The rcu_dump_cpu_stacks() holds the leaf rcu_node structure's ->lock
when dumping the stakcks of any CPUs stalling the current grace period.
This lock is held to prevent confusion that would otherwise occur when
the stalled CPU reported its quiescent state (and then went on to do
unrelated things) just as the backtrace NMI was heading towards it.
This has worked well, but on larger systems has recently been observed
to cause severe lock contention resulting in CSD-lock stalls and other
general unhappiness.
This commit therefore does printk_deferred_enter() before acquiring
the lock and printk_deferred_exit() after releasing it, thus deferring
the overhead of actually outputting the stack trace out of that lock's
critical section.
Reported-by: Rik van Riel <riel@surriel.com>
Suggested-by: Rik van Riel <riel@surriel.com>
Signed-off-by: "Paul E. McKenney" <paulmck@kernel.org>
Signed-off-by: Neeraj Upadhyay <neeraj.upadhyay@kernel.org>
Pre-GP accesses performed by the update side must be ordered against
post-GP accesses performed by the readers. This is ensured by the
bypass or nocb locking on enqueue time, followed by the fully ordered
rnp locking initiated while callbacks are accelerated, and then
propagated throughout the whole GP lifecyle associated with the
callbacks.
Therefore the explicit barrier advertizing ordering between bypass
enqueue and rcuo wakeup is superfluous. If anything, it would even only
order the first bypass callback enqueue against the rcuo wakeup and
ignore all the subsequent ones.
Remove the needless barrier.
Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Neeraj Upadhyay <neeraj.upadhyay@kernel.org>
A callback enqueuer currently wakes up the rcuo kthread if it is adding
the first non-done callback of a CPU, whether the kthread is waiting on
a grace period or not (unless the CPU is offline).
This looks like a desired behaviour because then the rcuo kthread
doesn't wait for the end of the current grace period to handle the
callback. It is accelerated right away and assigned to the next grace
period. The GP kthread is notified about that fact and iterates with
the upcoming GP without sleeping in-between.
However this best-case scenario is contradicted by a few details,
depending on the situation:
1) If the callback is a non-bypass one queued with IRQs enabled, the
wake up only occurs if no other pending callbacks are on the list.
Therefore the theoretical "optimization" actually applies on rare
occasions.
2) If the callback is a non-bypass one queued with IRQs disabled, the
situation is similar with even more uncertainty due to the deferred
wake up.
3) If the callback is lazy, a few jiffies don't make any difference.
4) If the callback is bypass, the wake up timer is programmed 2 jiffies
ahead by rcuo in case the regular pending queue has been handled
in the meantime. The rare storm of callbacks can otherwise wait for
the currently elapsing grace period to be flushed and handled.
For all those reasons, the optimization is only theoretical and
occasional. Therefore it is reasonable that callbacks enqueuers only
wake up the rcuo kthread when it is not already waiting on a grace
period to complete.
Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Neeraj Upadhyay <neeraj.upadhyay@kernel.org>
After a CPU is marked offline and until it reaches its final trip to
idle, rcuo has several opportunities to be woken up, either because
a callback has been queued in the meantime or because
rcutree_report_cpu_dead() has issued the final deferred NOCB wake up.
If RCU-boosting is enabled, RCU kthreads are set to SCHED_FIFO policy.
And if RT-bandwidth is enabled, the related hrtimer might be armed.
However this then happens after hrtimers have been migrated at the
CPUHP_AP_HRTIMERS_DYING stage, which is broken as reported by the
following warning:
Call trace:
enqueue_hrtimer+0x7c/0xf8
hrtimer_start_range_ns+0x2b8/0x300
enqueue_task_rt+0x298/0x3f0
enqueue_task+0x94/0x188
ttwu_do_activate+0xb4/0x27c
try_to_wake_up+0x2d8/0x79c
wake_up_process+0x18/0x28
__wake_nocb_gp+0x80/0x1a0
do_nocb_deferred_wakeup_common+0x3c/0xcc
rcu_report_dead+0x68/0x1ac
cpuhp_report_idle_dead+0x48/0x9c
do_idle+0x288/0x294
cpu_startup_entry+0x34/0x3c
secondary_start_kernel+0x138/0x158
Fix this with waking up rcuo using an IPI if necessary. Since the
existing API to deal with this situation only handles swait queue, rcuo
is only woken up from offline CPUs if it's not already waiting on a
grace period. In the worst case some callbacks will just wait for a
grace period to complete before being assigned to a subsequent one.
Reported-by: "Cheng-Jui Wang (王正睿)" <Cheng-Jui.Wang@mediatek.com>
Fixes: 5c0930ccaa ("hrtimers: Push pending hrtimers away from outgoing CPU earlier")
Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Neeraj Upadhyay <neeraj.upadhyay@kernel.org>
Now that the (de-)offloading process can only apply to offline CPUs,
there is no more concurrency between rcu_core and nocb kthreads. Also
the mutation now happens on empty queues.
Therefore the state machine can be reduced to a single bit called
SEGCBLIST_OFFLOADED. Simplify the transition as follows:
* Upon offloading: queue the rdp to be added to the rcuog list and
wait for the rcuog kthread to set the SEGCBLIST_OFFLOADED bit. Unpark
rcuo kthread.
* Upon de-offloading: Park rcuo kthread. Queue the rdp to be removed
from the rcuog list and wait for the rcuog kthread to clear the
SEGCBLIST_OFFLOADED bit.
Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Reviewed-by: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: Neeraj Upadhyay <neeraj.upadhyay@kernel.org>
Pull perf fixes from Borislav Petkov:
- Fix perf's AUX buffer serialization
- Prevent uninitialized struct members in perf's uprobes handling
* tag 'perf_urgent_for_v6.11_rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
perf/aux: Fix AUX buffer serialization
uprobes: Use kzalloc to allocate xol area
pick_task_scx() must be preceded by balance_scx() but there currently is a
bug where fair could say yes on balance() but no on pick_task(), which then
ends up calling pick_task_scx() without preceding balance_scx(). Work around
by dropping WARN_ON_ONCE() and ignoring cases which don't make sense.
This isn't great and can theoretically lead to stalls. However, for
switch_all cases, this happens only while a BPF scheduler is being loaded or
unloaded, and, for partial cases, fair will likely keep triggering this CPU.
This will be reverted once the fair behavior is fixed.
Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
static_call_module_notify() triggers a WARN_ON(), when memory allocation
fails in __static_call_add_module().
That's not really justified, because the failure case must be correctly
handled by the well known call chain and the error code is passed
through to the initiating userspace application.
A memory allocation fail is not a fatal problem, but the WARN_ON() takes
the machine out when panic_on_warn is set.
Replace it with a pr_warn().
Fixes: 9183c3f9ed ("static_call: Add inline static call infrastructure")
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/8734mf7pmb.ffs@tglx
Module insertion invokes static_call_add_module() to initialize the static
calls in a module. static_call_add_module() invokes __static_call_init(),
which allocates a struct static_call_mod to either encapsulate the built-in
static call sites of the associated key into it so further modules can be
added or to append the module to the module chain.
If that allocation fails the function returns with an error code and the
module core invokes static_call_del_module() to clean up eventually added
static_call_mod entries.
This works correctly, when all keys used by the module were converted over
to a module chain before the failure. If not then static_call_del_module()
causes a #GP as it blindly assumes that key::mods points to a valid struct
static_call_mod.
The problem is that key::mods is not a individual struct member of struct
static_call_key, it's part of a union to save space:
union {
/* bit 0: 0 = mods, 1 = sites */
unsigned long type;
struct static_call_mod *mods;
struct static_call_site *sites;
};
key::sites is a pointer to the list of built-in usage sites of the static
call. The type of the pointer is differentiated by bit 0. A mods pointer
has the bit clear, the sites pointer has the bit set.
As static_call_del_module() blidly assumes that the pointer is a valid
static_call_mod type, it fails to check for this failure case and
dereferences the pointer to the list of built-in call sites, which is
obviously bogus.
Cure it by checking whether the key has a sites or a mods pointer.
If it's a sites pointer then the key is not to be touched. As the sites are
walked in the same order as in __static_call_init() the site walk can be
terminated because all subsequent sites have not been touched by the init
code due to the error exit.
If it was converted before the allocation fail, then the inner loop which
searches for a module match will find nothing.
A fail in the second allocation in __static_call_init() is harmless and
does not require special treatment. The first allocation succeeded and
converted the key to a module chain. That first entry has mod::mod == NULL
and mod::next == NULL, so the inner loop of static_call_del_module() will
neither find a module match nor a module chain. The next site in the walk
was either already converted, but can't match the module, or it will exit
the outer loop because it has a static_call_site pointer and not a
static_call_mod pointer.
Fixes: 9183c3f9ed ("static_call: Add inline static call infrastructure")
Closes: https://lore.kernel.org/all/20230915082126.4187913-1-ruanjinjie@huawei.com
Reported-by: Jinjie Ruan <ruanjinjie@huawei.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Jinjie Ruan <ruanjinjie@huawei.com>
Link: https://lore.kernel.org/r/87zfon6b0s.ffs@tglx
Pull bpf fixes from Alexei Starovoitov:
- Fix crash when btf_parse_base() returns an error (Martin Lau)
- Fix out of bounds access in btf_name_valid_section() (Jeongjun Park)
* tag 'bpf-6.11-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf:
selftests/bpf: Add a selftest to check for incorrect names
bpf: add check for invalid name in btf_name_valid_section()
bpf: Fix a crash when btf_parse_base() returns an error pointer
Pull tracing fixes from Steven Rostedt:
- Fix adding a new fgraph callback after function graph tracing has
already started.
If the new caller does not initialize its hash before registering the
fgraph_ops, it can cause a NULL pointer dereference. Fix this by
adding a new parameter to ftrace_graph_enable_direct() passing in the
newly added gops directly and not rely on using the fgraph_array[],
as entries in the fgraph_array[] must be initialized.
Assign the new gops to the fgraph_array[] after it goes through
ftrace_startup_subops() as that will properly initialize the
gops->ops and initialize its hashes.
- Fix a memory leak in fgraph storage memory test.
If the "multiple fgraph storage on a function" boot up selftest fails
in the registering of the function graph tracer, it will not free the
memory it allocated for the filter. Break the loop up into two where
it allocates the filters first and then registers the functions where
any errors will do the appropriate clean ups.
- Only clear the timerlat timers if it has an associated kthread.
In the rtla tool that uses timerlat, if it was killed just as it was
shutting down, the signals can free the kthread and the timer. But
the closing of the timerlat files could cause the hrtimer_cancel() to
be called on the already freed timer. As the kthread variable is is
set to NULL when the kthreads are stopped and the timers are freed it
can be used to know not to call hrtimer_cancel() on the timer if the
kthread variable is NULL.
- Use a cpumask to keep track of osnoise/timerlat kthreads
The timerlat tracer can use user space threads for its analysis. With
the killing of the rtla tool, the kernel can get confused between if
it is using a user space thread to analyze or one of its own kernel
threads. When this confusion happens, kthread_stop() can be called on
a user space thread and bad things happen. As the kernel threads are
per-cpu, a bitmask can be used to know when a kernel thread is used
or when a user space thread is used.
- Add missing interface_lock to osnoise/timerlat stop_kthread()
The stop_kthread() function in osnoise/timerlat clears the osnoise
kthread variable, and if it was a user space thread does a put_task
on it. But this can race with the closing of the timerlat files that
also does a put_task on the kthread, and if the race happens the task
will have put_task called on it twice and oops.
- Add cond_resched() to the tracing_iter_reset() loop.
The latency tracers keep writing to the ring buffer without resetting
when it issues a new "start" event (like interrupts being disabled).
When reading the buffer with an iterator, the tracing_iter_reset()
sets its pointer to that start event by walking through all the
events in the buffer until it gets to the time stamp of the start
event. In the case of a very large buffer, the loop that looks for
the start event has been reported taking a very long time with a non
preempt kernel that it can trigger a soft lock up warning. Add a
cond_resched() into that loop to make sure that doesn't happen.
- Use list_del_rcu() for eventfs ei->list variable
It was reported that running loops of creating and deleting kprobe
events could cause a crash due to the eventfs list iteration hitting
a LIST_POISON variable. This is because the list is protected by SRCU
but when an item is deleted from the list, it was using list_del()
which poisons the "next" pointer. This is what list_del_rcu() was to
prevent.
* tag 'trace-v6.11-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace:
tracing/timerlat: Add interface_lock around clearing of kthread in stop_kthread()
tracing/timerlat: Only clear timer if a kthread exists
tracing/osnoise: Use a cpumask to know what threads are kthreads
eventfs: Use list_del_rcu() for SRCU protected list variable
tracing: Avoid possible softlockup in tracing_iter_reset()
tracing: Fix memory leak in fgraph storage selftest
tracing: fgraph: Fix to add new fgraph_ops to array after ftrace_startup_subops()
Commit 980ca8ceea ("bpf: check bpf_dummy_struct_ops program params for
test runs") does bitwise AND between reg_type and PTR_MAYBE_NULL, which
is correct, but due to type difference the compiler complains:
net/bpf/bpf_dummy_struct_ops.c:118:31: warning: bitwise operation between different enumeration types ('const enum bpf_reg_type' and 'enum bpf_type_flag') [-Wenum-enum-conversion]
118 | if (info && (info->reg_type & PTR_MAYBE_NULL))
| ~~~~~~~~~~~~~~ ^ ~~~~~~~~~~~~~~
Workaround the warning by moving the type_may_be_null() helper from
verifier.c into bpf_verifier.h, and reuse it here to check whether param
is nullable.
Fixes: 980ca8ceea ("bpf: check bpf_dummy_struct_ops program params for test runs")
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202404241956.HEiRYwWq-lkp@intel.com/
Signed-off-by: Shung-Hsi Yu <shung-hsi.yu@suse.com>
Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Link: https://lore.kernel.org/r/20240905055233.70203-1-shung-hsi.yu@suse.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Uprobe multi link does its own process (thread leader) filtering before
running the bpf program by comparing task's vm pointers.
But as Oleg pointed out there can be processes sharing the vm (CLONE_VM),
so we can't just compare task->vm pointers, but instead we need to use
same_thread_group call.
Suggested-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Oleg Nesterov <oleg@redhat.com>
Link: https://lore.kernel.org/bpf/20240905115124.1503998-2-jolsa@kernel.org
The timerlat interface will get and put the task that is part of the
"kthread" field of the osn_var to keep it around until all references are
released. But here's a race in the "stop_kthread()" code that will call
put_task_struct() on the kthread if it is not a kernel thread. This can
race with the releasing of the references to that task struct and the
put_task_struct() can be called twice when it should have been called just
once.
Take the interface_lock() in stop_kthread() to synchronize this change.
But to do so, the function stop_per_cpu_kthreads() needs to change the
loop from for_each_online_cpu() to for_each_possible_cpu() and remove the
cpu_read_lock(), as the interface_lock can not be taken while the cpu
locks are held. The only side effect of this change is that it may do some
extra work, as the per_cpu variables of the offline CPUs would not be set
anyway, and would simply be skipped in the loop.
Remove unneeded "return;" in stop_kthread().
Cc: stable@vger.kernel.org
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Tomas Glozar <tglozar@redhat.com>
Cc: John Kacur <jkacur@redhat.com>
Cc: "Luis Claudio R. Goncalves" <lgoncalv@redhat.com>
Link: https://lore.kernel.org/20240905113359.2b934242@gandalf.local.home
Fixes: e88ed227f6 ("tracing/timerlat: Add user-space interface")
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
The timerlat tracer can use user space threads to check for osnoise and
timer latency. If the program using this is killed via a SIGTERM, the
threads are shutdown one at a time and another tracing instance can start
up resetting the threads before they are fully closed. That causes the
hrtimer assigned to the kthread to be shutdown and freed twice when the
dying thread finally closes the file descriptors, causing a use-after-free
bug.
Only cancel the hrtimer if the associated thread is still around. Also add
the interface_lock around the resetting of the tlat_var->kthread.
Note, this is just a quick fix that can be backported to stable. A real
fix is to have a better synchronization between the shutdown of old
threads and the starting of new ones.
Link: https://lore.kernel.org/all/20240820130001.124768-1-tglozar@redhat.com/
Cc: stable@vger.kernel.org
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: "Luis Claudio R. Goncalves" <lgoncalv@redhat.com>
Link: https://lore.kernel.org/20240905085330.45985730@gandalf.local.home
Fixes: e88ed227f6 ("tracing/timerlat: Add user-space interface")
Reported-by: Tomas Glozar <tglozar@redhat.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
The start_kthread() and stop_thread() code was not always called with the
interface_lock held. This means that the kthread variable could be
unexpectedly changed causing the kthread_stop() to be called on it when it
should not have been, leading to:
while true; do
rtla timerlat top -u -q & PID=$!;
sleep 5;
kill -INT $PID;
sleep 0.001;
kill -TERM $PID;
wait $PID;
done
Causing the following OOPS:
Oops: general protection fault, probably for non-canonical address 0xdffffc0000000002: 0000 [#1] PREEMPT SMP KASAN PTI
KASAN: null-ptr-deref in range [0x0000000000000010-0x0000000000000017]
CPU: 5 UID: 0 PID: 885 Comm: timerlatu/5 Not tainted 6.11.0-rc4-test-00002-gbc754cc76d1b-dirty #125 a533010b71dab205ad2f507188ce8c82203b0254
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-debian-1.16.3-2 04/01/2014
RIP: 0010:hrtimer_active+0x58/0x300
Code: 48 c1 ee 03 41 54 48 01 d1 48 01 d6 55 53 48 83 ec 20 80 39 00 0f 85 30 02 00 00 49 8b 6f 30 4c 8d 75 10 4c 89 f0 48 c1 e8 03 <0f> b6 3c 10 4c 89 f0 83 e0 07 83 c0 03 40 38 f8 7c 09 40 84 ff 0f
RSP: 0018:ffff88811d97f940 EFLAGS: 00010202
RAX: 0000000000000002 RBX: ffff88823c6b5b28 RCX: ffffed10478d6b6b
RDX: dffffc0000000000 RSI: ffffed10478d6b6c RDI: ffff88823c6b5b28
RBP: 0000000000000000 R08: ffff88823c6b5b58 R09: ffff88823c6b5b60
R10: ffff88811d97f957 R11: 0000000000000010 R12: 00000000000a801d
R13: ffff88810d8b35d8 R14: 0000000000000010 R15: ffff88823c6b5b28
FS: 0000000000000000(0000) GS:ffff88823c680000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000561858ad7258 CR3: 000000007729e001 CR4: 0000000000170ef0
Call Trace:
<TASK>
? die_addr+0x40/0xa0
? exc_general_protection+0x154/0x230
? asm_exc_general_protection+0x26/0x30
? hrtimer_active+0x58/0x300
? __pfx_mutex_lock+0x10/0x10
? __pfx_locks_remove_file+0x10/0x10
hrtimer_cancel+0x15/0x40
timerlat_fd_release+0x8e/0x1f0
? security_file_release+0x43/0x80
__fput+0x372/0xb10
task_work_run+0x11e/0x1f0
? _raw_spin_lock+0x85/0xe0
? __pfx_task_work_run+0x10/0x10
? poison_slab_object+0x109/0x170
? do_exit+0x7a0/0x24b0
do_exit+0x7bd/0x24b0
? __pfx_migrate_enable+0x10/0x10
? __pfx_do_exit+0x10/0x10
? __pfx_read_tsc+0x10/0x10
? ktime_get+0x64/0x140
? _raw_spin_lock_irq+0x86/0xe0
do_group_exit+0xb0/0x220
get_signal+0x17ba/0x1b50
? vfs_read+0x179/0xa40
? timerlat_fd_read+0x30b/0x9d0
? __pfx_get_signal+0x10/0x10
? __pfx_timerlat_fd_read+0x10/0x10
arch_do_signal_or_restart+0x8c/0x570
? __pfx_arch_do_signal_or_restart+0x10/0x10
? vfs_read+0x179/0xa40
? ksys_read+0xfe/0x1d0
? __pfx_ksys_read+0x10/0x10
syscall_exit_to_user_mode+0xbc/0x130
do_syscall_64+0x74/0x110
? __pfx___rseq_handle_notify_resume+0x10/0x10
? __pfx_ksys_read+0x10/0x10
? fpregs_restore_userregs+0xdb/0x1e0
? fpregs_restore_userregs+0xdb/0x1e0
? syscall_exit_to_user_mode+0x116/0x130
? do_syscall_64+0x74/0x110
? do_syscall_64+0x74/0x110
? do_syscall_64+0x74/0x110
entry_SYSCALL_64_after_hwframe+0x71/0x79
RIP: 0033:0x7ff0070eca9c
Code: Unable to access opcode bytes at 0x7ff0070eca72.
RSP: 002b:00007ff006dff8c0 EFLAGS: 00000246 ORIG_RAX: 0000000000000000
RAX: 0000000000000000 RBX: 0000000000000005 RCX: 00007ff0070eca9c
RDX: 0000000000000400 RSI: 00007ff006dff9a0 RDI: 0000000000000003
RBP: 00007ff006dffde0 R08: 0000000000000000 R09: 00007ff000000ba0
R10: 00007ff007004b08 R11: 0000000000000246 R12: 0000000000000003
R13: 00007ff006dff9a0 R14: 0000000000000007 R15: 0000000000000008
</TASK>
Modules linked in: snd_hda_intel snd_intel_dspcfg snd_intel_sdw_acpi snd_hda_codec snd_hwdep snd_hda_core
---[ end trace 0000000000000000 ]---
This is because it would mistakenly call kthread_stop() on a user space
thread making it "exit" before it actually exits.
Since kthreads are created based on global behavior, use a cpumask to know
when kthreads are running and that they need to be shutdown before
proceeding to do new work.
Link: https://lore.kernel.org/all/20240820130001.124768-1-tglozar@redhat.com/
This was debugged by using the persistent ring buffer:
Link: https://lore.kernel.org/all/20240823013902.135036960@goodmis.org/
Note, locking was originally used to fix this, but that proved to cause too
many deadlocks to work around:
https://lore.kernel.org/linux-trace-kernel/20240823102816.5e55753b@gandalf.local.home/
Cc: stable@vger.kernel.org
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: "Luis Claudio R. Goncalves" <lgoncalv@redhat.com>
Link: https://lore.kernel.org/20240904103428.08efdf4c@gandalf.local.home
Fixes: e88ed227f6 ("tracing/timerlat: Add user-space interface")
Reported-by: Tomas Glozar <tglozar@redhat.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Another big bottleneck to scalablity is uprobe_treelock that's taken in
a very hot path in handle_swbp(). Now that uprobes are SRCU-protected,
take advantage of that and make uprobes_tree RB-tree look up lockless.
To make RB-tree RCU-protected lockless lookup correct, we need to take
into account that such RB-tree lookup can return false negatives if there
are parallel RB-tree modifications (rotations) going on. We use seqcount
lock to detect whether RB-tree changed, and if we find nothing while
RB-tree got modified inbetween, we just retry. If uprobe was found, then
it's guaranteed to be a correct lookup.
With all the lock-avoiding changes done, we get a pretty decent
improvement in performance and scalability of uprobes with number of
CPUs, even though we are still nowhere near linear scalability. This is
due to SRCU not really scaling very well with number of CPUs on
a particular hardware that was used for testing (80-core Intel Xeon Gold
6138 CPU @ 2.00GHz), but also due to the remaning mmap_lock, which is
currently taken to resolve interrupt address to inode+offset and then
uprobe instance. And, of course, uretprobes still need similar RCU to
avoid refcount in the hot path, which will be addressed in the follow up
patches.
Nevertheless, the improvement is good. We used BPF selftest-based
uprobe-nop and uretprobe-nop benchmarks to get the below numbers,
varying number of CPUs on which uprobes and uretprobes are triggered.
BASELINE
========
uprobe-nop ( 1 cpus): 3.032 ± 0.023M/s ( 3.032M/s/cpu)
uprobe-nop ( 2 cpus): 3.452 ± 0.005M/s ( 1.726M/s/cpu)
uprobe-nop ( 4 cpus): 3.663 ± 0.005M/s ( 0.916M/s/cpu)
uprobe-nop ( 8 cpus): 3.718 ± 0.038M/s ( 0.465M/s/cpu)
uprobe-nop (16 cpus): 3.344 ± 0.008M/s ( 0.209M/s/cpu)
uprobe-nop (32 cpus): 2.288 ± 0.021M/s ( 0.071M/s/cpu)
uprobe-nop (64 cpus): 3.205 ± 0.004M/s ( 0.050M/s/cpu)
uretprobe-nop ( 1 cpus): 1.979 ± 0.005M/s ( 1.979M/s/cpu)
uretprobe-nop ( 2 cpus): 2.361 ± 0.005M/s ( 1.180M/s/cpu)
uretprobe-nop ( 4 cpus): 2.309 ± 0.002M/s ( 0.577M/s/cpu)
uretprobe-nop ( 8 cpus): 2.253 ± 0.001M/s ( 0.282M/s/cpu)
uretprobe-nop (16 cpus): 2.007 ± 0.000M/s ( 0.125M/s/cpu)
uretprobe-nop (32 cpus): 1.624 ± 0.003M/s ( 0.051M/s/cpu)
uretprobe-nop (64 cpus): 2.149 ± 0.001M/s ( 0.034M/s/cpu)
SRCU CHANGES
============
uprobe-nop ( 1 cpus): 3.276 ± 0.005M/s ( 3.276M/s/cpu)
uprobe-nop ( 2 cpus): 4.125 ± 0.002M/s ( 2.063M/s/cpu)
uprobe-nop ( 4 cpus): 7.713 ± 0.002M/s ( 1.928M/s/cpu)
uprobe-nop ( 8 cpus): 8.097 ± 0.006M/s ( 1.012M/s/cpu)
uprobe-nop (16 cpus): 6.501 ± 0.056M/s ( 0.406M/s/cpu)
uprobe-nop (32 cpus): 4.398 ± 0.084M/s ( 0.137M/s/cpu)
uprobe-nop (64 cpus): 6.452 ± 0.000M/s ( 0.101M/s/cpu)
uretprobe-nop ( 1 cpus): 2.055 ± 0.001M/s ( 2.055M/s/cpu)
uretprobe-nop ( 2 cpus): 2.677 ± 0.000M/s ( 1.339M/s/cpu)
uretprobe-nop ( 4 cpus): 4.561 ± 0.003M/s ( 1.140M/s/cpu)
uretprobe-nop ( 8 cpus): 5.291 ± 0.002M/s ( 0.661M/s/cpu)
uretprobe-nop (16 cpus): 5.065 ± 0.019M/s ( 0.317M/s/cpu)
uretprobe-nop (32 cpus): 3.622 ± 0.003M/s ( 0.113M/s/cpu)
uretprobe-nop (64 cpus): 3.723 ± 0.002M/s ( 0.058M/s/cpu)
Peak througput increased from 3.7 mln/s (uprobe triggerings) up to about
8 mln/s. For uretprobes it's a bit more modest with bump from 2.4 mln/s
to 5mln/s.
Suggested-by: "Peter Zijlstra (Intel)" <peterz@infradead.org>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Link: https://lore.kernel.org/r/20240903174603.3554182-8-andrii@kernel.org
With uprobe_unregister() having grown a synchronize_srcu(), it becomes
fairly slow to call. Esp. since both users of this API call it in a
loop.
Peel off the sync_srcu() and do it once, after the loop.
We also need to add uprobe_unregister_sync() into uprobe_register()'s
error handling path, as we need to be careful about returning to the
caller before we have a guarantee that partially attached consumer won't
be called anymore. This is an unlikely slow path and this should be
totally fine to be slow in the case of a failed attach.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: "Peter Zijlstra (Intel)" <peterz@infradead.org>
Co-developed-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Link: https://lore.kernel.org/r/20240903174603.3554182-6-andrii@kernel.org
uprobe->register_rwsem is one of a few big bottlenecks to scalability of
uprobes, so we need to get rid of it to improve uprobe performance and
multi-CPU scalability.
First, we turn uprobe's consumer list to a typical doubly-linked list
and utilize existing RCU-aware helpers for traversing such lists, as
well as adding and removing elements from it.
For entry uprobes we already have SRCU protection active since before
uprobe lookup. For uretprobe we keep refcount, guaranteeing that uprobe
won't go away from under us, but we add SRCU protection around consumer
list traversal.
Lastly, to keep handler_chain()'s UPROBE_HANDLER_REMOVE handling simple,
we remember whether any removal was requested during handler calls, but
then we double-check the decision under a proper register_rwsem using
consumers' filter callbacks. Handler removal is very rare, so this extra
lock won't hurt performance, overall, but we also avoid the need for any
extra protection (e.g., seqcount locks).
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Link: https://lore.kernel.org/r/20240903174603.3554182-5-andrii@kernel.org
To avoid unnecessarily taking a (brief) refcount on uprobe during
breakpoint handling in handle_swbp for entry uprobes, make find_uprobe()
not take refcount, but protect the lifetime of a uprobe instance with
RCU. This improves scalability, as refcount gets quite expensive due to
cache line bouncing between multiple CPUs.
Specifically, we utilize our own uprobe-specific SRCU instance for this
RCU protection. put_uprobe() will delay actual kfree() using call_srcu().
For now, uretprobe and single-stepping handling will still acquire
refcount as necessary. We'll address these issues in follow up patches
by making them use SRCU with timeout.
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Link: https://lore.kernel.org/r/20240903174603.3554182-3-andrii@kernel.org
Revamp how struct uprobe is refcounted, and thus how its lifetime is
managed.
Right now, there are a few possible "owners" of uprobe refcount:
- uprobes_tree RB tree assumes one refcount when uprobe is registered
and added to the lookup tree;
- while uprobe is triggered and kernel is handling it in the breakpoint
handler code, temporary refcount bump is done to keep uprobe from
being freed;
- if we have uretprobe requested on a given struct uprobe instance, we
take another refcount to keep uprobe alive until user space code
returns from the function and triggers return handler.
The uprobe_tree's extra refcount of 1 is confusing and problematic. No
matter how many actual consumers are attached, they all share the same
refcount, and we have an extra logic to drop the "last" (which might not
really be last) refcount once uprobe's consumer list becomes empty.
This is unconventional and has to be kept in mind as a special case all
the time. Further, because of this design we have the situations where
find_uprobe() will find uprobe, bump refcount, return it to the caller,
but that uprobe will still need uprobe_is_active() check, after which
the caller is required to drop refcount and try again. This is just too
many details leaking to the higher level logic.
This patch changes refcounting scheme in such a way as to not have
uprobes_tree keeping extra refcount for struct uprobe. Instead, each
uprobe_consumer is assuming its own refcount, which will be dropped
when consumer is unregistered. Other than that, all the active users of
uprobe (entry and return uprobe handling code) keeps exactly the same
refcounting approach.
With the above setup, once uprobe's refcount drops to zero, we need to
make sure that uprobe's "destructor" removes uprobe from uprobes_tree,
of course. This, though, races with uprobe entry handling code in
handle_swbp(), which, through find_active_uprobe()->find_uprobe() lookup,
can race with uprobe being destroyed after refcount drops to zero (e.g.,
due to uprobe_consumer unregistering). So we add try_get_uprobe(), which
will attempt to bump refcount, unless it already is zero. Caller needs
to guarantee that uprobe instance won't be freed in parallel, which is
the case while we keep uprobes_treelock (for read or write, doesn't
matter).
Note also, we now don't leak the race between registration and
unregistration, so we remove the retry logic completely. If
find_uprobe() returns valid uprobe, it's guaranteed to remain in
uprobes_tree with properly incremented refcount. The race is handled
inside __insert_uprobe() and put_uprobe() working together:
__insert_uprobe() will remove uprobe from RB-tree, if it can't bump
refcount and will retry to insert the new uprobe instance. put_uprobe()
won't attempt to remove uprobe from RB-tree, if it's already not there.
All that is protected by uprobes_treelock, which keeps things simple.
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Link: https://lore.kernel.org/r/20240903174603.3554182-2-andrii@kernel.org
In perf_adjust_period, we will first calculate period, and then use
this period to calculate delta. However, when delta is less than 0,
there will be a deviation compared to when delta is greater than or
equal to 0. For example, when delta is in the range of [-14,-1], the
range of delta = delta + 7 is between [-7,6], so the final value of
delta/8 is 0. Therefore, the impact of -1 and -2 will be ignored.
This is unacceptable when the target period is very short, because
we will lose a lot of samples.
Here are some tests and analyzes:
before:
# perf record -e cs -F 1000 ./a.out
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.022 MB perf.data (518 samples) ]
# perf script
...
a.out 396 257.956048: 23 cs: ffffffff81f4eeec schedul>
a.out 396 257.957891: 23 cs: ffffffff81f4eeec schedul>
a.out 396 257.959730: 23 cs: ffffffff81f4eeec schedul>
a.out 396 257.961545: 23 cs: ffffffff81f4eeec schedul>
a.out 396 257.963355: 23 cs: ffffffff81f4eeec schedul>
a.out 396 257.965163: 23 cs: ffffffff81f4eeec schedul>
a.out 396 257.966973: 23 cs: ffffffff81f4eeec schedul>
a.out 396 257.968785: 23 cs: ffffffff81f4eeec schedul>
a.out 396 257.970593: 23 cs: ffffffff81f4eeec schedul>
...
after:
# perf record -e cs -F 1000 ./a.out
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.058 MB perf.data (1466 samples) ]
# perf script
...
a.out 395 59.338813: 11 cs: ffffffff81f4eeec schedul>
a.out 395 59.339707: 12 cs: ffffffff81f4eeec schedul>
a.out 395 59.340682: 13 cs: ffffffff81f4eeec schedul>
a.out 395 59.341751: 13 cs: ffffffff81f4eeec schedul>
a.out 395 59.342799: 12 cs: ffffffff81f4eeec schedul>
a.out 395 59.343765: 11 cs: ffffffff81f4eeec schedul>
a.out 395 59.344651: 11 cs: ffffffff81f4eeec schedul>
a.out 395 59.345539: 12 cs: ffffffff81f4eeec schedul>
a.out 395 59.346502: 13 cs: ffffffff81f4eeec schedul>
...
test.c
int main() {
for (int i = 0; i < 20000; i++)
usleep(10);
return 0;
}
# time ./a.out
real 0m1.583s
user 0m0.040s
sys 0m0.298s
The above results were tested on x86-64 qemu with KVM enabled using
test.c as test program. Ideally, we should have around 1500 samples,
but the previous algorithm had only about 500, whereas the modified
algorithm now has about 1400. Further more, the new version shows 1
sample per 0.001s, while the previous one is 1 sample per 0.002s.This
indicates that the new algorithm is more sensitive to small negative
values compared to old algorithm.
Fixes: bd2b5b1284 ("perf_counter: More aggressive frequency adjustment")
Signed-off-by: Luo Gengkun <luogengkun@huaweicloud.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Adrian Hunter <adrian.hunter@intel.com>
Reviewed-by: Kan Liang <kan.liang@linux.intel.com>
Cc: stable@vger.kernel.org
Link: https://lkml.kernel.org/r/20240831074316.2106159-2-luogengkun@huaweicloud.com
In __tracing_open(), when max latency tracers took place on the cpu,
the time start of its buffer would be updated, then event entries with
timestamps being earlier than start of the buffer would be skipped
(see tracing_iter_reset()).
Softlockup will occur if the kernel is non-preemptible and too many
entries were skipped in the loop that reset every cpu buffer, so add
cond_resched() to avoid it.
Cc: stable@vger.kernel.org
Fixes: 2f26ebd549 ("tracing: use timestamp to determine start of latency traces")
Link: https://lore.kernel.org/20240827124654.3817443-1-zhengyejian@huaweicloud.com
Suggested-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Zheng Yejian <zhengyejian@huaweicloud.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Pull bpf/master to receive baebe9aaba ("bpf: allow passing struct
bpf_iter_<type> as kfunc arguments") and related changes in preparation for
the DSQ iterator patchset.
Signed-off-by: Tejun Heo <tj@kernel.org>
The newly created cpuset-v1.c file uses cpus_read_lock/unlock() functions
which are defined in cpu.h but not included in cpuset-internal.h yet
leading to compilation error under certain kernel configurations. Fix it
by moving the cpu.h include from cpuset.c to cpuset-internal.h. While
at it, sort the include files in alphabetic order.
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202408311612.mQTuO946-lkp@intel.com/
Fixes: 047b830974 ("cgroup/cpuset: move relax_domain_level to cpuset-v1.c")
Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
Add sched_ext_ops operations to init/exit cgroups, and track task migrations
and config changes. A BPF scheduler may not implement or implement only
subset of cgroup features. The implemented features can be indicated using
%SCX_OPS_HAS_CGOUP_* flags. If cgroup configuration makes use of features
that are not implemented, a warning is triggered.
While a BPF scheduler is being enabled and disabled, relevant cgroup
operations are locked out using scx_cgroup_rwsem. This avoids situations
like task prep taking place while the task is being moved across cgroups,
making things easier for BPF schedulers.
v7: - cgroup interface file visibility toggling is dropped in favor just
warning messages. Dynamically changing interface visiblity caused more
confusion than helping.
v6: - Updated to reflect the removal of SCX_KF_SLEEPABLE.
- Updated to use CONFIG_GROUP_SCHED_WEIGHT and fixes for
!CONFIG_FAIR_GROUP_SCHED && CONFIG_EXT_GROUP_SCHED.
v5: - Flipped the locking order between scx_cgroup_rwsem and
cpus_read_lock() to avoid locking order conflict w/ cpuset. Better
documentation around locking.
- sched_move_task() takes an early exit if the source and destination
are identical. This triggered the warning in scx_cgroup_can_attach()
as it left p->scx.cgrp_moving_from uncleared. Updated the cgroup
migration path so that ops.cgroup_prep_move() is skipped for identity
migrations so that its invocations always match ops.cgroup_move()
one-to-one.
v4: - Example schedulers moved into their own patches.
- Fix build failure when !CONFIG_CGROUP_SCHED, reported by Andrea Righi.
v3: - Make scx_example_pair switch all tasks by default.
- Convert to BPF inline iterators.
- scx_bpf_task_cgroup() is added to determine the current cgroup from
CPU controller's POV. This allows BPF schedulers to accurately track
CPU cgroup membership.
- scx_example_flatcg added. This demonstrates flattened hierarchy
implementation of CPU cgroup control and shows significant performance
improvement when cgroups which are nested multiple levels are under
competition.
v2: - Build fixes for different CONFIG combinations.
Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: David Vernet <dvernet@meta.com>
Acked-by: Josh Don <joshdon@google.com>
Acked-by: Hao Luo <haoluo@google.com>
Acked-by: Barret Rhoden <brho@google.com>
Reported-by: kernel test robot <lkp@intel.com>
Cc: Andrea Righi <andrea.righi@canonical.com>
sched_ext will soon add cgroup cpu.weigh support. The cgroup interface code
is currently gated behind CONFIG_FAIR_GROUP_SCHED. As the fair class and/or
SCX may implement the feature, put the interface code behind the new
CONFIG_CGROUP_SCHED_WEIGHT which is selected by CONFIG_FAIR_GROUP_SCHED.
This allows either sched class to enable the itnerface code without ading
more complex CONFIG tests.
When !CONFIG_FAIR_GROUP_SCHED, a dummy version of sched_group_set_shares()
is added to support later CONFIG_CGROUP_SCHED_WEIGHT &&
!CONFIG_FAIR_GROUP_SCHED builds.
No functional changes.
Signed-off-by: Tejun Heo <tj@kernel.org>
Move tg_weight() upward and make cpu_shares_read_u64() use it too. This
makes the weight retrieval shared between cgroup v1 and v2 paths and will be
used to implement cgroup support for sched_ext.
No functional changes.
Signed-off-by: Tejun Heo <tj@kernel.org>
A new BPF extensible sched_class will use css_tg() in the init and exit
paths to visit all task_groups by walking cgroups.
v4: __setscheduler_prio() is already exposed. Dropped from this patch.
v3: Dropped SCHED_CHANGE_BLOCK() as upstream is adding more generic cleanup
mechanism.
v2: Expose SCHED_CHANGE_BLOCK() too and update the description.
Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: David Vernet <dvernet@meta.com>
Acked-by: Josh Don <joshdon@google.com>
Acked-by: Hao Luo <haoluo@google.com>
Acked-by: Barret Rhoden <brho@google.com>
During scx_ops_enable(), SCX needs to invoke the sleepable ops.init_task()
on every task. To do this, it does get_task_struct() on each iterated task,
drop the lock and then call ops.init_task().
However, a TASK_DEAD task may already have lost all its usage count and be
waiting for RCU grace period to be freed. If get_task_struct() is called on
such task, use-after-free can happen. To avoid such situations,
scx_ops_enable() skips initialization of TASK_DEAD tasks, which seems safe
as they are never going to be scheduled again.
Unfortunately, a racing sched_setscheduler(2) can grab the task before the
task is unhashed and then continue to e.g. move the task from RT to SCX
after TASK_DEAD is set and ops_enable skipped the task. As the task hasn't
gone through scx_ops_init_task(), scx_ops_enable_task() called from
switching_to_scx() triggers the following warning:
sched_ext: Invalid task state transition 0 -> 3 for stress-ng-race-[2872]
WARNING: CPU: 6 PID: 2367 at kernel/sched/ext.c:3327 scx_ops_enable_task+0x18f/0x1f0
...
RIP: 0010:scx_ops_enable_task+0x18f/0x1f0
...
switching_to_scx+0x13/0xa0
__sched_setscheduler+0x84e/0xa50
do_sched_setscheduler+0x104/0x1c0
__x64_sys_sched_setscheduler+0x18/0x30
do_syscall_64+0x7b/0x140
entry_SYSCALL_64_after_hwframe+0x76/0x7e
As in the ops_disable path, it just doesn't seem like a good idea to leave
any task in an inconsistent state, even when the task is dead. The root
cause is ops_enable not being able to tell reliably whether a task is truly
dead (no one else is looking at it and it's about to be freed) and was
testing TASK_DEAD instead. Fix it by testing the task's usage count
directly.
- ops_init no longer ignores TASK_DEAD tasks. As now all users iterate all
tasks, @include_dead is removed from scx_task_iter_next_locked() along
with dead task filtering.
- tryget_task_struct() is added. Tasks are skipped iff tryget_task_struct()
fails.
Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: David Vernet <void@manifault.com>
Cc: Peter Zijlstra <peterz@infradead.org>
scx_ops_disable_workfn() only switches !TASK_DEAD tasks out of SCX while
calling scx_ops_exit_task() on all tasks including dead ones. This can leave
a dead task on SCX but with SCX_TASK_NONE state, which is inconsistent.
If another task was in the process of changing the TASK_DEAD task's
scheduling class and grabs the rq lock after scx_ops_disable_workfn() is
done with the task, the task ends up calling scx_ops_disable_task() on the
dead task which is in an inconsistent state triggering a warning:
WARNING: CPU: 6 PID: 3316 at kernel/sched/ext.c:3411 scx_ops_disable_task+0x12c/0x160
...
RIP: 0010:scx_ops_disable_task+0x12c/0x160
...
Call Trace:
<TASK>
check_class_changed+0x2c/0x70
__sched_setscheduler+0x8a0/0xa50
do_sched_setscheduler+0x104/0x1c0
__x64_sys_sched_setscheduler+0x18/0x30
do_syscall_64+0x7b/0x140
entry_SYSCALL_64_after_hwframe+0x76/0x7e
RIP: 0033:0x7f140d70ea5b
There is no reason to leave dead tasks on SCX when unloading the BPF
scheduler. Fix by making scx_ops_disable_workfn() eject all tasks including
the dead ones from SCX.
Signed-off-by: Tejun Heo <tj@kernel.org>
This patch removes the insn_buf array stack usage from the
inline_bpf_loop(). Instead, the env->insn_buf is used. The
usage in inline_bpf_loop() needs more than 16 insn, so the
INSN_BUF_SIZE needs to be increased from 16 to 32.
The compiler stack size warning on the verifier is gone
after this change.
Cc: Eduard Zingerman <eddyz87@gmail.com>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://lore.kernel.org/r/20240904180847.56947-2-martin.lau@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
If the length of the name string is 1 and the value of name[0] is NULL
byte, an OOB vulnerability occurs in btf_name_valid_section() and the
return value is true, so the invalid name passes the check.
To solve this, you need to check if the first position is NULL byte and
if the first character is printable.
Suggested-by: Eduard Zingerman <eddyz87@gmail.com>
Fixes: bd70a8fb7c ("bpf: Allow all printable characters in BTF DATASEC names")
Signed-off-by: Jeongjun Park <aha310510@gmail.com>
Link: https://lore.kernel.org/r/20240831054702.364455-1-aha310510@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Ole reported that event->mmap_mutex is strictly insufficient to
serialize the AUX buffer, add a per RB mutex to fully serialize it.
Note that in the lock order comment the perf_event::mmap_mutex order
was already wrong, that is, it nesting under mmap_lock is not new with
this patch.
Fixes: 45bfb2e504 ("perf: Add AUX area to ring buffer for raw data streams")
Reported-by: Ole <ole@binarygecko.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Pull misc fixes from Andrew Morton:
"17 hotfixes, 15 of which are cc:stable.
Mostly MM, no identifiable theme. And a few nilfs2 fixups"
* tag 'mm-hotfixes-stable-2024-09-03-20-19' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm:
alloc_tag: fix allocation tag reporting when CONFIG_MODULES=n
mm: vmalloc: optimize vmap_lazy_nr arithmetic when purging each vmap_area
mailmap: update entry for Jan Kuliga
codetag: debug: mark codetags for poisoned page as empty
mm/memcontrol: respect zswap.writeback setting from parent cg too
scripts: fix gfp-translate after ___GFP_*_BITS conversion to an enum
Revert "mm: skip CMA pages when they are not available"
maple_tree: remove rcu_read_lock() from mt_validate()
kexec_file: fix elfcorehdr digest exclusion when CONFIG_CRASH_HOTPLUG=y
mm/slub: add check for s->flags in the alloc_tagging_slab_free_hook
nilfs2: fix state management in error path of log writing function
nilfs2: fix missing cleanup on rollforward recovery error
nilfs2: protect references to superblock parameters exposed in sysfs
userfaultfd: don't BUG_ON() if khugepaged yanks our page table
userfaultfd: fix checks for huge PMDs
mm: vmalloc: ensure vmap_block is initialised before adding to queue
selftests: mm: fix build errors on armhf
Legacy console printing from printk() caller context may invoke
the console driver from atomic context. This leads to a lockdep
splat because the console driver will acquire a sleeping lock
and the caller may already hold a spinning lock. This is noticed
by lockdep on !PREEMPT_RT configurations because it will lead to
a problem on PREEMPT_RT.
However, on PREEMPT_RT the printing path from atomic context is
always avoided and the console driver is always invoked from a
dedicated thread. Thus the lockdep splat on !PREEMPT_RT is a
false positive.
For !PREEMPT_RT override the lock-context before invoking the
console driver to avoid the false positive.
Do not override the lock-context for PREEMPT_RT in order to
allow lockdep to catch any real locking context issues related
to the write callback usage.
Signed-off-by: John Ogness <john.ogness@linutronix.de>
Reviewed-by: Petr Mladek <pmladek@suse.com>
Link: https://lore.kernel.org/r/20240904120536.115780-18-john.ogness@linutronix.de
Signed-off-by: Petr Mladek <pmladek@suse.com>
The write() callback of legacy consoles usually makes use of
spinlocks. This is not permitted with PREEMPT_RT in atomic
contexts.
For PREEMPT_RT, create a new kthread to handle printing of all
the legacy consoles (and nbcon consoles if boot consoles are
registered). This allows legacy consoles to work on PREEMPT_RT
without requiring modification. (However they will not have
the reliability properties guaranteed by nbcon atomic
consoles.)
Use the existing printk_kthreads_check_locked() to start/stop
the legacy kthread as needed.
Introduce the macro force_legacy_kthread() to query if the
forced threading of legacy consoles is in effect. Although
currently only enabled for PREEMPT_RT, this acts as a simple
mechanism for the future to allow other preemption models to
easily take advantage of the non-interference property provided
by the legacy kthread.
When force_legacy_kthread() is true, the legacy kthread
fulfills the role of the console_flush_type @legacy_offload by
waking the legacy kthread instead of printing via the
console_lock in the irq_work. If the legacy kthread is not
yet available, no legacy printing takes place (unless in
panic).
If for some reason the legacy kthread fails to create, any
legacy consoles are unregistered. With force_legacy_kthread(),
the legacy kthread is a critical component for legacy consoles.
These changes only affect CONFIG_PREEMPT_RT.
Signed-off-by: John Ogness <john.ogness@linutronix.de>
Reviewed-by: Petr Mladek <pmladek@suse.com>
Link: https://lore.kernel.org/r/20240904120536.115780-16-john.ogness@linutronix.de
Signed-off-by: Petr Mladek <pmladek@suse.com>
An emergency or panic context can takeover console ownership
while the current owner was printing a printk message. The
atomic printer will re-print the message that the previous
owner was printing. However, this can look confusing to the
user and may even seem as though a message was lost.
[3430014.1
[3430014.181123] usb 1-2: Product: USB Audio
Add a new field @nbcon_prev_seq to struct console to track
the sequence number to print that was assigned to the previous
console owner. If this matches the sequence number to print
that the current owner is assigned, then a takeover must have
occurred. In this case, print an additional message to inform
the user that the previous message is being printed again.
[3430014.1
** replaying previous printk message **
[3430014.181123] usb 1-2: Product: USB Audio
Signed-off-by: John Ogness <john.ogness@linutronix.de>
Reviewed-by: Petr Mladek <pmladek@suse.com>
Link: https://lore.kernel.org/r/20240904120536.115780-12-john.ogness@linutronix.de
Signed-off-by: Petr Mladek <pmladek@suse.com>
