The original memory barriers in count_stat_eventual.c ensure
writing to global_count happens before writing to stopflag and
reading from stopflag happens before later reading from global_count.
Thus, smp_load_acquire and smp_store_release will suffice.
In count_lim_sig.c, there is only one ordering required, that is
writing to counter happens before setting theft to THEFT_READY in
add_count/sub_count's fast path. Therefore, partial memory barrier
will suffice.
Signed-off-by: Alan Huang <mmpgouride@xxxxxxxxx>
---
CodeSamples/count/count_lim_sig.c | 10 +++-------
CodeSamples/count/count_stat_eventual.c | 6 ++----
count/count.tex | 9 ++++-----
3 files changed, 9 insertions(+), 16 deletions(-)
diff --git a/CodeSamples/count/count_lim_sig.c b/CodeSamples/count/count_lim_sig.c
index 59da8077..c2f61197 100644
--- a/CodeSamples/count/count_lim_sig.c
+++ b/CodeSamples/count/count_lim_sig.c
@@ -56,12 +56,10 @@ static void flush_local_count_sig(int unused) //\lnlbl{flush_sig:b}
{
if (READ_ONCE(theft) != THEFT_REQ) //\lnlbl{flush_sig:check:REQ}
return; //\lnlbl{flush_sig:return:n}
- smp_mb(); //\lnlbl{flush_sig:mb:1}
WRITE_ONCE(theft, THEFT_ACK); //\lnlbl{flush_sig:set:ACK}
if (!counting) { //\lnlbl{flush_sig:check:fast}
- WRITE_ONCE(theft, THEFT_READY); //\lnlbl{flush_sig:set:READY}
+ smp_store_release(&theft, THEFT_READY); //\lnlbl{flush_sig:set:READY}
}
- smp_mb();
} //\lnlbl{flush_sig:e}
static void flush_local_count(void) //\lnlbl{flush:b}
@@ -125,8 +123,7 @@ int add_count(unsigned long delta) //\lnlbl{b}
WRITE_ONCE(counting, 0); //\lnlbl{clearcnt}
barrier(); //\lnlbl{barrier:3}
if (READ_ONCE(theft) == THEFT_ACK) { //\lnlbl{check:ACK}
- smp_mb(); //\lnlbl{mb}
- WRITE_ONCE(theft, THEFT_READY); //\lnlbl{READY}
+ smp_store_release(&theft, THEFT_READY); //\lnlbl{READY}
}
if (fastpath)
return 1; //\lnlbl{return:fs}
@@ -164,8 +161,7 @@ int sub_count(unsigned long delta)
WRITE_ONCE(counting, 0);
barrier();
if (READ_ONCE(theft) == THEFT_ACK) {
- smp_mb();
- WRITE_ONCE(theft, THEFT_READY);
+ smp_store_release(&theft, THEFT_READY);
}
if (fastpath)
return 1;
diff --git a/CodeSamples/count/count_stat_eventual.c b/CodeSamples/count/count_stat_eventual.c
index 967644de..7157ee0e 100644
--- a/CodeSamples/count/count_stat_eventual.c
+++ b/CodeSamples/count/count_stat_eventual.c
@@ -51,8 +51,7 @@ void *eventual(void *arg) //\lnlbl{eventual:b}
WRITE_ONCE(global_count, sum);
poll(NULL, 0, 1);
if (READ_ONCE(stopflag)) {
- smp_mb();
- WRITE_ONCE(stopflag, stopflag + 1);
+ smp_store_release(&stopflag, stopflag + 1);
}
}
return NULL;
@@ -73,9 +72,8 @@ void count_init(void) //\lnlbl{init:b}
void count_cleanup(void) //\lnlbl{cleanup:b}
{
WRITE_ONCE(stopflag, 1);
- while (READ_ONCE(stopflag) < 3)
+ while (smp_load_acquire(&stopflag) < 3)
poll(NULL, 0, 1);
- smp_mb();
} //\lnlbl{cleanup:e}
//\end{snippet}
diff --git a/count/count.tex b/count/count.tex
index 80ada104..899ea7e9 100644
--- a/count/count.tex
+++ b/count/count.tex
@@ -2425,12 +2425,11 @@ handler used in the theft process.
\Clnref{check:REQ,return:n} check to see if
the \co{theft} state is REQ, and, if not
returns without change.
-\Clnref{mb:1} executes a \IX{memory barrier} to ensure that the sampling
-of the theft variable happens before any change to that variable.
\Clnref{set:ACK} sets the \co{theft} state to ACK, and, if
\clnref{check:fast} sees that
this thread's fastpaths are not running, \clnref{set:READY} sets the \co{theft}
-state to READY\@.
+state to READY, the release store here is to ensure that the change to counter
+in fast path happens before changing the theft varibale to READY\@.
\end{fcvref}
\begin{listing}
@@ -2595,8 +2594,8 @@ handlers to undertake theft.
\Clnref{barrier:3} again disables compiler reordering, and then
\clnref{check:ACK}
checks to see if the signal handler deferred the \co{theft}
-state-change to READY, and, if so, \clnref{mb} executes a memory
-barrier to ensure that any CPU that sees \clnref{READY} setting state to
+state-change to READY, and, if so, the release store at \clnref{READY}
+is to ensure that any CPU that sees \clnref{READY} setting state to
READY also sees the effects of \clnref{add:f}.
If the fastpath addition at \clnref{add:f} was executed, then
\clnref{return:fs} returns
--
2.34.1
