Add support for MADV_COLLAPSE to collapse shmem-backed and file-backed
memory into THPs (requires CONFIG_READ_ONLY_THP_FOR_FS=y).
On success, the backing memory will be a hugepage. For the memory range
and process provided, the page tables will synchronously have a huge pmd
installed, mapping the THP. Other mappings of the file extent mapped by
the memory range may be added to a set of entries that khugepaged will
later process and attempt update their page tables to map the THP by a
pmd.
This functionality unlocks two important uses:
(1) Immediately back executable text by THPs. Current support provided
by CONFIG_READ_ONLY_THP_FOR_FS may take a long time on a large
system which might impair services from serving at their full rated
load after (re)starting. Tricks like mremap(2)'ing text onto
anonymous memory to immediately realize iTLB performance prevents
page sharing and demand paging, both of which increase steady state
memory footprint. Now, we can have the best of both worlds: Peak
upfront performance and lower RAM footprints.
(2) userfaultfd-based live migration of virtual machines satisfy UFFD
faults by fetching native-sized pages over the network (to avoid
latency of transferring an entire hugepage). However, after guest
memory has been fully copied to the new host, MADV_COLLAPSE can
be used to immediately increase guest performance.
Since khugepaged is single threaded, this change now introduces
possibility of collapse contexts racing in file collapse path. There a
important few places to consider:
(1) hpage_collapse_scan_file(), when we xas_pause() and drop RCU.
We could have the memory collapsed out from under us, but
the next xas_for_each() iteration will correctly pick up the
hugepage. The hugepage might not be up to date (insofar as
copying of small page contents might not have completed - the
page still may be locked), but regardless what small page index
we were iterating over, we'll find the hugepage and identify it
as a suitably aligned compound page of order HPAGE_PMD_ORDER.
In khugepaged path, we locklessly check the value of the pmd,
and only add it to deferred collapse array if we find pmd
mapping pte table. This is fine, since other values that could
have raced in right afterwards denote failure, or that the
memory was successfully collapsed, so we don't need further
processing.
In madvise path, we'll take mmap_lock() in write to serialize
against page table updates and will know what to do based on the
true value of the pmd: recheck all ptes if we point to a pte table,
directly install the pmd, if the pmd has been cleared, but
memory not yet faulted, or nothing at all if we find a huge pmd.
It's worth putting emphasis here on how we treat the none pmd
here. If khugepaged has processed this mm's page tables
already, it will have left the pmd cleared (ready for refault by
the process). Depending on the VMA flags and sysfs settings,
amount of RAM on the machine, and the current load, could be a
relatively common occurrence - and as such is one we'd like to
handle successfully in MADV_COLLAPSE. When we see the none pmd
in collapse_pte_mapped_thp(), we've locked mmap_lock in write
and checked (a) huepaged_vma_check() to see if the backing
memory is appropriate still, along with VMA sizing and
appropriate hugepage alignment within the file, and (b) we've
found a hugepage head of order HPAGE_PMD_ORDER at the offset
in the file mapped by our hugepage-aligned virtual address.
Even though the common-case is likely race with khugepaged,
given these checks (regardless how we got here - we could be
operating on a completely different file than originally checked
in hpage_collapse_scan_file() for all we know) it should be safe
to directly make the pmd a huge pmd pointing to this hugepage.
(2) collapse_file() is mostly serialized on the same file extent by
lock sequence:
| lock hupepage
| lock mapping->i_pages
| lock 1st page
| unlock mapping->i_pages
| <page checks>
| lock mapping->i_pages
| page_ref_freeze(3)
| xas_store(hugepage)
| unlock mapping->i_pages
| page_ref_unfreeze(1)
| unlock 1st page
V unlock hugepage
Once a context (who already has their fresh hugepage locked)
locks mapping->i_pages exclusively, it will hold said lock
until it locks the first page, and it will hold that lock until
the after the hugepage has been added to the page cache (and
will unlock the hugepage after page table update, though that
isn't important here).
A racing context that loses the race for mapping->i_pages will
then lose the race to locking the first page. Here - depending
on how far the other racing context has gotten - we might find
the new hugepage (in which case we'll exit cleanly when we
check PageTransCompound()), or we'll find the "old" 1st small
page (in which we'll exit cleanly when we discover unexpected
refcount of 2 after isolate_lru_page()). This is assuming we
are able to successfully lock the page we find - in shmem path,
we could just fail the trylock and exit cleanly anyways.
Failure path in collapse_file() is similar: once we hold lock
on 1st small page, we are serialized against other collapse
contexts. Before the 1st small page is unlocked, we add it
back to the pagecache and unfreeze the refcount appropriately.
Contexts who lost the race to the 1st small page will then find
the same 1st small page with the correct refcount and will be
able to proceed.
[zokeefe@google.com: don't check pmd value twice in collapse_pte_mapped_thp()]
Link: https://lkml.kernel.org/r/20220927033854.477018-1-zokeefe@google.com
[shy828301@gmail.com: Delete hugepage_vma_revalidate_anon(), remove
check for multi-add in khugepaged_add_pte_mapped_thp()]
Link: https://lore.kernel.org/linux-mm/CAHbLzkrtpM=ic7cYAHcqkubah5VTR8N5=k5RT8MTvv5rN1Y91w@mail.gmail.com/
Link: https://lkml.kernel.org/r/20220907144521.3115321-4-zokeefe@google.com
Link: https://lkml.kernel.org/r/20220922224046.1143204-4-zokeefe@google.com
Signed-off-by: Zach O'Keefe <zokeefe@google.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Chris Kennelly <ckennelly@google.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: James Houghton <jthoughton@google.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Pasha Tatashin <pasha.tatashin@soleen.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Rongwei Wang <rongwei.wang@linux.alibaba.com>
Cc: SeongJae Park <sj@kernel.org>
Cc: Song Liu <songliubraving@fb.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Yang Shi <shy828301@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
The main benefit of THPs are that they can be mapped at the pmd level,
increasing the likelihood of TLB hit and spending less cycles in page
table walks. pte-mapped hugepages - that is - hugepage-aligned compound
pages of order HPAGE_PMD_ORDER mapped by ptes - although being contiguous
in physical memory, don't have this advantage. In fact, one could argue
they are detrimental to system performance overall since they occupy a
precious hugepage-aligned/sized region of physical memory that could
otherwise be used more effectively. Additionally, pte-mapped hugepages
can be the cheapest memory to collapse for khugepaged since no new
hugepage allocation or copying of memory contents is necessary - we only
need to update the mapping page tables.
In the anonymous collapse path, we are able to collapse pte-mapped
hugepages (albeit, perhaps suboptimally), but the file/shmem path makes no
effort when compound pages (of any order) are encountered.
Identify pte-mapped hugepages in the file/shmem collapse path. The
final step of which makes a racy check of the value of the pmd to
ensure it maps a pte table. This should be fine, since races that
result in false-positive (i.e. attempt collapse even though we
shouldn't) will fail later in collapse_pte_mapped_thp() once we
actually lock mmap_lock and reinspect the pmd value. Races that result
in false-negatives (i.e. where we decide to not attempt collapse, but
should have) shouldn't be an issue, since in the worst case, we do
nothing - which is what we've done up to this point. We make a similar
check in retract_page_tables(). If we do think we've found a
pte-mapped hugepgae in khugepaged context, attempt to update page
tables mapping this hugepage.
Note that these collapses still count towards the
/sys/kernel/mm/transparent_hugepage/khugepaged/pages_collapsed counter,
and if the pte-mapped hugepage was also mapped into multiple process'
address spaces, could be incremented for each page table update. Since we
increment the counter when a pte-mapped hugepage is successfully added to
the list of to-collapse pte-mapped THPs, it's possible that we never
actually update the page table either. This is different from how
file/shmem pages_collapsed accounting works today where only a successful
page cache update is counted (it's also possible here that no page tables
are actually changed). Though it incurs some slop, this is preferred to
either not accounting for the event at all, or plumbing through data in
struct mm_slot on whether to account for the collapse or not.
Also note that work still needs to be done to support arbitrary compound
pages, and that this should all be converted to using folios.
[shy828301@gmail.com: Spelling mistake, update comment, and add Documentation]
Link: https://lore.kernel.org/linux-mm/CAHbLzkpHwZxFzjfX9nxVoRhzup8WMjMfyL6Xiq8mZ9M-N3ombw@mail.gmail.com/
Link: https://lkml.kernel.org/r/20220907144521.3115321-3-zokeefe@google.com
Link: https://lkml.kernel.org/r/20220922224046.1143204-3-zokeefe@google.com
Signed-off-by: Zach O'Keefe <zokeefe@google.com>
Reviewed-by: Yang Shi <shy828301@gmail.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Chris Kennelly <ckennelly@google.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: James Houghton <jthoughton@google.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Pasha Tatashin <pasha.tatashin@soleen.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Rongwei Wang <rongwei.wang@linux.alibaba.com>
Cc: SeongJae Park <sj@kernel.org>
Cc: Song Liu <songliubraving@fb.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Patch series "mm: add file/shmem support to MADV_COLLAPSE", v4.
This series builds on top of the previous "mm: userspace hugepage
collapse" series which introduced the MADV_COLLAPSE madvise mode and added
support for private, anonymous mappings[2], by adding support for file and
shmem backed memory to CONFIG_READ_ONLY_THP_FOR_FS=y kernels.
File and shmem support have been added with effort to align with existing
MADV_COLLAPSE semantics and policy decisions[3]. Collapse of shmem-backed
memory ignores kernel-guiding directives and heuristics including all
sysfs settings (transparent_hugepage/shmem_enabled), and tmpfs huge= mount
options (shmem always supports large folios). Like anonymous mappings, on
successful return of MADV_COLLAPSE on file/shmem memory, the contents of
memory mapped by the addresses provided will be synchronously pmd-mapped
THPs.
This functionality unlocks two important uses:
(1) Immediately back executable text by THPs. Current support provided
by CONFIG_READ_ONLY_THP_FOR_FS may take a long time on a large
system which might impair services from serving at their full rated
load after (re)starting. Tricks like mremap(2)'ing text onto
anonymous memory to immediately realize iTLB performance prevents
page sharing and demand paging, both of which increase steady state
memory footprint. Now, we can have the best of both worlds: Peak
upfront performance and lower RAM footprints.
(2) userfaultfd-based live migration of virtual machines satisfy UFFD
faults by fetching native-sized pages over the network (to avoid
latency of transferring an entire hugepage). However, after guest
memory has been fully copied to the new host, MADV_COLLAPSE can
be used to immediately increase guest performance.
khugepaged has received a small improvement by association and can now
detect and collapse pte-mapped THPs. However, there is still work to be
done along the file collapse path. Compound pages of arbitrary order
still needs to be supported and THP collapse needs to be converted to
using folios in general. Eventually, we'd like to move away from the
read-only and executable-mapped constraints currently imposed on eligible
files and support any inode claiming huge folio support. That said, I
think the series as-is covers enough to claim that MADV_COLLAPSE supports
file/shmem memory.
Patches 1-3 Implement the guts of the series.
Patch 4 Is a tracepoint for debugging.
Patches 5-9 Refactor existing khugepaged selftests to work with new
memory types + new collapse tests.
Patch 10 Adds a userfaultfd selftest mode to mimic a functional test
of UFFDIO_REGISTER_MODE_MINOR+MADV_COLLAPSE live migration.
(v4 note: "userfaultfd shmem" selftest is failing as of
Sep 22 mm-unstable)
[1] https://lore.kernel.org/linux-mm/YyiK8YvVcrtZo0z3@google.com/
[2] https://lore.kernel.org/linux-mm/20220706235936.2197195-1-zokeefe@google.com/
[3] https://lore.kernel.org/linux-mm/YtBmhaiPHUTkJml8@google.com/
[4] https://lore.kernel.org/linux-mm/20220922222731.1124481-1-zokeefe@google.com/
[5] https://lore.kernel.org/linux-mm/20220922184651.1016461-1-zokeefe@google.com/
This patch (of 10):
Extend 'mm/thp: add flag to enforce sysfs THP in hugepage_vma_check()' to
shmem, allowing callers to ignore
/sys/kernel/transparent_hugepage/shmem_enabled and tmpfs huge= mount.
This is intended to be used by MADV_COLLAPSE, and the rationale is
analogous to the anon/file case: MADV_COLLAPSE is not coupled to
directives that advise the kernel's decisions on when THPs should be
considered eligible. shmem/tmpfs always claims large folio support,
regardless of sysfs or mount options.
[shy828301@gmail.com: test shmem_huge_force explicitly]
Link: https://lore.kernel.org/linux-mm/CAHbLzko3A5-TpS0BgBeKkx5cuOkWgLvWXQH=TdgW-baO4rPtdg@mail.gmail.com/
Link: https://lkml.kernel.org/r/20220922224046.1143204-1-zokeefe@google.com
Link: https://lkml.kernel.org/r/20220907144521.3115321-2-zokeefe@google.com
Link: https://lkml.kernel.org/r/20220922224046.1143204-2-zokeefe@google.com
Signed-off-by: Zach O'Keefe <zokeefe@google.com>
Reviewed-by: Yang Shi <shy828301@gmail.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Chris Kennelly <ckennelly@google.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: James Houghton <jthoughton@google.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Pasha Tatashin <pasha.tatashin@soleen.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Rongwei Wang <rongwei.wang@linux.alibaba.com>
Cc: SeongJae Park <sj@kernel.org>
Cc: Song Liu <songliubraving@fb.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
MADV_COLLAPSE is a best-effort request that attempts to set an actionable
errno value if the request cannot be fulfilled at the time. EAGAIN should
be used to communicate that a resource was temporarily unavailable, but
that the user may try again immediately.
SCAN_DEL_PAGE_LRU is an internal result code used when a page cannot be
isolated from it's LRU list. Since this, like SCAN_PAGE_LRU, is likely a
transitory state, make MADV_COLLAPSE return EAGAIN so that users know they
may reattempt the operation.
Another important scenario to consider is race with khugepaged.
khugepaged might isolate a page while MADV_COLLAPSE is interested in it.
Even though racing with khugepaged might mean that the memory has already
been collapsed, signalling an errno that is non-intrinsic to that memory
or arguments provided to madvise(2) lets the user know that future
attempts might (and in this case likely would) succeed, and avoids
false-negative assumptions by the user.
Link: https://lkml.kernel.org/r/20220922184651.1016461-1-zokeefe@google.com
Fixes: 7d8faaf155 ("mm/madvise: introduce MADV_COLLAPSE sync hugepage collapse")
Signed-off-by: Zach O'Keefe <zokeefe@google.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Chris Kennelly <ckennelly@google.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: James Houghton <jthoughton@google.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Pasha Tatashin <pasha.tatashin@soleen.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Rongwei Wang <rongwei.wang@linux.alibaba.com>
Cc: SeongJae Park <sj@kernel.org>
Cc: Song Liu <songliubraving@fb.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Yang Shi <shy828301@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Patch series "mm: memcontrol: cleanup and optimize for two accounting
params", v2.
This patch (of 2):
There are currently two helpers for checking if cgroup kmem
accounting is enabled:
- mem_cgroup_kmem_disabled
- memcg_kmem_enabled
mem_cgroup_kmem_disabled is a simple helper that returns true
if cgroup.memory=nokmem is specified, otherwise returns false.
memcg_kmem_enabled is a bit different, it returns true if
cgroup.memory=nokmem is not specified and there was at least one
non-root memory control enabled cgroup ever created. This help improve
performance when kmem accounting was not actually activated. And it's
optimized with static branch.
The usage of mem_cgroup_kmem_disabled is for sub-systems that need to
preallocate data for kmem accounting since they could be initialized
before kmem accounting is activated. But count_objcg_event doesn't
need that, so using memcg_kmem_enabled is better here.
Link: https://lkml.kernel.org/r/20220919180634.45958-1-ryncsn@gmail.com
Link: https://lkml.kernel.org/r/20220919180634.45958-2-ryncsn@gmail.com
Signed-off-by: Kairui Song <kasong@tencent.com>
Acked-by: Shakeel Butt <shakeelb@google.com>
Acked-by: Roman Gushchin <roman.gushchin@linux.dev>
Acked-by: Muchun Song <songmuchun@bytedance.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
When creating hugetlb pages, the hugetlb code must first allocate
contiguous pages from a low level allocator such as buddy, cma or
memblock. The pages returned from these low level allocators are ref
counted. This creates potential issues with other code taking speculative
references on these pages before they can be transformed to a hugetlb
page. This issue has been addressed with methods and code such as that
provided in [1].
Recent discussions about vmemmap freeing [2] have indicated that it would
be beneficial to freeze all sub pages, including the head page of pages
returned from low level allocators before converting to a hugetlb page.
This helps avoid races if we want to replace the page containing vmemmap
for the head page.
There have been proposals to change at least the buddy allocator to return
frozen pages as described at [3]. If such a change is made, it can be
employed by the hugetlb code. However, as mentioned above hugetlb uses
several low level allocators so each would need to be modified to return
frozen pages. For now, we can manually freeze the returned pages. This
is done in two places:
1) alloc_buddy_huge_page, only the returned head page is ref counted.
We freeze the head page, retrying once in the VERY rare case where
there may be an inflated ref count.
2) prep_compound_gigantic_page, for gigantic pages the current code
freezes all pages except the head page. New code will simply freeze
the head page as well.
In a few other places, code checks for inflated ref counts on newly
allocated hugetlb pages. With the modifications to freeze after
allocating, this code can be removed.
After hugetlb pages are freshly allocated, they are often added to the
hugetlb free lists. Since these pages were previously ref counted, this
was done via put_page() which would end up calling the hugetlb destructor:
free_huge_page. With changes to freeze pages, we simply call
free_huge_page directly to add the pages to the free list.
In a few other places, freshly allocated hugetlb pages were immediately
put into use, and the expectation was they were already ref counted. In
these cases, we must manually ref count the page.
[1] https://lore.kernel.org/linux-mm/20210622021423.154662-3-mike.kravetz@oracle.com/
[2] https://lore.kernel.org/linux-mm/20220802180309.19340-1-joao.m.martins@oracle.com/
[3] https://lore.kernel.org/linux-mm/20220809171854.3725722-1-willy@infradead.org/
[mike.kravetz@oracle.com: fix NULL pointer dereference]
Link: https://lkml.kernel.org/r/20220921202702.106069-1-mike.kravetz@oracle.com
Link: https://lkml.kernel.org/r/20220916214638.155744-1-mike.kravetz@oracle.com
Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com>
Reviewed-by: Oscar Salvador <osalvador@suse.de>
Reviewed-by: Muchun Song <songmuchun@bytedance.com>
Reviewed-by: Miaohe Lin <linmiaohe@huawei.com>
Cc: Joao Martins <joao.m.martins@oracle.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Peter Xu <peterx@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
In MIGRATE_ISOLATE case, zone freepage state shouldn't be modified as
caller will take care of it. Add missing is_migrate_isolate() here to
avoid possible unbalanced freepage state. This would happen if someone
isolates the block, and then we face an MCE failure/soft-offline on a page
within that block. __mod_zone_freepage_state() will be triggered via
below call trace which already had been triggered back when block was
isolated:
take_page_off_buddy
break_down_buddy_pages
set_page_guard
Link: https://lkml.kernel.org/r/20220916072257.9639-9-linmiaohe@huawei.com
Fixes: 06be6ff3d2 ("mm,hwpoison: rework soft offline for free pages")
Signed-off-by: Miaohe Lin <linmiaohe@huawei.com>
Reviewed-by: Oscar Salvador <osalvador@suse.de>
Reviewed-by: David Hildenbrand <david@redhat.com>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Matthew Wilcox <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Patch series "A few cleanup patches for mm", v2.
This series contains a few cleanup patches to remove the obsolete comments
and functions, use helper macro to improve readability and so on. More
details can be found in the respective changelogs.
This patch (of 16):
If ALLOC_KSWAPD is set, wake_all_kswapds() will be called to ensure kswapd
doesn't accidentally go to sleep. But when reserve_flags is set,
alloc_flags will be overwritten and ALLOC_KSWAPD is thus lost. Preserve
the ALLOC_KSWAPD flag in alloc_flags to ensure kswapd won't go to sleep
accidentally.
Link: https://lkml.kernel.org/r/20220916072257.9639-1-linmiaohe@huawei.com
Link: https://lkml.kernel.org/r/20220916072257.9639-2-linmiaohe@huawei.com
Fixes: 0a79cdad5e ("mm: use alloc_flags to record if kswapd can wake")
Signed-off-by: Miaohe Lin <linmiaohe@huawei.com>
Acked-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Oscar Salvador <osalvador@suse.de>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Matthew Wilcox <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
