[PATCH V12 04/14] riscv: qspinlock: errata: Add ERRATA_THEAD_WRITE_ONCE fixup

[guoren]

From: Guo Ren <guoren@xxxxxxxxxxxxxxxxx>

The early version of T-Head C9xx cores has a store merge buffer
delay problem. The store merge buffer could improve the store queue
performance by merging multi-store requests, but when there are not
continued store requests, the prior single store request would be
waiting in the store queue for a long time. That would cause
significant problems for communication between multi-cores. This
problem was found on sg2042 & th1520 platforms with the qspinlock
lock torture test.

So appending a fence w.o could immediately flush the store merge
buffer and let other cores see the write result.

This will apply the WRITE_ONCE errata to handle the non-standard
behavior via appending a fence w.o instruction for WRITE_ONCE().

Reviewed-by: Leonardo Bras <leobras@xxxxxxxxxx>
Signed-off-by: Guo Ren <guoren@xxxxxxxxxxxxxxxxx>
Signed-off-by: Guo Ren <guoren@xxxxxxxxxx>
---
 arch/riscv/Kconfig.errata              | 19 ++++++++++++++++
 arch/riscv/errata/thead/errata.c       | 20 +++++++++++++++++
 arch/riscv/include/asm/rwonce.h        | 31 ++++++++++++++++++++++++++
 arch/riscv/include/asm/vendorid_list.h |  3 ++-
 include/asm-generic/rwonce.h           |  2 ++
 5 files changed, 74 insertions(+), 1 deletion(-)
 create mode 100644 arch/riscv/include/asm/rwonce.h

diff --git a/arch/riscv/Kconfig.errata b/arch/riscv/Kconfig.errata
index e2c731cfed8c..2824ff165741 100644
--- a/arch/riscv/Kconfig.errata
+++ b/arch/riscv/Kconfig.errata
@@ -99,4 +99,23 @@ config ERRATA_THEAD_PMU
 
 	  If you don't know what to do here, say "Y".
 
+config ERRATA_THEAD_WRITE_ONCE
+	bool "Apply T-Head WRITE_ONCE errata"
+	depends on ERRATA_THEAD
+	default y
+	help
+	  The early version of T-Head C9xx cores of sg2042 has a store merge
+	  buffer delay problem. The store merge buffer could improve the store
+	  queue performance by merging multi-store requests, but when there are
+	  no continued store requests, the prior single store request would be
+	  waiting in the store queue for a long time. That would cause signifi-
+	  cant problems for communication between multi-cores. Appending a
+	  fence w.o could immediately flush the store merge buffer and let other
+	  cores see the write result.
+
+	  This will apply the WRITE_ONCE errata to handle the non-standard beh-
+	  avior via appending a fence w.o instruction for WRITE_ONCE().
+
+	  If you don't know what to do here, say "Y".
+
 endmenu # "CPU errata selection"
diff --git a/arch/riscv/errata/thead/errata.c b/arch/riscv/errata/thead/errata.c
index 0554ed4bf087..f6c1da819670 100644
--- a/arch/riscv/errata/thead/errata.c
+++ b/arch/riscv/errata/thead/errata.c
@@ -69,6 +69,23 @@ static bool errata_probe_pmu(unsigned int stage,
 	return true;
 }
 
+static bool errata_probe_write_once(unsigned int stage,
+				    unsigned long arch_id, unsigned long impid)
+{
+	if (!IS_ENABLED(CONFIG_ERRATA_THEAD_WRITE_ONCE))
+		return false;
+
+	/* target-c9xx cores report arch_id and impid as 0 */
+	if (arch_id != 0 || impid != 0)
+		return false;
+
+	if (stage == RISCV_ALTERNATIVES_BOOT ||
+	    stage == RISCV_ALTERNATIVES_MODULE)
+		return true;
+
+	return false;
+}
+
 static u32 thead_errata_probe(unsigned int stage,
 			      unsigned long archid, unsigned long impid)
 {
@@ -83,6 +100,9 @@ static u32 thead_errata_probe(unsigned int stage,
 	if (errata_probe_pmu(stage, archid, impid))
 		cpu_req_errata |= BIT(ERRATA_THEAD_PMU);
 
+	if (errata_probe_write_once(stage, archid, impid))
+		cpu_req_errata |= BIT(ERRATA_THEAD_WRITE_ONCE);
+
 	return cpu_req_errata;
 }
 
diff --git a/arch/riscv/include/asm/rwonce.h b/arch/riscv/include/asm/rwonce.h
new file mode 100644
index 000000000000..4c407c482ed0
--- /dev/null
+++ b/arch/riscv/include/asm/rwonce.h
@@ -0,0 +1,31 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ASM_RWONCE_H
+#define __ASM_RWONCE_H
+
+#include <linux/compiler_types.h>
+#include <asm/alternative-macros.h>
+#include <asm/vendorid_list.h>
+
+#if defined(CONFIG_ERRATA_THEAD_WRITE_ONCE) && !defined(NO_ALTERNATIVE)
+#define write_once_flush()				\
+do {							\
+	asm volatile(ALTERNATIVE(			\
+		__nops(1),				\
+		"fence w, o\n\t",			\
+		THEAD_VENDOR_ID,			\
+		ERRATA_THEAD_WRITE_ONCE,		\
+		CONFIG_ERRATA_THEAD_WRITE_ONCE)		\
+		: : : "memory");			\
+} while (0)
+
+#define __WRITE_ONCE(x, val)				\
+do {							\
+	*(volatile typeof(x) *)&(x) = (val);		\
+	write_once_flush();				\
+} while (0)
+#endif
+
+#include <asm-generic/rwonce.h>
+
+#endif	/* __ASM_RWONCE_H */
diff --git a/arch/riscv/include/asm/vendorid_list.h b/arch/riscv/include/asm/vendorid_list.h
index c503373193d2..5df1862bf0c9 100644
--- a/arch/riscv/include/asm/vendorid_list.h
+++ b/arch/riscv/include/asm/vendorid_list.h
@@ -24,7 +24,8 @@
 #define	ERRATA_THEAD_PBMT 0
 #define	ERRATA_THEAD_CMO 1
 #define	ERRATA_THEAD_PMU 2
-#define	ERRATA_THEAD_NUMBER 3
+#define	ERRATA_THEAD_WRITE_ONCE 3
+#define	ERRATA_THEAD_NUMBER 4
 #endif
 
 #endif
diff --git a/include/asm-generic/rwonce.h b/include/asm-generic/rwonce.h
index 8d0a6280e982..fb07fe8c6e45 100644
--- a/include/asm-generic/rwonce.h
+++ b/include/asm-generic/rwonce.h
@@ -50,10 +50,12 @@
 	__READ_ONCE(x);							\
 })
 
+#ifndef __WRITE_ONCE
 #define __WRITE_ONCE(x, val)						\
 do {									\
 	*(volatile typeof(x) *)&(x) = (val);				\
 } while (0)
+#endif
 
 #define WRITE_ONCE(x, val)						\
 do {									\
-- 
2.40.1