The reader code in rb_get_reader_page() swaps a new reader page into the
ring buffer by doing cmpxchg on old->list.prev->next to point it to the
new page. Following that, if the operation is successful,
old->list.next->prev gets updated too. This means the underlying
doubly-linked list is temporarily inconsistent, page->prev->next or
page->next->prev might not be equal back to page for some page in the
ring buffer.
The resize operation in ring_buffer_resize() can be invoked in parallel.
It calls rb_check_pages() which can detect the described inconsistency
and stop further tracing:
[ 190.271762] ------------[ cut here ]------------
[ 190.271771] WARNING: CPU: 1 PID: 6186 at kernel/trace/ring_buffer.c:1467 rb_check_pages.isra.0+0x6a/0xa0
[ 190.271789] Modules linked in: [...]
[ 190.271991] Unloaded tainted modules: intel_uncore_frequency(E):1 skx_edac(E):1
[ 190.272002] CPU: 1 PID: 6186 Comm: cmd.sh Kdump: loaded Tainted: G E 6.9.0-rc6-default #5 158d3e1e6d0b091c34c3b96bfd99a1c58306d79f
[ 190.272011] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.16.0-0-gd239552c-rebuilt.opensuse.org 04/01/2014
[ 190.272015] RIP: 0010:rb_check_pages.isra.0+0x6a/0xa0
[ 190.272023] Code: [...]
[ 190.272028] RSP: 0018:ffff9c37463abb70 EFLAGS: 00010206
[ 190.272034] RAX: ffff8eba04b6cb80 RBX: 0000000000000007 RCX: ffff8eba01f13d80
[ 190.272038] RDX: ffff8eba01f130c0 RSI: ffff8eba04b6cd00 RDI: ffff8eba0004c700
[ 190.272042] RBP: ffff8eba0004c700 R08: 0000000000010002 R09: 0000000000000000
[ 190.272045] R10: 00000000ffff7f52 R11: ffff8eba7f600000 R12: ffff8eba0004c720
[ 190.272049] R13: ffff8eba00223a00 R14: 0000000000000008 R15: ffff8eba067a8000
[ 190.272053] FS: 00007f1bd64752c0(0000) GS:ffff8eba7f680000(0000) knlGS:0000000000000000
[ 190.272057] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 190.272061] CR2: 00007f1bd6662590 CR3: 000000010291e001 CR4: 0000000000370ef0
[ 190.272070] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[ 190.272073] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[ 190.272077] Call Trace:
[ 190.272098] <TASK>
[ 190.272189] ring_buffer_resize+0x2ab/0x460
[ 190.272199] __tracing_resize_ring_buffer.part.0+0x23/0xa0
[ 190.272206] tracing_resize_ring_buffer+0x65/0x90
[ 190.272216] tracing_entries_write+0x74/0xc0
[ 190.272225] vfs_write+0xf5/0x420
[ 190.272248] ksys_write+0x67/0xe0
[ 190.272256] do_syscall_64+0x82/0x170
[ 190.272363] entry_SYSCALL_64_after_hwframe+0x76/0x7e
[ 190.272373] RIP: 0033:0x7f1bd657d263
[ 190.272381] Code: [...]
[ 190.272385] RSP: 002b:00007ffe72b643f8 EFLAGS: 00000246 ORIG_RAX: 0000000000000001
[ 190.272391] RAX: ffffffffffffffda RBX: 0000000000000002 RCX: 00007f1bd657d263
[ 190.272395] RDX: 0000000000000002 RSI: 0000555a6eb538e0 RDI: 0000000000000001
[ 190.272398] RBP: 0000555a6eb538e0 R08: 000000000000000a R09: 0000000000000000
[ 190.272401] R10: 0000555a6eb55190 R11: 0000000000000246 R12: 00007f1bd6662500
[ 190.272404] R13: 0000000000000002 R14: 00007f1bd6667c00 R15: 0000000000000002
[ 190.272412] </TASK>
[ 190.272414] ---[ end trace 0000000000000000 ]---
Note that ring_buffer_resize() calls rb_check_pages() only if the parent
trace_buffer has recording disabled. Recent commit d78ab79270
("tracing: Stop current tracer when resizing buffer") causes that it is
now always the case which makes it more likely to experience this issue.
The window to hit this race is nonetheless very small. To help
reproducing it, one can add a delay loop in rb_get_reader_page():
ret = rb_head_page_replace(reader, cpu_buffer->reader_page);
if (!ret)
goto spin;
for (unsigned i = 0; i < 1U << 26; i++) /* inserted delay loop */
__asm__ __volatile__ ("" : : : "memory");
rb_list_head(reader->list.next)->prev = &cpu_buffer->reader_page->list;
.. and then run the following commands on the target system:
echo 1 > /sys/kernel/tracing/events/sched/sched_switch/enable
while true; do
echo 16 > /sys/kernel/tracing/buffer_size_kb; sleep 0.1
echo 8 > /sys/kernel/tracing/buffer_size_kb; sleep 0.1
done &
while true; do
for i in /sys/kernel/tracing/per_cpu/*; do
timeout 0.1 cat $i/trace_pipe; sleep 0.2
done
done
To fix the problem, make sure ring_buffer_resize() doesn't invoke
rb_check_pages() concurrently with a reader operating on the same
ring_buffer_per_cpu by taking its cpu_buffer->reader_lock.
Link: https://lore.kernel.org/linux-trace-kernel/20240517134008.24529-3-petr.pavlu@suse.com
Cc: stable@vger.kernel.org
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Fixes: 659f451ff2 ("ring-buffer: Add integrity check at end of iter read")
Signed-off-by: Petr Pavlu <petr.pavlu@suse.com>
[ Fixed whitespace ]
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Adjust the following code documentation:
* Kernel-doc comments for ring_buffer_read_prepare() and
ring_buffer_read_finish() mention that recording to the ring buffer is
disabled when the read is active. Remove mention of this restriction
because it was already lifted in commit 1039221cc2 ("ring-buffer: Do
not disable recording when there is an iterator").
* Function ring_buffer_read_finish() performs a self-check of the
ring-buffer by locking cpu_buffer->reader_lock and then calling
rb_check_pages(). The preceding comment explains that the lock is
needed because rb_check_pages() clears the HEAD flag required by
readers which might be running in parallel. Remove this explanation
because commit 8843e06f67 ("ring-buffer: Handle race between
rb_move_tail and rb_check_pages") simplified the function so it no
longer resets the mentioned flag. Nonetheless, the lock is still
needed because a reader swapping a page into the ring buffer can make
the underlying doubly-linked list temporarily inconsistent.
This is a non-functional change.
Link: https://lore.kernel.org/linux-trace-kernel/20240517134008.24529-2-petr.pavlu@suse.com
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: Petr Pavlu <petr.pavlu@suse.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
While testing libtracefs on the mmapped ring buffer, the test that checks
if missed events are accounted for failed when using the mapped buffer.
This is because the mapped page does not update the missed events that
were dropped because the writer filled up the ring buffer before the
reader could catch it.
Add the missed events to the reader page/sub-buffer when the IOCTL is done
and a new reader page is acquired.
Note that all accesses to the reader_page via rb_page_commit() had to be
switched to rb_page_size(), and rb_page_size() which was just a copy of
rb_page_commit() but now it masks out the RB_MISSED bits. This is needed
as the mapped reader page is still active in the ring buffer code and
where it reads the commit field of the bpage for the size, it now must
mask it otherwise the missed bits that are now set will corrupt the size
returned.
Link: https://lore.kernel.org/linux-trace-kernel/20240312175405.12fb6726@gandalf.local.home
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Vincent Donnefort <vdonnefort@google.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
In preparation for allowing the user-space to map a ring-buffer, add
a set of mapping functions:
ring_buffer_{map,unmap}()
And controls on the ring-buffer:
ring_buffer_map_get_reader() /* swap reader and head */
Mapping the ring-buffer also involves:
A unique ID for each subbuf of the ring-buffer, currently they are
only identified through their in-kernel VA.
A meta-page, where are stored ring-buffer statistics and a
description for the current reader
The linear mapping exposes the meta-page, and each subbuf of the
ring-buffer, ordered following their unique ID, assigned during the
first mapping.
Once mapped, no subbuf can get in or out of the ring-buffer: the buffer
size will remain unmodified and the splice enabling functions will in
reality simply memcpy the data instead of swapping subbufs.
Link: https://lore.kernel.org/linux-trace-kernel/20240510140435.3550353-3-vdonnefort@google.com
CC: <linux-mm@kvack.org>
Signed-off-by: Vincent Donnefort <vdonnefort@google.com>
Acked-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
In preparation for the ring-buffer memory mapping, allocate compound
pages for the ring-buffer sub-buffers to enable us to map them to
user-space with vm_insert_pages().
Link: https://lore.kernel.org/linux-trace-kernel/20240510140435.3550353-2-vdonnefort@google.com
Acked-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Vincent Donnefort <vdonnefort@google.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
The "buffer_percent" logic that is used by the ring buffer splice code to
only wake up the tasks when there's no data after the buffer is filled to
the percentage of the "buffer_percent" file is dependent on three
variables that determine the amount of data that is in the ring buffer:
1) pages_read - incremented whenever a new sub-buffer is consumed
2) pages_lost - incremented every time a writer overwrites a sub-buffer
3) pages_touched - incremented when a write goes to a new sub-buffer
The percentage is the calculation of:
(pages_touched - (pages_lost + pages_read)) / nr_pages
Basically, the amount of data is the total number of sub-bufs that have been
touched, minus the number of sub-bufs lost and sub-bufs consumed. This is
divided by the total count to give the buffer percentage. When the
percentage is greater than the value in the "buffer_percent" file, it
wakes up splice readers waiting for that amount.
It was observed that over time, the amount read from the splice was
constantly decreasing the longer the trace was running. That is, if one
asked for 60%, it would read over 60% when it first starts tracing, but
then it would be woken up at under 60% and would slowly decrease the
amount of data read after being woken up, where the amount becomes much
less than the buffer percent.
This was due to an accounting of the pages_touched incrementation. This
value is incremented whenever a writer transfers to a new sub-buffer. But
the place where it was incremented was incorrect. If a writer overflowed
the current sub-buffer it would go to the next one. If it gets preempted
by an interrupt at that time, and the interrupt performs a trace, it too
will end up going to the next sub-buffer. But only one should increment
the counter. Unfortunately, that was not the case.
Change the cmpxchg() that does the real switch of the tail-page into a
try_cmpxchg(), and on success, perform the increment of pages_touched. This
will only increment the counter once for when the writer moves to a new
sub-buffer, and not when there's a race and is incremented for when a
writer and its preempting writer both move to the same new sub-buffer.
Link: https://lore.kernel.org/linux-trace-kernel/20240409151309.0d0e5056@gandalf.local.home
Cc: stable@vger.kernel.org
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Fixes: 2c2b0a78b3 ("ring-buffer: Add percentage of ring buffer full to wake up reader")
Acked-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
The default behavior of ring_buffer_wait() when passed a NULL "cond"
parameter is to exit the function the first time it is woken up. The
current implementation uses a counter that starts at zero and when it is
greater than one it exits the wait_event_interruptible().
But this relies on the internal working of wait_event_interruptible() as
that code basically has:
if (cond)
return;
prepare_to_wait();
if (!cond)
schedule();
finish_wait();
That is, cond is called twice before it sleeps. The default cond of
ring_buffer_wait() needs to account for that and wait for its counter to
increment twice before exiting.
Instead, use the seq/atomic_inc logic that is used by the tracing code
that calls this function. Add an atomic_t seq to rb_irq_work and when cond
is NULL, have the default callback take a descriptor as its data that
holds the rbwork and the value of the seq when it started.
The wakeups will now increment the rbwork->seq and the cond callback will
simply check if that number is different, and no longer have to rely on
the implementation of wait_event_interruptible().
Link: https://lore.kernel.org/linux-trace-kernel/20240315063115.6cb5d205@gandalf.local.home
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Fixes: 7af9ded0c2 ("ring-buffer: Use wait_event_interruptible() in ring_buffer_wait()")
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
In function ring_buffer_iter_empty(), cpu_buffer->commit_page is read
while other threads may change it. It may cause the time_stamp that read
in the next line come from a different page. Use READ_ONCE() to avoid
having to reason about compiler optimizations now and in future.
Link: https://lore.kernel.org/linux-trace-kernel/tencent_DFF7D3561A0686B5E8FC079150A02505180A@qq.com
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: linke li <lilinke99@qq.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
In preparation for the ring-buffer memory mapping where each subbuf will
be accessible to user-space, zero all the page allocations.
Link: https://lore.kernel.org/linux-trace-kernel/20240220202310.2489614-2-vdonnefort@google.com
Signed-off-by: Vincent Donnefort <vdonnefort@google.com>
Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
- Do not update shortest_full in rb_watermark_hit() if the watermark
is hit. The shortest_full field was being updated regardless if
the task was going to wait or not. If the watermark is hit, then
the task is not going to wait, so do not update the shortest_full
field (used by the waker).
- Update shortest_full field before setting the full_waiters_pending flag
In the poll logic, the full_waiters_pending flag was being set
before the shortest_full field was set. If the full_waiters_pending
flag is set, writers will check the shortest_full field which has
the least percentage of data that the ring buffer needs to be
filled before waking up. The writer will check shortest_full if
full_waiters_pending is set, and if the ring buffer percentage filled
is greater than shortest full, then it will call the irq_work to
wake up the waiters.
The problem was that the poll logic set the full_waiters_pending flag
before updating shortest_full, which when zero will always trigger
the writer to call the irq_work to wake up the waiters. The irq_work
will reset the shortest_full field back to zero as the woken waiters
is suppose to reset it.
- There's some optimized logic in the rb_watermark_hit() that is used
in ring_buffer_wait(). Use that helper function in the poll logic
as well.
- Restructure ring_buffer_wait() to use wait_event_interruptible()
The logic to wake up pending readers when the file descriptor is
closed is racy. Restructure ring_buffer_wait() to allow callers
to pass in conditions besides the ring buffer having enough data
in it by using wait_event_interruptible().
- Update the tracing_wait_on_pipe() to call ring_buffer_wait() with
its own conditions to exit the wait loop.
-----BEGIN PGP SIGNATURE-----
iIoEABYIADIWIQRRSw7ePDh/lE+zeZMp5XQQmuv6qgUCZfH6MRQccm9zdGVkdEBn
b29kbWlzLm9yZwAKCRAp5XQQmuv6qtlwAP9ZoSIkvw2MVu7FclgAguaX2CaylGEw
sv0wZaCy1kgAPgD8CFhezZcHrt/RwJibpMxVnUs+DDqYnGdJsHYLihlbWgg=
=99FG
-----END PGP SIGNATURE-----
Merge tag 'trace-ring-buffer-v6.8-rc7-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace
Pull tracing updates from Steven Rostedt:
- Do not update shortest_full in rb_watermark_hit() if the watermark is
hit. The shortest_full field was being updated regardless if the task
was going to wait or not. If the watermark is hit, then the task is
not going to wait, so do not update the shortest_full field (used by
the waker).
- Update shortest_full field before setting the full_waiters_pending
flag
In the poll logic, the full_waiters_pending flag was being set before
the shortest_full field was set. If the full_waiters_pending flag is
set, writers will check the shortest_full field which has the least
percentage of data that the ring buffer needs to be filled before
waking up. The writer will check shortest_full if
full_waiters_pending is set, and if the ring buffer percentage filled
is greater than shortest full, then it will call the irq_work to wake
up the waiters.
The problem was that the poll logic set the full_waiters_pending flag
before updating shortest_full, which when zero will always trigger
the writer to call the irq_work to wake up the waiters. The irq_work
will reset the shortest_full field back to zero as the woken waiters
is suppose to reset it.
- There's some optimized logic in the rb_watermark_hit() that is used
in ring_buffer_wait(). Use that helper function in the poll logic as
well.
- Restructure ring_buffer_wait() to use wait_event_interruptible()
The logic to wake up pending readers when the file descriptor is
closed is racy. Restructure ring_buffer_wait() to allow callers to
pass in conditions besides the ring buffer having enough data in it
by using wait_event_interruptible().
- Update the tracing_wait_on_pipe() to call ring_buffer_wait() with its
own conditions to exit the wait loop.
* tag 'trace-ring-buffer-v6.8-rc7-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace:
tracing/ring-buffer: Fix wait_on_pipe() race
ring-buffer: Use wait_event_interruptible() in ring_buffer_wait()
ring-buffer: Reuse rb_watermark_hit() for the poll logic
ring-buffer: Fix full_waiters_pending in poll
ring-buffer: Do not set shortest_full when full target is hit
When the trace_pipe_raw file is closed, there should be no new readers on
the file descriptor. This is mostly handled with the waking and wait_index
fields of the iterator. But there's still a slight race.
CPU 0 CPU 1
----- -----
wait_index++;
index = wait_index;
ring_buffer_wake_waiters();
wait_on_pipe()
ring_buffer_wait();
The ring_buffer_wait() will miss the wakeup from CPU 1. The problem is
that the ring_buffer_wait() needs the logic of:
prepare_to_wait();
if (!condition)
schedule();
Where the missing condition check is the iter->wait_index update.
Have the ring_buffer_wait() take a conditional callback function and a
data parameter that can be used within the wait_event_interruptible() of
the ring_buffer_wait() function.
In wait_on_pipe(), pass a condition function that will check if the
wait_index has been updated, if it has, it will return true to break out
of the wait_event_interruptible() loop.
Create a new field "closed" in the trace_iterator and set it in the
.flush() callback before calling ring_buffer_wake_waiters().
This will keep any new readers from waiting on a closed file descriptor.
Have the wait_on_pipe() condition callback also check the closed field.
Change the wait_index field of the trace_iterator to atomic_t. There's no
reason it needs to be 'long' and making it atomic and using
atomic_read_acquire() and atomic_fetch_inc_release() will provide the
necessary memory barriers.
Add a "woken" flag to tracing_buffers_splice_read() to exit the loop after
one more try to fetch data. That is, if it waited for data and something
woke it up, it should try to collect any new data and then exit back to
user space.
Link: https://lore.kernel.org/linux-trace-kernel/CAHk-=wgsNgewHFxZAJiAQznwPMqEtQmi1waeS2O1v6L4c_Um5A@mail.gmail.com/
Link: https://lore.kernel.org/linux-trace-kernel/20240312121703.557950713@goodmis.org
Cc: stable@vger.kernel.org
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: linke li <lilinke99@qq.com>
Cc: Rabin Vincent <rabin@rab.in>
Fixes: f3ddb74ad0 ("tracing: Wake up ring buffer waiters on closing of the file")
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Convert ring_buffer_wait() over to wait_event_interruptible(). The default
condition is to execute the wait loop inside __wait_event() just once.
This does not change the ring_buffer_wait() prototype yet, but
restructures the code so that it can take a "cond" and "data" parameter
and will call wait_event_interruptible() with a helper function as the
condition.
The helper function (rb_wait_cond) takes the cond function and data
parameters. It will first check if the buffer hit the watermark defined by
the "full" parameter and then call the passed in condition parameter. If
either are true, it returns true.
If rb_wait_cond() does not return true, it will set the appropriate
"waiters_pending" flag and returns false.
Link: https://lore.kernel.org/linux-trace-kernel/CAHk-=wgsNgewHFxZAJiAQznwPMqEtQmi1waeS2O1v6L4c_Um5A@mail.gmail.com/
Link: https://lore.kernel.org/linux-trace-kernel/20240312121703.399598519@goodmis.org
Cc: stable@vger.kernel.org
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: linke li <lilinke99@qq.com>
Cc: Rabin Vincent <rabin@rab.in>
Fixes: f3ddb74ad0 ("tracing: Wake up ring buffer waiters on closing of the file")
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
The check for knowing if the poll should wait or not is basically the
exact same logic as rb_watermark_hit(). The only difference is that
rb_watermark_hit() also handles the !full case. But for the full case, the
logic is the same. Just call that instead of duplicating the code in
ring_buffer_poll_wait().
Link: https://lore.kernel.org/linux-trace-kernel/20240312131952.802267543@goodmis.org
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
If a reader of the ring buffer is doing a poll, and waiting for the ring
buffer to hit a specific watermark, there could be a case where it gets
into an infinite ping-pong loop.
The poll code has:
rbwork->full_waiters_pending = true;
if (!cpu_buffer->shortest_full ||
cpu_buffer->shortest_full > full)
cpu_buffer->shortest_full = full;
The writer will see full_waiters_pending and check if the ring buffer is
filled over the percentage of the shortest_full value. If it is, it calls
an irq_work to wake up all the waiters.
But the code could get into a circular loop:
CPU 0 CPU 1
----- -----
[ Poll ]
[ shortest_full = 0 ]
rbwork->full_waiters_pending = true;
if (rbwork->full_waiters_pending &&
[ buffer percent ] > shortest_full) {
rbwork->wakeup_full = true;
[ queue_irqwork ]
cpu_buffer->shortest_full = full;
[ IRQ work ]
if (rbwork->wakeup_full) {
cpu_buffer->shortest_full = 0;
wakeup poll waiters;
[woken]
if ([ buffer percent ] > full)
break;
rbwork->full_waiters_pending = true;
if (rbwork->full_waiters_pending &&
[ buffer percent ] > shortest_full) {
rbwork->wakeup_full = true;
[ queue_irqwork ]
cpu_buffer->shortest_full = full;
[ IRQ work ]
if (rbwork->wakeup_full) {
cpu_buffer->shortest_full = 0;
wakeup poll waiters;
[woken]
[ Wash, rinse, repeat! ]
In the poll, the shortest_full needs to be set before the
full_pending_waiters, as once that is set, the writer will compare the
current shortest_full (which is incorrect) to decide to call the irq_work,
which will reset the shortest_full (expecting the readers to update it).
Also move the setting of full_waiters_pending after the check if the ring
buffer has the required percentage filled. There's no reason to tell the
writer to wake up waiters if there are no waiters.
Link: https://lore.kernel.org/linux-trace-kernel/20240312131952.630922155@goodmis.org
Cc: stable@vger.kernel.org
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Fixes: 42fb0a1e84 ("tracing/ring-buffer: Have polling block on watermark")
Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
The rb_watermark_hit() checks if the amount of data in the ring buffer is
above the percentage level passed in by the "full" variable. If it is, it
returns true.
But it also sets the "shortest_full" field of the cpu_buffer that informs
writers that it needs to call the irq_work if the amount of data on the
ring buffer is above the requested amount.
The rb_watermark_hit() always sets the shortest_full even if the amount in
the ring buffer is what it wants. As it is not going to wait, because it
has what it wants, there's no reason to set shortest_full.
Link: https://lore.kernel.org/linux-trace-kernel/20240312115641.6aa8ba08@gandalf.local.home
Cc: stable@vger.kernel.org
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Fixes: 42fb0a1e84 ("tracing/ring-buffer: Have polling block on watermark")
Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
- The biggest change is the rework of the percpu code,
to support the 'Named Address Spaces' GCC feature,
by Uros Bizjak:
- This allows C code to access GS and FS segment relative
memory via variables declared with such attributes,
which allows the compiler to better optimize those accesses
than the previous inline assembly code.
- The series also includes a number of micro-optimizations
for various percpu access methods, plus a number of
cleanups of %gs accesses in assembly code.
- These changes have been exposed to linux-next testing for
the last ~5 months, with no known regressions in this area.
- Fix/clean up __switch_to()'s broken but accidentally
working handling of FPU switching - which also generates
better code.
- Propagate more RIP-relative addressing in assembly code,
to generate slightly better code.
- Rework the CPU mitigations Kconfig space to be less idiosyncratic,
to make it easier for distros to follow & maintain these options.
- Rework the x86 idle code to cure RCU violations and
to clean up the logic.
- Clean up the vDSO Makefile logic.
- Misc cleanups and fixes.
[ Please note that there's a higher number of merge commits in
this branch (three) than is usual in x86 topic trees. This happened
due to the long testing lifecycle of the percpu changes that
involved 3 merge windows, which generated a longer history
and various interactions with other core x86 changes that we
felt better about to carry in a single branch. ]
Signed-off-by: Ingo Molnar <mingo@kernel.org>
-----BEGIN PGP SIGNATURE-----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=3v4F
-----END PGP SIGNATURE-----
Merge tag 'x86-core-2024-03-11' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull core x86 updates from Ingo Molnar:
- The biggest change is the rework of the percpu code, to support the
'Named Address Spaces' GCC feature, by Uros Bizjak:
- This allows C code to access GS and FS segment relative memory
via variables declared with such attributes, which allows the
compiler to better optimize those accesses than the previous
inline assembly code.
- The series also includes a number of micro-optimizations for
various percpu access methods, plus a number of cleanups of %gs
accesses in assembly code.
- These changes have been exposed to linux-next testing for the
last ~5 months, with no known regressions in this area.
- Fix/clean up __switch_to()'s broken but accidentally working handling
of FPU switching - which also generates better code
- Propagate more RIP-relative addressing in assembly code, to generate
slightly better code
- Rework the CPU mitigations Kconfig space to be less idiosyncratic, to
make it easier for distros to follow & maintain these options
- Rework the x86 idle code to cure RCU violations and to clean up the
logic
- Clean up the vDSO Makefile logic
- Misc cleanups and fixes
* tag 'x86-core-2024-03-11' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (52 commits)
x86/idle: Select idle routine only once
x86/idle: Let prefer_mwait_c1_over_halt() return bool
x86/idle: Cleanup idle_setup()
x86/idle: Clean up idle selection
x86/idle: Sanitize X86_BUG_AMD_E400 handling
sched/idle: Conditionally handle tick broadcast in default_idle_call()
x86: Increase brk randomness entropy for 64-bit systems
x86/vdso: Move vDSO to mmap region
x86/vdso/kbuild: Group non-standard build attributes and primary object file rules together
x86/vdso: Fix rethunk patching for vdso-image-{32,64}.o
x86/retpoline: Ensure default return thunk isn't used at runtime
x86/vdso: Use CONFIG_COMPAT_32 to specify vdso32
x86/vdso: Use $(addprefix ) instead of $(foreach )
x86/vdso: Simplify obj-y addition
x86/vdso: Consolidate targets and clean-files
x86/bugs: Rename CONFIG_RETHUNK => CONFIG_MITIGATION_RETHUNK
x86/bugs: Rename CONFIG_CPU_SRSO => CONFIG_MITIGATION_SRSO
x86/bugs: Rename CONFIG_CPU_IBRS_ENTRY => CONFIG_MITIGATION_IBRS_ENTRY
x86/bugs: Rename CONFIG_CPU_UNRET_ENTRY => CONFIG_MITIGATION_UNRET_ENTRY
x86/bugs: Rename CONFIG_SLS => CONFIG_MITIGATION_SLS
...
The "shortest_full" variable is used to keep track of the waiter that is
waiting for the smallest amount on the ring buffer before being woken up.
When a tasks waits on the ring buffer, it passes in a "full" value that is
a percentage. 0 means wake up on any data. 1-100 means wake up from 1% to
100% full buffer.
As all waiters are on the same wait queue, the wake up happens for the
waiter with the smallest percentage.
The problem is that the smallest_full on the cpu_buffer that stores the
smallest amount doesn't get reset when all the waiters are woken up. It
does get reset when the ring buffer is reset (echo > /sys/kernel/tracing/trace).
This means that tasks may be woken up more often then when they want to
be. Instead, have the shortest_full field get reset just before waking up
all the tasks. If the tasks wait again, they will update the shortest_full
before sleeping.
Also add locking around setting of shortest_full in the poll logic, and
change "work" to "rbwork" to match the variable name for rb_irq_work
structures that are used in other places.
Link: https://lore.kernel.org/linux-trace-kernel/20240308202431.948914369@goodmis.org
Cc: stable@vger.kernel.org
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: linke li <lilinke99@qq.com>
Cc: Rabin Vincent <rabin@rab.in>
Fixes: 2c2b0a78b3 ("ring-buffer: Add percentage of ring buffer full to wake up reader")
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
A task can wait on a ring buffer for when it fills up to a specific
watermark. The writer will check the minimum watermark that waiters are
waiting for and if the ring buffer is past that, it will wake up all the
waiters.
The waiters are in a wait loop, and will first check if a signal is
pending and then check if the ring buffer is at the desired level where it
should break out of the loop.
If a file that uses a ring buffer closes, and there's threads waiting on
the ring buffer, it needs to wake up those threads. To do this, a
"wait_index" was used.
Before entering the wait loop, the waiter will read the wait_index. On
wakeup, it will check if the wait_index is different than when it entered
the loop, and will exit the loop if it is. The waker will only need to
update the wait_index before waking up the waiters.
This had a couple of bugs. One trivial one and one broken by design.
The trivial bug was that the waiter checked the wait_index after the
schedule() call. It had to be checked between the prepare_to_wait() and
the schedule() which it was not.
The main bug is that the first check to set the default wait_index will
always be outside the prepare_to_wait() and the schedule(). That's because
the ring_buffer_wait() doesn't have enough context to know if it should
break out of the loop.
The loop itself is not needed, because all the callers to the
ring_buffer_wait() also has their own loop, as the callers have a better
sense of what the context is to decide whether to break out of the loop
or not.
Just have the ring_buffer_wait() block once, and if it gets woken up, exit
the function and let the callers decide what to do next.
Link: https://lore.kernel.org/all/CAHk-=whs5MdtNjzFkTyaUy=vHi=qwWgPi0JgTe6OYUYMNSRZfg@mail.gmail.com/
Link: https://lore.kernel.org/linux-trace-kernel/20240308202431.792933613@goodmis.org
Cc: stable@vger.kernel.org
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: linke li <lilinke99@qq.com>
Cc: Rabin Vincent <rabin@rab.in>
Fixes: e30f53aad2 ("tracing: Do not busy wait in buffer splice")
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
The data on the subbuffer is measured by a write variable that also
contains status flags. The counter is just 20 bits in length. If the
subbuffer is bigger than then counter, it will fail.
Make sure that the subbuffer can not be set to greater than the counter
that keeps track of the data on the subbuffer.
Link: https://lore.kernel.org/linux-trace-kernel/20240220095112.77e9cb81@gandalf.local.home
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Fixes: 2808e31ec1 ("ring-buffer: Add interface for configuring trace sub buffer size")
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
The return type for ring_buffer_poll_wait() is __poll_t. This is behind
the scenes an unsigned where we can set event bits. In case of a
non-allocated CPU, we do return instead -EINVAL (0xffffffea). Lucky us,
this ends up setting few error bits (EPOLLERR | EPOLLHUP | EPOLLNVAL), so
user-space at least is aware something went wrong.
Nonetheless, this is an incorrect code. Replace that -EINVAL with a
proper EPOLLERR to clean that output. As this doesn't change the
behaviour, there's no need to treat this change as a bug fix.
Link: https://lore.kernel.org/linux-trace-kernel/20240131140955.3322792-1-vdonnefort@google.com
Cc: stable@vger.kernel.org
Fixes: 6721cb6002 ("ring-buffer: Do not poll non allocated cpu buffers")
Signed-off-by: Vincent Donnefort <vdonnefort@google.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
- Allow kernel trace instance creation to specify what events are created
Inside the kernel, a subsystem may create a tracing instance that it can
use to send events to user space. This sub-system may not care about the
thousands of events that exist in eventfs. Allow the sub-system to specify
what sub-systems of events it cares about, and only those events are exposed
to this instance.
- Allow the ring buffer to be broken up into bigger sub-buffers than just the
architecture page size. A new tracefs file called "buffer_subbuf_size_kb"
is created. The user can now specify a minimum size the sub-buffer may be
in kilobytes. Note, that the implementation currently make the sub-buffer
size a power of 2 pages (1, 2, 4, 8, 16, ...) but the user only writes in
kilobyte size, and the sub-buffer will be updated to the next size that
it will can accommodate it. If the user writes in 10, it will change the
size to be 4 pages on x86 (16K), as that is the next available size that
can hold 10K pages.
- Update the debug output when a corrupt time is detected in the ring buffer.
If the ring buffer detects inconsistent timestamps, there's a debug config
options that will dump the contents of the meta data of the sub-buffer that
is used for debugging. Add some more information to this dump that helps
with debugging.
- Add more timestamp debugging checks (only triggers when the config is enabled)
- Increase the trace_seq iterator to 2 page sizes.
- Allow strings written into tracefs_marker to be larger. Up to just under
2 page sizes (based on what trace_seq can hold).
- Increase the trace_maker_raw write to be as big as a sub-buffer can hold.
- Remove 32 bit time stamp logic, now that the rb_time_cmpxchg() has been
removed.
- More selftests were added.
- Some code clean ups as well.
-----BEGIN PGP SIGNATURE-----
iIoEABYIADIWIQRRSw7ePDh/lE+zeZMp5XQQmuv6qgUCZZ8p3BQccm9zdGVkdEBn
b29kbWlzLm9yZwAKCRAp5XQQmuv6ql2GAQDZg/zlFEiJHyTfWbCIE8pA3T5xbzKo
26TNxIZAxJJZpQEAvGFU5Smy14pG6soEoVMp8B6ZOANbqU8VVamhOL+r+Qw=
=0OYG
-----END PGP SIGNATURE-----
Merge tag 'trace-v6.8' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace
Pull tracing updates from Steven Rostedt:
- Allow kernel trace instance creation to specify what events are
created
Inside the kernel, a subsystem may create a tracing instance that it
can use to send events to user space. This sub-system may not care
about the thousands of events that exist in eventfs. Allow the
sub-system to specify what sub-systems of events it cares about, and
only those events are exposed to this instance.
- Allow the ring buffer to be broken up into bigger sub-buffers than
just the architecture page size.
A new tracefs file called "buffer_subbuf_size_kb" is created. The
user can now specify a minimum size the sub-buffer may be in
kilobytes. Note, that the implementation currently make the
sub-buffer size a power of 2 pages (1, 2, 4, 8, 16, ...) but the user
only writes in kilobyte size, and the sub-buffer will be updated to
the next size that it will can accommodate it. If the user writes in
10, it will change the size to be 4 pages on x86 (16K), as that is
the next available size that can hold 10K pages.
- Update the debug output when a corrupt time is detected in the ring
buffer. If the ring buffer detects inconsistent timestamps, there's a
debug config options that will dump the contents of the meta data of
the sub-buffer that is used for debugging. Add some more information
to this dump that helps with debugging.
- Add more timestamp debugging checks (only triggers when the config is
enabled)
- Increase the trace_seq iterator to 2 page sizes.
- Allow strings written into tracefs_marker to be larger. Up to just
under 2 page sizes (based on what trace_seq can hold).
- Increase the trace_maker_raw write to be as big as a sub-buffer can
hold.
- Remove 32 bit time stamp logic, now that the rb_time_cmpxchg() has
been removed.
- More selftests were added.
- Some code clean ups as well.
* tag 'trace-v6.8' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace: (29 commits)
ring-buffer: Remove stale comment from ring_buffer_size()
tracing histograms: Simplify parse_actions() function
tracing/selftests: Remove exec permissions from trace_marker.tc test
ring-buffer: Use subbuf_order for buffer page masking
tracing: Update subbuffer with kilobytes not page order
ringbuffer/selftest: Add basic selftest to test changing subbuf order
ring-buffer: Add documentation on the buffer_subbuf_order file
ring-buffer: Just update the subbuffers when changing their allocation order
ring-buffer: Keep the same size when updating the order
tracing: Stop the tracing while changing the ring buffer subbuf size
tracing: Update snapshot order along with main buffer order
ring-buffer: Make sure the spare sub buffer used for reads has same size
ring-buffer: Do no swap cpu buffers if order is different
ring-buffer: Clear pages on error in ring_buffer_subbuf_order_set() failure
ring-buffer: Read and write to ring buffers with custom sub buffer size
ring-buffer: Set new size of the ring buffer sub page
ring-buffer: Add interface for configuring trace sub buffer size
ring-buffer: Page size per ring buffer
ring-buffer: Have ring_buffer_print_page_header() be able to access ring_buffer_iter
ring-buffer: Check if absolute timestamp goes backwards
...
Step 5/10 of the namespace unification of CPU mitigations related Kconfig options.
[ mingo: Converted a few more uses in comments/messages as well. ]
Suggested-by: Josh Poimboeuf <jpoimboe@kernel.org>
Signed-off-by: Breno Leitao <leitao@debian.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Ariel Miculas <amiculas@cisco.com>
Acked-by: Josh Poimboeuf <jpoimboe@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20231121160740.1249350-6-leitao@debian.org
It's been 11 years since the ring_buffer_size() function was updated to
use the nr_pages from the buffer->buffers[cpu] structure instead of using
the buffer->nr_pages that no longer exists.
The comment in the code is more of what a change log should have and is
pretty much useless for development. It's saying how things worked back in
2012 that bares no purpose on today's code. Remove it.
Link: https://lore.kernel.org/linux-trace-kernel/84d3b41a72bd43dbb9d44921ef535c92@AcuMS.aculab.com/
Link: https://lore.kernel.org/linux-trace-kernel/20231220081028.7cd7e8e2@gandalf.local.home
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Reported-by: David Laight <David.Laight@ACULAB.COM>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Acked-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
If an application blocks on the snapshot or snapshot_raw files, expecting
to be woken up when a snapshot occurs, it will not happen. Or it may
happen with an unexpected result.
That result is that the application will be reading the main buffer
instead of the snapshot buffer. That is because when the snapshot occurs,
the main and snapshot buffers are swapped. But the reader has a descriptor
still pointing to the buffer that it originally connected to.
This is fine for the main buffer readers, as they may be blocked waiting
for a watermark to be hit, and when a snapshot occurs, the data that the
main readers want is now on the snapshot buffer.
But for waiters of the snapshot buffer, they are waiting for an event to
occur that will trigger the snapshot and they can then consume it quickly
to save the snapshot before the next snapshot occurs. But to do this, they
need to read the new snapshot buffer, not the old one that is now
receiving new data.
Also, it does not make sense to have a watermark "buffer_percent" on the
snapshot buffer, as the snapshot buffer is static and does not receive new
data except all at once.
Link: https://lore.kernel.org/linux-trace-kernel/20231228095149.77f5b45d@gandalf.local.home
Cc: stable@vger.kernel.org
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Acked-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Fixes: debdd57f51 ("tracing: Make a snapshot feature available from userspace")
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
The tracefs file "buffer_percent" is to allow user space to set a
water-mark on how much of the tracing ring buffer needs to be filled in
order to wake up a blocked reader.
0 - is to wait until any data is in the buffer
1 - is to wait for 1% of the sub buffers to be filled
50 - would be half of the sub buffers are filled with data
100 - is not to wake the waiter until the ring buffer is completely full
Unfortunately the test for being full was:
dirty = ring_buffer_nr_dirty_pages(buffer, cpu);
return (dirty * 100) > (full * nr_pages);
Where "full" is the value for "buffer_percent".
There is two issues with the above when full == 100.
1. dirty * 100 > 100 * nr_pages will never be true
That is, the above is basically saying that if the user sets
buffer_percent to 100, more pages need to be dirty than exist in the
ring buffer!
2. The page that the writer is on is never considered dirty, as dirty
pages are only those that are full. When the writer goes to a new
sub-buffer, it clears the contents of that sub-buffer.
That is, even if the check was ">=" it would still not be equal as the
most pages that can be considered "dirty" is nr_pages - 1.
To fix this, add one to dirty and use ">=" in the compare.
Link: https://lore.kernel.org/linux-trace-kernel/20231226125902.4a057f1d@gandalf.local.home
Cc: stable@vger.kernel.org
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Acked-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Fixes: 03329f9939 ("tracing: Add tracefs file buffer_percentage")
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
The comparisons to PAGE_SIZE were all converted to use the
buffer->subbuf_order, but the use of PAGE_MASK was missed.
Convert all the PAGE_MASK usages over to:
(PAGE_SIZE << cpu_buffer->buffer->subbuf_order) - 1
Link: https://lore.kernel.org/linux-trace-kernel/20231219173800.66eefb7a@gandalf.local.home
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Tzvetomir Stoyanov <tz.stoyanov@gmail.com>
Cc: Vincent Donnefort <vdonnefort@google.com>
Cc: Kent Overstreet <kent.overstreet@gmail.com>
Fixes: 139f840021 ("ring-buffer: Page size per ring buffer")
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
The ring_buffer_subbuf_order_set() was creating ring_buffer_per_cpu
cpu_buffers with the new subbuffers with the updated order, and if they
all successfully were created, then they the ring_buffer's per_cpu buffers
would be freed and replaced by them.
The problem is that the freed per_cpu buffers contains state that would be
lost. Running the following commands:
1. # echo 3 > /sys/kernel/tracing/buffer_subbuf_order
2. # echo 0 > /sys/kernel/tracing/tracing_cpumask
3. # echo 1 > /sys/kernel/tracing/snapshot
4. # echo ff > /sys/kernel/tracing/tracing_cpumask
5. # echo test > /sys/kernel/tracing/trace_marker
Would result in:
-bash: echo: write error: Bad file descriptor
That's because the state of the per_cpu buffers of the snapshot buffer is
lost when the order is changed (the order of a freed snapshot buffer goes
to 0 to save memory, and when the snapshot buffer is allocated again, it
goes back to what the main buffer is).
In operation 2, the snapshot buffers were set to "disable" (as all the
ring buffers CPUs were disabled).
In operation 3, the snapshot is allocated and a call to
ring_buffer_subbuf_order_set() replaced the per_cpu buffers losing the
"record_disable" count.
When it was enabled again, the atomic_dec(&cpu_buffer->record_disable) was
decrementing a zero, setting it to -1. Writing 1 into the snapshot would
swap the snapshot buffer with the main buffer, so now the main buffer is
"disabled", and nothing can write to the ring buffer anymore.
Instead of creating new per_cpu buffers and losing the state of the old
buffers, basically do what the resize does and just allocate new subbuf
pages into the new_pages link list of the per_cpu buffer and if they all
succeed, then replace the old sub buffers with the new ones. This keeps
the per_cpu buffer descriptor in tact and by doing so, keeps its state.
Link: https://lore.kernel.org/linux-trace-kernel/20231219185630.944104939@goodmis.org
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Tzvetomir Stoyanov <tz.stoyanov@gmail.com>
Cc: Vincent Donnefort <vdonnefort@google.com>
Cc: Kent Overstreet <kent.overstreet@gmail.com>
Fixes: f9b94daa54 ("ring-buffer: Set new size of the ring buffer sub page")
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
The function ring_buffer_subbuf_order_set() just updated the sub-buffers
to the new size, but this also changes the size of the buffer in doing so.
As the size is determined by nr_pages * subbuf_size. If the subbuf_size is
increased without decreasing the nr_pages, this causes the total size of
the buffer to increase.
This broke the latency tracers as the snapshot needs to be the same size
as the main buffer. The size of the snapshot buffer is only expanded when
needed, and because the order is still the same, the size becomes out of
sync with the main buffer, as the main buffer increased in size without
the tracing system knowing.
Calculate the nr_pages to allocate with the new subbuf_size to be
buffer_size / new_subbuf_size.
Link: https://lore.kernel.org/linux-trace-kernel/20231219185630.649397785@goodmis.org
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Tzvetomir Stoyanov <tz.stoyanov@gmail.com>
Cc: Vincent Donnefort <vdonnefort@google.com>
Cc: Kent Overstreet <kent.overstreet@gmail.com>
Fixes: f9b94daa54 ("ring-buffer: Set new size of the ring buffer sub page")
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
As all the subbuffer order (subbuffer sizes) must be the same throughout
the ring buffer, check the order of the buffers that are doing a CPU
buffer swap in ring_buffer_swap_cpu() to make sure they are the same.
If the are not the same, then fail to do the swap, otherwise the ring
buffer will think the CPU buffer has a specific subbuffer size when it
does not.
Link: https://lore.kernel.org/linux-trace-kernel/20231219185629.467894710@goodmis.org
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Tzvetomir Stoyanov <tz.stoyanov@gmail.com>
Cc: Vincent Donnefort <vdonnefort@google.com>
Cc: Kent Overstreet <kent.overstreet@gmail.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
On failure to allocate ring buffer pages, the pointer to the CPU buffer
pages is freed, but the pages that were allocated previously were not.
Make sure they are freed too.
Link: https://lore.kernel.org/linux-trace-kernel/20231219185629.179352802@goodmis.org
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Tzvetomir Stoyanov <tz.stoyanov@gmail.com>
Cc: Vincent Donnefort <vdonnefort@google.com>
Cc: Kent Overstreet <kent.overstreet@gmail.com>
Fixes: f9b94daa54 ("tracing: Set new size of the ring buffer sub page")
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
As the size of the ring sub buffer page can be changed dynamically,
the logic that reads and writes to the buffer should be fixed to take
that into account. Some internal ring buffer APIs are changed:
ring_buffer_alloc_read_page()
ring_buffer_free_read_page()
ring_buffer_read_page()
A new API is introduced:
ring_buffer_read_page_data()
Link: https://lore.kernel.org/linux-trace-devel/20211213094825.61876-6-tz.stoyanov@gmail.com
Link: https://lore.kernel.org/linux-trace-kernel/20231219185628.875145995@goodmis.org
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Vincent Donnefort <vdonnefort@google.com>
Cc: Kent Overstreet <kent.overstreet@gmail.com>
Signed-off-by: Tzvetomir Stoyanov (VMware) <tz.stoyanov@gmail.com>
[ Fixed kerneldoc on data_page parameter in ring_buffer_free_read_page() ]
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
There are two approaches when changing the size of the ring buffer
sub page:
1. Destroying all pages and allocating new pages with the new size.
2. Allocating new pages, copying the content of the old pages before
destroying them.
The first approach is easier, it is selected in the proposed
implementation. Changing the ring buffer sub page size is supposed to
not happen frequently. Usually, that size should be set only once,
when the buffer is not in use yet and is supposed to be empty.
Link: https://lore.kernel.org/linux-trace-devel/20211213094825.61876-5-tz.stoyanov@gmail.com
Link: https://lore.kernel.org/linux-trace-kernel/20231219185628.588995543@goodmis.org
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Vincent Donnefort <vdonnefort@google.com>
Cc: Kent Overstreet <kent.overstreet@gmail.com>
Signed-off-by: Tzvetomir Stoyanov (VMware) <tz.stoyanov@gmail.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
The trace ring buffer sub page size can be configured, per trace
instance. A new ftrace file "buffer_subbuf_order" is added to get and
set the size of the ring buffer sub page for current trace instance.
The size must be an order of system page size, that's why the new
interface works with system page order, instead of absolute page size:
0 means the ring buffer sub page is equal to 1 system page and so
forth:
0 - 1 system page
1 - 2 system pages
2 - 4 system pages
...
The ring buffer sub page size is limited between 1 and 128 system
pages. The default value is 1 system page.
New ring buffer APIs are introduced:
ring_buffer_subbuf_order_set()
ring_buffer_subbuf_order_get()
ring_buffer_subbuf_size_get()
Link: https://lore.kernel.org/linux-trace-devel/20211213094825.61876-4-tz.stoyanov@gmail.com
Link: https://lore.kernel.org/linux-trace-kernel/20231219185628.298324722@goodmis.org
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Vincent Donnefort <vdonnefort@google.com>
Cc: Kent Overstreet <kent.overstreet@gmail.com>
Signed-off-by: Tzvetomir Stoyanov (VMware) <tz.stoyanov@gmail.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Currently the size of one sub buffer page is global for all buffers and
it is hard coded to one system page. In order to introduce configurable
ring buffer sub page size, the internal logic should be refactored to
work with sub page size per ring buffer.
Link: https://lore.kernel.org/linux-trace-devel/20211213094825.61876-3-tz.stoyanov@gmail.com
Link: https://lore.kernel.org/linux-trace-kernel/20231219185628.009147038@goodmis.org
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Vincent Donnefort <vdonnefort@google.com>
Cc: Kent Overstreet <kent.overstreet@gmail.com>
Signed-off-by: Tzvetomir Stoyanov (VMware) <tz.stoyanov@gmail.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
In order to introduce sub-buffer size per ring buffer, some internal
refactoring is needed. As ring_buffer_print_page_header() will depend on
the trace_buffer structure, it is moved after the structure definition.
Link: https://lore.kernel.org/linux-trace-devel/20211213094825.61876-2-tz.stoyanov@gmail.com
Link: https://lore.kernel.org/linux-trace-kernel/20231219185627.723857541@goodmis.org
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Vincent Donnefort <vdonnefort@google.com>
Cc: Kent Overstreet <kent.overstreet@gmail.com>
Signed-off-by: Tzvetomir Stoyanov (VMware) <tz.stoyanov@gmail.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
The check_buffer() which checks the timestamps of the ring buffer
sub-buffer page, when enabled, only checks if the adding of deltas of the
events from the last absolute timestamp or the timestamp of the sub-buffer
page adds up to the current event.
What it does not check is if the absolute timestamp causes the time of the
events to go backwards, as that can cause issues elsewhere.
Test for the timestamp going backwards too.
This also fixes a slight issue where if the warning triggers at boot up
(because of the resetting of the tsc), it will disable all further checks,
even those that are after boot Have it continue checking if the warning
was ignored during boot up.
Link: https://lore.kernel.org/linux-trace-kernel/20231219074732.18b092d4@gandalf.local.home
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
When the ring buffer timestamp verifier triggers, it dumps the content of
the sub-buffer. But currently it only dumps the timestamps and the offset
of the data as well as the deltas. It would be even more informative if
the event data also showed the interrupt context level it was in.
That is, if each event showed that the event was written in normal,
softirq, irq or NMI context. Then a better idea about how the events may
have been interrupted from each other.
As the payload of the ring buffer is really a black box of the ring
buffer, just assume that if the payload is larger than a trace entry, that
it is a trace entry. As trace entries have the interrupt context
information saved in a flags field, look at that location and report the
output of the flags.
If the payload is not a trace entry, there's no way to really know, and
the information will be garbage. But that's OK, because this is for
debugging only (this output is not used in production as the buffer check
that calls it causes a huge overhead to the tracing). This information,
when available, is crucial for debugging timestamp issues. If it's
garbage, it will also be pretty obvious that its garbage too.
As this output usually happens in kselftests of the tracing code, the user
will know what the payload is at the time.
Link: https://lore.kernel.org/linux-trace-kernel/20231219074542.6f304601@gandalf.local.home
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Suggested-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Each event has a 27 bit timestamp delta that is used to hold the delta
from the last event. If the time between events is greater than 2^27, then
a timestamp is added that holds a 59 bit absolute timestamp.
Until a389d86f7f ("ring-buffer: Have nested events still record running
time stamp"), if an interrupt interrupted an event in progress, all the
events delta would be zero to not deal with the races that need to be
handled. The commit a389d86f7f changed that to handle the races giving
all events, even those that preempt other events, still have an accurate
timestamp.
To handle those races requires performing 64-bit cmpxchg on the
timestamps. But doing 64-bit cmpxchg on 32-bit architectures is considered
very slow. To try to deal with this the timestamp logic was broken into
two and then three 32-bit cmpxchgs, with the thought that two (or three)
32-bit cmpxchgs are still faster than a single 64-bit cmpxchg on 32-bit
architectures.
Part of the problem with this is that I didn't have any 32-bit
architectures to test on. After hitting several subtle bugs in this code,
an effort was made to try and see if three 32-bit cmpxchgs are indeed
faster than a single 64-bit. After a few people brushed off the dust of
their old 32-bit machines, tests were done, and even though 32-bit cmpxchg
was faster than a single 64-bit, it was in the order of 50% at best, not
300%.
After some more refactoring of the code, all 4 64-bit cmpxchg were removed:
https://lore.kernel.org/linux-trace-kernel/20231211114420.36dde01b@gandalf.local.homehttps://lore.kernel.org/linux-trace-kernel/20231214222921.193037a7@gandalf.local.homehttps://lore.kernel.org/linux-trace-kernel/20231215081810.1f4f38fe@rorschach.local.homehttps://lore.kernel.org/linux-trace-kernel/20231218230712.3a76b081@gandalf.local.home/
With all the 64-bit cmpxchg removed, the complex 32-bit workaround can also be
removed.
The 32-bit and 64-bit logic is now exactly the same.
Link: https://lore.kernel.org/all/20231213214632.15047c40@gandalf.local.home/
Link: https://lore.kernel.org/linux-trace-kernel/20231219074303.28f9abda@gandalf.local.home
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Allow a trace write to be as big as the ring buffer tracing data will
allow. Currently, it only allows writes of 1KB in size, but there's no
reason that it cannot allow what the ring buffer can hold.
Link: https://lore.kernel.org/linux-trace-kernel/20231212131901.5f501e72@gandalf.local.home
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
On bugs that have the ring buffer timestamp get out of sync, the config
CONFIG_RING_BUFFER_VALIDATE_TIME_DELTAS, that checks for it and if it is
detected it causes a dump of the bad sub buffer.
It shows each event and their timestamp as well as the delta in the event.
But it's also good to see the offset into the subbuffer for that event to
know if how close to the end it is.
Also print where the last event actually ended compared to where it was
expected to end.
Link: https://lore.kernel.org/linux-trace-kernel/20231211131623.59eaebd2@gandalf.local.home
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Acked-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
To synchronize the timestamps with the ring buffer reservation, there are
two timestamps that are saved in the buffer meta data.
1. before_stamp
2. write_stamp
When the two are equal, the write_stamp is considered valid, as in, it may
be used to calculate the delta of the next event as the write_stamp is the
timestamp of the previous reserved event on the buffer.
This is done by the following:
/*A*/ w = current position on the ring buffer
before = before_stamp
after = write_stamp
ts = read current timestamp
if (before != after) {
write_stamp is not valid, force adding an absolute
timestamp.
}
/*B*/ before_stamp = ts
/*C*/ write = local_add_return(event length, position on ring buffer)
if (w == write - event length) {
/* Nothing interrupted between A and C */
/*E*/ write_stamp = ts;
delta = ts - after
/*
* If nothing interrupted again,
* before_stamp == write_stamp and write_stamp
* can be used to calculate the delta for
* events that come in after this one.
*/
} else {
/*
* The slow path!
* Was interrupted between A and C.
*/
This is the place that there's a bug. We currently have:
after = write_stamp
ts = read current timestamp
/*F*/ if (write == current position on the ring buffer &&
after < ts && cmpxchg(write_stamp, after, ts)) {
delta = ts - after;
} else {
delta = 0;
}
The assumption is that if the current position on the ring buffer hasn't
moved between C and F, then it also was not interrupted, and that the last
event written has a timestamp that matches the write_stamp. That is the
write_stamp is valid.
But this may not be the case:
If a task context event was interrupted by softirq between B and C.
And the softirq wrote an event that got interrupted by a hard irq between
C and E.
and the hard irq wrote an event (does not need to be interrupted)
We have:
/*B*/ before_stamp = ts of normal context
---> interrupted by softirq
/*B*/ before_stamp = ts of softirq context
---> interrupted by hardirq
/*B*/ before_stamp = ts of hard irq context
/*E*/ write_stamp = ts of hard irq context
/* matches and write_stamp valid */
<----
/*E*/ write_stamp = ts of softirq context
/* No longer matches before_stamp, write_stamp is not valid! */
<---
w != write - length, go to slow path
// Right now the order of events in the ring buffer is:
//
// |-- softirq event --|-- hard irq event --|-- normal context event --|
//
after = write_stamp (this is the ts of softirq)
ts = read current timestamp
if (write == current position on the ring buffer [true] &&
after < ts [true] && cmpxchg(write_stamp, after, ts) [true]) {
delta = ts - after [Wrong!]
The delta is to be between the hard irq event and the normal context
event, but the above logic made the delta between the softirq event and
the normal context event, where the hard irq event is between the two. This
will shift all the remaining event timestamps on the sub-buffer
incorrectly.
The write_stamp is only valid if it matches the before_stamp. The cmpxchg
does nothing to help this.
Instead, the following logic can be done to fix this:
before = before_stamp
ts = read current timestamp
before_stamp = ts
after = write_stamp
if (write == current position on the ring buffer &&
after == before && after < ts) {
delta = ts - after
} else {
delta = 0;
}
The above will only use the write_stamp if it still matches before_stamp
and was tested to not have changed since C.
As a bonus, with this logic we do not need any 64-bit cmpxchg() at all!
This means the 32-bit rb_time_t workaround can finally be removed. But
that's for a later time.
Link: https://lore.kernel.org/linux-trace-kernel/20231218175229.58ec3daf@gandalf.local.home/
Link: https://lore.kernel.org/linux-trace-kernel/20231218230712.3a76b081@gandalf.local.home
Cc: stable@vger.kernel.org
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Fixes: dd93942570 ("ring-buffer: Do not try to put back write_stamp")
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
As the ring buffer recording requires cmpxchg() to work, if the
architecture does not support cmpxchg in NMI, then do not do any recording
within an NMI.
Link: https://lore.kernel.org/linux-trace-kernel/20231213175403.6fc18540@gandalf.local.home
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
The rb_time_cmpxchg() on 32-bit architectures requires setting three
32-bit words to represent the 64-bit timestamp, with some salt for
synchronization. Those are: msb, top, and bottom
The issue is, the rb_time_cmpxchg() did not properly salt the msb portion,
and the msb that was written was stale.
Link: https://lore.kernel.org/linux-trace-kernel/20231215084114.20899342@rorschach.local.home
Cc: stable@vger.kernel.org
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Fixes: f03f2abce4 ("ring-buffer: Have 32 bit time stamps use all 64 bits")
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
The following race can cause rb_time_read() to observe a corrupted time
stamp:
rb_time_cmpxchg()
[...]
if (!rb_time_read_cmpxchg(&t->msb, msb, msb2))
return false;
if (!rb_time_read_cmpxchg(&t->top, top, top2))
return false;
<interrupted before updating bottom>
__rb_time_read()
[...]
do {
c = local_read(&t->cnt);
top = local_read(&t->top);
bottom = local_read(&t->bottom);
msb = local_read(&t->msb);
} while (c != local_read(&t->cnt));
*cnt = rb_time_cnt(top);
/* If top and msb counts don't match, this interrupted a write */
if (*cnt != rb_time_cnt(msb))
return false;
^ this check fails to catch that "bottom" is still not updated.
So the old "bottom" value is returned, which is wrong.
Fix this by checking that all three of msb, top, and bottom 2-bit cnt
values match.
The reason to favor checking all three fields over requiring a specific
update order for both rb_time_set() and rb_time_cmpxchg() is because
checking all three fields is more robust to handle partial failures of
rb_time_cmpxchg() when interrupted by nested rb_time_set().
Link: https://lore.kernel.org/lkml/20231211201324.652870-1-mathieu.desnoyers@efficios.com/
Link: https://lore.kernel.org/linux-trace-kernel/20231212193049.680122-1-mathieu.desnoyers@efficios.com
Fixes: f458a14534 ("ring-buffer: Test last update in 32bit version of __rb_time_read()")
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Mathieu Desnoyers pointed out an issue in the rb_time_cmpxchg() for 32 bit
architectures. That is:
static bool rb_time_cmpxchg(rb_time_t *t, u64 expect, u64 set)
{
unsigned long cnt, top, bottom, msb;
unsigned long cnt2, top2, bottom2, msb2;
u64 val;
/* The cmpxchg always fails if it interrupted an update */
if (!__rb_time_read(t, &val, &cnt2))
return false;
if (val != expect)
return false;
<<<< interrupted here!
cnt = local_read(&t->cnt);
The problem is that the synchronization counter in the rb_time_t is read
*after* the value of the timestamp is read. That means if an interrupt
were to come in between the value being read and the counter being read,
it can change the value and the counter and the interrupted process would
be clueless about it!
The counter needs to be read first and then the value. That way it is easy
to tell if the value is stale or not. If the counter hasn't been updated,
then the value is still good.
Link: https://lore.kernel.org/linux-trace-kernel/20231211201324.652870-1-mathieu.desnoyers@efficios.com/
Link: https://lore.kernel.org/linux-trace-kernel/20231212115301.7a9c9a64@gandalf.local.home
Cc: stable@vger.kernel.org
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Fixes: 10464b4aa6 ("ring-buffer: Add rb_time_t 64 bit operations for speeding up 32 bit")
Reported-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Reviewed-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
When filtering is enabled, a temporary buffer is created to place the
content of the trace event output so that the filter logic can decide
from the trace event output if the trace event should be filtered out or
not. If it is to be filtered out, the content in the temporary buffer is
simply discarded, otherwise it is written into the trace buffer.
But if an interrupt were to come in while a previous event was using that
temporary buffer, the event written by the interrupt would actually go
into the ring buffer itself to prevent corrupting the data on the
temporary buffer. If the event is to be filtered out, the event in the
ring buffer is discarded, or if it fails to discard because another event
were to have already come in, it is turned into padding.
The update to the write_stamp in the rb_try_to_discard() happens after a
fix was made to force the next event after the discard to use an absolute
timestamp by setting the before_stamp to zero so it does not match the
write_stamp (which causes an event to use the absolute timestamp).
But there's an effort in rb_try_to_discard() to put back the write_stamp
to what it was before the event was added. But this is useless and
wasteful because nothing is going to be using that write_stamp for
calculations as it still will not match the before_stamp.
Remove this useless update, and in doing so, we remove another
cmpxchg64()!
Also update the comments to reflect this change as well as remove some
extra white space in another comment.
Link: https://lore.kernel.org/linux-trace-kernel/20231215081810.1f4f38fe@rorschach.local.home
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Joel Fernandes <joel@joelfernandes.org>
Cc: Vincent Donnefort <vdonnefort@google.com>
Fixes: b2dd797543 ("ring-buffer: Force absolute timestamp on discard of event")
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
If an update to an event is interrupted by another event between the time
the initial event allocated its buffer and where it wrote to the
write_stamp, the code try to reset the write stamp back to the what it had
just overwritten. It knows that it was overwritten via checking the
before_stamp, and if it didn't match what it wrote to the before_stamp
before it allocated its space, it knows it was overwritten.
To put back the write_stamp, it uses the before_stamp it read. The problem
here is that by writing the before_stamp to the write_stamp it makes the
two equal again, which means that the write_stamp can be considered valid
as the last timestamp written to the ring buffer. But this is not
necessarily true. The event that interrupted the event could have been
interrupted in a way that it was interrupted as well, and can end up
leaving with an invalid write_stamp. But if this happens and returns to
this context that uses the before_stamp to update the write_stamp again,
it can possibly incorrectly make it valid, causing later events to have in
correct time stamps.
As it is OK to leave this function with an invalid write_stamp (one that
doesn't match the before_stamp), there's no reason to try to make it valid
again in this case. If this race happens, then just leave with the invalid
write_stamp and the next event to come along will just add a absolute
timestamp and validate everything again.
Bonus points: This gets rid of another cmpxchg64!
Link: https://lore.kernel.org/linux-trace-kernel/20231214222921.193037a7@gandalf.local.home
Cc: stable@vger.kernel.org
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Joel Fernandes <joel@joelfernandes.org>
Cc: Vincent Donnefort <vdonnefort@google.com>
Fixes: a389d86f7f ("ring-buffer: Have nested events still record running time stamp")
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
For the ring buffer iterator (non-consuming read), the event needs to be
copied into the iterator buffer to make sure that a writer does not
overwrite it while the user is reading it. If a write happens during the
copy, the buffer is simply discarded.
But the temp buffer itself was not big enough. The allocation of the
buffer was only BUF_MAX_DATA_SIZE, which is the maximum data size that can
be passed into the ring buffer and saved. But the temp buffer needs to
hold the meta data as well. That would be BUF_PAGE_SIZE and not
BUF_MAX_DATA_SIZE.
Link: https://lore.kernel.org/linux-trace-kernel/20231212072558.61f76493@gandalf.local.home
Cc: stable@vger.kernel.org
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Fixes: 785888c544 ("ring-buffer: Have rb_iter_head_event() handle concurrent writer")
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Petr Pavlu