Pull locking updates from Borislav Petkov:
"Lots of cleanups and preparation. Highlights:
- futex: Cleanup and remove runtime futex_cmpxchg detection
- rtmutex: Some fixes for the PREEMPT_RT locking infrastructure
- kcsan: Share owner_on_cpu() between mutex,rtmutex and rwsem and
annotate the racy owner->on_cpu access *once*.
- atomic64: Dead-Code-Elemination"
[ Description above by Peter Zijlstra ]
* tag 'locking_core_for_v5.17_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
locking/atomic: atomic64: Remove unusable atomic ops
futex: Fix additional regressions
locking: Allow to include asm/spinlock_types.h from linux/spinlock_types_raw.h
x86/mm: Include spinlock_t definition in pgtable.
locking: Mark racy reads of owner->on_cpu
locking: Make owner_on_cpu() into <linux/sched.h>
lockdep/selftests: Adapt ww-tests for PREEMPT_RT
lockdep/selftests: Skip the softirq related tests on PREEMPT_RT
lockdep/selftests: Unbalanced migrate_disable() & rcu_read_lock().
lockdep/selftests: Avoid using local_lock_{acquire|release}().
lockdep: Remove softirq accounting on PREEMPT_RT.
locking/rtmutex: Add rt_mutex_lock_nest_lock() and rt_mutex_lock_killable().
locking/rtmutex: Squash self-deadlock check for ww_rt_mutex.
locking: Remove rt_rwlock_is_contended().
sched: Trigger warning if ->migration_disabled counter underflows.
futex: Fix sparc32/m68k/nds32 build regression
futex: Remove futex_cmpxchg detection
futex: Ensure futex_atomic_cmpxchg_inatomic() is present
kernel/locking: Use a pointer in ww_mutex_trylock().
Pull RCU updates from Paul McKenney:
- Documentation updates, perhaps most notably Neil Brown's writeup of
the reference-counting analogy to RCU.
- Expedited grace-period cleanups.
- Remove CONFIG_RCU_FAST_NO_HZ due to lack of valid users. I have asked
around, posted a blog entry, and sent this series to LKML without
result.
- Miscellaneous fixes.
- RCU callback offloading updates, perhaps most notably Frederic
Weisbecker's updates allowing CPUs booted in the de-offloaded state
to be offloaded at runtime.
- nolibc fixes from Willy Tarreau and Anmar Faizi, but also including
Mark Brown's addition of gettid().
- RCU Tasks Trace fixes, including changes that increase the
scalability of call_rcu_tasks_trace() for the BPF folks (Martin Lau
and KP Singh).
- Various fixes including those from Wander Lairson Costa and Li
Zhijian.
- Fixes plus addition of tests for the increased call_rcu_tasks_trace()
scalability.
* tag 'rcu.2022.01.09a' of git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu: (87 commits)
rcu/nocb: Merge rcu_spawn_cpu_nocb_kthread() and rcu_spawn_one_nocb_kthread()
rcu/nocb: Allow empty "rcu_nocbs" kernel parameter
rcu/nocb: Create kthreads on all CPUs if "rcu_nocbs=" or "nohz_full=" are passed
rcu/nocb: Optimize kthreads and rdp initialization
rcu/nocb: Prepare nocb_cb_wait() to start with a non-offloaded rdp
rcu/nocb: Remove rcu_node structure from nocb list when de-offloaded
rcu-tasks: Use fewer callbacks queues if callback flood ends
rcu-tasks: Use separate ->percpu_dequeue_lim for callback dequeueing
rcu-tasks: Use more callback queues if contention encountered
rcu-tasks: Avoid raw-spinlocked wakeups from call_rcu_tasks_generic()
rcu-tasks: Count trylocks to estimate call_rcu_tasks() contention
rcu-tasks: Add rcupdate.rcu_task_enqueue_lim to set initial queueing
rcu-tasks: Make rcu_barrier_tasks*() handle multiple callback queues
rcu-tasks: Use workqueues for multiple rcu_tasks_invoke_cbs() invocations
rcu-tasks: Abstract invocations of callbacks
rcu-tasks: Abstract checking of callback lists
rcu-tasks: Add a ->percpu_enqueue_lim to the rcu_tasks structure
rcu-tasks: Inspect stalled task's trc state in locked state
rcu-tasks: Use spin_lock_rcu_node() and friends
rcutorture: Combine n_max_cbs from all kthreads in a callback flood
...
There is not really a softirq context on PREEMPT_RT. Softirqs on
PREEMPT_RT are always invoked within the context of a threaded
interrupt handler or within ksoftirqd. The "in-softirq" context is
preemptible and is protected by a per-CPU lock to ensure mutual
exclusion.
There is no difference on PREEMPT_RT between spin_lock_irq() and
spin_lock() because the former does not disable interrupts. Therefore
if a lock is used in_softirq() and locked once with spin_lock_irq()
then lockdep will report this with "inconsistent {SOFTIRQ-ON-W} ->
{IN-SOFTIRQ-W} usage".
Teach lockdep that we don't really do softirqs on -RT.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20211129174654.668506-6-bigeasy@linutronix.de
The locking selftest for ww-mutex expects to operate directly on the
base-mutex which becomes a rtmutex on PREEMPT_RT.
Add a rtmutex based implementation of mutex_lock_nest_lock() and
mutex_lock_killable() named rt_mutex_lock_nest_lock() abd
rt_mutex_lock_killable().
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20211129174654.668506-5-bigeasy@linutronix.de
Similar to the issues in commits:
6467822b8c ("locking/rtmutex: Prevent spurious EDEADLK return caused by ww_mutexes")
a055fcc132 ("locking/rtmutex: Return success on deadlock for ww_mutex waiters")
ww_rt_mutex_lock() should not return EDEADLK without first going through
the __ww_mutex logic to set the required state. In fact, the chain-walk
can deal with the spurious cycles (per the above commits) this check
warns about and is trying to avoid.
Therefore ignore this test for ww_rt_mutex and simply let things fall
in place.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20211129174654.668506-4-bigeasy@linutronix.de
rt_rwlock_is_contended() has no users. It makes no sense to use it as
rwlock_is_contended() because it is a sleeping lock on RT and
preemption is possible. It reports always != 0 if used by a writer and
even if there is a waiter then the lock might not be handed over if
the current owner has the highest priority.
Remove rt_rwlock_is_contended().
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20211129174654.668506-3-bigeasy@linutronix.de
We found that a process with 10 thousnads threads has been encountered
a regression problem from Linux-v4.14 to Linux-v5.4. It is a kind of
workload which will concurrently allocate lots of memory in different
threads sometimes. In this case, we will see the down_read_trylock()
with a high hotspot. Therefore, we suppose that rwsem has a regression
at least since Linux-v5.4. In order to easily debug this problem, we
write a simply benchmark to create the similar situation lile the
following.
```c++
#include <sys/mman.h>
#include <sys/time.h>
#include <sys/resource.h>
#include <sched.h>
#include <cstdio>
#include <cassert>
#include <thread>
#include <vector>
#include <chrono>
volatile int mutex;
void trigger(int cpu, char* ptr, std::size_t sz)
{
cpu_set_t set;
CPU_ZERO(&set);
CPU_SET(cpu, &set);
assert(pthread_setaffinity_np(pthread_self(), sizeof(set), &set) == 0);
while (mutex);
for (std::size_t i = 0; i < sz; i += 4096) {
*ptr = '\0';
ptr += 4096;
}
}
int main(int argc, char* argv[])
{
std::size_t sz = 100;
if (argc > 1)
sz = atoi(argv[1]);
auto nproc = std::thread::hardware_concurrency();
std::vector<std::thread> thr;
sz <<= 30;
auto* ptr = mmap(nullptr, sz, PROT_READ | PROT_WRITE, MAP_ANON |
MAP_PRIVATE, -1, 0);
assert(ptr != MAP_FAILED);
char* cptr = static_cast<char*>(ptr);
auto run = sz / nproc;
run = (run >> 12) << 12;
mutex = 1;
for (auto i = 0U; i < nproc; ++i) {
thr.emplace_back(std::thread([i, cptr, run]() { trigger(i, cptr, run); }));
cptr += run;
}
rusage usage_start;
getrusage(RUSAGE_SELF, &usage_start);
auto start = std::chrono::system_clock::now();
mutex = 0;
for (auto& t : thr)
t.join();
rusage usage_end;
getrusage(RUSAGE_SELF, &usage_end);
auto end = std::chrono::system_clock::now();
timeval utime;
timeval stime;
timersub(&usage_end.ru_utime, &usage_start.ru_utime, &utime);
timersub(&usage_end.ru_stime, &usage_start.ru_stime, &stime);
printf("usr: %ld.%06ld\n", utime.tv_sec, utime.tv_usec);
printf("sys: %ld.%06ld\n", stime.tv_sec, stime.tv_usec);
printf("real: %lu\n",
std::chrono::duration_cast<std::chrono::milliseconds>(end -
start).count());
return 0;
}
```
The functionality of above program is simply which creates `nproc`
threads and each of them are trying to touch memory (trigger page
fault) on different CPU. Then we will see the similar profile by
`perf top`.
25.55% [kernel] [k] down_read_trylock
14.78% [kernel] [k] handle_mm_fault
13.45% [kernel] [k] up_read
8.61% [kernel] [k] clear_page_erms
3.89% [kernel] [k] __do_page_fault
The highest hot instruction, which accounts for about 92%, in
down_read_trylock() is cmpxchg like the following.
91.89 │ lock cmpxchg %rdx,(%rdi)
Sice the problem is found by migrating from Linux-v4.14 to Linux-v5.4,
so we easily found that the commit ddb20d1d3a ("locking/rwsem: Optimize
down_read_trylock()") caused the regression. The reason is that the
commit assumes the rwsem is not contended at all. But it is not always
true for mmap lock which could be contended with thousands threads.
So most threads almost need to run at least 2 times of "cmpxchg" to
acquire the lock. The overhead of atomic operation is higher than
non-atomic instructions, which caused the regression.
By using the above benchmark, the real executing time on a x86-64 system
before and after the patch were:
Before Patch After Patch
# of Threads real real reduced by
------------ ------ ------ ----------
1 65,373 65,206 ~0.0%
4 15,467 15,378 ~0.5%
40 6,214 5,528 ~11.0%
For the uncontended case, the new down_read_trylock() is the same as
before. For the contended cases, the new down_read_trylock() is faster
than before. The more contended, the more fast.
Signed-off-by: Muchun Song <songmuchun@bytedance.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Waiman Long <longman@redhat.com>
Link: https://lore.kernel.org/r/20211118094455.9068-1-songmuchun@bytedance.com
There are some inconsistency in the way that the handoff bit is being
handled in readers and writers that lead to a race condition.
Firstly, when a queue head writer set the handoff bit, it will clear
it when the writer is being killed or interrupted on its way out
without acquiring the lock. That is not the case for a queue head
reader. The handoff bit will simply be inherited by the next waiter.
Secondly, in the out_nolock path of rwsem_down_read_slowpath(), both
the waiter and handoff bits are cleared if the wait queue becomes
empty. For rwsem_down_write_slowpath(), however, the handoff bit is
not checked and cleared if the wait queue is empty. This can
potentially make the handoff bit set with empty wait queue.
Worse, the situation in rwsem_down_write_slowpath() relies on wstate,
a variable set outside of the critical section containing the ->count
manipulation, this leads to race condition where RWSEM_FLAG_HANDOFF
can be double subtracted, corrupting ->count.
To make the handoff bit handling more consistent and robust, extract
out handoff bit clearing code into the new rwsem_del_waiter() helper
function. Also, completely eradicate wstate; always evaluate
everything inside the same critical section.
The common function will only use atomic_long_andnot() to clear bits
when the wait queue is empty to avoid possible race condition. If the
first waiter with handoff bit set is killed or interrupted to exit the
slowpath without acquiring the lock, the next waiter will inherit the
handoff bit.
While at it, simplify the trylock for loop in
rwsem_down_write_slowpath() to make it easier to read.
Fixes: 4f23dbc1e6 ("locking/rwsem: Implement lock handoff to prevent lock starvation")
Reported-by: Zhenhua Ma <mazhenhua@xiaomi.com>
Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20211116012912.723980-1-longman@redhat.com
Merge more updates from Andrew Morton:
"87 patches.
Subsystems affected by this patch series: mm (pagecache and hugetlb),
procfs, misc, MAINTAINERS, lib, checkpatch, binfmt, kallsyms, ramfs,
init, codafs, nilfs2, hfs, crash_dump, signals, seq_file, fork,
sysvfs, kcov, gdb, resource, selftests, and ipc"
* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (87 commits)
ipc/ipc_sysctl.c: remove fallback for !CONFIG_PROC_SYSCTL
ipc: check checkpoint_restore_ns_capable() to modify C/R proc files
selftests/kselftest/runner/run_one(): allow running non-executable files
virtio-mem: disallow mapping virtio-mem memory via /dev/mem
kernel/resource: disallow access to exclusive system RAM regions
kernel/resource: clean up and optimize iomem_is_exclusive()
scripts/gdb: handle split debug for vmlinux
kcov: replace local_irq_save() with a local_lock_t
kcov: avoid enable+disable interrupts if !in_task()
kcov: allocate per-CPU memory on the relevant node
Documentation/kcov: define `ip' in the example
Documentation/kcov: include types.h in the example
sysv: use BUILD_BUG_ON instead of runtime check
kernel/fork.c: unshare(): use swap() to make code cleaner
seq_file: fix passing wrong private data
seq_file: move seq_escape() to a header
signal: remove duplicate include in signal.h
crash_dump: remove duplicate include in crash_dump.h
crash_dump: fix boolreturn.cocci warning
hfs/hfsplus: use WARN_ON for sanity check
...
Merge misc updates from Andrew Morton:
"257 patches.
Subsystems affected by this patch series: scripts, ocfs2, vfs, and
mm (slab-generic, slab, slub, kconfig, dax, kasan, debug, pagecache,
gup, swap, memcg, pagemap, mprotect, mremap, iomap, tracing, vmalloc,
pagealloc, memory-failure, hugetlb, userfaultfd, vmscan, tools,
memblock, oom-kill, hugetlbfs, migration, thp, readahead, nommu, ksm,
vmstat, madvise, memory-hotplug, rmap, zsmalloc, highmem, zram,
cleanups, kfence, and damon)"
* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (257 commits)
mm/damon: remove return value from before_terminate callback
mm/damon: fix a few spelling mistakes in comments and a pr_debug message
mm/damon: simplify stop mechanism
Docs/admin-guide/mm/pagemap: wordsmith page flags descriptions
Docs/admin-guide/mm/damon/start: simplify the content
Docs/admin-guide/mm/damon/start: fix a wrong link
Docs/admin-guide/mm/damon/start: fix wrong example commands
mm/damon/dbgfs: add adaptive_targets list check before enable monitor_on
mm/damon: remove unnecessary variable initialization
Documentation/admin-guide/mm/damon: add a document for DAMON_RECLAIM
mm/damon: introduce DAMON-based Reclamation (DAMON_RECLAIM)
selftests/damon: support watermarks
mm/damon/dbgfs: support watermarks
mm/damon/schemes: activate schemes based on a watermarks mechanism
tools/selftests/damon: update for regions prioritization of schemes
mm/damon/dbgfs: support prioritization weights
mm/damon/vaddr,paddr: support pageout prioritization
mm/damon/schemes: prioritize regions within the quotas
mm/damon/selftests: support schemes quotas
mm/damon/dbgfs: support quotas of schemes
...
Pull RCU updates from Paul McKenney:
- Miscellaneous fixes
- Torture-test updates for smp_call_function(), most notably improved
checking of module parameters.
- Tasks-trace RCU updates that fix a number of rare but important
race-condition bugs.
- Other torture-test updates, most notably better checking of module
parameters. In addition, rcutorture may once again be run on
CONFIG_PREEMPT_RT kernels.
- Torture-test scripting updates, most notably specifying the new
CONFIG_KCSAN_STRICT kconfig option rather than maintaining an
ever-changing list of individual KCSAN kconfig options.
* tag 'rcu.2021.11.01a' of git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu: (46 commits)
rcu: Fix rcu_dynticks_curr_cpu_in_eqs() vs noinstr
rcu: Always inline rcu_dynticks_task*_{enter,exit}()
torture: Make kvm-remote.sh print size of downloaded tarball
torture: Allot 1G of memory for scftorture runs
tools/rcu: Add an extract-stall script
scftorture: Warn on individual scf_torture_init() error conditions
scftorture: Count reschedule IPIs
scftorture: Account for weight_resched when checking for all zeroes
scftorture: Shut down if nonsensical arguments given
scftorture: Allow zero weight to exclude an smp_call_function*() category
rcu: Avoid unneeded function call in rcu_read_unlock()
rcu-tasks: Update comments to cond_resched_tasks_rcu_qs()
rcu-tasks: Fix IPI failure handling in trc_wait_for_one_reader
rcu-tasks: Fix read-side primitives comment for call_rcu_tasks_trace
rcu-tasks: Clarify read side section info for rcu_tasks_rude GP primitives
rcu-tasks: Correct comparisons for CPU numbers in show_stalled_task_trace
rcu-tasks: Correct firstreport usage in check_all_holdout_tasks_trace
rcu-tasks: Fix s/rcu_add_holdout/trc_add_holdout/ typo in comment
rcu-tasks: Move RTGS_WAIT_CBS to beginning of rcu_tasks_kthread() loop
rcu-tasks: Fix s/instruction/instructions/ typo in comment
...
Pull objtool updates from Thomas Gleixner:
- Improve retpoline code patching by separating it from alternatives
which reduces memory footprint and allows to do better optimizations
in the actual runtime patching.
- Add proper retpoline support for x86/BPF
- Address noinstr warnings in x86/kvm, lockdep and paravirtualization
code
- Add support to handle pv_opsindirect calls in the noinstr analysis
- Classify symbols upfront and cache the result to avoid redundant
str*cmp() invocations.
- Add a CFI hash to reduce memory consumption which also reduces
runtime on a allyesconfig by ~50%
- Adjust XEN code to make objtool handling more robust and as a side
effect to prevent text fragmentation due to placement of the
hypercall page.
* tag 'objtool-core-2021-10-31' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (41 commits)
bpf,x86: Respect X86_FEATURE_RETPOLINE*
bpf,x86: Simplify computing label offsets
x86,bugs: Unconditionally allow spectre_v2=retpoline,amd
x86/alternative: Add debug prints to apply_retpolines()
x86/alternative: Try inline spectre_v2=retpoline,amd
x86/alternative: Handle Jcc __x86_indirect_thunk_\reg
x86/alternative: Implement .retpoline_sites support
x86/retpoline: Create a retpoline thunk array
x86/retpoline: Move the retpoline thunk declarations to nospec-branch.h
x86/asm: Fixup odd GEN-for-each-reg.h usage
x86/asm: Fix register order
x86/retpoline: Remove unused replacement symbols
objtool,x86: Replace alternatives with .retpoline_sites
objtool: Shrink struct instruction
objtool: Explicitly avoid self modifying code in .altinstr_replacement
objtool: Classify symbols
objtool: Support pv_opsindirect calls for noinstr
x86/xen: Rework the xen_{cpu,irq,mmu}_opsarrays
x86/xen: Mark xen_force_evtchn_callback() noinstr
x86/xen: Make irq_disable() noinstr
...
parisc, ia64 and powerpc32 are the only remaining architectures that
provide custom arch_{spin,read,write}_lock_flags() functions, which are
meant to re-enable interrupts while waiting for a spinlock.
However, none of these can actually run into this codepath, because
it is only called on architectures without CONFIG_GENERIC_LOCKBREAK,
or when CONFIG_DEBUG_LOCK_ALLOC is set without CONFIG_LOCKDEP, and none
of those combinations are possible on the three architectures.
Going back in the git history, it appears that arch/mn10300 may have
been able to run into this code path, but there is a good chance that
it never worked. On the architectures that still exist, it was
already impossible to hit back in 2008 after the introduction of
CONFIG_GENERIC_LOCKBREAK, and possibly earlier.
As this is all dead code, just remove it and the helper functions built
around it. For arch/ia64, the inline asm could be cleaned up, but
it seems safer to leave it untouched.
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Helge Deller <deller@gmx.de> # parisc
Link: https://lore.kernel.org/r/20211022120058.1031690-1-arnd@kernel.org
