Instead of converting adjust_next between bytes and pages number, let's
just store the virtual address into adjust_next.
Also, this patch fixes one typo in the comment of vma_adjust_trans_huge().
[vbabka@suse.cz: changelog tweak]
Signed-off-by: Wei Yang <richard.weiyang@linux.alibaba.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Link: http://lkml.kernel.org/r/20200828081031.11306-1-richard.weiyang@linux.alibaba.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Patch series "Fix PageDoubleMap".
This is a purely theoretical problem for now as none of the filesystems
which use PG_private_2 (ie PG_fscache) are being converted at this time,
but it's confusing to leave it like this.
This patch (of 2):
PG_private_2 is defined as being PF_ANY (applicable to tail pages as well
as regular & head pages). That means that the first tail page of a
double-map page will appear to have Private2 set. Use the Workingset bit
instead which is defined as PF_HEAD so any attempt to access the
Workingset bit on a tail page will redirect to the head page's Workingset
bit.
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Zi Yan <ziy@nvidia.com>
Link: https://lkml.kernel.org/r/20200629151933.15671-1-willy@infradead.org
Link: https://lkml.kernel.org/r/20200629151933.15671-2-willy@infradead.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Patch series "Try to release mmap_lock temporarily in smaps_rollup", v4.
Recently, we have observed some janky issues caused by unpleasantly long
contention on mmap_lock which is held by smaps_rollup when probing large
processes. To address the problem, we let smaps_rollup detect if anyone
wants to acquire mmap_lock for write attempts. If yes, just release the
lock temporarily to ease the contention.
smaps_rollup is a procfs interface which allows users to summarize the
process's memory usage without the overhead of seq_* calls. Android uses
it to sample the memory usage of various processes to balance its memory
pool sizes. If no one wants to take the lock for write requests,
smaps_rollup with this patch will behave like the original one.
Although there are on-going mmap_lock optimizations like range-based
locks, the lock applied to smaps_rollup would be the coarse one, which is
hard to avoid the occurrence of aforementioned issues. So the detection
and temporary release for write attempts on mmap_lock in smaps_rollup is
still necessary.
This patch (of 3):
Add new API to query if someone wants to acquire mmap_lock for write
attempts.
Using this instead of rwsem_is_contended makes it more tolerant of future
changes to the lock type.
Signed-off-by: Chinwen Chang <chinwen.chang@mediatek.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Steven Price <steven.price@arm.com>
Acked-by: Michel Lespinasse <walken@google.com>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Daniel Jordan <daniel.m.jordan@oracle.com>
Cc: Daniel Kiss <daniel.kiss@arm.com>
Cc: Davidlohr Bueso <dbueso@suse.de>
Cc: Huang Ying <ying.huang@intel.com>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Jimmy Assarsson <jimmyassarsson@gmail.com>
Cc: Laurent Dufour <ldufour@linux.ibm.com>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: Matthias Brugger <matthias.bgg@gmail.com>
Cc: Song Liu <songliubraving@fb.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Link: http://lkml.kernel.org/r/1597715898-3854-1-git-send-email-chinwen.chang@mediatek.com
Link: http://lkml.kernel.org/r/1597715898-3854-2-git-send-email-chinwen.chang@mediatek.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Avoid accidental wrong builds, due to built-in rules working just a little
bit too well--but not quite as well as required for our situation here.
In other words, "make userfaultfd" (for example) is supposed to fail to
build at all, because this Makefile only supports either "make" (all), or
"make /full/path". However, the built-in rules, if not suppressed, will
pick up CFLAGS and the initial LDLIBS (but not the target-specific LDLIBS,
because those are only set for the full path target!). This causes it to
get pretty far into building things despite using incorrect values such as
an *occasionally* incomplete LDLIBS value.
Signed-off-by: John Hubbard <jhubbard@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Link: https://lkml.kernel.org/r/20200915012901.1655280-3-jhubbard@nvidia.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Patch series "selftests/vm: fix some minor aggravating factors in the Makefile".
This fixes a couple of minor aggravating factors that I ran across while
trying to do some changes in selftests/vm. These are simple things, but
like most things with GNU Make, it's rarely obvious what's wrong until you
understand *the entire Makefile and all of its includes*.
So while there is, of course, joy in learning those details, I thought I'd
fix these little things, so as to allow others to skip out on the Joy if
they so choose. :)
First of all, if you have an item (let's choose userfaultfd for an
example) that fails to build, you might do this:
$ make -j32
# ...you observe a failed item in the threaded output
# OK, let's get a closer look
$ make
# ...but now the build quietly "succeeds".
That's what Patch 0001 fixes.
Second, if you instead attempt this approach for your closer look (a casual
mistake, as it's not supported):
$ make userfaultfd
# ...userfaultfd fails to link, due to incomplete LDLIBS
That's what Patch 0002 fixes.
This patch (of 2):
If one or more of these selftest fail to build, then after the first
failure, subsequent invocations of "make" will make it appear that there
are no build failures, after all.
That's because the failed build products remain, with up-to-date
timestamps, thus tricking Make (and you!) into believing that there's
nothing else to build.
Fix this by telling Make to delete targets that didn't completely
succeed.
Signed-off-by: John Hubbard <jhubbard@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Link: https://lkml.kernel.org/r/20200915012901.1655280-1-jhubbard@nvidia.com
Link: https://lkml.kernel.org/r/20200915012901.1655280-2-jhubbard@nvidia.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The code in mc_handle_swap_pte() checks for non_swap_entry() and returns
NULL before checking is_device_private_entry() so device private pages are
never handled. Fix this by checking for non_swap_entry() after handling
device private swap PTEs.
I assume the memory cgroup accounting would be off somehow when moving
a process to another memory cgroup. Currently, the device private page
is charged like a normal anonymous page when allocated and is uncharged
when the page is freed so I think that path is OK.
Signed-off-by: Ralph Campbell <rcampbell@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: Balbir Singh <bsingharora@gmail.com>
Cc: Ira Weiny <ira.weiny@intel.com>
Link: https://lkml.kernel.org/r/20201009215952.2726-1-rcampbell@nvidia.com
xFixes: c733a82874 ("mm/memcontrol: support MEMORY_DEVICE_PRIVATE")
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
mem_cgroup_from_obj() checks the lowest bit of the page->mem_cgroup
pointer to determine if the page has an attached obj_cgroup vector instead
of a regular memcg pointer. If it's not set, it simple returns the
page->mem_cgroup value as a struct mem_cgroup pointer.
The commit 10befea91b ("mm: memcg/slab: use a single set of kmem_caches
for all allocations") changed the moment when this bit is set: if
previously it was set on the allocation of the slab page, now it can be
set well after, when the first accounted object is allocated on this page.
It opened a race: if page->mem_cgroup is set concurrently after the first
page_has_obj_cgroups(page) check, a pointer to the obj_cgroups array can
be returned as a memory cgroup pointer.
A simple check for page->mem_cgroup pointer for NULL before the
page_has_obj_cgroups() check fixes the race. Indeed, if the pointer is
not NULL, it's either a simple mem_cgroup pointer or a pointer to
obj_cgroup vector. The pointer can be asynchronously changed from NULL to
(obj_cgroup_vec | 0x1UL), but can't be changed from a valid memcg pointer
to objcg vector or back.
If the object passed to mem_cgroup_from_obj() is a slab object and
page->mem_cgroup is NULL, it means that the object is not accounted, so
the function must return NULL.
I've discovered the race looking at the code, so far I haven't seen it in
the wild.
Fixes: 10befea91b ("mm: memcg/slab: use a single set of kmem_caches for all allocations")
Signed-off-by: Roman Gushchin <guro@fb.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Link: https://lkml.kernel.org/r/20200910022435.2773735-1-guro@fb.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Our users reported that there're some random latency spikes when their RT
process is running. Finally we found that latency spike is caused by
FADV_DONTNEED. Which may call lru_add_drain_all() to drain LRU cache on
remote CPUs, and then waits the per-cpu work to complete. The wait time
is uncertain, which may be tens millisecond.
That behavior is unreasonable, because this process is bound to a specific
CPU and the file is only accessed by itself, IOW, there should be no
pagecache pages on a per-cpu pagevec of a remote CPU. That unreasonable
behavior is partially caused by the wrong comparation of the number of
invalidated pages and the number of the target. For example,
if (count < (end_index - start_index + 1))
The count above is how many pages were invalidated in the local CPU, and
(end_index - start_index + 1) is how many pages should be invalidated.
The usage of (end_index - start_index + 1) is incorrect, because they are
virtual addresses, which may not mapped to pages. Besides that, there may
be holes between start and end. So we'd better check whether there are
still pages on per-cpu pagevec after drain the local cpu, and then decide
whether or not to call lru_add_drain_all().
After I applied it with a hotfix to our production environment, most of
the lru_add_drain_all() can be avoided.
Suggested-by: Mel Gorman <mgorman@suse.de>
Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Mel Gorman <mgorman@suse.de>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Link: https://lkml.kernel.org/r/20200923133318.14373-1-laoar.shao@gmail.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
We dereference page->mapping and page->index directly after calling
find_subpage() and these fields are not valid for tail pages. While
commit 4101196b19 ("mm: page cache: store only head pages in i_pages")
introduced the call to find_subpage(), the problem existed prior to this;
I'm going to suggest all the way back to when THPs first existed.
The user-visible effects of this are almost negligible. To hit it, you
have to mmap a tmpfs file at an unaligned address and then it's only a
disabled optimisation causing page faults to happen more frequently than
they otherwise would.
Fix this by keeping both head and page pointers and checking the
appropriate one. We could use page_mapping() and page_to_index(), but
that's higher overhead.
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: William Kucharski <william.kucharski@oracle.com>
Link: https://lkml.kernel.org/r/20200911012532.24761-1-willy@infradead.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
