parisc: Improve LWS-CAS performance

The attached change significantly improves the performance of the LWS-CAS code
in syscall.S.
This allows a number of packages to build (e.g., zeromq3, gtest and libxs)
that previously failed because slow LWS-CAS performance under contention. In
particular, interrupts taken while the lock was taken degraded performance
significantly.

The change does the following:

1) Disables interrupts around the CAS operation, and
2) Changes the loads and stores to use the ordered completer, "o", on
PA 2.0. "o" and "ma" with a zero offset are equivalent. The latter is
accepted on both PA 1.X and 2.0.

The use of ordered loads and stores probably makes no difference on all
existing hardware, but it seemed pedantically correct. In particular, the CAS
operation must complete before LDCW lock is released. As written before, a
processor could reorder the operations.

I don't believe the period interrupts are disabled is long enough to
significantly increase interrupt latency. For example, the TLB insert code is
longer. Worst case is a memory fault in the CAS operation.

Signed-off-by: John David Anglin <dave.anglin@bell.net>
Cc: stable@vger.kernel.org # 3.13+
Signed-off-by: Helge Deller <deller@gmx.de>

diff --git a/arch/parisc/kernel/syscall.S b/arch/parisc/kernel/syscall.S
index a63bb179f79a1fcd56a7bcf1adbe759f46587b71..83878601103701df4497913c89d5702897249a38 100644 (file)
--- a/arch/parisc/kernel/syscall.S
+++ b/arch/parisc/kernel/syscall.S
@@ -589,10 +589,13 @@ cas_nocontend:
 # endif
 /* ENABLE_LWS_DEBUG */
 
+       rsm     PSW_SM_I, %r0                           /* Disable interrupts */
+       /* COW breaks can cause contention on UP systems */
        LDCW    0(%sr2,%r20), %r28                      /* Try to acquire the lock */
        cmpb,<>,n       %r0, %r28, cas_action           /* Did we get it? */
 cas_wouldblock:
        ldo     2(%r0), %r28                            /* 2nd case */
+       ssm     PSW_SM_I, %r0
        b       lws_exit                                /* Contended... */
        ldo     -EAGAIN(%r0), %r21                      /* Spin in userspace */
 
@@ -619,15 +622,17 @@ cas_action:
        stw     %r1, 4(%sr2,%r20)
 #endif
        /* The load and store could fail */
-1:     ldw     0(%sr3,%r26), %r28
+1:     ldw,ma  0(%sr3,%r26), %r28
        sub,<>  %r28, %r25, %r0
-2:     stw     %r24, 0(%sr3,%r26)
+2:     stw,ma  %r24, 0(%sr3,%r26)
        /* Free lock */
-       stw     %r20, 0(%sr2,%r20)
+       stw,ma  %r20, 0(%sr2,%r20)
 #if ENABLE_LWS_DEBUG
        /* Clear thread register indicator */
        stw     %r0, 4(%sr2,%r20)
 #endif
+       /* Enable interrupts */
+       ssm     PSW_SM_I, %r0
        /* Return to userspace, set no error */
        b       lws_exit
        copy    %r0, %r21
@@ -639,6 +644,7 @@ cas_action:
 #if ENABLE_LWS_DEBUG
        stw     %r0, 4(%sr2,%r20)
 #endif
+       ssm     PSW_SM_I, %r0
        b       lws_exit
        ldo     -EFAULT(%r0),%r21       /* set errno */
        nop