Pull tracing updates from Steven Rostedt:
- User events are finally ready!
After lots of collaboration between various parties, we finally
locked down on a stable interface for user events that can also work
with user space only tracing.
This is implemented by telling the kernel (or user space library, but
that part is user space only and not part of this patch set), where
the variable is that the application uses to know if something is
listening to the trace.
There's also an interface to tell the kernel about these events,
which will show up in the /sys/kernel/tracing/events/user_events/
directory, where it can be enabled.
When it's enabled, the kernel will update the variable, to tell the
application to start writing to the kernel.
See https://lwn.net/Articles/927595/
- Cleaned up the direct trampolines code to simplify arm64 addition of
direct trampolines.
Direct trampolines use the ftrace interface but instead of jumping to
the ftrace trampoline, applications (mostly BPF) can register their
own trampoline for performance reasons.
- Some updates to the fprobe infrastructure. fprobes are more efficient
than kprobes, as it does not need to save all the registers that
kprobes on ftrace do. More work needs to be done before the fprobes
will be exposed as dynamic events.
- More updates to references to the obsolete path of
/sys/kernel/debug/tracing for the new /sys/kernel/tracing path.
- Add a seq_buf_do_printk() helper to seq_bufs, to print a large buffer
line by line instead of all at once.
There are users in production kernels that have a large data dump
that originally used printk() directly, but the data dump was larger
than what printk() allowed as a single print.
Using seq_buf() to do the printing fixes that.
- Add /sys/kernel/tracing/touched_functions that shows all functions
that was every traced by ftrace or a direct trampoline. This is used
for debugging issues where a traced function could have caused a
crash by a bpf program or live patching.
- Add a "fields" option that is similar to "raw" but outputs the fields
of the events. It's easier to read by humans.
- Some minor fixes and clean ups.
* tag 'trace-v6.4' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace: (41 commits)
ring-buffer: Sync IRQ works before buffer destruction
tracing: Add missing spaces in trace_print_hex_seq()
ring-buffer: Ensure proper resetting of atomic variables in ring_buffer_reset_online_cpus
recordmcount: Fix memory leaks in the uwrite function
tracing/user_events: Limit max fault-in attempts
tracing/user_events: Prevent same address and bit per process
tracing/user_events: Ensure bit is cleared on unregister
tracing/user_events: Ensure write index cannot be negative
seq_buf: Add seq_buf_do_printk() helper
tracing: Fix print_fields() for __dyn_loc/__rel_loc
tracing/user_events: Set event filter_type from type
ring-buffer: Clearly check null ptr returned by rb_set_head_page()
tracing: Unbreak user events
tracing/user_events: Use print_format_fields() for trace output
tracing/user_events: Align structs with tabs for readability
tracing/user_events: Limit global user_event count
tracing/user_events: Charge event allocs to cgroups
tracing/user_events: Update documentation for ABI
tracing/user_events: Use write ABI in example
tracing/user_events: Add ABI self-test
...
Pull scheduler updates from Ingo Molnar:
- Allow unprivileged PSI poll()ing
- Fix performance regression introduced by mm_cid
- Improve livepatch stalls by adding livepatch task switching to
cond_resched(). This resolves livepatching busy-loop stalls with
certain CPU-bound kthreads
- Improve sched_move_task() performance on autogroup configs
- On core-scheduling CPUs, avoid selecting throttled tasks to run
- Misc cleanups, fixes and improvements
* tag 'sched-core-2023-04-27' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
sched/clock: Fix local_clock() before sched_clock_init()
sched/rt: Fix bad task migration for rt tasks
sched: Fix performance regression introduced by mm_cid
sched/core: Make sched_dynamic_mutex static
sched/psi: Allow unprivileged polling of N*2s period
sched/psi: Extract update_triggers side effect
sched/psi: Rename existing poll members in preparation
sched/psi: Rearrange polling code in preparation
sched/fair: Fix inaccurate tally of ttwu_move_affine
vhost: Fix livepatch timeouts in vhost_worker()
livepatch,sched: Add livepatch task switching to cond_resched()
livepatch: Skip task_call_func() for current task
livepatch: Convert stack entries array to percpu
sched: Interleave cfs bandwidth timers for improved single thread performance at low utilization
sched/core: Reduce cost of sched_move_task when config autogroup
sched/core: Avoid selecting the task that is throttled to run when core-sched enable
sched/topology: Make sched_energy_mutex,update static
Pull MM updates from Andrew Morton:
- Nick Piggin's "shoot lazy tlbs" series, to improve the peformance of
switching from a user process to a kernel thread.
- More folio conversions from Kefeng Wang, Zhang Peng and Pankaj
Raghav.
- zsmalloc performance improvements from Sergey Senozhatsky.
- Yue Zhao has found and fixed some data race issues around the
alteration of memcg userspace tunables.
- VFS rationalizations from Christoph Hellwig:
- removal of most of the callers of write_one_page()
- make __filemap_get_folio()'s return value more useful
- Luis Chamberlain has changed tmpfs so it no longer requires swap
backing. Use `mount -o noswap'.
- Qi Zheng has made the slab shrinkers operate locklessly, providing
some scalability benefits.
- Keith Busch has improved dmapool's performance, making part of its
operations O(1) rather than O(n).
- Peter Xu adds the UFFD_FEATURE_WP_UNPOPULATED feature to userfaultd,
permitting userspace to wr-protect anon memory unpopulated ptes.
- Kirill Shutemov has changed MAX_ORDER's meaning to be inclusive
rather than exclusive, and has fixed a bunch of errors which were
caused by its unintuitive meaning.
- Axel Rasmussen give userfaultfd the UFFDIO_CONTINUE_MODE_WP feature,
which causes minor faults to install a write-protected pte.
- Vlastimil Babka has done some maintenance work on vma_merge():
cleanups to the kernel code and improvements to our userspace test
harness.
- Cleanups to do_fault_around() by Lorenzo Stoakes.
- Mike Rapoport has moved a lot of initialization code out of various
mm/ files and into mm/mm_init.c.
- Lorenzo Stoakes removd vmf_insert_mixed_prot(), which was added for
DRM, but DRM doesn't use it any more.
- Lorenzo has also coverted read_kcore() and vread() to use iterators
and has thereby removed the use of bounce buffers in some cases.
- Lorenzo has also contributed further cleanups of vma_merge().
- Chaitanya Prakash provides some fixes to the mmap selftesting code.
- Matthew Wilcox changes xfs and afs so they no longer take sleeping
locks in ->map_page(), a step towards RCUification of pagefaults.
- Suren Baghdasaryan has improved mmap_lock scalability by switching to
per-VMA locking.
- Frederic Weisbecker has reworked the percpu cache draining so that it
no longer causes latency glitches on cpu isolated workloads.
- Mike Rapoport cleans up and corrects the ARCH_FORCE_MAX_ORDER Kconfig
logic.
- Liu Shixin has changed zswap's initialization so we no longer waste a
chunk of memory if zswap is not being used.
- Yosry Ahmed has improved the performance of memcg statistics
flushing.
- David Stevens has fixed several issues involving khugepaged,
userfaultfd and shmem.
- Christoph Hellwig has provided some cleanup work to zram's IO-related
code paths.
- David Hildenbrand has fixed up some issues in the selftest code's
testing of our pte state changing.
- Pankaj Raghav has made page_endio() unneeded and has removed it.
- Peter Xu contributed some rationalizations of the userfaultfd
selftests.
- Yosry Ahmed has fixed an issue around memcg's page recalim
accounting.
- Chaitanya Prakash has fixed some arm-related issues in the
selftests/mm code.
- Longlong Xia has improved the way in which KSM handles hwpoisoned
pages.
- Peter Xu fixes a few issues with uffd-wp at fork() time.
- Stefan Roesch has changed KSM so that it may now be used on a
per-process and per-cgroup basis.
* tag 'mm-stable-2023-04-27-15-30' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (369 commits)
mm,unmap: avoid flushing TLB in batch if PTE is inaccessible
shmem: restrict noswap option to initial user namespace
mm/khugepaged: fix conflicting mods to collapse_file()
sparse: remove unnecessary 0 values from rc
mm: move 'mmap_min_addr' logic from callers into vm_unmapped_area()
hugetlb: pte_alloc_huge() to replace huge pte_alloc_map()
maple_tree: fix allocation in mas_sparse_area()
mm: do not increment pgfault stats when page fault handler retries
zsmalloc: allow only one active pool compaction context
selftests/mm: add new selftests for KSM
mm: add new KSM process and sysfs knobs
mm: add new api to enable ksm per process
mm: shrinkers: fix debugfs file permissions
mm: don't check VMA write permissions if the PTE/PMD indicates write permissions
migrate_pages_batch: fix statistics for longterm pin retry
userfaultfd: use helper function range_in_vma()
lib/show_mem.c: use for_each_populated_zone() simplify code
mm: correct arg in reclaim_pages()/reclaim_clean_pages_from_list()
fs/buffer: convert create_page_buffers to folio_create_buffers
fs/buffer: add folio_create_empty_buffers helper
...
Pull pidfd updates from Christian Brauner:
"This adds a new pidfd_prepare() helper which allows the caller to
reserve a pidfd number and allocates a new pidfd file that stashes the
provided struct pid.
It should be avoided installing a file descriptor into a task's file
descriptor table just to close it again via close_fd() in case an
error occurs. The fd has been visible to userspace and might already
be in use. Instead, a file descriptor should be reserved but not
installed into the caller's file descriptor table.
If another failure path is hit then the reserved file descriptor and
file can just be put without any userspace visible side-effects. And
if all failure paths are cleared the file descriptor and file can be
installed into the task's file descriptor table.
This helper is now used in all places that open coded this
functionality before. For example, this is currently done during
copy_process() and fanotify used pidfd_create(), which returns a pidfd
that has already been made visibile in the caller's file descriptor
table, but then closed it using close_fd().
In one of the next merge windows there is also new functionality
coming to unix domain sockets that will have to rely on
pidfd_prepare()"
* tag 'v6.4/pidfd.file' of git://git.kernel.org/pub/scm/linux/kernel/git/brauner/linux:
fanotify: use pidfd_prepare()
fork: use pidfd_prepare()
pid: add pidfd_prepare()
Pull user work thread updates from Christian Brauner:
"This contains the work generalizing the ability to create a kernel
worker from a userspace process.
Such user workers will run with the same credentials as the userspace
process they were created from providing stronger security and
accounting guarantees than the traditional override_creds() approach
ever could've hoped for.
The original work was heavily based and optimzed for the needs of
io_uring which was the first user. However, as it quickly turned out
the ability to create user workers inherting properties from a
userspace process is generally useful.
The vhost subsystem currently creates workers using the kthread api.
The consequences of using the kthread api are that RLIMITs don't work
correctly as they are inherited from khtreadd. This leads to bugs
where more workers are created than would be allowed by the RLIMITs of
the userspace process in lieu of which workers are created.
Problems like this disappear with user workers created from the
userspace processes for which they perform the work. In addition,
providing this api allows vhost to remove additional complexity. For
example, cgroup and mm sharing will just work out of the box with user
workers based on the relevant userspace process instead of manually
ensuring the correct cgroup and mm contexts are used.
So the vhost subsystem should simply be made to use the same mechanism
as io_uring. To this end the original mechanism used for
create_io_thread() is generalized into user workers:
- Introduce PF_USER_WORKER as a generic indicator that a given task
is a user worker, i.e., a kernel task that was created from a
userspace process. Now a PF_IO_WORKER thread is just a specialized
version of PF_USER_WORKER. So io_uring io workers raise both flags.
- Make copy_process() available to core kernel code
- Extend struct kernel_clone_args with the following bitfields
allowing to indicate to copy_process():
- to create a user worker (raise PF_USER_WORKER)
- to not inherit any files from the userspace process
- to ignore signals
After all generic changes are in place the vhost subsystem implements
a new dedicated vhost api based on user workers. Finally, vhost is
switched to rely on the new api moving it off of kthreads.
Thanks to Mike for sticking it out and making it through this rather
arduous journey"
* tag 'v6.4/kernel.user_worker' of git://git.kernel.org/pub/scm/linux/kernel/git/brauner/linux:
vhost: use vhost_tasks for worker threads
vhost: move worker thread fields to new struct
vhost_task: Allow vhost layer to use copy_process
fork: allow kernel code to call copy_process
fork: Add kernel_clone_args flag to ignore signals
fork: add kernel_clone_args flag to not dup/clone files
fork/vm: Move common PF_IO_WORKER behavior to new flag
kernel: Make io_thread and kthread bit fields
kthread: Pass in the thread's name during creation
kernel: Allow a kernel thread's name to be set in copy_process
csky: Remove kernel_thread declaration
Introduce per-mm/cpu current concurrency id (mm_cid) to fix a PostgreSQL
sysbench regression reported by Aaron Lu.
Keep track of the currently allocated mm_cid for each mm/cpu rather than
freeing them immediately on context switch. This eliminates most atomic
operations when context switching back and forth between threads
belonging to different memory spaces in multi-threaded scenarios (many
processes, each with many threads). The per-mm/per-cpu mm_cid values are
serialized by their respective runqueue locks.
Thread migration is handled by introducing invocation to
sched_mm_cid_migrate_to() (with destination runqueue lock held) in
activate_task() for migrating tasks. If the destination cpu's mm_cid is
unset, and if the source runqueue is not actively using its mm_cid, then
the source cpu's mm_cid is moved to the destination cpu on migration.
Introduce a task-work executed periodically, similarly to NUMA work,
which delays reclaim of cid values when they are unused for a period of
time.
Keep track of the allocation time for each per-cpu cid, and let the task
work clear them when they are observed to be older than
SCHED_MM_CID_PERIOD_NS and unused. This task work also clears all
mm_cids which are greater or equal to the Hamming weight of the mm
cidmask to keep concurrency ids compact.
Because we want to ensure the mm_cid converges towards the smaller
values as migrations happen, the prior optimization that was done when
context switching between threads belonging to the same mm is removed,
because it could delay the lazy release of the destination runqueue
mm_cid after it has been replaced by a migration. Removing this prior
optimization is not an issue performance-wise because the introduced
per-mm/per-cpu mm_cid tracking also covers this more specific case.
Fixes: af7f588d8f ("sched: Introduce per-memory-map concurrency ID")
Reported-by: Aaron Lu <aaron.lu@intel.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Aaron Lu <aaron.lu@intel.com>
Link: https://lore.kernel.org/lkml/20230327080502.GA570847@ziqianlu-desk2/
commit f1a7941243 ("mm: convert mm's rss stats into percpu_counter")
introduces a memory leak by missing a call to destroy_context() when a
percpu_counter fails to allocate.
Before introducing the per-cpu counter allocations, init_new_context() was
the last call that could fail in mm_init(), and thus there was no need to
ever invoke destroy_context() in the error paths. Adding the following
percpu counter allocations adds error paths after init_new_context(),
which means its associated destroy_context() needs to be called when
percpu counters fail to allocate.
Link: https://lkml.kernel.org/r/20230330133822.66271-1-mathieu.desnoyers@efficios.com
Fixes: f1a7941243 ("mm: convert mm's rss stats into percpu_counter")
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Acked-by: Shakeel Butt <shakeelb@google.com>
Cc: Marek Szyprowski <m.szyprowski@samsung.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Pach series "sched/numa: Enhance vma scanning", v3.
The patchset proposes one of the enhancements to numa vma scanning
suggested by Mel. This is continuation of [3].
Reposting the rebased patchset to akpm mm-unstable tree (March 1)
Existing mechanism of scan period involves, scan period derived from
per-thread stats. Process Adaptive autoNUMA [1] proposed to gather NUMA
fault stats at per-process level to capture aplication behaviour better.
During that course of discussion, Mel proposed several ideas to enhance
current numa balancing. One of the suggestion was below
Track what threads access a VMA. The suggestion was to use an unsigned
long pid_mask and use the lower bits to tag approximately what threads
access a VMA. Skip VMAs that did not trap a fault. This would be
approximate because of PID collisions but would reduce scanning of areas
the thread is not interested in. The above suggestion intends not to
penalize threads that has no interest in the vma, thus reduce scanning
overhead.
V3 changes are mostly based on PeterZ comments (details below in changes)
Summary of patchset:
Current patchset implements:
1. Delay the vma scanning logic for newly created VMA's so that
additional overhead of scanning is not incurred for short lived tasks
(implementation by Mel)
2. Store the information of tasks accessing VMA in 2 windows. It is
regularly cleared in (4*sysctl_numa_balancing_scan_delay) interval.
The above time is derived from experimenting (Suggested by PeterZ) to
balance between frequent clearing vs obsolete access data
3. hash_32 used to encode task index accessing VMA information
4. VMA's acess information is used to skip scanning for the tasks
which had not accessed VMA
Changes since V2:
patch1:
- Renaming of structure, macro to function,
- Add explanation to heuristics
- Adding more details from result (PeterZ)
Patch2:
- Usage of test and set bit (PeterZ)
- Move storing access PID info to numa_migrate_prep()
- Add a note on fainess among tasks allowed to scan
(PeterZ)
Patch3:
- Maintain two windows of access PID information
(PeterZ supported implementation and Gave idea to extend
to N if needed)
Patch4:
- Apply hash_32 function to track VMA accessing PIDs (PeterZ)
Changes since RFC V1:
- Include Mel's vma scan delay patch
- Change the accessing pid store logic (Thanks Mel)
- Fencing structure / code to NUMA_BALANCING (David, Mel)
- Adding clearing access PID logic (Mel)
- Descriptive change log ( Mike Rapoport)
Things to ponder over:
==========================================
- Improvement to clearing accessing PIDs logic (discussed in-detail in
patch3 itself (Done in this patchset by implementing 2 window history)
- Current scan period is not changed in the patchset, so we do see
frequent tries to scan. Relaxing scan period dynamically could improve
results further.
[1] sched/numa: Process Adaptive autoNUMA
Link: https://lore.kernel.org/lkml/20220128052851.17162-1-bharata@amd.com/T/
[2] RFC V1 Link:
https://lore.kernel.org/all/cover.1673610485.git.raghavendra.kt@amd.com/
[3] V2 Link:
https://lore.kernel.org/lkml/cover.1675159422.git.raghavendra.kt@amd.com/
Results:
Summary: Huge autonuma cost reduction seen in mmtest. Kernbench improvement
is more than 5% and huge system time (80%+) improvement from mmtest autonuma.
(dbench had huge std deviation to post)
kernbench
===========
6.2.0-mmunstable-base 6.2.0-mmunstable-patched
Amean user-256 22002.51 ( 0.00%) 22649.95 * -2.94%*
Amean syst-256 10162.78 ( 0.00%) 8214.13 * 19.17%*
Amean elsp-256 160.74 ( 0.00%) 156.92 * 2.38%*
Duration User 66017.43 67959.84
Duration System 30503.15 24657.03
Duration Elapsed 504.61 493.12
6.2.0-mmunstable-base 6.2.0-mmunstable-patched
Ops NUMA alloc hit 1738835089.00 1738780310.00
Ops NUMA alloc local 1738834448.00 1738779711.00
Ops NUMA base-page range updates 477310.00 392566.00
Ops NUMA PTE updates 477310.00 392566.00
Ops NUMA hint faults 96817.00 87555.00
Ops NUMA hint local faults % 10150.00 2192.00
Ops NUMA hint local percent 10.48 2.50
Ops NUMA pages migrated 86660.00 85363.00
Ops AutoNUMA cost 489.07 442.14
autonumabench
===============
6.2.0-mmunstable-base 6.2.0-mmunstable-patched
Amean syst-NUMA01 399.50 ( 0.00%) 52.05 * 86.97%*
Amean syst-NUMA01_THREADLOCAL 0.21 ( 0.00%) 0.22 * -5.41%*
Amean syst-NUMA02 0.80 ( 0.00%) 0.78 * 2.68%*
Amean syst-NUMA02_SMT 0.65 ( 0.00%) 0.68 * -3.95%*
Amean elsp-NUMA01 313.26 ( 0.00%) 313.11 * 0.05%*
Amean elsp-NUMA01_THREADLOCAL 1.06 ( 0.00%) 1.08 * -1.76%*
Amean elsp-NUMA02 3.19 ( 0.00%) 3.24 * -1.52%*
Amean elsp-NUMA02_SMT 3.72 ( 0.00%) 3.61 * 2.92%*
Duration User 396433.47 324835.96
Duration System 2808.70 376.66
Duration Elapsed 2258.61 2258.12
6.2.0-mmunstable-base 6.2.0-mmunstable-patched
Ops NUMA alloc hit 59921806.00 49623489.00
Ops NUMA alloc miss 0.00 0.00
Ops NUMA interleave hit 0.00 0.00
Ops NUMA alloc local 59920880.00 49622594.00
Ops NUMA base-page range updates 152259275.00 50075.00
Ops NUMA PTE updates 152259275.00 50075.00
Ops NUMA PMD updates 0.00 0.00
Ops NUMA hint faults 154660352.00 39014.00
Ops NUMA hint local faults % 138550501.00 23139.00
Ops NUMA hint local percent 89.58 59.31
Ops NUMA pages migrated 8179067.00 14147.00
Ops AutoNUMA cost 774522.98 195.69
This patch (of 4):
Currently whenever a new task is created we wait for
sysctl_numa_balancing_scan_delay to avoid unnessary scanning overhead.
Extend the same logic to new or very short-lived VMAs.
[raghavendra.kt@amd.com: add initialization in vm_area_dup())]
Link: https://lkml.kernel.org/r/cover.1677672277.git.raghavendra.kt@amd.com
Link: https://lkml.kernel.org/r/7a6fbba87c8b51e67efd3e74285bb4cb311a16ca.1677672277.git.raghavendra.kt@amd.com
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Signed-off-by: Raghavendra K T <raghavendra.kt@amd.com>
Cc: Bharata B Rao <bharata@amd.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Disha Talreja <dishaa.talreja@amd.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
vma->lock being part of the vm_area_struct causes performance regression
during page faults because during contention its count and owner fields
are constantly updated and having other parts of vm_area_struct used
during page fault handling next to them causes constant cache line
bouncing. Fix that by moving the lock outside of the vm_area_struct.
All attempts to keep vma->lock inside vm_area_struct in a separate cache
line still produce performance regression especially on NUMA machines.
Smallest regression was achieved when lock is placed in the fourth cache
line but that bloats vm_area_struct to 256 bytes.
Considering performance and memory impact, separate lock looks like the
best option. It increases memory footprint of each VMA but that can be
optimized later if the new size causes issues. Note that after this
change vma_init() does not allocate or initialize vma->lock anymore. A
number of drivers allocate a pseudo VMA on the stack but they never use
the VMA's lock, therefore it does not need to be allocated. The future
drivers which might need the VMA lock should use
vm_area_alloc()/vm_area_free() to allocate the VMA.
Link: https://lkml.kernel.org/r/20230227173632.3292573-34-surenb@google.com
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
call_rcu() can take a long time when callback offloading is enabled. Its
use in the vm_area_free can cause regressions in the exit path when
multiple VMAs are being freed.
Because exit_mmap() is called only after the last mm user drops its
refcount, the page fault handlers can't be racing with it. Any other
possible user like oom-reaper or process_mrelease are already synchronized
using mmap_lock. Therefore exit_mmap() can free VMAs directly, without
the use of call_rcu().
Expose __vm_area_free() and use it from exit_mmap() to avoid possible
call_rcu() floods and performance regressions caused by it.
Link: https://lkml.kernel.org/r/20230227173632.3292573-33-surenb@google.com
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Introduce per-VMA locking. The lock implementation relies on a per-vma
and per-mm sequence counters to note exclusive locking:
- read lock - (implemented by vma_start_read) requires the vma
(vm_lock_seq) and mm (mm_lock_seq) sequence counters to differ.
If they match then there must be a vma exclusive lock held somewhere.
- read unlock - (implemented by vma_end_read) is a trivial vma->lock
unlock.
- write lock - (vma_start_write) requires the mmap_lock to be held
exclusively and the current mm counter is assigned to the vma counter.
This will allow multiple vmas to be locked under a single mmap_lock
write lock (e.g. during vma merging). The vma counter is modified
under exclusive vma lock.
- write unlock - (vma_end_write_all) is a batch release of all vma
locks held. It doesn't pair with a specific vma_start_write! It is
done before exclusive mmap_lock is released by incrementing mm
sequence counter (mm_lock_seq).
- write downgrade - if the mmap_lock is downgraded to the read lock, all
vma write locks are released as well (effectivelly same as write
unlock).
Link: https://lkml.kernel.org/r/20230227173632.3292573-13-surenb@google.com
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Use the maple tree in RCU mode for VMA tracking.
The maple tree tracks the stack and is able to update the pivot
(lower/upper boundary) in-place to allow the page fault handler to write
to the tree while holding just the mmap read lock. This is safe as the
writes to the stack have a guard VMA which ensures there will always be a
NULL in the direction of the growth and thus will only update a pivot.
It is possible, but not recommended, to have VMAs that grow up/down
without guard VMAs. syzbot has constructed a testcase which sets up a VMA
to grow and consume the empty space. Overwriting the entire NULL entry
causes the tree to be altered in a way that is not safe for concurrent
readers; the readers may see a node being rewritten or one that does not
match the maple state they are using.
Enabling RCU mode allows the concurrent readers to see a stable node and
will return the expected result.
[Liam.Howlett@Oracle.com: we don't need to free the nodes with RCU[
Link: https://lore.kernel.org/linux-mm/000000000000b0a65805f663ace6@google.com/
Link: https://lkml.kernel.org/r/20230227173632.3292573-9-surenb@google.com
Fixes: d4af56c5c7 ("mm: start tracking VMAs with maple tree")
Signed-off-by: Liam R. Howlett <Liam.Howlett@oracle.com>
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
Reported-by: syzbot+8d95422d3537159ca390@syzkaller.appspotmail.com
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Stop open-coding get_unused_fd_flags() and anon_inode_getfile(). That's
brittle just for keeping the flags between both calls in sync. Use the
dedicated helper.
Message-Id: <20230327-pidfd-file-api-v1-2-5c0e9a3158e4@kernel.org>
Signed-off-by: Christian Brauner <brauner@kernel.org>
Add a new helper that allows to reserve a pidfd and allocates a new
pidfd file that stashes the provided struct pid. This will allow us to
remove places that either open code this function or that call
pidfd_create() but then have to call close_fd() because there are still
failure points after pidfd_create() has been called.
Reviewed-by: Jan Kara <jack@suse.cz>
Message-Id: <20230327-pidfd-file-api-v1-1-5c0e9a3158e4@kernel.org>
Signed-off-by: Christian Brauner <brauner@kernel.org>
During tracefs discussions it was decided instead of requiring a mapping
within a user-process to track the lifetime of memory descriptors we
should hook the appropriate calls. Do this by adding the minimal stubs
required for task fork, exec, and exit. Currently this is just a NOP.
Future patches will implement these calls fully.
Link: https://lkml.kernel.org/r/20230328235219.203-3-beaub@linux.microsoft.com
Suggested-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: Beau Belgrave <beaub@linux.microsoft.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
On big systems, the mm refcount can become highly contented when doing a
lot of context switching with threaded applications. user<->idle switch
is one of the important cases. Abandoning lazy tlb entirely slows this
switching down quite a bit in the common uncontended case, so that is not
viable.
Implement a scheme where lazy tlb mm references do not contribute to the
refcount, instead they get explicitly removed when the refcount reaches
zero.
The final mmdrop() sends IPIs to all CPUs in the mm_cpumask and they
switch away from this mm to init_mm if it was being used as the lazy tlb
mm. Enabling the shoot lazies option therefore requires that the arch
ensures that mm_cpumask contains all CPUs that could possibly be using mm.
A DEBUG_VM option IPIs every CPU in the system after this to ensure there
are no references remaining before the mm is freed.
Shootdown IPIs cost could be an issue, but they have not been observed to
be a serious problem with this scheme, because short-lived processes tend
not to migrate CPUs much, therefore they don't get much chance to leave
lazy tlb mm references on remote CPUs. There are a lot of options to
reduce them if necessary, described in comments.
The near-worst-case can be benchmarked with will-it-scale:
context_switch1_threads -t $(($(nproc) / 2))
This will create nproc threads (nproc / 2 switching pairs) all sharing the
same mm that spread over all CPUs so each CPU does thread->idle->thread
switching.
[ Rik came up with basically the same idea a few years ago, so credit
to him for that. ]
Link: https://lore.kernel.org/linux-mm/20230118080011.2258375-1-npiggin@gmail.com/
Link: https://lore.kernel.org/all/20180728215357.3249-11-riel@surriel.com/
Link: https://lkml.kernel.org/r/20230203071837.1136453-5-npiggin@gmail.com
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Nadav Amit <nadav.amit@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Pull xfs percpu counter fixes from Darrick Wong:
"We discovered a filesystem summary counter corruption problem that was
traced to cpu hot-remove racing with the call to percpu_counter_sum
that sets the free block count in the superblock when writing it to
disk. The root cause is that percpu_counter_sum doesn't cull from
dying cpus and hence misses those counter values if the cpu shutdown
hooks have not yet run to merge the values.
I'm hoping this is a fairly painless fix to the problem, since the
dying cpu mask should generally be empty. It's been in for-next for a
week without any complaints from the bots.
- Fix a race in the percpu counters summation code where the
summation failed to add in the values for any CPUs that were dying
but not yet dead. This fixes some minor discrepancies and incorrect
assertions when running generic/650"
* tag 'xfs-6.3-fixes-4' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux:
pcpcntr: remove percpu_counter_sum_all()
fork: remove use of percpu_counter_sum_all
pcpcntrs: fix dying cpu summation race
cpumask: introduce for_each_cpu_or
This effectively reverts the change made in commit f689054aac
("percpu_counter: add percpu_counter_sum_all interface") as the
race condition percpu_counter_sum_all() was invented to avoid is
now handled directly in percpu_counter_sum() and nobody needs to
care about summing racing with cpu unplug anymore.
Signed-off-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
The next patch adds helpers like create_io_thread, but for use by the
vhost layer. There are several functions, so they are in their own file
instead of cluttering up fork.c. This patch allows that new file to
call copy_process.
Signed-off-by: Mike Christie <michael.christie@oracle.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Christian Brauner (Microsoft) <brauner@kernel.org>
Since:
commit 10ab825bde ("change kernel threads to ignore signals instead of
blocking them")
kthreads have been ignoring signals by default, and the vhost layer has
never had a need to change that. This patch adds an option flag,
USER_WORKER_SIG_IGN, handled in copy_process() after copy_sighand()
and copy_signals() so vhost_tasks added in the next patches can continue
to ignore singals.
Signed-off-by: Christian Brauner <brauner@kernel.org>
Signed-off-by: Mike Christie <michael.christie@oracle.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Christian Brauner (Microsoft) <brauner@kernel.org>
Each vhost device gets a thread that is used to perform IO and management
operations. Instead of a thread that is accessing a device, the thread is
part of the device, so when it creates a thread using a helper based on
copy_process we can't dup or clone the parent's files/FDS because it
would do an extra increment on ourself.
Later, when we do:
Qemu process exits:
do_exit -> exit_files -> put_files_struct -> close_files
we would leak the device's resources because of that extra refcount
on the fd or file_struct.
This patch adds a no_files option so these worker threads can prevent
taking an extra refcount on themselves.
Signed-off-by: Mike Christie <michael.christie@oracle.com>
Acked-by: Christian Brauner <brauner@kernel.org>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Christian Brauner (Microsoft) <brauner@kernel.org>
