isolate_huge_page() expects we pass the head of hugetlb page to it:
bool isolate_huge_page(...)
{
...
VM_BUG_ON_PAGE(!PageHead(page), page);
...
}
While I really cannot think of any situation where we end up with a
non-head page between hands in do_migrate_range(), let us make sure the
code is as sane as possible by explicitly passing the Head. Since we
already got the pointer, it does not take us extra effort.
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Oscar Salvador <[email protected]>
Reviewed-by: Andrew Morton <[email protected]>
Reviewed-by: David Hildenbrand <[email protected]>
Acked-by: Michal Hocko <[email protected]>
Cc: Anthony Yznaga <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
From: John Hubbard <[email protected]>
This combines the common elements of these routines:
page_cache_get_speculative()
page_cache_add_speculative()
This was anticipated by the original author, as shown by the comment in
commit ce0ad7f095 ("powerpc/mm: Lockless get_user_pages_fast() for
64-bit (v3)"):
"Same as above, but add instead of inc (could just be merged)"
There is no intention to introduce any behavioral change, but there is a
small risk of that, due to slightly differing ways of expressing the
TINY_RCU and related configurations.
This also removes the VM_BUG_ON(in_interrupt()) that was in
page_cache_add_speculative(), but not in page_cache_get_speculative().
This provides slightly less detection of such bugs, but it given that it
was only there on the "add" path anyway, we can likely do without it
just fine.
And it removes the
VM_BUG_ON_PAGE(PageCompound(page) && page != compound_head(page), page);
that page_cache_add_speculative() had.
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: John Hubbard <[email protected]>
Reviewed-by: Andrew Morton <[email protected]>
Cc: Benjamin Herrenschmidt <[email protected]>
Cc: Dave Kleikamp <[email protected]>
Cc: Hugh Dickins <[email protected]>
Cc: Jeff Layton <[email protected]>
Cc: Matthew Wilcox <[email protected]>
Cc: Nicholas Piggin <[email protected]>
Cc: Vlastimil Babka <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
Andrea has noted that page migration code propagates page_mapping(page)
through the whole migration stack down to migrate_page() function so it
seems stupid to then use page_mapping(page) in expected_page_refs()
instead of passed down 'mapping' argument. I agree so let's make
expected_page_refs() more in line with the rest of the migration stack.
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Jan Kara <[email protected]>
Suggested-by: Andrea Arcangeli <[email protected]>
Reviewed-by: Andrea Arcangeli <[email protected]>
Cc: Mel Gorman <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
Many kernel-doc comments in mm/ have the return value descriptions
either misformatted or omitted at all which makes kernel-doc script
unhappy:
$ make V=1 htmldocs
...
./mm/util.c:36: info: Scanning doc for kstrdup
./mm/util.c:41: warning: No description found for return value of 'kstrdup'
./mm/util.c:57: info: Scanning doc for kstrdup_const
./mm/util.c:66: warning: No description found for return value of 'kstrdup_const'
./mm/util.c:75: info: Scanning doc for kstrndup
./mm/util.c:83: warning: No description found for return value of 'kstrndup'
...
Fixing the formatting and adding the missing return value descriptions
eliminates ~100 such warnings.
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Mike Rapoport <[email protected]>
Reviewed-by: Andrew Morton <[email protected]>
Cc: Jonathan Corbet <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
The descriptions of userspace memory access functions had minor issues
with formatting that made kernel-doc unable to properly detect the
function/macro names and the return value sections:
./arch/x86/include/asm/uaccess.h:80: info: Scanning doc for
./arch/x86/include/asm/uaccess.h:139: info: Scanning doc for
./arch/x86/include/asm/uaccess.h:231: info: Scanning doc for
./arch/x86/include/asm/uaccess.h:505: info: Scanning doc for
./arch/x86/include/asm/uaccess.h:530: info: Scanning doc for
./arch/x86/lib/usercopy_32.c:58: info: Scanning doc for
./arch/x86/lib/usercopy_32.c:69: warning: No description found for return
value of 'clear_user'
./arch/x86/lib/usercopy_32.c:78: info: Scanning doc for
./arch/x86/lib/usercopy_32.c:90: warning: No description found for return
value of '__clear_user'
Fix the formatting.
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Mike Rapoport <[email protected]>
Reviewed-by: Andrew Morton <[email protected]>
Cc: Jonathan Corbet <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
mm/debug-pagealloc.c is no more, so of course header now needs to be
updated. This seems like something checkpatch should be able to catch -
worth looking into?
Link: http://lkml.kernel.org/r/[email protected]
Fixes: 8823b1dbc0 ("mm/page_poison.c: enable PAGE_POISONING as a separate option")
Signed-off-by: Michael S. Tsirkin <[email protected]>
Reviewed-by: Andrew Morton <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
Dan Carpenter reports a potential NULL dereference in
get_swap_page_of_type:
Smatch complains that the NULL checks on "si" aren't consistent. This
seems like a real bug because we have not ensured that the type is
valid and so "si" can be NULL.
Add the missing check for NULL, taking care to use a read barrier to
ensure CPU1 observes CPU0's updates in the correct order:
CPU0 CPU1
alloc_swap_info() if (type >= nr_swapfiles)
swap_info[type] = p /* handle invalid entry */
smp_wmb() smp_rmb()
++nr_swapfiles p = swap_info[type]
Without smp_rmb, CPU1 might observe CPU0's write to nr_swapfiles before
CPU0's write to swap_info[type] and read NULL from swap_info[type].
Ying Huang noticed other places in swapfile.c don't order these reads
properly. Introduce swap_type_to_swap_info to encourage correct usage.
Use READ_ONCE and WRITE_ONCE to follow the Linux Kernel Memory Model
(see tools/memory-model/Documentation/explanation.txt).
This ordering need not be enforced in places where swap_lock is held
(e.g. si_swapinfo) because swap_lock serializes updates to nr_swapfiles
and the swap_info array.
Link: http://lkml.kernel.org/r/[email protected]
Fixes: ec8acf20af ("swap: add per-partition lock for swapfile")
Signed-off-by: Daniel Jordan <[email protected]>
Reported-by: Dan Carpenter <[email protected]>
Suggested-by: "Huang, Ying" <[email protected]>
Reviewed-by: Andrea Parri <[email protected]>
Acked-by: Peter Zijlstra (Intel) <[email protected]>
Cc: Alan Stern <[email protected]>
Cc: Andi Kleen <[email protected]>
Cc: Dave Hansen <[email protected]>
Cc: Omar Sandoval <[email protected]>
Cc: Paul McKenney <[email protected]>
Cc: Shaohua Li <[email protected]>
Cc: Stephen Rothwell <[email protected]>
Cc: Tejun Heo <[email protected]>
Cc: Will Deacon <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
On path shrink_inactive_list() ---> shrink_page_list() we allocate stack
variables for the statistics twice. This is completely useless, and
this just consumes stack much more, then we really need.
The patch kills duplicate stack variables from shrink_page_list(), and
this reduce stack usage and object file size significantly:
Stack usage:
Before: vmscan.c:1122:22:shrink_page_list 648 static
After: vmscan.c:1122:22:shrink_page_list 616 static
Size of vmscan.o:
text data bss dec hex filename
Before: 56866 4720 128 61714 f112 mm/vmscan.o
After: 56770 4720 128 61618 f0b2 mm/vmscan.o
Link: http://lkml.kernel.org/r/154894900030.5211.12104993874109647641.stgit@localhost.localdomain
Signed-off-by: Kirill Tkhai <[email protected]>
Reviewed-by: Daniel Jordan <[email protected]>
Reviewed-by: Andrew Morton <[email protected]>
Acked-by: Michal Hocko <[email protected]>
Cc: Johannes Weiner <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
ksmd needs to search the stable tree to look for the suitable KSM page,
but the KSM page might be locked for a while due to i.e. KSM page rmap
walk. Basically it is not a big deal since commit 2c653d0ee2 ("ksm:
introduce ksm_max_page_sharing per page deduplication limit"), since
max_page_sharing limits the number of shared KSM pages.
But it still sounds not worth waiting for the lock, the page can be
skip, then try to merge it in the next scan to avoid potential stall if
its content is still intact.
Introduce trylock mode to get_ksm_page() to not block on page lock, like
what try_to_merge_one_page() does. And, define three possible
operations (nolock, lock and trylock) as enum type to avoid stacking up
bools and make the code more readable.
Return -EBUSY if trylock fails, since NULL means not find suitable KSM
page, which is a valid case.
With the default max_page_sharing setting (256), there is almost no
observed change comparing lock vs trylock.
However, with ksm02 of LTP, the reduced ksmd full scan time can be
observed, which has set max_page_sharing to 786432. With lock version,
ksmd may tak 10s - 11s to run two full scans, with trylock version ksmd
may take 8s - 11s to run two full scans. And, the number of
pages_sharing and pages_to_scan keep same. Basically, this change has
no harm.
[[email protected]: fix BUG_ON()]
Link: http://lkml.kernel.org/r/[email protected]
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Yang Shi <[email protected]>
Signed-off-by: Hugh Dickins <[email protected]>
Suggested-by: John Hubbard <[email protected]>
Reviewed-by: Kirill Tkhai <[email protected]>
Cc: Hugh Dickins <[email protected]>
Cc: Andrea Arcangeli <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
Currently THP allocation events data is fairly opaque, since you can
only get it system-wide. This patch makes it easier to reason about
transparent hugepage behaviour on a per-memcg basis.
For anonymous THP-backed pages, we already have MEMCG_RSS_HUGE in v1,
which is used for v1's rss_huge [sic]. This is reused here as it's
fairly involved to untangle NR_ANON_THPS right now to make it per-memcg,
since right now some of this is delegated to rmap before we have any
memcg actually assigned to the page. It's a good idea to rework that,
but let's leave untangling THP allocation for a future patch.
[[email protected]: fix build]
[[email protected]: fix memcontrol build when THP is disabled]
Link: http://lkml.kernel.org/r/[email protected]
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Chris Down <[email protected]>
Acked-by: Johannes Weiner <[email protected]>
Cc: Tejun Heo <[email protected]>
Cc: Roman Gushchin <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
In current implementation, both kswapd and direct reclaim has to iterate
all mem cgroups. It is not a problem before offline mem cgroups could
be iterated. But, currently with iterating offline mem cgroups, it
could be very time consuming. In our workloads, we saw over 400K mem
cgroups accumulated in some cases, only a few hundred are online memcgs.
Although kswapd could help out to reduce the number of memcgs, direct
reclaim still get hit with iterating a number of offline memcgs in some
cases. We experienced the responsiveness problems due to this
occassionally.
A simple test with pref shows it may take around 220ms to iterate 8K
memcgs in direct reclaim:
dd 13873 [011] 578.542919: vmscan:mm_vmscan_direct_reclaim_begin
dd 13873 [011] 578.758689: vmscan:mm_vmscan_direct_reclaim_end
So for 400K, it may take around 11 seconds to iterate all memcgs.
Here just break the iteration once it reclaims enough pages as what
memcg direct reclaim does. This may hurt the fairness among memcgs.
But the cached iterator cookie could help to achieve the fairness more
or less.
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Yang Shi <[email protected]>
Acked-by: Johannes Weiner <[email protected]>
Acked-by: Michal Hocko <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
Android uses ashmem for sharing memory regions. We are looking forward
to migrating all usecases of ashmem to memfd so that we can possibly
remove the ashmem driver in the future from staging while also
benefiting from using memfd and contributing to it. Note staging
drivers are also not ABI and generally can be removed at anytime.
One of the main usecases Android has is the ability to create a region
and mmap it as writeable, then add protection against making any
"future" writes while keeping the existing already mmap'ed
writeable-region active. This allows us to implement a usecase where
receivers of the shared memory buffer can get a read-only view, while
the sender continues to write to the buffer. See CursorWindow
documentation in Android for more details:
https://developer.android.com/reference/android/database/CursorWindow
This usecase cannot be implemented with the existing F_SEAL_WRITE seal.
To support the usecase, this patch adds a new F_SEAL_FUTURE_WRITE seal
which prevents any future mmap and write syscalls from succeeding while
keeping the existing mmap active.
A better way to do F_SEAL_FUTURE_WRITE seal was discussed [1] last week
where we don't need to modify core VFS structures to get the same
behavior of the seal. This solves several side-effects pointed by Andy.
self-tests are provided in later patch to verify the expected semantics.
[1] https://lore.kernel.org/lkml/[email protected]/
Thanks a lot to Andy for suggestions to improve code.
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Joel Fernandes (Google) <[email protected]>
Acked-by: John Stultz <[email protected]>
Cc: Andy Lutomirski <[email protected]>
Cc: Minchan Kim <[email protected]>
Cc: Jann Horn <[email protected]>
Cc: Al Viro <[email protected]>
Cc: Andy Lutomirski <[email protected]>
Cc: Hugh Dickins <[email protected]>
Cc: J. Bruce Fields <[email protected]>
Cc: Jeff Layton <[email protected]>
Cc: Marc-Andr Lureau <[email protected]>
Cc: Matthew Wilcox <[email protected]>
Cc: Mike Kravetz <[email protected]>
Cc: Shuah Khan <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
The current code doesn't do page migration if the page allocated is a
compound page. With HugeTLB migration support, we can end up allocating
hugetlb pages from CMA region. Also, THP pages can be allocated from
CMA region. This patch updates the code to handle compound pages
correctly. The patch also switches to a single get_user_pages with the
right count, instead of doing one get_user_pages per page. That avoids
reading page table multiple times. This is done by using
get_user_pages_longterm, because that also takes care of DAX backed
pages.
DAX pages lifetime is dictated by file system rules and as such, we need
to make sure that we free these pages on operations like truncate and
punch hole. If we have long term pin on these pages, which are mostly
return to userspace with elevated page count, the entity holding the
long term pin may not be aware of the fact that file got truncated and
the file system blocks possibly got reused. That can result in
corruption.
The patch also converts the hpas member of mm_iommu_table_group_mem_t to
a union. We use the same storage location to store pointers to struct
page. We cannot update all the code path use struct page *, because we
access hpas in real mode and we can't do that struct page * to pfn
conversion in real mode.
[[email protected]: address review feedback, update changelog]
Link: http://lkml.kernel.org/r/[email protected]
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Aneesh Kumar K.V <[email protected]>
Reviewed-by: Michael Ellerman <[email protected]>
Cc: Alexey Kardashevskiy <[email protected]>
Cc: Andrea Arcangeli <[email protected]>
Cc: David Gibson <[email protected]>
Cc: Michal Hocko <[email protected]>
Cc: Mel Gorman <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
This patch updates get_user_pages_longterm to migrate pages allocated
out of CMA region. This makes sure that we don't keep non-movable pages
(due to page reference count) in the CMA area.
This will be used by ppc64 in a later patch to avoid pinning pages in
the CMA region. ppc64 uses CMA region for allocation of the hardware
page table (hash page table) and not able to migrate pages out of CMA
region results in page table allocation failures.
One case where we hit this easy is when a guest using a VFIO passthrough
device. VFIO locks all the guest's memory and if the guest memory is
backed by CMA region, it becomes unmovable resulting in fragmenting the
CMA and possibly preventing other guests from allocation a large enough
hash page table.
NOTE: We allocate the new page without using __GFP_THISNODE
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Aneesh Kumar K.V <[email protected]>
Cc: Alexey Kardashevskiy <[email protected]>
Cc: Andrea Arcangeli <[email protected]>
Cc: David Gibson <[email protected]>
Cc: Michael Ellerman <[email protected]>
Cc: Michal Hocko <[email protected]>
Cc: Mel Gorman <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
Patch series "mm/kvm/vfio/ppc64: Migrate compound pages out of CMA
region", v8.
ppc64 uses the CMA area for the allocation of guest page table (hash
page table). We won't be able to start guest if we fail to allocate
hash page table. We have observed hash table allocation failure because
we failed to migrate pages out of CMA region because they were pinned.
This happen when we are using VFIO. VFIO on ppc64 pins the entire guest
RAM. If the guest RAM pages get allocated out of CMA region, we won't
be able to migrate those pages. The pages are also pinned for the
lifetime of the guest.
Currently we support migration of non-compound pages. With THP and with
the addition of hugetlb migration we can end up allocating compound
pages from CMA region. This patch series add support for migrating
compound pages.
This patch (of 4):
Add PF_MEMALLOC_NOCMA which make sure any allocation in that context is
marked non-movable and hence cannot be satisfied by CMA region.
This is useful with get_user_pages_longterm where we want to take a page
pin by migrating pages from CMA region. Marking the section
PF_MEMALLOC_NOCMA ensures that we avoid unnecessary page migration
later.
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Aneesh Kumar K.V <[email protected]>
Suggested-by: Andrea Arcangeli <[email protected]>
Reviewed-by: Andrea Arcangeli <[email protected]>
Cc: Michal Hocko <[email protected]>
Cc: Alexey Kardashevskiy <[email protected]>
Cc: David Gibson <[email protected]>
Cc: Michael Ellerman <[email protected]>
Cc: Mel Gorman <[email protected]>
Cc: Vlastimil Babka <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
The usage of PG_reserved and how PG_reserved pages are to be treated is
buried deep down in different parts of the kernel. Let's shine some
light onto these details by documenting current users and expected
behavior.
Especially, clarify on the "Some of them might not even exist" case.
These are physical memory gaps that will never be dumped as they are not
marked as IORESOURCE_SYSRAM. PG_reserved does in general not hinder
anybody from dumping or swapping. In some cases, these pages will not
be stored in the hibernation image.
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: David Hildenbrand <[email protected]>
Reviewed-by: Andrew Morton <[email protected]>
Cc: Stephen Rothwell <[email protected]>
Cc: Pavel Tatashin <[email protected]>
Cc: Michal Hocko <[email protected]>
Cc: Alexander Duyck <[email protected]>
Cc: Matthew Wilcox <[email protected]>
Cc: Anthony Yznaga <[email protected]>
Cc: Miles Chen <[email protected]>
Cc: <[email protected]>
Cc: Dan Williams <[email protected]>
Cc: Randy Dunlap <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
In the old days, remap_pfn_range() required pages to be marked as
PG_reserved, so they would e.g. never get swapped out. This was
required for special mappings. Nowadays, this is fully handled via the
VMA (VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP inside
remap_pfn_range() to be precise). PG_reserved is no longer required but
only a relic from the past.
So only architecture specific MM handling might require it (e.g. to
detect them as MMIO pages). As there are no architecture specific
checks for PageReserved() apart from MCA handling in ia64code, this can
go. Use simple vzalloc()/vfree() instead.
Note that before calling vzalloc(), size has already been aligned to
PAGE_SIZE, no need to align again.
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: David Hildenbrand <[email protected]>
Cc: Tony Luck <[email protected]>
Cc: Fenghua Yu <[email protected]>
Cc: Oleg Nesterov <[email protected]>
Cc: David Hildenbrand <[email protected]>
Cc: David Howells <[email protected]>
Cc: Mike Rapoport <[email protected]>
Cc: Michal Hocko <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
Patch series "mm: PG_reserved cleanups and documentation", v2.
I was recently going over all users of PG_reserved. Short story: it is
difficult and sometimes not really clear if setting/checking for
PG_reserved is only a relict from the past. Easy to break things. I
guess I now have a pretty good idea wh things are like that nowadays and
how they evolved.
I had way more cleanups in this series inititally, but some
architectures take PG_reserved as a way to apply a different caching
strategy (for MMIO pages). So I decided to only include the most
obvious changes (that are less likely to break something). So the big
chunk of manual SetPageReserved users are MMIO/DMA related things on
device buffers.
Most notably, for device memory we will hopefully soon stop setting
PG_reserved. Then the documentation has to be updated.
This patch (of 9):
The l1 GATT page table is kept in a special on-chip page with 64
entries. We allocate the l2 page table pages via get_zeroed_page() and
enter them into the table. These l2 pages are modified accordingly when
inserting/removing memory via efficeon_insert_memory and
efficeon_remove_memory.
Apart from that, these pages are not exposed or ioremap'ed. We can stop
setting them reserved (propably copied from generic code).
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: David Hildenbrand <[email protected]>
Cc: David Airlie <[email protected]>
Cc: Arnd Bergmann <[email protected]>
Cc: Greg Kroah-Hartman <[email protected]>
Cc: Michal Hocko <[email protected]>
Cc: Matthew Wilcox <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
This patch was initially posted by Kelley Nielsen. Reposting the patch
with all review comments addressed and with minor modifications and
optimizations. Also, folding in the fixes offered by Hugh Dickins and
Huang Ying. Tests were rerun and commit message updated with new
results.
try_to_unuse() is of quadratic complexity, with a lot of wasted effort.
It unuses swap entries one by one, potentially iterating over all the
page tables for all the processes in the system for each one.
This new proposed implementation of try_to_unuse simplifies its
complexity to linear. It iterates over the system's mms once, unusing
all the affected entries as it walks each set of page tables. It also
makes similar changes to shmem_unuse.
Improvement
swapoff was called on a swap partition containing about 6G of data, in a
VM(8cpu, 16G RAM), and calls to unuse_pte_range() were counted.
Present implementation....about 1200M calls(8min, avg 80% cpu util).
Prototype.................about 9.0K calls(3min, avg 5% cpu util).
Details
In shmem_unuse(), iterate over the shmem_swaplist and, for each
shmem_inode_info that contains a swap entry, pass it to
shmem_unuse_inode(), along with the swap type. In shmem_unuse_inode(),
iterate over its associated xarray, and store the index and value of
each swap entry in an array for passing to shmem_swapin_page() outside
of the RCU critical section.
In try_to_unuse(), instead of iterating over the entries in the type and
unusing them one by one, perhaps walking all the page tables for all the
processes for each one, iterate over the mmlist, making one pass. Pass
each mm to unuse_mm() to begin its page table walk, and during the walk,
unuse all the ptes that have backing store in the swap type received by
try_to_unuse(). After the walk, check the type for orphaned swap
entries with find_next_to_unuse(), and remove them from the swap cache.
If find_next_to_unuse() starts over at the beginning of the type, repeat
the check of the shmem_swaplist and the walk a maximum of three times.
Change unuse_mm() and the intervening walk functions down to
unuse_pte_range() to take the type as a parameter, and to iterate over
their entire range, calling the next function down on every iteration.
In unuse_pte_range(), make a swap entry from each pte in the range using
the passed in type. If it has backing store in the type, call
swapin_readahead() to retrieve the page and pass it to unuse_pte().
Pass the count of pages_to_unuse down the page table walks in
try_to_unuse(), and return from the walk when the desired number of
pages has been swapped back in.
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Vineeth Remanan Pillai <[email protected]>
Signed-off-by: Kelley Nielsen <[email protected]>
Signed-off-by: Huang Ying <[email protected]>
Acked-by: Hugh Dickins <[email protected]>
Cc: Rik van Riel <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
Syzbot with KMSAN reports (excerpt):
==================================================================
BUG: KMSAN: uninit-value in mpol_rebind_policy mm/mempolicy.c:353 [inline]
BUG: KMSAN: uninit-value in mpol_rebind_mm+0x249/0x370 mm/mempolicy.c:384
CPU: 1 PID: 17420 Comm: syz-executor4 Not tainted 4.20.0-rc7+ #15
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS
Google 01/01/2011
Call Trace:
__dump_stack lib/dump_stack.c:77 [inline]
dump_stack+0x173/0x1d0 lib/dump_stack.c:113
kmsan_report+0x12e/0x2a0 mm/kmsan/kmsan.c:613
__msan_warning+0x82/0xf0 mm/kmsan/kmsan_instr.c:295
mpol_rebind_policy mm/mempolicy.c:353 [inline]
mpol_rebind_mm+0x249/0x370 mm/mempolicy.c:384
update_tasks_nodemask+0x608/0xca0 kernel/cgroup/cpuset.c:1120
update_nodemasks_hier kernel/cgroup/cpuset.c:1185 [inline]
update_nodemask kernel/cgroup/cpuset.c:1253 [inline]
cpuset_write_resmask+0x2a98/0x34b0 kernel/cgroup/cpuset.c:1728
...
Uninit was created at:
kmsan_save_stack_with_flags mm/kmsan/kmsan.c:204 [inline]
kmsan_internal_poison_shadow+0x92/0x150 mm/kmsan/kmsan.c:158
kmsan_kmalloc+0xa6/0x130 mm/kmsan/kmsan_hooks.c:176
kmem_cache_alloc+0x572/0xb90 mm/slub.c:2777
mpol_new mm/mempolicy.c:276 [inline]
do_mbind mm/mempolicy.c:1180 [inline]
kernel_mbind+0x8a7/0x31a0 mm/mempolicy.c:1347
__do_sys_mbind mm/mempolicy.c:1354 [inline]
As it's difficult to report where exactly the uninit value resides in
the mempolicy object, we have to guess a bit. mm/mempolicy.c:353
contains this part of mpol_rebind_policy():
if (!mpol_store_user_nodemask(pol) &&
nodes_equal(pol->w.cpuset_mems_allowed, *newmask))
"mpol_store_user_nodemask(pol)" is testing pol->flags, which I couldn't
ever see being uninitialized after leaving mpol_new(). So I'll guess
it's actually about accessing pol->w.cpuset_mems_allowed on line 354,
but still part of statement starting on line 353.
For w.cpuset_mems_allowed to be not initialized, and the nodes_equal()
reachable for a mempolicy where mpol_set_nodemask() is called in
do_mbind(), it seems the only possibility is a MPOL_PREFERRED policy
with empty set of nodes, i.e. MPOL_LOCAL equivalent, with MPOL_F_LOCAL
flag. Let's exclude such policies from the nodes_equal() check. Note
the uninit access should be benign anyway, as rebinding this kind of
policy is always a no-op. Therefore no actual need for stable
inclusion.
Link: http://lkml.kernel.org/r/[email protected]
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Vlastimil Babka <[email protected]>
Reported-by: [email protected]
Cc: Alexander Potapenko <[email protected]>
Cc: Dmitry Vyukov <[email protected]>
Cc: Andrea Arcangeli <[email protected]>
Cc: "Kirill A. Shutemov" <[email protected]>
Cc: Michal Hocko <[email protected]>
Cc: David Rientjes <[email protected]>
Cc: Yisheng Xie <[email protected]>
Cc: zhong jiang <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
If a memory cgroup contains a single process with many threads
(including different process group sharing the mm) then it is possible
to trigger a race when the oom killer complains that there are no oom
elible tasks and complain into the log which is both annoying and
confusing because there is no actual problem. The race looks as
follows:
P1 oom_reaper P2
try_charge try_charge
mem_cgroup_out_of_memory
mutex_lock(oom_lock)
out_of_memory
oom_kill_process(P1,P2)
wake_oom_reaper
mutex_unlock(oom_lock)
oom_reap_task
mutex_lock(oom_lock)
select_bad_process # no victim
The problem is more visible with many threads.
Fix this by checking for fatal_signal_pending from
mem_cgroup_out_of_memory when the oom_lock is already held.
The oom bypass is safe because we do the same early in the try_charge
path already. The situation migh have changed in the mean time. It
should be safe to check for fatal_signal_pending and tsk_is_oom_victim
but for a better code readability abstract the current charge bypass
condition into should_force_charge and reuse it from that path. "
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Tetsuo Handa <[email protected]>
Acked-by: Michal Hocko <[email protected]>
Acked-by: Johannes Weiner <[email protected]>
Cc: David Rientjes <[email protected]>
Cc: Kirill Tkhai <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
There are two early memory allocations that use
memblock_alloc_node_nopanic() and do not check its return value.
While this happens very early during boot and chances that the
allocation will fail are diminishing, it is still worth to have proper
checks for the allocation errors.
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Mike Rapoport <[email protected]>
Reviewed-by: William Kucharski <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
The variable 'addr' is redundant in arch_get_unmapped_area_topdown(),
just use parameter 'addr0' directly. Then remove the const qualifier of
the parameter, and change its name to 'addr'.
And in according with other functions, remove the const qualifier of all
other no-pointer parameters in function arch_get_unmapped_area_topdown().
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Yang Fan <[email protected]>
Reviewed-by: Mike Rapoport <[email protected]>
Cc: William Kucharski <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
Since the start of the git history of Linux, the kernel after selecting
the worst process to be oom-killed, prefer to kill its child (if the
child does not share mm with the parent). Later it was changed to
prefer to kill a child who is worst. If the parent is still the worst
then the parent will be killed.
This heuristic assumes that the children did less work than their parent
and by killing one of them, the work lost will be less. However this is
very workload dependent. If there is a workload which can benefit from
this heuristic, can use oom_score_adj to prefer children to be killed
before the parent.
The select_bad_process() has already selected the worst process in the
system/memcg. There is no need to recheck the badness of its children
and hoping to find a worse candidate. That's a lot of unneeded racy
work. Also the heuristic is dangerous because it make fork bomb like
workloads to recover much later because we constantly pick and kill
processes which are not memory hogs. So, let's remove this whole
heuristic.
[[email protected]: coding-style fixes]
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Shakeel Butt <[email protected]>
Acked-by: Michal Hocko <[email protected]>
Acked-by: Roman Gushchin <[email protected]>
Acked-by: Johannes Weiner <[email protected]>
Cc: David Rientjes <[email protected]>
Cc: Tetsuo Handa <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
It's never appropriate to map a page allocated by SLAB into userspace.
A buggy device driver might try this, or an attacker might be able to
find a way to make it happen.
Christoph said:
: Let's just fail the code. Currently this may work with SLUB. But SLAB
: and SLOB overlay fields with mapcount. So you would have a corrupted page
: struct if you mapped a slab page to user space.
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Matthew Wilcox <[email protected]>
Reviewed-by: Kees Cook <[email protected]>
Acked-by: Pekka Enberg <[email protected]>
Cc: Rik van Riel <[email protected]>
Cc: Christoph Lameter <[email protected]>
Cc: David Rientjes <[email protected]>
Cc: Joonsoo Kim <[email protected]>
Cc: Michael Ellerman <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
One of the vmalloc stress test case triggers the kernel BUG():
<snip>
[60.562151] ------------[ cut here ]------------
[60.562154] kernel BUG at mm/vmalloc.c:512!
[60.562206] invalid opcode: 0000 [#1] PREEMPT SMP PTI
[60.562247] CPU: 0 PID: 430 Comm: vmalloc_test/0 Not tainted 4.20.0+ #161
[60.562293] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1 04/01/2014
[60.562351] RIP: 0010:alloc_vmap_area+0x36f/0x390
<snip>
it can happen due to big align request resulting in overflowing of
calculated address, i.e. it becomes 0 after ALIGN()'s fixup.
Fix it by checking if calculated address is within vstart/vend range.
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Uladzislau Rezki (Sony) <[email protected]>
Reviewed-by: Andrew Morton <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: Joel Fernandes <[email protected]>
Cc: Matthew Wilcox <[email protected]>
Cc: Michal Hocko <[email protected]>
Cc: Oleksiy Avramchenko <[email protected]>
Cc: Steven Rostedt <[email protected]>
Cc: Tejun Heo <[email protected]>
Cc: Thomas Garnier <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
