hmm_range_fault() calls find_vma() and walk_page_range() in a loop. This
is unnecessary duplication since walk_page_range() calls find_vma() in a
loop already.
Simplify hmm_range_fault() by defining a walk_test() callback function to
filter unhandled vmas.
This also fixes a bug where hmm_range_fault() was not checking start >=
vma->vm_start before checking vma->vm_flags so hmm_range_fault() could
return an error based on the wrong vma for the requested range.
It also fixes a bug when the vma has no read access and the caller did not
request a fault, there shouldn't be any error return code.
Link: https://lore.kernel.org/r/20191104222141.5173-2-rcampbell@nvidia.com
Signed-off-by: Ralph Campbell <rcampbell@nvidia.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
hmm_mirror's handling of ranges does not use a sequence count which
results in this bug:
CPU0 CPU1
hmm_range_wait_until_valid(range)
valid == true
hmm_range_fault(range)
hmm_invalidate_range_start()
range->valid = false
hmm_invalidate_range_end()
range->valid = true
hmm_range_valid(range)
valid == true
Where the hmm_range_valid() should not have succeeded.
Adding the required sequence count would make it nearly identical to the
new mmu_interval_notifier. Instead replace the hmm_mirror stuff with
mmu_interval_notifier.
Co-existence of the two APIs is the first step.
Link: https://lore.kernel.org/r/20191112202231.3856-4-jgg@ziepe.ca
Reviewed-by: Jérôme Glisse <jglisse@redhat.com>
Tested-by: Philip Yang <Philip.Yang@amd.com>
Tested-by: Ralph Campbell <rcampbell@nvidia.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Of the 13 users of mmu_notifiers, 8 of them use only
invalidate_range_start/end() and immediately intersect the
mmu_notifier_range with some kind of internal list of VAs. 4 use an
interval tree (i915_gem, radeon_mn, umem_odp, hfi1). 4 use a linked list
of some kind (scif_dma, vhost, gntdev, hmm)
And the remaining 5 either don't use invalidate_range_start() or do some
special thing with it.
It turns out that building a correct scheme with an interval tree is
pretty complicated, particularly if the use case is synchronizing against
another thread doing get_user_pages(). Many of these implementations have
various subtle and difficult to fix races.
This approach puts the interval tree as common code at the top of the mmu
notifier call tree and implements a shareable locking scheme.
It includes:
- An interval tree tracking VA ranges, with per-range callbacks
- A read/write locking scheme for the interval tree that avoids
sleeping in the notifier path (for OOM killer)
- A sequence counter based collision-retry locking scheme to tell
device page fault that a VA range is being concurrently invalidated.
This is based on various ideas:
- hmm accumulates invalidated VA ranges and releases them when all
invalidates are done, via active_invalidate_ranges count.
This approach avoids having to intersect the interval tree twice (as
umem_odp does) at the potential cost of a longer device page fault.
- kvm/umem_odp use a sequence counter to drive the collision retry,
via invalidate_seq
- a deferred work todo list on unlock scheme like RTNL, via deferred_list.
This makes adding/removing interval tree members more deterministic
- seqlock, except this version makes the seqlock idea multi-holder on the
write side by protecting it with active_invalidate_ranges and a spinlock
To minimize MM overhead when only the interval tree is being used, the
entire SRCU and hlist overheads are dropped using some simple
branches. Similarly the interval tree overhead is dropped when in hlist
mode.
The overhead from the mandatory spinlock is broadly the same as most of
existing users which already had a lock (or two) of some sort on the
invalidation path.
Link: https://lore.kernel.org/r/20191112202231.3856-3-jgg@ziepe.ca
Acked-by: Christian König <christian.koenig@amd.com>
Tested-by: Philip Yang <Philip.Yang@amd.com>
Tested-by: Ralph Campbell <rcampbell@nvidia.com>
Reviewed-by: John Hubbard <jhubbard@nvidia.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Minor conflict in drivers/s390/net/qeth_l2_main.c, kept the lock
from commit c8183f5489 ("s390/qeth: fix potential deadlock on
workqueue flush"), removed the code which was removed by commit
9897d583b0 ("s390/qeth: consolidate some duplicated HW cmd code").
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
It's possible to hit the WARN_ON_ONCE(page_mapped(page)) in
remove_stable_node() when it races with __mmput() and squeezes in
between ksm_exit() and exit_mmap().
WARNING: CPU: 0 PID: 3295 at mm/ksm.c:888 remove_stable_node+0x10c/0x150
Call Trace:
remove_all_stable_nodes+0x12b/0x330
run_store+0x4ef/0x7b0
kernfs_fop_write+0x200/0x420
vfs_write+0x154/0x450
ksys_write+0xf9/0x1d0
do_syscall_64+0x99/0x510
entry_SYSCALL_64_after_hwframe+0x49/0xbe
Remove the warning as there is nothing scary going on.
Link: http://lkml.kernel.org/r/20191119131850.5675-1-aryabinin@virtuozzo.com
Fixes: cbf86cfe04 ("ksm: remove old stable nodes more thoroughly")
Signed-off-by: Andrey Ryabinin <aryabinin@virtuozzo.com>
Acked-by: Hugh Dickins <hughd@google.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Daniel Borkmann says:
====================
pull-request: bpf-next 2019-11-20
The following pull-request contains BPF updates for your *net-next* tree.
We've added 81 non-merge commits during the last 17 day(s) which contain
a total of 120 files changed, 4958 insertions(+), 1081 deletions(-).
There are 3 trivial conflicts, resolve it by always taking the chunk from
196e8ca748:
<<<<<<< HEAD
=======
void *bpf_map_area_mmapable_alloc(u64 size, int numa_node);
>>>>>>> 196e8ca748
<<<<<<< HEAD
void *bpf_map_area_alloc(u64 size, int numa_node)
=======
static void *__bpf_map_area_alloc(u64 size, int numa_node, bool mmapable)
>>>>>>> 196e8ca748
<<<<<<< HEAD
if (size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) {
=======
/* kmalloc()'ed memory can't be mmap()'ed */
if (!mmapable && size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) {
>>>>>>> 196e8ca748
The main changes are:
1) Addition of BPF trampoline which works as a bridge between kernel functions,
BPF programs and other BPF programs along with two new use cases: i) fentry/fexit
BPF programs for tracing with practically zero overhead to call into BPF (as
opposed to k[ret]probes) and ii) attachment of the former to networking related
programs to see input/output of networking programs (covering xdpdump use case),
from Alexei Starovoitov.
2) BPF array map mmap support and use in libbpf for global data maps; also a big
batch of libbpf improvements, among others, support for reading bitfields in a
relocatable manner (via libbpf's CO-RE helper API), from Andrii Nakryiko.
3) Extend s390x JIT with usage of relative long jumps and loads in order to lift
the current 64/512k size limits on JITed BPF programs there, from Ilya Leoshkevich.
4) Add BPF audit support and emit messages upon successful prog load and unload in
order to have a timeline of events, from Daniel Borkmann and Jiri Olsa.
5) Extension to libbpf and xdpsock sample programs to demo the shared umem mode
(XDP_SHARED_UMEM) as well as RX-only and TX-only sockets, from Magnus Karlsson.
6) Several follow-up bug fixes for libbpf's auto-pinning code and a new API
call named bpf_get_link_xdp_info() for retrieving the full set of prog
IDs attached to XDP, from Toke Høiland-Jørgensen.
7) Add BTF support for array of int, array of struct and multidimensional arrays
and enable it for skb->cb[] access in kfree_skb test, from Martin KaFai Lau.
8) Fix AF_XDP by using the correct number of channels from ethtool, from Luigi Rizzo.
9) Two fixes for BPF selftest to get rid of a hang in test_tc_tunnel and to avoid
xdping to be run as standalone, from Jiri Benc.
10) Various BPF selftest fixes when run with latest LLVM trunk, from Yonghong Song.
11) Fix a memory leak in BPF fentry test run data, from Colin Ian King.
12) Various smaller misc cleanups and improvements mostly all over BPF selftests and
samples, from Daniel T. Lee, Andre Guedes, Anders Roxell, Mao Wenan, Yue Haibing.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Add ability to memory-map contents of BPF array map. This is extremely useful
for working with BPF global data from userspace programs. It allows to avoid
typical bpf_map_{lookup,update}_elem operations, improving both performance
and usability.
There had to be special considerations for map freezing, to avoid having
writable memory view into a frozen map. To solve this issue, map freezing and
mmap-ing is happening under mutex now:
- if map is already frozen, no writable mapping is allowed;
- if map has writable memory mappings active (accounted in map->writecnt),
map freezing will keep failing with -EBUSY;
- once number of writable memory mappings drops to zero, map freezing can be
performed again.
Only non-per-CPU plain arrays are supported right now. Maps with spinlocks
can't be memory mapped either.
For BPF_F_MMAPABLE array, memory allocation has to be done through vmalloc()
to be mmap()'able. We also need to make sure that array data memory is
page-sized and page-aligned, so we over-allocate memory in such a way that
struct bpf_array is at the end of a single page of memory with array->value
being aligned with the start of the second page. On deallocation we need to
accomodate this memory arrangement to free vmalloc()'ed memory correctly.
One important consideration regarding how memory-mapping subsystem functions.
Memory-mapping subsystem provides few optional callbacks, among them open()
and close(). close() is called for each memory region that is unmapped, so
that users can decrease their reference counters and free up resources, if
necessary. open() is *almost* symmetrical: it's called for each memory region
that is being mapped, **except** the very first one. So bpf_map_mmap does
initial refcnt bump, while open() will do any extra ones after that. Thus
number of close() calls is equal to number of open() calls plus one more.
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Song Liu <songliubraving@fb.com>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Link: https://lore.kernel.org/bpf/20191117172806.2195367-4-andriin@fb.com
This blacklists several compilation units from KCSAN. See the respective
inline comments for the reasoning.
Signed-off-by: Marco Elver <elver@google.com>
Acked-by: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
PageAnon() and PageKsm() use the low two bits of the page->mapping
pointer to indicate the page type. PageAnon() only checks the LSB while
PageKsm() checks the least significant 2 bits are equal to 3.
Therefore, PageAnon() is true for KSM pages. __dump_page() incorrectly
will never print "ksm" because it checks PageAnon() first. Fix this by
checking PageKsm() first.
Link: http://lkml.kernel.org/r/20191113000651.20677-1-rcampbell@nvidia.com
Fixes: 1c6fb1d89e ("mm: print more information about mapping in __dump_page")
Signed-off-by: Ralph Campbell <rcampbell@nvidia.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Jerome Glisse <jglisse@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
When dumping struct page information, __dump_page() prints the page type
with a trailing blank followed by the page flags on a separate line:
anon
flags: 0x100000000090034(uptodate|lru|active|head|swapbacked)
It looks like the intent was to use pr_cont() for printing "flags:" but
pr_cont() usage is discouraged so fix this by extending the format to
include the flags into a single line:
anon flags: 0x100000000090034(uptodate|lru|active|head|swapbacked)
If the page is file backed, the name might be long so use two lines:
shmem_aops name:"dev/zero"
flags: 0x10000000008000c(uptodate|dirty|swapbacked)
Eliminate pr_conf() usage as well for appending compound_mapcount.
Link: http://lkml.kernel.org/r/20191112012608.16926-1-rcampbell@nvidia.com
Signed-off-by: Ralph Campbell <rcampbell@nvidia.com>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Jerome Glisse <jglisse@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The following race is observed due to which a processes faulting on a
swap entry, finds the page neither in swapcache nor swap. This causes
zram to give a zero filled page that gets mapped to the process,
resulting in a user space crash later.
Consider parent and child processes Pa and Pb sharing the same swap slot
with swap_count 2. Swap is on zram with SWP_SYNCHRONOUS_IO set.
Virtual address 'VA' of Pa and Pb points to the shared swap entry.
Pa Pb
fault on VA fault on VA
do_swap_page do_swap_page
lookup_swap_cache fails lookup_swap_cache fails
Pb scheduled out
swapin_readahead (deletes zram entry)
swap_free (makes swap_count 1)
Pb scheduled in
swap_readpage (swap_count == 1)
Takes SWP_SYNCHRONOUS_IO path
zram enrty absent
zram gives a zero filled page
Fix this by making sure that swap slot is freed only when swap count
drops down to one.
Link: http://lkml.kernel.org/r/1571743294-14285-1-git-send-email-vinmenon@codeaurora.org
Fixes: aa8d22a11d ("mm: swap: SWP_SYNCHRONOUS_IO: skip swapcache only if swapped page has no other reference")
Signed-off-by: Vinayak Menon <vinmenon@codeaurora.org>
Suggested-by: Minchan Kim <minchan@google.com>
Acked-by: Minchan Kim <minchan@kernel.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
try_offline_node() is pretty much broken right now:
- The node span is updated when onlining memory, not when adding it. We
ignore memory that was mever onlined. Bad.
- We touch possible garbage memmaps. The pfn_to_nid(pfn) can easily
trigger a kernel panic. Bad for memory that is offline but also bad
for subsection hotadd with ZONE_DEVICE, whereby the memmap of the
first PFN of a section might contain garbage.
- Sections belonging to mixed nodes are not properly considered.
As memory blocks might belong to multiple nodes, we would have to walk
all pageblocks (or at least subsections) within present sections.
However, we don't have a way to identify whether a memmap that is not
online was initialized (relevant for ZONE_DEVICE). This makes things
more complicated.
Luckily, we can piggy pack on the node span and the nid stored in memory
blocks. Currently, the node span is grown when calling
move_pfn_range_to_zone() - e.g., when onlining memory, and shrunk when
removing memory, before calling try_offline_node(). Sysfs links are
created via link_mem_sections(), e.g., during boot or when adding
memory.
If the node still spans memory or if any memory block belongs to the
nid, we don't set the node offline. As memory blocks that span multiple
nodes cannot get offlined, the nid stored in memory blocks is reliable
enough (for such online memory blocks, the node still spans the memory).
Introduce for_each_memory_block() to efficiently walk all memory blocks.
Note: We will soon stop shrinking the ZONE_DEVICE zone and the node span
when removing ZONE_DEVICE memory to fix similar issues (access of
garbage memmaps) - until we have a reliable way to identify whether
these memmaps were properly initialized. This implies later, that once
a node had ZONE_DEVICE memory, we won't be able to set a node offline -
which should be acceptable.
Since commit f1dd2cd13c ("mm, memory_hotplug: do not associate
hotadded memory to zones until online") memory that is added is not
assoziated with a zone/node (memmap not initialized). The introducing
commit 60a5a19e74 ("memory-hotplug: remove sysfs file of node")
already missed that we could have multiple nodes for a section and that
the zone/node span is updated when onlining pages, not when adding them.
I tested this by hotplugging two DIMMs to a memory-less and cpu-less
NUMA node. The node is properly onlined when adding the DIMMs. When
removing the DIMMs, the node is properly offlined.
Masayoshi Mizuma reported:
: Without this patch, memory hotplug fails as panic:
:
: BUG: kernel NULL pointer dereference, address: 0000000000000000
: ...
: Call Trace:
: remove_memory_block_devices+0x81/0xc0
: try_remove_memory+0xb4/0x130
: __remove_memory+0xa/0x20
: acpi_memory_device_remove+0x84/0x100
: acpi_bus_trim+0x57/0x90
: acpi_bus_trim+0x2e/0x90
: acpi_device_hotplug+0x2b2/0x4d0
: acpi_hotplug_work_fn+0x1a/0x30
: process_one_work+0x171/0x380
: worker_thread+0x49/0x3f0
: kthread+0xf8/0x130
: ret_from_fork+0x35/0x40
[david@redhat.com: v3]
Link: http://lkml.kernel.org/r/20191102120221.7553-1-david@redhat.com
Link: http://lkml.kernel.org/r/20191028105458.28320-1-david@redhat.com
Fixes: 60a5a19e74 ("memory-hotplug: remove sysfs file of node")
Fixes: f1dd2cd13c ("mm, memory_hotplug: do not associate hotadded memory to zones until online") # visiable after d0dc12e86b
Signed-off-by: David Hildenbrand <david@redhat.com>
Tested-by: Masayoshi Mizuma <m.mizuma@jp.fujitsu.com>
Cc: Tang Chen <tangchen@cn.fujitsu.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: "Rafael J. Wysocki" <rafael@kernel.org>
Cc: Keith Busch <keith.busch@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: "Peter Zijlstra (Intel)" <peterz@infradead.org>
Cc: Jani Nikula <jani.nikula@intel.com>
Cc: Nayna Jain <nayna@linux.ibm.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Pavel Tatashin <pasha.tatashin@soleen.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
In collapse_file(), for !is_shmem case, current check cannot guarantee
the locked page is up-to-date. Specifically, xas_unlock_irq() should
not be called before lock_page() and get_page(); and it is necessary to
recheck PageUptodate() after locking the page.
With this bug and CONFIG_READ_ONLY_THP_FOR_FS=y, madvise(HUGE)'ed .text
may contain corrupted data. This is because khugepaged mistakenly
collapses some not up-to-date sub pages into a huge page, and assumes
the huge page is up-to-date. This will NOT corrupt data in the disk,
because the page is read-only and never written back. Fix this by
properly checking PageUptodate() after locking the page. This check
replaces "VM_BUG_ON_PAGE(!PageUptodate(page), page);".
Also, move PageDirty() check after locking the page. Current khugepaged
should not try to collapse dirty file THP, because it is limited to
read-only .text. The only case we hit a dirty page here is when the
page hasn't been written since write. Bail out and retry when this
happens.
syzbot reported bug on previous version of this patch.
Link: http://lkml.kernel.org/r/20191106060930.2571389-2-songliubraving@fb.com
Fixes: 99cb0dbd47 ("mm,thp: add read-only THP support for (non-shmem) FS")
Signed-off-by: Song Liu <songliubraving@fb.com>
Reported-by: syzbot+efb9e48b9fbdc49bb34a@syzkaller.appspotmail.com
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: William Kucharski <william.kucharski@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Commit 1b7e816fc8 ("mm: slub: Fix slab walking for init_on_free")
fixed one problem with the slab walking but missed a key detail: When
walking the list, the head and tail pointers need to be updated since we
end up reversing the list as a result. Without doing this, bulk free is
broken.
One way this is exposed is a NULL pointer with slub_debug=F:
=============================================================================
BUG skbuff_head_cache (Tainted: G T): Object already free
-----------------------------------------------------------------------------
INFO: Slab 0x000000000d2d2f8f objects=16 used=3 fp=0x0000000064309071 flags=0x3fff00000000201
BUG: kernel NULL pointer dereference, address: 0000000000000000
Oops: 0000 [#1] PREEMPT SMP PTI
RIP: 0010:print_trailer+0x70/0x1d5
Call Trace:
<IRQ>
free_debug_processing.cold.37+0xc9/0x149
__slab_free+0x22a/0x3d0
kmem_cache_free_bulk+0x415/0x420
__kfree_skb_flush+0x30/0x40
net_rx_action+0x2dd/0x480
__do_softirq+0xf0/0x246
irq_exit+0x93/0xb0
do_IRQ+0xa0/0x110
common_interrupt+0xf/0xf
</IRQ>
Given we're now almost identical to the existing debugging code which
correctly walks the list, combine with that.
Link: https://lkml.kernel.org/r/20191104170303.GA50361@gandi.net
Link: http://lkml.kernel.org/r/20191106222208.26815-1-labbott@redhat.com
Fixes: 1b7e816fc8 ("mm: slub: Fix slab walking for init_on_free")
Signed-off-by: Laura Abbott <labbott@redhat.com>
Reported-by: Thibaut Sautereau <thibaut.sautereau@clip-os.org>
Acked-by: David Rientjes <rientjes@google.com>
Tested-by: Alexander Potapenko <glider@google.com>
Acked-by: Alexander Potapenko <glider@google.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: <clipos@ssi.gouv.fr>
Cc: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
An exiting task might belong to an offline cgroup. In this case an
attempt to grab a cgroup reference from the task can end up with an
infinite loop in hugetlb_cgroup_charge_cgroup(), because neither the
cgroup will become online, neither the task will be migrated to a live
cgroup.
Fix this by switching over to css_tryget(). As css_tryget_online()
can't guarantee that the cgroup won't go offline, in most cases the
check doesn't make sense. In this particular case users of
hugetlb_cgroup_charge_cgroup() are not affected by this change.
A similar problem is described by commit 18fa84a2db ("cgroup: Use
css_tryget() instead of css_tryget_online() in task_get_css()").
Link: http://lkml.kernel.org/r/20191106225131.3543616-2-guro@fb.com
Signed-off-by: Roman Gushchin <guro@fb.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
We've encountered a rcu stall in get_mem_cgroup_from_mm():
rcu: INFO: rcu_sched self-detected stall on CPU
rcu: 33-....: (21000 ticks this GP) idle=6c6/1/0x4000000000000002 softirq=35441/35441 fqs=5017
(t=21031 jiffies g=324821 q=95837) NMI backtrace for cpu 33
<...>
RIP: 0010:get_mem_cgroup_from_mm+0x2f/0x90
<...>
__memcg_kmem_charge+0x55/0x140
__alloc_pages_nodemask+0x267/0x320
pipe_write+0x1ad/0x400
new_sync_write+0x127/0x1c0
__kernel_write+0x4f/0xf0
dump_emit+0x91/0xc0
writenote+0xa0/0xc0
elf_core_dump+0x11af/0x1430
do_coredump+0xc65/0xee0
get_signal+0x132/0x7c0
do_signal+0x36/0x640
exit_to_usermode_loop+0x61/0xd0
do_syscall_64+0xd4/0x100
entry_SYSCALL_64_after_hwframe+0x44/0xa9
The problem is caused by an exiting task which is associated with an
offline memcg. We're iterating over and over in the do {} while
(!css_tryget_online()) loop, but obviously the memcg won't become online
and the exiting task won't be migrated to a live memcg.
Let's fix it by switching from css_tryget_online() to css_tryget().
As css_tryget_online() cannot guarantee that the memcg won't go offline,
the check is usually useless, except some rare cases when for example it
determines if something should be presented to a user.
A similar problem is described by commit 18fa84a2db ("cgroup: Use
css_tryget() instead of css_tryget_online() in task_get_css()").
Johannes:
: The bug aside, it doesn't matter whether the cgroup is online for the
: callers. It used to matter when offlining needed to evacuate all charges
: from the memcg, and so needed to prevent new ones from showing up, but we
: don't care now.
Link: http://lkml.kernel.org/r/20191106225131.3543616-1-guro@fb.com
Signed-off-by: Roman Gushchin <guro@fb.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Shakeel Butt <shakeeb@google.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Michal Koutn <mkoutny@suse.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Recently, I hit the following issue when running upstream.
kernel BUG at mm/vmscan.c:1521!
invalid opcode: 0000 [#1] SMP KASAN PTI
CPU: 0 PID: 23385 Comm: syz-executor.6 Not tainted 5.4.0-rc4+ #1
RIP: 0010:shrink_page_list+0x12b6/0x3530 mm/vmscan.c:1521
Call Trace:
reclaim_pages+0x499/0x800 mm/vmscan.c:2188
madvise_cold_or_pageout_pte_range+0x58a/0x710 mm/madvise.c:453
walk_pmd_range mm/pagewalk.c:53 [inline]
walk_pud_range mm/pagewalk.c:112 [inline]
walk_p4d_range mm/pagewalk.c:139 [inline]
walk_pgd_range mm/pagewalk.c:166 [inline]
__walk_page_range+0x45a/0xc20 mm/pagewalk.c:261
walk_page_range+0x179/0x310 mm/pagewalk.c:349
madvise_pageout_page_range mm/madvise.c:506 [inline]
madvise_pageout+0x1f0/0x330 mm/madvise.c:542
madvise_vma mm/madvise.c:931 [inline]
__do_sys_madvise+0x7d2/0x1600 mm/madvise.c:1113
do_syscall_64+0x9f/0x4c0 arch/x86/entry/common.c:290
entry_SYSCALL_64_after_hwframe+0x49/0xbe
madvise_pageout() accesses the specified range of the vma and isolates
them, then runs shrink_page_list() to reclaim its memory. But it also
isolates the unevictable pages to reclaim. Hence, we can catch the
cases in shrink_page_list().
The root cause is that we scan the page tables instead of specific LRU
list. and so we need to filter out the unevictable lru pages from our
end.
Link: http://lkml.kernel.org/r/1572616245-18946-1-git-send-email-zhongjiang@huawei.com
Fixes: 1a4e58cce8 ("mm: introduce MADV_PAGEOUT")
Signed-off-by: zhong jiang <zhongjiang@huawei.com>
Suggested-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Minchan Kim <minchan@kernel.org>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Commit d883544515 ("mm: mempolicy: make the behavior consistent when
MPOL_MF_MOVE* and MPOL_MF_STRICT were specified") fixed the return value
of mbind() for a couple of corner cases. But, it altered the errno for
some other cases, for example, mbind() should return -EFAULT when part
or all of the memory range specified by nodemask and maxnode points
outside your accessible address space, or there was an unmapped hole in
the specified memory range specified by addr and len.
Fix this by preserving the errno returned by queue_pages_range(). And,
the pagelist may be not empty even though queue_pages_range() returns
error, put the pages back to LRU since mbind_range() is not called to
really apply the policy so those pages should not be migrated, this is
also the old behavior before the problematic commit.
Link: http://lkml.kernel.org/r/1572454731-3925-1-git-send-email-yang.shi@linux.alibaba.com
Fixes: d883544515 ("mm: mempolicy: make the behavior consistent when MPOL_MF_MOVE* and MPOL_MF_STRICT were specified")
Signed-off-by: Yang Shi <yang.shi@linux.alibaba.com>
Reported-by: Li Xinhai <lixinhai.lxh@gmail.com>
Reviewed-by: Li Xinhai <lixinhai.lxh@gmail.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: <stable@vger.kernel.org> [4.19 and 5.2+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Now that we have KERNEL_HEADER_TEST all headers are generally compile
tested, so relying on makefile tricks to avoid compiling code that depends
on CONFIG_MMU_NOTIFIER is more annoying.
Instead follow the usual pattern and provide most of the header with only
the functions stubbed out when CONFIG_MMU_NOTIFIER is disabled. This
ensures code compiles no matter what the config setting is.
While here, struct mmu_notifier_mm is private to mmu_notifier.c, move it.
Link: https://lore.kernel.org/r/20191112202231.3856-2-jgg@ziepe.ca
Reviewed-by: Jérôme Glisse <jglisse@redhat.com>
Tested-by: Ralph Campbell <rcampbell@nvidia.com>
Reviewed-by: John Hubbard <jhubbard@nvidia.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
One conflict in the BPF samples Makefile, some fixes in 'net' whilst
we were converting over to Makefile.target rules in 'net-next'.
Signed-off-by: David S. Miller <davem@davemloft.net>
While upgrading from 4.16 to 5.2, we noticed these allocation errors in
the log of the new kernel:
SLUB: Unable to allocate memory on node -1, gfp=0xa20(GFP_ATOMIC)
cache: tw_sock_TCPv6(960:helper-logs), object size: 232, buffer size: 240, default order: 1, min order: 0
node 0: slabs: 5, objs: 170, free: 0
slab_out_of_memory+1
___slab_alloc+969
__slab_alloc+14
kmem_cache_alloc+346
inet_twsk_alloc+60
tcp_time_wait+46
tcp_fin+206
tcp_data_queue+2034
tcp_rcv_state_process+784
tcp_v6_do_rcv+405
__release_sock+118
tcp_close+385
inet_release+46
__sock_release+55
sock_close+17
__fput+170
task_work_run+127
exit_to_usermode_loop+191
do_syscall_64+212
entry_SYSCALL_64_after_hwframe+68
accompanied by an increase in machines going completely radio silent
under memory pressure.
One thing that changed since 4.16 is e699e2c6a6 ("net, mm: account
sock objects to kmemcg"), which made these slab caches subject to cgroup
memory accounting and control.
The problem with that is that cgroups, unlike the page allocator, do not
maintain dedicated atomic reserves. As a cgroup's usage hovers at its
limit, atomic allocations - such as done during network rx - can fail
consistently for extended periods of time. The kernel is not able to
operate under these conditions.
We don't want to revert the culprit patch, because it indeed tracks a
potentially substantial amount of memory used by a cgroup.
We also don't want to implement dedicated atomic reserves for cgroups.
There is no point in keeping a fixed margin of unused bytes in the
cgroup's memory budget to accomodate a consumer that is impossible to
predict - we'd be wasting memory and get into configuration headaches,
not unlike what we have going with min_free_kbytes. We do this for
physical mem because we have to, but cgroups are an accounting game.
Instead, account these privileged allocations to the cgroup, but let
them bypass the configured limit if they have to. This way, we get the
benefits of accounting the consumed memory and have it exert pressure on
the rest of the cgroup, but like with the page allocator, we shift the
burden of reclaimining on behalf of atomic allocations onto the regular
allocations that can block.
Link: http://lkml.kernel.org/r/20191022233708.365764-1-hannes@cmpxchg.org
Fixes: e699e2c6a6 ("net, mm: account sock objects to kmemcg")
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Cc: Suleiman Souhlal <suleiman@google.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: <stable@vger.kernel.org> [4.18+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
We recently started updating the node span based on the zone span to
avoid touching uninitialized memmaps.
Currently, we will always detect the node span to start at 0, meaning a
node can easily span too many pages. pgdat_is_empty() will still work
correctly if all zones span no pages. We should skip over all zones
without spanned pages and properly handle the first detected zone that
spans pages.
Unfortunately, in contrast to the zone span (/proc/zoneinfo), the node
span cannot easily be inspected and tested. The node span gives no real
guarantees when an architecture supports memory hotplug, meaning it can
easily contain holes or span pages of different nodes.
The node span is not really used after init on architectures that
support memory hotplug.
E.g., we use it in mm/memory_hotplug.c:try_offline_node() and in
mm/kmemleak.c:kmemleak_scan(). These users seem to be fine.
Link: http://lkml.kernel.org/r/20191027222714.5313-1-david@redhat.com
Fixes: 00d6c019b5 ("mm/memory_hotplug: don't access uninitialized memmaps in shrink_pgdat_span()")
Signed-off-by: David Hildenbrand <david@redhat.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Pavel Tatashin <pasha.tatashin@soleen.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
page_cgroup_ino() doesn't return a valid memcg pointer for non-compound
slab pages, because it depends on PgHead AND PgSlab flags to be set to
determine the memory cgroup from the kmem_cache. It's correct for
compound pages, but not for generic small pages. Those don't have PgHead
set, so it ends up returning zero.
Fix this by replacing the condition to PageSlab() && !PageTail().
Before this patch:
[root@localhost ~]# ./page-types -c /sys/fs/cgroup/user.slice/user-0.slice/user@0.service/ | grep slab
0x0000000000000080 38 0 _______S___________________________________ slab
After this patch:
[root@localhost ~]# ./page-types -c /sys/fs/cgroup/user.slice/user-0.slice/user@0.service/ | grep slab
0x0000000000000080 147 0 _______S___________________________________ slab
Also, hwpoison_filter_task() uses output of page_cgroup_ino() in order
to filter error injection events based on memcg. So if
page_cgroup_ino() fails to return memcg pointer, we just fail to inject
memory error. Considering that hwpoison filter is for testing, affected
users are limited and the impact should be marginal.
[n-horiguchi@ah.jp.nec.com: changelog additions]
Link: http://lkml.kernel.org/r/20191031012151.2722280-1-guro@fb.com
Fixes: 4d96ba3530 ("mm: memcg/slab: stop setting page->mem_cgroup pointer for slab pages")
Signed-off-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Acked-by: David Rientjes <rientjes@google.com>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Cc: Daniel Jordan <daniel.m.jordan@oracle.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
While investigating a bug related to higher atomic allocation failures,
we noticed the failure warnings positively drowning the console, and in
our case trigger lockup warnings because of a serial console too slow to
handle all that output.
But even if we had a faster console, it's unclear what additional
information the current level of repetition provides.
Allocation failures happen for three reasons: The machine is OOM, the VM
is failing to handle reasonable requests, or somebody is making
unreasonable requests (and didn't acknowledge their opportunism with
__GFP_NOWARN). Having the memory dump, a callstack, and the ratelimit
stats on skipped failure warnings should provide enough information to
let users/admins/developers know whether something is wrong and point
them in the right direction for debugging, bpftracing etc.
Limit allocation failure warnings to one spew every ten seconds.
Link: http://lkml.kernel.org/r/20191028194906.26899-1-hannes@cmpxchg.org
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
pagetypeinfo_showfree_print is called by zone->lock held in irq mode.
This is not really nice because it blocks both any interrupts on that
cpu and the page allocator. On large machines this might even trigger
the hard lockup detector.
Considering the pagetypeinfo is a debugging tool we do not really need
exact numbers here. The primary reason to look at the outuput is to see
how pageblocks are spread among different migratetypes and low number of
pages is much more interesting therefore putting a bound on the number
of pages on the free_list sounds like a reasonable tradeoff.
The new output will simply tell
[...]
Node 6, zone Normal, type Movable >100000 >100000 >100000 >100000 41019 31560 23996 10054 3229 983 648
instead of
Node 6, zone Normal, type Movable 399568 294127 221558 102119 41019 31560 23996 10054 3229 983 648
The limit has been chosen arbitrary and it is a subject of a future
change should there be a need for that.
While we are at it, also drop the zone lock after each free_list
iteration which will help with the IRQ and page allocator responsiveness
even further as the IRQ lock held time is always bound to those 100k
pages.
[akpm@linux-foundation.org: tweak comment text, per David Hildenbrand]
Link: http://lkml.kernel.org/r/20191025072610.18526-3-mhocko@kernel.org
Signed-off-by: Michal Hocko <mhocko@suse.com>
Suggested-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Waiman Long <longman@redhat.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: David Hildenbrand <david@redhat.com>
Acked-by: Rafael Aquini <aquini@redhat.com>
Acked-by: David Rientjes <rientjes@google.com>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Jann Horn <jannh@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Roman Gushchin <guro@fb.com>
Cc: Song Liu <songliubraving@fb.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Deferred memory initialisation updates zone->managed_pages during the
initialisation phase but before that finishes, the per-cpu page
allocator (pcpu) calculates the number of pages allocated/freed in
batches as well as the maximum number of pages allowed on a per-cpu
list. As zone->managed_pages is not up to date yet, the pcpu
initialisation calculates inappropriately low batch and high values.
This increases zone lock contention quite severely in some cases with
the degree of severity depending on how many CPUs share a local zone and
the size of the zone. A private report indicated that kernel build
times were excessive with extremely high system CPU usage. A perf
profile indicated that a large chunk of time was lost on zone->lock
contention.
This patch recalculates the pcpu batch and high values after deferred
initialisation completes for every populated zone in the system. It was
tested on a 2-socket AMD EPYC 2 machine using a kernel compilation
workload -- allmodconfig and all available CPUs.
mmtests configuration: config-workload-kernbench-max Configuration was
modified to build on a fresh XFS partition.
kernbench
5.4.0-rc3 5.4.0-rc3
vanilla resetpcpu-v2
Amean user-256 13249.50 ( 0.00%) 16401.31 * -23.79%*
Amean syst-256 14760.30 ( 0.00%) 4448.39 * 69.86%*
Amean elsp-256 162.42 ( 0.00%) 119.13 * 26.65%*
Stddev user-256 42.97 ( 0.00%) 19.15 ( 55.43%)
Stddev syst-256 336.87 ( 0.00%) 6.71 ( 98.01%)
Stddev elsp-256 2.46 ( 0.00%) 0.39 ( 84.03%)
5.4.0-rc3 5.4.0-rc3
vanilla resetpcpu-v2
Duration User 39766.24 49221.79
Duration System 44298.10 13361.67
Duration Elapsed 519.11 388.87
The patch reduces system CPU usage by 69.86% and total build time by
26.65%. The variance of system CPU usage is also much reduced.
Before, this was the breakdown of batch and high values over all zones
was:
256 batch: 1
256 batch: 63
512 batch: 7
256 high: 0
256 high: 378
512 high: 42
512 pcpu pagesets had a batch limit of 7 and a high limit of 42. After
the patch:
256 batch: 1
768 batch: 63
256 high: 0
768 high: 378
[mgorman@techsingularity.net: fix merge/linkage snafu]
Link: http://lkml.kernel.org/r/20191023084705.GD3016@techsingularity.netLink: http://lkml.kernel.org/r/20191021094808.28824-2-mgorman@techsingularity.net
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Acked-by: Michal Hocko <mhocko@suse.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: Matt Fleming <matt@codeblueprint.co.uk>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Qian Cai <cai@lca.pw>
Cc: <stable@vger.kernel.org> [4.1+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Add two utilities to 1) write-protect and 2) clean all ptes pointing into
a range of an address space.
The utilities are intended to aid in tracking dirty pages (either
driver-allocated system memory or pci device memory).
The write-protect utility should be used in conjunction with
page_mkwrite() and pfn_mkwrite() to trigger write page-faults on page
accesses. Typically one would want to use this on sparse accesses into
large memory regions. The clean utility should be used to utilize
hardware dirtying functionality and avoid the overhead of page-faults,
typically on large accesses into small memory regions.
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rik van Riel <riel@surriel.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Huang Ying <ying.huang@intel.com>
Cc: Jérôme Glisse <jglisse@redhat.com>
Cc: Kirill A. Shutemov <kirill@shutemov.name>
Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com>
Acked-by: Andrew Morton <akpm@linux-foundation.org>
Add two new probe_kernel_read_strict() and strncpy_from_unsafe_strict()
helpers which by default alias to the __probe_kernel_read() and the
__strncpy_from_unsafe(), respectively, but can be overridden by archs
which have non-overlapping address ranges for kernel space and user
space in order to bail out with -EFAULT when attempting to probe user
memory including non-canonical user access addresses [0]:
4-level page tables:
user-space mem: 0x0000000000000000 - 0x00007fffffffffff
non-canonical: 0x0000800000000000 - 0xffff7fffffffffff
5-level page tables:
user-space mem: 0x0000000000000000 - 0x00ffffffffffffff
non-canonical: 0x0100000000000000 - 0xfeffffffffffffff
The idea is that these helpers are complementary to the probe_user_read()
and strncpy_from_unsafe_user() which probe user-only memory. Both added
helpers here do the same, but for kernel-only addresses.
Both set of helpers are going to be used for BPF tracing. They also
explicitly avoid throwing the splat for non-canonical user addresses from
00c42373d3 ("x86-64: add warning for non-canonical user access address
dereferences").
For compat, the current probe_kernel_read() and strncpy_from_unsafe() are
left as-is.
[0] Documentation/x86/x86_64/mm.txt
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: x86@kernel.org
Link: https://lore.kernel.org/bpf/eefeefd769aa5a013531f491a71f0936779e916b.1572649915.git.daniel@iogearbox.net
Commit 3d7081822f ("uaccess: Add non-pagefault user-space read functions")
missed to add probe write function, therefore factor out a probe_write_common()
helper with most logic of probe_kernel_write() except setting KERNEL_DS, and
add a new probe_user_write() helper so it can be used from BPF side.
Again, on some archs, the user address space and kernel address space can
co-exist and be overlapping, so in such case, setting KERNEL_DS would mean
that the given address is treated as being in kernel address space.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Link: https://lore.kernel.org/bpf/9df2542e68141bfa3addde631441ee45503856a8.1572649915.git.daniel@iogearbox.net
If a device driver like nouveau tries to use hmm_range_fault() to access
the special shared zero page in system memory, hmm_range_fault() will
return -EFAULT and kill the process.
Allow hmm_range_fault() to return success (0) when the CPU pagetable entry
points to the special shared zero page.
page_to_pfn() and pfn_to_page() are defined on the zero page so just
handle it like any other page.
Link: https://lore.kernel.org/r/20191023195515.13168-3-rcampbell@nvidia.com
Signed-off-by: Ralph Campbell <rcampbell@nvidia.com>
Reviewed-by: "Jérôme Glisse" <jglisse@redhat.com>
Acked-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Uninitialized memmaps contain garbage and in the worst case trigger
kernel BUGs, especially with CONFIG_PAGE_POISONING. They should not get
touched.
Let's make sure that we only consider online memory (managed by the
buddy) that has initialized memmaps. ZONE_DEVICE is not applicable.
page_zone() will call page_to_nid(), which will trigger
VM_BUG_ON_PGFLAGS(PagePoisoned(page), page) with CONFIG_PAGE_POISONING
and CONFIG_DEBUG_VM_PGFLAGS when called on uninitialized memmaps. This
can be the case when an offline memory block (e.g., never onlined) is
spanned by a zone.
Note: As explained by Michal in [1], alloc_contig_range() will verify
the range. So it boils down to the wrong access in this function.
[1] http://lkml.kernel.org/r/20180423000943.GO17484@dhcp22.suse.cz
Link: http://lkml.kernel.org/r/20191015120717.4858-1-david@redhat.com
Fixes: f1dd2cd13c ("mm, memory_hotplug: do not associate hotadded memory to zones until online") [visible after d0dc12e86b]
Signed-off-by: David Hildenbrand <david@redhat.com>
Reported-by: Michal Hocko <mhocko@kernel.org>
Acked-by: Michal Hocko <mhocko@suse.com>
Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: <stable@vger.kernel.org> [4.13+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Until commit 92d12f9544 ("memblock: refactor internal allocation
functions") the maximal address for memblock allocations was forced to
memblock.current_limit only for the allocation functions returning
virtual address. The changes introduced by that commit moved the limit
enforcement into the allocation core and as a result the allocation
functions returning physical address also started to limit allocations
to memblock.current_limit.
This caused breakage of etnaviv GPU driver:
etnaviv etnaviv: bound 130000.gpu (ops gpu_ops)
etnaviv etnaviv: bound 134000.gpu (ops gpu_ops)
etnaviv etnaviv: bound 2204000.gpu (ops gpu_ops)
etnaviv-gpu 130000.gpu: model: GC2000, revision: 5108
etnaviv-gpu 130000.gpu: command buffer outside valid memory window
etnaviv-gpu 134000.gpu: model: GC320, revision: 5007
etnaviv-gpu 134000.gpu: command buffer outside valid memory window
etnaviv-gpu 2204000.gpu: model: GC355, revision: 1215
etnaviv-gpu 2204000.gpu: Ignoring GPU with VG and FE2.0
Restore the behaviour of memblock_phys* family so that these functions
will not enforce memblock.current_limit.
Link: http://lkml.kernel.org/r/1570915861-17633-1-git-send-email-rppt@kernel.org
Fixes: 92d12f9544 ("memblock: refactor internal allocation functions")
Signed-off-by: Mike Rapoport <rppt@linux.ibm.com>
Reported-by: Adam Ford <aford173@gmail.com>
Tested-by: Adam Ford <aford173@gmail.com> [imx6q-logicpd]
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Fabio Estevam <festevam@gmail.com>
Cc: Lucas Stach <l.stach@pengutronix.de>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Commit 1a61ab8038 ("mm: memcontrol: replace zone summing with
lruvec_page_state()") has made lruvec_page_state to use per-cpu counters
instead of calculating it directly from lru_zone_size with an idea that
this would be more effective.
Tim has reported that this is not really the case for their database
benchmark which is showing an opposite results where lruvec_page_state
is taking up a huge chunk of CPU cycles (about 25% of the system time
which is roughly 7% of total cpu cycles) on 5.3 kernels. The workload
is running on a larger machine (96cpus), it has many cgroups (500) and
it is heavily direct reclaim bound.
Tim Chen said:
: The problem can also be reproduced by running simple multi-threaded
: pmbench benchmark with a fast Optane SSD swap (see profile below).
:
:
: 6.15% 3.08% pmbench [kernel.vmlinux] [k] lruvec_lru_size
: |
: |--3.07%--lruvec_lru_size
: | |
: | |--2.11%--cpumask_next
: | | |
: | | --1.66%--find_next_bit
: | |
: | --0.57%--call_function_interrupt
: | |
: | --0.55%--smp_call_function_interrupt
: |
: |--1.59%--0x441f0fc3d009
: | _ops_rdtsc_init_base_freq
: | access_histogram
: | page_fault
: | __do_page_fault
: | handle_mm_fault
: | __handle_mm_fault
: | |
: | --1.54%--do_swap_page
: | swapin_readahead
: | swap_cluster_readahead
: | |
: | --1.53%--read_swap_cache_async
: | __read_swap_cache_async
: | alloc_pages_vma
: | __alloc_pages_nodemask
: | __alloc_pages_slowpath
: | try_to_free_pages
: | do_try_to_free_pages
: | shrink_node
: | shrink_node_memcg
: | |
: | |--0.77%--lruvec_lru_size
: | |
: | --0.76%--inactive_list_is_low
: | |
: | --0.76%--lruvec_lru_size
: |
: --1.50%--measure_read
: page_fault
: __do_page_fault
: handle_mm_fault
: __handle_mm_fault
: do_swap_page
: swapin_readahead
: swap_cluster_readahead
: |
: --1.48%--read_swap_cache_async
: __read_swap_cache_async
: alloc_pages_vma
: __alloc_pages_nodemask
: __alloc_pages_slowpath
: try_to_free_pages
: do_try_to_free_pages
: shrink_node
: shrink_node_memcg
: |
: |--0.75%--inactive_list_is_low
: | |
: | --0.75%--lruvec_lru_size
: |
: --0.73%--lruvec_lru_size
The likely culprit is the cache traffic the lruvec_page_state_local
generates. Dave Hansen says:
: I was thinking purely of the cache footprint. If it's reading
: pn->lruvec_stat_local->count[idx] is three separate cachelines, so 192
: bytes of cache *96 CPUs = 18k of data, mostly read-only. 1 cgroup would
: be 18k of data for the whole system and the caching would be pretty
: efficient and all 18k would probably survive a tight page fault loop in
: the L1. 500 cgroups would be ~90k of data per CPU thread which doesn't
: fit in the L1 and probably wouldn't survive a tight page fault loop if
: both logical threads were banging on different cgroups.
:
: It's just a theory, but it's why I noted the number of cgroups when I
: initially saw this show up in profiles
Fix the regression by partially reverting the said commit and calculate
the lru size explicitly.
Link: http://lkml.kernel.org/r/20190905071034.16822-1-honglei.wang@oracle.com
Fixes: 1a61ab8038 ("mm: memcontrol: replace zone summing with lruvec_page_state()")
Signed-off-by: Honglei Wang <honglei.wang@oracle.com>
Reported-by: Tim Chen <tim.c.chen@linux.intel.com>
Acked-by: Tim Chen <tim.c.chen@linux.intel.com>
Tested-by: Tim Chen <tim.c.chen@linux.intel.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Roman Gushchin <guro@fb.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: <stable@vger.kernel.org> [5.2+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
