linux/arch/x86/kernel
Rafael J. Wysocki 406f992e4a x86 / hibernate: Use hlt_play_dead() when resuming from hibernation
On Intel hardware, native_play_dead() uses mwait_play_dead() by
default and only falls back to the other methods if that fails.
That also happens during resume from hibernation, when the restore
(boot) kernel runs disable_nonboot_cpus() to take all of the CPUs
except for the boot one offline.

However, that is problematic, because the address passed to
__monitor() in mwait_play_dead() is likely to be written to in the
last phase of hibernate image restoration and that causes the "dead"
CPU to start executing instructions again.  Unfortunately, the page
containing the address in that CPU's instruction pointer may not be
valid any more at that point.

First, that page may have been overwritten with image kernel memory
contents already, so the instructions the CPU attempts to execute may
simply be invalid.  Second, the page tables previously used by that
CPU may have been overwritten by image kernel memory contents, so the
address in its instruction pointer is impossible to resolve then.

A report from Varun Koyyalagunta and investigation carried out by
Chen Yu show that the latter sometimes happens in practice.

To prevent it from happening, temporarily change the smp_ops.play_dead
pointer during resume from hibernation so that it points to a special
"play dead" routine which uses hlt_play_dead() and avoids the
inadvertent "revivals" of "dead" CPUs this way.

A slightly unpleasant consequence of this change is that if the
system is hibernated with one or more CPUs offline, it will generally
draw more power after resume than it did before hibernation, because
the physical state entered by CPUs via hlt_play_dead() is higher-power
than the mwait_play_dead() one in the majority of cases.  It is
possible to work around this, but it is unclear how much of a problem
that's going to be in practice, so the workaround will be implemented
later if it turns out to be necessary.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=106371
Reported-by: Varun Koyyalagunta <cpudebug@centtech.com>
Original-by: Chen Yu <yu.c.chen@intel.com>
Tested-by: Chen Yu <yu.c.chen@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
2016-07-15 22:42:48 +02:00
..
acpi ACPI material for v4.7-rc1 2016-05-16 19:41:41 -07:00
apic x86/ioapic: Fix incorrect pointers in ioapic_setup_resources() 2016-06-10 14:45:54 +02:00
cpu x86/cpu/AMD: Extend X86_FEATURE_TOPOEXT workaround to newer models 2016-06-08 13:51:34 +02:00
fpu x86/fpu: Get rid of x87 math exception helpers 2016-04-13 11:37:44 +02:00
kprobes kprobes/x86: Clear TF bit in fault on single-stepping 2016-06-14 12:00:54 +02:00
.gitignore
alternative.c x86/asm: Stop depending on ptrace.h in alternative.h 2016-04-29 11:56:40 +02:00
amd_gart_64.c
amd_nb.c x86/cpu: Get rid of compute_unit_id 2016-03-29 10:45:04 +02:00
apb_timer.c x86/apb/timer: Use proper mask to modify hotplug action 2016-03-19 13:40:08 +01:00
aperture_64.c param: convert some "on"/"off" users to strtobool 2016-03-17 15:09:34 -07:00
apm_32.c x86/apm32: Remove paravirt_enabled() use 2016-04-22 10:29:03 +02:00
asm-offsets_32.c x86/entry/32: Simplify and fix up the SYSENTER stack #DB/NMI fixup 2016-03-10 09:48:14 +01:00
asm-offsets_64.c x86/syscalls: Add syscall entry qualifiers 2016-01-29 09:46:38 +01:00
asm-offsets.c x86/boot: Move compressed kernel to the end of the decompression buffer 2016-04-29 11:03:29 +02:00
audit_64.c
bootflag.c
check.c Linux 4.2-rc8 2015-08-25 09:59:19 +02:00
cpuid.c new helpers: no_seek_end_llseek{,_size}() 2015-12-23 10:41:31 -05:00
crash_dump_32.c
crash_dump_64.c
crash.c x86/kexec: Remove walk_iomem_res() call with GART type 2016-01-30 09:49:59 +01:00
devicetree.c x86/cpufeature: Replace cpu_has_apic with boot_cpu_has() usage 2016-04-13 11:37:41 +02:00
doublefault.c
dumpstack_32.c x86: avoid avoid passing around 'thread_info' in stack dumping code 2016-06-23 12:20:01 -07:00
dumpstack_64.c x86: avoid avoid passing around 'thread_info' in stack dumping code 2016-06-23 12:20:01 -07:00
dumpstack.c x86: fix up a few misc stack pointer vs thread_info confusions 2016-06-24 16:55:53 -07:00
e820.c Merge branch 'x86-asm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip 2016-03-15 09:32:27 -07:00
early_printk.c x86: Fix misspellings in comments 2016-02-24 08:44:58 +01:00
early-quirks.c Linux 4.4-rc2 2015-11-23 09:04:05 +01:00
ebda.c x86/init: Rename EBDA code file 2016-04-22 10:29:07 +02:00
espfix_64.c x86: get rid of superfluous __GFP_REPEAT 2016-06-24 17:23:52 -07:00
ftrace.c Nothing major this round. Mostly small clean ups and fixes. 2016-03-24 10:52:25 -07:00
head32.c x86/rtc: Replace paravirt rtc check with platform legacy quirk 2016-04-22 10:29:01 +02:00
head64.c x86/rtc: Replace paravirt rtc check with platform legacy quirk 2016-04-22 10:29:01 +02:00
head_32.S Merge branch 'x86/urgent' into x86/asm, to refresh the tree 2016-04-29 11:55:04 +02:00
head_64.S x86/asm: Make sure verify_cpu() has a good stack 2016-04-13 11:52:19 +02:00
hpet.c Merge branch 'x86-cleanups-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip 2016-05-16 16:40:14 -07:00
hw_breakpoint.c x86/cpufeature: Remove unused and seldomly used cpu_has_xx macros 2015-12-19 11:49:55 +01:00
i386_ksyms_32.c
i8237.c
i8253.c clockevents/drivers/i8253: Migrate to new 'set-state' interface 2015-08-10 11:40:30 +02:00
i8259.c x86/irq: Probe for PIC presence before allocating descs for legacy IRQs 2015-11-07 10:37:37 +01:00
io_delay.c
ioport.c x86/iopl: Fix iopl capability check on Xen PV 2016-03-17 09:49:27 +01:00
irq_32.c x86: fix up a few misc stack pointer vs thread_info confusions 2016-06-24 16:55:53 -07:00
irq_64.c x86/irq: Drop unlikely before IS_ERR_OR_NULL 2015-10-01 11:08:56 +02:00
irq_work.c treewide: Remove old email address 2015-11-23 09:44:58 +01:00
irq.c x86/irq: Call irq_force_move_complete with irq descriptor 2016-01-15 13:44:01 +01:00
irqinit.c x86/irq: Store irq descriptor in vector array 2015-08-06 00:14:59 +02:00
jump_label.c x86/asm: Stop depending on ptrace.h in alternative.h 2016-04-29 11:56:40 +02:00
kdebugfs.c
kexec-bzimage64.c KEYS: Generalise system_verify_data() to provide access to internal content 2016-04-06 16:14:24 +01:00
kgdb.c x86/asm: Stop depending on ptrace.h in alternative.h 2016-04-29 11:56:40 +02:00
ksysfs.c
kvm.c Merge branch 'x86-boot-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip 2016-05-16 15:54:01 -07:00
kvmclock.c x86: Fix misspellings in comments 2016-02-24 08:44:58 +01:00
ldt.c x86/mm: Factor out LDT init from context init 2016-02-18 19:46:31 +01:00
machine_kexec_32.c
machine_kexec_64.c kexec: provide arch_kexec_protect(unprotect)_crashkres() 2016-05-23 17:04:14 -07:00
Makefile Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jikos/livepatching 2016-05-17 17:11:27 -07:00
mcount_64.S ftrace/x86: Set ftrace_stub to weak to prevent gcc from using short jumps to it 2016-05-20 13:28:40 -04:00
mmconf-fam10h_64.c
module.c x86/asm: Stop depending on ptrace.h in alternative.h 2016-04-29 11:56:40 +02:00
mpparse.c x86/cpufeature: Use enum cpuid_leafs instead of magic numbers 2016-02-01 10:46:48 +01:00
msr.c x86/cpufeature: Carve out X86_FEATURE_* 2016-01-30 11:22:17 +01:00
nmi_selftest.c
nmi.c x86/nmi: Mark 'ignore_nmis' as __read_mostly 2016-03-08 12:48:19 +01:00
paravirt_patch_32.c x86/paravirt: Remove the unused irq_enable_sysexit pv op 2015-11-23 10:48:16 +01:00
paravirt_patch_64.c x86/entry, x86/paravirt: Remove the unused usergs_sysret32 PV op 2015-11-23 10:48:16 +01:00
paravirt-spinlocks.c
paravirt.c Merge branch 'x86-boot-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip 2016-05-16 15:54:01 -07:00
pci-calgary_64.c x86/platform/calgary: Constify cal_chipset_ops structures 2015-11-29 08:50:58 +01:00
pci-dma.c mm, page_alloc: distinguish between being unable to sleep, unwilling to sleep and avoiding waking kswapd 2015-11-06 17:50:42 -08:00
pci-iommu_table.c x86: Fix non-static inlines 2016-04-16 13:21:40 +02:00
pci-nommu.c
pci-swiotlb.c x86/mm/64: Enable SWIOTLB if system has SRAT memory regions above MAX_DMA32_PFN 2015-12-06 12:46:31 +01:00
pcspeaker.c
perf_regs.c
platform-quirks.c x86/init: Disable pnpbios and rtc for X86_SUBARCH_CE4100 2016-04-22 10:29:09 +02:00
pmem.c x86, kexec, nvdimm: Use walk_iomem_res_desc() for iomem search 2016-01-30 09:49:59 +01:00
probe_roms.c
process_32.c sched/core, sched/x86: Kill thread_info::saved_preempt_count 2015-10-06 17:08:18 +02:00
process_64.c x86/fsgsbase/64: Use TASK_SIZE_MAX for FSBASE/GSBASE upper limits 2016-05-20 09:10:03 +02:00
process.c exit_thread: accept a task parameter to be exited 2016-05-20 17:58:30 -07:00
ptrace.c x86/fsgsbase/64: Use TASK_SIZE_MAX for FSBASE/GSBASE upper limits 2016-05-20 09:10:03 +02:00
pvclock.c x86/vdso: Remove pvclock fixmap machinery 2015-12-11 08:56:03 +01:00
quirks.c timers/x86/hpet: Type adjustments 2015-10-21 11:17:32 +02:00
reboot_fixups_32.c
reboot.c x86/efi: Force EFI reboot to process pending capsules 2016-04-28 11:34:04 +02:00
relocate_kernel_32.S
relocate_kernel_64.S
resource.c
rtc.c x86/init: Disable pnpbios and rtc for X86_SUBARCH_CE4100 2016-04-22 10:29:09 +02:00
setup_percpu.c
setup.c ACPI / x86: Cleanup initrd related code 2016-04-18 23:59:09 +02:00
signal_compat.c x86/compat: Move copy_siginfo_*_user32() to signal_compat.c 2015-07-06 15:28:55 +02:00
signal.c Merge branch 'x86-asm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip 2016-05-16 15:15:17 -07:00
smp.c x86/smp: Remove single IPI wrapper 2015-11-05 13:07:54 +01:00
smpboot.c x86 / hibernate: Use hlt_play_dead() when resuming from hibernation 2016-07-15 22:42:48 +02:00
stacktrace.c perf: generalize perf_callchain 2016-02-20 00:21:44 -05:00
step.c Merge branch 'x86/urgent' into x86/asm to fix up conflicts and to pick up fixes 2015-08-18 09:39:47 +02:00
sys_x86_64.c
sysfb_efi.c Merge branch 'linus' into efi/core, to pick up fixes 2016-05-07 07:00:07 +02:00
sysfb_simplefb.c
sysfb.c
tboot.c x86/tboot: Remove paravirt_enabled() use 2016-04-22 10:29:04 +02:00
tce_64.c x86/cpufeature: Remove cpu_has_clflush 2016-03-31 13:35:09 +02:00
test_nx.c x86/mm: Always enable CONFIG_DEBUG_RODATA and remove the Kconfig option 2016-02-22 08:51:38 +01:00
test_rodata.c x86/mm: Always enable CONFIG_DEBUG_RODATA and remove the Kconfig option 2016-02-22 08:51:38 +01:00
time.c
tls.c x86/tls: Synchronize segment registers in set_thread_area() 2016-04-29 11:56:42 +02:00
tls.h
topology.c x86: Drop bogus __ref / __refdata annotations 2015-07-20 18:57:20 +02:00
trace_clock.c x86/asm/tsc: Add rdtsc_ordered() and use it in trivial call sites 2015-07-06 15:23:29 +02:00
tracepoint.c
traps.c x86/entry/traps: Don't force in_interrupt() to return true in IST handlers 2016-06-10 13:54:47 +02:00
tsc_msr.c x86/tsc: Add missing Cherrytrail frequency to the table 2016-05-12 14:27:14 +02:00
tsc_sync.c x86/asm/tsc/sync: Use rdtsc_ordered() in check_tsc_warp() and drop extra barriers 2015-07-06 15:23:29 +02:00
tsc.c x86/tsc: Save an indentation level in recalibrate_cpu_khz() 2016-04-13 11:37:43 +02:00
uprobes.c Merge branch 'x86-asm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip 2016-05-16 15:15:17 -07:00
verify_cpu.S x86/cpufeature: Carve out X86_FEATURE_* 2016-01-30 11:22:17 +01:00
vm86_32.c x86/cpufeature: Replace the old static_cpu_has() with safe variant 2016-01-30 11:22:18 +01:00
vmlinux.lds.S x86/boot: Move compressed kernel to the end of the decompression buffer 2016-04-29 11:03:29 +02:00
vsmp_64.c
x86_init.c x86/tsc: Remove unused tsc_pre_init() hook 2015-11-19 11:03:13 +01:00
x8664_ksyms_64.c x86/mm, x86/mce: Add memcpy_mcsafe() 2016-03-08 17:54:38 +01:00