linux_dsm_epyc7002/mm
Linus Torvalds 2b047252d0 Fix TLB gather virtual address range invalidation corner cases
Ben Tebulin reported:

 "Since v3.7.2 on two independent machines a very specific Git
  repository fails in 9/10 cases on git-fsck due to an SHA1/memory
  failures.  This only occurs on a very specific repository and can be
  reproduced stably on two independent laptops.  Git mailing list ran
  out of ideas and for me this looks like some very exotic kernel issue"

and bisected the failure to the backport of commit 53a59fc67f ("mm:
limit mmu_gather batching to fix soft lockups on !CONFIG_PREEMPT").

That commit itself is not actually buggy, but what it does is to make it
much more likely to hit the partial TLB invalidation case, since it
introduces a new case in tlb_next_batch() that previously only ever
happened when running out of memory.

The real bug is that the TLB gather virtual memory range setup is subtly
buggered.  It was introduced in commit 597e1c3580 ("mm/mmu_gather:
enable tlb flush range in generic mmu_gather"), and the range handling
was already fixed at least once in commit e6c495a96c ("mm: fix the TLB
range flushed when __tlb_remove_page() runs out of slots"), but that fix
was not complete.

The problem with the TLB gather virtual address range is that it isn't
set up by the initial tlb_gather_mmu() initialization (which didn't get
the TLB range information), but it is set up ad-hoc later by the
functions that actually flush the TLB.  And so any such case that forgot
to update the TLB range entries would potentially miss TLB invalidates.

Rather than try to figure out exactly which particular ad-hoc range
setup was missing (I personally suspect it's the hugetlb case in
zap_huge_pmd(), which didn't have the same logic as zap_pte_range()
did), this patch just gets rid of the problem at the source: make the
TLB range information available to tlb_gather_mmu(), and initialize it
when initializing all the other tlb gather fields.

This makes the patch larger, but conceptually much simpler.  And the end
result is much more understandable; even if you want to play games with
partial ranges when invalidating the TLB contents in chunks, now the
range information is always there, and anybody who doesn't want to
bother with it won't introduce subtle bugs.

Ben verified that this fixes his problem.

Reported-bisected-and-tested-by: Ben Tebulin <tebulin@googlemail.com>
Build-testing-by: Stephen Rothwell <sfr@canb.auug.org.au>
Build-testing-by: Richard Weinberger <richard.weinberger@gmail.com>
Reviewed-by: Michal Hocko <mhocko@suse.cz>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Cc: stable@vger.kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-08-16 08:52:46 -07:00
..
backing-dev.c sysfs.h: add __ATTR_RW() macro 2013-07-16 10:57:36 -07:00
balloon_compaction.c mm: introduce a common interface for balloon pages mobility 2012-12-11 17:22:26 -08:00
bootmem.c mm: kill free_all_bootmem_node() 2013-07-03 16:07:39 -07:00
bounce.c Merge branch 'for-3.10/core' of git://git.kernel.dk/linux-block 2013-05-08 10:13:35 -07:00
cleancache.c mm: cleancache: clean up cleancache_enabled 2013-04-30 17:04:01 -07:00
compaction.c mm: add & use zone_end_pfn() and zone_spans_pfn() 2013-02-23 17:50:20 -08:00
debug-pagealloc.c mm, x86: Remove debug_pagealloc_enabled 2011-12-06 09:24:07 +01:00
dmapool.c dmapool: make DMAPOOL_DEBUG detect corruption of free marker 2012-12-11 17:22:24 -08:00
fadvise.c teach SYSCALL_DEFINE<n> how to deal with long long/unsigned long long 2013-03-03 22:46:22 -05:00
failslab.c switch debugfs to umode_t 2012-01-03 22:54:56 -05:00
filemap_xip.c lift sb_start_write() out of ->write() 2013-04-09 14:12:56 -04:00
filemap.c mm: remove unused VM_<READfoo> macros and expand other in-place 2013-07-09 10:33:23 -07:00
fremap.c mm: save soft-dirty bits on file pages 2013-08-13 17:57:48 -07:00
frontswap.c frontswap: fix incorrect zeroing and allocation size for frontswap_map 2013-06-12 16:29:46 -07:00
highmem.c Some nice cleanups, and even a patch my wife did as a "live" demo for 2012-12-20 08:37:05 -08:00
huge_memory.c thp, mm: avoid PageUnevictable on active/inactive lru lists 2013-07-31 14:41:03 -07:00
hugetlb_cgroup.c mm/hugetlb: create hugetlb cgroup file in hugetlb_init 2012-12-18 15:02:15 -08:00
hugetlb.c Fix TLB gather virtual address range invalidation corner cases 2013-08-16 08:52:46 -07:00
hwpoison-inject.c memcg: rename config variables 2012-07-31 18:42:43 -07:00
init-mm.c atomic: use <linux/atomic.h> 2011-07-26 16:49:47 -07:00
internal.h mm: remove unused __put_page() 2013-07-09 10:33:22 -07:00
interval_tree.c mm: add CONFIG_DEBUG_VM_RB build option 2012-10-09 16:22:42 +09:00
Kconfig zswap: add to mm/ 2013-07-10 18:11:34 -07:00
Kconfig.debug mm: more intensive memory corruption debugging 2012-01-10 16:30:42 -08:00
kmemcheck.c
kmemleak-test.c kmemleak: remove memset by using kzalloc 2011-01-27 18:31:51 +00:00
kmemleak.c hlist: drop the node parameter from iterators 2013-02-27 19:10:24 -08:00
ksm.c ksm: fix m68k build: only NUMA needs pfn_to_nid 2013-03-08 15:05:34 -08:00
maccess.c mm: Map most files to use export.h instead of module.h 2011-10-31 09:20:12 -04:00
madvise.c mm: madvise: complete input validation before taking lock 2013-04-29 15:54:37 -07:00
Makefile zswap: add to mm/ 2013-07-10 18:11:34 -07:00
memblock.c mm/memblock.c: fix wrong comment in __next_free_mem_range() 2013-07-09 10:33:23 -07:00
memcontrol.c memcg: don't initialize kmem-cache destroying work for root caches 2013-08-13 17:57:47 -07:00
memory_hotplug.c mm/memory_hotplug.c: fix return value of online_pages() 2013-07-09 10:33:25 -07:00
memory-failure.c mm/memory-failure.c: fix memory leak in successful soft offlining 2013-07-03 16:07:31 -07:00
memory.c Fix TLB gather virtual address range invalidation corner cases 2013-08-16 08:52:46 -07:00
mempolicy.c mm: mempolicy: fix mbind_range() && vma_adjust() interaction 2013-07-31 14:41:02 -07:00
mempool.c mempool: add @gfp_mask to mempool_create_node() 2012-06-25 11:53:47 +02:00
migrate.c mm: migration: add migrate_entry_wait_huge() 2013-06-12 16:29:46 -07:00
mincore.c swap: make each swap partition have one address_space 2013-02-23 17:50:17 -08:00
mlock.c Revert "mm: introduce VM_POPULATE flag to better deal with racy userspace programs" 2013-03-28 17:45:51 -07:00
mm_init.c mm: tune vm_committed_as percpu_counter batching size 2013-07-03 16:07:32 -07:00
mmap.c Fix TLB gather virtual address range invalidation corner cases 2013-08-16 08:52:46 -07:00
mmu_context.c mm: remove old aio use_mm() comment 2013-05-07 18:38:27 -07:00
mmu_notifier.c treewide: relase -> release 2013-06-28 14:34:33 +02:00
mmzone.c mm: rename page struct field helpers 2013-02-23 17:50:18 -08:00
mprotect.c mm/mprotect.c: coding-style cleanups 2012-12-18 15:02:15 -08:00
mremap.c mm: mremap: validate input before taking lock 2013-07-09 10:33:20 -07:00
msync.c sanitize vfs_fsync calling conventions 2010-05-21 18:31:21 -04:00
nobootmem.c mm: concentrate modification of totalram_pages into the mm core 2013-07-03 16:07:33 -07:00
nommu.c mm: remove free_area_cache 2013-07-10 18:11:34 -07:00
oom_kill.c memcg, oom: provide more precise dump info while memcg oom happening 2013-02-23 17:50:08 -08:00
page_alloc.c mm: honor min_free_kbytes set by user 2013-07-09 10:33:25 -07:00
page_cgroup.c memcontrol: use N_MEMORY instead N_HIGH_MEMORY 2012-12-12 17:38:32 -08:00
page_io.c mm: remove compressed copy from zram in-memory 2013-07-03 16:07:26 -07:00
page_isolation.c mm: fix zone_watermark_ok_safe() accounting of isolated pages 2013-01-04 16:11:46 -08:00
page-writeback.c kernel: delete __cpuinit usage from all core kernel files 2013-07-14 19:36:59 -04:00
pagewalk.c mm/pagewalk.c: walk_page_range should avoid VM_PFNMAP areas 2013-05-24 16:22:53 -07:00
percpu-km.c percpu: clear memory allocated with the km allocator 2010-10-02 10:28:42 +03:00
percpu-vm.c mm: fix kernel-doc warnings 2012-06-20 14:39:36 -07:00
percpu.c mm, percpu: Make sure percpu_alloc early parameter has an argument 2012-12-02 06:23:04 -08:00
pgtable-generic.c mm/THP: add pmd args to pgtable deposit and withdraw APIs 2013-06-20 16:55:07 +10:00
process_vm_access.c Fix: compat_rw_copy_check_uvector() misuse in aio, readv, writev, and security keys 2013-03-12 11:05:45 -07:00
quicklist.c mm: delete various needless include <linux/module.h> 2011-10-31 09:20:11 -04:00
readahead.c mm: change invalidatepage prototype to accept length 2013-05-21 23:17:23 -04:00
rmap.c mm: save soft-dirty bits on file pages 2013-08-13 17:57:48 -07:00
shmem.c tmpfs: fix SEEK_DATA/SEEK_HOLE regression 2013-08-04 11:40:17 -07:00
slab_common.c Merge branch 'slab/for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/penberg/linux 2013-07-14 15:14:29 -07:00
slab.c kernel: delete __cpuinit usage from all core kernel files 2013-07-14 19:36:59 -04:00
slab.h mm/slab: Give s_next and s_stop slab-specific names 2013-07-08 11:02:17 +03:00
slob.c Merge branch 'slab/for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/penberg/linux 2013-07-14 15:14:29 -07:00
slub.c Revert "slub: do not put a slab to cpu partial list when cpu_partial is 0" 2013-08-08 09:06:37 -07:00
sparse-vmemmap.c sparse-vmemmap: specify vmemmap population range in bytes 2013-04-29 15:54:35 -07:00
sparse.c mm/sparse.c: put clear_hwpoisoned_pages within CONFIG_MEMORY_HOTREMOVE 2013-07-09 10:33:22 -07:00
swap_state.c swap: avoid read_swap_cache_async() race to deadlock while waiting on discard I/O completion 2013-06-12 16:29:45 -07:00
swap.c thp, mm: avoid PageUnevictable on active/inactive lru lists 2013-07-31 14:41:03 -07:00
swapfile.c mm: save soft-dirty bits on swapped pages 2013-08-13 17:57:47 -07:00
truncate.c mm: teach truncate_inode_pages_range() to handle non page aligned ranges 2013-05-27 23:32:35 -04:00
util.c mm: remove free_area_cache 2013-07-10 18:11:34 -07:00
vmalloc.c mm/vmalloc.c: fix an overflow bug in alloc_vmap_area() 2013-07-09 10:33:23 -07:00
vmpressure.c vmpressure: make sure there are no events queued after memcg is offlined 2013-07-31 14:41:04 -07:00
vmscan.c mm: vmscan: do not scale writeback pages when deciding whether to set ZONE_WRITEBACK 2013-07-09 10:33:23 -07:00
vmstat.c kernel: delete __cpuinit usage from all core kernel files 2013-07-14 19:36:59 -04:00
zbud.c mm: zbud: fix condition check on allocation size 2013-07-31 14:41:03 -07:00
zswap.c zswap: add to mm/ 2013-07-10 18:11:34 -07:00