| Age | Commit message (Collapse) | Author | Files | Lines |
|---|
|
Batched completions can clear multiple bits, but we're only decrementing
the wait_cnt by one each time. This can cause waiters to never be woken,
stalling IO. Use the batched count instead.
Link: https://bugzilla.kernel.org/show_bug.cgi?id=215679
Signed-off-by: Keith Busch <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Jens Axboe <[email protected]>
|
|
Use try_cmpxchg instead of cmpxchg (*ptr, old, new) == old in
set_mask_bits and bit_clear_unless. x86 CMPXCHG instruction returns
success in ZF flag, so this change saves a compare after cmpxchg (and
related move instruction in front of cmpxchg).
Also, try_cmpxchg implicitly assigns old *ptr value to "old" when cmpxchg
fails, enabling further code simplifications.
Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Uros Bizjak <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
|
|
Use atomic64_try_cmpxchg instead of
atomic64_cmpxchg (*ptr, old, new) == old in inode_set_max_iversion_raw,
inode_maybe_inc_version and inode_query_iversion. x86 CMPXCHG instruction
returns success in ZF flag, so this change saves a compare after cmpxchg
(and related move instruction in front of cmpxchg).
Also, try_cmpxchg implicitly assigns old *ptr value to "old" when cmpxchg
fails, enabling further code simplifications.
The loop in inode_maybe_inc_iversion improves from:
5563: 48 89 ca mov %rcx,%rdx
5566: 48 89 c8 mov %rcx,%rax
5569: 48 83 e2 fe and $0xfffffffffffffffe,%rdx
556d: 48 83 c2 02 add $0x2,%rdx
5571: f0 48 0f b1 16 lock cmpxchg %rdx,(%rsi)
5576: 48 39 c1 cmp %rax,%rcx
5579: 0f 84 85 fc ff ff je 5204 <...>
557f: 48 89 c1 mov %rax,%rcx
5582: eb df jmp 5563 <...>
to:
5563: 48 89 c2 mov %rax,%rdx
5566: 48 83 e2 fe and $0xfffffffffffffffe,%rdx
556a: 48 83 c2 02 add $0x2,%rdx
556e: f0 48 0f b1 11 lock cmpxchg %rdx,(%rcx)
5573: 0f 84 8b fc ff ff je 5204 <...>
5579: eb e8 jmp 5563 <...>
Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Uros Bizjak <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
|
|
Only x86 has own release_thread(), introduce a new weak release_thread()
function to clean empty definitions in other ARCHs.
Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Kefeng Wang <[email protected]>
Acked-by: Guo Ren <[email protected]> [csky]
Acked-by: Russell King (Oracle) <[email protected]>
Acked-by: Geert Uytterhoeven <[email protected]>
Acked-by: Brian Cain <[email protected]>
Acked-by: Michael Ellerman <[email protected]> [powerpc]
Acked-by: Stafford Horne <[email protected]> [openrisc]
Acked-by: Catalin Marinas <[email protected]> [arm64]
Acked-by: Huacai Chen <[email protected]> [LoongArch]
Cc: Alexander Gordeev <[email protected]>
Cc: Anton Ivanov <[email protected]>
Cc: Borislav Petkov <[email protected]>
Cc: Christian Borntraeger <[email protected]>
Cc: Christophe Leroy <[email protected]>
Cc: Chris Zankel <[email protected]>
Cc: Dave Hansen <[email protected]>
Cc: "David S. Miller" <[email protected]>
Cc: Dinh Nguyen <[email protected]>
Cc: Guo Ren <[email protected]> [csky]
Cc: Heiko Carstens <[email protected]>
Cc: Helge Deller <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: Ivan Kokshaysky <[email protected]>
Cc: James Bottomley <[email protected]>
Cc: Johannes Berg <[email protected]>
Cc: Jonas Bonn <[email protected]>
Cc: Matt Turner <[email protected]>
Cc: Max Filippov <[email protected]>
Cc: Michal Simek <[email protected]>
Cc: Nicholas Piggin <[email protected]>
Cc: Palmer Dabbelt <[email protected]>
Cc: Paul Walmsley <[email protected]>
Cc: Richard Henderson <[email protected]>
Cc: Richard Weinberger <[email protected]>
Cc: Rich Felker <[email protected]>
Cc: Stefan Kristiansson <[email protected]>
Cc: Sven Schnelle <[email protected]>
Cc: Thomas Bogendoerfer <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: Vasily Gorbik <[email protected]>
Cc: Vineet Gupta <[email protected]>
Cc: Will Deacon <[email protected]>
Cc: Xuerui Wang <[email protected]>
Cc: Yoshinori Sato <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
|
|
Patch series "kexec, panic: Making crash_kexec() NMI safe", v4.
This patch (of 2):
Most acquistions of kexec_mutex are done via mutex_trylock() - those were
a direct "translation" from:
8c5a1cf0ad3a ("kexec: use a mutex for locking rather than xchg()")
there have however been two additions since then that use mutex_lock():
crash_get_memory_size() and crash_shrink_memory().
A later commit will replace said mutex with an atomic variable, and
locking operations will become atomic_cmpxchg(). Rather than having those
mutex_lock() become while (atomic_cmpxchg(&lock, 0, 1)), turn them into
trylocks that can return -EBUSY on acquisition failure.
This does halve the printable size of the crash kernel, but that's still
neighbouring 2G for 32bit kernels which should be ample enough.
Link: https://lkml.kernel.org/r/[email protected]
Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Valentin Schneider <[email protected]>
Cc: Arnd Bergmann <[email protected]>
Cc: "Eric W . Biederman" <[email protected]>
Cc: Juri Lelli <[email protected]>
Cc: Luis Claudio R. Goncalves <[email protected]>
Cc: Miaohe Lin <[email protected]>
Cc: Petr Mladek <[email protected]>
Cc: Sebastian Andrzej Siewior <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: Baoquan He <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
|
|
commit 6c287605fd56 ("mm: remember exclusively mapped anonymous pages with
PG_anon_exclusive") made sure that when PageAnonExclusive() has to be
cleared during temporary unmapping of a page, that the PTE is
cleared/invalidated and that the TLB is flushed.
What we want to achieve in all cases is that we cannot end up with a pin on
an anonymous page that may be shared, because such pins would be
unreliable and could result in memory corruptions when the mapped page
and the pin go out of sync due to a write fault.
That TLB flush handling was inspired by an outdated comment in
mm/ksm.c:write_protect_page(), which similarly required the TLB flush in
the past to synchronize with GUP-fast. However, ever since general RCU GUP
fast was introduced in commit 2667f50e8b81 ("mm: introduce a general RCU
get_user_pages_fast()"), a TLB flush is no longer sufficient to handle
concurrent GUP-fast in all cases -- it only handles traditional IPI-based
GUP-fast correctly.
Peter Xu (thankfully) questioned whether that TLB flush is really
required. On architectures that send an IPI broadcast on TLB flush,
it works as expected. To synchronize with RCU GUP-fast properly, we're
conceptually fine, however, we have to enforce a certain memory order and
are missing memory barriers.
Let's document that, avoid the TLB flush where possible and use proper
explicit memory barriers where required. We shouldn't really care about the
additional memory barriers here, as we're not on extremely hot paths --
and we're getting rid of some TLB flushes.
We use a smp_mb() pair for handling concurrent pinning and a
smp_rmb()/smp_wmb() pair for handling the corner case of only temporary
PTE changes but permanent PageAnonExclusive changes.
One extreme example, whereby GUP-fast takes a R/O pin and KSM wants to
convert an exclusive anonymous page to a KSM page, and that page is already
mapped write-protected (-> no PTE change) would be:
Thread 0 (KSM) Thread 1 (GUP-fast)
(B1) Read the PTE
# (B2) skipped without FOLL_WRITE
(A1) Clear PTE
smp_mb()
(A2) Check pinned
(B3) Pin the mapped page
smp_mb()
(A3) Clear PageAnonExclusive
smp_wmb()
(A4) Restore PTE
(B4) Check if the PTE changed
smp_rmb()
(B5) Check PageAnonExclusive
Thread 1 will properly detect that PageAnonExclusive was cleared and
back off.
Note that we don't need a memory barrier between checking if the page is
pinned and clearing PageAnonExclusive, because stores are not
speculated.
The possible issues due to reordering are of theoretical nature so far
and attempts to reproduce the race failed.
Especially the "no PTE change" case isn't the common case, because we'd
need an exclusive anonymous page that's mapped R/O and the PTE is clean
in KSM code -- and using KSM with page pinning isn't extremely common.
Further, the clear+TLB flush we used for now implies a memory barrier.
So the problematic missing part should be the missing memory barrier
after pinning but before checking if the PTE changed.
Link: https://lkml.kernel.org/r/[email protected]
Fixes: 6c287605fd56 ("mm: remember exclusively mapped anonymous pages with PG_anon_exclusive")
Signed-off-by: David Hildenbrand <[email protected]>
Cc: Jason Gunthorpe <[email protected]>
Cc: John Hubbard <[email protected]>
Cc: Andrea Arcangeli <[email protected]>
Cc: Hugh Dickins <[email protected]>
Cc: Peter Xu <[email protected]>
Cc: Alistair Popple <[email protected]>
Cc: Nadav Amit <[email protected]>
Cc: Yang Shi <[email protected]>
Cc: Vlastimil Babka <[email protected]>
Cc: Michal Hocko <[email protected]>
Cc: Mike Kravetz <[email protected]>
Cc: Andrea Parri <[email protected]>
Cc: Will Deacon <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: "Paul E. McKenney" <[email protected]>
Cc: Christoph von Recklinghausen <[email protected]>
Cc: Don Dutile <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
|
|
Patch series "A few cleanup patches for hugetlb", v2.
This series contains a few cleanup patches to use helper functions to
simplify the codes, remove unneeded nid parameter and so on. More
details can be found in the respective changelogs.
This patch (of 10):
Make hugetlb_cma_check() static as it's only used inside mm/hugetlb.c.
Link: https://lkml.kernel.org/r/[email protected]
Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Miaohe Lin <[email protected]>
Reviewed-by: Muchun Song <[email protected]>
Cc: Mike Kravetz <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
|
|
bh_submit_read() has no user anymore, just remove it.
Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Zhang Yi <[email protected]>
Reviewed-by: Jan Kara <[email protected]>
Reviewed-by: Christoph Hellwig <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
|
|
Now that all ll_rw_block() users has been replaced to new safe helpers,
we just remove it here.
Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Zhang Yi <[email protected]>
Reviewed-by: Jan Kara <[email protected]>
Reviewed-by: Christoph Hellwig <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
|
|
Current ll_rw_block() helper is fragile because it assumes that locked
buffer means it's under IO which is submitted by some other who holds
the lock, it skip buffer if it failed to get the lock, so it's only
safe on the readahead path. Unfortunately, now that most filesystems
still use this helper mistakenly on the sync metadata read path. There
is no guarantee that the one who holds the buffer lock always submit IO
(e.g. buffer_migrate_folio_norefs() after commit 88dbcbb3a484 ("blkdev:
avoid migration stalls for blkdev pages"), it could lead to false
positive -EIO when submitting reading IO.
This patch add some friendly buffer read helpers to prepare replacing
ll_rw_block() and similar calls. We can only call bh_readahead_[]
helpers for the readahead paths.
Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Zhang Yi <[email protected]>
Reviewed-by: Jan Kara <[email protected]>
Reviewed-by: Christoph Hellwig <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
|
|
Patch series "fs/buffer: remove ll_rw_block()", v2.
ll_rw_block() will skip locked buffer before submitting IO, it assumes
that locked buffer means it is under IO. This assumption is not always
true because we cannot guarantee every buffer lock path would submit IO.
After commit 88dbcbb3a484 ("blkdev: avoid migration stalls for blkdev
pages"), buffer_migrate_folio_norefs() becomes one exceptional case, and
there may be others. So ll_rw_block() is not safe on the sync read path,
we could get false positive EIO return value when filesystem reading
metadata. It seems that it could be only used on the readahead path.
Unfortunately, many filesystem misuse the ll_rw_block() on the sync read
path. This patch set just remove ll_rw_block() and add new friendly
helpers, which could prevent false positive EIO on the read metadata path.
Thanks for the suggestion from Jan, the original discussion is at [1].
patch 1: remove unused helpers in fs/buffer.c
patch 2: add new bh_read_[*] helpers
patch 3-11: remove all ll_rw_block() calls in filesystems
patch 12-14: do some leftover cleanups.
[1]. https://lore.kernel.org/linux-mm/[email protected]/
This patch (of 14):
No one use __breadahead_gfp() and sb_breadahead_unmovable() any more,
remove them.
Link: https://lkml.kernel.org/r/[email protected]
Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Zhang Yi <[email protected]>
Reviewed-by: Jan Kara <[email protected]>
Reviewed-by: Christoph Hellwig <[email protected]>
Cc: Alexander Viro <[email protected]>
Cc: Andreas Gruenbacher <[email protected]>
Cc: Bob Peterson <[email protected]>
Cc: Evgeniy Dushistov <[email protected]>
Cc: Heming Zhao <[email protected]>
Cc: Jens Axboe <[email protected]>
Cc: Konstantin Komarov <[email protected]>
Cc: Mark Fasheh <[email protected]>
Cc: Theodore Ts'o <[email protected]>
Cc: Yu Kuai <[email protected]>
Cc: Zhihao Cheng <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
|
|
Simplify code by removing redundant CONFIG_TRANSPARENT_HUGEPAGE judgment.
No functional change.
Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Liu Shixin <[email protected]>
Cc: Kefeng Wang <[email protected]>
Cc: Matthew Wilcox <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
|
|
Simplify code of has_transparent_hugepage define by using IS_BUILTIN.
No functional change.
Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Liu Shixin <[email protected]>
Reviewed-by: David Hildenbrand <[email protected]>
Cc: Hugh Dickins <[email protected]>
Cc: Kefeng Wang <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
|
|
kswapd_run/stop() will set pgdat->kswapd to NULL, which could race with
kswapd_is_running() in kcompactd(),
kswapd_run/stop() kcompactd()
kswapd_is_running()
pgdat->kswapd // error or nomal ptr
verify pgdat->kswapd
// load non-NULL
pgdat->kswapd
pgdat->kswapd = NULL
task_is_running(pgdat->kswapd)
// Null pointer derefence
KASAN reports the null-ptr-deref shown below,
vmscan: Failed to start kswapd on node 0
...
BUG: KASAN: null-ptr-deref in kcompactd+0x440/0x504
Read of size 8 at addr 0000000000000024 by task kcompactd0/37
CPU: 0 PID: 37 Comm: kcompactd0 Kdump: loaded Tainted: G OE 5.10.60 #1
Hardware name: QEMU KVM Virtual Machine, BIOS 0.0.0 02/06/2015
Call trace:
dump_backtrace+0x0/0x394
show_stack+0x34/0x4c
dump_stack+0x158/0x1e4
__kasan_report+0x138/0x140
kasan_report+0x44/0xdc
__asan_load8+0x94/0xd0
kcompactd+0x440/0x504
kthread+0x1a4/0x1f0
ret_from_fork+0x10/0x18
At present kswapd/kcompactd_run() and kswapd/kcompactd_stop() are protected
by mem_hotplug_begin/done(), but without kcompactd(). There is no need to
involve memory hotplug lock in kcompactd(), so let's add a new mutex to
protect pgdat->kswapd accesses.
Also, because the kcompactd task will check the state of kswapd task, it's
better to call kcompactd_stop() before kswapd_stop() to reduce lock
conflicts.
[[email protected]: add comments]
Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Kefeng Wang <[email protected]>
Cc: David Hildenbrand <[email protected]>
Cc: Muchun Song <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
|
|
Directly check state of struct memory_block, no need a single function.
Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Kefeng Wang <[email protected]>
Reviewed-by: David Hildenbrand <[email protected]>
Reviewed-by: Oscar Salvador <[email protected]>
Reviewed-by: Anshuman Khandual <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
|
|
All callers of find_get_pages_contig() have been removed, so it is no
longer needed.
Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Vishal Moola (Oracle) <[email protected]>
Cc: Al Viro <[email protected]>
Cc: Chris Mason <[email protected]>
Cc: David Sterba <[email protected]>
Cc: David Sterba <[email protected]>
Cc: Josef Bacik <[email protected]>
Cc: Matthew Wilcox <[email protected]>
Cc: Ryusuke Konishi <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
|
|
Patch series "Convert to filemap_get_folios_contig()", v3.
This patch series replaces find_get_pages_contig() with
filemap_get_folios_contig().
This patch (of 7):
This function is meant to replace find_get_pages_contig().
Unlike find_get_pages_contig(), filemap_get_folios_contig() no longer
takes in a target number of pages to find - It returns up to 15 contiguous
folios.
To be more consistent with filemap_get_folios(),
filemap_get_folios_contig() now also updates the start index passed in,
and takes an end index.
Link: https://lkml.kernel.org/r/[email protected]
Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Vishal Moola (Oracle) <[email protected]>
Cc: Chris Mason <[email protected]>
Cc: Josef Bacik <[email protected]>
Cc: David Sterba <[email protected]>
Cc: Ryusuke Konishi <[email protected]>
Cc: Al Viro <[email protected]>
Cc: Matthew Wilcox <[email protected]>
Cc: David Sterba <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
|
|
In commit 2f1ee0913ce5 ("Revert "mm: use early_pfn_to_nid in
page_ext_init""), we call page_ext_init() after page_alloc_init_late() to
avoid some panic problem. It seems that we cannot track early page
allocations in current kernel even if page structure has been initialized
early.
This patch introduces a new boot parameter 'early_page_ext' to resolve
this problem. If we pass it to the kernel, page_ext_init() will be moved
up and the feature 'deferred initialization of struct pages' will be
disabled to initialize the page allocator early and prevent the panic
problem above. It can help us to catch early page allocations. This is
useful especially when we find that the free memory value is not the same
right after different kernel booting.
[[email protected]: fix section issue by removing __meminitdata]
Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Li Zhe <[email protected]>
Suggested-by: Michal Hocko <[email protected]>
Acked-by: Michal Hocko <[email protected]>
Acked-by: Vlastimil Babka <[email protected]>
Cc: Jason A. Donenfeld <[email protected]>
Cc: Jonathan Corbet <[email protected]>
Cc: Kees Cook <[email protected]>
Cc: Mark-PK Tsai <[email protected]>
Cc: Masami Hiramatsu (Google) <[email protected]>
Cc: Steven Rostedt <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
|
|
For several years, MEMCG_CHARGE_BATCH was kept at 32 but with bigger
machines and the network intensive workloads requiring througput in Gbps,
32 is too small and makes the memcg charging path a bottleneck. For now,
increase it to 64 for easy acceptance to 6.0. We will need to revisit
this in future for ever increasing demand of higher performance.
Please note that the memcg charge path drain the per-cpu memcg charge
stock, so there should not be any oom behavior change. Though it does
have impact on rstat flushing and high limit reclaim backoff.
To evaluate the impact of this optimization, on a 72 CPUs machine, we
ran the following workload in a three level of cgroup hierarchy.
$ netserver -6
# 36 instances of netperf with following params
$ netperf -6 -H ::1 -l 60 -t TCP_SENDFILE -- -m 10K
Results (average throughput of netperf):
Without (6.0-rc1) 10482.7 Mbps
With patch 17064.7 Mbps (62.7% improvement)
With the patch, the throughput improved by 62.7%.
Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Shakeel Butt <[email protected]>
Reported-by: kernel test robot <[email protected]>
Acked-by: Soheil Hassas Yeganeh <[email protected]>
Reviewed-by: Feng Tang <[email protected]>
Acked-by: Roman Gushchin <[email protected]>
Acked-by: Muchun Song <[email protected]>
Acked-by: Michal Hocko <[email protected]>
Cc: Eric Dumazet <[email protected]>
Cc: Johannes Weiner <[email protected]>
Cc: "Michal Koutný" <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
|
|
With memcg v2 enabled, memcg->memory.usage is a very hot member for the
workloads doing memcg charging on multiple CPUs concurrently.
Particularly the network intensive workloads. In addition, there is a
false cache sharing between memory.usage and memory.high on the charge
path. This patch moves the usage into a separate cacheline and move all
the read most fields into separate cacheline.
To evaluate the impact of this optimization, on a 72 CPUs machine, we ran
the following workload in a three level of cgroup hierarchy.
$ netserver -6
# 36 instances of netperf with following params
$ netperf -6 -H ::1 -l 60 -t TCP_SENDFILE -- -m 10K
Results (average throughput of netperf):
Without (6.0-rc1) 10482.7 Mbps
With patch 12413.7 Mbps (18.4% improvement)
With the patch, the throughput improved by 18.4%.
One side-effect of this patch is the increase in the size of struct
mem_cgroup. For example with this patch on 64 bit build, the size of
struct mem_cgroup increased from 4032 bytes to 4416 bytes. However for
the performance improvement, this additional size is worth it. In
addition there are opportunities to reduce the size of struct mem_cgroup
like deprecation of kmem and tcpmem page counters and better packing.
Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Shakeel Butt <[email protected]>
Reported-by: kernel test robot <[email protected]>
Reviewed-by: Feng Tang <[email protected]>
Acked-by: Soheil Hassas Yeganeh <[email protected]>
Acked-by: Roman Gushchin <[email protected]>
Acked-by: Michal Hocko <[email protected]>
Cc: Eric Dumazet <[email protected]>
Cc: Johannes Weiner <[email protected]>
Cc: "Michal Koutný" <[email protected]>
Cc: Muchun Song <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
|
|
Empty PTEs are passed to the pte_entry callback, not to pte_hole.
Link: https://lkml.kernel.org/r/3695521.kQq0lBPeGt@devpool047
Signed-off-by: Rolf Eike Beer <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
|
|
The below is one path where race between page_ext and offline of the
respective memory blocks will cause use-after-free on the access of
page_ext structure.
process1 process2
--------- ---------
a)doing /proc/page_owner doing memory offline
through offline_pages.
b) PageBuddy check is failed
thus proceed to get the
page_owner information
through page_ext access.
page_ext = lookup_page_ext(page);
migrate_pages();
.................
Since all pages are successfully
migrated as part of the offline
operation,send MEM_OFFLINE notification
where for page_ext it calls:
offline_page_ext()-->
__free_page_ext()-->
free_page_ext()-->
vfree(ms->page_ext)
mem_section->page_ext = NULL
c) Check for the PAGE_EXT
flags in the page_ext->flags
access results into the
use-after-free (leading to
the translation faults).
As mentioned above, there is really no synchronization between page_ext
access and its freeing in the memory_offline.
The memory offline steps(roughly) on a memory block is as below:
1) Isolate all the pages
2) while(1)
try free the pages to buddy.(->free_list[MIGRATE_ISOLATE])
3) delete the pages from this buddy list.
4) Then free page_ext.(Note: The struct page is still alive as it is
freed only during hot remove of the memory which frees the memmap,
which steps the user might not perform).
This design leads to the state where struct page is alive but the struct
page_ext is freed, where the later is ideally part of the former which
just representing the page_flags (check [3] for why this design is
chosen).
The abovementioned race is just one example __but the problem persists in
the other paths too involving page_ext->flags access(eg:
page_is_idle())__.
Fix all the paths where offline races with page_ext access by maintaining
synchronization with rcu lock and is achieved in 3 steps:
1) Invalidate all the page_ext's of the sections of a memory block by
storing a flag in the LSB of mem_section->page_ext.
2) Wait until all the existing readers to finish working with the
->page_ext's with synchronize_rcu(). Any parallel process that starts
after this call will not get page_ext, through lookup_page_ext(), for
the block parallel offline operation is being performed.
3) Now safely free all sections ->page_ext's of the block on which
offline operation is being performed.
Note: If synchronize_rcu() takes time then optimizations can be done in
this path through call_rcu()[2].
Thanks to David Hildenbrand for his views/suggestions on the initial
discussion[1] and Pavan kondeti for various inputs on this patch.
[1] https://lore.kernel.org/linux-mm/[email protected]/
[2] https://lore.kernel.org/all/[email protected]/T/#u
[3] https://lore.kernel.org/all/[email protected]/
[[email protected]: rename label `loop' to `ext_put_continue' per David]
Link: https://lkml.kernel.org/r/[email protected]
Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Charan Teja Kalla <[email protected]>
Suggested-by: David Hildenbrand <[email protected]>
Suggested-by: Michal Hocko <[email protected]>
Acked-by: Michal Hocko <[email protected]>
Acked-by: David Hildenbrand <[email protected]>
Cc: Fernand Sieber <[email protected]>
Cc: Minchan Kim <[email protected]>
Cc: Pasha Tatashin <[email protected]>
Cc: Pavan Kondeti <[email protected]>
Cc: SeongJae Park <[email protected]>
Cc: Shakeel Butt <[email protected]>
Cc: Vlastimil Babka <[email protected]>
Cc: William Kucharski <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
|
|
find_min_pfn_with_active_regions() is only called from free_area_init().
Open-code the PHYS_PFN(memblock_start_of_DRAM()) into free_area_init(),
and kill find_min_pfn_with_active_regions().
Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Kefeng Wang <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
|
|
This Kconfig option is used by individual arch to set its desired
MAX_ORDER. Rename it to reflect its actual use.
Link: https://lkml.kernel.org/r/[email protected]
Acked-by: Mike Rapoport <[email protected]>
Signed-off-by: Zi Yan <[email protected]>
Acked-by: Guo Ren <[email protected]> [csky]
Acked-by: Arnd Bergmann <[email protected]>
Acked-by: Catalin Marinas <[email protected]> [arm64]
Acked-by: Huacai Chen <[email protected]> [LoongArch]
Acked-by: Michael Ellerman <[email protected]> [powerpc]
Cc: Vineet Gupta <[email protected]>
Cc: Taichi Sugaya <[email protected]>
Cc: Neil Armstrong <[email protected]>
Cc: Qin Jian <[email protected]>
Cc: Guo Ren <[email protected]>
Cc: Geert Uytterhoeven <[email protected]>
Cc: Thomas Bogendoerfer <[email protected]>
Cc: Dinh Nguyen <[email protected]>
Cc: Christophe Leroy <[email protected]>
Cc: Yoshinori Sato <[email protected]>
Cc: "David S. Miller" <[email protected]>
Cc: Chris Zankel <[email protected]>
Cc: Ley Foon Tan <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
|
|
The promotion hot threshold is workload and system configuration
dependent. So in this patch, a method to adjust the hot threshold
automatically is implemented. The basic idea is to control the number of
the candidate promotion pages to match the promotion rate limit. If the
hint page fault latency of a page is less than the hot threshold, we will
try to promote the page, and the page is called the candidate promotion
page.
If the number of the candidate promotion pages in the statistics interval
is much more than the promotion rate limit, the hot threshold will be
decreased to reduce the number of the candidate promotion pages.
Otherwise, the hot threshold will be increased to increase the number of
the candidate promotion pages.
To make the above method works, in each statistics interval, the total
number of the pages to check (on which the hint page faults occur) and the
hot/cold distribution need to be stable. Because the page tables are
scanned linearly in NUMA balancing, but the hot/cold distribution isn't
uniform along the address usually, the statistics interval should be
larger than the NUMA balancing scan period. So in the patch, the max scan
period is used as statistics interval and it works well in our tests.
Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: "Huang, Ying" <[email protected]>
Reviewed-by: Baolin Wang <[email protected]>
Tested-by: Baolin Wang <[email protected]>
Cc: Dave Hansen <[email protected]>
Cc: Johannes Weiner <[email protected]>
Cc: Mel Gorman <[email protected]>
Cc: Michal Hocko <[email protected]>
Cc: osalvador <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Rik van Riel <[email protected]>
Cc: Shakeel Butt <[email protected]>
Cc: Wei Xu <[email protected]>
Cc: Yang Shi <[email protected]>
Cc: Zhong Jiang <[email protected]>
Cc: Zi Yan <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
|
|
In NUMA balancing memory tiering mode, if there are hot pages in slow
memory node and cold pages in fast memory node, we need to promote/demote
hot/cold pages between the fast and cold memory nodes.
A choice is to promote/demote as fast as possible. But the CPU cycles and
memory bandwidth consumed by the high promoting/demoting throughput will
hurt the latency of some workload because of accessing inflating and slow
memory bandwidth contention.
A way to resolve this issue is to restrict the max promoting/demoting
throughput. It will take longer to finish the promoting/demoting. But
the workload latency will be better. This is implemented in this patch as
the page promotion rate limit mechanism.
The number of the candidate pages to be promoted to the fast memory node
via NUMA balancing is counted, if the count exceeds the limit specified by
the users, the NUMA balancing promotion will be stopped until the next
second.
A new sysctl knob kernel.numa_balancing_promote_rate_limit_MBps is added
for the users to specify the limit.
Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: "Huang, Ying" <[email protected]>
Reviewed-by: Baolin Wang <[email protected]>
Tested-by: Baolin Wang <[email protected]>
Cc: Dave Hansen <[email protected]>
Cc: Johannes Weiner <[email protected]>
Cc: Mel Gorman <[email protected]>
Cc: Michal Hocko <[email protected]>
Cc: osalvador <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Rik van Riel <[email protected]>
Cc: Shakeel Butt <[email protected]>
Cc: Wei Xu <[email protected]>
Cc: Yang Shi <[email protected]>
Cc: Zhong Jiang <[email protected]>
Cc: Zi Yan <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
|
|
Patch series "memory tiering: hot page selection", v4.
To optimize page placement in a memory tiering system with NUMA balancing,
the hot pages in the slow memory nodes need to be identified.
Essentially, the original NUMA balancing implementation selects the mostly
recently accessed (MRU) pages to promote. But this isn't a perfect
algorithm to identify the hot pages. Because the pages with quite low
access frequency may be accessed eventually given the NUMA balancing page
table scanning period could be quite long (e.g. 60 seconds). So in this
patchset, we implement a new hot page identification algorithm based on
the latency between NUMA balancing page table scanning and hint page
fault. Which is a kind of mostly frequently accessed (MFU) algorithm.
In NUMA balancing memory tiering mode, if there are hot pages in slow
memory node and cold pages in fast memory node, we need to promote/demote
hot/cold pages between the fast and cold memory nodes.
A choice is to promote/demote as fast as possible. But the CPU cycles and
memory bandwidth consumed by the high promoting/demoting throughput will
hurt the latency of some workload because of accessing inflating and slow
memory bandwidth contention.
A way to resolve this issue is to restrict the max promoting/demoting
throughput. It will take longer to finish the promoting/demoting. But
the workload latency will be better. This is implemented in this patchset
as the page promotion rate limit mechanism.
The promotion hot threshold is workload and system configuration
dependent. So in this patchset, a method to adjust the hot threshold
automatically is implemented. The basic idea is to control the number of
the candidate promotion pages to match the promotion rate limit.
We used the pmbench memory accessing benchmark tested the patchset on a
2-socket server system with DRAM and PMEM installed. The test results are
as follows,
pmbench score promote rate
(accesses/s) MB/s
------------- ------------
base 146887704.1 725.6
hot selection 165695601.2 544.0
rate limit 162814569.8 165.2
auto adjustment 170495294.0 136.9
From the results above,
With hot page selection patch [1/3], the pmbench score increases about
12.8%, and promote rate (overhead) decreases about 25.0%, compared with
base kernel.
With rate limit patch [2/3], pmbench score decreases about 1.7%, and
promote rate decreases about 69.6%, compared with hot page selection
patch.
With threshold auto adjustment patch [3/3], pmbench score increases about
4.7%, and promote rate decrease about 17.1%, compared with rate limit
patch.
Baolin helped to test the patchset with MySQL on a machine which contains
1 DRAM node (30G) and 1 PMEM node (126G).
sysbench /usr/share/sysbench/oltp_read_write.lua \
......
--tables=200 \
--table-size=1000000 \
--report-interval=10 \
--threads=16 \
--time=120
The tps can be improved about 5%.
This patch (of 3):
To optimize page placement in a memory tiering system with NUMA balancing,
the hot pages in the slow memory node need to be identified. Essentially,
the original NUMA balancing implementation selects the mostly recently
accessed (MRU) pages to promote. But this isn't a perfect algorithm to
identify the hot pages. Because the pages with quite low access frequency
may be accessed eventually given the NUMA balancing page table scanning
period could be quite long (e.g. 60 seconds). The most frequently
accessed (MFU) algorithm is better.
So, in this patch we implemented a better hot page selection algorithm.
Which is based on NUMA balancing page table scanning and hint page fault
as follows,
- When the page tables of the processes are scanned to change PTE/PMD
to be PROT_NONE, the current time is recorded in struct page as scan
time.
- When the page is accessed, hint page fault will occur. The scan
time is gotten from the struct page. And The hint page fault
latency is defined as
hint page fault time - scan time
The shorter the hint page fault latency of a page is, the higher the
probability of their access frequency to be higher. So the hint page
fault latency is a better estimation of the page hot/cold.
It's hard to find some extra space in struct page to hold the scan time.
Fortunately, we can reuse some bits used by the original NUMA balancing.
NUMA balancing uses some bits in struct page to store the page accessing
CPU and PID (referring to page_cpupid_xchg_last()). Which is used by the
multi-stage node selection algorithm to avoid to migrate pages shared
accessed by the NUMA nodes back and forth. But for pages in the slow
memory node, even if they are shared accessed by multiple NUMA nodes, as
long as the pages are hot, they need to be promoted to the fast memory
node. So the accessing CPU and PID information are unnecessary for the
slow memory pages. We can reuse these bits in struct page to record the
scan time. For the fast memory pages, these bits are used as before.
For the hot threshold, the default value is 1 second, which works well in
our performance test. All pages with hint page fault latency < hot
threshold will be considered hot.
It's hard for users to determine the hot threshold. So we don't provide a
kernel ABI to set it, just provide a debugfs interface for advanced users
to experiment. We will continue to work on a hot threshold automatic
adjustment mechanism.
The downside of the above method is that the response time to the workload
hot spot changing may be much longer. For example,
- A previous cold memory area becomes hot
- The hint page fault will be triggered. But the hint page fault
latency isn't shorter than the hot threshold. So the pages will
not be promoted.
- When the memory area is scanned again, maybe after a scan period,
the hint page fault latency measured will be shorter than the hot
threshold and the pages will be promoted.
To mitigate this, if there are enough free space in the fast memory node,
the hot threshold will not be used, all pages will be promoted upon the
hint page fault for fast response.
Thanks Zhong Jiang reported and tested the fix for a bug when disabling
memory tiering mode dynamically.
Link: https://lkml.kernel.org/r/[email protected]
Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: "Huang, Ying" <[email protected]>
Reviewed-by: Baolin Wang <[email protected]>
Tested-by: Baolin Wang <[email protected]>
Cc: Johannes Weiner <[email protected]>
Cc: Michal Hocko <[email protected]>
Cc: Rik van Riel <[email protected]>
Cc: Mel Gorman <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Dave Hansen <[email protected]>
Cc: Yang Shi <[email protected]>
Cc: Zi Yan <[email protected]>
Cc: Wei Xu <[email protected]>
Cc: osalvador <[email protected]>
Cc: Shakeel Butt <[email protected]>
Cc: Zhong Jiang <[email protected]>
Cc: Oscar Salvador <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
|
|
gfp_migratetype() also expects GFP_RECLAIMABLE and
GFP_MOVABLE|GFP_RECLAIMABLE to be shiftable into MIGRATE_* enum values, so
add some more BUILD_BUG_ONs to reflect this assumption.
Link: https://linux-review.googlesource.com/id/Iae64e2182f75c3aca776a486b71a72571d66d83e
Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Peter Collingbourne <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
|
|
The return value of set_hugetlb_cgroup and set_hugetlb_cgroup_rsvd are
always ignored. Remove them to clean up the code.
Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Miaohe Lin <[email protected]>
Reviewed-by: Mike Kravetz <[email protected]>
Cc: Mina Almasry <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
|
|
By default kfence allocation can happen for any slab object, whose size is
up to PAGE_SIZE, as long as that allocation is the first allocation after
expiration of kfence sample interval. But in certain debugging scenarios
we may be interested in debugging corruptions involving some specific slub
objects like dentry or ext4_* etc. In such cases limiting kfence for
allocations involving only specific slub objects will increase the
probablity of catching the issue since kfence pool will not be consumed by
other slab objects.
This patch introduces a sysfs interface
'/sys/kernel/slab/<name>/skip_kfence' to disable kfence for specific
slabs. Having the interface work in this way does not impact
current/default behavior of kfence and allows us to use kfence for
specific slabs (when needed) as well. The decision to skip/use kfence is
taken depending on whether kmem_cache.flags has (newly introduced)
SLAB_SKIP_KFENCE flag set or not.
Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Imran Khan <[email protected]>
Reviewed-by: Vlastimil Babka <[email protected]>
Reviewed-by: Marco Elver <[email protected]>
Reviewed-by: Hyeonggon Yoo <[email protected]>
Cc: Alexander Potapenko <[email protected]>
Cc: Dmitry Vyukov <[email protected]>
Cc: Christoph Lameter <[email protected]>
Cc: Pekka Enberg <[email protected]>
Cc: David Rientjes <[email protected]>
Cc: Joonsoo Kim <[email protected]>
Cc: Roman Gushchin <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
|
|
Muchun Song found that after MPOL_PREFERRED_MANY policy was introduced in
commit b27abaccf8e8 ("mm/mempolicy: add MPOL_PREFERRED_MANY for multiple
preferred nodes"), the policy_nodemask_current()'s semantics for this new
policy has been changed, which returns 'preferred' nodes instead of
'allowed' nodes.
With the changed semantic of policy_nodemask_current, a task with
MPOL_PREFERRED_MANY policy could fail to get its reservation even though
it can fall back to other nodes (either defined by cpusets or all online
nodes) for that reservation failing mmap calles unnecessarily early.
The fix is to not consider MPOL_PREFERRED_MANY for reservations at all
because they, unlike MPOL_MBIND, do not pose any actual hard constrain.
Michal suggested the policy_nodemask_current() is only used by hugetlb,
and could be moved to hugetlb code with more explicit name to enforce the
'allowed' semantics for which only MPOL_BIND policy matters.
apply_policy_zone() is made extern to be called in hugetlb code and its
return value is changed to bool.
[1]. https://lore.kernel.org/lkml/[email protected]/t/
Link: https://lkml.kernel.org/r/[email protected]
Fixes: b27abaccf8e8 ("mm/mempolicy: add MPOL_PREFERRED_MANY for multiple preferred nodes")
Signed-off-by: Feng Tang <[email protected]>
Reported-by: Muchun Song <[email protected]>
Suggested-by: Michal Hocko <[email protected]>
Acked-by: Michal Hocko <[email protected]>
Reviewed-by: Muchun Song <[email protected]>
Cc: Mike Kravetz <[email protected]>
Cc: Dave Hansen <[email protected]>
Cc: Ben Widawsky <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
|
|
The magic number 0 and 1 are used in several places in vmscan.c.
Define macros for them to improve code readability.
Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Yang Yang <[email protected]>
Cc: Johannes Weiner <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
|
|
This idea was introduced by David Rientjes[1].
Introduce a new madvise mode, MADV_COLLAPSE, that allows users to request
a synchronous collapse of memory at their own expense.
The benefits of this approach are:
* CPU is charged to the process that wants to spend the cycles for the
THP
* Avoid unpredictable timing of khugepaged collapse
Semantics
This call is independent of the system-wide THP sysfs settings, but will
fail for memory marked VM_NOHUGEPAGE. If the ranges provided span
multiple VMAs, the semantics of the collapse over each VMA is independent
from the others. This implies a hugepage cannot cross a VMA boundary. If
collapse of a given hugepage-aligned/sized region fails, the operation may
continue to attempt collapsing the remainder of memory specified.
The memory ranges provided must be page-aligned, but are not required to
be hugepage-aligned. If the memory ranges are not hugepage-aligned, the
start/end of the range will be clamped to the first/last hugepage-aligned
address covered by said range. The memory ranges must span at least one
hugepage-sized region.
All non-resident pages covered by the range will first be
swapped/faulted-in, before being internally copied onto a freshly
allocated hugepage. Unmapped pages will have their data directly
initialized to 0 in the new hugepage. However, for every eligible
hugepage aligned/sized region to-be collapsed, at least one page must
currently be backed by memory (a PMD covering the address range must
already exist).
Allocation for the new hugepage may enter direct reclaim and/or
compaction, regardless of VMA flags. When the system has multiple NUMA
nodes, the hugepage will be allocated from the node providing the most
native pages. This operation operates on the current state of the
specified process and makes no persistent changes or guarantees on how
pages will be mapped, constructed, or faulted in the future
Return Value
If all hugepage-sized/aligned regions covered by the provided range were
either successfully collapsed, or were already PMD-mapped THPs, this
operation will be deemed successful. On success, process_madvise(2)
returns the number of bytes advised, and madvise(2) returns 0. Else, -1
is returned and errno is set to indicate the error for the most-recently
attempted hugepage collapse. Note that many failures might have occurred,
since the operation may continue to collapse in the event a single
hugepage-sized/aligned region fails.
ENOMEM Memory allocation failed or VMA not found
EBUSY Memcg charging failed
EAGAIN Required resource temporarily unavailable. Try again
might succeed.
EINVAL Other error: No PMD found, subpage doesn't have Present
bit set, "Special" page no backed by struct page, VMA
incorrectly sized, address not page-aligned, ...
Most notable here is ENOMEM and EBUSY (new to madvise) which are intended
to provide the caller with actionable feedback so they may take an
appropriate fallback measure.
Use Cases
An immediate user of this new functionality are malloc() implementations
that manage memory in hugepage-sized chunks, but sometimes subrelease
memory back to the system in native-sized chunks via MADV_DONTNEED;
zapping the pmd. Later, when the memory is hot, the implementation could
madvise(MADV_COLLAPSE) to re-back the memory by THPs to regain hugepage
coverage and dTLB performance. TCMalloc is such an implementation that
could benefit from this[2].
Only privately-mapped anon memory is supported for now, but additional
support for file, shmem, and HugeTLB high-granularity mappings[2] is
expected. File and tmpfs/shmem support would permit:
* Backing executable text by THPs. Current support provided by
CONFIG_READ_ONLY_THP_FOR_FS may take a long time on a large system which
might impair services from serving at their full rated load after
(re)starting. Tricks like mremap(2)'ing text onto anonymous memory to
immediately realize iTLB performance prevents page sharing and demand
paging, both of which increase steady state memory footprint. With
MADV_COLLAPSE, we get the best of both worlds: Peak upfront performance
and lower RAM footprints.
* Backing guest memory by hugapages after the memory contents have been
migrated in native-page-sized chunks to a new host, in a
userfaultfd-based live-migration stack.
[1] https://lore.kernel.org/linux-mm/[email protected]/
[2] https://github.com/google/tcmalloc/tree/master/tcmalloc
[[email protected]: avoid possible memory leak in failure path]
Link: https://lkml.kernel.org/r/[email protected]
[[email protected] add missing kfree() to madvise_collapse()]
Link: https://lore.kernel.org/linux-mm/[email protected]/
Link: https://lkml.kernel.org/r/[email protected]
[[email protected]: delay computation of hpage boundaries until use]]
Link: https://lkml.kernel.org/r/[email protected]
Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Zach O'Keefe <[email protected]>
Signed-off-by: "Souptick Joarder (HPE)" <[email protected]>
Suggested-by: David Rientjes <[email protected]>
Cc: Alex Shi <[email protected]>
Cc: Andrea Arcangeli <[email protected]>
Cc: Arnd Bergmann <[email protected]>
Cc: Axel Rasmussen <[email protected]>
Cc: Chris Kennelly <[email protected]>
Cc: Chris Zankel <[email protected]>
Cc: David Hildenbrand <[email protected]>
Cc: Helge Deller <[email protected]>
Cc: Hugh Dickins <[email protected]>
Cc: Ivan Kokshaysky <[email protected]>
Cc: James Bottomley <[email protected]>
Cc: Jens Axboe <[email protected]>
Cc: "Kirill A. Shutemov" <[email protected]>
Cc: Matthew Wilcox <[email protected]>
Cc: Matt Turner <[email protected]>
Cc: Max Filippov <[email protected]>
Cc: Miaohe Lin <[email protected]>
Cc: Michal Hocko <[email protected]>
Cc: Minchan Kim <[email protected]>
Cc: Pasha Tatashin <[email protected]>
Cc: Pavel Begunkov <[email protected]>
Cc: Peter Xu <[email protected]>
Cc: Rongwei Wang <[email protected]>
Cc: SeongJae Park <[email protected]>
Cc: Song Liu <[email protected]>
Cc: Thomas Bogendoerfer <[email protected]>
Cc: Vlastimil Babka <[email protected]>
Cc: Yang Shi <[email protected]>
Cc: Zi Yan <[email protected]>
Cc: Dan Carpenter <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
|
|
MADV_COLLAPSE is not coupled to the kernel-oriented sysfs THP settings[1].
hugepage_vma_check() is the authority on determining if a VMA is eligible
for THP allocation/collapse, and currently enforces the sysfs THP
settings. Add a flag to disable these checks. For now, only apply this
arg to anon and file, which use /sys/kernel/transparent_hugepage/enabled.
We can expand this to shmem, which uses
/sys/kernel/transparent_hugepage/shmem_enabled, later.
Use this flag in collapse_pte_mapped_thp() where previously the VMA flags
passed to hugepage_vma_check() were OR'd with VM_HUGEPAGE to elide the
VM_HUGEPAGE check in "madvise" THP mode. Prior to "mm: khugepaged: check
THP flag in hugepage_vma_check()", this check also didn't check "never"
THP mode. As such, this restores the previous behavior of
collapse_pte_mapped_thp() where sysfs THP settings are ignored. See
comment in code for justification why this is OK.
[1] https://lore.kernel.org/linux-mm/CAAa6QmQxay1_=Pmt8oCX2-Va18t44FV-Vs-WsQt_6+qBks4nZA@mail.gmail.com/
Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Zach O'Keefe <[email protected]>
Reviewed-by: Yang Shi <[email protected]>
Cc: Alex Shi <[email protected]>
Cc: Andrea Arcangeli <[email protected]>
Cc: Arnd Bergmann <[email protected]>
Cc: Axel Rasmussen <[email protected]>
Cc: Chris Kennelly <[email protected]>
Cc: Chris Zankel <[email protected]>
Cc: David Hildenbrand <[email protected]>
Cc: David Rientjes <[email protected]>
Cc: Helge Deller <[email protected]>
Cc: Hugh Dickins <[email protected]>
Cc: Ivan Kokshaysky <[email protected]>
Cc: James Bottomley <[email protected]>
Cc: Jens Axboe <[email protected]>
Cc: "Kirill A. Shutemov" <[email protected]>
Cc: Matthew Wilcox <[email protected]>
Cc: Matt Turner <[email protected]>
Cc: Max Filippov <[email protected]>
Cc: Miaohe Lin <[email protected]>
Cc: Michal Hocko <[email protected]>
Cc: Minchan Kim <[email protected]>
Cc: Pasha Tatashin <[email protected]>
Cc: Pavel Begunkov <[email protected]>
Cc: Peter Xu <[email protected]>
Cc: Rongwei Wang <[email protected]>
Cc: SeongJae Park <[email protected]>
Cc: Song Liu <[email protected]>
Cc: Thomas Bogendoerfer <[email protected]>
Cc: Vlastimil Babka <[email protected]>
Cc: Zi Yan <[email protected]>
Cc: Dan Carpenter <[email protected]>
Cc: "Souptick Joarder (HPE)" <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
|
|
To prepare for STATX_DIOALIGN support, make two changes to
fscrypt_dio_supported().
First, remove the filesystem-block-alignment check and make the
filesystems handle it instead. It previously made sense to have it in
fs/crypto/; however, to support STATX_DIOALIGN the alignment restriction
would have to be returned to filesystems. It ends up being simpler if
filesystems handle this part themselves, especially for f2fs which only
allows fs-block-aligned DIO in the first place.
Second, make fscrypt_dio_supported() work on inodes whose encryption key
hasn't been set up yet, by making it set up the key if needed. This is
required for statx(), since statx() doesn't require a file descriptor.
Reviewed-by: Christoph Hellwig <[email protected]>
Signed-off-by: Eric Biggers <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
|
|
Add support for STATX_DIOALIGN to block devices, so that direct I/O
alignment restrictions are exposed to userspace in a generic way.
Note that this breaks the tradition of stat operating only on the block
device node, not the block device itself. However, it was felt that
doing this is preferable, in order to make the interface useful and
avoid needing separate interfaces for regular files and block devices.
Signed-off-by: Eric Biggers <[email protected]>
Reviewed-by: Christoph Hellwig <[email protected]>
Reviewed-by: Christian Brauner (Microsoft) <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
|
|
Traditionally, the conditions for when DIO (direct I/O) is supported
were fairly simple. For both block devices and regular files, DIO had
to be aligned to the logical block size of the block device.
However, due to filesystem features that have been added over time (e.g.
multi-device support, data journalling, inline data, encryption, verity,
compression, checkpoint disabling, log-structured mode), the conditions
for when DIO is allowed on a regular file have gotten increasingly
complex. Whether a particular regular file supports DIO, and with what
alignment, can depend on various file attributes and filesystem mount
options, as well as which block device(s) the file's data is located on.
Moreover, the general rule of DIO needing to be aligned to the block
device's logical block size was recently relaxed to allow user buffers
(but not file offsets) aligned to the DMA alignment instead. See
commit bf8d08532bc1 ("iomap: add support for dma aligned direct-io").
XFS has an ioctl XFS_IOC_DIOINFO that exposes DIO alignment information.
Uplifting this to the VFS is one possibility. However, as discussed
(https://lore.kernel.org/linux-fsdevel/[email protected]/T/#u),
this ioctl is rarely used and not known to be used outside of
XFS-specific code. It was also never intended to indicate when a file
doesn't support DIO at all, nor was it intended for block devices.
Therefore, let's expose this information via statx(). Add the
STATX_DIOALIGN flag and two new statx fields associated with it:
* stx_dio_mem_align: the alignment (in bytes) required for user memory
buffers for DIO, or 0 if DIO is not supported on the file.
* stx_dio_offset_align: the alignment (in bytes) required for file
offsets and I/O segment lengths for DIO, or 0 if DIO is not supported
on the file. This will only be nonzero if stx_dio_mem_align is
nonzero, and vice versa.
Note that as with other statx() extensions, if STATX_DIOALIGN isn't set
in the returned statx struct, then these new fields won't be filled in.
This will happen if the file is neither a regular file nor a block
device, or if the file is a regular file and the filesystem doesn't
support STATX_DIOALIGN. It might also happen if the caller didn't
include STATX_DIOALIGN in the request mask, since statx() isn't required
to return unrequested information.
This commit only adds the VFS-level plumbing for STATX_DIOALIGN. For
regular files, individual filesystems will still need to add code to
support it. For block devices, a separate commit will wire it up too.
Reviewed-by: Christoph Hellwig <[email protected]>
Reviewed-by: Darrick J. Wong <[email protected]>
Reviewed-by: Martin K. Petersen <[email protected]>
Reviewed-by: Christian Brauner (Microsoft) <[email protected]>
Signed-off-by: Eric Biggers <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
|
|
Some pagemap types, like MEMORY_DEVICE_GENERIC (device-dax) do not even
have pagemap ops which results in crash signatures like this:
BUG: kernel NULL pointer dereference, address: 0000000000000010
#PF: supervisor read access in kernel mode
#PF: error_code(0x0000) - not-present page
PGD 8000000205073067 P4D 8000000205073067 PUD 2062b3067 PMD 0
Oops: 0000 [#1] PREEMPT SMP PTI
CPU: 22 PID: 4535 Comm: device-dax Tainted: G OE N 6.0.0-rc2+ #59
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 0.0.0 02/06/2015
RIP: 0010:memory_failure+0x667/0xba0
[..]
Call Trace:
<TASK>
? _printk+0x58/0x73
do_madvise.part.0.cold+0xaf/0xc5
Check for ops before checking if the ops have a memory_failure()
handler.
Link: https://lkml.kernel.org/r/166153428781.2758201.1990616683438224741.stgit@dwillia2-xfh.jf.intel.com
Fixes: 33a8f7f2b3a3 ("pagemap,pmem: introduce ->memory_failure()")
Signed-off-by: Dan Williams <[email protected]>
Acked-by: Naoya Horiguchi <[email protected]>
Reviewed-by: Miaohe Lin <[email protected]>
Reviewed-by: Christoph Hellwig <[email protected]>
Cc: Shiyang Ruan <[email protected]>
Cc: Darrick J. Wong <[email protected]>
Cc: Al Viro <[email protected]>
Cc: Dave Chinner <[email protected]>
Cc: Goldwyn Rodrigues <[email protected]>
Cc: Jane Chu <[email protected]>
Cc: Matthew Wilcox <[email protected]>
Cc: Ritesh Harjani <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
|
|
git://anongit.freedesktop.org/drm/drm-misc into drm-next
drm-misc-next for v6.1-rc1:
[airlied - fix sun4i_tv build]
UAPI Changes:
- Hide unregistered connectors from GETCONNECTOR ioctl.
- drm/virtio no longer advertises LINEAR modifier, as it doesn't work.
-
Cross-subsystem Changes:
- Fix GPF in udmabuf failure path.
Core Changes:
- Rework TTM placement to use intersect/compatible functions.
- Drop legacy DP-MST support.
- More DP-MST related fixes, and move all state into atomic.
- Make DRM_MIPI_DBI select DRM_KMS_HELPER.
- Add audio_infoframe packing for DP.
- Add logging when some atomic check functions fail.
- Assorted documentation updates and fixes.
Driver Changes:
- Assorted cleanups and fixes in msm, lcdif, nouveau, virtio,
panel/ilitek, bridge/icn6211, tve200, gma500, bridge/*, panfrost, via,
bochs, qxl, sun4i.
- Add add AUO B133UAN02.1, IVO M133NW4J-R3, Innolux N120ACA-EA1 eDP panels.
- Improve DP-MST modeset state handling in amdgpu, nouveau, i915.
- Drop DP-MST from radeon driver, it was broken and only user of legacy
DP-MST.
- Handle unplugging better in vc4.
- Simplify drm cmdparser tests.
- Add DP support to ti-sn65dsi86.
- Add MT8195 DP support to mediatek.
- Support RGB565, XRGB64, and ARGB64 formats in vkms.
- Convert sun4i tv support to atomic.
- Refactor vc4/vec TV Modesetting, and fix timings.
- Use atomic helpers instead of simple display helpers in ssd130x.
Maintainer changes:
- Add Douglas Anderson as reviewer for panel-edp.
Signed-off-by: Dave Airlie <[email protected]>
From: Maarten Lankhorst <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu
Pull iommu fixes from Joerg Roedel:
- Intel VT-d fixes from Lu Baolu:
- Boot kdump kernels with VT-d scalable mode on
- Calculate the right page table levels
- Fix two recursive locking issues
- Fix a lockdep splat issue
- AMD IOMMU fixes:
- Fix for completion-wait command to use full 64 bits of data
- Fix PASID related issue where GPU sound devices failed to
initialize
- Fix for Virtio-IOMMU to report correct caching behavior, needed for
use with VFIO
* tag 'iommu-fixes-v6.0-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu:
iommu: Fix false ownership failure on AMD systems with PASID activated
iommu/vt-d: Fix possible recursive locking in intel_iommu_init()
iommu/virtio: Fix interaction with VFIO
iommu/vt-d: Fix lockdep splat due to klist iteration in atomic context
iommu/vt-d: Fix recursive lock issue in iommu_flush_dev_iotlb()
iommu/vt-d: Correctly calculate sagaw value of IOMMU
iommu/vt-d: Fix kdump kernels boot failure with scalable mode
iommu/amd: use full 64-bit value in build_completion_wait()
|
|
In order for everyone to understand clearly why we want to use
maintenance charging for batteries, expand the description with two
diagrams and some text.
Signed-off-by: Linus Walleij <[email protected]>
Reviewed-by: Matti Vaittinen <[email protected]>
Signed-off-by: Sebastian Reichel <[email protected]>
|
|
The global rwsem dmar_global_lock was introduced by commit 3a5670e8ac932
("iommu/vt-d: Introduce a rwsem to protect global data structures"). It
is used to protect DMAR related global data from DMAR hotplug operations.
The dmar_global_lock used in the intel_iommu_init() might cause recursive
locking issue, for example, intel_iommu_get_resv_regions() is taking the
dmar_global_lock from within a section where intel_iommu_init() already
holds it via probe_acpi_namespace_devices().
Using dmar_global_lock in intel_iommu_init() could be relaxed since it is
unlikely that any IO board must be hot added before the IOMMU subsystem is
initialized. This eliminates the possible recursive locking issue by moving
down DMAR hotplug support after the IOMMU is initialized and removing the
uses of dmar_global_lock in intel_iommu_init().
Fixes: d5692d4af08cd ("iommu/vt-d: Fix suspicious RCU usage in probe_acpi_namespace_devices()")
Reported-by: Robin Murphy <[email protected]>
Signed-off-by: Lu Baolu <[email protected]>
Reviewed-by: Kevin Tian <[email protected]>
Link: https://lore.kernel.org/r/894db0ccae854b35c73814485569b634237b5538.1657034828.git.robin.murphy@arm.com
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Joerg Roedel <[email protected]>
|
|
Verifier logic to confirm that a callback function returns 0 or 1 was
added in commit 69c087ba6225b ("bpf: Add bpf_for_each_map_elem() helper").
At the time, callback return value was only used to continue or stop
iteration.
In order to support callbacks with a broader return value range, such as
those added in rbtree series[0] and others, add a callback_ret_range to
bpf_func_state. Verifier's helpers which set in_callback_fn will also
set the new field, which the verifier will later use to check return
value bounds.
Default to tnum_range(0, 0) instead of using tnum_unknown as a sentinel
value as the latter would prevent the valid range (0, U64_MAX) being
used. Previous global default tnum_range(0, 1) is explicitly set for
extant callback helpers. The change to global default was made after
discussion around this patch in rbtree series [1], goal here is to make
it more obvious that callback_ret_range should be explicitly set.
[0]: lore.kernel.org/bpf/[email protected]/
[1]: lore.kernel.org/bpf/[email protected]/
Signed-off-by: Dave Marchevsky <[email protected]>
Reviewed-by: Stanislav Fomichev <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Alexei Starovoitov <[email protected]>
|
|
Add corresponding unimplemented stub for when CONFIG_BPF_SYSCALL=n
Signed-off-by: Daniel Xu <[email protected]>
Acked-by: Kumar Kartikeya Dwivedi <[email protected]>
Link: https://lore.kernel.org/r/4021398e884433b1fef57a4d28361bb9fcf1bd05.1662568410.git.dxu@dxuuu.xyz
Signed-off-by: Alexei Starovoitov <[email protected]>
|
|
Wrapper function that finds all memory type resources by
using acpi_dev_get_resources(). It removes the need for the
drivers to check the resource data type separately.
Signed-off-by: Heikki Krogerus <[email protected]>
Signed-off-by: Rafael J. Wysocki <[email protected]>
|
|
git://git.infradead.org/users/hch/dma-mapping
Pull dma-mapping fixes from Christoph Hellwig:
- revert a panic on swiotlb initialization failure (Yu Zhao)
- fix the lookup for partial syncs in dma-debug (Robin Murphy)
- fix a shift overflow in swiotlb (Chao Gao)
- fix a comment typo in swiotlb (Chao Gao)
- mark a function static now that all abusers are gone (Christoph
Hellwig)
* tag 'dma-mapping-6.0-2022-09-10' of git://git.infradead.org/users/hch/dma-mapping:
dma-mapping: mark dma_supported static
swiotlb: fix a typo
swiotlb: avoid potential left shift overflow
dma-debug: improve search for partial syncs
Revert "swiotlb: panic if nslabs is too small"
|
|
Linux 6.0-rc4 so we can test on BeagleBone again.
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core
Pull driver core fixes from Greg KH:
"Here are some small driver core and debugfs fixes for 6.0-rc5.
Included in here are:
- multiple attempts to get the arch_topology code to work properly on
non-cluster SMT systems. First attempt caused build breakages in
linux-next and 0-day, second try worked.
- debugfs fixes for a long-suffering memory leak. The pattern of
debugfs_remove(debugfs_lookup(...)) turns out to leak dentries, so
add debugfs_lookup_and_remove() to fix this problem. Also fix up
the scheduler debug code that highlighted this problem. Fixes for
other subsystems will be trickling in over the next few months for
this same issue once the debugfs function is merged.
All of these have been in linux-next since Wednesday with no reported
problems"
* tag 'driver-core-6.0-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core:
arch_topology: Make cluster topology span at least SMT CPUs
sched/debug: fix dentry leak in update_sched_domain_debugfs
debugfs: add debugfs_lookup_and_remove()
driver core: fix driver_set_override() issue with empty strings
Revert "arch_topology: Make cluster topology span at least SMT CPUs"
arch_topology: Make cluster topology span at least SMT CPUs
|
|
Pull rdma fixes from Jason Gunthorpe:
"Many bug fixes in several drivers:
- Fix misuse of the DMA API in rtrs
- Several irdma issues: hung task due to SQ flushing, incorrect
capability reporting to userspace, improper error handling for MW
corners, touching an uninitialized SGL for during invalidation.
- hns was using the wrong page size limits for the HW, an incorrect
calculation of wqe_shift causing WQE corruption, and mis computed a
timer id.
- Fix a crash in SRP triggered by blktests
- Fix compiler errors by calling virt_to_page() with the proper type
in siw
- Userspace triggerable deadlock in ODP
- mlx5 could use the wrong profile due to some driver loading races,
counters were not working in some device configurations, and a
crash on error unwind"
* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma:
RDMA/irdma: Report RNR NAK generation in device caps
RDMA/irdma: Use s/g array in post send only when its valid
RDMA/irdma: Return correct WC error for bind operation failure
RDMA/irdma: Return error on MR deregister CQP failure
RDMA/irdma: Report the correct max cqes from query device
MAINTAINERS: Update maintainers of HiSilicon RoCE
RDMA/mlx5: Fix UMR cleanup on error flow of driver init
RDMA/mlx5: Set local port to one when accessing counters
RDMA/mlx5: Rely on RoCE fw cap instead of devlink when setting profile
IB/core: Fix a nested dead lock as part of ODP flow
RDMA/siw: Pass a pointer to virt_to_page()
RDMA/srp: Set scmnd->result only when scmnd is not NULL
RDMA/hns: Remove the num_qpc_timer variable
RDMA/hns: Fix wrong fixed value of qp->rq.wqe_shift
RDMA/hns: Fix supported page size
RDMA/cma: Fix arguments order in net device validation
RDMA/irdma: Fix drain SQ hang with no completion
RDMA/rtrs-srv: Pass the correct number of entries for dma mapped SGL
RDMA/rtrs-clt: Use the right sg_cnt after ib_dma_map_sg
|
|
On some platforms it is found that Linux more aggressively enters s2idle
than Windows enters Modern Standby and this uncovers some synchronization
issues for the platform. To aid in debugging this class of problems in
the future, add support for an extra optional callback intended for
drivers to emit extra debugging.
Signed-off-by: Mario Limonciello <[email protected]>
Acked-by: Rafael J. Wysocki <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Hans de Goede <[email protected]>
|