerg/m68knommu 2013-06-08 11:50:17 -07:00
metag Removal of GENERIC_GPIO for v3.10 2013-05-09 09:59:16 -07:00
microblaze microblaze: Use static inline functions in cacheflush.h 2013-06-03 11:33:23 +02:00
mips Merge branch 'upstream' of git://git.linux-mips.org/pub/scm/ralf/upstream-linus 2013-06-12 11:48:14 -07:00
mn10300 MN10300: Need pci_iomap() and __pci_ioport_map() defining 2013-05-30 13:38:48 +09:00
openrisc Removal of GENERIC_GPIO for v3.10 2013-05-09 09:59:16 -07:00
parisc parisc: kernel: using strlcpy() instead of strcpy() 2013-06-01 14:29:01 +02:00
powerpc Merge branch 'merge' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc 2013-06-14 19:25:04 -10:00
s390 s390/pci: Implement IRQ functions if !PCI 2013-06-10 16:06:04 +02:00
score score: remove redundant kcore_list entries 2013-05-25 10:27:27 -07:00
sh Removal of GENERIC_GPIO for v3.10 2013-05-09 09:59:16 -07:00
sparc of: Fix locking vs. interrupts 2013-06-13 22:12:14 +01:00
tile Merge branch 'stable' of git://git.kernel.org/pub/scm/linux/kernel/git/cmetcalf/linux-tile 2013-05-09 14:34:58 -07:00
um Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs 2013-05-07 15:14:53 -07:00
unicore32 Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/signal 2013-05-10 09:21:05 -07:00
x86 trace,x86: Do not call local_irq_save() in load_current_idt() 2013-06-22 13:16:19 -04:00
xtensa Xtensa patchset for v3.10-rc1 2013-05-09 14:38:16 -07:00
.gitignore
Kconfig Merge branch 'core-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip 2013-05-15 14:04:00 -07:00