radix tree test suite: fix allocation calculation in kmem_cache_alloc_bulk()
The bulk allocation is iterating through an array and storing enough
memory for the entire bulk allocation instead of a single array entry.
Only allocate an array element of the size set in the kmem_cache.
Link: https://lkml.kernel.org/r/20230929201359.2857583-1-Liam.Howlett@oracle.com Fixes: cc86e0c2f306 ("radix tree test suite: add support for slab bulk APIs") Signed-off-by: Liam R. Howlett <Liam.Howlett@oracle.com> Reported-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Add pagemap ioctl tests. Add several different types of tests to judge
the correction of the interface.
Link: https://lkml.kernel.org/r/20230821141518.870589-7-usama.anjum@collabora.com Signed-off-by: Muhammad Usama Anjum <usama.anjum@collabora.com> Cc: Alex Sierra <alex.sierra@amd.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Andrei Vagin <avagin@gmail.com> Cc: Axel Rasmussen <axelrasmussen@google.com> Cc: Christian Brauner <brauner@kernel.org> Cc: Cyrill Gorcunov <gorcunov@gmail.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: David Hildenbrand <david@redhat.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Gustavo A. R. Silva <gustavoars@kernel.org> Cc: "Liam R. Howlett" <Liam.Howlett@oracle.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Michal Miroslaw <emmir@google.com> Cc: Michał Mirosław <mirq-linux@rere.qmqm.pl> Cc: Mike Rapoport (IBM) <rppt@kernel.org> Cc: Nadav Amit <namit@vmware.com> Cc: Pasha Tatashin <pasha.tatashin@soleen.com> Cc: Paul Gofman <pgofman@codeweavers.com> Cc: Peter Xu <peterx@redhat.com> Cc: Shuah Khan <shuah@kernel.org> Cc: Suren Baghdasaryan <surenb@google.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Yang Shi <shy828301@gmail.com> Cc: Yun Zhou <yun.zhou@windriver.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
mm/pagemap: add documentation of PAGEMAP_SCAN IOCTL
Add some explanation and method to use write-protection and written-to
on memory range.
Link: https://lkml.kernel.org/r/20230821141518.870589-6-usama.anjum@collabora.com Signed-off-by: Muhammad Usama Anjum <usama.anjum@collabora.com> Cc: Alex Sierra <alex.sierra@amd.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Andrei Vagin <avagin@gmail.com> Cc: Axel Rasmussen <axelrasmussen@google.com> Cc: Christian Brauner <brauner@kernel.org> Cc: Cyrill Gorcunov <gorcunov@gmail.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: David Hildenbrand <david@redhat.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Gustavo A. R. Silva <gustavoars@kernel.org> Cc: "Liam R. Howlett" <Liam.Howlett@oracle.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Michal Miroslaw <emmir@google.com> Cc: Michał Mirosław <mirq-linux@rere.qmqm.pl> Cc: Mike Rapoport (IBM) <rppt@kernel.org> Cc: Nadav Amit <namit@vmware.com> Cc: Pasha Tatashin <pasha.tatashin@soleen.com> Cc: Paul Gofman <pgofman@codeweavers.com> Cc: Peter Xu <peterx@redhat.com> Cc: Shuah Khan <shuah@kernel.org> Cc: Suren Baghdasaryan <surenb@google.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Yang Shi <shy828301@gmail.com> Cc: Yun Zhou <yun.zhou@windriver.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
tools headers UAPI: update linux/fs.h with the kernel sources
New IOCTL and macros has been added in the kernel sources. Update the
tools header file as well.
Link: https://lkml.kernel.org/r/20230821141518.870589-5-usama.anjum@collabora.com Signed-off-by: Muhammad Usama Anjum <usama.anjum@collabora.com> Cc: Alex Sierra <alex.sierra@amd.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Andrei Vagin <avagin@gmail.com> Cc: Axel Rasmussen <axelrasmussen@google.com> Cc: Christian Brauner <brauner@kernel.org> Cc: Cyrill Gorcunov <gorcunov@gmail.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: David Hildenbrand <david@redhat.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Gustavo A. R. Silva <gustavoars@kernel.org> Cc: "Liam R. Howlett" <Liam.Howlett@oracle.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Michal Miroslaw <emmir@google.com> Cc: Michał Mirosław <mirq-linux@rere.qmqm.pl> Cc: Mike Rapoport (IBM) <rppt@kernel.org> Cc: Nadav Amit <namit@vmware.com> Cc: Pasha Tatashin <pasha.tatashin@soleen.com> Cc: Paul Gofman <pgofman@codeweavers.com> Cc: Peter Xu <peterx@redhat.com> Cc: Shuah Khan <shuah@kernel.org> Cc: Suren Baghdasaryan <surenb@google.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Yang Shi <shy828301@gmail.com> Cc: Yun Zhou <yun.zhou@windriver.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
fs/proc/task_mmu: add fast paths to get/clear PAGE_IS_WRITTEN flag
Adding fast code paths to handle specifically only get and/or clear
operation of PAGE_IS_WRITTEN, increases its performance by 0-35%. The
results of some test cases are given below:
Test-case-1
t1 = (Get + WP) time
t2 = WP time
t1 t2
Without this patch: 140-170mcs 90-115mcs
With this patch: 110mcs 80mcs
Worst case diff: 35% faster 30% faster
Test-case-2
t3 = atomic Get and WP
t3
Without this patch: 120-140mcs
With this patch: 100-110mcs
Worst case diff: 21% faster
Link: https://lkml.kernel.org/r/20230821141518.870589-4-usama.anjum@collabora.com Signed-off-by: Muhammad Usama Anjum <usama.anjum@collabora.com> Cc: Alex Sierra <alex.sierra@amd.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Andrei Vagin <avagin@gmail.com> Cc: Axel Rasmussen <axelrasmussen@google.com> Cc: Christian Brauner <brauner@kernel.org> Cc: Cyrill Gorcunov <gorcunov@gmail.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: David Hildenbrand <david@redhat.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Gustavo A. R. Silva <gustavoars@kernel.org> Cc: "Liam R. Howlett" <Liam.Howlett@oracle.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Michal Miroslaw <emmir@google.com> Cc: Michał Mirosław <mirq-linux@rere.qmqm.pl> Cc: Mike Rapoport (IBM) <rppt@kernel.org> Cc: Nadav Amit <namit@vmware.com> Cc: Pasha Tatashin <pasha.tatashin@soleen.com> Cc: Paul Gofman <pgofman@codeweavers.com> Cc: Peter Xu <peterx@redhat.com> Cc: Shuah Khan <shuah@kernel.org> Cc: Suren Baghdasaryan <surenb@google.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Yang Shi <shy828301@gmail.com> Cc: Yun Zhou <yun.zhou@windriver.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
fs/proc/task_mmu: implement IOCTL to get and optionally clear info about PTEs
The PAGEMAP_SCAN IOCTL on the pagemap file can be used to get or optionally
clear the info about page table entries. The following operations are
supported in this IOCTL:
- Scan the address range and get the memory ranges matching the provided
criteria. This is performed when the output buffer is specified.
- Write-protect the pages. The PM_SCAN_WP_MATCHING is used to write-protect
the pages of interest. The PM_SCAN_CHECK_WPASYNC aborts the operation if
non-Async Write Protected pages are found. The ``PM_SCAN_WP_MATCHING``
can be used with or without PM_SCAN_CHECK_WPASYNC.
- Both of those operations can be combined into one atomic operation where
we can get and write protect the pages as well.
Following flags about pages are currently supported:
- PAGE_IS_WPALLOWED - Page has async-write-protection enabled
- PAGE_IS_WRITTEN - Page has been written to from the time it was write protected
- PAGE_IS_FILE - Page is file backed
- PAGE_IS_PRESENT - Page is present in the memory
- PAGE_IS_SWAPPED - Page is in swapped
- PAGE_IS_PFNZERO - Page has zero PFN
- PAGE_IS_HUGE - Page is THP or Hugetlb backed
This IOCTL can be extended to get information about more PTE bits. The
entire address range passed by user [start, end) is scanned until either
the user provided buffer is full or max_pages have been found.
[akpm@linux-foundation.org: update it for "mm: hugetlb: add huge page size param to set_huge_pte_at()"]
[akpm@linux-foundation.org: fix CONFIG_HUGETLB_PAGE=n warning]
[arnd@arndb.de: hide unused pagemap_scan_backout_range() function] Link: https://lkml.kernel.org/r/20230927060257.2975412-1-arnd@kernel.org
[sfr@canb.auug.org.au: fix "fs/proc/task_mmu: hide unused pagemap_scan_backout_range() function"] Link: https://lkml.kernel.org/r/20230928092223.0625c6bf@canb.auug.org.au Link: https://lkml.kernel.org/r/20230821141518.870589-3-usama.anjum@collabora.com Signed-off-by: Muhammad Usama Anjum <usama.anjum@collabora.com> Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl> Signed-off-by: Arnd Bergmann <arnd@arndb.de> Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au> Reviewed-by: Andrei Vagin <avagin@gmail.com> Reviewed-by: Michał Mirosław <mirq-linux@rere.qmqm.pl> Cc: Alex Sierra <alex.sierra@amd.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Axel Rasmussen <axelrasmussen@google.com> Cc: Christian Brauner <brauner@kernel.org> Cc: Cyrill Gorcunov <gorcunov@gmail.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: David Hildenbrand <david@redhat.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Gustavo A. R. Silva <gustavoars@kernel.org> Cc: "Liam R. Howlett" <Liam.Howlett@oracle.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Michal Miroslaw <emmir@google.com> Cc: Mike Rapoport (IBM) <rppt@kernel.org> Cc: Nadav Amit <namit@vmware.com> Cc: Pasha Tatashin <pasha.tatashin@soleen.com> Cc: Paul Gofman <pgofman@codeweavers.com> Cc: Peter Xu <peterx@redhat.com> Cc: Shuah Khan <shuah@kernel.org> Cc: Suren Baghdasaryan <surenb@google.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Yang Shi <shy828301@gmail.com> Cc: Yun Zhou <yun.zhou@windriver.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Peter Xu [Mon, 21 Aug 2023 14:15:13 +0000 (19:15 +0500)]
userfaultfd: UFFD_FEATURE_WP_ASYNC
Patch series "Implement IOCTL to get and optionally clear info about
PTEs", v33.
*Motivation*
The real motivation for adding PAGEMAP_SCAN IOCTL is to emulate Windows
GetWriteWatch() and ResetWriteWatch() syscalls [1]. The GetWriteWatch()
retrieves the addresses of the pages that are written to in a region of
virtual memory.
This syscall is used in Windows applications and games etc. This syscall
is being emulated in pretty slow manner in userspace. Our purpose is to
enhance the kernel such that we translate it efficiently in a better way.
Currently some out of tree hack patches are being used to efficiently
emulate it in some kernels. We intend to replace those with these
patches. So the whole gaming on Linux can effectively get benefit from
this. It means there would be tons of users of this code.
CRIU use case [2] was mentioned by Andrei and Danylo:
> Use cases for migrating sparse VMAs are binaries sanitized with ASAN,
> MSAN or TSAN [3]. All of these sanitizers produce sparse mappings of
> shadow memory [4]. Being able to migrate such binaries allows to highly
> reduce the amount of work needed to identify and fix post-migration
> crashes, which happen constantly.
Andrei defines the following uses of this code:
* it is more granular and allows us to track changed pages more
effectively. The current interface can clear dirty bits for the entire
process only. In addition, reading info about pages is a separate
operation. It means we must freeze the process to read information
about all its pages, reset dirty bits, only then we can start dumping
pages. The information about pages becomes more and more outdated,
while we are processing pages. The new interface solves both these
downsides. First, it allows us to read pte bits and clear the
soft-dirty bit atomically. It means that CRIU will not need to freeze
processes to pre-dump their memory. Second, it clears soft-dirty bits
for a specified region of memory. It means CRIU will have actual info
about pages to the moment of dumping them.
* The new interface has to be much faster because basic page filtering
is happening in the kernel. With the old interface, we have to read
pagemap for each page.
*Implementation Evolution (Short Summary)*
From the definition of GetWriteWatch(), we feel like kernel's soft-dirty
feature can be used under the hood with some additions like:
* reset soft-dirty flag for only a specific region of memory instead of
clearing the flag for the entire process
* get and clear soft-dirty flag for a specific region atomically
So we decided to use ioctl on pagemap file to read or/and reset soft-dirty
flag. But using soft-dirty flag, sometimes we get extra pages which weren't
even written. They had become soft-dirty because of VMA merging and
VM_SOFTDIRTY flag. This breaks the definition of GetWriteWatch(). We were
able to by-pass this short coming by ignoring VM_SOFTDIRTY until David
reported that mprotect etc messes up the soft-dirty flag while ignoring
VM_SOFTDIRTY [5]. This wasn't happening until [6] got introduced. We
discussed if we can revert these patches. But we could not reach to any
conclusion. So at this point, I made couple of tries to solve this whole
VM_SOFTDIRTY issue by correcting the soft-dirty implementation:
* [7] Correct the bug fixed wrongly back in 2014. It had potential to cause
regression. We left it behind.
* [8] Keep a list of soft-dirty part of a VMA across splits and merges. I
got the reply don't increase the size of the VMA by 8 bytes.
At this point, we left soft-dirty considering it is too much delicate and
userfaultfd [9] seemed like the only way forward. From there onward, we
have been basing soft-dirty emulation on userfaultfd wp feature where
kernel resolves the faults itself when WP_ASYNC feature is used. It was
straight forward to add WP_ASYNC feature in userfautlfd. Now we get only
those pages dirty or written-to which are really written in reality. (PS
There is another WP_UNPOPULATED userfautfd feature is required which is
needed to avoid pre-faulting memory before write-protecting [9].)
All the different masks were added on the request of CRIU devs to create
interface more generic and better.
Add a new userfaultfd-wp feature UFFD_FEATURE_WP_ASYNC, that allows
userfaultfd wr-protect faults to be resolved by the kernel directly.
It can be used like a high accuracy version of soft-dirty, without vma
modifications during tracking, and also with ranged support by default
rather than for a whole mm when reset the protections due to existence of
ioctl(UFFDIO_WRITEPROTECT).
Several goals of such a dirty tracking interface:
1. All types of memory should be supported and tracable. This is nature
for soft-dirty but should mention when the context is userfaultfd,
because it used to only support anon/shmem/hugetlb. The problem is for
a dirty tracking purpose these three types may not be enough, and it's
legal to track anything e.g. any page cache writes from mmap.
2. Protections can be applied to partial of a memory range, without vma
split/merge fuss. The hope is that the tracking itself should not
affect any vma layout change. It also helps when reset happens because
the reset will not need mmap write lock which can block the tracee.
3. Accuracy needs to be maintained. This means we need pte markers to work
on any type of VMA.
One could question that, the whole concept of async dirty tracking is not
really close to fundamentally what userfaultfd used to be: it's not "a
fault to be serviced by userspace" anymore. However, using userfaultfd-wp
here as a framework is convenient for us in at least:
1. VM_UFFD_WP vma flag, which has a very good name to suite something like
this, so we don't need VM_YET_ANOTHER_SOFT_DIRTY. Just use a new
feature bit to identify from a sync version of uffd-wp registration.
2. PTE markers logic can be leveraged across the whole kernel to maintain
the uffd-wp bit as long as an arch supports, this also applies to this
case where uffd-wp bit will be a hint to dirty information and it will
not go lost easily (e.g. when some page cache ptes got zapped).
3. Reuse ioctl(UFFDIO_WRITEPROTECT) interface for either starting or
resetting a range of memory, while there's no counterpart in the old
soft-dirty world, hence if this is wanted in a new design we'll need a
new interface otherwise.
We can somehow understand that commonality because uffd-wp was
fundamentally a similar idea of write-protecting pages just like
soft-dirty.
This implementation allows WP_ASYNC to imply WP_UNPOPULATED, because so
far WP_ASYNC seems to not usable if without WP_UNPOPULATE. This also
gives us chance to modify impl of WP_ASYNC just in case it could be not
depending on WP_UNPOPULATED anymore in the future kernels. It's also fine
to imply that because both features will rely on PTE_MARKER_UFFD_WP config
option, so they'll show up together (or both missing) in an UFFDIO_API
probe.
vma_can_userfault() now allows any VMA if the userfaultfd registration is
only about async uffd-wp. So we can track dirty for all kinds of memory
including generic file systems (like XFS, EXT4 or BTRFS).
One trick worth mention in do_wp_page() is that we need to manually update
vmf->orig_pte here because it can be used later with a pte_same() check -
this path always has FAULT_FLAG_ORIG_PTE_VALID set in the flags.
The major defect of this approach of dirty tracking is we need to populate
the pgtables when tracking starts. Soft-dirty doesn't do it like that.
It's unwanted in the case where the range of memory to track is huge and
unpopulated (e.g., tracking updates on a 10G file with mmap() on top,
without having any page cache installed yet). One way to improve this is
to allow pte markers exist for larger than PTE level for PMD+. That will
not change the interface if to implemented, so we can leave that for
later.
Link: https://lkml.kernel.org/r/20230821141518.870589-1-usama.anjum@collabora.com Link: https://lkml.kernel.org/r/20230821141518.870589-2-usama.anjum@collabora.com Signed-off-by: Peter Xu <peterx@redhat.com> Co-developed-by: Muhammad Usama Anjum <usama.anjum@collabora.com> Signed-off-by: Muhammad Usama Anjum <usama.anjum@collabora.com> Cc: Alex Sierra <alex.sierra@amd.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Andrei Vagin <avagin@gmail.com> Cc: Axel Rasmussen <axelrasmussen@google.com> Cc: Christian Brauner <brauner@kernel.org> Cc: Cyrill Gorcunov <gorcunov@gmail.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: David Hildenbrand <david@redhat.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Gustavo A. R. Silva <gustavoars@kernel.org> Cc: "Liam R. Howlett" <Liam.Howlett@oracle.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Michal Miroslaw <emmir@google.com> Cc: Mike Rapoport (IBM) <rppt@kernel.org> Cc: Nadav Amit <namit@vmware.com> Cc: Pasha Tatashin <pasha.tatashin@soleen.com> Cc: Paul Gofman <pgofman@codeweavers.com> Cc: Shuah Khan <shuah@kernel.org> Cc: Suren Baghdasaryan <surenb@google.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Yang Shi <shy828301@gmail.com> Cc: Yun Zhou <yun.zhou@windriver.com> Cc: Michał Mirosław <mirq-linux@rere.qmqm.pl> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Yosry Ahmed [Fri, 22 Sep 2023 17:57:40 +0000 (17:57 +0000)]
mm: memcg: normalize the value passed into memcg_rstat_updated()
memcg_rstat_updated() uses the value of the state update to keep track of
the magnitude of pending updates, so that we only do a stats flush when
it's worth the work. Most values passed into memcg_rstat_updated() are in
pages, however, a few of them are actually in bytes or KBs.
To put this into perspective, a 512 byte slab allocation today would look
the same as allocating 512 pages. This may result in premature flushes,
which means unnecessary work and latency.
Normalize all the state values passed into memcg_rstat_updated() to pages.
Round up non-zero sub-page to 1 page, because memcg_rstat_updated()
ignores 0 page updates.
Link: https://lkml.kernel.org/r/20230922175741.635002-3-yosryahmed@google.com Fixes: 5b3be698a872 ("memcg: better bounds on the memcg stats updates") Signed-off-by: Yosry Ahmed <yosryahmed@google.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Cc: Michal Hocko <mhocko@kernel.org> Cc: Michal Koutný <mkoutny@suse.com> Cc: Muchun Song <muchun.song@linux.dev> Cc: Roman Gushchin <roman.gushchin@linux.dev> Cc: Shakeel Butt <shakeelb@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Yosry Ahmed [Fri, 22 Sep 2023 17:57:39 +0000 (17:57 +0000)]
mm: memcg: refactor page state unit helpers
Patch series "mm: memcg: fix tracking of pending stats updates values", v2.
While working on adjacent code [1], I realized that the values passed into
memcg_rstat_updated() to keep track of the magnitude of pending updates is
consistent. It is mostly in pages, but sometimes it can be in bytes or
KBs. Fix that.
Patch 1 reworks memcg_page_state_unit() so that we can reuse it in patch 2
to check and normalize the units of state updates.
memcg_page_state_unit() is currently used to identify the unit of a memcg
state item so that all stats in memory.stat are in bytes. However, it
lies about the units of WORKINGSET_* stats. These stats actually
represent pages, but we present them to userspace as a scalar number of
events. In retrospect, maybe those stats should have been memcg "events"
rather than memcg "state".
In preparation for using memcg_page_state_unit() for other purposes that
need to know the truthful units of different stat items, break it down
into two helpers:
- memcg_page_state_unit() retuns the actual unit of the item.
- memcg_page_state_output_unit() returns the unit used for output.
Use the latter instead of the former in memcg_page_state_output() and
lruvec_page_state_output(). While we are at it, let's show cgroup v1 some
love and add memcg_page_state_local_output() for consistency.
mm/memcg: annotate struct mem_cgroup_threshold_ary with __counted_by
Prepare for the coming implementation by GCC and Clang of the __counted_by
attribute. Flexible array members annotated with __counted_by can have
their accesses bounds-checked at run-time checking via CONFIG_UBSAN_BOUNDS
(for array indexing) and CONFIG_FORTIFY_SOURCE (for strcpy/memcpy-family
functions).
As found with Coccinelle[1], add __counted_by for struct
mem_cgroup_threshold_ary.
Mike Kravetz [Tue, 17 Oct 2023 02:55:49 +0000 (19:55 -0700)]
hugetlb: check for hugetlb folio before vmemmap_restore
In commit d8f5f7e445f0 ("hugetlb: set hugetlb page flag before
optimizing vmemmap") checks were added to print a warning if
hugetlb_vmemmap_restore was called on a non-hugetlb page.
This was mostly due to ordering issues in the hugetlb page set up and tear
down sequencees. One place missed was the routine
dissolve_free_huge_page.
Naoya Horiguchi noted: "I saw that VM_WARN_ON_ONCE() in
hugetlb_vmemmap_restore is triggered when memory_failure() is called on a
free hugetlb page with vmemmap optimization disabled (the warning is not
triggered if vmemmap optimization is enabled). I think that we need check
folio_test_hugetlb() before dissolve_free_huge_page() calls
hugetlb_vmemmap_restore_folio()."
Perform the check as suggested by Naoya.
Link: https://lkml.kernel.org/r/20231017032140.GA3680@monkey Fixes: d8f5f7e445f0 ("hugetlb: set hugetlb page flag before optimizing vmemmap") Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com> Suggested-by: Naoya Horiguchi <naoya.horiguchi@linux.dev> Tested-by: Naoya Horiguchi <naoya.horiguchi@linux.dev> Cc: Anshuman Khandual <anshuman.khandual@arm.com> Cc: Barry Song <song.bao.hua@hisilicon.com> Cc: David Hildenbrand <david@redhat.com> Cc: David Rientjes <rientjes@google.com> Cc: Joao Martins <joao.m.martins@oracle.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Miaohe Lin <linmiaohe@huawei.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Muchun Song <songmuchun@bytedance.com> Cc: Oscar Salvador <osalvador@suse.de> Cc: Xiongchun Duan <duanxiongchun@bytedance.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Tiezhu Yang [Tue, 11 Jul 2023 09:13:34 +0000 (17:13 +0800)]
selftests/clone3: Fix broken test under !CONFIG_TIME_NS
When execute the following command to test clone3 under !CONFIG_TIME_NS:
# make headers && cd tools/testing/selftests/clone3 && make && ./clone3
we can see the following error info:
# [7538] Trying clone3() with flags 0x80 (size 0)
# Invalid argument - Failed to create new process
# [7538] clone3() with flags says: -22 expected 0
not ok 18 [7538] Result (-22) is different than expected (0)
...
# Totals: pass:18 fail:1 xfail:0 xpass:0 skip:0 error:0
This is because if CONFIG_TIME_NS is not set, but the flag
CLONE_NEWTIME (0x80) is used to clone a time namespace, it
will return -EINVAL in copy_time_ns().
If kernel does not support CONFIG_TIME_NS, /proc/self/ns/time
will be not exist, and then we should skip clone3() test with
CLONE_NEWTIME.
With this patch under !CONFIG_TIME_NS:
# make headers && cd tools/testing/selftests/clone3 && make && ./clone3
...
# Time namespaces are not supported
ok 18 # SKIP Skipping clone3() with CLONE_NEWTIME
...
# Totals: pass:18 fail:0 xfail:0 xpass:0 skip:1 error:0
Link: https://lkml.kernel.org/r/1689066814-13295-1-git-send-email-yangtiezhu@loongson.cn Fixes: 515bddf0ec41 ("selftests/clone3: test clone3 with CLONE_NEWTIME") Signed-off-by: Tiezhu Yang <yangtiezhu@loongson.cn> Suggested-by: Thomas Gleixner <tglx@linutronix.de> Cc: Christian Brauner <brauner@kernel.org> Cc: Shuah Khan <shuah@kernel.org> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Liam R. Howlett [Thu, 12 Oct 2023 15:52:33 +0000 (11:52 -0400)]
maple_tree: add GFP_KERNEL to allocations in mas_expected_entries()
Users complained about OOM errors during fork without triggering
compaction. This can be fixed by modifying the flags used in
mas_expected_entries() so that the compaction will be triggered in low
memory situations. Since mas_expected_entries() is only used during fork,
the extra argument does not need to be passed through.
Additionally, the two test_maple_tree test cases and one benchmark test
were altered to use the correct locking type so that allocations would not
trigger sleeping and thus fail. Testing was completed with lockdep atomic
sleep detection.
The additional locking change requires rwsem support additions to the
tools/ directory through the use of pthreads pthread_rwlock_t. With this
change test_maple_tree works in userspace, as a module, and in-kernel.
Users may notice that the system gave up early on attempting to start new
processes instead of attempting to reclaim memory.
selftests/mm: include mman header to access MREMAP_DONTUNMAP identifier
Definition for MREMAP_DONTUNMAP is not present in glibc older than 2.32
thus throwing an undeclared error when running make on mm. Including
linux/mman.h solves the build error for people having older glibc.
Oleksij Rempel [Wed, 11 Oct 2023 11:25:19 +0000 (13:25 +0200)]
mailmap: correct email aliasing for Oleksij Rempel
Ensure the current work email addresses for Oleksij Rempel are preserved
and not overridden by private address. Alias the alternate work email to
the primary work email address.
Link: https://lkml.kernel.org/r/20231011112519.1427077-1-o.rempel@pengutronix.de Signed-off-by: Oleksij Rempel <o.rempel@pengutronix.de> Cc: Jakub Kicinski <kuba@kernel.org> Cc: Konrad Dybcio <konrad.dybcio@linaro.org> # qcom Cc: Mark Brown <broonie@kernel.org> Cc: Qais Yousef <qyousef@layalina.io> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
mailmap: map Bartosz's old address to the current one
I no longer work for BayLibre but many DT bindings have my BL address in
the maintainers entries. Map it to the email address I use for kernel
development.
SeongJae Park [Sat, 7 Oct 2023 20:04:32 +0000 (20:04 +0000)]
mm/damon/sysfs: check DAMOS regions update progress from before_terminate()
DAMON_SYSFS can receive DAMOS tried regions update request while kdamond
is already out of the main loop and before_terminate callback
(damon_sysfs_before_terminate() in this case) is not yet called. And
damon_sysfs_handle_cmd() can further be finished before the callback is
invoked. Then, damon_sysfs_before_terminate() unlocks damon_sysfs_lock,
which is not locked by anyone. This happens because the callback function
assumes damon_sysfs_cmd_request_callback() should be called before it.
Check if the assumption was true before doing the unlock, to avoid this
problem.
Link: https://lkml.kernel.org/r/20231007200432.3110-1-sj@kernel.org Fixes: f1d13cacabe1 ("mm/damon/sysfs: implement DAMOS tried regions update command") Signed-off-by: SeongJae Park <sj@kernel.org> Cc: <stable@vger.kernel.org> [6.2.x] Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Arnd Bergmann [Mon, 16 Oct 2023 20:08:38 +0000 (22:08 +0200)]
kasan: disable kasan_non_canonical_hook() for HW tags
On arm64, building with CONFIG_KASAN_HW_TAGS now causes a compile-time
error:
mm/kasan/report.c: In function 'kasan_non_canonical_hook':
mm/kasan/report.c:637:20: error: 'KASAN_SHADOW_OFFSET' undeclared (first use in this function)
637 | if (addr < KASAN_SHADOW_OFFSET)
| ^~~~~~~~~~~~~~~~~~~
mm/kasan/report.c:637:20: note: each undeclared identifier is reported only once for each function it appears in
mm/kasan/report.c:640:77: error: expected expression before ';' token
640 | orig_addr = (addr - KASAN_SHADOW_OFFSET) << KASAN_SHADOW_SCALE_SHIFT;
This was caused by removing the dependency on CONFIG_KASAN_INLINE that
used to prevent this from happening. Use the more specific dependency
on KASAN_SW_TAGS || KASAN_GENERIC to only ignore the function for hwasan
mode.
Link: https://lkml.kernel.org/r/20231016200925.984439-1-arnd@kernel.org Fixes: 12ec6a919b0f ("kasan: print the original fault addr when access invalid shadow") Signed-off-by: Arnd Bergmann <arnd@arndb.de> Cc: Alexander Potapenko <glider@google.com> Cc: Andrey Konovalov <andreyknvl@gmail.com> Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Haibo Li <haibo.li@mediatek.com> Cc: Kees Cook <keescook@chromium.org> Cc: Vincenzo Frascino <vincenzo.frascino@arm.com> Cc: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com> Cc: Matthias Brugger <matthias.bgg@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Haibo Li [Mon, 9 Oct 2023 07:37:48 +0000 (15:37 +0800)]
kasan: print the original fault addr when access invalid shadow
when the checked address is illegal,the corresponding shadow address from
kasan_mem_to_shadow may have no mapping in mmu table. Access such shadow
address causes kernel oops. Here is a sample about oops on arm64(VA
39bit) with KASAN_SW_TAGS and KASAN_OUTLINE on:
Rik van Riel [Fri, 6 Oct 2023 03:59:08 +0000 (23:59 -0400)]
hugetlbfs: close race between MADV_DONTNEED and page fault
Malloc libraries, like jemalloc and tcalloc, take decisions on when to
call madvise independently from the code in the main application.
This sometimes results in the application page faulting on an address,
right after the malloc library has shot down the backing memory with
MADV_DONTNEED.
Usually this is harmless, because we always have some 4kB pages sitting
around to satisfy a page fault. However, with hugetlbfs systems often
allocate only the exact number of huge pages that the application wants.
Due to TLB batching, hugetlbfs MADV_DONTNEED will free pages outside of
any lock taken on the page fault path, which can open up the following
race condition:
CPU 1 CPU 2
MADV_DONTNEED
unmap page
shoot down TLB entry
page fault
fail to allocate a huge page
killed with SIGBUS
free page
Fix that race by pulling the locking from __unmap_hugepage_final_range
into helper functions called from zap_page_range_single. This ensures
page faults stay locked out of the MADV_DONTNEED VMA until the huge pages
have actually been freed.
Link: https://lkml.kernel.org/r/20231006040020.3677377-4-riel@surriel.com Fixes: 04ada095dcfc ("hugetlb: don't delete vma_lock in hugetlb MADV_DONTNEED processing") Signed-off-by: Rik van Riel <riel@surriel.com> Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Muchun Song <muchun.song@linux.dev> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Rik van Riel [Fri, 6 Oct 2023 03:59:07 +0000 (23:59 -0400)]
hugetlbfs: extend hugetlb_vma_lock to private VMAs
Extend the locking scheme used to protect shared hugetlb mappings from
truncate vs page fault races, in order to protect private hugetlb mappings
(with resv_map) against MADV_DONTNEED.
Add a read-write semaphore to the resv_map data structure, and use that
from the hugetlb_vma_(un)lock_* functions, in preparation for closing the
race between MADV_DONTNEED and page faults.
Link: https://lkml.kernel.org/r/20231006040020.3677377-3-riel@surriel.com Fixes: 04ada095dcfc ("hugetlb: don't delete vma_lock in hugetlb MADV_DONTNEED processing") Signed-off-by: Rik van Riel <riel@surriel.com> Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Muchun Song <muchun.song@linux.dev> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Rik van Riel [Fri, 6 Oct 2023 03:59:06 +0000 (23:59 -0400)]
hugetlbfs: clear resv_map pointer if mmap fails
Patch series "hugetlbfs: close race between MADV_DONTNEED and page fault", v7.
Malloc libraries, like jemalloc and tcalloc, take decisions on when to
call madvise independently from the code in the main application.
This sometimes results in the application page faulting on an address,
right after the malloc library has shot down the backing memory with
MADV_DONTNEED.
Usually this is harmless, because we always have some 4kB pages sitting
around to satisfy a page fault. However, with hugetlbfs systems often
allocate only the exact number of huge pages that the application wants.
Due to TLB batching, hugetlbfs MADV_DONTNEED will free pages outside of
any lock taken on the page fault path, which can open up the following
race condition:
CPU 1 CPU 2
MADV_DONTNEED
unmap page
shoot down TLB entry
page fault
fail to allocate a huge page
killed with SIGBUS
free page
Fix that race by extending the hugetlb_vma_lock locking scheme to also
cover private hugetlb mappings (with resv_map), and pulling the locking
from __unmap_hugepage_final_range into helper functions called from
zap_page_range_single. This ensures page faults stay locked out of the
MADV_DONTNEED VMA until the huge pages have actually been freed.
This patch (of 3):
Hugetlbfs leaves a dangling pointer in the VMA if mmap fails. This has
not been a problem so far, but other code in this patch series tries to
follow that pointer.
Johannes Weiner [Fri, 6 Oct 2023 16:00:24 +0000 (12:00 -0400)]
mm: zswap: fix pool refcount bug around shrink_worker()
When a zswap store fails due to the limit, it acquires a pool reference
and queues the shrinker. When the shrinker runs, it drops the reference.
However, there can be multiple store attempts before the shrinker wakes up
and runs once. This results in reference leaks and eventual saturation
warnings for the pool refcount.
Fix this by dropping the reference again when the shrinker is already
queued. This ensures one reference per shrinker run.
Link: https://lkml.kernel.org/r/20231006160024.170748-1-hannes@cmpxchg.org Fixes: 45190f01dd40 ("mm/zswap.c: add allocation hysteresis if pool limit is hit") Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reported-by: Chris Mason <clm@fb.com> Acked-by: Nhat Pham <nphamcs@gmail.com> Cc: Vitaly Wool <vitaly.wool@konsulko.com> Cc: Domenico Cerasuolo <cerasuolodomenico@gmail.com> Cc: <stable@vger.kernel.org> [5.6+] Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Stefan Roesch [Tue, 26 Sep 2023 04:09:39 +0000 (21:09 -0700)]
mm/ksm: document pages_skipped sysfs knob
This adds documentation for the new metric pages_skipped.
Link: https://lkml.kernel.org/r/20230926040939.516161-5-shr@devkernel.io Signed-off-by: Stefan Roesch <shr@devkernel.io> Reviewed-by: David Hildenbrand <david@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Rik van Riel <riel@surriel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Stefan Roesch [Tue, 26 Sep 2023 04:09:38 +0000 (21:09 -0700)]
mm/ksm: document smart scan mode
This adds documentation for the smart scan mode of KSM.
[akpm@linux-foundation.org: fix typo]
[akpm@linux-foundation.org: document that smart_scan defaults to on] Link: https://lkml.kernel.org/r/20230926040939.516161-4-shr@devkernel.io Signed-off-by: Stefan Roesch <shr@devkernel.io> Reviewed-by: David Hildenbrand <david@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Rik van Riel <riel@surriel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Stefan Roesch [Tue, 26 Sep 2023 04:09:37 +0000 (21:09 -0700)]
mm/ksm: add pages_skipped metric
This change adds the "pages skipped" metric. To be able to evaluate how
successful smart page scanning is, the pages skipped metric can be
compared to the pages scanned metric.
The pages skipped metric is a cumulative counter. The counter is stored
under /sys/kernel/mm/ksm/pages_skipped.
Link: https://lkml.kernel.org/r/20230926040939.516161-3-shr@devkernel.io Signed-off-by: Stefan Roesch <shr@devkernel.io> Reviewed-by: David Hildenbrand <david@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Rik van Riel <riel@surriel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Stefan Roesch [Tue, 26 Sep 2023 04:09:36 +0000 (21:09 -0700)]
mm/ksm: add "smart" page scanning mode
Patch series "Smart scanning mode for KSM", v3.
This patch series adds "smart scanning" for KSM.
What is smart scanning?
=======================
KSM evaluates all the candidate pages for each scan. It does not use historic
information from previous scans. This has the effect that candidate pages that
couldn't be used for KSM de-duplication continue to be evaluated for each scan.
The idea of "smart scanning" is to keep historic information. With the historic
information we can temporarily skip the candidate page for one or several scans.
Details:
========
"Smart scanning" is to keep two small counters to store if the page has been
used for KSM. One counter stores how often we already tried to use the page for
KSM and the other counter stores how often we skip a page.
How often we skip the candidate page depends how often a page failed KSM
de-duplication. The code skips a maximum of 8 times. During testing this has
shown to be a good compromise for different workloads.
New sysfs knob:
===============
Smart scanning is not enabled by default. With /sys/kernel/mm/ksm/smart_scan
smart scanning can be enabled.
Monitoring:
===========
To monitor how effective smart scanning is a new sysfs knob has been introduced.
/sys/kernel/mm/pages_skipped report how many pages have been skipped by smart
scanning.
Results:
========
- Various workloads have shown a 20% - 25% reduction in page scans
For the instagram workload for instance, the number of pages scanned has been
reduced from over 20M pages per scan to less than 15M pages.
- Less pages scans also resulted in an overall higher de-duplication rate as
some shorter lived pages could be de-duplicated additionally
- Less pages scanned allows to reduce the pages_to_scan parameter
and this resulted in a 25% reduction in terms of CPU.
- The improvements have been observed for workloads that enable KSM with
madvise as well as prctl
This patch (of 4):
This change adds a "smart" page scanning mode for KSM. So far all the
candidate pages are continuously scanned to find candidates for
de-duplication. There are a considerably number of pages that cannot be
de-duplicated. This is costly in terms of CPU. By using smart scanning
considerable CPU savings can be achieved.
This change takes the history of scanning pages into account and skips the
page scanning of certain pages for a while if de-deduplication for this
page has not been successful in the past.
To do this it introduces two new fields in the ksm_rmap_item structure:
age and remaining_skips. age, is the KSM age and remaining_skips
determines how often scanning of this page is skipped. The age field is
incremented each time the page is scanned and the page cannot be de-
duplicated. age updated is capped at U8_MAX.
How often a page is skipped is dependent how often de-duplication has been
tried so far and the number of skips is currently limited to 8. This
value has shown to be effective with different workloads.
The feature is currently disable by default and can be enabled with the
new smart_scan knob.
The feature has shown to be very effective: upt to 25% of the page scans
can be eliminated; the pages_to_scan rate can be reduced by 40 - 50% and a
similar de-duplication rate can be maintained.
dax, kmem: calculate abstract distance with general interface
Previously, a fixed abstract distance MEMTIER_DEFAULT_DAX_ADISTANCE is
used for slow memory type in kmem driver. This limits the usage of kmem
driver, for example, it cannot be used for HBM (high bandwidth memory).
So, we use the general abstract distance calculation mechanism in kmem
drivers to get more accurate abstract distance on systems with proper
support. The original MEMTIER_DEFAULT_DAX_ADISTANCE is used as fallback
only.
Now, multiple memory types may be managed by kmem. These memory types are
put into the "kmem_memory_types" list and protected by
kmem_memory_type_lock.
Link: https://lkml.kernel.org/r/20230926060628.265989-5-ying.huang@intel.com Signed-off-by: "Huang, Ying" <ying.huang@intel.com> Tested-by: Bharata B Rao <bharata@amd.com> Reviewed-by: Dave Jiang <dave.jiang@intel.com> Reviewed-by: Alistair Popple <apopple@nvidia.com> Cc: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com> Cc: Wei Xu <weixugc@google.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Yang Shi <shy828301@gmail.com> Cc: Rafael J Wysocki <rafael.j.wysocki@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
A memory tiering abstract distance calculation algorithm based on ACPI
HMAT is implemented. The basic idea is as follows.
The performance attributes of system default DRAM nodes are recorded as
the base line. Whose abstract distance is MEMTIER_ADISTANCE_DRAM. Then,
the ratio of the abstract distance of a memory node (target) to
MEMTIER_ADISTANCE_DRAM is scaled based on the ratio of the performance
attributes of the node to that of the default DRAM nodes.
The functions to record the read/write latency/bandwidth of the default
DRAM nodes and calculate abstract distance according to read/write
latency/bandwidth ratio will be used by CXL CDAT (Coherent Device
Attribute Table) and other memory device drivers. So, they are put in
memory-tiers.c.
Link: https://lkml.kernel.org/r/20230926060628.265989-4-ying.huang@intel.com Signed-off-by: "Huang, Ying" <ying.huang@intel.com> Tested-by: Bharata B Rao <bharata@amd.com> Reviewed-by: Dave Jiang <dave.jiang@intel.com> Reviewed-by: Alistair Popple <apopple@nvidia.com> Cc: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com> Cc: Wei Xu <weixugc@google.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Yang Shi <shy828301@gmail.com> Cc: Rafael J Wysocki <rafael.j.wysocki@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Previously, in hmat_register_target_initiators(), the performance
attributes are calculated and the corresponding sysfs links and files are
created too. Which is called during memory onlining.
But now, to calculate the abstract distance of a memory target before
memory onlining, we need to calculate the performance attributes for a
memory target without creating sysfs links and files.
To do that, hmat_register_target_initiators() is refactored to make it
possible to calculate performance attributes separately.
Link: https://lkml.kernel.org/r/20230926060628.265989-3-ying.huang@intel.com Signed-off-by: "Huang, Ying" <ying.huang@intel.com> Reviewed-by: Alistair Popple <apopple@nvidia.com> Tested-by: Alistair Popple <apopple@nvidia.com> Tested-by: Bharata B Rao <bharata@amd.com> Reviewed-by: Dave Jiang <dave.jiang@intel.com> Cc: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com> Cc: Wei Xu <weixugc@google.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Yang Shi <shy828301@gmail.com> Cc: Rafael J Wysocki <rafael.j.wysocki@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Patch series "memory tiering: calculate abstract distance based on ACPI
HMAT", v4.
We have the explicit memory tiers framework to manage systems with
multiple types of memory, e.g., DRAM in DIMM slots and CXL memory devices.
Where, same kind of memory devices will be grouped into memory types,
then put into memory tiers. To describe the performance of a memory type,
abstract distance is defined. Which is in direct proportion to the memory
latency and inversely proportional to the memory bandwidth. To keep the
code as simple as possible, fixed abstract distance is used in dax/kmem to
describe slow memory such as Optane DCPMM.
To support more memory types, in this series, we added the abstract
distance calculation algorithm management mechanism, provided a algorithm
implementation based on ACPI HMAT, and used the general abstract distance
calculation interface in dax/kmem driver. So, dax/kmem can support HBM
(high bandwidth memory) in addition to the original Optane DCPMM.
This patch (of 4):
The abstract distance may be calculated by various drivers, such as ACPI
HMAT, CXL CDAT, etc. While it may be used by various code which hot-add
memory node, such as dax/kmem etc. To decouple the algorithm users and
the providers, the abstract distance calculation algorithms management
mechanism is implemented in this patch. It provides interface for the
providers to register the implementation, and interface for the users.
Multiple algorithm implementations can cooperate via calculating abstract
distance for different memory nodes. The preference of algorithm
implementations can be specified via priority (notifier_block.priority).
Link: https://lkml.kernel.org/r/20230926060628.265989-1-ying.huang@intel.com Link: https://lkml.kernel.org/r/20230926060628.265989-2-ying.huang@intel.com Signed-off-by: "Huang, Ying" <ying.huang@intel.com> Tested-by: Bharata B Rao <bharata@amd.com> Reviewed-by: Alistair Popple <apopple@nvidia.com> Reviewed-by: Dave Jiang <dave.jiang@intel.com> Cc: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com> Cc: Wei Xu <weixugc@google.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Yang Shi <shy828301@gmail.com> Cc: Rafael J Wysocki <rafael.j.wysocki@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
mm/filemap: remove hugetlb special casing in filemap.c
Remove special cased hugetlb handling code within the page cache by
changing the granularity of ->index to the base page size rather than the
huge page size. The motivation of this patch is to reduce complexity
within the filemap code while also increasing performance by removing
branches that are evaluated on every page cache lookup.
To support the change in index, new wrappers for hugetlb page cache
interactions are added. These wrappers perform the conversion to a linear
index which is now expected by the page cache for huge pages.
Perf was used to check the performance differences after the patch.
Overall the performance is similar to mainline with a very small larger
overhead that occurs in __filemap_add_folio() and
hugetlb_add_to_page_cache(). This is because of the larger overhead that
occurs in xa_load() and xa_store() as the xarray is now using more entries
to store hugetlb folios in the page cache.
Timing
aarch64
2MB Page Size
6.5-rc3 + this patch:
[root@sidhakum-ol9-1 hugepages]# time fallocate -l 700GB test.txt
real 1m49.568s
user 0m0.000s
sys 1m49.461s
6.5-rc3:
[root]# time fallocate -l 700GB test.txt
real 1m47.495s
user 0m0.000s
sys 1m47.370s
1GB Page Size
6.5-rc3 + this patch:
[root@sidhakum-ol9-1 hugepages1G]# time fallocate -l 700GB test.txt
real 1m47.024s
user 0m0.000s
sys 1m46.921s
6.5-rc3:
[root@sidhakum-ol9-1 hugepages1G]# time fallocate -l 700GB test.txt
real 1m44.551s
user 0m0.000s
sys 1m44.438s
x86
2MB Page Size
6.5-rc3 + this patch:
[root@sidhakum-ol9-2 hugepages]# time fallocate -l 100GB test.txt
real 0m22.383s
user 0m0.000s
sys 0m22.255s
6.5-rc3:
[opc@sidhakum-ol9-2 hugepages]$ time sudo fallocate -l 100GB /dev/hugepages/test.txt
real 0m22.735s
user 0m0.038s
sys 0m22.567s
1GB Page Size
6.5-rc3 + this patch:
[root@sidhakum-ol9-2 hugepages1GB]# time fallocate -l 100GB test.txt
real 0m25.786s
user 0m0.001s
sys 0m25.589s
6.5-rc3:
[root@sidhakum-ol9-2 hugepages1G]# time fallocate -l 100GB test.txt
real 0m33.454s
user 0m0.001s
sys 0m33.193s
aarch64:
workload - fallocate a 700GB file backed by huge pages
Stefan Roesch [Fri, 22 Sep 2023 21:11:41 +0000 (14:11 -0700)]
mm/ksm: test case for prctl fork/exec workflow
This adds a new test case to the ksm functional tests to make sure that
the KSM setting is inherited by the child process when doing a fork/exec.
Link: https://lkml.kernel.org/r/20230922211141.320789-3-shr@devkernel.io Signed-off-by: Stefan Roesch <shr@devkernel.io> Reviewed-by: David Hildenbrand <david@redhat.com> Cc: Carl Klemm <carl@uvos.xyz> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Rik van Riel <riel@surriel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Stefan Roesch [Fri, 22 Sep 2023 21:11:40 +0000 (14:11 -0700)]
mm/ksm: support fork/exec for prctl
Patch series "mm/ksm: add fork-exec support for prctl", v4.
A process can enable KSM with the prctl system call. When the process is
forked the KSM flag is inherited by the child process. However if the
process is executing an exec system call directly after the fork, the KSM
setting is cleared. This patch series addresses this problem.
1) Change the mask in coredump.h for execing a new process
2) Add a new test case in ksm_functional_tests
This patch (of 2):
Today we have two ways to enable KSM:
1) madvise system call
This allows to enable KSM for a memory region for a long time.
2) prctl system call
This is a recent addition to enable KSM for the complete process.
In addition when a process is forked, the KSM setting is inherited.
This change only affects the second case.
One of the use cases for (2) was to support the ability to enable
KSM for cgroups. This allows systemd to enable KSM for the seed
process. By enabling it in the seed process all child processes inherit
the setting.
This works correctly when the process is forked. However it doesn't
support fork/exec workflow.
From the previous cover letter:
....
Use case 3:
With the madvise call sharing opportunities are only enabled for the
current process: it is a workload-local decision. A considerable number
of sharing opportunities may exist across multiple workloads or jobs
(if they are part of the same security domain). Only a higler level
entity like a job scheduler or container can know for certain if its
running one or more instances of a job. That job scheduler however
doesn't have the necessary internal workload knowledge to make targeted
madvise calls.
....
In addition it can also be a bit surprising that fork keeps the KSM
setting and fork/exec does not.
si_meminfo() will read and assign more info not just free/ram pages. For
just DAMOS_WMARK_FREE_MEM_RATE use, only get free and ram pages is ok to
save cpu.
Kefeng Wang [Thu, 21 Sep 2023 07:44:17 +0000 (15:44 +0800)]
sched/numa, mm: make numa migrate functions to take a folio
The cpupid (or access time) is stored in the head page for THP, so it is
safely to make should_numa_migrate_memory() and numa_hint_fault_latency()
to take a folio. This is in preparation for large folio numa balancing.
Link: https://lkml.kernel.org/r/20230921074417.24004-7-wangkefeng.wang@huawei.com Signed-off-by: Kefeng Wang <wangkefeng.wang@huawei.com> Cc: David Hildenbrand <david@redhat.com> Cc: "Huang, Ying" <ying.huang@intel.com> Cc: Hugh Dickins <hughd@google.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Zi Yan <ziy@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Kefeng Wang [Thu, 21 Sep 2023 07:44:16 +0000 (15:44 +0800)]
mm: mempolicy: make mpol_misplaced() to take a folio
In preparation for large folio numa balancing, make mpol_misplaced() to
take a folio, no functional change intended.
Link: https://lkml.kernel.org/r/20230921074417.24004-6-wangkefeng.wang@huawei.com Signed-off-by: Kefeng Wang <wangkefeng.wang@huawei.com> Cc: David Hildenbrand <david@redhat.com> Cc: "Huang, Ying" <ying.huang@intel.com> Cc: Hugh Dickins <hughd@google.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Zi Yan <ziy@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Kefeng Wang [Thu, 21 Sep 2023 07:44:15 +0000 (15:44 +0800)]
mm: memory: make numa_migrate_prep() to take a folio
In preparation for large folio numa balancing, make numa_migrate_prep() to
take a folio, no functional change intended.
Link: https://lkml.kernel.org/r/20230921074417.24004-5-wangkefeng.wang@huawei.com Signed-off-by: Kefeng Wang <wangkefeng.wang@huawei.com> Cc: David Hildenbrand <david@redhat.com> Cc: "Huang, Ying" <ying.huang@intel.com> Cc: Hugh Dickins <hughd@google.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Zi Yan <ziy@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Kefeng Wang [Thu, 21 Sep 2023 07:44:14 +0000 (15:44 +0800)]
mm: memory: use a folio in do_numa_page()
Numa balancing only try to migrate non-compound page in do_numa_page(),
use a folio in it to save several compound_head calls, note we use
folio_estimated_sharers(), it is enough to check the folio sharers since
only normal page is handled, if large folio numa balancing is supported, a
precise folio sharers check would be used, no functional change intended.
Link: https://lkml.kernel.org/r/20230921074417.24004-4-wangkefeng.wang@huawei.com Signed-off-by: Kefeng Wang <wangkefeng.wang@huawei.com> Cc: David Hildenbrand <david@redhat.com> Cc: "Huang, Ying" <ying.huang@intel.com> Cc: Hugh Dickins <hughd@google.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Zi Yan <ziy@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Kefeng Wang [Thu, 21 Sep 2023 07:44:13 +0000 (15:44 +0800)]
mm: huge_memory: use a folio in do_huge_pmd_numa_page()
Use a folio in do_huge_pmd_numa_page(), reduce three page_folio() calls to
one, no functional change intended.
Link: https://lkml.kernel.org/r/20230921074417.24004-3-wangkefeng.wang@huawei.com Signed-off-by: Kefeng Wang <wangkefeng.wang@huawei.com> Cc: David Hildenbrand <david@redhat.com> Cc: "Huang, Ying" <ying.huang@intel.com> Cc: Hugh Dickins <hughd@google.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Zi Yan <ziy@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Kefeng Wang [Thu, 21 Sep 2023 07:44:12 +0000 (15:44 +0800)]
mm: memory: add vm_normal_folio_pmd()
Patch series "mm: convert numa balancing functions to use a folio", v2.
do_numa_pages() only handles non-compound pages, and only PMD-mapped THPs
are handled in do_huge_pmd_numa_page(). But a large, PTE-mapped folio
will be supported so let's convert more numa balancing functions to
use/take a folio in preparation for that, no functional change intended
for now.
This patch (of 6):
The new vm_normal_folio_pmd() wrapper is similar to vm_normal_folio(),
which allow them to completely replace the struct page variables with
struct folio variables.
Florent Revest [Mon, 28 Aug 2023 15:08:57 +0000 (17:08 +0200)]
mm: add a NO_INHERIT flag to the PR_SET_MDWE prctl
This extends the current PR_SET_MDWE prctl arg with a bit to indicate that
the process doesn't want MDWE protection to propagate to children.
To implement this no-inherit mode, the tag in current->mm->flags must be
absent from MMF_INIT_MASK. This means that the encoding for "MDWE but
without inherit" is different in the prctl than in the mm flags. This
leads to a bit of bit-mangling in the prctl implementation.
Link: https://lkml.kernel.org/r/20230828150858.393570-6-revest@chromium.org Signed-off-by: Florent Revest <revest@chromium.org> Reviewed-by: Kees Cook <keescook@chromium.org> Reviewed-by: Catalin Marinas <catalin.marinas@arm.com> Cc: Alexey Izbyshev <izbyshev@ispras.ru> Cc: Anshuman Khandual <anshuman.khandual@arm.com> Cc: Ayush Jain <ayush.jain3@amd.com> Cc: David Hildenbrand <david@redhat.com> Cc: Greg Thelen <gthelen@google.com> Cc: Joey Gouly <joey.gouly@arm.com> Cc: KP Singh <kpsingh@kernel.org> Cc: Mark Brown <broonie@kernel.org> Cc: Michal Hocko <mhocko@suse.com> Cc: Peter Xu <peterx@redhat.com> Cc: Ryan Roberts <ryan.roberts@arm.com> Cc: Szabolcs Nagy <Szabolcs.Nagy@arm.com> Cc: Topi Miettinen <toiwoton@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Florent Revest [Mon, 28 Aug 2023 15:08:56 +0000 (17:08 +0200)]
mm: make PR_MDWE_REFUSE_EXEC_GAIN an unsigned long
Defining a prctl flag as an int is a footgun because on a 64 bit machine
and with a variadic implementation of prctl (like in musl and glibc), when
used directly as a prctl argument, it can get casted to long with garbage
upper bits which would result in unexpected behaviors.
This patch changes the constant to an unsigned long to eliminate that
possibilities. This does not break UAPI.
I think that a stable backport would be "nice to have": to reduce the
chances that users build binaries that could end up with garbage bits in
their MDWE prctl arguments. We are not aware of anyone having yet
encountered this corner case with MDWE prctls but a backport would reduce
the likelihood it happens, since this sort of issues has happened with
other prctls. But If this is perceived as a backporting burden, I suppose
we could also live without a stable backport.
Link: https://lkml.kernel.org/r/20230828150858.393570-5-revest@chromium.org Fixes: b507808ebce2 ("mm: implement memory-deny-write-execute as a prctl") Signed-off-by: Florent Revest <revest@chromium.org> Suggested-by: Alexey Izbyshev <izbyshev@ispras.ru> Reviewed-by: David Hildenbrand <david@redhat.com> Reviewed-by: Kees Cook <keescook@chromium.org> Acked-by: Catalin Marinas <catalin.marinas@arm.com> Cc: Anshuman Khandual <anshuman.khandual@arm.com> Cc: Ayush Jain <ayush.jain3@amd.com> Cc: Greg Thelen <gthelen@google.com> Cc: Joey Gouly <joey.gouly@arm.com> Cc: KP Singh <kpsingh@kernel.org> Cc: Mark Brown <broonie@kernel.org> Cc: Michal Hocko <mhocko@suse.com> Cc: Peter Xu <peterx@redhat.com> Cc: Ryan Roberts <ryan.roberts@arm.com> Cc: Szabolcs Nagy <Szabolcs.Nagy@arm.com> Cc: Topi Miettinen <toiwoton@gmail.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Florent Revest [Mon, 28 Aug 2023 15:08:54 +0000 (17:08 +0200)]
kselftest: vm: fix mdwe's mmap_FIXED test case
I checked with the original author, the mmap_FIXED test case wasn't
properly tested and fails. Currently, it maps two consecutive (non
overlapping) pages and expects the second mapping to be denied by MDWE but
these two pages have nothing to do with each other so MDWE is actually out
of the picture here.
What the test actually intended to do was to remap a virtual address using
MAP_FIXED. However, this operation unmaps the existing mapping and
creates a new one so the va is backed by a new page and MDWE is again out
of the picture, all remappings should succeed.
This patch keeps the test case to make it clear that this situation is
expected to work: MDWE shouldn't block a MAP_FIXED replacement.
Link: https://lkml.kernel.org/r/20230828150858.393570-3-revest@chromium.org Fixes: 4cf1fe34fd18 ("kselftest: vm: add tests for memory-deny-write-execute") Signed-off-by: Florent Revest <revest@chromium.org> Reviewed-by: David Hildenbrand <david@redhat.com> Reviewed-by: Kees Cook <keescook@chromium.org> Reviewed-by: Catalin Marinas <catalin.marinas@arm.com> Reviewed-by: Ryan Roberts <ryan.roberts@arm.com> Tested-by: Ryan Roberts <ryan.roberts@arm.com> Tested-by: Ayush Jain <ayush.jain3@amd.com> Cc: Alexey Izbyshev <izbyshev@ispras.ru> Cc: Anshuman Khandual <anshuman.khandual@arm.com> Cc: Greg Thelen <gthelen@google.com> Cc: Joey Gouly <joey.gouly@arm.com> Cc: KP Singh <kpsingh@kernel.org> Cc: Mark Brown <broonie@kernel.org> Cc: Michal Hocko <mhocko@suse.com> Cc: Peter Xu <peterx@redhat.com> Cc: Szabolcs Nagy <Szabolcs.Nagy@arm.com> Cc: Topi Miettinen <toiwoton@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Florent Revest [Mon, 28 Aug 2023 15:08:53 +0000 (17:08 +0200)]
kselftest: vm: fix tabs/spaces inconsistency in the mdwe test
Patch series "MDWE without inheritance", v4.
Joey recently introduced a Memory-Deny-Write-Executable (MDWE) prctl which
tags current with a flag that prevents pages that were previously not
executable from becoming executable. This tag always gets inherited by
children tasks. (it's in MMF_INIT_MASK)
At Google, we've been using a somewhat similar downstream patch for a few
years now. To make the adoption of this feature easier, we've had it
support a mode in which the W^X flag does not propagate to children. For
example, this is handy if a C process which wants W^X protection suspects
it could start children processes that would use a JIT.
I'd like to align our features with the upstream prctl. This series
proposes a new NO_INHERIT flag to the MDWE prctl to make this kind of
adoption easier. It sets a different flag in current that is not in
MMF_INIT_MASK and which does not propagate.
As part of looking into MDWE, I also fixed a couple of things in the MDWE
test.
The background for this was discussed in these threads:
v1: https://lore.kernel.org/all/66900d0ad42797a55259061f757beece@ispras.ru/
v2: https://lore.kernel.org/all/d7e3749c-a718-df94-92af-1cb0fecab772@redhat.com/
This patch (of 6):
Fix tabs/spaces inconsistency in the mdwe test.
Link: https://lkml.kernel.org/r/20230828150858.393570-1-revest@chromium.org Link: https://lkml.kernel.org/r/20230828150858.393570-2-revest@chromium.org Signed-off-by: Florent Revest <revest@chromium.org> Reviewed-by: David Hildenbrand <david@redhat.com> Reviewed-by: Kees Cook <keescook@chromium.org> Acked-by: Catalin Marinas <catalin.marinas@arm.com> Cc: Alexey Izbyshev <izbyshev@ispras.ru> Cc: Anshuman Khandual <anshuman.khandual@arm.com> Cc: Ayush Jain <ayush.jain3@amd.com> Cc: Greg Thelen <gthelen@google.com> Cc: Joey Gouly <joey.gouly@arm.com> Cc: KP Singh <kpsingh@kernel.org> Cc: Mark Brown <broonie@kernel.org> Cc: Michal Hocko <mhocko@suse.com> Cc: Peter Xu <peterx@redhat.com> Cc: Szabolcs Nagy <Szabolcs.Nagy@arm.com> Cc: Topi Miettinen <toiwoton@gmail.com> Cc: Ryan Roberts <ryan.roberts@arm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
delayacct: add memory reclaim delay in get_page_from_freelist
The current memory reclaim delay statistics only count the direct memory
reclaim of the task in do_try_to_free_pages(). In systems with NUMA open,
some tasks occasionally experience slower response times, but the total
count of reclaim does not increase, using ftrace can show that
node_reclaim has occurred.
The memory reclaim occurring in get_page_from_freelist() is also due to
heavy memory load. To get the impact of tasks in memory reclaim, this
patch adds the statistics of the memory reclaim delay statistics for
__node_reclaim().
Document what mmu_notifier_invalidate_range_start_nonblock() is for. Also
add a __must_check annotation to signal that callers must bail out if a
notifier vetoes the operation.
Link: https://lkml.kernel.org/r/20230918201832.265108-1-jannh@google.com Signed-off-by: Jann Horn <jannh@google.com> Reviewed-by: Jason Gunthorpe <jgg@nvidia.com> Reviewed-by: Alistair Popple <apopple@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Liu Shixin [Fri, 15 Sep 2023 10:58:45 +0000 (18:58 +0800)]
memcg: remove unused do_memsw_account in memcg1_stat_format
Since commit b25806dcd3d5("mm: memcontrol: deprecate swapaccounting=0
mode") do_memsw_account() is synonymous with
!cgroup_subsys_on_dfl(memory_cgrp_subsys), It always equals true in
memcg1_stat_format(). Remove the unused code.
Link: https://lkml.kernel.org/r/20230915105845.3199656-3-liushixin2@huawei.com Signed-off-by: Liu Shixin <liushixin2@huawei.com> Suggested-by: Michal Koutný <mkoutny@suse.com> Reviewed-by: Yosry Ahmed <yosryahmed@google.com> Acked-by: Tejun heo <tj@kernel.org> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Kefeng Wang <wangkefeng.wang@huawei.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Muchun Song <songmuchun@bytedance.com> Cc: Roman Gushchin <roman.gushchin@linux.dev> Cc: Shakeel Butt <shakeelb@google.com> Cc: Zefan Li <lizefan.x@bytedance.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Liu Shixin [Fri, 15 Sep 2023 10:58:44 +0000 (18:58 +0800)]
memcg: expose swapcache stat for memcg v1
Patch series "Expose swapcache stat for memcg v1", v2.
Since commit b6038942480e ("mm: memcg: add swapcache stat for memcg v2")
adds swapcache stat for the cgroup v2, it seems there is no reason to hide
it in memcg v1. Conversely, with swapcached it is more accurate to
evaluate the available memory for memcg.
Link: https://lkml.kernel.org/r/20230915105845.3199656-1-liushixin2@huawei.com Link: https://lkml.kernel.org/r/20230915105845.3199656-2-liushixin2@huawei.com Signed-off-by: Liu Shixin <liushixin2@huawei.com> Suggested-by: Yosry Ahmed <yosryahmed@google.com> Acked-by: Tejun Heo <tj@kernel.org> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Kefeng Wang <wangkefeng.wang@huawei.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Michal Koutný <mkoutny@suse.com> Cc: Zefan Li <lizefan.x@bytedance.com> Cc: Roman Gushchin <roman.gushchin@linux.dev> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Shakeel Butt <shakeelb@google.com> Cc: Muchun Song <songmuchun@bytedance.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Baolin Wang [Mon, 18 Sep 2023 06:31:42 +0000 (14:31 +0800)]
mm: add statistics for PUD level pagetable
Recently, we found that cross-die access to pagetable pages on ARM64
machines can cause performance fluctuations in our business. Currently,
there are no PMU events available to track this situation on our ARM64
machines, so accurate pagetable accounting can help to analyze this issue,
but now the PUD level pagetable accounting is missed.
So introduce pagetable_pud_ctor/dtor() to help to get accurate PUD
pagetable accounting, as well as converting the architectures which use
generic PUD pagetable allocation to add corresponding PUD pagetable
accounting. Moreover this patch will mark the PUD level pagetable with
PG_table flag, which will help to do sanity validation in
unpoison_memory().
On my testing machine, I can see more pagetables statistics after the patch
with page-types tool:
Before patch:
flags page-count MB symbolic-flags long-symbolic-flags
0x0000000004000000 27326 106 __________________________g_________________ pgtable
After patch:
0x0000000004000000 27541 107 __________________________g_________________ pgtable
Link: https://lkml.kernel.org/r/876c71c03a7e69c17722a690e3225a4f7b172fb2.1695017383.git.baolin.wang@linux.alibaba.com Signed-off-by: Baolin Wang <baolin.wang@linux.alibaba.com> Acked-by: Mike Rapoport (IBM) <rppt@kernel.org> Acked-by: Vishal Moola (Oracle) <vishal.moola@gmail.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Borislav Petkov <bp@alien8.de> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Huacai Chen <chenhuacai@kernel.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Nicholas Piggin <npiggin@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Will Deacon <will@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Gregory Price [Tue, 3 Oct 2023 14:48:56 +0000 (10:48 -0400)]
mm/migrate: fix do_pages_move for compat pointers
do_pages_move does not handle compat pointers for the page list.
correctly. Add in_compat_syscall check and appropriate get_user fetch
when iterating the page list.
It makes the syscall in compat mode (32-bit userspace, 64-bit kernel)
work the same way as the native 32-bit syscall again, restoring the
behavior before my broken commit 5b1b561ba73c ("mm: simplify
compat_sys_move_pages").
More specifically, my patch moved the parsing of the 'pages' array from
the main entry point into do_pages_stat(), which left the syscall
working correctly for the 'stat' operation (nodes = NULL), while the
'move' operation (nodes != NULL) is now missing the conversion and
interprets 'pages' as an array of 64-bit pointers instead of the
intended 32-bit userspace pointers.
It is possible that nobody noticed this bug because the few
applications that actually call move_pages are unlikely to run in
compat mode because of their large memory requirements, but this
clearly fixes a user-visible regression and should have been caught by
ltp.
riscv: fix set_huge_pte_at() for NAPOT mappings when a swap entry is set
We used to determine the number of page table entries to set for a NAPOT
hugepage by using the pte value which actually fails when the pte to set
is a swap entry.
So take advantage of a recent fix for arm64 reported in [1] which
introduces the size of the mapping as an argument of set_huge_pte_at(): we
can then use this size to compute the number of page table entries to set
for a NAPOT region.
Link: https://lkml.kernel.org/r/20230928151846.8229-3-alexghiti@rivosinc.com Fixes: 82a1a1f3bfb6 ("riscv: mm: support Svnapot in hugetlb page") Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com> Reported-by: Ryan Roberts <ryan.roberts@arm.com> Closes: https://lore.kernel.org/linux-arm-kernel/20230922115804.2043771-1-ryan.roberts@arm.com/ [1] Reviewed-by: Andrew Jones <ajones@ventanamicro.com> Cc: Albert Ou <aou@eecs.berkeley.edu> Cc: Palmer Dabbelt <palmer@dabbelt.com> Cc: Paul Walmsley <paul.walmsley@sifive.com> Cc: Qinglin Pan <panqinglin2020@iscas.ac.cn> Cc: Conor Dooley <conor@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
riscv: handle VM_FAULT_[HWPOISON|HWPOISON_LARGE] faults instead of panicking
Patch series "Fix set_huge_pte_at()".
A recent report [1] from Ryan for arm64 revealed that we do not handle
swap entries when setting a hugepage backed by a NAPOT region (the contpte
riscv equivalent).
As explained in [1], the issue was discovered by a new test in kselftest
which uses poison entries, but the symptoms are different from arm64 though:
- the riscv kernel bugs because we do not handle VM_FAULT_HWPOISON*,
this is fixed by patch 1,
- after that, the test passes because the first pte_napot() fails (the
poison entry does not have the N bit set), and then we only set the
first page table entry covering the NAPOT hugepage, which is enough
for hugetlb_fault() to correctly raise a VM_FAULT_HWPOISON wherever we
write in this mapping since only this first page table entry is
checked
(see https://elixir.bootlin.com/linux/v6.6-rc3/source/mm/hugetlb.c#L6071).
But this seems fragile so patch 2 sets all page table entries of a
NAPOT mapping.
We used to panic when such faults were encountered but we should handle
those faults gracefully for userspace by sending a SIGBUS to the process,
like most architectures do.
When the calling function fails after the dup_anon_vma(), the
duplication of the anon_vma is not being undone. Add the necessary
unlink_anon_vma() call to the error paths that are missing them.
This issue showed up during inspection of the error path in vma_merge()
for an unrelated vma iterator issue.
Users may experience increased memory usage, which may be problematic as
the failure would likely be caused by a low memory situation.
Link: https://lkml.kernel.org/r/20230929183041.2835469-3-Liam.Howlett@oracle.com Fixes: d4af56c5c7c6 ("mm: start tracking VMAs with maple tree") Signed-off-by: Liam R. Howlett <Liam.Howlett@oracle.com> Reviewed-by: Lorenzo Stoakes <lstoakes@gmail.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: Jann Horn <jannh@google.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Suren Baghdasaryan <surenb@google.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
mmap: fix vma_iterator in error path of vma_merge()
During the error path, the vma iterator may not be correctly positioned or
set to the correct range. Undo the vma_prev() call by resetting to the
passed in address. Re-walking to the same range will fix the range to the
area previously passed in.
Users would notice increased cycles as vma_merge() would be called an
extra time with vma == prev, and thus would fail to merge and return.
Link: https://lore.kernel.org/linux-mm/CAG48ez12VN1JAOtTNMY+Y2YnsU45yL5giS-Qn=ejtiHpgJAbdQ@mail.gmail.com/ Link: https://lkml.kernel.org/r/20230929183041.2835469-2-Liam.Howlett@oracle.com Fixes: 18b098af2890 ("vma_merge: set vma iterator to correct position.") Signed-off-by: Liam R. Howlett <Liam.Howlett@oracle.com> Reported-by: Jann Horn <jannh@google.com> Closes: https://lore.kernel.org/linux-mm/CAG48ez12VN1JAOtTNMY+Y2YnsU45yL5giS-Qn=ejtiHpgJAbdQ@mail.gmail.com/ Reviewed-by: Lorenzo Stoakes <lstoakes@gmail.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Suren Baghdasaryan <surenb@google.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
The two users of mbind_range() are expecting that mbind_range() will
update the pointer to the previous VMA, or return an error. However,
set_mempolicy_home_node() does not call mbind_range() if there is no VMA
policy. The fix is to update the pointer to the previous VMA prior to
continuing iterating the VMAs when there is no policy.
Users may experience a WARN_ON() during VMA policy updates when updating
a range of VMAs on the home node.
Kemeng Shi [Wed, 27 Sep 2023 09:44:01 +0000 (17:44 +0800)]
mm/page_alloc: correct start page when guard page debug is enabled
When guard page debug is enabled and set_page_guard returns success, we
miss to forward page to point to start of next split range and we will do
split unexpectedly in page range without target page. Move start page
update before set_page_guard to fix this.
As we split to wrong target page, then splited pages are not able to merge
back to original order when target page is put back and splited pages
except target page is not usable. To be specific:
Consider target page is the third page in buddy page with order 2.
| buddy-2 | Page | Target | Page |
After break down to target page, we will only set first page to Guard
because of bug.
| Guard | Page | Target | Page |
When we try put_page_back_buddy with target page, the buddy page of target
if neither guard nor buddy, Then it's not able to construct original page
with order 2
| Guard | Page | buddy-0 | Page |
All pages except target page is not in free list and is not usable.
Link: https://lkml.kernel.org/r/20230927094401.68205-1-shikemeng@huaweicloud.com Fixes: 06be6ff3d2ec ("mm,hwpoison: rework soft offline for free pages") Signed-off-by: Kemeng Shi <shikemeng@huaweicloud.com> Acked-by: Naoya Horiguchi <naoya.horiguchi@nec.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Oscar Salvador <osalvador@suse.de> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
mm: mlock: update mlock_pte_range to handle large folio
Current kernel only lock base size folio during mlock syscall.
Add large folio support with following rules:
- Only mlock large folio when it's in VM_LOCKED VMA range
and fully mapped to page table.
fully mapped folio is required as if folio is not fully
mapped to a VM_LOCKED VMA, if system is in memory pressure,
page reclaim is allowed to pick up this folio, split it
and reclaim the pages which are not in VM_LOCKED VMA.
- munlock will apply to the large folio which is in VMA range
or cross the VMA boundary.
This is required to handle the case that the large folio is
mlocked, later the VMA is split in the middle of large folio.
Link: https://lkml.kernel.org/r/20230918073318.1181104-4-fengwei.yin@intel.com Signed-off-by: Yin Fengwei <fengwei.yin@intel.com> Cc: David Hildenbrand <david@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Ryan Roberts <ryan.roberts@arm.com> Cc: Yang Shi <shy828301@gmail.com> Cc: Yosry Ahmed <yosryahmed@google.com> Cc: Yu Zhao <yuzhao@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
mm: handle large folio when large folio in VM_LOCKED VMA range
If large folio is in the range of VM_LOCKED VMA, it should be mlocked to
avoid being picked by page reclaim. Which may split the large folio and
then mlock each pages again.
Mlock this kind of large folio to prevent them being picked by page
reclaim.
For the large folio which cross the boundary of VM_LOCKED VMA or not fully
mapped to VM_LOCKED VMA, we'd better not to mlock it. So if the system is
under memory pressure, this kind of large folio will be split and the
pages ouf of VM_LOCKED VMA can be reclaimed.
Ideally, for large folio, we should mlock it when the large folio is fully
mapped to VMA and munlock it if any page are unmampped from VMA. But it's
not easy to detect whether the large folio is fully mapped to VMA in some
cases (like add/remove rmap). So we update mlock_vma_folio() and
munlock_vma_folio() to mlock/munlock the folio according to vma->vm_flags.
Let caller to decide whether they should call these two functions.
For add rmap, only mlock normal 4K folio and postpone large folio handling
to page reclaim phase. It is possible to reuse page table iterator to
detect whether folio is fully mapped or not during page reclaim phase.
For remove rmap, invoke munlock_vma_folio() to munlock folio unconditionly
because rmap makes folio not fully mapped to VMA.
Link: https://lkml.kernel.org/r/20230918073318.1181104-3-fengwei.yin@intel.com Signed-off-by: Yin Fengwei <fengwei.yin@intel.com> Cc: David Hildenbrand <david@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Ryan Roberts <ryan.roberts@arm.com> Cc: Yang Shi <shy828301@gmail.com> Cc: Yosry Ahmed <yosryahmed@google.com> Cc: Yu Zhao <yuzhao@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
mm: add functions folio_in_range() and folio_within_vma()
Patch series "support large folio for mlock", v3.
Yu mentioned at [1] about the mlock() can't be applied to large folio.
I leant the related code and here is my understanding:
- For RLIMIT_MEMLOCK related, there is no problem. Because the
RLIMIT_MEMLOCK statistics is not related underneath page. That means
underneath page mlock or munlock doesn't impact the RLIMIT_MEMLOCK
statistics collection which is always correct.
- For keeping the page in RAM, there is no problem either. At least,
during try_to_unmap_one(), once detect the VMA has VM_LOCKED bit set in
vm_flags, the folio will be kept whatever the folio is mlocked or not.
So the function of mlock for large folio works. But it's not optimized
because the page reclaim needs scan these large folio and may split them.
This series identified the large folio for mlock to four types:
- The large folio is in VM_LOCKED range and fully mapped to the
range
- The large folio is in the VM_LOCKED range but not fully mapped to
the range
- The large folio cross VM_LOCKED VMA boundary
- The large folio cross last level page table boundary
For the first type, we mlock large folio so page reclaim will skip it.
For the second/third type, we don't mlock large folio. As the pages not
mapped to VM_LOACKED range are mapped to none VM_LOCKED range, if system
is in memory pressure situation, the large folio can be picked by page
reclaim and split. Then the pages not mapped to VM_LOCKED range can be
reclaimed.
For the fourth type, we don't mlock large folio because locking one page
table lock can't prevent the part in another last level page table being
unmapped. Thanks to Ryan for pointing this out.
To check whether the folio is fully mapped to the range, PTEs needs be
checked to see whether the page of folio is associated. Which needs take
page table lock and is heavy operation. So far, the only place needs this
check is madvise and page reclaim. These functions already have their own
PTE iterator.
patch1 introduce API to check whether large folio is in VMA range.
patch2 make page reclaim/mlock_vma_folio/munlock_vma_folio support
large folio mlock/munlock.
patch3 make mlock/munlock syscall support large folio.
Yu also mentioned a race which can make folio unevictable after munlock
during RFC v2 discussion [3]:
We decided that race issue didn't block this series based on:
- That race issue was not introduced by this series
- We had a looks-ok fix for that race issue. Need to wait
for mlock_count fixing patch as Yosry Ahmed suggested [4]
mm/damon/core-test: fix memory leak in damon_new_ctx()
When CONFIG_DAMON_KUNIT_TEST=y and making CONFIG_DEBUG_KMEMLEAK=y and
CONFIG_DEBUG_KMEMLEAK_AUTO_SCAN=y, the below memory leak is detected.
The damon_ctx which is allocated by kzalloc() in damon_new_ctx() in
damon_test_ops_registration() and damon_test_set_attrs() are not freed.
So use damon_destroy_ctx() to free it. After applying this patch, the
following memory leak is never detected
Link: https://lkml.kernel.org/r/20230918120951.2230468-3-ruanjinjie@huawei.com Fixes: d1836a3b2a9a ("mm/damon/core-test: initialise context before test in damon_test_set_attrs()") Fixes: 4f540f5ab4f2 ("mm/damon/core-test: add a kunit test case for ops registration") Signed-off-by: Jinjie Ruan <ruanjinjie@huawei.com> Reviewed-by: Feng Tang <feng.tang@intel.com> Reviewed-by: SeongJae Park <sj@kernel.org> Cc: Brendan Higgins <brendan.higgins@linux.dev> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
mm/damon/core-test: fix memory leak in damon_new_region()
Patch series "mm/damon/core-test: Fix memory leaks in core-test", v3.
There are a few memory leaks in core-test which are detected by kmemleak.
This patchset fixes the issues.
This patch (of 2):
When CONFIG_DAMON_KUNIT_TEST=y and making CONFIG_DEBUG_KMEMLEAK=y
and CONFIG_DEBUG_KMEMLEAK_AUTO_SCAN=y, the below memory leak is detected.
The damon_region which is allocated by kmem_cache_alloc() in
damon_new_region() in damon_test_regions() and
damon_test_update_monitoring_result() are not freed.
So for damon_test_regions(), replace damon_del_region() call with
damon_destroy_region() so that it calls both damon_del_region() and
damon_free_region(), the latter will free the damon_region. For
damon_test_update_monitoring_result(), call damon_free_region() to
free it. After applying this patch, the following memory leak is never
detected.
SeongJae Park [Sat, 16 Sep 2023 02:09:42 +0000 (02:09 +0000)]
mm/damon/sysfs-schemes: support DAMOS apply interval
Update DAMON sysfs interface to support DAMOS apply intervals by adding a
new file, 'apply_interval_us' in each scheme directory. Users can set and
get the interval for each scheme in microseconds by writing to and reading
from the file.
Link: https://lkml.kernel.org/r/20230916020945.47296-7-sj@kernel.org Signed-off-by: SeongJae Park <sj@kernel.org> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Shuah Khan <shuah@kernel.org> Cc: Steven Rostedt (Google) <rostedt@goodmis.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
DAMON-based operation schemes are applied for every aggregation interval.
That was mainly because schemes were using nr_accesses, which be complete
to be used for every aggregation interval. However, the schemes are now
using nr_accesses_bp, which is updated for each sampling interval in a way
that reasonable to be used. Therefore, there is no reason to apply
schemes for each aggregation interval.
The unnecessary alignment with aggregation interval was also making some
use cases of DAMOS tricky. Quotas setting under long aggregation interval
is one such example. Suppose the aggregation interval is ten seconds, and
there is a scheme having CPU quota 100ms per 1s. The scheme will actually
uses 100ms per ten seconds, since it cannobe be applied before next
aggregation interval. The feature is working as intended, but the results
might not that intuitive for some users. This could be fixed by updating
the quota to 1s per 10s. But, in the case, the CPU usage of DAMOS could
look like spikes, and would actually make a bad effect to other
CPU-sensitive workloads.
Implement a dedicated timing interval for each DAMON-based operation
scheme, namely apply_interval. The interval will be sampling interval
aligned, and each scheme will be applied for its apply_interval. The
interval is set to 0 by default, and it means the scheme should use the
aggregation interval instead. This avoids old users getting any
behavioral difference.
Link: https://lkml.kernel.org/r/20230916020945.47296-5-sj@kernel.org Signed-off-by: SeongJae Park <sj@kernel.org> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Shuah Khan <shuah@kernel.org> Cc: Steven Rostedt (Google) <rostedt@goodmis.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
SeongJae Park [Sat, 16 Sep 2023 02:09:39 +0000 (02:09 +0000)]
mm/damon/core: use nr_accesses_bp as a source of damos_before_apply tracepoint
damos_before_apply tracepoint is exposing access rate of DAMON regions
using nr_accesses field of regions, which was actually used by DAMOS in
the past. However, it has changed to use nr_accesses_bp instead. Update
the tracepoint to expose the value that DAMOS is really using.
Note that it doesn't expose the value as is in the basis point, but after
converting it to the natural number by dividing it by 10,000. Therefore
this change doesn't make user-visible behavioral differences.
Link: https://lkml.kernel.org/r/20230916020945.47296-4-sj@kernel.org Signed-off-by: SeongJae Park <sj@kernel.org> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Shuah Khan <shuah@kernel.org> Cc: Steven Rostedt (Google) <rostedt@goodmis.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
SeongJae Park [Sat, 16 Sep 2023 02:09:38 +0000 (02:09 +0000)]
mm/damon/sysfs-schemes: use nr_accesses_bp as the source of tried_regions/<N>/nr_accesses
DAMON sysfs interface exposes access rate of each region via DAMOS tried
regions directory. For this, the nr_accesses field of the region is used.
DAMOS was actually using nr_accesses in the past, but it uses
nr_accesses_bp now. Use the value that it is really using as the source.
Note that this doesn't expose nr_accesses_bp as is (in basis point), but
after converting it to the natural number by dividing the value by 10,000.
Hence there is no behavioral change from users' perspective.
Link: https://lkml.kernel.org/r/20230916020945.47296-3-sj@kernel.org Signed-off-by: SeongJae Park <sj@kernel.org> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Shuah Khan <shuah@kernel.org> Cc: Steven Rostedt (Google) <rostedt@goodmis.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
SeongJae Park [Sat, 16 Sep 2023 02:09:37 +0000 (02:09 +0000)]
mm/damon/core: make DAMOS uses nr_accesses_bp instead of nr_accesses
Patch series "mm/damon: implement DAMOS apply intervals".
DAMON-based operation schemes are applied for every aggregation interval.
That is mainly because schemes are using nr_accesses, which be complete to
be used for every aggregation interval.
This makes some DAMOS use cases be tricky. Quota setting under long
aggregation interval is one such example. Suppose the aggregation
interval is ten seconds, and there is a scheme having CPU quota 100ms per
1s. The scheme will actually uses 100ms per ten seconds, since it cannobe
be applied before next aggregation interval. The feature is working as
intended, but the results might not that intuitive for some users. This
could be fixed by updating the quota to 1s per 10s. But, in the case, the
CPU usage of DAMOS could look like spikes, and actually make a bad effect
to other CPU-sensitive workloads.
Also, with such huge aggregation interval, users may want schemes to be
applied more frequently.
DAMON provides nr_accesses_bp, which is updated for each sampling interval
in a way that reasonable to be used. By using that instead of
nr_accesses, DAMOS can have its own time interval and mitigate abovely
mentioned issues.
This patchset makes DAMOS schemes to use nr_accesses_bp instead of
nr_accesses, and have their own timing intervals. Also update DAMOS tried
regions sysfs files and DAMOS before_apply tracepoint to use the new data
as their source. Note that the interval is zero by default, and it is
interpreted to use the aggregation interval instead. This avoids making
user-visible behavioral changes.
Patches Seuqeunce
-----------------
The first patch (patch 1/9) makes DAMOS uses nr_accesses_bp instead of
nr_accesses, and following two patches (patches 2/9 and 3/9) updates DAMON
sysfs interface for DAMOS tried regions and the DAMOS before_apply
tracespoint to use nr_accesses_bp instead of nr_accesses, respectively.
The following two patches (patches 4/9 and 5/9) implements the
scheme-specific apply interval for DAMON kernel API users and update the
design document for the new feature.
Finally, the following four patches (patches 6/9, 7/9, 8/9 and 9/9) add
support of the feature in DAMON sysfs interface, add a simple selftest
test case, and document the new file on the usage and the ABI documents,
repsectively.
This patch (of 9):
DAMON provides nr_accesses_bp, which becomes same to nr_accesses * 10000
for every aggregation interval, but updated every sampling interval with a
reasonable accuracy. Since DAMON-based operation schemes are applied in
every aggregation interval using nr_accesses, using nr_accesses_bp instead
will make no difference to users. Meanwhile, it allows DAMOS to apply the
schemes in a time interval that less than the aggregation interval. It
could be useful and more flexible for some cases. Do it.
Anything found on a linked list threaded through ->lru is guaranteed to be
a folio as the compound_head found in a tail page overlaps the ->lru
member of struct page. So we can pull folios directly off these lists no
matter whether pages or folios were added to the list.
Link: https://lkml.kernel.org/r/20230824141325.2704553-3-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org> Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com> Reviewed-by: Muchun Song <songmuchun@bytedance.com> Cc: Sidhartha Kumar <sidhartha.kumar@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Usama Arif [Wed, 13 Sep 2023 10:54:01 +0000 (11:54 +0100)]
mm: hugetlb: skip initialization of gigantic tail struct pages if freed by HVO
The new boot flow when it comes to initialization of gigantic pages is as
follows:
- At boot time, for a gigantic page during __alloc_bootmem_hugepage, the
region after the first struct page is marked as noinit.
- This results in only the first struct page to be initialized in
reserve_bootmem_region. As the tail struct pages are not initialized at
this point, there can be a significant saving in boot time if HVO
succeeds later on.
- Later on in the boot, the head page is prepped and the first
HUGETLB_VMEMMAP_RESERVE_SIZE / sizeof(struct page) - 1 tail struct pages
are initialized.
- HVO is attempted. If it is not successful, then the rest of the tail
struct pages are initialized. If it is successful, no more tail struct
pages need to be initialized saving significant boot time.
The WARN_ON for increased ref count in gather_bootmem_prealloc was changed
to a VM_BUG_ON. This is OK as there should be no speculative references
this early in boot process. The VM_BUG_ON's are there just in case such
code is introduced.
[akpm@linux-foundation.org: make it nicer for 80 cols] Link: https://lkml.kernel.org/r/20230913105401.519709-5-usama.arif@bytedance.com Signed-off-by: Usama Arif <usama.arif@bytedance.com> Reviewed-by: Muchun Song <songmuchun@bytedance.com> Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com> Cc: Fam Zheng <fam.zheng@bytedance.com> Cc: Mike Rapoport (IBM) <rppt@kernel.org> Cc: Punit Agrawal <punit.agrawal@bytedance.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Usama Arif [Wed, 13 Sep 2023 10:54:00 +0000 (11:54 +0100)]
memblock: introduce MEMBLOCK_RSRV_NOINIT flag
For reserved memory regions marked with this flag, reserve_bootmem_region
is not called during memmap_init_reserved_pages. This can be used to
avoid struct page initialization for regions which won't need them, for
e.g. hugepages with Hugepage Vmemmap Optimization enabled.
Link: https://lkml.kernel.org/r/20230913105401.519709-4-usama.arif@bytedance.com Signed-off-by: Usama Arif <usama.arif@bytedance.com> Acked-by: Muchun Song <songmuchun@bytedance.com> Reviewed-by: Mike Rapoport (IBM) <rppt@kernel.org> Cc: Fam Zheng <fam.zheng@bytedance.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Punit Agrawal <punit.agrawal@bytedance.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Usama Arif [Wed, 13 Sep 2023 10:53:59 +0000 (11:53 +0100)]
memblock: pass memblock_type to memblock_setclr_flag
This allows setting flags to both memblock types and is in preparation for
setting flags (for e.g. to not initialize struct pages) on reserved
memory region.
Usama Arif [Wed, 13 Sep 2023 10:53:58 +0000 (11:53 +0100)]
mm: hugetlb_vmemmap: use nid of the head page to reallocate it
Patch series "mm: hugetlb: Skip initialization of gigantic tail struct
pages if freed by HVO", v5.
This series moves the boot time initialization of tail struct pages of a
gigantic page to later on in the boot. Only the
HUGETLB_VMEMMAP_RESERVE_SIZE / sizeof(struct page) - 1 tail struct pages
are initialized at the start. If HVO is successful, then no more tail
struct pages need to be initialized. For a 1G hugepage, this series avoid
initialization of 262144 - 63 = 262081 struct pages per hugepage.
When tested on a 512G system (allocating 500 1G hugepages), the kexec-boot
times with DEFERRED_STRUCT_PAGE_INIT enabled are:
- with patches, HVO enabled: 1.32 seconds
- with patches, HVO disabled: 2.15 seconds
- without patches, HVO enabled: 3.90 seconds
- without patches, HVO disabled: 3.58 seconds
This represents an approximately 70% reduction in boot time and will
significantly reduce server downtime when using a large number of gigantic
pages.
This patch (of 4):
If tail page prep and initialization is skipped, then the "start" page
will not contain the correct nid. Use the nid from first vmemap page.
SeongJae Park [Fri, 15 Sep 2023 02:52:50 +0000 (02:52 +0000)]
mm/damon/core: skip updating nr_accesses_bp for each aggregation interval
damon_merge_regions_of(), which is called for each aggregation interval,
updates nr_accesses_bp to nr_accesses * 10000. However, nr_accesses_bp is
updated for each sampling interval via damon_moving_sum() using the
aggregation interval as the moving time window. And by the definition of
the algorithm, the value becomes same to discrete-window based sum for
each time window-aligned time. Hence, nr_accesses_bp will be same to
nr_accesses * 10000 for each aggregation interval without explicit update.
Remove the unnecessary update of nr_accesses_bp in
damon_merge_regions_of().
SeongJae Park [Fri, 15 Sep 2023 02:52:49 +0000 (02:52 +0000)]
mm/damon/core: use pseudo-moving sum for nr_accesses_bp
Let nr_accesses_bp be calculated as a pseudo-moving sum that updated for
every sampling interval, using damon_moving_sum(). This is assumed to be
useful for cases that the aggregation interval is set quite huge, but the
monivoting results need to be collected earlier than next aggregation
interval is passed.
SeongJae Park [Fri, 15 Sep 2023 02:52:48 +0000 (02:52 +0000)]
mm/damon/core: introduce nr_accesses_bp
Add yet another representation of the access rate of each region, namely
nr_accesses_bp. It is just same to the nr_accesses but represents the
value in basis point (1 in 10,000), and updated at once in every
aggregation interval. That is, moving_accesses_bp is just nr_accesses *
10000. This may seems useless at the moment. However, it will be useful
for representing less than one nr_accesses value that will be needed to
make moving sum-based nr_accesses.
SeongJae Park [Fri, 15 Sep 2023 02:52:46 +0000 (02:52 +0000)]
mm/damon/core: implement a pseudo-moving sum function
For values that continuously change, moving average or sum are good ways
to provide fast updates while handling temporal and errorneous variability
of the value. For example, the access rate counter (nr_accesses) is
calculated as a sum of the number of positive sampled access check results
that collected during a discrete time window (aggregation interval), and
hence it handles temporal and errorneous access check results, but
provides the update only for every aggregation interval. Using a moving
sum method for that could allow providing the value for every sampling
interval. That could be useful for getting monitoring results snapshot or
running DAMOS in fine-grained timing.
However, supporting the moving sum for cases that number of samples in the
time window is arbirary could impose high overhead, since the number of
past values that it needs to keep could be too high. The nr_accesses
would also be one of the cases. To mitigate the overhead, implement a
pseudo-moving sum function that only provides an estimated pseudo-moving
sum. It assumes there was no error in last discrete time window and
subtract constant portion of last discrete time window sum.
Note that the function is not strictly implementing the moving sum, but it
keeps a property of moving sum, which makes the value same to the
dsicrete-window based sum for each time window-aligned timing. Hence,
people collecting the value in the old timings would show no difference.
When getting mm_struct of the monitoring target process fails, there wil
be no need to increase the access rate counter (nr_accesses) of the
regions for the process. Hence, damon_va_check_accesses() skips calling
damon_update_region_access_rate() in the case. This breaks the assumption
that damon_update_region_access_rate() is called for every region, for
every sampling interval. Call the function for every region even in the
case. This might increase the overhead in some cases, but such case would
not be frequent, so no significant impact is really expected.
SeongJae Park [Fri, 15 Sep 2023 02:52:44 +0000 (02:52 +0000)]
mm/damon/core: define and use a dedicated function for region access rate update
Patch series "mm/damon: provide pseudo-moving sum based access rate".
DAMON checks the access to each region for every sampling interval,
increase the access rate counter of the region, namely nr_accesses, if the
access was made. For every aggregation interval, the counter is reset.
The counter is exposed to users to be used as a metric showing the
relative access rate (frequency) of each region. In other words, DAMON
provides access rate of each region in every aggregation interval. The
aggregation avoids temporal access pattern changes making things
confusing. However, this also makes a few DAMON-related operations to
unnecessarily need to be aligned to the aggregation interval. This can
restrict the flexibility of DAMON applications, especially when the
aggregation interval is huge.
To provide the monitoring results in finer-grained timing while keeping
handling of temporal access pattern change, this patchset implements a
pseudo-moving sum based access rate metric. It is pseudo-moving sum
because strict moving sum implementation would need to keep all values for
last time window, and that could incur high overhead of there could be
arbitrary number of values in a time window. Especially in case of the
nr_accesses, since the sampling interval and aggregation interval can
arbitrarily set and the past values should be maintained for every region,
it could be risky. The pseudo-moving sum assumes there were no temporal
access pattern change in last discrete time window to remove the needs for
keeping the list of the last time window values. As a result, it beocmes
not strict moving sum implementation, but provides a reasonable accuracy.
Also, it keeps an important property of the moving sum. That is, the
moving sum becomes same to discrete-window based sum at the time that
aligns to the time window. This means using the pseudo moving sum based
nr_accesses makes no change to users who shows the value for every
aggregation interval.
Patches Sequence
----------------
The sequence of the patches is as follows. The first four patches are for
preparation of the change. The first two (patches 1 and 2) implements a
helper function for nr_accesses update and eliminate corner case that
skips use of the function, respectively. Following two (patches 3 and 4)
respectively implement the pseudo-moving sum function and its simple unit
test case.
Two patches for making DAMON to use the pseudo-moving sum follow. The
fifthe one (patch 5) introduces a new field for representing the
pseudo-moving sum-based access rate of each region, and the sixth one
makes the new representation to actually updated with the pseudo-moving
sum function.
Last two patches (patches 7 and 8) makes followup fixes for skipping
unnecessary updates and marking the moving sum function as static,
respectively.
This patch (of 8):
Each DAMON operarions set is updating nr_accesses field of each
damon_region for each of their access check results, from the
check_accesses() callback. Directly accessing the field could make things
complex to manage and change in future. Define and use a dedicated
function for the purpose.
SeongJae Park [Thu, 14 Sep 2023 02:15:23 +0000 (02:15 +0000)]
mm/damon/core: use number of passed access sampling as a timer
DAMON sleeps for sampling interval after each sampling, and check if the
aggregation interval and the ops update interval have passed using
ktime_get_coarse_ts64() and baseline timestamps for the intervals. That
design is for making the operations occur at deterministic timing
regardless of the time that spend for each work. However, it turned out
it is not that useful, and incur not-that-intuitive results.
After all, timer functions, and especially sleep functions that DAMON uses
to wait for specific timing, are not necessarily strictly accurate. It is
legal design, so no problem. However, depending on such inaccuracies, the
nr_accesses can be larger than aggregation interval divided by sampling
interval. For example, with the default setting (5 ms sampling interval
and 100 ms aggregation interval) we frequently show regions having
nr_accesses larger than 20. Also, if the execution of a DAMOS scheme
takes a long time, next aggregation could happen before enough number of
samples are collected. This is not what usual users would intuitively
expect.
Since access check sampling is the smallest unit work of DAMON, using the
number of passed sampling intervals as the DAMON-internal timer can easily
avoid these problems. That is, convert aggregation and ops update
intervals to numbers of sampling intervals that need to be passed before
those operations be executed, count the number of passed sampling
intervals, and invoke the operations as soon as the specific amount of
sampling intervals passed. Make the change.
Note that this could make a behavioral change to settings that using
intervals that not aligned by the sampling interval. For example, if the
sampling interval is 5 ms and the aggregation interval is 12 ms, DAMON
effectively uses 15 ms as its aggregation interval, because it checks
whether the aggregation interval after sleeping the sampling interval.
This change will make DAMON to effectively use 10 ms as aggregation
interval, since it uses 'aggregation interval / sampling interval *
sampling interval' as the effective aggregation interval, and we don't use
floating point types. Usual users would have used aligned intervals, so
this behavioral change is not expected to make any meaningful impact, so
just make this change.
Zi Yan [Wed, 13 Sep 2023 20:12:48 +0000 (16:12 -0400)]
mips: use nth_page() in place of direct struct page manipulation
__flush_dcache_pages() is called during hugetlb migration via
migrate_pages() -> migrate_hugetlbs() -> unmap_and_move_huge_page() ->
move_to_new_folio() -> flush_dcache_folio(). And with hugetlb and without
sparsemem vmemmap, struct page is not guaranteed to be contiguous beyond a
section. Use nth_page() instead.
Without the fix, a wrong address might be used for data cache page flush.
No bug is reported. The fix comes from code inspection.
Link: https://lkml.kernel.org/r/20230913201248.452081-6-zi.yan@sent.com Fixes: 15fa3e8e3269 ("mips: implement the new page table range API") Signed-off-by: Zi Yan <ziy@nvidia.com> Cc: David Hildenbrand <david@redhat.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Mike Rapoport (IBM) <rppt@kernel.org> Cc: Muchun Song <songmuchun@bytedance.com> Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Zi Yan [Wed, 13 Sep 2023 20:12:47 +0000 (16:12 -0400)]
fs: use nth_page() in place of direct struct page manipulation
When dealing with hugetlb pages, struct page is not guaranteed to be
contiguous on SPARSEMEM without VMEMMAP. Use nth_page() to handle it
properly.
Without the fix, a wrong subpage might be checked for HWPoison, causing wrong
number of bytes of a page copied to user space. No bug is reported. The fix
comes from code inspection.
Link: https://lkml.kernel.org/r/20230913201248.452081-5-zi.yan@sent.com Fixes: 38c1ddbde6c6 ("hugetlbfs: improve read HWPOISON hugepage") Signed-off-by: Zi Yan <ziy@nvidia.com> Reviewed-by: Muchun Song <songmuchun@bytedance.com> Cc: David Hildenbrand <david@redhat.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Mike Rapoport (IBM) <rppt@kernel.org> Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Zi Yan [Wed, 13 Sep 2023 20:12:46 +0000 (16:12 -0400)]
mm/memory_hotplug: use pfn math in place of direct struct page manipulation
When dealing with hugetlb pages, manipulating struct page pointers
directly can get to wrong struct page, since struct page is not guaranteed
to be contiguous on SPARSEMEM without VMEMMAP. Use pfn calculation to
handle it properly.
Without the fix, a wrong number of page might be skipped. Since skip cannot be
negative, scan_movable_page() will end early and might miss a movable page with
-ENOENT. This might fail offline_pages(). No bug is reported. The fix comes
from code inspection.
Link: https://lkml.kernel.org/r/20230913201248.452081-4-zi.yan@sent.com Fixes: eeb0efd071d8 ("mm,memory_hotplug: fix scan_movable_pages() for gigantic hugepages") Signed-off-by: Zi Yan <ziy@nvidia.com> Reviewed-by: Muchun Song <songmuchun@bytedance.com> Acked-by: David Hildenbrand <david@redhat.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Mike Rapoport (IBM) <rppt@kernel.org> Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Zi Yan [Wed, 13 Sep 2023 20:12:45 +0000 (16:12 -0400)]
mm/hugetlb: use nth_page() in place of direct struct page manipulation
When dealing with hugetlb pages, manipulating struct page pointers
directly can get to wrong struct page, since struct page is not guaranteed
to be contiguous on SPARSEMEM without VMEMMAP. Use nth_page() to handle
it properly.
A wrong or non-existing page might be tried to be grabbed, either
leading to a non freeable page or kernel memory access errors. No bug
is reported. It comes from code inspection.
Link: https://lkml.kernel.org/r/20230913201248.452081-3-zi.yan@sent.com Fixes: 57a196a58421 ("hugetlb: simplify hugetlb handling in follow_page_mask") Signed-off-by: Zi Yan <ziy@nvidia.com> Reviewed-by: Muchun Song <songmuchun@bytedance.com> Cc: David Hildenbrand <david@redhat.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Mike Rapoport (IBM) <rppt@kernel.org> Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
projects / linux.git / log