linux/include/asm-generic
Aneesh Kumar K.V c777e2a8b6 powerpc/mm: Fix Multi hit ERAT cause by recent THP update
With ppc64 we use the deposited pgtable_t to store the hash pte slot
information. We should not withdraw the deposited pgtable_t without
marking the pmd none. This ensure that low level hash fault handling
will skip this huge pte and we will handle them at upper levels.

Recent change to pmd splitting changed the above in order to handle the
race between pmd split and exit_mmap. The race is explained below.

Consider following race:

		CPU0				CPU1
shrink_page_list()
  add_to_swap()
    split_huge_page_to_list()
      __split_huge_pmd_locked()
        pmdp_huge_clear_flush_notify()
	// pmd_none() == true
					exit_mmap()
					  unmap_vmas()
					    zap_pmd_range()
					      // no action on pmd since pmd_none() == true
	pmd_populate()

As result the THP will not be freed. The leak is detected by check_mm():

	BUG: Bad rss-counter state mm:ffff880058d2e580 idx:1 val:512

The above required us to not mark pmd none during a pmd split.

The fix for ppc is to clear the huge pte of _PAGE_USER, so that low
level fault handling code skip this pte. At higher level we do take ptl
lock. That should serialze us against the pmd split. Once the lock is
acquired we do check the pmd again using pmd_same. That should always
return false for us and hence we should retry the access. We do the
pmd_same check in all case after taking plt with
THP (do_huge_pmd_wp_page, do_huge_pmd_numa_page and
huge_pmd_set_accessed)

Also make sure we wait for irq disable section in other cpus to finish
before flipping a huge pte entry with a regular pmd entry. Code paths
like find_linux_pte_or_hugepte depend on irq disable to get
a stable pte_t pointer. A parallel thp split need to make sure we
don't convert a pmd pte to a regular pmd entry without waiting for the
irq disable section to finish.

Fixes: eef1b3ba05 ("thp: implement split_huge_pmd()")
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2016-02-15 21:10:04 +11:00
..
bitops move count_zeroes.h out of asm-generic 2015-10-15 00:21:07 +02:00
4level-fixup.h mm, asm-generic: define PUD_SHIFT in <asm-generic/4level-fixup.h> 2015-02-11 17:06:03 -08:00
asm-offsets.h asm-generic: Add common asm-offsets.h 2015-06-23 13:35:49 +09:00
atomic-long.h atomic: remove all traces of READ_ONCE_CTRL() and atomic*_read_ctrl() 2015-11-03 17:22:17 -08:00
atomic.h atomic, arch: Audit atomic_{read,set}() 2015-09-23 09:54:28 +02:00
atomic64.h atomic: Provide atomic_{or,xor,and} 2015-07-27 14:06:24 +02:00
audit_change_attr.h audit: Modify a set of system calls in audit class definitions 2014-01-17 17:01:46 -05:00
audit_dir_write.h audit: support the "standard" <asm-generic/unistd.h> 2011-05-04 14:41:28 -04:00
audit_read.h audit: support the "standard" <asm-generic/unistd.h> 2011-05-04 14:41:28 -04:00
audit_signal.h
audit_write.h audit: Modify a set of system calls in audit class definitions 2014-01-17 17:01:46 -05:00
barrier.h asm-generic: implement virt_xxx memory barriers 2016-01-12 20:46:59 +02:00
bitops.h arch: Prepare for smp_mb__{before,after}_atomic() 2014-04-18 11:40:30 +02:00
bitsperlong.h UAPI: (Scripted) Disintegrate include/asm-generic 2012-10-04 18:20:15 +01:00
bug.h bug: Make BUG() always stop the machine 2014-04-07 16:36:10 -07:00
bugs.h
cache.h
cacheflush.h asm-generic/cacheflush.h: flush icache when copying to user pages 2011-05-25 08:39:37 -07:00
checksum.h asm-generic headers: Allow yet more arch overrides in checksum.h 2013-02-11 20:00:33 +05:30
clkdev.h asm-generic: COMMON_CLK defines __clk_{get,put} 2014-09-25 18:00:45 -07:00
cmpxchg-local.h LLVMLinux: Remove warning about returning an uninitialized variable 2014-04-09 13:44:35 -07:00
cmpxchg.h asm-generic: cmpxchg: avoid warnings from macro-ized cmpxchg() implementations 2015-10-15 00:21:13 +02:00
cputime.h cputime: Generic on-demand virtual cputime accounting 2013-01-27 19:23:27 +01:00
cputime_jiffies.h sched, time: Fix build error with 64 bit cputime_t on 32 bit systems 2014-10-03 05:46:55 +02:00
cputime_nsecs.h sched, time: Fix build error with 64 bit cputime_t on 32 bit systems 2014-10-03 05:46:55 +02:00
current.h
delay.h asm-generic: delay.h fix udelay and ndelay for 8 bit args 2011-07-22 18:45:33 +02:00
device.h
div64.h
dma-coherent.h DMA-API: Change dma_declare_coherent_memory() CPU address to phys_addr_t 2014-05-20 16:55:23 -06:00
dma-contiguous.h asm-generic: Add dma-contiguous.h 2014-09-22 13:35:51 +02:00
dma-mapping-broken.h asm-generic/dma-mapping-broken.h: Provide dma_alloc_attrs()/dma_free_attrs() 2012-12-25 20:14:54 +01:00
dma-mapping-common.h dma-mapping: consolidate dma_set_mask 2015-09-10 13:29:01 -07:00
dma.h
early_ioremap.h Merge branch 'akpm' (patches from Andrew) 2015-09-08 17:52:23 -07:00
emergency-restart.h
exec.h Split arch_align_stack() out from asm-generic/system.h 2012-03-28 18:30:03 +01:00
fb.h
fixmap.h mm: provide early_memremap_ro to establish read-only mapping 2015-08-20 12:24:22 +01:00
ftrace.h
futex.h sched/preempt, futex: Disable preemption in UP futex_atomic_cmpxchg_inatomic() explicitly 2015-05-19 08:39:16 +02:00
getorder.h bitops: Add missing parentheses to new get_order macro 2012-02-24 10:39:27 -08:00
gpio.h gpio: remove gpiod_sysfs_set_active_low 2015-05-12 10:46:53 +02:00
hardirq.h
hugetlb.h mm: Fix generic hugetlb pte check return type. 2013-10-02 20:02:35 -04:00
hw_irq.h
ide_iops.h
int-ll64.h UAPI: (Scripted) Disintegrate include/asm-generic 2012-10-04 18:20:15 +01:00
io-64-nonatomic-hi-lo.h asm-generic: temporarily add back asm-generic/io-64-nonatomic*.h 2015-10-16 12:08:53 +02:00
io-64-nonatomic-lo-hi.h asm-generic: temporarily add back asm-generic/io-64-nonatomic*.h 2015-10-16 12:08:53 +02:00
io.h x86/mm, asm-generic: Add IOMMU ioremap_uc() variant default 2015-07-21 10:47:03 +02:00
ioctl.h include/asm-generic/ioctl.h: fix _IOC_TYPECHECK sparse error 2014-06-06 16:08:13 -07:00
iomap.h x86/mm, asm-generic: Add ioremap_wt() for creating Write-Through mappings 2015-06-07 15:28:56 +02:00
irq.h
irq_regs.h
irq_work.h irq_work: Introduce arch_irq_work_has_interrupt() 2014-09-13 18:38:07 +02:00
irqflags.h
Kbuild.asm UAPI: Set up uapi/asm/Kbuild.asm 2012-10-02 18:01:56 +01:00
kdebug.h
kmap_types.h asm-generic: remove km_type definitions 2012-07-24 15:27:30 +08:00
kvm_para.h KVM: add kvm_para_available to asm-generic/kvm_para.h 2013-06-05 13:21:29 +03:00
libata-portmap.h
linkage.h
local.h atomic: use <linux/atomic.h> 2011-07-26 16:49:47 -07:00
local64.h atomic: use <linux/atomic.h> 2011-07-26 16:49:47 -07:00
mcs_spinlock.h locking/mcs: Allow architecture specific asm files to be used for contended case 2014-02-09 21:18:52 +01:00
memory_model.h mm: add PHYS_PFN, use it in __phys_to_pfn() 2016-01-14 16:00:49 -08:00
mm-arch-hooks.h mm: clean up per architecture MM hook header files 2015-07-17 16:39:53 -07:00
mm_hooks.h mm: Make arch_unmap()/bprm_mm_init() available to all architectures 2014-11-19 11:54:13 +01:00
mmu.h asm-generic/mmu.h: Add support for FDPIC 2012-12-09 23:14:14 +01:00
mmu_context.h asm-generic: Remove asm-generic arch_bprm_mm_init() 2014-11-22 21:52:08 +01:00
module.h Make most arch asm/module.h files use asm-generic/module.h 2012-09-28 14:31:03 +09:30
msi.h asm-generic: Add msi.h 2014-11-23 13:01:47 +01:00
mutex-dec.h locking/mutex: Use acquire/release semantics 2015-10-06 17:28:20 +02:00
mutex-null.h arch: Make __mutex_fastpath_lock_retval return whether fastpath succeeded or not 2013-06-26 12:10:55 +02:00
mutex-xchg.h locking/mutex: Use acquire/release semantics 2015-10-06 17:28:20 +02:00
mutex.h
page.h The following changes since commit 3ee72ca992 2012-01-10 17:39:40 -08:00
param.h UAPI: (Scripted) Disintegrate include/asm-generic 2012-10-04 18:20:15 +01:00
parport.h include: remove __dev* attributes. 2013-01-03 15:57:16 -08:00
pci-bridge.h PCI: work around Stratus ftServer broken PCIe hierarchy 2012-04-30 15:21:02 -06:00
pci-dma-compat.h pci: remove pci_dma_supported 2015-11-10 16:32:11 -08:00
pci.h PCI: Remove unused pcibios_select_root() (again) 2015-06-08 07:56:21 -05:00
pci_iomap.h PCI: Add pci_iomap_wc() variants 2015-08-25 09:59:45 +02:00
percpu.h percpu: preffity percpu header files 2014-06-17 19:12:40 -04:00
pgalloc.h
pgtable-nopmd.h
pgtable-nopud.h
pgtable.h powerpc/mm: Fix Multi hit ERAT cause by recent THP update 2016-02-15 21:10:04 +11:00
preempt.h sched/core: Create preempt_count invariant 2015-10-06 17:08:14 +02:00
ptrace.h asm-generic/ptrace.h: start a common low level ptrace helper 2011-05-26 17:12:36 -07:00
qrwlock.h locking/qrwlock: Make use of _{acquire|release|relaxed}() atomics 2015-08-12 11:59:06 +02:00
qrwlock_types.h locking/qrwlock: Rename ->lock to ->wait_lock 2015-09-18 09:27:29 +02:00
qspinlock.h locking/qspinlock: Use _acquire/_release() versions of cmpxchg() & xchg() 2015-11-23 10:01:58 +01:00
qspinlock_types.h locking/qspinlock: Optimize for smaller NR_CPUS 2015-05-08 12:36:48 +02:00
resource.h asm-generic: remove _STK_LIM_MAX 2014-05-15 00:32:09 +01:00
rtc.h rtc: cmos: century support 2015-09-05 13:19:09 +02:00
rwsem.h locking/rwsem: Use acquire/release semantics 2015-10-06 17:28:24 +02:00
seccomp.h seccomp: allow COMPAT sigreturn overrides 2015-04-17 09:04:09 -04:00
sections.h asm/sections: add helpers to check for section data 2016-01-16 11:17:24 -08:00
segment.h
serial.h
siginfo.h constify copy_siginfo_to_user{,32}() 2013-11-09 00:16:29 -05:00
signal.h unify default ptrace_signal_deliver 2012-11-29 00:01:23 -05:00
simd.h crypto: create generic version of ablk_helper 2013-09-24 06:02:24 +10:00
sizes.h ARM: 7430/1: sizes.h: move from asm-generic to <linux/sizes.h> 2012-06-28 17:14:34 +01:00
spinlock.h
statfs.h UAPI: (Scripted) Disintegrate include/asm-generic 2012-10-04 18:20:15 +01:00
string.h
switch_to.h Split the switch_to() wrapper out of asm-generic/system.h 2012-03-28 18:30:03 +01:00
syscall.h syscall.h: fix doc text for syscall_get_arch() 2014-09-23 16:20:00 -04:00
syscalls.h burying unused conditionals 2013-02-14 09:21:15 -05:00
termios-base.h
termios.h UAPI: (Scripted) Disintegrate include/asm-generic 2012-10-04 18:20:15 +01:00
timex.h
tlb.h treewide: Remove old email address 2015-11-23 09:44:58 +01:00
tlbflush.h BUG: headers with BUG/BUG_ON etc. need linux/bug.h 2012-03-04 17:54:34 -05:00
topology.h
trace_clock.h tracing,x86: Add a TSC trace_clock 2012-11-13 15:48:27 -05:00
uaccess-unaligned.h
uaccess.h asm-generic: {get,put}_user ptr argument evaluate only 1 time 2015-11-08 22:44:42 +09:00
unaligned.h asm-generic: allow generic unaligned access if the arch supports it 2014-05-08 10:22:23 +02:00
unistd.h We get rid of the general module prefix confusion with a binary config option, 2013-05-05 10:58:06 -07:00
user.h
vga.h
vmlinux.lds.h clocksource / ACPI: Add probing infrastructure for ACPI-based clocksources 2015-10-01 02:18:38 +02:00
vtime.h include/asm-generic/vtime.h: avoid zero-length file 2013-09-30 14:31:02 -07:00
word-at-a-time.h Make asm/word-at-a-time.h available on all architectures 2015-07-08 16:41:55 -04:00
xor.h asm-generic: xor: mark static functions as __maybe_unused 2012-10-03 21:21:06 +02:00