iv/linux
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge branch 'for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu into core/rcu

Browse Source 
Pull RCU updates from Paul E. McKenney:

 - Documentation updates.

 - Miscellaneous fixes.

 - Parallelize SRCU callback handling (plus overlapping patches).

Signed-off-by: Ingo Molnar <mingo@kernel.org>
This commit is contained in:
Ingo Molnar 2017-04-23 11:12:44 +02:00
commit 58d30c36d4
71 changed files with 3637 additions and 1116 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
Documentation/RCU/00-INDEX
View File

@ -17,7 +17,7 @@ rcu_dereference.txt
rcubarrier.txt
- RCU and Unloadable Modules
rculist_nulls.txt
- RCU list primitives for use with SLAB_DESTROY_BY_RCU
- RCU list primitives for use with SLAB_TYPESAFE_BY_RCU
rcuref.txt
- Reference-count design for elements of lists/arrays protected by RCU
rcu.txt

233
Documentation/RCU/Design/Data-Structures/Data-Structures.html
View File

@ -19,6 +19,8 @@ to each other.
The <tt>rcu_state</tt> Structure</a>
<li> <a href="#The rcu_node Structure">
The <tt>rcu_node</tt> Structure</a>
<li> <a href="#The rcu_segcblist Structure">
The <tt>rcu_segcblist</tt> Structure</a>
<li> <a href="#The rcu_data Structure">
The <tt>rcu_data</tt> Structure</a>
<li> <a href="#The rcu_dynticks Structure">
@ -841,6 +843,134 @@ for lockdep lock-class names.
Finally, lines&nbsp;64-66 produce an error if the maximum number of
CPUs is too large for the specified fanout.
<h3><a name="The rcu_segcblist Structure">
The <tt>rcu_segcblist</tt> Structure</a></h3>
The <tt>rcu_segcblist</tt> structure maintains a segmented list of
callbacks as follows:
<pre>
1 #define RCU_DONE_TAIL 0
2 #define RCU_WAIT_TAIL 1
3 #define RCU_NEXT_READY_TAIL 2
4 #define RCU_NEXT_TAIL 3
5 #define RCU_CBLIST_NSEGS 4
6
7 struct rcu_segcblist {
8 struct rcu_head *head;
9 struct rcu_head **tails[RCU_CBLIST_NSEGS];
10 unsigned long gp_seq[RCU_CBLIST_NSEGS];
11 long len;
12 long len_lazy;
13 };
</pre>
<p>
The segments are as follows:
<ol>
<li> <tt>RCU_DONE_TAIL</tt>: Callbacks whose grace periods have elapsed.
These callbacks are ready to be invoked.
<li> <tt>RCU_WAIT_TAIL</tt>: Callbacks that are waiting for the
current grace period.
Note that different CPUs can have different ideas about which
grace period is current, hence the <tt>-&gt;gp_seq</tt> field.
<li> <tt>RCU_NEXT_READY_TAIL</tt>: Callbacks waiting for the next
grace period to start.
<li> <tt>RCU_NEXT_TAIL</tt>: Callbacks that have not yet been
associated with a grace period.
</ol>
<p>
The <tt>-&gt;head</tt> pointer references the first callback or
is <tt>NULL</tt> if the list contains no callbacks (which is
<i>not</i> the same as being empty).
Each element of the <tt>-&gt;tails[]</tt> array references the
<tt>-&gt;next</tt> pointer of the last callback in the corresponding
segment of the list, or the list's <tt>-&gt;head</tt> pointer if
that segment and all previous segments are empty.
If the corresponding segment is empty but some previous segment is
not empty, then the array element is identical to its predecessor.
Older callbacks are closer to the head of the list, and new callbacks
are added at the tail.
This relationship between the <tt>-&gt;head</tt> pointer, the
<tt>-&gt;tails[]</tt> array, and the callbacks is shown in this
diagram:
</p><p><img src="nxtlist.svg" alt="nxtlist.svg" width="40%">
</p><p>In this figure, the <tt>-&gt;head</tt> pointer references the
first
RCU callback in the list.
The <tt>-&gt;tails[RCU_DONE_TAIL]</tt> array element references
the <tt>-&gt;head</tt> pointer itself, indicating that none
of the callbacks is ready to invoke.
The <tt>-&gt;tails[RCU_WAIT_TAIL]</tt> array element references callback
CB&nbsp;2's <tt>-&gt;next</tt> pointer, which indicates that
CB&nbsp;1 and CB&nbsp;2 are both waiting on the current grace period,
give or take possible disagreements about exactly which grace period
is the current one.
The <tt>-&gt;tails[RCU_NEXT_READY_TAIL]</tt> array element
references the same RCU callback that <tt>-&gt;tails[RCU_WAIT_TAIL]</tt>
does, which indicates that there are no callbacks waiting on the next
RCU grace period.
The <tt>-&gt;tails[RCU_NEXT_TAIL]</tt> array element references
CB&nbsp;4's <tt>-&gt;next</tt> pointer, indicating that all the
remaining RCU callbacks have not yet been assigned to an RCU grace
period.
Note that the <tt>-&gt;tails[RCU_NEXT_TAIL]</tt> array element
always references the last RCU callback's <tt>-&gt;next</tt> pointer
unless the callback list is empty, in which case it references
the <tt>-&gt;head</tt> pointer.
<p>
There is one additional important special case for the
<tt>-&gt;tails[RCU_NEXT_TAIL]</tt> array element: It can be <tt>NULL</tt>
when this list is <i>disabled</i>.
Lists are disabled when the corresponding CPU is offline or when
the corresponding CPU's callbacks are offloaded to a kthread,
both of which are described elsewhere.
</p><p>CPUs advance their callbacks from the
<tt>RCU_NEXT_TAIL</tt> to the <tt>RCU_NEXT_READY_TAIL</tt> to the
<tt>RCU_WAIT_TAIL</tt> to the <tt>RCU_DONE_TAIL</tt> list segments
as grace periods advance.
</p><p>The <tt>-&gt;gp_seq[]</tt> array records grace-period
numbers corresponding to the list segments.
This is what allows different CPUs to have different ideas as to
which is the current grace period while still avoiding premature
invocation of their callbacks.
In particular, this allows CPUs that go idle for extended periods
to determine which of their callbacks are ready to be invoked after
reawakening.
</p><p>The <tt>-&gt;len</tt> counter contains the number of
callbacks in <tt>-&gt;head</tt>, and the
<tt>-&gt;len_lazy</tt> contains the number of those callbacks that
are known to only free memory, and whose invocation can therefore
be safely deferred.
<p><b>Important note</b>: It is the <tt>-&gt;len</tt> field that
determines whether or not there are callbacks associated with
this <tt>rcu_segcblist</tt> structure, <i>not</i> the <tt>-&gt;head</tt>
pointer.
The reason for this is that all the ready-to-invoke callbacks
(that is, those in the <tt>RCU_DONE_TAIL</tt> segment) are extracted
all at once at callback-invocation time.
If callback invocation must be postponed, for example, because a
high-priority process just woke up on this CPU, then the remaining
callbacks are placed back on the <tt>RCU_DONE_TAIL</tt> segment.
Either way, the <tt>-&gt;len</tt> and <tt>-&gt;len_lazy</tt> counts
are adjusted after the corresponding callbacks have been invoked, and so
again it is the <tt>-&gt;len</tt> count that accurately reflects whether
or not there are callbacks associated with this <tt>rcu_segcblist</tt>
structure.
Of course, off-CPU sampling of the <tt>-&gt;len</tt> count requires
the use of appropriate synchronization, for example, memory barriers.
This synchronization can be a bit subtle, particularly in the case
of <tt>rcu_barrier()</tt>.
<h3><a name="The rcu_data Structure">
The <tt>rcu_data</tt> Structure</a></h3>
@ -983,62 +1113,18 @@ choice.
as follows:
<pre>
1 struct rcu_head *nxtlist;
2 struct rcu_head **nxttail[RCU_NEXT_SIZE];
3 unsigned long nxtcompleted[RCU_NEXT_SIZE];
4 long qlen_lazy;
5 long qlen;
6 long qlen_last_fqs_check;
1 struct rcu_segcblist cblist;
2 long qlen_last_fqs_check;
3 unsigned long n_cbs_invoked;
4 unsigned long n_nocbs_invoked;
5 unsigned long n_cbs_orphaned;
6 unsigned long n_cbs_adopted;
7 unsigned long n_force_qs_snap;
8 unsigned long n_cbs_invoked;
9 unsigned long n_cbs_orphaned;
10 unsigned long n_cbs_adopted;
11 long blimit;
8 long blimit;
</pre>
<p>The <tt>-&gt;nxtlist</tt> pointer and the
<tt>-&gt;nxttail[]</tt> array form a four-segment list with
older callbacks near the head and newer ones near the tail.
Each segment contains callbacks with the corresponding relationship
to the current grace period.
The pointer out of the end of each of the four segments is referenced
by the element of the <tt>-&gt;nxttail[]</tt> array indexed by
<tt>RCU_DONE_TAIL</tt> (for callbacks handled by a prior grace period),
<tt>RCU_WAIT_TAIL</tt> (for callbacks waiting on the current grace period),
<tt>RCU_NEXT_READY_TAIL</tt> (for callbacks that will wait on the next
grace period), and
<tt>RCU_NEXT_TAIL</tt> (for callbacks that are not yet associated
with a specific grace period)
respectively, as shown in the following figure.
</p><p><img src="nxtlist.svg" alt="nxtlist.svg" width="40%">
</p><p>In this figure, the <tt>-&gt;nxtlist</tt> pointer references the
first
RCU callback in the list.
The <tt>-&gt;nxttail[RCU_DONE_TAIL]</tt> array element references
the <tt>-&gt;nxtlist</tt> pointer itself, indicating that none
of the callbacks is ready to invoke.
The <tt>-&gt;nxttail[RCU_WAIT_TAIL]</tt> array element references callback
CB&nbsp;2's <tt>-&gt;next</tt> pointer, which indicates that
CB&nbsp;1 and CB&nbsp;2 are both waiting on the current grace period.
The <tt>-&gt;nxttail[RCU_NEXT_READY_TAIL]</tt> array element
references the same RCU callback that <tt>-&gt;nxttail[RCU_WAIT_TAIL]</tt>
does, which indicates that there are no callbacks waiting on the next
RCU grace period.
The <tt>-&gt;nxttail[RCU_NEXT_TAIL]</tt> array element references
CB&nbsp;4's <tt>-&gt;next</tt> pointer, indicating that all the
remaining RCU callbacks have not yet been assigned to an RCU grace
period.
Note that the <tt>-&gt;nxttail[RCU_NEXT_TAIL]</tt> array element
always references the last RCU callback's <tt>-&gt;next</tt> pointer
unless the callback list is empty, in which case it references
the <tt>-&gt;nxtlist</tt> pointer.
</p><p>CPUs advance their callbacks from the
<tt>RCU_NEXT_TAIL</tt> to the <tt>RCU_NEXT_READY_TAIL</tt> to the
<tt>RCU_WAIT_TAIL</tt> to the <tt>RCU_DONE_TAIL</tt> list segments
as grace periods advance.
<p>The <tt>-&gt;cblist</tt> structure is the segmented callback list
described earlier.
The CPU advances the callbacks in its <tt>rcu_data</tt> structure
whenever it notices that another RCU grace period has completed.
The CPU detects the completion of an RCU grace period by noticing
@ -1049,16 +1135,7 @@ Recall that each <tt>rcu_node</tt> structure's
<tt>-&gt;completed</tt> field is updated at the end of each
grace period.
</p><p>The <tt>-&gt;nxtcompleted[]</tt> array records grace-period
numbers corresponding to the list segments.
This allows CPUs that go idle for extended periods to determine
which of their callbacks are ready to be invoked after reawakening.
</p><p>The <tt>-&gt;qlen</tt> counter contains the number of
callbacks in <tt>-&gt;nxtlist</tt>, and the
<tt>-&gt;qlen_lazy</tt> contains the number of those callbacks that
are known to only free memory, and whose invocation can therefore
be safely deferred.
<p>
The <tt>-&gt;qlen_last_fqs_check</tt> and
<tt>-&gt;n_force_qs_snap</tt> coordinate the forcing of quiescent
states from <tt>call_rcu()</tt> and friends when callback
@ -1069,6 +1146,10 @@ lists grow excessively long.
fields count the number of callbacks invoked,
sent to other CPUs when this CPU goes offline,
and received from other CPUs when those other CPUs go offline.
The <tt>-&gt;n_nocbs_invoked</tt> is used when the CPU's callbacks
are offloaded to a kthread.
<p>
Finally, the <tt>-&gt;blimit</tt> counter is the maximum number of
RCU callbacks that may be invoked at a given time.
@ -1104,6 +1185,9 @@ Its fields are as follows:
1 int dynticks_nesting;
2 int dynticks_nmi_nesting;
3 atomic_t dynticks;
4 bool rcu_need_heavy_qs;
5 unsigned long rcu_qs_ctr;
6 bool rcu_urgent_qs;
</pre>
<p>The <tt>-&gt;dynticks_nesting</tt> field counts the
@ -1117,11 +1201,32 @@ NMIs are counted by the <tt>-&gt;dynticks_nmi_nesting</tt>
field, except that NMIs that interrupt non-dyntick-idle execution
are not counted.
</p><p>Finally, the <tt>-&gt;dynticks</tt> field counts the corresponding
</p><p>The <tt>-&gt;dynticks</tt> field counts the corresponding
CPU's transitions to and from dyntick-idle mode, so that this counter
has an even value when the CPU is in dyntick-idle mode and an odd
value otherwise.
</p><p>The <tt>-&gt;rcu_need_heavy_qs</tt> field is used
to record the fact that the RCU core code would really like to
see a quiescent state from the corresponding CPU, so much so that
it is willing to call for heavy-weight dyntick-counter operations.
This flag is checked by RCU's context-switch and <tt>cond_resched()</tt>
code, which provide a momentary idle sojourn in response.
</p><p>The <tt>-&gt;rcu_qs_ctr</tt> field is used to record
quiescent states from <tt>cond_resched()</tt>.
Because <tt>cond_resched()</tt> can execute quite frequently, this
must be quite lightweight, as in a non-atomic increment of this
per-CPU field.
</p><p>Finally, the <tt>-&gt;rcu_urgent_qs</tt> field is used to record
the fact that the RCU core code would really like to see a quiescent
state from the corresponding CPU, with the various other fields indicating
just how badly RCU wants this quiescent state.
This flag is checked by RCU's context-switch and <tt>cond_resched()</tt>
code, which, if nothing else, non-atomically increment <tt>-&gt;rcu_qs_ctr</tt>
in response.
<table>
<tr><th>&nbsp;</th></tr>
<tr><th align="left">Quick Quiz:</th></tr>

34
Documentation/RCU/Design/Data-Structures/nxtlist.svg
View File

@ -19,7 +19,7 @@
id="svg2"
version="1.1"
inkscape:version="0.48.4 r9939"
sodipodi:docname="nxtlist.fig">
sodipodi:docname="segcblist.svg">
<metadata
id="metadata94">
<rdf:RDF>
@ -28,7 +28,7 @@
<dc:format>image/svg+xml</dc:format>
<dc:type
rdf:resource="http://purl.org/dc/dcmitype/StillImage" />
<dc:title></dc:title>
<dc:title />
</cc:Work>
</rdf:RDF>
</metadata>
@ -241,61 +241,51 @@
xml:space="preserve"
x="225"
y="675"
fill="#000000"
font-family="Courier"
font-style="normal"
font-weight="bold"
font-size="324"
text-anchor="start"
id="text64">nxtlist</text>
id="text64"
style="font-size:324px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;font-family:Courier">-&gt;head</text>
<!-- Text -->
<text
xml:space="preserve"
x="225"
y="1800"
fill="#000000"
font-family="Courier"
font-style="normal"
font-weight="bold"
font-size="324"
text-anchor="start"
id="text66">nxttail[RCU_DONE_TAIL]</text>
id="text66"
style="font-size:324px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;font-family:Courier">-&gt;tails[RCU_DONE_TAIL]</text>
<!-- Text -->
<text
xml:space="preserve"
x="225"
y="2925"
fill="#000000"
font-family="Courier"
font-style="normal"
font-weight="bold"
font-size="324"
text-anchor="start"
id="text68">nxttail[RCU_WAIT_TAIL]</text>
id="text68"
style="font-size:324px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;font-family:Courier">-&gt;tails[RCU_WAIT_TAIL]</text>
<!-- Text -->
<text
xml:space="preserve"
x="225"
y="4050"
fill="#000000"
font-family="Courier"
font-style="normal"
font-weight="bold"
font-size="324"
text-anchor="start"
id="text70">nxttail[RCU_NEXT_READY_TAIL]</text>
id="text70"
style="font-size:324px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;font-family:Courier">-&gt;tails[RCU_NEXT_READY_TAIL]</text>
<!-- Text -->
<text
xml:space="preserve"
x="225"
y="5175"
fill="#000000"
font-family="Courier"
font-style="normal"
font-weight="bold"
font-size="324"
text-anchor="start"
id="text72">nxttail[RCU_NEXT_TAIL]</text>
id="text72"
style="font-size:324px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;font-family:Courier">-&gt;tails[RCU_NEXT_TAIL]</text>
<!-- Text -->
<text
xml:space="preserve"

Side by Side Swipe Overlay

Before

Width:  |  Height:  |  Size: 11 KiB

After

Width:  |  Height:  |  Size: 11 KiB

47
Documentation/RCU/Design/Expedited-Grace-Periods/Expedited-Grace-Periods.html
View File

@ -284,6 +284,7 @@ Expedited Grace Period Refinements</a></h2>
Funnel locking and wait/wakeup</a>.
<li> <a href="#Use of Workqueues">Use of Workqueues</a>.
<li> <a href="#Stall Warnings">Stall warnings</a>.
<li> <a href="#Mid-Boot Operation">Mid-boot operation</a>.
</ol>
<h3><a name="Idle-CPU Checks">Idle-CPU Checks</a></h3>
@ -524,7 +525,7 @@ their grace periods and carrying out their wakeups.
In earlier implementations, the task requesting the expedited
grace period also drove it to completion.
This straightforward approach had the disadvantage of needing to
account for signals sent to user tasks,
account for POSIX signals sent to user tasks,
so more recent implemementations use the Linux kernel's
<a href="https://www.kernel.org/doc/Documentation/workqueue.txt">workqueues</a>.
@ -533,8 +534,8 @@ The requesting task still does counter snapshotting and funnel-lock
processing, but the task reaching the top of the funnel lock
does a <tt>schedule_work()</tt> (from <tt>_synchronize_rcu_expedited()</tt>
so that a workqueue kthread does the actual grace-period processing.
Because workqueue kthreads do not accept signals, grace-period-wait
processing need not allow for signals.
Because workqueue kthreads do not accept POSIX signals, grace-period-wait
processing need not allow for POSIX signals.
In addition, this approach allows wakeups for the previous expedited
grace period to be overlapped with processing for the next expedited
@ -586,6 +587,46 @@ blocking the current grace period are printed.
Each stall warning results in another pass through the loop, but the
second and subsequent passes use longer stall times.
<h3><a name="Mid-Boot Operation">Mid-boot operation</a></h3>
<p>
The use of workqueues has the advantage that the expedited
grace-period code need not worry about POSIX signals.
Unfortunately, it has the
corresponding disadvantage that workqueues cannot be used until
they are initialized, which does not happen until some time after
the scheduler spawns the first task.
Given that there are parts of the kernel that really do want to
execute grace periods during this mid-boot &ldquo;dead zone&rdquo;,
expedited grace periods must do something else during thie time.
<p>
What they do is to fall back to the old practice of requiring that the
requesting task drive the expedited grace period, as was the case
before the use of workqueues.
However, the requesting task is only required to drive the grace period
during the mid-boot dead zone.
Before mid-boot, a synchronous grace period is a no-op.
Some time after mid-boot, workqueues are used.
<p>
Non-expedited non-SRCU synchronous grace periods must also operate
normally during mid-boot.
This is handled by causing non-expedited grace periods to take the
expedited code path during mid-boot.
<p>
The current code assumes that there are no POSIX signals during
the mid-boot dead zone.
However, if an overwhelming need for POSIX signals somehow arises,
appropriate adjustments can be made to the expedited stall-warning code.
One such adjustment would reinstate the pre-workqueue stall-warning
checks, but only during the mid-boot dead zone.
<p>
With this refinement, synchronous grace periods can now be used from
task context pretty much any time during the life of the kernel.
<h3><a name="Summary">
Summary</a></h3>

195
Documentation/RCU/Design/Requirements/Requirements.html
View File

@ -659,8 +659,9 @@ systems with more than one CPU:
In other words, a given instance of <tt>synchronize_rcu()</tt>
can avoid waiting on a given RCU read-side critical section only
if it can prove that <tt>synchronize_rcu()</tt> started first.
</font>
<p>
<p><font color="ffffff">
A related question is &ldquo;When <tt>rcu_read_lock()</tt>
doesn't generate any code, why does it matter how it relates
to a grace period?&rdquo;
@ -675,8 +676,9 @@ systems with more than one CPU:
within the critical section, in which case none of the accesses
within the critical section may observe the effects of any
access following the grace period.
</font>
<p>
<p><font color="ffffff">
As of late 2016, mathematical models of RCU take this
viewpoint, for example, see slides&nbsp;62 and&nbsp;63
of the
@ -1616,8 +1618,8 @@ CPUs should at least make reasonable forward progress.
In return for its shorter latencies, <tt>synchronize_rcu_expedited()</tt>
is permitted to impose modest degradation of real-time latency
on non-idle online CPUs.
That said, it will likely be necessary to take further steps to reduce this
degradation, hopefully to roughly that of a scheduling-clock interrupt.
Here, &ldquo;modest&rdquo; means roughly the same latency
degradation as a scheduling-clock interrupt.
<p>
There are a number of situations where even
@ -1913,12 +1915,9 @@ This requirement is another factor driving batching of grace periods,
but it is also the driving force behind the checks for large numbers
of queued RCU callbacks in the <tt>call_rcu()</tt> code path.
Finally, high update rates should not delay RCU read-side critical
sections, although some read-side delays can occur when using
sections, although some small read-side delays can occur when using
<tt>synchronize_rcu_expedited()</tt>, courtesy of this function's use
of <tt>try_stop_cpus()</tt>.
(In the future, <tt>synchronize_rcu_expedited()</tt> will be
converted to use lighter-weight inter-processor interrupts (IPIs),
but this will still disturb readers, though to a much smaller degree.)
of <tt>smp_call_function_single()</tt>.
<p>
Although all three of these corner cases were understood in the early
@ -2154,7 +2153,8 @@ as will <tt>rcu_assign_pointer()</tt>.
<p>
Although <tt>call_rcu()</tt> may be invoked at any
time during boot, callbacks are not guaranteed to be invoked until after
the scheduler is fully up and running.
all of RCU's kthreads have been spawned, which occurs at
<tt>early_initcall()</tt> time.
This delay in callback invocation is due to the fact that RCU does not
invoke callbacks until it is fully initialized, and this full initialization
cannot occur until after the scheduler has initialized itself to the
@ -2167,8 +2167,10 @@ on what operations those callbacks could invoke.
Perhaps surprisingly, <tt>synchronize_rcu()</tt>,
<a href="#Bottom-Half Flavor"><tt>synchronize_rcu_bh()</tt></a>
(<a href="#Bottom-Half Flavor">discussed below</a>),
and
<a href="#Sched Flavor"><tt>synchronize_sched()</tt></a>
<a href="#Sched Flavor"><tt>synchronize_sched()</tt></a>,
<tt>synchronize_rcu_expedited()</tt>,
<tt>synchronize_rcu_bh_expedited()</tt>, and
<tt>synchronize_sched_expedited()</tt>
will all operate normally
during very early boot, the reason being that there is only one CPU
and preemption is disabled.
@ -2178,45 +2180,59 @@ state and thus a grace period, so the early-boot implementation can
be a no-op.
<p>
Both <tt>synchronize_rcu_bh()</tt> and <tt>synchronize_sched()</tt>
continue to operate normally through the remainder of boot, courtesy
of the fact that preemption is disabled across their RCU read-side
critical sections and also courtesy of the fact that there is still
only one CPU.
However, once the scheduler starts initializing, preemption is enabled.
There is still only a single CPU, but the fact that preemption is enabled
means that the no-op implementation of <tt>synchronize_rcu()</tt> no
longer works in <tt>CONFIG_PREEMPT=y</tt> kernels.
Therefore, as soon as the scheduler starts initializing, the early-boot
fastpath is disabled.
This means that <tt>synchronize_rcu()</tt> switches to its runtime
mode of operation where it posts callbacks, which in turn means that
any call to <tt>synchronize_rcu()</tt> will block until the corresponding
callback is invoked.
Unfortunately, the callback cannot be invoked until RCU's runtime
grace-period machinery is up and running, which cannot happen until
the scheduler has initialized itself sufficiently to allow RCU's
kthreads to be spawned.
Therefore, invoking <tt>synchronize_rcu()</tt> during scheduler
initialization can result in deadlock.
However, once the scheduler has spawned its first kthread, this early
boot trick fails for <tt>synchronize_rcu()</tt> (as well as for
<tt>synchronize_rcu_expedited()</tt>) in <tt>CONFIG_PREEMPT=y</tt>
kernels.
The reason is that an RCU read-side critical section might be preempted,
which means that a subsequent <tt>synchronize_rcu()</tt> really does have
to wait for something, as opposed to simply returning immediately.
Unfortunately, <tt>synchronize_rcu()</tt> can't do this until all of
its kthreads are spawned, which doesn't happen until some time during
<tt>early_initcalls()</tt> time.
But this is no excuse: RCU is nevertheless required to correctly handle
synchronous grace periods during this time period.
Once all of its kthreads are up and running, RCU starts running
normally.
<table>
<tr><th>&nbsp;</th></tr>
<tr><th align="left">Quick Quiz:</th></tr>
<tr><td>
So what happens with <tt>synchronize_rcu()</tt> during
scheduler initialization for <tt>CONFIG_PREEMPT=n</tt>
kernels?
How can RCU possibly handle grace periods before all of its
kthreads have been spawned???
</td></tr>
<tr><th align="left">Answer:</th></tr>
<tr><td bgcolor="#ffffff"><font color="ffffff">
In <tt>CONFIG_PREEMPT=n</tt> kernel, <tt>synchronize_rcu()</tt>
maps directly to <tt>synchronize_sched()</tt>.
Therefore, <tt>synchronize_rcu()</tt> works normally throughout
boot in <tt>CONFIG_PREEMPT=n</tt> kernels.
However, your code must also work in <tt>CONFIG_PREEMPT=y</tt> kernels,
so it is still necessary to avoid invoking <tt>synchronize_rcu()</tt>
during scheduler initialization.
Very carefully!
</font>
<p><font color="ffffff">
During the &ldquo;dead zone&rdquo; between the time that the
scheduler spawns the first task and the time that all of RCU's
kthreads have been spawned, all synchronous grace periods are
handled by the expedited grace-period mechanism.
At runtime, this expedited mechanism relies on workqueues, but
during the dead zone the requesting task itself drives the
desired expedited grace period.
Because dead-zone execution takes place within task context,
everything works.
Once the dead zone ends, expedited grace periods go back to
using workqueues, as is required to avoid problems that would
otherwise occur when a user task received a POSIX signal while
driving an expedited grace period.
</font>
<p><font color="ffffff">
And yes, this does mean that it is unhelpful to send POSIX
signals to random tasks between the time that the scheduler
spawns its first kthread and the time that RCU's kthreads
have all been spawned.
If there ever turns out to be a good reason for sending POSIX
signals during that time, appropriate adjustments will be made.
(If it turns out that POSIX signals are sent during this time for
no good reason, other adjustments will be made, appropriate
or otherwise.)
</font></td></tr>
<tr><td>&nbsp;</td></tr>
</table>
@ -2295,12 +2311,61 @@ situation, and Dipankar Sarma incorporated <tt>rcu_barrier()</tt> into RCU.
The need for <tt>rcu_barrier()</tt> for module unloading became
apparent later.
<p>
<b>Important note</b>: The <tt>rcu_barrier()</tt> function is not,
repeat, <i>not</i>, obligated to wait for a grace period.
It is instead only required to wait for RCU callbacks that have
already been posted.
Therefore, if there are no RCU callbacks posted anywhere in the system,
<tt>rcu_barrier()</tt> is within its rights to return immediately.
Even if there are callbacks posted, <tt>rcu_barrier()</tt> does not
necessarily need to wait for a grace period.
<table>
<tr><th>&nbsp;</th></tr>
<tr><th align="left">Quick Quiz:</th></tr>
<tr><td>
Wait a minute!
Each RCU callbacks must wait for a grace period to complete,
and <tt>rcu_barrier()</tt> must wait for each pre-existing
callback to be invoked.
Doesn't <tt>rcu_barrier()</tt> therefore need to wait for
a full grace period if there is even one callback posted anywhere
in the system?
</td></tr>
<tr><th align="left">Answer:</th></tr>
<tr><td bgcolor="#ffffff"><font color="ffffff">
Absolutely not!!!
</font>
<p><font color="ffffff">
Yes, each RCU callbacks must wait for a grace period to complete,
but it might well be partly (or even completely) finished waiting
by the time <tt>rcu_barrier()</tt> is invoked.
In that case, <tt>rcu_barrier()</tt> need only wait for the
remaining portion of the grace period to elapse.
So even if there are quite a few callbacks posted,
<tt>rcu_barrier()</tt> might well return quite quickly.
</font>
<p><font color="ffffff">
So if you need to wait for a grace period as well as for all
pre-existing callbacks, you will need to invoke both
<tt>synchronize_rcu()</tt> and <tt>rcu_barrier()</tt>.
If latency is a concern, you can always use workqueues
to invoke them concurrently.
</font></td></tr>
<tr><td>&nbsp;</td></tr>
</table>
<h3><a name="Hotplug CPU">Hotplug CPU</a></h3>
<p>
The Linux kernel supports CPU hotplug, which means that CPUs
can come and go.
It is of course illegal to use any RCU API member from an offline CPU.
It is of course illegal to use any RCU API member from an offline CPU,
with the exception of <a href="#Sleepable RCU">SRCU</a> read-side
critical sections.
This requirement was present from day one in DYNIX/ptx, but
on the other hand, the Linux kernel's CPU-hotplug implementation
is &ldquo;interesting.&rdquo;
@ -2310,19 +2375,18 @@ The Linux-kernel CPU-hotplug implementation has notifiers that
are used to allow the various kernel subsystems (including RCU)
to respond appropriately to a given CPU-hotplug operation.
Most RCU operations may be invoked from CPU-hotplug notifiers,
including even normal synchronous grace-period operations
such as <tt>synchronize_rcu()</tt>.
However, expedited grace-period operations such as
<tt>synchronize_rcu_expedited()</tt> are not supported,
due to the fact that current implementations block CPU-hotplug
operations, which could result in deadlock.
including even synchronous grace-period operations such as
<tt>synchronize_rcu()</tt> and <tt>synchronize_rcu_expedited()</tt>.
<p>
In addition, all-callback-wait operations such as
However, all-callback-wait operations such as
<tt>rcu_barrier()</tt> are also not supported, due to the
fact that there are phases of CPU-hotplug operations where
the outgoing CPU's callbacks will not be invoked until after
the CPU-hotplug operation ends, which could also result in deadlock.
Furthermore, <tt>rcu_barrier()</tt> blocks CPU-hotplug operations
during its execution, which results in another type of deadlock
when invoked from a CPU-hotplug notifier.
<h3><a name="Scheduler and RCU">Scheduler and RCU</a></h3>
@ -2863,6 +2927,27 @@ It also motivates the <tt>smp_mb__after_srcu_read_unlock()</tt>
API, which, in combination with <tt>srcu_read_unlock()</tt>,
guarantees a full memory barrier.
<p>
Also unlike other RCU flavors, SRCU's callbacks-wait function
<tt>srcu_barrier()</tt> may be invoked from CPU-hotplug notifiers,
though this is not necessarily a good idea.
The reason that this is possible is that SRCU is insensitive
to whether or not a CPU is online, which means that <tt>srcu_barrier()</tt>
need not exclude CPU-hotplug operations.
<p>
As of v4.12, SRCU's callbacks are maintained per-CPU, eliminating
a locking bottleneck present in prior kernel versions.
Although this will allow users to put much heavier stress on
<tt>call_srcu()</tt>, it is important to note that SRCU does not
yet take any special steps to deal with callback flooding.
So if you are posting (say) 10,000 SRCU callbacks per second per CPU,
you are probably totally OK, but if you intend to post (say) 1,000,000
SRCU callbacks per second per CPU, please run some tests first.
SRCU just might need a few adjustment to deal with that sort of load.
Of course, your mileage may vary based on the speed of your CPUs and
the size of your memory.
<p>
The
<a href="https://lwn.net/Articles/609973/#RCU Per-Flavor API Table">SRCU API</a>
@ -3021,8 +3106,8 @@ to do some redesign to avoid this scalability problem.
<p>
RCU disables CPU hotplug in a few places, perhaps most notably in the
expedited grace-period and <tt>rcu_barrier()</tt> operations.
If there is a strong reason to use expedited grace periods in CPU-hotplug
<tt>rcu_barrier()</tt> operations.
If there is a strong reason to use <tt>rcu_barrier()</tt> in CPU-hotplug
notifiers, it will be necessary to avoid disabling CPU hotplug.
This would introduce some complexity, so there had better be a <i>very</i>
good reason.
@ -3096,9 +3181,5 @@ Andy Lutomirski for their help in rendering
this article human readable, and to Michelle Rankin for her support
of this effort.
Other contributions are acknowledged in the Linux kernel's git archive.
The cartoon is copyright (c) 2013 by Melissa Broussard,
and is provided
under the terms of the Creative Commons Attribution-Share Alike 3.0
United States license.
</body></html>

9
Documentation/RCU/rcu_dereference.txt
View File

@ -138,6 +138,15 @@ o Be very careful about comparing pointers obtained from
This sort of comparison occurs frequently when scanning
RCU-protected circular linked lists.
Note that if checks for being within an RCU read-side
critical section are not required and the pointer is never
dereferenced, rcu_access_pointer() should be used in place
of rcu_dereference(). The rcu_access_pointer() primitive
does not require an enclosing read-side critical section,
and also omits the smp_read_barrier_depends() included in
rcu_dereference(), which in turn should provide a small
performance gain in some CPUs (e.g., the DEC Alpha).
o The comparison is against a pointer that references memory
that was initialized "a long time ago." The reason
this is safe is that even if misordering occurs, the

6
Documentation/RCU/rculist_nulls.txt
View File

@ -1,5 +1,5 @@
Using hlist_nulls to protect read-mostly linked lists and
objects using SLAB_DESTROY_BY_RCU allocations.
objects using SLAB_TYPESAFE_BY_RCU allocations.
Please read the basics in Documentation/RCU/listRCU.txt
@ -7,7 +7,7 @@ Using special makers (called 'nulls') is a convenient way
to solve following problem :
A typical RCU linked list managing objects which are
allocated with SLAB_DESTROY_BY_RCU kmem_cache can
allocated with SLAB_TYPESAFE_BY_RCU kmem_cache can
use following algos :
1) Lookup algo
@ -96,7 +96,7 @@ unlock_chain(); // typically a spin_unlock()
3) Remove algo
--------------
Nothing special here, we can use a standard RCU hlist deletion.
But thanks to SLAB_DESTROY_BY_RCU, beware a deleted object can be reused
But thanks to SLAB_TYPESAFE_BY_RCU, beware a deleted object can be reused
very very fast (before the end of RCU grace period)
if (put_last_reference_on(obj) {

190
Documentation/RCU/stallwarn.txt
View File

@ -1,9 +1,102 @@
Using RCU's CPU Stall Detector
The rcu_cpu_stall_suppress module parameter enables RCU's CPU stall
detector, which detects conditions that unduly delay RCU grace periods.
This module parameter enables CPU stall detection by default, but
may be overridden via boot-time parameter or at runtime via sysfs.
This document first discusses what sorts of issues RCU's CPU stall
detector can locate, and then discusses kernel parameters and Kconfig
options that can be used to fine-tune the detector's operation. Finally,
this document explains the stall detector's "splat" format.
What Causes RCU CPU Stall Warnings?
So your kernel printed an RCU CPU stall warning. The next question is
"What caused it?" The following problems can result in RCU CPU stall
warnings:
o A CPU looping in an RCU read-side critical section.
o A CPU looping with interrupts disabled.
o A CPU looping with preemption disabled. This condition can
result in RCU-sched stalls and, if ksoftirqd is in use, RCU-bh
stalls.
o A CPU looping with bottom halves disabled. This condition can
result in RCU-sched and RCU-bh stalls.
o For !CONFIG_PREEMPT kernels, a CPU looping anywhere in the
kernel without invoking schedule(). Note that cond_resched()
does not necessarily prevent RCU CPU stall warnings. Therefore,
if the looping in the kernel is really expected and desirable
behavior, you might need to replace some of the cond_resched()
calls with calls to cond_resched_rcu_qs().
o Booting Linux using a console connection that is too slow to
keep up with the boot-time console-message rate. For example,
a 115Kbaud serial console can be -way- too slow to keep up
with boot-time message rates, and will frequently result in
RCU CPU stall warning messages. Especially if you have added
debug printk()s.
o Anything that prevents RCU's grace-period kthreads from running.
This can result in the "All QSes seen" console-log message.
This message will include information on when the kthread last
ran and how often it should be expected to run.
o A CPU-bound real-time task in a CONFIG_PREEMPT kernel, which might
happen to preempt a low-priority task in the middle of an RCU
read-side critical section. This is especially damaging if
that low-priority task is not permitted to run on any other CPU,
in which case the next RCU grace period can never complete, which
will eventually cause the system to run out of memory and hang.
While the system is in the process of running itself out of
memory, you might see stall-warning messages.
o A CPU-bound real-time task in a CONFIG_PREEMPT_RT kernel that
is running at a higher priority than the RCU softirq threads.
This will prevent RCU callbacks from ever being invoked,
and in a CONFIG_PREEMPT_RCU kernel will further prevent
RCU grace periods from ever completing. Either way, the
system will eventually run out of memory and hang. In the
CONFIG_PREEMPT_RCU case, you might see stall-warning
messages.
o A hardware or software issue shuts off the scheduler-clock
interrupt on a CPU that is not in dyntick-idle mode. This
problem really has happened, and seems to be most likely to
result in RCU CPU stall warnings for CONFIG_NO_HZ_COMMON=n kernels.
o A bug in the RCU implementation.
o A hardware failure. This is quite unlikely, but has occurred
at least once in real life. A CPU failed in a running system,
becoming unresponsive, but not causing an immediate crash.
This resulted in a series of RCU CPU stall warnings, eventually
leading the realization that the CPU had failed.
The RCU, RCU-sched, RCU-bh, and RCU-tasks implementations have CPU stall
warning. Note that SRCU does -not- have CPU stall warnings. Please note
that RCU only detects CPU stalls when there is a grace period in progress.
No grace period, no CPU stall warnings.
To diagnose the cause of the stall, inspect the stack traces.
The offending function will usually be near the top of the stack.
If you have a series of stall warnings from a single extended stall,
comparing the stack traces can often help determine where the stall
is occurring, which will usually be in the function nearest the top of
that portion of the stack which remains the same from trace to trace.
If you can reliably trigger the stall, ftrace can be quite helpful.
RCU bugs can often be debugged with the help of CONFIG_RCU_TRACE
and with RCU's event tracing. For information on RCU's event tracing,
see include/trace/events/rcu.h.
Fine-Tuning the RCU CPU Stall Detector
The rcuupdate.rcu_cpu_stall_suppress module parameter disables RCU's
CPU stall detector, which detects conditions that unduly delay RCU grace
periods. This module parameter enables CPU stall detection by default,
but may be overridden via boot-time parameter or at runtime via sysfs.
The stall detector's idea of what constitutes "unduly delayed" is
controlled by a set of kernel configuration variables and cpp macros:
@ -56,6 +149,9 @@ rcupdate.rcu_task_stall_timeout
And continues with the output of sched_show_task() for each
task stalling the current RCU-tasks grace period.
Interpreting RCU's CPU Stall-Detector "Splats"
For non-RCU-tasks flavors of RCU, when a CPU detects that it is stalling,
it will print a message similar to the following:
@ -178,89 +274,3 @@ grace period is in flight.
It is entirely possible to see stall warnings from normal and from
expedited grace periods at about the same time from the same run.
What Causes RCU CPU Stall Warnings?
So your kernel printed an RCU CPU stall warning. The next question is
"What caused it?" The following problems can result in RCU CPU stall
warnings:
o A CPU looping in an RCU read-side critical section.
o A CPU looping with interrupts disabled. This condition can
result in RCU-sched and RCU-bh stalls.
o A CPU looping with preemption disabled. This condition can
result in RCU-sched stalls and, if ksoftirqd is in use, RCU-bh
stalls.
o A CPU looping with bottom halves disabled. This condition can
result in RCU-sched and RCU-bh stalls.
o For !CONFIG_PREEMPT kernels, a CPU looping anywhere in the
kernel without invoking schedule(). Note that cond_resched()
does not necessarily prevent RCU CPU stall warnings. Therefore,
if the looping in the kernel is really expected and desirable
behavior, you might need to replace some of the cond_resched()
calls with calls to cond_resched_rcu_qs().
o Booting Linux using a console connection that is too slow to
keep up with the boot-time console-message rate. For example,
a 115Kbaud serial console can be -way- too slow to keep up
with boot-time message rates, and will frequently result in
RCU CPU stall warning messages. Especially if you have added
debug printk()s.
o Anything that prevents RCU's grace-period kthreads from running.
This can result in the "All QSes seen" console-log message.
This message will include information on when the kthread last
ran and how often it should be expected to run.
o A CPU-bound real-time task in a CONFIG_PREEMPT kernel, which might
happen to preempt a low-priority task in the middle of an RCU
read-side critical section. This is especially damaging if
that low-priority task is not permitted to run on any other CPU,
in which case the next RCU grace period can never complete, which
will eventually cause the system to run out of memory and hang.
While the system is in the process of running itself out of
memory, you might see stall-warning messages.
o A CPU-bound real-time task in a CONFIG_PREEMPT_RT kernel that
is running at a higher priority than the RCU softirq threads.
This will prevent RCU callbacks from ever being invoked,
and in a CONFIG_PREEMPT_RCU kernel will further prevent
RCU grace periods from ever completing. Either way, the
system will eventually run out of memory and hang. In the
CONFIG_PREEMPT_RCU case, you might see stall-warning
messages.
o A hardware or software issue shuts off the scheduler-clock
interrupt on a CPU that is not in dyntick-idle mode. This
problem really has happened, and seems to be most likely to
result in RCU CPU stall warnings for CONFIG_NO_HZ_COMMON=n kernels.
o A bug in the RCU implementation.
o A hardware failure. This is quite unlikely, but has occurred
at least once in real life. A CPU failed in a running system,
becoming unresponsive, but not causing an immediate crash.
This resulted in a series of RCU CPU stall warnings, eventually
leading the realization that the CPU had failed.
The RCU, RCU-sched, RCU-bh, and RCU-tasks implementations have CPU stall
warning. Note that SRCU does -not- have CPU stall warnings. Please note
that RCU only detects CPU stalls when there is a grace period in progress.
No grace period, no CPU stall warnings.
To diagnose the cause of the stall, inspect the stack traces.
The offending function will usually be near the top of the stack.
If you have a series of stall warnings from a single extended stall,
comparing the stack traces can often help determine where the stall
is occurring, which will usually be in the function nearest the top of
that portion of the stack which remains the same from trace to trace.
If you can reliably trigger the stall, ftrace can be quite helpful.
RCU bugs can often be debugged with the help of CONFIG_RCU_TRACE
and with RCU's event tracing. For information on RCU's event tracing,
see include/trace/events/rcu.h.

32
Documentation/RCU/whatisRCU.txt
View File

@ -562,7 +562,9 @@ This section presents a "toy" RCU implementation that is based on
familiar locking primitives. Its overhead makes it a non-starter for
real-life use, as does its lack of scalability. It is also unsuitable
for realtime use, since it allows scheduling latency to "bleed" from
one read-side critical section to another.
one read-side critical section to another. It also assumes recursive
reader-writer locks: If you try this with non-recursive locks, and
you allow nested rcu_read_lock() calls, you can deadlock.
However, it is probably the easiest implementation to relate to, so is
a good starting point.
@ -587,20 +589,21 @@ It is extremely simple:
write_unlock(&rcu_gp_mutex);
}
[You can ignore rcu_assign_pointer() and rcu_dereference() without
missing much. But here they are anyway. And whatever you do, don't
forget about them when submitting patches making use of RCU!]
[You can ignore rcu_assign_pointer() and rcu_dereference() without missing
much. But here are simplified versions anyway. And whatever you do,
don't forget about them when submitting patches making use of RCU!]
#define rcu_assign_pointer(p, v) ({ \
smp_wmb(); \
(p) = (v); \
})
#define rcu_assign_pointer(p, v) \
({ \
smp_store_release(&(p), (v)); \
})
#define rcu_dereference(p) ({ \
typeof(p) _________p1 = p; \
smp_read_barrier_depends(); \
(_________p1); \
})
#define rcu_dereference(p) \
({ \
typeof(p) _________p1 = p; \
smp_read_barrier_depends(); \
(_________p1); \
})
The rcu_read_lock() and rcu_read_unlock() primitive read-acquire
@ -925,7 +928,8 @@ d. Do you need RCU grace periods to complete even in the face
e. Is your workload too update-intensive for normal use of
RCU, but inappropriate for other synchronization mechanisms?
If so, consider SLAB_DESTROY_BY_RCU. But please be careful!
If so, consider SLAB_TYPESAFE_BY_RCU (which was originally
named SLAB_DESTROY_BY_RCU). But please be careful!
f. Do you need read-side critical sections that are respected
even though they are in the middle of the idle loop, during

2
Documentation/memory-barriers.txt
View File

@ -768,7 +768,7 @@ equal to zero, in which case the compiler is within its rights to
transform the above code into the following:
q = READ_ONCE(a);
WRITE_ONCE(b, 1);
WRITE_ONCE(b, 2);
do_something_else();
Given this transformation, the CPU is not required to respect the ordering

3
arch/Kconfig
View File

@ -320,6 +320,9 @@ config HAVE_CMPXCHG_LOCAL
config HAVE_CMPXCHG_DOUBLE
bool
config ARCH_WEAK_RELEASE_ACQUIRE
bool
config ARCH_WANT_IPC_PARSE_VERSION
bool

1
arch/powerpc/Kconfig
View File

@ -99,6 +99,7 @@ config PPC
select ARCH_USE_BUILTIN_BSWAP
select ARCH_USE_CMPXCHG_LOCKREF if PPC64
select ARCH_WANT_IPC_PARSE_VERSION
select ARCH_WEAK_RELEASE_ACQUIRE
select BINFMT_ELF
select BUILDTIME_EXTABLE_SORT
select CLONE_BACKWARDS

2
drivers/gpu/drm/i915/i915_gem.c
View File

@ -4665,7 +4665,7 @@ i915_gem_load_init(struct drm_i915_private *dev_priv)
dev_priv->requests = KMEM_CACHE(drm_i915_gem_request,
SLAB_HWCACHE_ALIGN |
SLAB_RECLAIM_ACCOUNT |
SLAB_DESTROY_BY_RCU);
SLAB_TYPESAFE_BY_RCU);
if (!dev_priv->requests)
goto err_vmas;

2
drivers/gpu/drm/i915/i915_gem_request.h
View File

@ -493,7 +493,7 @@ static inline struct drm_i915_gem_request *
__i915_gem_active_get_rcu(const struct i915_gem_active *active)
{
/* Performing a lockless retrieval of the active request is super
* tricky. SLAB_DESTROY_BY_RCU merely guarantees that the backing
* tricky. SLAB_TYPESAFE_BY_RCU merely guarantees that the backing
* slab of request objects will not be freed whilst we hold the
* RCU read lock. It does not guarantee that the request itself
* will not be freed and then *reused*. Viz,

2
drivers/staging/lustre/lustre/ldlm/ldlm_lockd.c
View File

@ -1071,7 +1071,7 @@ int ldlm_init(void)
ldlm_lock_slab = kmem_cache_create("ldlm_locks",
sizeof(struct ldlm_lock), 0,
SLAB_HWCACHE_ALIGN |
SLAB_DESTROY_BY_RCU, NULL);
SLAB_TYPESAFE_BY_RCU, NULL);
if (!ldlm_lock_slab) {
kmem_cache_destroy(ldlm_resource_slab);
return -ENOMEM;

2
fs/jbd2/journal.c
View File

@ -2340,7 +2340,7 @@ static int jbd2_journal_init_journal_head_cache(void)
jbd2_journal_head_cache = kmem_cache_create("jbd2_journal_head",
sizeof(struct journal_head),
0, /* offset */
SLAB_TEMPORARY | SLAB_DESTROY_BY_RCU,
SLAB_TEMPORARY | SLAB_TYPESAFE_BY_RCU,
NULL); /* ctor */
retval = 0;
if (!jbd2_journal_head_cache) {

2
fs/signalfd.c
View File

@ -38,7 +38,7 @@ void signalfd_cleanup(struct sighand_struct *sighand)
/*
* The lockless check can race with remove_wait_queue() in progress,
* but in this case its caller should run under rcu_read_lock() and
* sighand_cachep is SLAB_DESTROY_BY_RCU, we can safely return.
* sighand_cachep is SLAB_TYPESAFE_BY_RCU, we can safely return.
*/
if (likely(!waitqueue_active(wqh)))
return;

4
include/linux/dma-fence.h
View File

@ -229,7 +229,7 @@ static inline struct dma_fence *dma_fence_get_rcu(struct dma_fence *fence)
*
* Function returns NULL if no refcount could be obtained, or the fence.
* This function handles acquiring a reference to a fence that may be
* reallocated within the RCU grace period (such as with SLAB_DESTROY_BY_RCU),
* reallocated within the RCU grace period (such as with SLAB_TYPESAFE_BY_RCU),
* so long as the caller is using RCU on the pointer to the fence.
*
* An alternative mechanism is to employ a seqlock to protect a bunch of
@ -257,7 +257,7 @@ dma_fence_get_rcu_safe(struct dma_fence * __rcu *fencep)
* have successfully acquire a reference to it. If it no
* longer matches, we are holding a reference to some other
* reallocated pointer. This is possible if the allocator
* is using a freelist like SLAB_DESTROY_BY_RCU where the
* is using a freelist like SLAB_TYPESAFE_BY_RCU where the
* fence remains valid for the RCU grace period, but it
* may be reallocated. When using such allocators, we are
* responsible for ensuring the reference we get is to

4
include/linux/kvm_host.h
View File

@ -375,8 +375,6 @@ struct kvm {
struct mutex slots_lock;
struct mm_struct *mm; /* userspace tied to this vm */
struct kvm_memslots *memslots[KVM_ADDRESS_SPACE_NUM];
struct srcu_struct srcu;
struct srcu_struct irq_srcu;
struct kvm_vcpu *vcpus[KVM_MAX_VCPUS];
/*
@ -429,6 +427,8 @@ struct kvm {
struct list_head devices;
struct dentry *debugfs_dentry;
struct kvm_stat_data **debugfs_stat_data;
struct srcu_struct srcu;
struct srcu_struct irq_srcu;
};
#define kvm_err(fmt, ...) \

99
include/linux/rcu_node_tree.h Normal file
View File

@ -0,0 +1,99 @@
/*
* RCU node combining tree definitions. These are used to compute
* global attributes while avoiding common-case global contention. A key
* property that these computations rely on is a tournament-style approach
* where only one of the tasks contending a lower level in the tree need
* advance to the next higher level. If properly configured, this allows
* unlimited scalability while maintaining a constant level of contention
* on the root node.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, you can access it online at
* http://www.gnu.org/licenses/gpl-2.0.html.
*
* Copyright IBM Corporation, 2017
*
* Author: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
*/
#ifndef __LINUX_RCU_NODE_TREE_H
#define __LINUX_RCU_NODE_TREE_H
/*
* Define shape of hierarchy based on NR_CPUS, CONFIG_RCU_FANOUT, and
* CONFIG_RCU_FANOUT_LEAF.
* In theory, it should be possible to add more levels straightforwardly.
* In practice, this did work well going from three levels to four.
* Of course, your mileage may vary.
*/
#ifdef CONFIG_RCU_FANOUT
#define RCU_FANOUT CONFIG_RCU_FANOUT
#else /* #ifdef CONFIG_RCU_FANOUT */
# ifdef CONFIG_64BIT
# define RCU_FANOUT 64
# else
# define RCU_FANOUT 32
# endif
#endif /* #else #ifdef CONFIG_RCU_FANOUT */
#ifdef CONFIG_RCU_FANOUT_LEAF
#define RCU_FANOUT_LEAF CONFIG_RCU_FANOUT_LEAF
#else /* #ifdef CONFIG_RCU_FANOUT_LEAF */
#define RCU_FANOUT_LEAF 16
#endif /* #else #ifdef CONFIG_RCU_FANOUT_LEAF */
#define RCU_FANOUT_1 (RCU_FANOUT_LEAF)
#define RCU_FANOUT_2 (RCU_FANOUT_1 * RCU_FANOUT)
#define RCU_FANOUT_3 (RCU_FANOUT_2 * RCU_FANOUT)
#define RCU_FANOUT_4 (RCU_FANOUT_3 * RCU_FANOUT)
#if NR_CPUS <= RCU_FANOUT_1
# define RCU_NUM_LVLS 1
# define NUM_RCU_LVL_0 1
# define NUM_RCU_NODES NUM_RCU_LVL_0
# define NUM_RCU_LVL_INIT { NUM_RCU_LVL_0 }
# define RCU_NODE_NAME_INIT { "rcu_node_0" }
# define RCU_FQS_NAME_INIT { "rcu_node_fqs_0" }
#elif NR_CPUS <= RCU_FANOUT_2
# define RCU_NUM_LVLS 2
# define NUM_RCU_LVL_0 1
# define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_1)
# define NUM_RCU_NODES (NUM_RCU_LVL_0 + NUM_RCU_LVL_1)
# define NUM_RCU_LVL_INIT { NUM_RCU_LVL_0, NUM_RCU_LVL_1 }
# define RCU_NODE_NAME_INIT { "rcu_node_0", "rcu_node_1" }
# define RCU_FQS_NAME_INIT { "rcu_node_fqs_0", "rcu_node_fqs_1" }
#elif NR_CPUS <= RCU_FANOUT_3
# define RCU_NUM_LVLS 3
# define NUM_RCU_LVL_0 1
# define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_2)
# define NUM_RCU_LVL_2 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_1)
# define NUM_RCU_NODES (NUM_RCU_LVL_0 + NUM_RCU_LVL_1 + NUM_RCU_LVL_2)
# define NUM_RCU_LVL_INIT { NUM_RCU_LVL_0, NUM_RCU_LVL_1, NUM_RCU_LVL_2 }
# define RCU_NODE_NAME_INIT { "rcu_node_0", "rcu_node_1", "rcu_node_2" }
# define RCU_FQS_NAME_INIT { "rcu_node_fqs_0", "rcu_node_fqs_1", "rcu_node_fqs_2" }
#elif NR_CPUS <= RCU_FANOUT_4
# define RCU_NUM_LVLS 4
# define NUM_RCU_LVL_0 1
# define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_3)
# define NUM_RCU_LVL_2 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_2)
# define NUM_RCU_LVL_3 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_1)
# define NUM_RCU_NODES (NUM_RCU_LVL_0 + NUM_RCU_LVL_1 + NUM_RCU_LVL_2 + NUM_RCU_LVL_3)
# define NUM_RCU_LVL_INIT { NUM_RCU_LVL_0, NUM_RCU_LVL_1, NUM_RCU_LVL_2, NUM_RCU_LVL_3 }
# define RCU_NODE_NAME_INIT { "rcu_node_0", "rcu_node_1", "rcu_node_2", "rcu_node_3" }
# define RCU_FQS_NAME_INIT { "rcu_node_fqs_0", "rcu_node_fqs_1", "rcu_node_fqs_2", "rcu_node_fqs_3" }
#else
# error "CONFIG_RCU_FANOUT insufficient for NR_CPUS"
#endif /* #if (NR_CPUS) <= RCU_FANOUT_1 */
#endif /* __LINUX_RCU_NODE_TREE_H */

712
include/linux/rcu_segcblist.h Normal file
View File

@ -0,0 +1,712 @@
/*
* RCU segmented callback lists
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, you can access it online at
* http://www.gnu.org/licenses/gpl-2.0.html.
*
* Copyright IBM Corporation, 2017
*
* Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
*/
#ifndef __KERNEL_RCU_SEGCBLIST_H
#define __KERNEL_RCU_SEGCBLIST_H
/* Simple unsegmented callback lists. */
struct rcu_cblist {
struct rcu_head *head;
struct rcu_head **tail;
long len;
long len_lazy;
};
#define RCU_CBLIST_INITIALIZER(n) { .head = NULL, .tail = &n.head }
/* Initialize simple callback list. */
static inline void rcu_cblist_init(struct rcu_cblist *rclp)
{
rclp->head = NULL;
rclp->tail = &rclp->head;
rclp->len = 0;
rclp->len_lazy = 0;
}
/* Is simple callback list empty? */
static inline bool rcu_cblist_empty(struct rcu_cblist *rclp)
{
return !rclp->head;
}
/* Return number of callbacks in simple callback list. */
static inline long rcu_cblist_n_cbs(struct rcu_cblist *rclp)
{
return rclp->len;
}
/* Return number of lazy callbacks in simple callback list. */
static inline long rcu_cblist_n_lazy_cbs(struct rcu_cblist *rclp)
{
return rclp->len_lazy;
}
/*
* Debug function to actually count the number of callbacks.
* If the number exceeds the limit specified, return -1.
*/
static inline long rcu_cblist_count_cbs(struct rcu_cblist *rclp, long lim)
{
int cnt = 0;
struct rcu_head **rhpp = &rclp->head;
for (;;) {
if (!*rhpp)
return cnt;
if (++cnt > lim)
return -1;
rhpp = &(*rhpp)->next;
}
}
/*
* Dequeue the oldest rcu_head structure from the specified callback
* list. This function assumes that the callback is non-lazy, but
* the caller can later invoke rcu_cblist_dequeued_lazy() if it
* finds otherwise (and if it cares about laziness). This allows
* different users to have different ways of determining laziness.
*/
static inline struct rcu_head *rcu_cblist_dequeue(struct rcu_cblist *rclp)
{
struct rcu_head *rhp;
rhp = rclp->head;
if (!rhp)
return NULL;
rclp->len--;
rclp->head = rhp->next;
if (!rclp->head)
rclp->tail = &rclp->head;
return rhp;
}
/*
* Account for the fact that a previously dequeued callback turned out
* to be marked as lazy.
*/
static inline void rcu_cblist_dequeued_lazy(struct rcu_cblist *rclp)
{
rclp->len_lazy--;
}
/*
* Interim function to return rcu_cblist head pointer. Longer term, the
* rcu_cblist will be used more pervasively, removing the need for this
* function.
*/
static inline struct rcu_head *rcu_cblist_head(struct rcu_cblist *rclp)
{
return rclp->head;
}
/*
* Interim function to return rcu_cblist head pointer. Longer term, the
* rcu_cblist will be used more pervasively, removing the need for this
* function.
*/
static inline struct rcu_head **rcu_cblist_tail(struct rcu_cblist *rclp)
{
WARN_ON_ONCE(rcu_cblist_empty(rclp));
return rclp->tail;
}
/* Complicated segmented callback lists. ;-) */
/*
* Index values for segments in rcu_segcblist structure.
*
* The segments are as follows:
*
* [head, *tails[RCU_DONE_TAIL]):
* Callbacks whose grace period has elapsed, and thus can be invoked.
* [*tails[RCU_DONE_TAIL], *tails[RCU_WAIT_TAIL]):
* Callbacks waiting for the current GP from the current CPU's viewpoint.
* [*tails[RCU_WAIT_TAIL], *tails[RCU_NEXT_READY_TAIL]):
* Callbacks that arrived before the next GP started, again from
* the current CPU's viewpoint. These can be handled by the next GP.
* [*tails[RCU_NEXT_READY_TAIL], *tails[RCU_NEXT_TAIL]):
* Callbacks that might have arrived after the next GP started.
* There is some uncertainty as to when a given GP starts and
* ends, but a CPU knows the exact times if it is the one starting
* or ending the GP. Other CPUs know that the previous GP ends
* before the next one starts.
*
* Note that RCU_WAIT_TAIL cannot be empty unless RCU_NEXT_READY_TAIL is also
* empty.
*
* The ->gp_seq[] array contains the grace-period number at which the
* corresponding segment of callbacks will be ready to invoke. A given
* element of this array is meaningful only when the corresponding segment
* is non-empty, and it is never valid for RCU_DONE_TAIL (whose callbacks
* are already ready to invoke) or for RCU_NEXT_TAIL (whose callbacks have
* not yet been assigned a grace-period number).
*/
#define RCU_DONE_TAIL 0 /* Also RCU_WAIT head. */
#define RCU_WAIT_TAIL 1 /* Also RCU_NEXT_READY head. */
#define RCU_NEXT_READY_TAIL 2 /* Also RCU_NEXT head. */
#define RCU_NEXT_TAIL 3
#define RCU_CBLIST_NSEGS 4
struct rcu_segcblist {
struct rcu_head *head;
struct rcu_head **tails[RCU_CBLIST_NSEGS];
unsigned long gp_seq[RCU_CBLIST_NSEGS];
long len;
long len_lazy;
};
#define RCU_SEGCBLIST_INITIALIZER(n) \
{ \
.head = NULL, \
.tails[RCU_DONE_TAIL] = &n.head, \
.tails[RCU_WAIT_TAIL] = &n.head, \
.tails[RCU_NEXT_READY_TAIL] = &n.head, \
.tails[RCU_NEXT_TAIL] = &n.head, \
}
/*
* Initialize an rcu_segcblist structure.
*/
static inline void rcu_segcblist_init(struct rcu_segcblist *rsclp)
{
int i;
BUILD_BUG_ON(RCU_NEXT_TAIL + 1 != ARRAY_SIZE(rsclp->gp_seq));
BUILD_BUG_ON(ARRAY_SIZE(rsclp->tails) != ARRAY_SIZE(rsclp->gp_seq));
rsclp->head = NULL;
for (i = 0; i < RCU_CBLIST_NSEGS; i++)
rsclp->tails[i] = &rsclp->head;
rsclp->len = 0;
rsclp->len_lazy = 0;
}
/*
* Is the specified rcu_segcblist structure empty?
*
* But careful! The fact that the ->head field is NULL does not
* necessarily imply that there are no callbacks associated with
* this structure. When callbacks are being invoked, they are
* removed as a group. If callback invocation must be preempted,
* the remaining callbacks will be added back to the list. Either
* way, the counts are updated later.
*
* So it is often the case that rcu_segcblist_n_cbs() should be used
* instead.
*/
static inline bool rcu_segcblist_empty(struct rcu_segcblist *rsclp)
{
return !rsclp->head;
}
/* Return number of callbacks in segmented callback list. */
static inline long rcu_segcblist_n_cbs(struct rcu_segcblist *rsclp)
{
return READ_ONCE(rsclp->len);
}
/* Return number of lazy callbacks in segmented callback list. */
static inline long rcu_segcblist_n_lazy_cbs(struct rcu_segcblist *rsclp)
{
return rsclp->len_lazy;
}
/* Return number of lazy callbacks in segmented callback list. */
static inline long rcu_segcblist_n_nonlazy_cbs(struct rcu_segcblist *rsclp)
{
return rsclp->len - rsclp->len_lazy;
}
/*
* Is the specified rcu_segcblist enabled, for example, not corresponding
* to an offline or callback-offloaded CPU?
*/
static inline bool rcu_segcblist_is_enabled(struct rcu_segcblist *rsclp)
{
return !!rsclp->tails[RCU_NEXT_TAIL];
}
/*
* Disable the specified rcu_segcblist structure, so that callbacks can
* no longer be posted to it. This structure must be empty.
*/
static inline void rcu_segcblist_disable(struct rcu_segcblist *rsclp)
{
WARN_ON_ONCE(!rcu_segcblist_empty(rsclp));
WARN_ON_ONCE(rcu_segcblist_n_cbs(rsclp));
WARN_ON_ONCE(rcu_segcblist_n_lazy_cbs(rsclp));
rsclp->tails[RCU_NEXT_TAIL] = NULL;
}
/*
* Is the specified segment of the specified rcu_segcblist structure
* empty of callbacks?
*/
static inline bool rcu_segcblist_segempty(struct rcu_segcblist *rsclp, int seg)
{
if (seg == RCU_DONE_TAIL)
return &rsclp->head == rsclp->tails[RCU_DONE_TAIL];
return rsclp->tails[seg - 1] == rsclp->tails[seg];
}
/*
* Are all segments following the specified segment of the specified
* rcu_segcblist structure empty of callbacks? (The specified
* segment might well contain callbacks.)
*/
static inline bool rcu_segcblist_restempty(struct rcu_segcblist *rsclp, int seg)
{
return !*rsclp->tails[seg];
}
/*
* Does the specified rcu_segcblist structure contain callbacks that
* are ready to be invoked?
*/
static inline bool rcu_segcblist_ready_cbs(struct rcu_segcblist *rsclp)
{
return rcu_segcblist_is_enabled(rsclp) &&
&rsclp->head != rsclp->tails[RCU_DONE_TAIL];
}
/*
* Does the specified rcu_segcblist structure contain callbacks that
* are still pending, that is, not yet ready to be invoked?
*/
static inline bool rcu_segcblist_pend_cbs(struct rcu_segcblist *rsclp)
{
return rcu_segcblist_is_enabled(rsclp) &&
!rcu_segcblist_restempty(rsclp, RCU_DONE_TAIL);
}
/*
* Dequeue and return the first ready-to-invoke callback. If there
* are no ready-to-invoke callbacks, return NULL. Disables interrupts
* to avoid interference. Does not protect from interference from other
* CPUs or tasks.
*/
static inline struct rcu_head *
rcu_segcblist_dequeue(struct rcu_segcblist *rsclp)
{
unsigned long flags;
int i;
struct rcu_head *rhp;
local_irq_save(flags);
if (!rcu_segcblist_ready_cbs(rsclp)) {
local_irq_restore(flags);
return NULL;
}
rhp = rsclp->head;
BUG_ON(!rhp);
rsclp->head = rhp->next;
for (i = RCU_DONE_TAIL; i < RCU_CBLIST_NSEGS; i++) {
if (rsclp->tails[i] != &rhp->next)
break;
rsclp->tails[i] = &rsclp->head;
}
smp_mb(); /* Dequeue before decrement for rcu_barrier(). */
WRITE_ONCE(rsclp->len, rsclp->len - 1);
local_irq_restore(flags);
return rhp;
}
/*
* Account for the fact that a previously dequeued callback turned out
* to be marked as lazy.
*/
static inline void rcu_segcblist_dequeued_lazy(struct rcu_segcblist *rsclp)
{
unsigned long flags;
local_irq_save(flags);
rsclp->len_lazy--;
local_irq_restore(flags);
}
/*
* Return a pointer to the first callback in the specified rcu_segcblist
* structure. This is useful for diagnostics.
*/
static inline struct rcu_head *
rcu_segcblist_first_cb(struct rcu_segcblist *rsclp)
{
if (rcu_segcblist_is_enabled(rsclp))
return rsclp->head;
return NULL;
}
/*
* Return a pointer to the first pending callback in the specified
* rcu_segcblist structure. This is useful just after posting a given
* callback -- if that callback is the first pending callback, then
* you cannot rely on someone else having already started up the required
* grace period.
*/
static inline struct rcu_head *
rcu_segcblist_first_pend_cb(struct rcu_segcblist *rsclp)
{
if (rcu_segcblist_is_enabled(rsclp))
return *rsclp->tails[RCU_DONE_TAIL];
return NULL;
}
/*
* Does the specified rcu_segcblist structure contain callbacks that
* have not yet been processed beyond having been posted, that is,
* does it contain callbacks in its last segment?
*/
static inline bool rcu_segcblist_new_cbs(struct rcu_segcblist *rsclp)
{
return rcu_segcblist_is_enabled(rsclp) &&
!rcu_segcblist_restempty(rsclp, RCU_NEXT_READY_TAIL);
}
/*
* Enqueue the specified callback onto the specified rcu_segcblist
* structure, updating accounting as needed. Note that the ->len
* field may be accessed locklessly, hence the WRITE_ONCE().
* The ->len field is used by rcu_barrier() and friends to determine
* if it must post a callback on this structure, and it is OK
* for rcu_barrier() to sometimes post callbacks needlessly, but
* absolutely not OK for it to ever miss posting a callback.
*/
static inline void rcu_segcblist_enqueue(struct rcu_segcblist *rsclp,
struct rcu_head *rhp, bool lazy)
{
WRITE_ONCE(rsclp->len, rsclp->len + 1); /* ->len sampled locklessly. */
if (lazy)
rsclp->len_lazy++;
smp_mb(); /* Ensure counts are updated before callback is enqueued. */
rhp->next = NULL;
*rsclp->tails[RCU_NEXT_TAIL] = rhp;
rsclp->tails[RCU_NEXT_TAIL] = &rhp->next;
}
/*
* Entrain the specified callback onto the specified rcu_segcblist at
* the end of the last non-empty segment. If the entire rcu_segcblist
* is empty, make no change, but return false.
*
* This is intended for use by rcu_barrier()-like primitives, -not-
* for normal grace-period use. IMPORTANT: The callback you enqueue
* will wait for all prior callbacks, NOT necessarily for a grace
* period. You have been warned.
*/
static inline bool rcu_segcblist_entrain(struct rcu_segcblist *rsclp,
struct rcu_head *rhp, bool lazy)
{
int i;
if (rcu_segcblist_n_cbs(rsclp) == 0)
return false;
WRITE_ONCE(rsclp->len, rsclp->len + 1);
if (lazy)
rsclp->len_lazy++;
smp_mb(); /* Ensure counts are updated before callback is entrained. */
rhp->next = NULL;
for (i = RCU_NEXT_TAIL; i > RCU_DONE_TAIL; i--)
if (rsclp->tails[i] != rsclp->tails[i - 1])
break;
*rsclp->tails[i] = rhp;
for (; i <= RCU_NEXT_TAIL; i++)
rsclp->tails[i] = &rhp->next;
return true;
}
/*
* Extract only the counts from the specified rcu_segcblist structure,
* and place them in the specified rcu_cblist structure. This function
* supports both callback orphaning and invocation, hence the separation
* of counts and callbacks. (Callbacks ready for invocation must be
* orphaned and adopted separately from pending callbacks, but counts
* apply to all callbacks. Locking must be used to make sure that
* both orphaned-callbacks lists are consistent.)
*/
static inline void rcu_segcblist_extract_count(struct rcu_segcblist *rsclp,
struct rcu_cblist *rclp)
{
rclp->len_lazy += rsclp->len_lazy;
rclp->len += rsclp->len;
rsclp->len_lazy = 0;
WRITE_ONCE(rsclp->len, 0); /* ->len sampled locklessly. */
}
/*
* Extract only those callbacks ready to be invoked from the specified
* rcu_segcblist structure and place them in the specified rcu_cblist
* structure.
*/
static inline void rcu_segcblist_extract_done_cbs(struct rcu_segcblist *rsclp,
struct rcu_cblist *rclp)
{
int i;
if (!rcu_segcblist_ready_cbs(rsclp))
return; /* Nothing to do. */
*rclp->tail = rsclp->head;
rsclp->head = *rsclp->tails[RCU_DONE_TAIL];
*rsclp->tails[RCU_DONE_TAIL] = NULL;
rclp->tail = rsclp->tails[RCU_DONE_TAIL];
for (i = RCU_CBLIST_NSEGS - 1; i >= RCU_DONE_TAIL; i--)
if (rsclp->tails[i] == rsclp->tails[RCU_DONE_TAIL])
rsclp->tails[i] = &rsclp->head;
}
/*
* Extract only those callbacks still pending (not yet ready to be
* invoked) from the specified rcu_segcblist structure and place them in
* the specified rcu_cblist structure. Note that this loses information
* about any callbacks that might have been partway done waiting for
* their grace period. Too bad! They will have to start over.
*/
static inline void
rcu_segcblist_extract_pend_cbs(struct rcu_segcblist *rsclp,
struct rcu_cblist *rclp)
{
int i;
if (!rcu_segcblist_pend_cbs(rsclp))
return; /* Nothing to do. */
*rclp->tail = *rsclp->tails[RCU_DONE_TAIL];
rclp->tail = rsclp->tails[RCU_NEXT_TAIL];
*rsclp->tails[RCU_DONE_TAIL] = NULL;
for (i = RCU_DONE_TAIL + 1; i < RCU_CBLIST_NSEGS; i++)
rsclp->tails[i] = rsclp->tails[RCU_DONE_TAIL];
}
/*
* Move the entire contents of the specified rcu_segcblist structure,
* counts, callbacks, and all, to the specified rcu_cblist structure.
* @@@ Why do we need this??? Moving early-boot CBs to NOCB lists?
* @@@ Memory barrier needed? (Not if only used at boot time...)
*/
static inline void rcu_segcblist_extract_all(struct rcu_segcblist *rsclp,
struct rcu_cblist *rclp)
{
rcu_segcblist_extract_done_cbs(rsclp, rclp);
rcu_segcblist_extract_pend_cbs(rsclp, rclp);
rcu_segcblist_extract_count(rsclp, rclp);
}
/*
* Insert counts from the specified rcu_cblist structure in the
* specified rcu_segcblist structure.
*/
static inline void rcu_segcblist_insert_count(struct rcu_segcblist *rsclp,
struct rcu_cblist *rclp)
{
rsclp->len_lazy += rclp->len_lazy;
/* ->len sampled locklessly. */
WRITE_ONCE(rsclp->len, rsclp->len + rclp->len);
rclp->len_lazy = 0;
rclp->len = 0;
}
/*
* Move callbacks from the specified rcu_cblist to the beginning of the
* done-callbacks segment of the specified rcu_segcblist.
*/
static inline void rcu_segcblist_insert_done_cbs(struct rcu_segcblist *rsclp,
struct rcu_cblist *rclp)
{
int i;
if (!rclp->head)
return; /* No callbacks to move. */
*rclp->tail = rsclp->head;
rsclp->head = rclp->head;
for (i = RCU_DONE_TAIL; i < RCU_CBLIST_NSEGS; i++)
if (&rsclp->head == rsclp->tails[i])
rsclp->tails[i] = rclp->tail;
else
break;
rclp->head = NULL;
rclp->tail = &rclp->head;
}
/*
* Move callbacks from the specified rcu_cblist to the end of the
* new-callbacks segment of the specified rcu_segcblist.
*/
static inline void rcu_segcblist_insert_pend_cbs(struct rcu_segcblist *rsclp,
struct rcu_cblist *rclp)
{
if (!rclp->head)
return; /* Nothing to do. */
*rsclp->tails[RCU_NEXT_TAIL] = rclp->head;
rsclp->tails[RCU_NEXT_TAIL] = rclp->tail;
rclp->head = NULL;
rclp->tail = &rclp->head;
}
/*
* Advance the callbacks in the specified rcu_segcblist structure based
* on the current value passed in for the grace-period counter.
*/
static inline void rcu_segcblist_advance(struct rcu_segcblist *rsclp,
unsigned long seq)
{
int i, j;
WARN_ON_ONCE(!rcu_segcblist_is_enabled(rsclp));
if (rcu_segcblist_restempty(rsclp, RCU_DONE_TAIL))
return;
/*
* Find all callbacks whose ->gp_seq numbers indicate that they
* are ready to invoke, and put them into the RCU_DONE_TAIL segment.
*/
for (i = RCU_WAIT_TAIL; i < RCU_NEXT_TAIL; i++) {
if (ULONG_CMP_LT(seq, rsclp->gp_seq[i]))
break;
rsclp->tails[RCU_DONE_TAIL] = rsclp->tails[i];
}
/* If no callbacks moved, nothing more need be done. */
if (i == RCU_WAIT_TAIL)
return;
/* Clean up tail pointers that might have been misordered above. */
for (j = RCU_WAIT_TAIL; j < i; j++)
rsclp->tails[j] = rsclp->tails[RCU_DONE_TAIL];
/*
* Callbacks moved, so clean up the misordered ->tails[] pointers
* that now point into the middle of the list of ready-to-invoke
* callbacks. The overall effect is to copy down the later pointers
* into the gap that was created by the now-ready segments.
*/
for (j = RCU_WAIT_TAIL; i < RCU_NEXT_TAIL; i++, j++) {
if (rsclp->tails[j] == rsclp->tails[RCU_NEXT_TAIL])
break; /* No more callbacks. */
rsclp->tails[j] = rsclp->tails[i];
rsclp->gp_seq[j] = rsclp->gp_seq[i];
}
}
/*
* "Accelerate" callbacks based on more-accurate grace-period information.
* The reason for this is that RCU does not synchronize the beginnings and
* ends of grace periods, and that callbacks are posted locally. This in
* turn means that the callbacks must be labelled conservatively early
* on, as getting exact information would degrade both performance and
* scalability. When more accurate grace-period information becomes
* available, previously posted callbacks can be "accelerated", marking
* them to complete at the end of the earlier grace period.
*
* This function operates on an rcu_segcblist structure, and also the
* grace-period sequence number seq at which new callbacks would become
* ready to invoke. Returns true if there are callbacks that won't be
* ready to invoke until seq, false otherwise.
*/
static inline bool rcu_segcblist_accelerate(struct rcu_segcblist *rsclp,
unsigned long seq)
{
int i;
WARN_ON_ONCE(!rcu_segcblist_is_enabled(rsclp));
if (rcu_segcblist_restempty(rsclp, RCU_DONE_TAIL))
return false;
/*
* Find the segment preceding the oldest segment of callbacks
* whose ->gp_seq[] completion is at or after that passed in via
* "seq", skipping any empty segments. This oldest segment, along
* with any later segments, can be merged in with any newly arrived
* callbacks in the RCU_NEXT_TAIL segment, and assigned "seq"
* as their ->gp_seq[] grace-period completion sequence number.
*/
for (i = RCU_NEXT_READY_TAIL; i > RCU_DONE_TAIL; i--)
if (rsclp->tails[i] != rsclp->tails[i - 1] &&
ULONG_CMP_LT(rsclp->gp_seq[i], seq))
break;
/*
* If all the segments contain callbacks that correspond to
* earlier grace-period sequence numbers than "seq", leave.
* Assuming that the rcu_segcblist structure has enough
* segments in its arrays, this can only happen if some of
* the non-done segments contain callbacks that really are
* ready to invoke. This situation will get straightened
* out by the next call to rcu_segcblist_advance().
*
* Also advance to the oldest segment of callbacks whose
* ->gp_seq[] completion is at or after that passed in via "seq",
* skipping any empty segments.
*/
if (++i >= RCU_NEXT_TAIL)
return false;
/*
* Merge all later callbacks, including newly arrived callbacks,
* into the segment located by the for-loop above. Assign "seq"
* as the ->gp_seq[] value in order to correctly handle the case
* where there were no pending callbacks in the rcu_segcblist
* structure other than in the RCU_NEXT_TAIL segment.
*/
for (; i < RCU_NEXT_TAIL; i++) {
rsclp->tails[i] = rsclp->tails[RCU_NEXT_TAIL];
rsclp->gp_seq[i] = seq;
}
return true;
}
/*
* Scan the specified rcu_segcblist structure for callbacks that need
* a grace period later than the one specified by "seq". We don't look
* at the RCU_DONE_TAIL or RCU_NEXT_TAIL segments because they don't
* have a grace-period sequence number.
*/
static inline bool rcu_segcblist_future_gp_needed(struct rcu_segcblist *rsclp,
unsigned long seq)
{
int i;
for (i = RCU_WAIT_TAIL; i < RCU_NEXT_TAIL; i++)
if (rsclp->tails[i - 1] != rsclp->tails[i] &&
ULONG_CMP_LT(seq, rsclp->gp_seq[i]))
return true;
return false;
}
/*
* Interim function to return rcu_segcblist head pointer. Longer term, the
* rcu_segcblist will be used more pervasively, removing the need for this
* function.
*/
static inline struct rcu_head *rcu_segcblist_head(struct rcu_segcblist *rsclp)
{
return rsclp->head;
}
/*
* Interim function to return rcu_segcblist head pointer. Longer term, the
* rcu_segcblist will be used more pervasively, removing the need for this
* function.
*/
static inline struct rcu_head **rcu_segcblist_tail(struct rcu_segcblist *rsclp)
{
WARN_ON_ONCE(rcu_segcblist_empty(rsclp));
return rsclp->tails[RCU_NEXT_TAIL];
}
#endif /* __KERNEL_RCU_SEGCBLIST_H */

3
include/linux/rculist.h
View File

@ -509,7 +509,8 @@ static inline void hlist_add_tail_rcu(struct hlist_node *n,
{
struct hlist_node *i, *last = NULL;
for (i = hlist_first_rcu(h); i; i = hlist_next_rcu(i))
/* Note: write side code, so rcu accessors are not needed. */
for (i = h->first; i; i = i->next)
last = i;
if (last) {

17
include/linux/rcupdate.h
View File

@ -363,15 +363,20 @@ static inline void rcu_init_nohz(void)
#ifdef CONFIG_TASKS_RCU
#define TASKS_RCU(x) x
extern struct srcu_struct tasks_rcu_exit_srcu;
#define rcu_note_voluntary_context_switch(t) \
#define rcu_note_voluntary_context_switch_lite(t) \
do { \
rcu_all_qs(); \
if (READ_ONCE((t)->rcu_tasks_holdout)) \
WRITE_ONCE((t)->rcu_tasks_holdout, false); \
} while (0)
#define rcu_note_voluntary_context_switch(t) \
do { \
rcu_all_qs(); \
rcu_note_voluntary_context_switch_lite(t); \
} while (0)
#else /* #ifdef CONFIG_TASKS_RCU */
#define TASKS_RCU(x) do { } while (0)
#define rcu_note_voluntary_context_switch(t) rcu_all_qs()
#define rcu_note_voluntary_context_switch_lite(t) do { } while (0)
#define rcu_note_voluntary_context_switch(t) rcu_all_qs()
#endif /* #else #ifdef CONFIG_TASKS_RCU */
/**
@ -1127,11 +1132,11 @@ do { \
* if the UNLOCK and LOCK are executed by the same CPU or if the
* UNLOCK and LOCK operate on the same lock variable.
*/
#ifdef CONFIG_PPC
#ifdef CONFIG_ARCH_WEAK_RELEASE_ACQUIRE
#define smp_mb__after_unlock_lock() smp_mb() /* Full ordering for lock. */
#else /* #ifdef CONFIG_PPC */
#else /* #ifdef CONFIG_ARCH_WEAK_RELEASE_ACQUIRE */
#define smp_mb__after_unlock_lock() do { } while (0)
#endif /* #else #ifdef CONFIG_PPC */
#endif /* #else #ifdef CONFIG_ARCH_WEAK_RELEASE_ACQUIRE */
#endif /* __LINUX_RCUPDATE_H */

24
include/linux/rcutiny.h
View File

@ -33,6 +33,11 @@ static inline int rcu_dynticks_snap(struct rcu_dynticks *rdtp)
return 0;
}
static inline bool rcu_eqs_special_set(int cpu)
{
return false; /* Never flag non-existent other CPUs! */
}
static inline unsigned long get_state_synchronize_rcu(void)
{
return 0;
@ -87,10 +92,11 @@ static inline void kfree_call_rcu(struct rcu_head *head,
call_rcu(head, func);
}
static inline void rcu_note_context_switch(void)
{
rcu_sched_qs();
}
#define rcu_note_context_switch(preempt) \
do { \
rcu_sched_qs(); \
rcu_note_voluntary_context_switch_lite(current); \
} while (0)
/*
* Take advantage of the fact that there is only one CPU, which
@ -212,14 +218,14 @@ static inline void exit_rcu(void)
{
}
#ifdef CONFIG_DEBUG_LOCK_ALLOC
#if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_SRCU)
extern int rcu_scheduler_active __read_mostly;
void rcu_scheduler_starting(void);
#else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
#else /* #if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_SRCU) */
static inline void rcu_scheduler_starting(void)
{
}
#endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */
#endif /* #else #if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_SRCU) */
#if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE)
@ -237,6 +243,10 @@ static inline bool rcu_is_watching(void)
#endif /* #else defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE) */
static inline void rcu_request_urgent_qs_task(struct task_struct *t)
{
}
static inline void rcu_all_qs(void)
{
barrier(); /* Avoid RCU read-side critical sections leaking across. */

5
include/linux/rcutree.h
View File

@ -30,7 +30,7 @@
#ifndef __LINUX_RCUTREE_H
#define __LINUX_RCUTREE_H
void rcu_note_context_switch(void);
void rcu_note_context_switch(bool preempt);
int rcu_needs_cpu(u64 basem, u64 *nextevt);
void rcu_cpu_stall_reset(void);
@ -41,7 +41,7 @@ void rcu_cpu_stall_reset(void);
*/
static inline void rcu_virt_note_context_switch(int cpu)
{
rcu_note_context_switch();
rcu_note_context_switch(false);
}
void synchronize_rcu_bh(void);
@ -108,6 +108,7 @@ void rcu_scheduler_starting(void);
extern int rcu_scheduler_active __read_mostly;
bool rcu_is_watching(void);
void rcu_request_urgent_qs_task(struct task_struct *t);
void rcu_all_qs(void);

6
include/linux/slab.h
View File

@ -28,7 +28,7 @@
#define SLAB_STORE_USER 0x00010000UL /* DEBUG: Store the last owner for bug hunting */
#define SLAB_PANIC 0x00040000UL /* Panic if kmem_cache_create() fails */
/*
* SLAB_DESTROY_BY_RCU - **WARNING** READ THIS!
* SLAB_TYPESAFE_BY_RCU - **WARNING** READ THIS!
*
* This delays freeing the SLAB page by a grace period, it does _NOT_
* delay object freeing. This means that if you do kmem_cache_free()
@ -61,8 +61,10 @@
*
* rcu_read_lock before reading the address, then rcu_read_unlock after
* taking the spinlock within the structure expected at that address.
*
* Note that SLAB_TYPESAFE_BY_RCU was originally named SLAB_DESTROY_BY_RCU.
*/
#define SLAB_DESTROY_BY_RCU 0x00080000UL /* Defer freeing slabs to RCU */
#define SLAB_TYPESAFE_BY_RCU 0x00080000UL /* Defer freeing slabs to RCU */
#define SLAB_MEM_SPREAD 0x00100000UL /* Spread some memory over cpuset */
#define SLAB_TRACE 0x00200000UL /* Trace allocations and frees */

84
include/linux/srcu.h
View File

@ -22,7 +22,7 @@
* Lai Jiangshan <laijs@cn.fujitsu.com>
*
* For detailed explanation of Read-Copy Update mechanism see -
* Documentation/RCU/ *.txt
* Documentation/RCU/ *.txt
*
*/
@ -32,35 +32,9 @@
#include <linux/mutex.h>
#include <linux/rcupdate.h>
#include <linux/workqueue.h>
#include <linux/rcu_segcblist.h>
struct srcu_array {
unsigned long lock_count[2];
unsigned long unlock_count[2];
};
struct rcu_batch {
struct rcu_head *head, **tail;
};
#define RCU_BATCH_INIT(name) { NULL, &(name.head) }
struct srcu_struct {
unsigned long completed;
struct srcu_array __percpu *per_cpu_ref;
spinlock_t queue_lock; /* protect ->batch_queue, ->running */
bool running;
/* callbacks just queued */
struct rcu_batch batch_queue;
/* callbacks try to do the first check_zero */
struct rcu_batch batch_check0;
/* callbacks done with the first check_zero and the flip */
struct rcu_batch batch_check1;
struct rcu_batch batch_done;
struct delayed_work work;
#ifdef CONFIG_DEBUG_LOCK_ALLOC
struct lockdep_map dep_map;
#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
};
struct srcu_struct;
#ifdef CONFIG_DEBUG_LOCK_ALLOC
@ -82,46 +56,15 @@ int init_srcu_struct(struct srcu_struct *sp);
#define __SRCU_DEP_MAP_INIT(srcu_name)
#endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */
void process_srcu(struct work_struct *work);
#define __SRCU_STRUCT_INIT(name) \
{ \
.completed = -300, \
.per_cpu_ref = &name##_srcu_array, \
.queue_lock = __SPIN_LOCK_UNLOCKED(name.queue_lock), \
.running = false, \
.batch_queue = RCU_BATCH_INIT(name.batch_queue), \
.batch_check0 = RCU_BATCH_INIT(name.batch_check0), \
.batch_check1 = RCU_BATCH_INIT(name.batch_check1), \
.batch_done = RCU_BATCH_INIT(name.batch_done), \
.work = __DELAYED_WORK_INITIALIZER(name.work, process_srcu, 0),\
__SRCU_DEP_MAP_INIT(name) \
}
/*
* Define and initialize a srcu struct at build time.
* Do -not- call init_srcu_struct() nor cleanup_srcu_struct() on it.
*
* Note that although DEFINE_STATIC_SRCU() hides the name from other
* files, the per-CPU variable rules nevertheless require that the
* chosen name be globally unique. These rules also prohibit use of
* DEFINE_STATIC_SRCU() within a function. If these rules are too
* restrictive, declare the srcu_struct manually. For example, in
* each file:
*
* static struct srcu_struct my_srcu;
*
* Then, before the first use of each my_srcu, manually initialize it:
*
* init_srcu_struct(&my_srcu);
*
* See include/linux/percpu-defs.h for the rules on per-CPU variables.
*/
#define __DEFINE_SRCU(name, is_static) \
static DEFINE_PER_CPU(struct srcu_array, name##_srcu_array);\
is_static struct srcu_struct name = __SRCU_STRUCT_INIT(name)
#define DEFINE_SRCU(name) __DEFINE_SRCU(name, /* not static */)
#define DEFINE_STATIC_SRCU(name) __DEFINE_SRCU(name, static)
#ifdef CONFIG_TINY_SRCU
#include <linux/srcutiny.h>
#elif defined(CONFIG_TREE_SRCU)
#include <linux/srcutree.h>
#elif defined(CONFIG_CLASSIC_SRCU)
#include <linux/srcuclassic.h>
#else
#error "Unknown SRCU implementation specified to kernel configuration"
#endif
/**
* call_srcu() - Queue a callback for invocation after an SRCU grace period
@ -147,9 +90,6 @@ void cleanup_srcu_struct(struct srcu_struct *sp);
int __srcu_read_lock(struct srcu_struct *sp) __acquires(sp);
void __srcu_read_unlock(struct srcu_struct *sp, int idx) __releases(sp);
void synchronize_srcu(struct srcu_struct *sp);
void synchronize_srcu_expedited(struct srcu_struct *sp);
unsigned long srcu_batches_completed(struct srcu_struct *sp);
void srcu_barrier(struct srcu_struct *sp);
#ifdef CONFIG_DEBUG_LOCK_ALLOC

101
include/linux/srcuclassic.h Normal file
View File

@ -0,0 +1,101 @@
/*
* Sleepable Read-Copy Update mechanism for mutual exclusion,
* classic v4.11 variant.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, you can access it online at
* http://www.gnu.org/licenses/gpl-2.0.html.
*
* Copyright (C) IBM Corporation, 2017
*
* Author: Paul McKenney <paulmck@us.ibm.com>
*/
#ifndef _LINUX_SRCU_CLASSIC_H
#define _LINUX_SRCU_CLASSIC_H
struct srcu_array {
unsigned long lock_count[2];
unsigned long unlock_count[2];
};
struct rcu_batch {
struct rcu_head *head, **tail;
};
#define RCU_BATCH_INIT(name) { NULL, &(name.head) }
struct srcu_struct {
unsigned long completed;
struct srcu_array __percpu *per_cpu_ref;
spinlock_t queue_lock; /* protect ->batch_queue, ->running */
bool running;
/* callbacks just queued */
struct rcu_batch batch_queue;
/* callbacks try to do the first check_zero */
struct rcu_batch batch_check0;
/* callbacks done with the first check_zero and the flip */
struct rcu_batch batch_check1;
struct rcu_batch batch_done;
struct delayed_work work;
#ifdef CONFIG_DEBUG_LOCK_ALLOC
struct lockdep_map dep_map;
#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
};
void process_srcu(struct work_struct *work);
#define __SRCU_STRUCT_INIT(name) \
{ \
.completed = -300, \
.per_cpu_ref = &name##_srcu_array, \
.queue_lock = __SPIN_LOCK_UNLOCKED(name.queue_lock), \
.running = false, \
.batch_queue = RCU_BATCH_INIT(name.batch_queue), \
.batch_check0 = RCU_BATCH_INIT(name.batch_check0), \
.batch_check1 = RCU_BATCH_INIT(name.batch_check1), \
.batch_done = RCU_BATCH_INIT(name.batch_done), \
.work = __DELAYED_WORK_INITIALIZER(name.work, process_srcu, 0),\
__SRCU_DEP_MAP_INIT(name) \
}
/*
* Define and initialize a srcu struct at build time.
* Do -not- call init_srcu_struct() nor cleanup_srcu_struct() on it.
*
* Note that although DEFINE_STATIC_SRCU() hides the name from other
* files, the per-CPU variable rules nevertheless require that the
* chosen name be globally unique. These rules also prohibit use of
* DEFINE_STATIC_SRCU() within a function. If these rules are too
* restrictive, declare the srcu_struct manually. For example, in
* each file:
*
* static struct srcu_struct my_srcu;
*
* Then, before the first use of each my_srcu, manually initialize it:
*
* init_srcu_struct(&my_srcu);
*
* See include/linux/percpu-defs.h for the rules on per-CPU variables.
*/
#define __DEFINE_SRCU(name, is_static) \
static DEFINE_PER_CPU(struct srcu_array, name##_srcu_array);\
is_static struct srcu_struct name = __SRCU_STRUCT_INIT(name)
#define DEFINE_SRCU(name) __DEFINE_SRCU(name, /* not static */)
#define DEFINE_STATIC_SRCU(name) __DEFINE_SRCU(name, static)
void synchronize_srcu_expedited(struct srcu_struct *sp);
void srcu_barrier(struct srcu_struct *sp);
unsigned long srcu_batches_completed(struct srcu_struct *sp);
#endif

81
include/linux/srcutiny.h Normal file
View File

@ -0,0 +1,81 @@
/*
* Sleepable Read-Copy Update mechanism for mutual exclusion,
* tiny variant.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, you can access it online at
* http://www.gnu.org/licenses/gpl-2.0.html.
*
* Copyright (C) IBM Corporation, 2017
*
* Author: Paul McKenney <paulmck@us.ibm.com>
*/
#ifndef _LINUX_SRCU_TINY_H
#define _LINUX_SRCU_TINY_H
#include <linux/swait.h>
struct srcu_struct {
int srcu_lock_nesting[2]; /* srcu_read_lock() nesting depth. */
struct swait_queue_head srcu_wq;
/* Last srcu_read_unlock() wakes GP. */
unsigned long srcu_gp_seq; /* GP seq # for callback tagging. */
struct rcu_segcblist srcu_cblist;
/* Pending SRCU callbacks. */
int srcu_idx; /* Current reader array element. */
bool srcu_gp_running; /* GP workqueue running? */
bool srcu_gp_waiting; /* GP waiting for readers? */
struct work_struct srcu_work; /* For driving grace periods. */
#ifdef CONFIG_DEBUG_LOCK_ALLOC
struct lockdep_map dep_map;
#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
};
void srcu_drive_gp(struct work_struct *wp);
#define __SRCU_STRUCT_INIT(name) \
{ \
.srcu_wq = __SWAIT_QUEUE_HEAD_INITIALIZER(name.srcu_wq), \
.srcu_cblist = RCU_SEGCBLIST_INITIALIZER(name.srcu_cblist), \
.srcu_work = __WORK_INITIALIZER(name.srcu_work, srcu_drive_gp), \
__SRCU_DEP_MAP_INIT(name) \
}
/*
* This odd _STATIC_ arrangement is needed for API compatibility with
* Tree SRCU, which needs some per-CPU data.
*/
#define DEFINE_SRCU(name) \
struct srcu_struct name = __SRCU_STRUCT_INIT(name)
#define DEFINE_STATIC_SRCU(name) \
static struct srcu_struct name = __SRCU_STRUCT_INIT(name)
void synchronize_srcu(struct srcu_struct *sp);
static inline void synchronize_srcu_expedited(struct srcu_struct *sp)
{
synchronize_srcu(sp);
}
static inline void srcu_barrier(struct srcu_struct *sp)
{
synchronize_srcu(sp);
}
static inline unsigned long srcu_batches_completed(struct srcu_struct *sp)
{
return 0;
}
#endif

139
include/linux/srcutree.h Normal file
View File

@ -0,0 +1,139 @@
/*
* Sleepable Read-Copy Update mechanism for mutual exclusion,
* tree variant.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, you can access it online at
* http://www.gnu.org/licenses/gpl-2.0.html.
*
* Copyright (C) IBM Corporation, 2017
*
* Author: Paul McKenney <paulmck@us.ibm.com>
*/
#ifndef _LINUX_SRCU_TREE_H
#define _LINUX_SRCU_TREE_H
#include <linux/rcu_node_tree.h>
#include <linux/completion.h>
struct srcu_node;
struct srcu_struct;
/*
* Per-CPU structure feeding into leaf srcu_node, similar in function
* to rcu_node.
*/
struct srcu_data {
/* Read-side state. */
unsigned long srcu_lock_count[2]; /* Locks per CPU. */
unsigned long srcu_unlock_count[2]; /* Unlocks per CPU. */
/* Update-side state. */
spinlock_t lock ____cacheline_internodealigned_in_smp;
struct rcu_segcblist srcu_cblist; /* List of callbacks.*/
unsigned long srcu_gp_seq_needed; /* Furthest future GP needed. */
bool srcu_cblist_invoking; /* Invoking these CBs? */
struct delayed_work work; /* Context for CB invoking. */
struct rcu_head srcu_barrier_head; /* For srcu_barrier() use. */
struct srcu_node *mynode; /* Leaf srcu_node. */
int cpu;
struct srcu_struct *sp;
};
/*
* Node in SRCU combining tree, similar in function to rcu_data.
*/
struct srcu_node {
spinlock_t lock;
unsigned long srcu_have_cbs[4]; /* GP seq for children */
/* having CBs, but only */
/* is > ->srcu_gq_seq. */
struct srcu_node *srcu_parent; /* Next up in tree. */
int grplo; /* Least CPU for node. */
int grphi; /* Biggest CPU for node. */
};
/*
* Per-SRCU-domain structure, similar in function to rcu_state.
*/
struct srcu_struct {
struct srcu_node node[NUM_RCU_NODES]; /* Combining tree. */
struct srcu_node *level[RCU_NUM_LVLS + 1];
/* First node at each level. */
struct mutex srcu_cb_mutex; /* Serialize CB preparation. */
spinlock_t gp_lock; /* protect ->srcu_cblist */
struct mutex srcu_gp_mutex; /* Serialize GP work. */
unsigned int srcu_idx; /* Current rdr array element. */
unsigned long srcu_gp_seq; /* Grace-period seq #. */
unsigned long srcu_gp_seq_needed; /* Latest gp_seq needed. */
atomic_t srcu_exp_cnt; /* # ongoing expedited GPs. */
struct srcu_data __percpu *sda; /* Per-CPU srcu_data array. */
unsigned long srcu_barrier_seq; /* srcu_barrier seq #. */
struct mutex srcu_barrier_mutex; /* Serialize barrier ops. */
struct completion srcu_barrier_completion;
/* Awaken barrier rq at end. */
atomic_t srcu_barrier_cpu_cnt; /* # CPUs not yet posting a */
/* callback for the barrier */
/* operation. */
struct delayed_work work;
#ifdef CONFIG_DEBUG_LOCK_ALLOC
struct lockdep_map dep_map;
#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
};
/* Values for state variable (bottom bits of ->srcu_gp_seq). */
#define SRCU_STATE_IDLE 0
#define SRCU_STATE_SCAN1 1
#define SRCU_STATE_SCAN2 2
void process_srcu(struct work_struct *work);
#define __SRCU_STRUCT_INIT(name) \
{ \
.sda = &name##_srcu_data, \
.gp_lock = __SPIN_LOCK_UNLOCKED(name.gp_lock), \
.srcu_gp_seq_needed = 0 - 1, \
__SRCU_DEP_MAP_INIT(name) \
}
/*
* Define and initialize a srcu struct at build time.
* Do -not- call init_srcu_struct() nor cleanup_srcu_struct() on it.
*
* Note that although DEFINE_STATIC_SRCU() hides the name from other
* files, the per-CPU variable rules nevertheless require that the
* chosen name be globally unique. These rules also prohibit use of
* DEFINE_STATIC_SRCU() within a function. If these rules are too
* restrictive, declare the srcu_struct manually. For example, in
* each file:
*
* static struct srcu_struct my_srcu;
*
* Then, before the first use of each my_srcu, manually initialize it:
*
* init_srcu_struct(&my_srcu);
*
* See include/linux/percpu-defs.h for the rules on per-CPU variables.
*/
#define __DEFINE_SRCU(name, is_static) \
static DEFINE_PER_CPU(struct srcu_data, name##_srcu_data);\
is_static struct srcu_struct name = __SRCU_STRUCT_INIT(name)
#define DEFINE_SRCU(name) __DEFINE_SRCU(name, /* not static */)
#define DEFINE_STATIC_SRCU(name) __DEFINE_SRCU(name, static)
void synchronize_srcu_expedited(struct srcu_struct *sp);
void srcu_barrier(struct srcu_struct *sp);
unsigned long srcu_batches_completed(struct srcu_struct *sp);
#endif

2
include/linux/types.h
View File

@ -209,7 +209,7 @@ struct ustat {
* naturally due ABI requirements, but some architectures (like CRIS) have
* weird ABI and we need to ask it explicitly.
*
* The alignment is required to guarantee that bits 0 and 1 of @next will be
* The alignment is required to guarantee that bit 0 of @next will be
* clear under normal conditions -- as long as we use call_rcu(),
* call_rcu_bh(), call_rcu_sched(), or call_srcu() to queue callback.
*

2
include/net/sock.h
View File

@ -995,7 +995,7 @@ struct smc_hashinfo;
struct module;
/*
* caches using SLAB_DESTROY_BY_RCU should let .next pointer from nulls nodes
* caches using SLAB_TYPESAFE_BY_RCU should let .next pointer from nulls nodes
* un-modified. Special care is taken when initializing object to zero.
*/
static inline void sk_prot_clear_nulls(struct sock *sk, int size)

39
init/Kconfig
View File

@ -526,6 +526,35 @@ config SRCU
permits arbitrary sleeping or blocking within RCU read-side critical
sections.
config CLASSIC_SRCU
bool "Use v4.11 classic SRCU implementation"
default n
depends on RCU_EXPERT && SRCU
help
This option selects the traditional well-tested classic SRCU
implementation from v4.11, as might be desired for enterprise
Linux distributions. Without this option, the shiny new
Tiny SRCU and Tree SRCU implementations are used instead.
At some point, it is hoped that Tiny SRCU and Tree SRCU
will accumulate enough test time and confidence to allow
Classic SRCU to be dropped entirely.
Say Y if you need a rock-solid SRCU.
Say N if you would like help test Tree SRCU.
config TINY_SRCU
bool
default y if TINY_RCU && !CLASSIC_SRCU
help
This option selects the single-CPU non-preemptible version of SRCU.
config TREE_SRCU
bool
default y if !TINY_RCU && !CLASSIC_SRCU
help
This option selects the full-fledged version of SRCU.
config TASKS_RCU
bool
default n
@ -612,11 +641,17 @@ config RCU_FANOUT_LEAF
initialization. These systems tend to run CPU-bound, and thus
are not helped by synchronized interrupts, and thus tend to
skew them, which reduces lock contention enough that large
leaf-level fanouts work well.
leaf-level fanouts work well. That said, setting leaf-level
fanout to a large number will likely cause problematic
lock contention on the leaf-level rcu_node structures unless
you boot with the skew_tick kernel parameter.
Select a specific number if testing RCU itself.
Select the maximum permissible value for large systems.
Select the maximum permissible value for large systems, but
please understand that you may also need to set the skew_tick
kernel boot parameter to avoid contention on the rcu_node
structure's locks.
Take the default if unsure.

4
kernel/fork.c
View File

@ -1313,7 +1313,7 @@ void __cleanup_sighand(struct sighand_struct *sighand)
if (atomic_dec_and_test(&sighand->count)) {
signalfd_cleanup(sighand);
/*
* sighand_cachep is SLAB_DESTROY_BY_RCU so we can free it
* sighand_cachep is SLAB_TYPESAFE_BY_RCU so we can free it
* without an RCU grace period, see __lock_task_sighand().
*/
kmem_cache_free(sighand_cachep, sighand);
@ -2144,7 +2144,7 @@ void __init proc_caches_init(void)
{
sighand_cachep = kmem_cache_create("sighand_cache",
sizeof(struct sighand_struct), 0,
SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_DESTROY_BY_RCU|
SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_TYPESAFE_BY_RCU|
SLAB_NOTRACK|SLAB_ACCOUNT, sighand_ctor);
signal_cachep = kmem_cache_create("signal_cache",
sizeof(struct signal_struct), 0,

86
kernel/locking/lockdep.c
View File

@ -1144,10 +1144,10 @@ print_circular_bug_header(struct lock_list *entry, unsigned int depth,
return 0;
printk("\n");
printk("======================================================\n");
printk("[ INFO: possible circular locking dependency detected ]\n");
pr_warn("======================================================\n");
pr_warn("WARNING: possible circular locking dependency detected\n");
print_kernel_ident();
printk("-------------------------------------------------------\n");
pr_warn("------------------------------------------------------\n");
printk("%s/%d is trying to acquire lock:\n",
curr->comm, task_pid_nr(curr));
print_lock(check_src);
@ -1482,11 +1482,11 @@ print_bad_irq_dependency(struct task_struct *curr,
return 0;
printk("\n");
printk("======================================================\n");
printk("[ INFO: %s-safe -> %s-unsafe lock order detected ]\n",
pr_warn("=====================================================\n");
pr_warn("WARNING: %s-safe -> %s-unsafe lock order detected\n",
irqclass, irqclass);
print_kernel_ident();
printk("------------------------------------------------------\n");
pr_warn("-----------------------------------------------------\n");
printk("%s/%d [HC%u[%lu]:SC%u[%lu]:HE%u:SE%u] is trying to acquire:\n",
curr->comm, task_pid_nr(curr),
curr->hardirq_context, hardirq_count() >> HARDIRQ_SHIFT,
@ -1711,10 +1711,10 @@ print_deadlock_bug(struct task_struct *curr, struct held_lock *prev,
return 0;
printk("\n");
printk("=============================================\n");
printk("[ INFO: possible recursive locking detected ]\n");
pr_warn("============================================\n");
pr_warn("WARNING: possible recursive locking detected\n");
print_kernel_ident();
printk("---------------------------------------------\n");
pr_warn("--------------------------------------------\n");
printk("%s/%d is trying to acquire lock:\n",
curr->comm, task_pid_nr(curr));
print_lock(next);
@ -2061,10 +2061,10 @@ static void print_collision(struct task_struct *curr,
struct lock_chain *chain)
{
printk("\n");
printk("======================\n");
printk("[chain_key collision ]\n");
pr_warn("============================\n");
pr_warn("WARNING: chain_key collision\n");
print_kernel_ident();
printk("----------------------\n");
pr_warn("----------------------------\n");
printk("%s/%d: ", current->comm, task_pid_nr(current));
printk("Hash chain already cached but the contents don't match!\n");
@ -2360,10 +2360,10 @@ print_usage_bug(struct task_struct *curr, struct held_lock *this,
return 0;
printk("\n");
printk("=================================\n");
printk("[ INFO: inconsistent lock state ]\n");
pr_warn("================================\n");
pr_warn("WARNING: inconsistent lock state\n");
print_kernel_ident();
printk("---------------------------------\n");
pr_warn("--------------------------------\n");
printk("inconsistent {%s} -> {%s} usage.\n",
usage_str[prev_bit], usage_str[new_bit]);
@ -2425,10 +2425,10 @@ print_irq_inversion_bug(struct task_struct *curr,
return 0;
printk("\n");
printk("=========================================================\n");
printk("[ INFO: possible irq lock inversion dependency detected ]\n");
pr_warn("========================================================\n");
pr_warn("WARNING: possible irq lock inversion dependency detected\n");
print_kernel_ident();
printk("---------------------------------------------------------\n");
pr_warn("--------------------------------------------------------\n");
printk("%s/%d just changed the state of lock:\n",
curr->comm, task_pid_nr(curr));
print_lock(this);
@ -3170,10 +3170,10 @@ print_lock_nested_lock_not_held(struct task_struct *curr,
return 0;
printk("\n");
printk("==================================\n");
printk("[ BUG: Nested lock was not taken ]\n");
pr_warn("==================================\n");
pr_warn("WARNING: Nested lock was not taken\n");
print_kernel_ident();
printk("----------------------------------\n");
pr_warn("----------------------------------\n");
printk("%s/%d is trying to lock:\n", curr->comm, task_pid_nr(curr));
print_lock(hlock);
@ -3383,10 +3383,10 @@ print_unlock_imbalance_bug(struct task_struct *curr, struct lockdep_map *lock,
return 0;
printk("\n");
printk("=====================================\n");
printk("[ BUG: bad unlock balance detected! ]\n");
pr_warn("=====================================\n");
pr_warn("WARNING: bad unlock balance detected!\n");
print_kernel_ident();
printk("-------------------------------------\n");
pr_warn("-------------------------------------\n");
printk("%s/%d is trying to release lock (",
curr->comm, task_pid_nr(curr));
print_lockdep_cache(lock);
@ -3880,10 +3880,10 @@ print_lock_contention_bug(struct task_struct *curr, struct lockdep_map *lock,
return 0;
printk("\n");
printk("=================================\n");
printk("[ BUG: bad contention detected! ]\n");
pr_warn("=================================\n");
pr_warn("WARNING: bad contention detected!\n");
print_kernel_ident();
printk("---------------------------------\n");
pr_warn("---------------------------------\n");
printk("%s/%d is trying to contend lock (",
curr->comm, task_pid_nr(curr));
print_lockdep_cache(lock);
@ -4244,10 +4244,10 @@ print_freed_lock_bug(struct task_struct *curr, const void *mem_from,
return;
printk("\n");
printk("=========================\n");
printk("[ BUG: held lock freed! ]\n");
pr_warn("=========================\n");
pr_warn("WARNING: held lock freed!\n");
print_kernel_ident();
printk("-------------------------\n");
pr_warn("-------------------------\n");
printk("%s/%d is freeing memory %p-%p, with a lock still held there!\n",
curr->comm, task_pid_nr(curr), mem_from, mem_to-1);
print_lock(hlock);
@ -4302,11 +4302,11 @@ static void print_held_locks_bug(void)
return;
printk("\n");
printk("=====================================\n");
printk("[ BUG: %s/%d still has locks held! ]\n",
pr_warn("====================================\n");
pr_warn("WARNING: %s/%d still has locks held!\n",
current->comm, task_pid_nr(current));
print_kernel_ident();
printk("-------------------------------------\n");
pr_warn("------------------------------------\n");
lockdep_print_held_locks(current);
printk("\nstack backtrace:\n");
dump_stack();
@ -4371,7 +4371,7 @@ retry:
} while_each_thread(g, p);
printk("\n");
printk("=============================================\n\n");
pr_warn("=============================================\n\n");
if (unlock)
read_unlock(&tasklist_lock);
@ -4401,10 +4401,10 @@ asmlinkage __visible void lockdep_sys_exit(void)
if (!debug_locks_off())
return;
printk("\n");
printk("================================================\n");
printk("[ BUG: lock held when returning to user space! ]\n");
pr_warn("================================================\n");
pr_warn("WARNING: lock held when returning to user space!\n");
print_kernel_ident();
printk("------------------------------------------------\n");
pr_warn("------------------------------------------------\n");
printk("%s/%d is leaving the kernel with locks still held!\n",
curr->comm, curr->pid);
lockdep_print_held_locks(curr);
@ -4421,13 +4421,13 @@ void lockdep_rcu_suspicious(const char *file, const int line, const char *s)
#endif /* #ifdef CONFIG_PROVE_RCU_REPEATEDLY */
/* Note: the following can be executed concurrently, so be careful. */
printk("\n");
pr_err("===============================\n");
pr_err("[ ERR: suspicious RCU usage. ]\n");
pr_warn("=============================\n");
pr_warn("WARNING: suspicious RCU usage\n");
print_kernel_ident();
pr_err("-------------------------------\n");
pr_err("%s:%d %s!\n", file, line, s);
pr_err("\nother info that might help us debug this:\n\n");
pr_err("\n%srcu_scheduler_active = %d, debug_locks = %d\n",
pr_warn("-----------------------------\n");
printk("%s:%d %s!\n", file, line, s);
printk("\nother info that might help us debug this:\n\n");
printk("\n%srcu_scheduler_active = %d, debug_locks = %d\n",
!rcu_lockdep_current_cpu_online()
? "RCU used illegally from offline CPU!\n"
: !rcu_is_watching()

9
kernel/locking/rtmutex-debug.c
View File

@ -102,10 +102,11 @@ void debug_rt_mutex_print_deadlock(struct rt_mutex_waiter *waiter)
return;
}
printk("\n============================================\n");
printk( "[ BUG: circular locking deadlock detected! ]\n");
printk("%s\n", print_tainted());
printk( "--------------------------------------------\n");
pr_warn("\n");
pr_warn("============================================\n");
pr_warn("WARNING: circular locking deadlock detected!\n");
pr_warn("%s\n", print_tainted());
pr_warn("--------------------------------------------\n");
printk("%s/%d is deadlocking current task %s/%d\n\n",
task->comm, task_pid_nr(task),
current->comm, task_pid_nr(current));

4
kernel/rcu/Makefile
View File

@ -3,7 +3,9 @@
KCOV_INSTRUMENT := n
obj-y += update.o sync.o
obj-$(CONFIG_SRCU) += srcu.o
obj-$(CONFIG_CLASSIC_SRCU) += srcu.o
obj-$(CONFIG_TREE_SRCU) += srcutree.o
obj-$(CONFIG_TINY_SRCU) += srcutiny.o
obj-$(CONFIG_RCU_TORTURE_TEST) += rcutorture.o
obj-$(CONFIG_RCU_PERF_TEST) += rcuperf.o
obj-$(CONFIG_TREE_RCU) += tree.o

153
kernel/rcu/rcu.h
View File

@ -56,6 +56,83 @@
#define DYNTICK_TASK_EXIT_IDLE (DYNTICK_TASK_NEST_VALUE + \
DYNTICK_TASK_FLAG)
/*
* Grace-period counter management.
*/
#define RCU_SEQ_CTR_SHIFT 2
#define RCU_SEQ_STATE_MASK ((1 << RCU_SEQ_CTR_SHIFT) - 1)
/*
* Return the counter portion of a sequence number previously returned
* by rcu_seq_snap() or rcu_seq_current().
*/
static inline unsigned long rcu_seq_ctr(unsigned long s)
{
return s >> RCU_SEQ_CTR_SHIFT;
}
/*
* Return the state portion of a sequence number previously returned
* by rcu_seq_snap() or rcu_seq_current().
*/
static inline int rcu_seq_state(unsigned long s)
{
return s & RCU_SEQ_STATE_MASK;
}
/*
* Set the state portion of the pointed-to sequence number.
* The caller is responsible for preventing conflicting updates.
*/
static inline void rcu_seq_set_state(unsigned long *sp, int newstate)
{
WARN_ON_ONCE(newstate & ~RCU_SEQ_STATE_MASK);
WRITE_ONCE(*sp, (*sp & ~RCU_SEQ_STATE_MASK) + newstate);
}
/* Adjust sequence number for start of update-side operation. */
static inline void rcu_seq_start(unsigned long *sp)
{
WRITE_ONCE(*sp, *sp + 1);
smp_mb(); /* Ensure update-side operation after counter increment. */
WARN_ON_ONCE(rcu_seq_state(*sp) != 1);
}
/* Adjust sequence number for end of update-side operation. */
static inline void rcu_seq_end(unsigned long *sp)
{
smp_mb(); /* Ensure update-side operation before counter increment. */
WARN_ON_ONCE(!rcu_seq_state(*sp));
WRITE_ONCE(*sp, (*sp | RCU_SEQ_STATE_MASK) + 1);
}
/* Take a snapshot of the update side's sequence number. */
static inline unsigned long rcu_seq_snap(unsigned long *sp)
{
unsigned long s;
s = (READ_ONCE(*sp) + 2 * RCU_SEQ_STATE_MASK + 1) & ~RCU_SEQ_STATE_MASK;
smp_mb(); /* Above access must not bleed into critical section. */
return s;
}
/* Return the current value the update side's sequence number, no ordering. */
static inline unsigned long rcu_seq_current(unsigned long *sp)
{
return READ_ONCE(*sp);
}
/*
* Given a snapshot from rcu_seq_snap(), determine whether or not a
* full update-side operation has occurred.
*/
static inline bool rcu_seq_done(unsigned long *sp, unsigned long s)
{
return ULONG_CMP_GE(READ_ONCE(*sp), s);
}
/*
* debug_rcu_head_queue()/debug_rcu_head_unqueue() are used internally
* by call_rcu() and rcu callback execution, and are therefore not part of the
@ -109,12 +186,12 @@ static inline bool __rcu_reclaim(const char *rn, struct rcu_head *head)
rcu_lock_acquire(&rcu_callback_map);
if (__is_kfree_rcu_offset(offset)) {
RCU_TRACE(trace_rcu_invoke_kfree_callback(rn, head, offset));
RCU_TRACE(trace_rcu_invoke_kfree_callback(rn, head, offset);)
kfree((void *)head - offset);
rcu_lock_release(&rcu_callback_map);
return true;
} else {
RCU_TRACE(trace_rcu_invoke_callback(rn, head));
RCU_TRACE(trace_rcu_invoke_callback(rn, head);)
head->func(head);
rcu_lock_release(&rcu_callback_map);
return false;
@ -144,4 +221,76 @@ void rcu_test_sync_prims(void);
*/
extern void resched_cpu(int cpu);
#if defined(SRCU) || !defined(TINY_RCU)
#include <linux/rcu_node_tree.h>
extern int rcu_num_lvls;
extern int num_rcu_lvl[];
extern int rcu_num_nodes;
static bool rcu_fanout_exact;
static int rcu_fanout_leaf;
/*
* Compute the per-level fanout, either using the exact fanout specified
* or balancing the tree, depending on the rcu_fanout_exact boot parameter.
*/
static inline void rcu_init_levelspread(int *levelspread, const int *levelcnt)
{
int i;
if (rcu_fanout_exact) {
levelspread[rcu_num_lvls - 1] = rcu_fanout_leaf;
for (i = rcu_num_lvls - 2; i >= 0; i--)
levelspread[i] = RCU_FANOUT;
} else {
int ccur;
int cprv;
cprv = nr_cpu_ids;
for (i = rcu_num_lvls - 1; i >= 0; i--) {
ccur = levelcnt[i];
levelspread[i] = (cprv + ccur - 1) / ccur;
cprv = ccur;
}
}
}
/*
* Do a full breadth-first scan of the rcu_node structures for the
* specified rcu_state structure.
*/
#define rcu_for_each_node_breadth_first(rsp, rnp) \
for ((rnp) = &(rsp)->node[0]; \
(rnp) < &(rsp)->node[rcu_num_nodes]; (rnp)++)
/*
* Do a breadth-first scan of the non-leaf rcu_node structures for the
* specified rcu_state structure. Note that if there is a singleton
* rcu_node tree with but one rcu_node structure, this loop is a no-op.
*/
#define rcu_for_each_nonleaf_node_breadth_first(rsp, rnp) \
for ((rnp) = &(rsp)->node[0]; \
(rnp) < (rsp)->level[rcu_num_lvls - 1]; (rnp)++)
/*
* Scan the leaves of the rcu_node hierarchy for the specified rcu_state
* structure. Note that if there is a singleton rcu_node tree with but
* one rcu_node structure, this loop -will- visit the rcu_node structure.
* It is still a leaf node, even if it is also the root node.
*/
#define rcu_for_each_leaf_node(rsp, rnp) \
for ((rnp) = (rsp)->level[rcu_num_lvls - 1]; \
(rnp) < &(rsp)->node[rcu_num_nodes]; (rnp)++)
/*
* Iterate over all possible CPUs in a leaf RCU node.
*/
#define for_each_leaf_node_possible_cpu(rnp, cpu) \
for ((cpu) = cpumask_next(rnp->grplo - 1, cpu_possible_mask); \
cpu <= rnp->grphi; \
cpu = cpumask_next((cpu), cpu_possible_mask))
#endif /* #if defined(SRCU) || !defined(TINY_RCU) */
#endif /* __LINUX_RCU_H */

35
kernel/rcu/rcutorture.c
View File

@ -559,19 +559,34 @@ static void srcu_torture_barrier(void)
static void srcu_torture_stats(void)
{
int cpu;
int idx = srcu_ctlp->completed & 0x1;
int __maybe_unused cpu;
int idx;
pr_alert("%s%s per-CPU(idx=%d):",
#if defined(CONFIG_TREE_SRCU) || defined(CONFIG_CLASSIC_SRCU)
#ifdef CONFIG_TREE_SRCU
idx = srcu_ctlp->srcu_idx & 0x1;
#else /* #ifdef CONFIG_TREE_SRCU */
idx = srcu_ctlp->completed & 0x1;
#endif /* #else #ifdef CONFIG_TREE_SRCU */
pr_alert("%s%s Tree SRCU per-CPU(idx=%d):",
torture_type, TORTURE_FLAG, idx);
for_each_possible_cpu(cpu) {
unsigned long l0, l1;
unsigned long u0, u1;
long c0, c1;
struct srcu_array *counts = per_cpu_ptr(srcu_ctlp->per_cpu_ref, cpu);
#ifdef CONFIG_TREE_SRCU
struct srcu_data *counts;
counts = per_cpu_ptr(srcu_ctlp->sda, cpu);
u0 = counts->srcu_unlock_count[!idx];
u1 = counts->srcu_unlock_count[idx];
#else /* #ifdef CONFIG_TREE_SRCU */
struct srcu_array *counts;
counts = per_cpu_ptr(srcu_ctlp->per_cpu_ref, cpu);
u0 = counts->unlock_count[!idx];
u1 = counts->unlock_count[idx];
#endif /* #else #ifdef CONFIG_TREE_SRCU */
/*
* Make sure that a lock is always counted if the corresponding
@ -579,14 +594,26 @@ static void srcu_torture_stats(void)
*/
smp_rmb();
#ifdef CONFIG_TREE_SRCU
l0 = counts->srcu_lock_count[!idx];
l1 = counts->srcu_lock_count[idx];
#else /* #ifdef CONFIG_TREE_SRCU */
l0 = counts->lock_count[!idx];
l1 = counts->lock_count[idx];
#endif /* #else #ifdef CONFIG_TREE_SRCU */
c0 = l0 - u0;
c1 = l1 - u1;
pr_cont(" %d(%ld,%ld)", cpu, c0, c1);
}
pr_cont("\n");
#elif defined(CONFIG_TINY_SRCU)
idx = READ_ONCE(srcu_ctlp->srcu_idx) & 0x1;
pr_alert("%s%s Tiny SRCU per-CPU(idx=%d): (%d,%d)\n",
torture_type, TORTURE_FLAG, idx,
READ_ONCE(srcu_ctlp->srcu_lock_nesting[!idx]),
READ_ONCE(srcu_ctlp->srcu_lock_nesting[idx]));
#endif
}
static void srcu_torture_synchronize_expedited(void)

12
kernel/rcu/srcu.c
View File

@ -22,7 +22,7 @@
* Lai Jiangshan <laijs@cn.fujitsu.com>
*
* For detailed explanation of Read-Copy Update mechanism see -
* Documentation/RCU/ *.txt
* Documentation/RCU/ *.txt
*
*/
@ -243,8 +243,14 @@ static bool srcu_readers_active(struct srcu_struct *sp)
* cleanup_srcu_struct - deconstruct a sleep-RCU structure
* @sp: structure to clean up.
*
* Must invoke this after you are finished using a given srcu_struct that
* was initialized via init_srcu_struct(), else you leak memory.
* Must invoke this only after you are finished using a given srcu_struct
* that was initialized via init_srcu_struct(). This code does some
* probabalistic checking, spotting late uses of srcu_read_lock(),
* synchronize_srcu(), synchronize_srcu_expedited(), and call_srcu().
* If any such late uses are detected, the per-CPU memory associated with
* the srcu_struct is simply leaked and WARN_ON() is invoked. If the
* caller frees the srcu_struct itself, a use-after-free crash will likely
* ensue, but at least there will be a warning printed.
*/
void cleanup_srcu_struct(struct srcu_struct *sp)
{

215
kernel/rcu/srcutiny.c Normal file
View File

@ -0,0 +1,215 @@
/*
* Sleepable Read-Copy Update mechanism for mutual exclusion,
* tiny version for non-preemptible single-CPU use.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, you can access it online at
* http://www.gnu.org/licenses/gpl-2.0.html.
*
* Copyright (C) IBM Corporation, 2017
*
* Author: Paul McKenney <paulmck@us.ibm.com>
*/
#include <linux/export.h>
#include <linux/mutex.h>
#include <linux/preempt.h>
#include <linux/rcupdate_wait.h>
#include <linux/sched.h>
#include <linux/delay.h>
#include <linux/srcu.h>
#include <linux/rcu_node_tree.h>
#include "rcu.h"
static int init_srcu_struct_fields(struct srcu_struct *sp)
{
sp->srcu_lock_nesting[0] = 0;
sp->srcu_lock_nesting[1] = 0;
init_swait_queue_head(&sp->srcu_wq);
sp->srcu_gp_seq = 0;
rcu_segcblist_init(&sp->srcu_cblist);
sp->srcu_gp_running = false;
sp->srcu_gp_waiting = false;
sp->srcu_idx = 0;
INIT_WORK(&sp->srcu_work, srcu_drive_gp);
return 0;
}
#ifdef CONFIG_DEBUG_LOCK_ALLOC
int __init_srcu_struct(struct srcu_struct *sp, const char *name,
struct lock_class_key *key)
{
/* Don't re-initialize a lock while it is held. */
debug_check_no_locks_freed((void *)sp, sizeof(*sp));
lockdep_init_map(&sp->dep_map, name, key, 0);
return init_srcu_struct_fields(sp);
}
EXPORT_SYMBOL_GPL(__init_srcu_struct);
#else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
/*
* init_srcu_struct - initialize a sleep-RCU structure
* @sp: structure to initialize.
*
* Must invoke this on a given srcu_struct before passing that srcu_struct
* to any other function. Each srcu_struct represents a separate domain
* of SRCU protection.
*/
int init_srcu_struct(struct srcu_struct *sp)
{
return init_srcu_struct_fields(sp);
}
EXPORT_SYMBOL_GPL(init_srcu_struct);
#endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */
/*
* cleanup_srcu_struct - deconstruct a sleep-RCU structure
* @sp: structure to clean up.
*
* Must invoke this after you are finished using a given srcu_struct that
* was initialized via init_srcu_struct(), else you leak memory.
*/
void cleanup_srcu_struct(struct srcu_struct *sp)
{
WARN_ON(sp->srcu_lock_nesting[0] || sp->srcu_lock_nesting[1]);
flush_work(&sp->srcu_work);
WARN_ON(rcu_seq_state(sp->srcu_gp_seq));
WARN_ON(sp->srcu_gp_running);
WARN_ON(sp->srcu_gp_waiting);
WARN_ON(!rcu_segcblist_empty(&sp->srcu_cblist));
}
EXPORT_SYMBOL_GPL(cleanup_srcu_struct);
/*
* Counts the new reader in the appropriate per-CPU element of the
* srcu_struct. Must be called from process context.
* Returns an index that must be passed to the matching srcu_read_unlock().
*/
int __srcu_read_lock(struct srcu_struct *sp)
{
int idx;
idx = READ_ONCE(sp->srcu_idx);
WRITE_ONCE(sp->srcu_lock_nesting[idx], sp->srcu_lock_nesting[idx] + 1);
return idx;
}
EXPORT_SYMBOL_GPL(__srcu_read_lock);
/*
* Removes the count for the old reader from the appropriate element of
* the srcu_struct. Must be called from process context.
*/
void __srcu_read_unlock(struct srcu_struct *sp, int idx)
{
int newval = sp->srcu_lock_nesting[idx] - 1;
WRITE_ONCE(sp->srcu_lock_nesting[idx], newval);
if (!newval && READ_ONCE(sp->srcu_gp_waiting))
swake_up(&sp->srcu_wq);
}
EXPORT_SYMBOL_GPL(__srcu_read_unlock);
/*
* Workqueue handler to drive one grace period and invoke any callbacks
* that become ready as a result. Single-CPU and !PREEMPT operation
* means that we get away with murder on synchronization. ;-)
*/
void srcu_drive_gp(struct work_struct *wp)
{
int idx;
struct rcu_cblist ready_cbs;
struct srcu_struct *sp;
struct rcu_head *rhp;
sp = container_of(wp, struct srcu_struct, srcu_work);
if (sp->srcu_gp_running || rcu_segcblist_empty(&sp->srcu_cblist))
return; /* Already running or nothing to do. */
/* Tag recently arrived callbacks and wait for readers. */
WRITE_ONCE(sp->srcu_gp_running, true);
rcu_segcblist_accelerate(&sp->srcu_cblist,
rcu_seq_snap(&sp->srcu_gp_seq));
rcu_seq_start(&sp->srcu_gp_seq);
idx = sp->srcu_idx;
WRITE_ONCE(sp->srcu_idx, !sp->srcu_idx);
WRITE_ONCE(sp->srcu_gp_waiting, true); /* srcu_read_unlock() wakes! */
swait_event(sp->srcu_wq, !READ_ONCE(sp->srcu_lock_nesting[idx]));
WRITE_ONCE(sp->srcu_gp_waiting, false); /* srcu_read_unlock() cheap. */
rcu_seq_end(&sp->srcu_gp_seq);
/* Update callback list based on GP, and invoke ready callbacks. */
rcu_segcblist_advance(&sp->srcu_cblist,
rcu_seq_current(&sp->srcu_gp_seq));
if (rcu_segcblist_ready_cbs(&sp->srcu_cblist)) {
rcu_cblist_init(&ready_cbs);
local_irq_disable();
rcu_segcblist_extract_done_cbs(&sp->srcu_cblist, &ready_cbs);
local_irq_enable();
rhp = rcu_cblist_dequeue(&ready_cbs);
for (; rhp != NULL; rhp = rcu_cblist_dequeue(&ready_cbs)) {
local_bh_disable();
rhp->func(rhp);
local_bh_enable();
}
local_irq_disable();
rcu_segcblist_insert_count(&sp->srcu_cblist, &ready_cbs);
local_irq_enable();
}
WRITE_ONCE(sp->srcu_gp_running, false);
/*
* If more callbacks, reschedule ourselves. This can race with
* a call_srcu() at interrupt level, but the ->srcu_gp_running
* checks will straighten that out.
*/
if (!rcu_segcblist_empty(&sp->srcu_cblist))
schedule_work(&sp->srcu_work);
}
EXPORT_SYMBOL_GPL(srcu_drive_gp);
/*
* Enqueue an SRCU callback on the specified srcu_struct structure,
* initiating grace-period processing if it is not already running.
*/
void call_srcu(struct srcu_struct *sp, struct rcu_head *head,
rcu_callback_t func)
{
unsigned long flags;
head->func = func;
local_irq_save(flags);
rcu_segcblist_enqueue(&sp->srcu_cblist, head, false);
local_irq_restore(flags);
if (!READ_ONCE(sp->srcu_gp_running))
schedule_work(&sp->srcu_work);
}
EXPORT_SYMBOL_GPL(call_srcu);
/*
* synchronize_srcu - wait for prior SRCU read-side critical-section completion
*/
void synchronize_srcu(struct srcu_struct *sp)
{
struct rcu_synchronize rs;
init_rcu_head_on_stack(&rs.head);
init_completion(&rs.completion);
call_srcu(sp, &rs.head, wakeme_after_rcu);
wait_for_completion(&rs.completion);
destroy_rcu_head_on_stack(&rs.head);
}
EXPORT_SYMBOL_GPL(synchronize_srcu);

996
kernel/rcu/srcutree.c Normal file
View File

@ -0,0 +1,996 @@
/*
* Sleepable Read-Copy Update mechanism for mutual exclusion.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, you can access it online at
* http://www.gnu.org/licenses/gpl-2.0.html.
*
* Copyright (C) IBM Corporation, 2006
* Copyright (C) Fujitsu, 2012
*
* Author: Paul McKenney <paulmck@us.ibm.com>
* Lai Jiangshan <laijs@cn.fujitsu.com>
*
* For detailed explanation of Read-Copy Update mechanism see -
* Documentation/RCU/ *.txt
*
*/
#include <linux/export.h>
#include <linux/mutex.h>
#include <linux/percpu.h>
#include <linux/preempt.h>
#include <linux/rcupdate_wait.h>
#include <linux/sched.h>
#include <linux/smp.h>
#include <linux/delay.h>
#include <linux/srcu.h>
#include "rcu.h"
static void srcu_invoke_callbacks(struct work_struct *work);
static void srcu_reschedule(struct srcu_struct *sp, unsigned long delay);
/*
* Initialize SRCU combining tree. Note that statically allocated
* srcu_struct structures might already have srcu_read_lock() and
* srcu_read_unlock() running against them. So if the is_static parameter
* is set, don't initialize ->srcu_lock_count[] and ->srcu_unlock_count[].
*/
static void init_srcu_struct_nodes(struct srcu_struct *sp, bool is_static)
{
int cpu;
int i;
int level = 0;
int levelspread[RCU_NUM_LVLS];
struct srcu_data *sdp;
struct srcu_node *snp;
struct srcu_node *snp_first;
/* Work out the overall tree geometry. */
sp->level[0] = &sp->node[0];
for (i = 1; i < rcu_num_lvls; i++)
sp->level[i] = sp->level[i - 1] + num_rcu_lvl[i - 1];
rcu_init_levelspread(levelspread, num_rcu_lvl);
/* Each pass through this loop initializes one srcu_node structure. */
rcu_for_each_node_breadth_first(sp, snp) {
spin_lock_init(&snp->lock);
for (i = 0; i < ARRAY_SIZE(snp->srcu_have_cbs); i++)
snp->srcu_have_cbs[i] = 0;
snp->grplo = -1;
snp->grphi = -1;
if (snp == &sp->node[0]) {
/* Root node, special case. */
snp->srcu_parent = NULL;
continue;
}
/* Non-root node. */
if (snp == sp->level[level + 1])
level++;
snp->srcu_parent = sp->level[level - 1] +
(snp - sp->level[level]) /
levelspread[level - 1];
}
/*
* Initialize the per-CPU srcu_data array, which feeds into the
* leaves of the srcu_node tree.
*/
WARN_ON_ONCE(ARRAY_SIZE(sdp->srcu_lock_count) !=
ARRAY_SIZE(sdp->srcu_unlock_count));
level = rcu_num_lvls - 1;
snp_first = sp->level[level];
for_each_possible_cpu(cpu) {
sdp = per_cpu_ptr(sp->sda, cpu);
spin_lock_init(&sdp->lock);
rcu_segcblist_init(&sdp->srcu_cblist);
sdp->srcu_cblist_invoking = false;
sdp->srcu_gp_seq_needed = sp->srcu_gp_seq;
sdp->mynode = &snp_first[cpu / levelspread[level]];
for (snp = sdp->mynode; snp != NULL; snp = snp->srcu_parent) {
if (snp->grplo < 0)
snp->grplo = cpu;
snp->grphi = cpu;
}
sdp->cpu = cpu;
INIT_DELAYED_WORK(&sdp->work, srcu_invoke_callbacks);
sdp->sp = sp;
if (is_static)
continue;
/* Dynamically allocated, better be no srcu_read_locks()! */
for (i = 0; i < ARRAY_SIZE(sdp->srcu_lock_count); i++) {
sdp->srcu_lock_count[i] = 0;
sdp->srcu_unlock_count[i] = 0;
}
}
}
/*
* Initialize non-compile-time initialized fields, including the
* associated srcu_node and srcu_data structures. The is_static
* parameter is passed through to init_srcu_struct_nodes(), and
* also tells us that ->sda has already been wired up to srcu_data.
*/
static int init_srcu_struct_fields(struct srcu_struct *sp, bool is_static)
{
mutex_init(&sp->srcu_cb_mutex);
mutex_init(&sp->srcu_gp_mutex);
sp->srcu_idx = 0;
sp->srcu_gp_seq = 0;
atomic_set(&sp->srcu_exp_cnt, 0);
sp->srcu_barrier_seq = 0;
mutex_init(&sp->srcu_barrier_mutex);
atomic_set(&sp->srcu_barrier_cpu_cnt, 0);
INIT_DELAYED_WORK(&sp->work, process_srcu);
if (!is_static)
sp->sda = alloc_percpu(struct srcu_data);
init_srcu_struct_nodes(sp, is_static);
smp_store_release(&sp->srcu_gp_seq_needed, 0); /* Init done. */
return sp->sda ? 0 : -ENOMEM;
}
#ifdef CONFIG_DEBUG_LOCK_ALLOC
int __init_srcu_struct(struct srcu_struct *sp, const char *name,
struct lock_class_key *key)
{
/* Don't re-initialize a lock while it is held. */
debug_check_no_locks_freed((void *)sp, sizeof(*sp));
lockdep_init_map(&sp->dep_map, name, key, 0);
spin_lock_init(&sp->gp_lock);
return init_srcu_struct_fields(sp, false);
}
EXPORT_SYMBOL_GPL(__init_srcu_struct);
#else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
/**
* init_srcu_struct - initialize a sleep-RCU structure
* @sp: structure to initialize.
*
* Must invoke this on a given srcu_struct before passing that srcu_struct
* to any other function. Each srcu_struct represents a separate domain
* of SRCU protection.
*/
int init_srcu_struct(struct srcu_struct *sp)
{
spin_lock_init(&sp->gp_lock);
return init_srcu_struct_fields(sp, false);
}
EXPORT_SYMBOL_GPL(init_srcu_struct);
#endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */
/*
* First-use initialization of statically allocated srcu_struct
* structure. Wiring up the combining tree is more than can be
* done with compile-time initialization, so this check is added
* to each update-side SRCU primitive. Use ->gp_lock, which -is-
* compile-time initialized, to resolve races involving multiple
* CPUs trying to garner first-use privileges.
*/
static void check_init_srcu_struct(struct srcu_struct *sp)
{
unsigned long flags;
WARN_ON_ONCE(rcu_scheduler_active == RCU_SCHEDULER_INIT);
/* The smp_load_acquire() pairs with the smp_store_release(). */
if (!rcu_seq_state(smp_load_acquire(&sp->srcu_gp_seq_needed))) /*^^^*/
return; /* Already initialized. */
spin_lock_irqsave(&sp->gp_lock, flags);
if (!rcu_seq_state(sp->srcu_gp_seq_needed)) {
spin_unlock_irqrestore(&sp->gp_lock, flags);
return;
}
init_srcu_struct_fields(sp, true);
spin_unlock_irqrestore(&sp->gp_lock, flags);
}
/*
* Returns approximate total of the readers' ->srcu_lock_count[] values
* for the rank of per-CPU counters specified by idx.
*/
static unsigned long srcu_readers_lock_idx(struct srcu_struct *sp, int idx)
{
int cpu;
unsigned long sum = 0;
for_each_possible_cpu(cpu) {
struct srcu_data *cpuc = per_cpu_ptr(sp->sda, cpu);
sum += READ_ONCE(cpuc->srcu_lock_count[idx]);
}
return sum;
}
/*
* Returns approximate total of the readers' ->srcu_unlock_count[] values
* for the rank of per-CPU counters specified by idx.
*/
static unsigned long srcu_readers_unlock_idx(struct srcu_struct *sp, int idx)
{
int cpu;
unsigned long sum = 0;
for_each_possible_cpu(cpu) {
struct srcu_data *cpuc = per_cpu_ptr(sp->sda, cpu);
sum += READ_ONCE(cpuc->srcu_unlock_count[idx]);
}
return sum;
}
/*
* Return true if the number of pre-existing readers is determined to
* be zero.
*/
static bool srcu_readers_active_idx_check(struct srcu_struct *sp, int idx)
{
unsigned long unlocks;
unlocks = srcu_readers_unlock_idx(sp, idx);
/*
* Make sure that a lock is always counted if the corresponding
* unlock is counted. Needs to be a smp_mb() as the read side may
* contain a read from a variable that is written to before the
* synchronize_srcu() in the write side. In this case smp_mb()s
* A and B act like the store buffering pattern.
*
* This smp_mb() also pairs with smp_mb() C to prevent accesses
* after the synchronize_srcu() from being executed before the
* grace period ends.
*/
smp_mb(); /* A */
/*
* If the locks are the same as the unlocks, then there must have
* been no readers on this index at some time in between. This does
* not mean that there are no more readers, as one could have read
* the current index but not have incremented the lock counter yet.
*
* Possible bug: There is no guarantee that there haven't been
* ULONG_MAX increments of ->srcu_lock_count[] since the unlocks were
* counted, meaning that this could return true even if there are
* still active readers. Since there are no memory barriers around
* srcu_flip(), the CPU is not required to increment ->srcu_idx
* before running srcu_readers_unlock_idx(), which means that there
* could be an arbitrarily large number of critical sections that
* execute after srcu_readers_unlock_idx() but use the old value
* of ->srcu_idx.
*/
return srcu_readers_lock_idx(sp, idx) == unlocks;
}
/**
* srcu_readers_active - returns true if there are readers. and false
* otherwise
* @sp: which srcu_struct to count active readers (holding srcu_read_lock).
*
* Note that this is not an atomic primitive, and can therefore suffer
* severe errors when invoked on an active srcu_struct. That said, it
* can be useful as an error check at cleanup time.
*/
static bool srcu_readers_active(struct srcu_struct *sp)
{
int cpu;
unsigned long sum = 0;
for_each_possible_cpu(cpu) {
struct srcu_data *cpuc = per_cpu_ptr(sp->sda, cpu);
sum += READ_ONCE(cpuc->srcu_lock_count[0]);
sum += READ_ONCE(cpuc->srcu_lock_count[1]);
sum -= READ_ONCE(cpuc->srcu_unlock_count[0]);
sum -= READ_ONCE(cpuc->srcu_unlock_count[1]);
}
return sum;
}
#define SRCU_INTERVAL 1
/**
* cleanup_srcu_struct - deconstruct a sleep-RCU structure
* @sp: structure to clean up.
*
* Must invoke this after you are finished using a given srcu_struct that
* was initialized via init_srcu_struct(), else you leak memory.
*/
void cleanup_srcu_struct(struct srcu_struct *sp)
{
int cpu;
WARN_ON_ONCE(atomic_read(&sp->srcu_exp_cnt));
if (WARN_ON(srcu_readers_active(sp)))
return; /* Leakage unless caller handles error. */
flush_delayed_work(&sp->work);
for_each_possible_cpu(cpu)
flush_delayed_work(&per_cpu_ptr(sp->sda, cpu)->work);
if (WARN_ON(rcu_seq_state(READ_ONCE(sp->srcu_gp_seq)) != SRCU_STATE_IDLE) ||
WARN_ON(srcu_readers_active(sp))) {
pr_info("cleanup_srcu_struct: Active srcu_struct %p state: %d\n", sp, rcu_seq_state(READ_ONCE(sp->srcu_gp_seq)));
return; /* Caller forgot to stop doing call_srcu()? */
}
free_percpu(sp->sda);
sp->sda = NULL;
}
EXPORT_SYMBOL_GPL(cleanup_srcu_struct);
/*
* Counts the new reader in the appropriate per-CPU element of the
* srcu_struct. Must be called from process context.
* Returns an index that must be passed to the matching srcu_read_unlock().
*/
int __srcu_read_lock(struct srcu_struct *sp)
{
int idx;
idx = READ_ONCE(sp->srcu_idx) & 0x1;
__this_cpu_inc(sp->sda->srcu_lock_count[idx]);
smp_mb(); /* B */ /* Avoid leaking the critical section. */
return idx;
}
EXPORT_SYMBOL_GPL(__srcu_read_lock);
/*
* Removes the count for the old reader from the appropriate per-CPU
* element of the srcu_struct. Note that this may well be a different
* CPU than that which was incremented by the corresponding srcu_read_lock().
* Must be called from process context.
*/
void __srcu_read_unlock(struct srcu_struct *sp, int idx)
{
smp_mb(); /* C */ /* Avoid leaking the critical section. */
this_cpu_inc(sp->sda->srcu_unlock_count[idx]);
}
EXPORT_SYMBOL_GPL(__srcu_read_unlock);
/*
* We use an adaptive strategy for synchronize_srcu() and especially for
* synchronize_srcu_expedited(). We spin for a fixed time period
* (defined below) to allow SRCU readers to exit their read-side critical
* sections. If there are still some readers after a few microseconds,
* we repeatedly block for 1-millisecond time periods.
*/
#define SRCU_RETRY_CHECK_DELAY 5
/*
* Start an SRCU grace period.
*/
static void srcu_gp_start(struct srcu_struct *sp)
{
struct srcu_data *sdp = this_cpu_ptr(sp->sda);
int state;
RCU_LOCKDEP_WARN(!lockdep_is_held(&sp->gp_lock),
"Invoked srcu_gp_start() without ->gp_lock!");
WARN_ON_ONCE(ULONG_CMP_GE(sp->srcu_gp_seq, sp->srcu_gp_seq_needed));
rcu_segcblist_advance(&sdp->srcu_cblist,
rcu_seq_current(&sp->srcu_gp_seq));
(void)rcu_segcblist_accelerate(&sdp->srcu_cblist,
rcu_seq_snap(&sp->srcu_gp_seq));
rcu_seq_start(&sp->srcu_gp_seq);
state = rcu_seq_state(READ_ONCE(sp->srcu_gp_seq));
WARN_ON_ONCE(state != SRCU_STATE_SCAN1);
}
/*
* Track online CPUs to guide callback workqueue placement.
*/
DEFINE_PER_CPU(bool, srcu_online);
void srcu_online_cpu(unsigned int cpu)
{
WRITE_ONCE(per_cpu(srcu_online, cpu), true);
}
void srcu_offline_cpu(unsigned int cpu)
{
WRITE_ONCE(per_cpu(srcu_online, cpu), false);
}
/*
* Place the workqueue handler on the specified CPU if online, otherwise
* just run it whereever. This is useful for placing workqueue handlers
* that are to invoke the specified CPU's callbacks.
*/
static bool srcu_queue_delayed_work_on(int cpu, struct workqueue_struct *wq,
struct delayed_work *dwork,
unsigned long delay)
{
bool ret;
preempt_disable();
if (READ_ONCE(per_cpu(srcu_online, cpu)))
ret = queue_delayed_work_on(cpu, wq, dwork, delay);
else
ret = queue_delayed_work(wq, dwork, delay);
preempt_enable();
return ret;
}
/*
* Schedule callback invocation for the specified srcu_data structure,
* if possible, on the corresponding CPU.
*/
static void srcu_schedule_cbs_sdp(struct srcu_data *sdp, unsigned long delay)
{
srcu_queue_delayed_work_on(sdp->cpu, system_power_efficient_wq,
&sdp->work, delay);
}
/*
* Schedule callback invocation for all srcu_data structures associated
* with the specified srcu_node structure, if possible, on the corresponding
* CPUs.
*/
static void srcu_schedule_cbs_snp(struct srcu_struct *sp, struct srcu_node *snp)
{
int cpu;
for (cpu = snp->grplo; cpu <= snp->grphi; cpu++)
srcu_schedule_cbs_sdp(per_cpu_ptr(sp->sda, cpu),
atomic_read(&sp->srcu_exp_cnt) ? 0 : SRCU_INTERVAL);
}
/*
* Note the end of an SRCU grace period. Initiates callback invocation
* and starts a new grace period if needed.
*
* The ->srcu_cb_mutex acquisition does not protect any data, but
* instead prevents more than one grace period from starting while we
* are initiating callback invocation. This allows the ->srcu_have_cbs[]
* array to have a finite number of elements.
*/
static void srcu_gp_end(struct srcu_struct *sp)
{
bool cbs;
unsigned long gpseq;
int idx;
int idxnext;
struct srcu_node *snp;
/* Prevent more than one additional grace period. */
mutex_lock(&sp->srcu_cb_mutex);
/* End the current grace period. */
spin_lock_irq(&sp->gp_lock);
idx = rcu_seq_state(sp->srcu_gp_seq);
WARN_ON_ONCE(idx != SRCU_STATE_SCAN2);
rcu_seq_end(&sp->srcu_gp_seq);
gpseq = rcu_seq_current(&sp->srcu_gp_seq);
spin_unlock_irq(&sp->gp_lock);
mutex_unlock(&sp->srcu_gp_mutex);
/* A new grace period can start at this point. But only one. */
/* Initiate callback invocation as needed. */
idx = rcu_seq_ctr(gpseq) % ARRAY_SIZE(snp->srcu_have_cbs);
idxnext = (idx + 1) % ARRAY_SIZE(snp->srcu_have_cbs);
rcu_for_each_node_breadth_first(sp, snp) {
spin_lock_irq(&snp->lock);
cbs = false;
if (snp >= sp->level[rcu_num_lvls - 1])
cbs = snp->srcu_have_cbs[idx] == gpseq;
snp->srcu_have_cbs[idx] = gpseq;
rcu_seq_set_state(&snp->srcu_have_cbs[idx], 1);
spin_unlock_irq(&snp->lock);
if (cbs) {
smp_mb(); /* GP end before CB invocation. */
srcu_schedule_cbs_snp(sp, snp);
}
}
/* Callback initiation done, allow grace periods after next. */
mutex_unlock(&sp->srcu_cb_mutex);
/* Start a new grace period if needed. */
spin_lock_irq(&sp->gp_lock);
gpseq = rcu_seq_current(&sp->srcu_gp_seq);
if (!rcu_seq_state(gpseq) &&
ULONG_CMP_LT(gpseq, sp->srcu_gp_seq_needed)) {
srcu_gp_start(sp);
spin_unlock_irq(&sp->gp_lock);
/* Throttle expedited grace periods: Should be rare! */
srcu_reschedule(sp, atomic_read(&sp->srcu_exp_cnt) &&
rcu_seq_ctr(gpseq) & 0xf
? 0
: SRCU_INTERVAL);
} else {
spin_unlock_irq(&sp->gp_lock);
}
}
/*
* Funnel-locking scheme to scalably mediate many concurrent grace-period
* requests. The winner has to do the work of actually starting grace
* period s. Losers must either ensure that their desired grace-period
* number is recorded on at least their leaf srcu_node structure, or they
* must take steps to invoke their own callbacks.
*/
static void srcu_funnel_gp_start(struct srcu_struct *sp,
struct srcu_data *sdp,
unsigned long s)
{
unsigned long flags;
int idx = rcu_seq_ctr(s) % ARRAY_SIZE(sdp->mynode->srcu_have_cbs);
struct srcu_node *snp = sdp->mynode;
unsigned long snp_seq;
/* Each pass through the loop does one level of the srcu_node tree. */
for (; snp != NULL; snp = snp->srcu_parent) {
if (rcu_seq_done(&sp->srcu_gp_seq, s) && snp != sdp->mynode)
return; /* GP already done and CBs recorded. */
spin_lock_irqsave(&snp->lock, flags);
if (ULONG_CMP_GE(snp->srcu_have_cbs[idx], s)) {
snp_seq = snp->srcu_have_cbs[idx];
spin_unlock_irqrestore(&snp->lock, flags);
if (snp == sdp->mynode && snp_seq != s) {
smp_mb(); /* CBs after GP! */
srcu_schedule_cbs_sdp(sdp, 0);
}
return;
}
snp->srcu_have_cbs[idx] = s;
spin_unlock_irqrestore(&snp->lock, flags);
}
/* Top of tree, must ensure the grace period will be started. */
spin_lock_irqsave(&sp->gp_lock, flags);
if (ULONG_CMP_LT(sp->srcu_gp_seq_needed, s)) {
/*
* Record need for grace period s. Pair with load
* acquire setting up for initialization.
*/
smp_store_release(&sp->srcu_gp_seq_needed, s); /*^^^*/
}
/* If grace period not already done and none in progress, start it. */
if (!rcu_seq_done(&sp->srcu_gp_seq, s) &&
rcu_seq_state(sp->srcu_gp_seq) == SRCU_STATE_IDLE) {
WARN_ON_ONCE(ULONG_CMP_GE(sp->srcu_gp_seq, sp->srcu_gp_seq_needed));
srcu_gp_start(sp);
queue_delayed_work(system_power_efficient_wq, &sp->work,
atomic_read(&sp->srcu_exp_cnt)
? 0
: SRCU_INTERVAL);
}
spin_unlock_irqrestore(&sp->gp_lock, flags);
}
/*
* Wait until all readers counted by array index idx complete, but
* loop an additional time if there is an expedited grace period pending.
* The caller must ensure that ->srcu_idx is not changed while checking.
*/
static bool try_check_zero(struct srcu_struct *sp, int idx, int trycount)
{
for (;;) {
if (srcu_readers_active_idx_check(sp, idx))
return true;
if (--trycount + !!atomic_read(&sp->srcu_exp_cnt) <= 0)
return false;
udelay(SRCU_RETRY_CHECK_DELAY);
}
}
/*
* Increment the ->srcu_idx counter so that future SRCU readers will
* use the other rank of the ->srcu_(un)lock_count[] arrays. This allows
* us to wait for pre-existing readers in a starvation-free manner.
*/
static void srcu_flip(struct srcu_struct *sp)
{
WRITE_ONCE(sp->srcu_idx, sp->srcu_idx + 1);
/*
* Ensure that if the updater misses an __srcu_read_unlock()
* increment, that task's next __srcu_read_lock() will see the
* above counter update. Note that both this memory barrier
* and the one in srcu_readers_active_idx_check() provide the
* guarantee for __srcu_read_lock().
*/
smp_mb(); /* D */ /* Pairs with C. */
}
/*
* Enqueue an SRCU callback on the srcu_data structure associated with
* the current CPU and the specified srcu_struct structure, initiating
* grace-period processing if it is not already running.
*
* Note that all CPUs must agree that the grace period extended beyond
* all pre-existing SRCU read-side critical section. On systems with
* more than one CPU, this means that when "func()" is invoked, each CPU
* is guaranteed to have executed a full memory barrier since the end of
* its last corresponding SRCU read-side critical section whose beginning
* preceded the call to call_rcu(). It also means that each CPU executing
* an SRCU read-side critical section that continues beyond the start of
* "func()" must have executed a memory barrier after the call_rcu()
* but before the beginning of that SRCU read-side critical section.
* Note that these guarantees include CPUs that are offline, idle, or
* executing in user mode, as well as CPUs that are executing in the kernel.
*
* Furthermore, if CPU A invoked call_rcu() and CPU B invoked the
* resulting SRCU callback function "func()", then both CPU A and CPU
* B are guaranteed to execute a full memory barrier during the time
* interval between the call to call_rcu() and the invocation of "func()".
* This guarantee applies even if CPU A and CPU B are the same CPU (but
* again only if the system has more than one CPU).
*
* Of course, these guarantees apply only for invocations of call_srcu(),
* srcu_read_lock(), and srcu_read_unlock() that are all passed the same
* srcu_struct structure.
*/
void call_srcu(struct srcu_struct *sp, struct rcu_head *rhp,
rcu_callback_t func)
{
unsigned long flags;
bool needgp = false;
unsigned long s;
struct srcu_data *sdp;
check_init_srcu_struct(sp);
rhp->func = func;
local_irq_save(flags);
sdp = this_cpu_ptr(sp->sda);
spin_lock(&sdp->lock);
rcu_segcblist_enqueue(&sdp->srcu_cblist, rhp, false);
rcu_segcblist_advance(&sdp->srcu_cblist,
rcu_seq_current(&sp->srcu_gp_seq));
s = rcu_seq_snap(&sp->srcu_gp_seq);
(void)rcu_segcblist_accelerate(&sdp->srcu_cblist, s);
if (ULONG_CMP_LT(sdp->srcu_gp_seq_needed, s)) {
sdp->srcu_gp_seq_needed = s;
needgp = true;
}
spin_unlock_irqrestore(&sdp->lock, flags);
if (needgp)
srcu_funnel_gp_start(sp, sdp, s);
}
EXPORT_SYMBOL_GPL(call_srcu);
/*
* Helper function for synchronize_srcu() and synchronize_srcu_expedited().
*/
static void __synchronize_srcu(struct srcu_struct *sp)
{
struct rcu_synchronize rcu;
RCU_LOCKDEP_WARN(lock_is_held(&sp->dep_map) ||
lock_is_held(&rcu_bh_lock_map) ||
lock_is_held(&rcu_lock_map) ||
lock_is_held(&rcu_sched_lock_map),
"Illegal synchronize_srcu() in same-type SRCU (or in RCU) read-side critical section");
if (rcu_scheduler_active == RCU_SCHEDULER_INACTIVE)
return;
might_sleep();
check_init_srcu_struct(sp);
init_completion(&rcu.completion);
init_rcu_head_on_stack(&rcu.head);
call_srcu(sp, &rcu.head, wakeme_after_rcu);
wait_for_completion(&rcu.completion);
destroy_rcu_head_on_stack(&rcu.head);
}
/**
* synchronize_srcu_expedited - Brute-force SRCU grace period
* @sp: srcu_struct with which to synchronize.
*
* Wait for an SRCU grace period to elapse, but be more aggressive about
* spinning rather than blocking when waiting.
*
* Note that synchronize_srcu_expedited() has the same deadlock and
* memory-ordering properties as does synchronize_srcu().
*/
void synchronize_srcu_expedited(struct srcu_struct *sp)
{
bool do_norm = rcu_gp_is_normal();
check_init_srcu_struct(sp);
if (!do_norm) {
atomic_inc(&sp->srcu_exp_cnt);
smp_mb__after_atomic(); /* increment before GP. */
}
__synchronize_srcu(sp);
if (!do_norm) {
smp_mb__before_atomic(); /* GP before decrement. */
WARN_ON_ONCE(atomic_dec_return(&sp->srcu_exp_cnt) < 0);
}
}
EXPORT_SYMBOL_GPL(synchronize_srcu_expedited);
/**
* synchronize_srcu - wait for prior SRCU read-side critical-section completion
* @sp: srcu_struct with which to synchronize.
*
* Wait for the count to drain to zero of both indexes. To avoid the
* possible starvation of synchronize_srcu(), it waits for the count of
* the index=((->srcu_idx & 1) ^ 1) to drain to zero at first,
* and then flip the srcu_idx and wait for the count of the other index.
*
* Can block; must be called from process context.
*
* Note that it is illegal to call synchronize_srcu() from the corresponding
* SRCU read-side critical section; doing so will result in deadlock.
* However, it is perfectly legal to call synchronize_srcu() on one
* srcu_struct from some other srcu_struct's read-side critical section,
* as long as the resulting graph of srcu_structs is acyclic.
*
* There are memory-ordering constraints implied by synchronize_srcu().
* On systems with more than one CPU, when synchronize_srcu() returns,
* each CPU is guaranteed to have executed a full memory barrier since
* the end of its last corresponding SRCU-sched read-side critical section
* whose beginning preceded the call to synchronize_srcu(). In addition,
* each CPU having an SRCU read-side critical section that extends beyond
* the return from synchronize_srcu() is guaranteed to have executed a
* full memory barrier after the beginning of synchronize_srcu() and before
* the beginning of that SRCU read-side critical section. Note that these
* guarantees include CPUs that are offline, idle, or executing in user mode,
* as well as CPUs that are executing in the kernel.
*
* Furthermore, if CPU A invoked synchronize_srcu(), which returned
* to its caller on CPU B, then both CPU A and CPU B are guaranteed
* to have executed a full memory barrier during the execution of
* synchronize_srcu(). This guarantee applies even if CPU A and CPU B
* are the same CPU, but again only if the system has more than one CPU.
*
* Of course, these memory-ordering guarantees apply only when
* synchronize_srcu(), srcu_read_lock(), and srcu_read_unlock() are
* passed the same srcu_struct structure.
*/
void synchronize_srcu(struct srcu_struct *sp)
{
if (rcu_gp_is_expedited())
synchronize_srcu_expedited(sp);
else
__synchronize_srcu(sp);
}
EXPORT_SYMBOL_GPL(synchronize_srcu);
/*
* Callback function for srcu_barrier() use.
*/
static void srcu_barrier_cb(struct rcu_head *rhp)
{
struct srcu_data *sdp;
struct srcu_struct *sp;
sdp = container_of(rhp, struct srcu_data, srcu_barrier_head);
sp = sdp->sp;
if (atomic_dec_and_test(&sp->srcu_barrier_cpu_cnt))
complete(&sp->srcu_barrier_completion);
}
/**
* srcu_barrier - Wait until all in-flight call_srcu() callbacks complete.
* @sp: srcu_struct on which to wait for in-flight callbacks.
*/
void srcu_barrier(struct srcu_struct *sp)
{
int cpu;
struct srcu_data *sdp;
unsigned long s = rcu_seq_snap(&sp->srcu_barrier_seq);
check_init_srcu_struct(sp);
mutex_lock(&sp->srcu_barrier_mutex);
if (rcu_seq_done(&sp->srcu_barrier_seq, s)) {
smp_mb(); /* Force ordering following return. */
mutex_unlock(&sp->srcu_barrier_mutex);
return; /* Someone else did our work for us. */
}
rcu_seq_start(&sp->srcu_barrier_seq);
init_completion(&sp->srcu_barrier_completion);
/* Initial count prevents reaching zero until all CBs are posted. */
atomic_set(&sp->srcu_barrier_cpu_cnt, 1);
/*
* Each pass through this loop enqueues a callback, but only
* on CPUs already having callbacks enqueued. Note that if
* a CPU already has callbacks enqueue, it must have already
* registered the need for a future grace period, so all we
* need do is enqueue a callback that will use the same
* grace period as the last callback already in the queue.
*/
for_each_possible_cpu(cpu) {
sdp = per_cpu_ptr(sp->sda, cpu);
spin_lock_irq(&sdp->lock);
atomic_inc(&sp->srcu_barrier_cpu_cnt);
sdp->srcu_barrier_head.func = srcu_barrier_cb;
if (!rcu_segcblist_entrain(&sdp->srcu_cblist,
&sdp->srcu_barrier_head, 0))
atomic_dec(&sp->srcu_barrier_cpu_cnt);
spin_unlock_irq(&sdp->lock);
}
/* Remove the initial count, at which point reaching zero can happen. */
if (atomic_dec_and_test(&sp->srcu_barrier_cpu_cnt))
complete(&sp->srcu_barrier_completion);
wait_for_completion(&sp->srcu_barrier_completion);
rcu_seq_end(&sp->srcu_barrier_seq);
mutex_unlock(&sp->srcu_barrier_mutex);
}
EXPORT_SYMBOL_GPL(srcu_barrier);
/**
* srcu_batches_completed - return batches completed.
* @sp: srcu_struct on which to report batch completion.
*
* Report the number of batches, correlated with, but not necessarily
* precisely the same as, the number of grace periods that have elapsed.
*/
unsigned long srcu_batches_completed(struct srcu_struct *sp)
{
return sp->srcu_idx;
}
EXPORT_SYMBOL_GPL(srcu_batches_completed);
/*
* Core SRCU state machine. Push state bits of ->srcu_gp_seq
* to SRCU_STATE_SCAN2, and invoke srcu_gp_end() when scan has
* completed in that state.
*/
static void srcu_advance_state(struct srcu_struct *sp)
{
int idx;
mutex_lock(&sp->srcu_gp_mutex);
/*
* Because readers might be delayed for an extended period after
* fetching ->srcu_idx for their index, at any point in time there
* might well be readers using both idx=0 and idx=1. We therefore
* need to wait for readers to clear from both index values before
* invoking a callback.
*
* The load-acquire ensures that we see the accesses performed
* by the prior grace period.
*/
idx = rcu_seq_state(smp_load_acquire(&sp->srcu_gp_seq)); /* ^^^ */
if (idx == SRCU_STATE_IDLE) {
spin_lock_irq(&sp->gp_lock);
if (ULONG_CMP_GE(sp->srcu_gp_seq, sp->srcu_gp_seq_needed)) {
WARN_ON_ONCE(rcu_seq_state(sp->srcu_gp_seq));
spin_unlock_irq(&sp->gp_lock);
mutex_unlock(&sp->srcu_gp_mutex);
return;
}
idx = rcu_seq_state(READ_ONCE(sp->srcu_gp_seq));
if (idx == SRCU_STATE_IDLE)
srcu_gp_start(sp);
spin_unlock_irq(&sp->gp_lock);
if (idx != SRCU_STATE_IDLE) {
mutex_unlock(&sp->srcu_gp_mutex);
return; /* Someone else started the grace period. */
}
}
if (rcu_seq_state(READ_ONCE(sp->srcu_gp_seq)) == SRCU_STATE_SCAN1) {
idx = 1 ^ (sp->srcu_idx & 1);
if (!try_check_zero(sp, idx, 1)) {
mutex_unlock(&sp->srcu_gp_mutex);
return; /* readers present, retry later. */
}
srcu_flip(sp);
rcu_seq_set_state(&sp->srcu_gp_seq, SRCU_STATE_SCAN2);
}
if (rcu_seq_state(READ_ONCE(sp->srcu_gp_seq)) == SRCU_STATE_SCAN2) {
/*
* SRCU read-side critical sections are normally short,
* so check at least twice in quick succession after a flip.
*/
idx = 1 ^ (sp->srcu_idx & 1);
if (!try_check_zero(sp, idx, 2)) {
mutex_unlock(&sp->srcu_gp_mutex);
return; /* readers present, retry later. */
}
srcu_gp_end(sp); /* Releases ->srcu_gp_mutex. */
}
}
/*
* Invoke a limited number of SRCU callbacks that have passed through
* their grace period. If there are more to do, SRCU will reschedule
* the workqueue. Note that needed memory barriers have been executed
* in this task's context by srcu_readers_active_idx_check().
*/
static void srcu_invoke_callbacks(struct work_struct *work)
{
bool more;
struct rcu_cblist ready_cbs;
struct rcu_head *rhp;
struct srcu_data *sdp;
struct srcu_struct *sp;
sdp = container_of(work, struct srcu_data, work.work);
sp = sdp->sp;
rcu_cblist_init(&ready_cbs);
spin_lock_irq(&sdp->lock);
smp_mb(); /* Old grace periods before callback invocation! */
rcu_segcblist_advance(&sdp->srcu_cblist,
rcu_seq_current(&sp->srcu_gp_seq));
if (sdp->srcu_cblist_invoking ||
!rcu_segcblist_ready_cbs(&sdp->srcu_cblist)) {
spin_unlock_irq(&sdp->lock);
return; /* Someone else on the job or nothing to do. */
}
/* We are on the job! Extract and invoke ready callbacks. */
sdp->srcu_cblist_invoking = true;
rcu_segcblist_extract_done_cbs(&sdp->srcu_cblist, &ready_cbs);
spin_unlock_irq(&sdp->lock);
rhp = rcu_cblist_dequeue(&ready_cbs);
for (; rhp != NULL; rhp = rcu_cblist_dequeue(&ready_cbs)) {
local_bh_disable();
rhp->func(rhp);
local_bh_enable();
}
/*
* Update counts, accelerate new callbacks, and if needed,
* schedule another round of callback invocation.
*/
spin_lock_irq(&sdp->lock);
rcu_segcblist_insert_count(&sdp->srcu_cblist, &ready_cbs);
(void)rcu_segcblist_accelerate(&sdp->srcu_cblist,
rcu_seq_snap(&sp->srcu_gp_seq));
sdp->srcu_cblist_invoking = false;
more = rcu_segcblist_ready_cbs(&sdp->srcu_cblist);
spin_unlock_irq(&sdp->lock);
if (more)
srcu_schedule_cbs_sdp(sdp, 0);
}
/*
* Finished one round of SRCU grace period. Start another if there are
* more SRCU callbacks queued, otherwise put SRCU into not-running state.
*/
static void srcu_reschedule(struct srcu_struct *sp, unsigned long delay)
{
bool pushgp = true;
spin_lock_irq(&sp->gp_lock);
if (ULONG_CMP_GE(sp->srcu_gp_seq, sp->srcu_gp_seq_needed)) {
if (!WARN_ON_ONCE(rcu_seq_state(sp->srcu_gp_seq))) {
/* All requests fulfilled, time to go idle. */
pushgp = false;
}
} else if (!rcu_seq_state(sp->srcu_gp_seq)) {
/* Outstanding request and no GP. Start one. */
srcu_gp_start(sp);
}
spin_unlock_irq(&sp->gp_lock);
if (pushgp)
queue_delayed_work(system_power_efficient_wq, &sp->work, delay);
}
/*
* This is the work-queue function that handles SRCU grace periods.
*/
void process_srcu(struct work_struct *work)
{
struct srcu_struct *sp;
sp = container_of(work, struct srcu_struct, work.work);
srcu_advance_state(sp);
srcu_reschedule(sp, atomic_read(&sp->srcu_exp_cnt) ? 0 : SRCU_INTERVAL);
}
EXPORT_SYMBOL_GPL(process_srcu);

20
kernel/rcu/tiny.c
View File

@ -79,7 +79,7 @@ EXPORT_SYMBOL(__rcu_is_watching);
*/
static int rcu_qsctr_help(struct rcu_ctrlblk *rcp)
{
RCU_TRACE(reset_cpu_stall_ticks(rcp));
RCU_TRACE(reset_cpu_stall_ticks(rcp);)
if (rcp->donetail != rcp->curtail) {
rcp->donetail = rcp->curtail;
return 1;
@ -125,7 +125,7 @@ void rcu_bh_qs(void)
*/
void rcu_check_callbacks(int user)
{
RCU_TRACE(check_cpu_stalls());
RCU_TRACE(check_cpu_stalls();)
if (user)
rcu_sched_qs();
else if (!in_softirq())
@ -143,7 +143,7 @@ static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp)
const char *rn = NULL;
struct rcu_head *next, *list;
unsigned long flags;
RCU_TRACE(int cb_count = 0);
RCU_TRACE(int cb_count = 0;)
/* Move the ready-to-invoke callbacks to a local list. */
local_irq_save(flags);
@ -152,7 +152,7 @@ static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp)
local_irq_restore(flags);
return;
}
RCU_TRACE(trace_rcu_batch_start(rcp->name, 0, rcp->qlen, -1));
RCU_TRACE(trace_rcu_batch_start(rcp->name, 0, rcp->qlen, -1);)
list = rcp->rcucblist;
rcp->rcucblist = *rcp->donetail;
*rcp->donetail = NULL;
@ -162,7 +162,7 @@ static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp)
local_irq_restore(flags);
/* Invoke the callbacks on the local list. */
RCU_TRACE(rn = rcp->name);
RCU_TRACE(rn = rcp->name;)
while (list) {
next = list->next;
prefetch(next);
@ -171,9 +171,9 @@ static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp)
__rcu_reclaim(rn, list);
local_bh_enable();
list = next;
RCU_TRACE(cb_count++);
RCU_TRACE(cb_count++;)
}
RCU_TRACE(rcu_trace_sub_qlen(rcp, cb_count));
RCU_TRACE(rcu_trace_sub_qlen(rcp, cb_count);)
RCU_TRACE(trace_rcu_batch_end(rcp->name,
cb_count, 0, need_resched(),
is_idle_task(current),
@ -221,7 +221,7 @@ static void __call_rcu(struct rcu_head *head,
local_irq_save(flags);
*rcp->curtail = head;
rcp->curtail = &head->next;
RCU_TRACE(rcp->qlen++);
RCU_TRACE(rcp->qlen++;)
local_irq_restore(flags);
if (unlikely(is_idle_task(current))) {
@ -254,8 +254,8 @@ EXPORT_SYMBOL_GPL(call_rcu_bh);
void __init rcu_init(void)
{
open_softirq(RCU_SOFTIRQ, rcu_process_callbacks);
RCU_TRACE(reset_cpu_stall_ticks(&rcu_sched_ctrlblk));
RCU_TRACE(reset_cpu_stall_ticks(&rcu_bh_ctrlblk));
RCU_TRACE(reset_cpu_stall_ticks(&rcu_sched_ctrlblk);)
RCU_TRACE(reset_cpu_stall_ticks(&rcu_bh_ctrlblk);)
rcu_early_boot_tests();
}

13
kernel/rcu/tiny_plugin.h
View File

@ -52,7 +52,7 @@ static struct rcu_ctrlblk rcu_bh_ctrlblk = {
RCU_TRACE(.name = "rcu_bh")
};
#ifdef CONFIG_DEBUG_LOCK_ALLOC
#if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_SRCU)
#include <linux/kernel_stat.h>
int rcu_scheduler_active __read_mostly;
@ -65,15 +65,16 @@ EXPORT_SYMBOL_GPL(rcu_scheduler_active);
* to RCU_SCHEDULER_RUNNING, skipping the RCU_SCHEDULER_INIT stage.
* The reason for this is that Tiny RCU does not need kthreads, so does
* not have to care about the fact that the scheduler is half-initialized
* at a certain phase of the boot process.
* at a certain phase of the boot process. Unless SRCU is in the mix.
*/
void __init rcu_scheduler_starting(void)
{
WARN_ON(nr_context_switches() > 0);
rcu_scheduler_active = RCU_SCHEDULER_RUNNING;
rcu_scheduler_active = IS_ENABLED(CONFIG_SRCU)
? RCU_SCHEDULER_INIT : RCU_SCHEDULER_RUNNING;
}
#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
#endif /* #if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_SRCU) */
#ifdef CONFIG_RCU_TRACE
@ -162,8 +163,8 @@ static void reset_cpu_stall_ticks(struct rcu_ctrlblk *rcp)
static void check_cpu_stalls(void)
{
RCU_TRACE(check_cpu_stall(&rcu_bh_ctrlblk));
RCU_TRACE(check_cpu_stall(&rcu_sched_ctrlblk));
RCU_TRACE(check_cpu_stall(&rcu_bh_ctrlblk);)
RCU_TRACE(check_cpu_stall(&rcu_sched_ctrlblk);)
}
#endif /* #ifdef CONFIG_RCU_TRACE */

696
kernel/rcu/tree.c
View File

File diff suppressed because it is too large Load Diff

164
kernel/rcu/tree.h
View File

@ -30,80 +30,8 @@
#include <linux/seqlock.h>
#include <linux/swait.h>
#include <linux/stop_machine.h>
/*
* Define shape of hierarchy based on NR_CPUS, CONFIG_RCU_FANOUT, and
* CONFIG_RCU_FANOUT_LEAF.
* In theory, it should be possible to add more levels straightforwardly.
* In practice, this did work well going from three levels to four.
* Of course, your mileage may vary.
*/
#ifdef CONFIG_RCU_FANOUT
#define RCU_FANOUT CONFIG_RCU_FANOUT
#else /* #ifdef CONFIG_RCU_FANOUT */
# ifdef CONFIG_64BIT
# define RCU_FANOUT 64
# else
# define RCU_FANOUT 32
# endif
#endif /* #else #ifdef CONFIG_RCU_FANOUT */
#ifdef CONFIG_RCU_FANOUT_LEAF
#define RCU_FANOUT_LEAF CONFIG_RCU_FANOUT_LEAF
#else /* #ifdef CONFIG_RCU_FANOUT_LEAF */
# ifdef CONFIG_64BIT
# define RCU_FANOUT_LEAF 64
# else
# define RCU_FANOUT_LEAF 32
# endif
#endif /* #else #ifdef CONFIG_RCU_FANOUT_LEAF */
#define RCU_FANOUT_1 (RCU_FANOUT_LEAF)
#define RCU_FANOUT_2 (RCU_FANOUT_1 * RCU_FANOUT)
#define RCU_FANOUT_3 (RCU_FANOUT_2 * RCU_FANOUT)
#define RCU_FANOUT_4 (RCU_FANOUT_3 * RCU_FANOUT)
#if NR_CPUS <= RCU_FANOUT_1
# define RCU_NUM_LVLS 1
# define NUM_RCU_LVL_0 1
# define NUM_RCU_NODES NUM_RCU_LVL_0
# define NUM_RCU_LVL_INIT { NUM_RCU_LVL_0 }
# define RCU_NODE_NAME_INIT { "rcu_node_0" }
# define RCU_FQS_NAME_INIT { "rcu_node_fqs_0" }
#elif NR_CPUS <= RCU_FANOUT_2
# define RCU_NUM_LVLS 2
# define NUM_RCU_LVL_0 1
# define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_1)
# define NUM_RCU_NODES (NUM_RCU_LVL_0 + NUM_RCU_LVL_1)
# define NUM_RCU_LVL_INIT { NUM_RCU_LVL_0, NUM_RCU_LVL_1 }
# define RCU_NODE_NAME_INIT { "rcu_node_0", "rcu_node_1" }
# define RCU_FQS_NAME_INIT { "rcu_node_fqs_0", "rcu_node_fqs_1" }
#elif NR_CPUS <= RCU_FANOUT_3
# define RCU_NUM_LVLS 3
# define NUM_RCU_LVL_0 1
# define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_2)
# define NUM_RCU_LVL_2 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_1)
# define NUM_RCU_NODES (NUM_RCU_LVL_0 + NUM_RCU_LVL_1 + NUM_RCU_LVL_2)
# define NUM_RCU_LVL_INIT { NUM_RCU_LVL_0, NUM_RCU_LVL_1, NUM_RCU_LVL_2 }
# define RCU_NODE_NAME_INIT { "rcu_node_0", "rcu_node_1", "rcu_node_2" }
# define RCU_FQS_NAME_INIT { "rcu_node_fqs_0", "rcu_node_fqs_1", "rcu_node_fqs_2" }
#elif NR_CPUS <= RCU_FANOUT_4
# define RCU_NUM_LVLS 4
# define NUM_RCU_LVL_0 1
# define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_3)
# define NUM_RCU_LVL_2 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_2)
# define NUM_RCU_LVL_3 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_1)
# define NUM_RCU_NODES (NUM_RCU_LVL_0 + NUM_RCU_LVL_1 + NUM_RCU_LVL_2 + NUM_RCU_LVL_3)
# define NUM_RCU_LVL_INIT { NUM_RCU_LVL_0, NUM_RCU_LVL_1, NUM_RCU_LVL_2, NUM_RCU_LVL_3 }
# define RCU_NODE_NAME_INIT { "rcu_node_0", "rcu_node_1", "rcu_node_2", "rcu_node_3" }
# define RCU_FQS_NAME_INIT { "rcu_node_fqs_0", "rcu_node_fqs_1", "rcu_node_fqs_2", "rcu_node_fqs_3" }
#else
# error "CONFIG_RCU_FANOUT insufficient for NR_CPUS"
#endif /* #if (NR_CPUS) <= RCU_FANOUT_1 */
extern int rcu_num_lvls;
extern int rcu_num_nodes;
#include <linux/rcu_segcblist.h>
#include <linux/rcu_node_tree.h>
/*
* Dynticks per-CPU state.
@ -113,6 +41,9 @@ struct rcu_dynticks {
/* Process level is worth LLONG_MAX/2. */
int dynticks_nmi_nesting; /* Track NMI nesting level. */
atomic_t dynticks; /* Even value for idle, else odd. */
bool rcu_need_heavy_qs; /* GP old, need heavy quiescent state. */
unsigned long rcu_qs_ctr; /* Light universal quiescent state ctr. */
bool rcu_urgent_qs; /* GP old need light quiescent state. */
#ifdef CONFIG_NO_HZ_FULL_SYSIDLE
long long dynticks_idle_nesting;
/* irq/process nesting level from idle. */
@ -261,41 +192,6 @@ struct rcu_node {
*/
#define leaf_node_cpu_bit(rnp, cpu) (1UL << ((cpu) - (rnp)->grplo))
/*
* Do a full breadth-first scan of the rcu_node structures for the
* specified rcu_state structure.
*/
#define rcu_for_each_node_breadth_first(rsp, rnp) \
for ((rnp) = &(rsp)->node[0]; \
(rnp) < &(rsp)->node[rcu_num_nodes]; (rnp)++)
/*
* Do a breadth-first scan of the non-leaf rcu_node structures for the
* specified rcu_state structure. Note that if there is a singleton
* rcu_node tree with but one rcu_node structure, this loop is a no-op.
*/
#define rcu_for_each_nonleaf_node_breadth_first(rsp, rnp) \
for ((rnp) = &(rsp)->node[0]; \
(rnp) < (rsp)->level[rcu_num_lvls - 1]; (rnp)++)
/*
* Scan the leaves of the rcu_node hierarchy for the specified rcu_state
* structure. Note that if there is a singleton rcu_node tree with but
* one rcu_node structure, this loop -will- visit the rcu_node structure.
* It is still a leaf node, even if it is also the root node.
*/
#define rcu_for_each_leaf_node(rsp, rnp) \
for ((rnp) = (rsp)->level[rcu_num_lvls - 1]; \
(rnp) < &(rsp)->node[rcu_num_nodes]; (rnp)++)
/*
* Iterate over all possible CPUs in a leaf RCU node.
*/
#define for_each_leaf_node_possible_cpu(rnp, cpu) \
for ((cpu) = cpumask_next(rnp->grplo - 1, cpu_possible_mask); \
cpu <= rnp->grphi; \
cpu = cpumask_next((cpu), cpu_possible_mask))
/*
* Union to allow "aggregate OR" operation on the need for a quiescent
* state by the normal and expedited grace periods.
@ -336,34 +232,9 @@ struct rcu_data {
/* period it is aware of. */
/* 2) batch handling */
/*
* If nxtlist is not NULL, it is partitioned as follows.
* Any of the partitions might be empty, in which case the
* pointer to that partition will be equal to the pointer for
* the following partition. When the list is empty, all of
* the nxttail elements point to the ->nxtlist pointer itself,
* which in that case is NULL.
*
* [nxtlist, *nxttail[RCU_DONE_TAIL]):
* Entries that batch # <= ->completed
* The grace period for these entries has completed, and
* the other grace-period-completed entries may be moved
* here temporarily in rcu_process_callbacks().
* [*nxttail[RCU_DONE_TAIL], *nxttail[RCU_WAIT_TAIL]):
* Entries that batch # <= ->completed - 1: waiting for current GP
* [*nxttail[RCU_WAIT_TAIL], *nxttail[RCU_NEXT_READY_TAIL]):
* Entries known to have arrived before current GP ended
* [*nxttail[RCU_NEXT_READY_TAIL], *nxttail[RCU_NEXT_TAIL]):
* Entries that might have arrived after current GP ended
* Note that the value of *nxttail[RCU_NEXT_TAIL] will
* always be NULL, as this is the end of the list.
*/
struct rcu_head *nxtlist;
struct rcu_head **nxttail[RCU_NEXT_SIZE];
unsigned long nxtcompleted[RCU_NEXT_SIZE];
/* grace periods for sublists. */
long qlen_lazy; /* # of lazy queued callbacks */
long qlen; /* # of queued callbacks, incl lazy */
struct rcu_segcblist cblist; /* Segmented callback list, with */
/* different callbacks waiting for */
/* different grace periods. */
long qlen_last_fqs_check;
/* qlen at last check for QS forcing */
unsigned long n_cbs_invoked; /* count of RCU cbs invoked. */
@ -482,7 +353,6 @@ struct rcu_state {
struct rcu_node *level[RCU_NUM_LVLS + 1];
/* Hierarchy levels (+1 to */
/* shut bogus gcc warning) */
u8 flavor_mask; /* bit in flavor mask. */
struct rcu_data __percpu *rda; /* pointer of percu rcu_data. */
call_rcu_func_t call; /* call_rcu() flavor. */
int ncpus; /* # CPUs seen so far. */
@ -502,14 +372,11 @@ struct rcu_state {
raw_spinlock_t orphan_lock ____cacheline_internodealigned_in_smp;
/* Protect following fields. */
struct rcu_head *orphan_nxtlist; /* Orphaned callbacks that */
struct rcu_cblist orphan_pend; /* Orphaned callbacks that */
/* need a grace period. */
struct rcu_head **orphan_nxttail; /* Tail of above. */
struct rcu_head *orphan_donelist; /* Orphaned callbacks that */
struct rcu_cblist orphan_done; /* Orphaned callbacks that */
/* are ready to invoke. */
struct rcu_head **orphan_donetail; /* Tail of above. */
long qlen_lazy; /* Number of lazy callbacks. */
long qlen; /* Total number of callbacks. */
/* (Contains counts.) */
/* End of fields guarded by orphan_lock. */
struct mutex barrier_mutex; /* Guards barrier fields. */
@ -596,6 +463,7 @@ extern struct rcu_state rcu_preempt_state;
#endif /* #ifdef CONFIG_PREEMPT_RCU */
int rcu_dynticks_snap(struct rcu_dynticks *rdtp);
bool rcu_eqs_special_set(int cpu);
#ifdef CONFIG_RCU_BOOST
DECLARE_PER_CPU(unsigned int, rcu_cpu_kthread_status);
@ -673,6 +541,14 @@ static bool rcu_nohz_full_cpu(struct rcu_state *rsp);
static void rcu_dynticks_task_enter(void);
static void rcu_dynticks_task_exit(void);
#ifdef CONFIG_SRCU
void srcu_online_cpu(unsigned int cpu);
void srcu_offline_cpu(unsigned int cpu);
#else /* #ifdef CONFIG_SRCU */
void srcu_online_cpu(unsigned int cpu) { }
void srcu_offline_cpu(unsigned int cpu) { }
#endif /* #else #ifdef CONFIG_SRCU */
#endif /* #ifndef RCU_TREE_NONCORE */
#ifdef CONFIG_RCU_TRACE

25
kernel/rcu/tree_exp.h
View File

@ -292,7 +292,7 @@ static bool exp_funnel_lock(struct rcu_state *rsp, unsigned long s)
trace_rcu_exp_funnel_lock(rsp->name, rnp->level,
rnp->grplo, rnp->grphi,
TPS("wait"));
wait_event(rnp->exp_wq[(s >> 1) & 0x3],
wait_event(rnp->exp_wq[rcu_seq_ctr(s) & 0x3],
sync_exp_work_done(rsp,
&rdp->exp_workdone2, s));
return true;
@ -331,6 +331,8 @@ static void sync_sched_exp_handler(void *data)
return;
}
__this_cpu_write(rcu_sched_data.cpu_no_qs.b.exp, true);
/* Store .exp before .rcu_urgent_qs. */
smp_store_release(this_cpu_ptr(&rcu_dynticks.rcu_urgent_qs), true);
resched_cpu(smp_processor_id());
}
@ -531,7 +533,8 @@ static void rcu_exp_wait_wake(struct rcu_state *rsp, unsigned long s)
rnp->exp_seq_rq = s;
spin_unlock(&rnp->exp_lock);
}
wake_up_all(&rnp->exp_wq[(rsp->expedited_sequence >> 1) & 0x3]);
smp_mb(); /* All above changes before wakeup. */
wake_up_all(&rnp->exp_wq[rcu_seq_ctr(rsp->expedited_sequence) & 0x3]);
}
trace_rcu_exp_grace_period(rsp->name, s, TPS("endwake"));
mutex_unlock(&rsp->exp_wake_mutex);
@ -609,9 +612,9 @@ static void _synchronize_rcu_expedited(struct rcu_state *rsp,
/* Wait for expedited grace period to complete. */
rdp = per_cpu_ptr(rsp->rda, raw_smp_processor_id());
rnp = rcu_get_root(rsp);
wait_event(rnp->exp_wq[(s >> 1) & 0x3],
sync_exp_work_done(rsp,
&rdp->exp_workdone0, s));
wait_event(rnp->exp_wq[rcu_seq_ctr(s) & 0x3],
sync_exp_work_done(rsp, &rdp->exp_workdone0, s));
smp_mb(); /* Workqueue actions happen before return. */
/* Let the next expedited grace period start. */
mutex_unlock(&rsp->exp_mutex);
@ -735,15 +738,3 @@ void synchronize_rcu_expedited(void)
EXPORT_SYMBOL_GPL(synchronize_rcu_expedited);
#endif /* #else #ifdef CONFIG_PREEMPT_RCU */
/*
* Switch to run-time mode once Tree RCU has fully initialized.
*/
static int __init rcu_exp_runtime_mode(void)
{
rcu_test_sync_prims();
rcu_scheduler_active = RCU_SCHEDULER_RUNNING;
rcu_test_sync_prims();
return 0;
}
core_initcall(rcu_exp_runtime_mode);

64
kernel/rcu/tree_plugin.h
View File

@ -1350,10 +1350,10 @@ static bool __maybe_unused rcu_try_advance_all_cbs(void)
*/
if ((rdp->completed != rnp->completed ||
unlikely(READ_ONCE(rdp->gpwrap))) &&
rdp->nxttail[RCU_DONE_TAIL] != rdp->nxttail[RCU_NEXT_TAIL])
rcu_segcblist_pend_cbs(&rdp->cblist))
note_gp_changes(rsp, rdp);
if (cpu_has_callbacks_ready_to_invoke(rdp))
if (rcu_segcblist_ready_cbs(&rdp->cblist))
cbs_ready = true;
}
return cbs_ready;
@ -1461,7 +1461,7 @@ static void rcu_prepare_for_idle(void)
rdtp->last_accelerate = jiffies;
for_each_rcu_flavor(rsp) {
rdp = this_cpu_ptr(rsp->rda);
if (!*rdp->nxttail[RCU_DONE_TAIL])
if (rcu_segcblist_pend_cbs(&rdp->cblist))
continue;
rnp = rdp->mynode;
raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */
@ -1529,7 +1529,7 @@ static void rcu_oom_notify_cpu(void *unused)
for_each_rcu_flavor(rsp) {
rdp = raw_cpu_ptr(rsp->rda);
if (rdp->qlen_lazy != 0) {
if (rcu_segcblist_n_lazy_cbs(&rdp->cblist)) {
atomic_inc(&oom_callback_count);
rsp->call(&rdp->oom_head, rcu_oom_callback);
}
@ -1709,7 +1709,7 @@ __setup("rcu_nocbs=", rcu_nocb_setup);
static int __init parse_rcu_nocb_poll(char *arg)
{
rcu_nocb_poll = 1;
rcu_nocb_poll = true;
return 0;
}
early_param("rcu_nocb_poll", parse_rcu_nocb_poll);
@ -1860,7 +1860,9 @@ static void __call_rcu_nocb_enqueue(struct rcu_data *rdp,
trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
TPS("WakeEmpty"));
} else {
rdp->nocb_defer_wakeup = RCU_NOGP_WAKE;
WRITE_ONCE(rdp->nocb_defer_wakeup, RCU_NOGP_WAKE);
/* Store ->nocb_defer_wakeup before ->rcu_urgent_qs. */
smp_store_release(this_cpu_ptr(&rcu_dynticks.rcu_urgent_qs), true);
trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
TPS("WakeEmptyIsDeferred"));
}
@ -1872,7 +1874,9 @@ static void __call_rcu_nocb_enqueue(struct rcu_data *rdp,
trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
TPS("WakeOvf"));
} else {
rdp->nocb_defer_wakeup = RCU_NOGP_WAKE_FORCE;
WRITE_ONCE(rdp->nocb_defer_wakeup, RCU_NOGP_WAKE_FORCE);
/* Store ->nocb_defer_wakeup before ->rcu_urgent_qs. */
smp_store_release(this_cpu_ptr(&rcu_dynticks.rcu_urgent_qs), true);
trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
TPS("WakeOvfIsDeferred"));
}
@ -1930,30 +1934,26 @@ static bool __maybe_unused rcu_nocb_adopt_orphan_cbs(struct rcu_state *rsp,
struct rcu_data *rdp,
unsigned long flags)
{
long ql = rsp->qlen;
long qll = rsp->qlen_lazy;
long ql = rcu_cblist_n_cbs(&rsp->orphan_done);
long qll = rcu_cblist_n_lazy_cbs(&rsp->orphan_done);
/* If this is not a no-CBs CPU, tell the caller to do it the old way. */
if (!rcu_is_nocb_cpu(smp_processor_id()))
return false;
rsp->qlen = 0;
rsp->qlen_lazy = 0;
/* First, enqueue the donelist, if any. This preserves CB ordering. */
if (rsp->orphan_donelist != NULL) {
__call_rcu_nocb_enqueue(rdp, rsp->orphan_donelist,
rsp->orphan_donetail, ql, qll, flags);
ql = qll = 0;
rsp->orphan_donelist = NULL;
rsp->orphan_donetail = &rsp->orphan_donelist;
if (!rcu_cblist_empty(&rsp->orphan_done)) {
__call_rcu_nocb_enqueue(rdp, rcu_cblist_head(&rsp->orphan_done),
rcu_cblist_tail(&rsp->orphan_done),
ql, qll, flags);
}
if (rsp->orphan_nxtlist != NULL) {
__call_rcu_nocb_enqueue(rdp, rsp->orphan_nxtlist,
rsp->orphan_nxttail, ql, qll, flags);
ql = qll = 0;
rsp->orphan_nxtlist = NULL;
rsp->orphan_nxttail = &rsp->orphan_nxtlist;
if (!rcu_cblist_empty(&rsp->orphan_pend)) {
__call_rcu_nocb_enqueue(rdp, rcu_cblist_head(&rsp->orphan_pend),
rcu_cblist_tail(&rsp->orphan_pend),
ql, qll, flags);
}
rcu_cblist_init(&rsp->orphan_done);
rcu_cblist_init(&rsp->orphan_pend);
return true;
}
@ -2395,16 +2395,16 @@ static bool init_nocb_callback_list(struct rcu_data *rdp)
return false;
/* If there are early-boot callbacks, move them to nocb lists. */
if (rdp->nxtlist) {
rdp->nocb_head = rdp->nxtlist;
rdp->nocb_tail = rdp->nxttail[RCU_NEXT_TAIL];
atomic_long_set(&rdp->nocb_q_count, rdp->qlen);
atomic_long_set(&rdp->nocb_q_count_lazy, rdp->qlen_lazy);
rdp->nxtlist = NULL;
rdp->qlen = 0;
rdp->qlen_lazy = 0;
if (!rcu_segcblist_empty(&rdp->cblist)) {
rdp->nocb_head = rcu_segcblist_head(&rdp->cblist);
rdp->nocb_tail = rcu_segcblist_tail(&rdp->cblist);
atomic_long_set(&rdp->nocb_q_count,
rcu_segcblist_n_cbs(&rdp->cblist));
atomic_long_set(&rdp->nocb_q_count_lazy,
rcu_segcblist_n_lazy_cbs(&rdp->cblist));
rcu_segcblist_init(&rdp->cblist);
}
rdp->nxttail[RCU_NEXT_TAIL] = NULL;
rcu_segcblist_disable(&rdp->cblist);
return true;
}

26
kernel/rcu/tree_trace.c
View File

@ -41,11 +41,11 @@
#include <linux/mutex.h>
#include <linux/debugfs.h>
#include <linux/seq_file.h>
#include <linux/prefetch.h>
#define RCU_TREE_NONCORE
#include "tree.h"
DECLARE_PER_CPU_SHARED_ALIGNED(unsigned long, rcu_qs_ctr);
#include "rcu.h"
static int r_open(struct inode *inode, struct file *file,
const struct seq_operations *op)
@ -121,7 +121,7 @@ static void print_one_rcu_data(struct seq_file *m, struct rcu_data *rdp)
cpu_is_offline(rdp->cpu) ? '!' : ' ',
ulong2long(rdp->completed), ulong2long(rdp->gpnum),
rdp->cpu_no_qs.b.norm,
rdp->rcu_qs_ctr_snap == per_cpu(rcu_qs_ctr, rdp->cpu),
rdp->rcu_qs_ctr_snap == per_cpu(rdp->dynticks->rcu_qs_ctr, rdp->cpu),
rdp->core_needs_qs);
seq_printf(m, " dt=%d/%llx/%d df=%lu",
rcu_dynticks_snap(rdp->dynticks),
@ -130,17 +130,15 @@ static void print_one_rcu_data(struct seq_file *m, struct rcu_data *rdp)
rdp->dynticks_fqs);
seq_printf(m, " of=%lu", rdp->offline_fqs);
rcu_nocb_q_lengths(rdp, &ql, &qll);
qll += rdp->qlen_lazy;
ql += rdp->qlen;
qll += rcu_segcblist_n_lazy_cbs(&rdp->cblist);
ql += rcu_segcblist_n_cbs(&rdp->cblist);
seq_printf(m, " ql=%ld/%ld qs=%c%c%c%c",
qll, ql,
".N"[rdp->nxttail[RCU_NEXT_READY_TAIL] !=
rdp->nxttail[RCU_NEXT_TAIL]],
".R"[rdp->nxttail[RCU_WAIT_TAIL] !=
rdp->nxttail[RCU_NEXT_READY_TAIL]],
".W"[rdp->nxttail[RCU_DONE_TAIL] !=
rdp->nxttail[RCU_WAIT_TAIL]],
".D"[&rdp->nxtlist != rdp->nxttail[RCU_DONE_TAIL]]);
".N"[!rcu_segcblist_segempty(&rdp->cblist, RCU_NEXT_TAIL)],
".R"[!rcu_segcblist_segempty(&rdp->cblist,
RCU_NEXT_READY_TAIL)],
".W"[!rcu_segcblist_segempty(&rdp->cblist, RCU_WAIT_TAIL)],
".D"[!rcu_segcblist_segempty(&rdp->cblist, RCU_DONE_TAIL)]);
#ifdef CONFIG_RCU_BOOST
seq_printf(m, " kt=%d/%c ktl=%x",
per_cpu(rcu_cpu_has_work, rdp->cpu),
@ -278,7 +276,9 @@ static void print_one_rcu_state(struct seq_file *m, struct rcu_state *rsp)
seq_printf(m, "nfqs=%lu/nfqsng=%lu(%lu) fqlh=%lu oqlen=%ld/%ld\n",
rsp->n_force_qs, rsp->n_force_qs_ngp,
rsp->n_force_qs - rsp->n_force_qs_ngp,
READ_ONCE(rsp->n_force_qs_lh), rsp->qlen_lazy, rsp->qlen);
READ_ONCE(rsp->n_force_qs_lh),
rcu_cblist_n_lazy_cbs(&rsp->orphan_done),
rcu_cblist_n_cbs(&rsp->orphan_done));
for (rnp = &rsp->node[0]; rnp - &rsp->node[0] < rcu_num_nodes; rnp++) {
if (rnp->level != level) {
seq_puts(m, "\n");

53
kernel/rcu/update.c
View File

@ -124,7 +124,7 @@ EXPORT_SYMBOL(rcu_read_lock_sched_held);
* non-expedited counterparts? Intended for use within RCU. Note
* that if the user specifies both rcu_expedited and rcu_normal, then
* rcu_normal wins. (Except during the time period during boot from
* when the first task is spawned until the rcu_exp_runtime_mode()
* when the first task is spawned until the rcu_set_runtime_mode()
* core_initcall() is invoked, at which point everything is expedited.)
*/
bool rcu_gp_is_normal(void)
@ -190,6 +190,39 @@ void rcu_end_inkernel_boot(void)
#endif /* #ifndef CONFIG_TINY_RCU */
/*
* Test each non-SRCU synchronous grace-period wait API. This is
* useful just after a change in mode for these primitives, and
* during early boot.
*/
void rcu_test_sync_prims(void)
{
if (!IS_ENABLED(CONFIG_PROVE_RCU))
return;
synchronize_rcu();
synchronize_rcu_bh();
synchronize_sched();
synchronize_rcu_expedited();
synchronize_rcu_bh_expedited();
synchronize_sched_expedited();
}
#if !defined(CONFIG_TINY_RCU) || defined(CONFIG_SRCU)
/*
* Switch to run-time mode once RCU has fully initialized.
*/
static int __init rcu_set_runtime_mode(void)
{
rcu_test_sync_prims();
rcu_scheduler_active = RCU_SCHEDULER_RUNNING;
rcu_test_sync_prims();
return 0;
}
core_initcall(rcu_set_runtime_mode);
#endif /* #if !defined(CONFIG_TINY_RCU) || defined(CONFIG_SRCU) */
#ifdef CONFIG_PREEMPT_RCU
/*
@ -632,6 +665,7 @@ static void check_holdout_task(struct task_struct *t,
put_task_struct(t);
return;
}
rcu_request_urgent_qs_task(t);
if (!needreport)
return;
if (*firstreport) {
@ -817,23 +851,6 @@ static void rcu_spawn_tasks_kthread(void)
#endif /* #ifdef CONFIG_TASKS_RCU */
/*
* Test each non-SRCU synchronous grace-period wait API. This is
* useful just after a change in mode for these primitives, and
* during early boot.
*/
void rcu_test_sync_prims(void)
{
if (!IS_ENABLED(CONFIG_PROVE_RCU))
return;
synchronize_rcu();
synchronize_rcu_bh();
synchronize_sched();
synchronize_rcu_expedited();
synchronize_rcu_bh_expedited();
synchronize_sched_expedited();
}
#ifdef CONFIG_PROVE_RCU
/*

2
kernel/sched/core.c
View File

@ -3378,7 +3378,7 @@ static void __sched notrace __schedule(bool preempt)
hrtick_clear(rq);
local_irq_disable();
rcu_note_context_switch();
rcu_note_context_switch(preempt);
/*
* Make sure that signal_pending_state()->signal_pending() below

2
kernel/signal.c
View File

@ -1237,7 +1237,7 @@ struct sighand_struct *__lock_task_sighand(struct task_struct *tsk,
}
/*
* This sighand can be already freed and even reused, but
* we rely on SLAB_DESTROY_BY_RCU and sighand_ctor() which
* we rely on SLAB_TYPESAFE_BY_RCU and sighand_ctor() which
* initializes ->siglock: this slab can't go away, it has
* the same object type, ->siglock can't be reinitialized.
*

6
mm/kasan/kasan.c
View File

@ -413,7 +413,7 @@ void kasan_cache_create(struct kmem_cache *cache, size_t *size,
*size += sizeof(struct kasan_alloc_meta);
/* Add free meta. */
if (cache->flags & SLAB_DESTROY_BY_RCU || cache->ctor ||
if (cache->flags & SLAB_TYPESAFE_BY_RCU || cache->ctor ||
cache->object_size < sizeof(struct kasan_free_meta)) {
cache->kasan_info.free_meta_offset = *size;
*size += sizeof(struct kasan_free_meta);
@ -561,7 +561,7 @@ static void kasan_poison_slab_free(struct kmem_cache *cache, void *object)
unsigned long rounded_up_size = round_up(size, KASAN_SHADOW_SCALE_SIZE);
/* RCU slabs could be legally used after free within the RCU period */
if (unlikely(cache->flags & SLAB_DESTROY_BY_RCU))
if (unlikely(cache->flags & SLAB_TYPESAFE_BY_RCU))
return;
kasan_poison_shadow(object, rounded_up_size, KASAN_KMALLOC_FREE);
@ -572,7 +572,7 @@ bool kasan_slab_free(struct kmem_cache *cache, void *object)
s8 shadow_byte;
/* RCU slabs could be legally used after free within the RCU period */
if (unlikely(cache->flags & SLAB_DESTROY_BY_RCU))
if (unlikely(cache->flags & SLAB_TYPESAFE_BY_RCU))
return false;
shadow_byte = READ_ONCE(*(s8 *)kasan_mem_to_shadow(object));

2
mm/kmemcheck.c
View File

@ -95,7 +95,7 @@ void kmemcheck_slab_alloc(struct kmem_cache *s, gfp_t gfpflags, void *object,
void kmemcheck_slab_free(struct kmem_cache *s, void *object, size_t size)
{
/* TODO: RCU freeing is unsupported for now; hide false positives. */
if (!s->ctor && !(s->flags & SLAB_DESTROY_BY_RCU))
if (!s->ctor && !(s->flags & SLAB_TYPESAFE_BY_RCU))
kmemcheck_mark_freed(object, size);
}

14
mm/mmu_notifier.c
View File

@ -21,7 +21,7 @@
#include <linux/slab.h>
/* global SRCU for all MMs */
static struct srcu_struct srcu;
DEFINE_STATIC_SRCU(srcu);
/*
* This function allows mmu_notifier::release callback to delay a call to
@ -252,12 +252,6 @@ static int do_mmu_notifier_register(struct mmu_notifier *mn,
BUG_ON(atomic_read(&mm->mm_users) <= 0);
/*
* Verify that mmu_notifier_init() already run and the global srcu is
* initialized.
*/
BUG_ON(!srcu.per_cpu_ref);
ret = -ENOMEM;
mmu_notifier_mm = kmalloc(sizeof(struct mmu_notifier_mm), GFP_KERNEL);
if (unlikely(!mmu_notifier_mm))
@ -406,9 +400,3 @@ void mmu_notifier_unregister_no_release(struct mmu_notifier *mn,
mmdrop(mm);
}
EXPORT_SYMBOL_GPL(mmu_notifier_unregister_no_release);
static int __init mmu_notifier_init(void)
{
return init_srcu_struct(&srcu);
}
subsys_initcall(mmu_notifier_init);

4
mm/rmap.c
View File

@ -430,7 +430,7 @@ static void anon_vma_ctor(void *data)
void __init anon_vma_init(void)
{
anon_vma_cachep = kmem_cache_create("anon_vma", sizeof(struct anon_vma),
0, SLAB_DESTROY_BY_RCU|SLAB_PANIC|SLAB_ACCOUNT,
0, SLAB_TYPESAFE_BY_RCU|SLAB_PANIC|SLAB_ACCOUNT,
anon_vma_ctor);
anon_vma_chain_cachep = KMEM_CACHE(anon_vma_chain,
SLAB_PANIC|SLAB_ACCOUNT);
@ -481,7 +481,7 @@ struct anon_vma *page_get_anon_vma(struct page *page)
* If this page is still mapped, then its anon_vma cannot have been
* freed. But if it has been unmapped, we have no security against the
* anon_vma structure being freed and reused (for another anon_vma:
* SLAB_DESTROY_BY_RCU guarantees that - so the atomic_inc_not_zero()
* SLAB_TYPESAFE_BY_RCU guarantees that - so the atomic_inc_not_zero()
* above cannot corrupt).
*/
if (!page_mapped(page)) {

6
mm/slab.c
View File

@ -1728,7 +1728,7 @@ static void slab_destroy(struct kmem_cache *cachep, struct page *page)
freelist = page->freelist;
slab_destroy_debugcheck(cachep, page);
if (unlikely(cachep->flags & SLAB_DESTROY_BY_RCU))
if (unlikely(cachep->flags & SLAB_TYPESAFE_BY_RCU))
call_rcu(&page->rcu_head, kmem_rcu_free);
else
kmem_freepages(cachep, page);
@ -1924,7 +1924,7 @@ static bool set_objfreelist_slab_cache(struct kmem_cache *cachep,
cachep->num = 0;
if (cachep->ctor || flags & SLAB_DESTROY_BY_RCU)
if (cachep->ctor || flags & SLAB_TYPESAFE_BY_RCU)
return false;
left = calculate_slab_order(cachep, size,
@ -2030,7 +2030,7 @@ __kmem_cache_create (struct kmem_cache *cachep, unsigned long flags)
if (size < 4096 || fls(size - 1) == fls(size-1 + REDZONE_ALIGN +
2 * sizeof(unsigned long long)))
flags |= SLAB_RED_ZONE | SLAB_STORE_USER;
if (!(flags & SLAB_DESTROY_BY_RCU))
if (!(flags & SLAB_TYPESAFE_BY_RCU))
flags |= SLAB_POISON;
#endif
#endif

4
mm/slab.h
View File

@ -126,7 +126,7 @@ static inline unsigned long kmem_cache_flags(unsigned long object_size,
/* Legal flag mask for kmem_cache_create(), for various configurations */
#define SLAB_CORE_FLAGS (SLAB_HWCACHE_ALIGN | SLAB_CACHE_DMA | SLAB_PANIC | \
SLAB_DESTROY_BY_RCU | SLAB_DEBUG_OBJECTS )
SLAB_TYPESAFE_BY_RCU | SLAB_DEBUG_OBJECTS )
#if defined(CONFIG_DEBUG_SLAB)
#define SLAB_DEBUG_FLAGS (SLAB_RED_ZONE | SLAB_POISON | SLAB_STORE_USER)
@ -415,7 +415,7 @@ static inline size_t slab_ksize(const struct kmem_cache *s)
* back there or track user information then we can
* only use the space before that information.
*/
if (s->flags & (SLAB_DESTROY_BY_RCU | SLAB_STORE_USER))
if (s->flags & (SLAB_TYPESAFE_BY_RCU | SLAB_STORE_USER))
return s->inuse;
/*
* Else we can use all the padding etc for the allocation

6
mm/slab_common.c
View File

@ -39,7 +39,7 @@ static DECLARE_WORK(slab_caches_to_rcu_destroy_work,
* Set of flags that will prevent slab merging
*/
#define SLAB_NEVER_MERGE (SLAB_RED_ZONE | SLAB_POISON | SLAB_STORE_USER | \
SLAB_TRACE | SLAB_DESTROY_BY_RCU | SLAB_NOLEAKTRACE | \
SLAB_TRACE | SLAB_TYPESAFE_BY_RCU | SLAB_NOLEAKTRACE | \
SLAB_FAILSLAB | SLAB_KASAN)
#define SLAB_MERGE_SAME (SLAB_RECLAIM_ACCOUNT | SLAB_CACHE_DMA | \
@ -500,7 +500,7 @@ static void slab_caches_to_rcu_destroy_workfn(struct work_struct *work)
struct kmem_cache *s, *s2;
/*
* On destruction, SLAB_DESTROY_BY_RCU kmem_caches are put on the
* On destruction, SLAB_TYPESAFE_BY_RCU kmem_caches are put on the
* @slab_caches_to_rcu_destroy list. The slab pages are freed
* through RCU and and the associated kmem_cache are dereferenced
* while freeing the pages, so the kmem_caches should be freed only
@ -537,7 +537,7 @@ static int shutdown_cache(struct kmem_cache *s)
memcg_unlink_cache(s);
list_del(&s->list);
if (s->flags & SLAB_DESTROY_BY_RCU) {
if (s->flags & SLAB_TYPESAFE_BY_RCU) {
list_add_tail(&s->list, &slab_caches_to_rcu_destroy);
schedule_work(&slab_caches_to_rcu_destroy_work);
} else {

6
mm/slob.c
View File

@ -126,7 +126,7 @@ static inline void clear_slob_page_free(struct page *sp)
/*
* struct slob_rcu is inserted at the tail of allocated slob blocks, which
* were created with a SLAB_DESTROY_BY_RCU slab. slob_rcu is used to free
* were created with a SLAB_TYPESAFE_BY_RCU slab. slob_rcu is used to free
* the block using call_rcu.
*/
struct slob_rcu {
@ -524,7 +524,7 @@ EXPORT_SYMBOL(ksize);
int __kmem_cache_create(struct kmem_cache *c, unsigned long flags)
{
if (flags & SLAB_DESTROY_BY_RCU) {
if (flags & SLAB_TYPESAFE_BY_RCU) {
/* leave room for rcu footer at the end of object */
c->size += sizeof(struct slob_rcu);
}
@ -598,7 +598,7 @@ static void kmem_rcu_free(struct rcu_head *head)
void kmem_cache_free(struct kmem_cache *c, void *b)
{
kmemleak_free_recursive(b, c->flags);
if (unlikely(c->flags & SLAB_DESTROY_BY_RCU)) {
if (unlikely(c->flags & SLAB_TYPESAFE_BY_RCU)) {
struct slob_rcu *slob_rcu;
slob_rcu = b + (c->size - sizeof(struct slob_rcu));
slob_rcu->size = c->size;

12
mm/slub.c
View File

@ -1687,7 +1687,7 @@ static void rcu_free_slab(struct rcu_head *h)
static void free_slab(struct kmem_cache *s, struct page *page)
{
if (unlikely(s->flags & SLAB_DESTROY_BY_RCU)) {
if (unlikely(s->flags & SLAB_TYPESAFE_BY_RCU)) {
struct rcu_head *head;
if (need_reserve_slab_rcu) {
@ -2963,7 +2963,7 @@ static __always_inline void slab_free(struct kmem_cache *s, struct page *page,
* slab_free_freelist_hook() could have put the items into quarantine.
* If so, no need to free them.
*/
if (s->flags & SLAB_KASAN && !(s->flags & SLAB_DESTROY_BY_RCU))
if (s->flags & SLAB_KASAN && !(s->flags & SLAB_TYPESAFE_BY_RCU))
return;
do_slab_free(s, page, head, tail, cnt, addr);
}
@ -3433,7 +3433,7 @@ static int calculate_sizes(struct kmem_cache *s, int forced_order)
* the slab may touch the object after free or before allocation
* then we should never poison the object itself.
*/
if ((flags & SLAB_POISON) && !(flags & SLAB_DESTROY_BY_RCU) &&
if ((flags & SLAB_POISON) && !(flags & SLAB_TYPESAFE_BY_RCU) &&
!s->ctor)
s->flags |= __OBJECT_POISON;
else
@ -3455,7 +3455,7 @@ static int calculate_sizes(struct kmem_cache *s, int forced_order)
*/
s->inuse = size;
if (((flags & (SLAB_DESTROY_BY_RCU | SLAB_POISON)) ||
if (((flags & (SLAB_TYPESAFE_BY_RCU | SLAB_POISON)) ||
s->ctor)) {
/*
* Relocate free pointer after the object if it is not
@ -3537,7 +3537,7 @@ static int kmem_cache_open(struct kmem_cache *s, unsigned long flags)
s->flags = kmem_cache_flags(s->size, flags, s->name, s->ctor);
s->reserved = 0;
if (need_reserve_slab_rcu && (s->flags & SLAB_DESTROY_BY_RCU))
if (need_reserve_slab_rcu && (s->flags & SLAB_TYPESAFE_BY_RCU))
s->reserved = sizeof(struct rcu_head);
if (!calculate_sizes(s, -1))
@ -5042,7 +5042,7 @@ SLAB_ATTR_RO(cache_dma);
static ssize_t destroy_by_rcu_show(struct kmem_cache *s, char *buf)
{
return sprintf(buf, "%d\n", !!(s->flags & SLAB_DESTROY_BY_RCU));
return sprintf(buf, "%d\n", !!(s->flags & SLAB_TYPESAFE_BY_RCU));
}
SLAB_ATTR_RO(destroy_by_rcu);

2
net/dccp/ipv4.c
View File

@ -951,7 +951,7 @@ static struct proto dccp_v4_prot = {
.orphan_count = &dccp_orphan_count,
.max_header = MAX_DCCP_HEADER,
.obj_size = sizeof(struct dccp_sock),
.slab_flags = SLAB_DESTROY_BY_RCU,
.slab_flags = SLAB_TYPESAFE_BY_RCU,
.rsk_prot = &dccp_request_sock_ops,
.twsk_prot = &dccp_timewait_sock_ops,
.h.hashinfo = &dccp_hashinfo,

2
net/dccp/ipv6.c
View File

@ -1014,7 +1014,7 @@ static struct proto dccp_v6_prot = {
.orphan_count = &dccp_orphan_count,
.max_header = MAX_DCCP_HEADER,
.obj_size = sizeof(struct dccp6_sock),
.slab_flags = SLAB_DESTROY_BY_RCU,
.slab_flags = SLAB_TYPESAFE_BY_RCU,
.rsk_prot = &dccp6_request_sock_ops,
.twsk_prot = &dccp6_timewait_sock_ops,
.h.hashinfo = &dccp_hashinfo,

2
net/ipv4/tcp_ipv4.c
View File

@ -2402,7 +2402,7 @@ struct proto tcp_prot = {
.sysctl_rmem = sysctl_tcp_rmem,
.max_header = MAX_TCP_HEADER,
.obj_size = sizeof(struct tcp_sock),
.slab_flags = SLAB_DESTROY_BY_RCU,
.slab_flags = SLAB_TYPESAFE_BY_RCU,
.twsk_prot = &tcp_timewait_sock_ops,
.rsk_prot = &tcp_request_sock_ops,
.h.hashinfo = &tcp_hashinfo,

2
net/ipv6/tcp_ipv6.c
View File

@ -1921,7 +1921,7 @@ struct proto tcpv6_prot = {
.sysctl_rmem = sysctl_tcp_rmem,
.max_header = MAX_TCP_HEADER,
.obj_size = sizeof(struct tcp6_sock),
.slab_flags = SLAB_DESTROY_BY_RCU,
.slab_flags = SLAB_TYPESAFE_BY_RCU,
.twsk_prot = &tcp6_timewait_sock_ops,
.rsk_prot = &tcp6_request_sock_ops,
.h.hashinfo = &tcp_hashinfo,

2
net/llc/af_llc.c
View File

@ -142,7 +142,7 @@ static struct proto llc_proto = {
.name = "LLC",
.owner = THIS_MODULE,
.obj_size = sizeof(struct llc_sock),
.slab_flags = SLAB_DESTROY_BY_RCU,
.slab_flags = SLAB_TYPESAFE_BY_RCU,
};
/**

4
net/llc/llc_conn.c
View File

@ -506,7 +506,7 @@ static struct sock *__llc_lookup_established(struct llc_sap *sap,
again:
sk_nulls_for_each_rcu(rc, node, laddr_hb) {
if (llc_estab_match(sap, daddr, laddr, rc)) {
/* Extra checks required by SLAB_DESTROY_BY_RCU */
/* Extra checks required by SLAB_TYPESAFE_BY_RCU */
if (unlikely(!atomic_inc_not_zero(&rc->sk_refcnt)))
goto again;
if (unlikely(llc_sk(rc)->sap != sap ||
@ -565,7 +565,7 @@ static struct sock *__llc_lookup_listener(struct llc_sap *sap,
again:
sk_nulls_for_each_rcu(rc, node, laddr_hb) {
if (llc_listener_match(sap, laddr, rc)) {
/* Extra checks required by SLAB_DESTROY_BY_RCU */
/* Extra checks required by SLAB_TYPESAFE_BY_RCU */
if (unlikely(!atomic_inc_not_zero(&rc->sk_refcnt)))
goto again;
if (unlikely(llc_sk(rc)->sap != sap ||

2
net/llc/llc_sap.c
View File

@ -328,7 +328,7 @@ static struct sock *llc_lookup_dgram(struct llc_sap *sap,
again:
sk_nulls_for_each_rcu(rc, node, laddr_hb) {
if (llc_dgram_match(sap, laddr, rc)) {
/* Extra checks required by SLAB_DESTROY_BY_RCU */
/* Extra checks required by SLAB_TYPESAFE_BY_RCU */
if (unlikely(!atomic_inc_not_zero(&rc->sk_refcnt)))
goto again;
if (unlikely(llc_sk(rc)->sap != sap ||

8
net/netfilter/nf_conntrack_core.c
View File

@ -918,7 +918,7 @@ static unsigned int early_drop_list(struct net *net,
continue;
/* kill only if still in same netns -- might have moved due to
* SLAB_DESTROY_BY_RCU rules.
* SLAB_TYPESAFE_BY_RCU rules.
*
* We steal the timer reference. If that fails timer has
* already fired or someone else deleted it. Just drop ref
@ -1073,7 +1073,7 @@ __nf_conntrack_alloc(struct net *net,
/*
* Do not use kmem_cache_zalloc(), as this cache uses
* SLAB_DESTROY_BY_RCU.
* SLAB_TYPESAFE_BY_RCU.
*/
ct = kmem_cache_alloc(nf_conntrack_cachep, gfp);
if (ct == NULL)
@ -1118,7 +1118,7 @@ void nf_conntrack_free(struct nf_conn *ct)
struct net *net = nf_ct_net(ct);
/* A freed object has refcnt == 0, that's
* the golden rule for SLAB_DESTROY_BY_RCU
* the golden rule for SLAB_TYPESAFE_BY_RCU
*/
NF_CT_ASSERT(atomic_read(&ct->ct_general.use) == 0);
@ -1882,7 +1882,7 @@ int nf_conntrack_init_start(void)
nf_conntrack_cachep = kmem_cache_create("nf_conntrack",
sizeof(struct nf_conn),
NFCT_INFOMASK + 1,
SLAB_DESTROY_BY_RCU | SLAB_HWCACHE_ALIGN, NULL);
SLAB_TYPESAFE_BY_RCU | SLAB_HWCACHE_ALIGN, NULL);
if (!nf_conntrack_cachep)
goto err_cachep;

2
net/smc/af_smc.c
View File

@ -101,7 +101,7 @@ struct proto smc_proto = {
.unhash = smc_unhash_sk,
.obj_size = sizeof(struct smc_sock),
.h.smc_hash = &smc_v4_hashinfo,
.slab_flags = SLAB_DESTROY_BY_RCU,
.slab_flags = SLAB_TYPESAFE_BY_RCU,
};
EXPORT_SYMBOL_GPL(smc_proto);

2
tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
View File

@ -170,7 +170,7 @@ qemu_append="`identify_qemu_append "$QEMU"`"
# Pull in Kconfig-fragment boot parameters
boot_args="`configfrag_boot_params "$boot_args" "$config_template"`"
# Generate kernel-version-specific boot parameters
boot_args="`per_version_boot_params "$boot_args" $builddir/.config $seconds`"
boot_args="`per_version_boot_params "$boot_args" $resdir/.config $seconds`"
if test -n "$TORTURE_BUILDONLY"
then