parisc: Define mb() and add memory barriers to assembler unlock sequences

For years I thought all parisc machines executed loads and stores in
order. However, Jeff Law recently indicated on gcc-patches that this is
not correct. There are various degrees of out-of-order execution all the
way back to the PA7xxx processor series (hit-under-miss). The PA8xxx
series has full out-of-order execution for both integer operations, and
loads and stores.

This is described in the following article:
http://web.archive.org/web/20040214092531/http://www.cpus.hp.com/technical_references/advperf.shtml

For this reason, we need to define mb() and to insert a memory barrier
before the store unlocking spinlocks. This ensures that all memory
accesses are complete prior to unlocking. The ldcw instruction performs
the same function on entry.

Signed-off-by: John David Anglin <dave.anglin@bell.net>
Cc: stable@vger.kernel.org # 4.0+
Signed-off-by: Helge Deller <deller@gmx.de>

arch/parisc/include/asm/barrier.h

@@ -0,0 +1,32 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_BARRIER_H
+#define __ASM_BARRIER_H
+
+#ifndef __ASSEMBLY__
+
+/* The synchronize caches instruction executes as a nop on systems in
+   which all memory references are performed in order. */
+#define synchronize_caches() __asm__ __volatile__ ("sync" : : : "memory")
+
+#if defined(CONFIG_SMP)
+#define mb()		do { synchronize_caches(); } while (0)
+#define rmb()		mb()
+#define wmb()		mb()
+#define dma_rmb()	mb()
+#define dma_wmb()	mb()
+#else
+#define mb()		barrier()
+#define rmb()		barrier()
+#define wmb()		barrier()
+#define dma_rmb()	barrier()
+#define dma_wmb()	barrier()
+#endif
+
+#define __smp_mb()	mb()
+#define __smp_rmb()	mb()
+#define __smp_wmb()	mb()
+
+#include <asm-generic/barrier.h>
+
+#endif /* !__ASSEMBLY__ */
+#endif /* __ASM_BARRIER_H */

arch/parisc/kernel/entry.S

@@ -481,6 +481,8 @@
 	/* Release pa_tlb_lock lock without reloading lock address. */
 	.macro		tlb_unlock0	spc,tmp
 #ifdef CONFIG_SMP
+	or,COND(=)	%r0,\spc,%r0
+	sync
 	or,COND(=)	%r0,\spc,%r0
 	stw             \spc,0(\tmp)
 #endif

arch/parisc/kernel/pacache.S

@@ -353,6 +353,7 @@ ENDPROC_CFI(flush_data_cache_local)
 	.macro	tlb_unlock	la,flags,tmp
 #ifdef CONFIG_SMP
 	ldi		1,\tmp
+	sync
 	stw		\tmp,0(\la)
 	mtsm		\flags
 #endif

arch/parisc/kernel/syscall.S

@@ -633,6 +633,7 @@ cas_action:
 	sub,<>	%r28, %r25, %r0
 2:	stw,ma	%r24, 0(%r26)
 	/* Free lock */
+	sync
 	stw,ma	%r20, 0(%sr2,%r20)
 #if ENABLE_LWS_DEBUG
 	/* Clear thread register indicator */
@@ -647,6 +648,7 @@ cas_action:
 3:		
 	/* Error occurred on load or store */
 	/* Free lock */
+	sync
 	stw	%r20, 0(%sr2,%r20)
 #if ENABLE_LWS_DEBUG
 	stw	%r0, 4(%sr2,%r20)
@@ -848,6 +850,7 @@ cas2_action:
 
 cas2_end:
 	/* Free lock */
+	sync
 	stw,ma	%r20, 0(%sr2,%r20)
 	/* Enable interrupts */
 	ssm	PSW_SM_I, %r0
@@ -858,6 +861,7 @@ cas2_end:
 22:
 	/* Error occurred on load or store */
 	/* Free lock */
+	sync
 	stw	%r20, 0(%sr2,%r20)
 	ssm	PSW_SM_I, %r0
 	ldo	1(%r0),%r28