diff mbox series

[V10,03/19] riscv: qspinlock: errata: Add ERRATA_THEAD_WRITE_ONCE fixup

Message ID 20230802164701.192791-4-guoren@kernel.org (mailing list archive)
State New, archived
Headers show
Series riscv: Add Native/Paravirt/CNA qspinlock support | expand

Commit Message

Guo Ren Aug. 2, 2023, 4:46 p.m. UTC
From: Guo Ren <guoren@linux.alibaba.com>

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().

Signed-off-by: Guo Ren <guoren@linux.alibaba.com>
Signed-off-by: Guo Ren <guoren@kernel.org>
---
 arch/riscv/Kconfig.errata              | 19 +++++++++++++++++++
 arch/riscv/errata/thead/errata.c       | 20 ++++++++++++++++++++
 arch/riscv/include/asm/errata_list.h   | 13 -------------
 arch/riscv/include/asm/rwonce.h        | 24 ++++++++++++++++++++++++
 arch/riscv/include/asm/vendorid_list.h | 14 ++++++++++++++
 include/asm-generic/rwonce.h           |  2 ++
 6 files changed, 79 insertions(+), 13 deletions(-)
 create mode 100644 arch/riscv/include/asm/rwonce.h
diff mbox series

Patch

diff --git a/arch/riscv/Kconfig.errata b/arch/riscv/Kconfig.errata
index 0c8f4652cd82..4745a5c57e7c 100644
--- a/arch/riscv/Kconfig.errata
+++ b/arch/riscv/Kconfig.errata
@@ -77,4 +77,23 @@  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 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
+	  significant 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
+	  behavior 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 be84b14f0118..881729746d2e 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_EARLY_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/errata_list.h b/arch/riscv/include/asm/errata_list.h
index 712cab7adffe..fbb2b8d39321 100644
--- a/arch/riscv/include/asm/errata_list.h
+++ b/arch/riscv/include/asm/errata_list.h
@@ -11,19 +11,6 @@ 
 #include <asm/hwcap.h>
 #include <asm/vendorid_list.h>
 
-#ifdef CONFIG_ERRATA_SIFIVE
-#define	ERRATA_SIFIVE_CIP_453 0
-#define	ERRATA_SIFIVE_CIP_1200 1
-#define	ERRATA_SIFIVE_NUMBER 2
-#endif
-
-#ifdef CONFIG_ERRATA_THEAD
-#define	ERRATA_THEAD_PBMT 0
-#define	ERRATA_THEAD_CMO 1
-#define	ERRATA_THEAD_PMU 2
-#define	ERRATA_THEAD_NUMBER 3
-#endif
-
 #ifdef __ASSEMBLY__
 
 #define ALT_INSN_FAULT(x)						\
diff --git a/arch/riscv/include/asm/rwonce.h b/arch/riscv/include/asm/rwonce.h
new file mode 100644
index 000000000000..be0b8864969d
--- /dev/null
+++ b/arch/riscv/include/asm/rwonce.h
@@ -0,0 +1,24 @@ 
+/* 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>
+
+#define __WRITE_ONCE(x, val)				\
+do {							\
+	*(volatile typeof(x) *)&(x) = (val);		\
+	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)
+
+#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 cb89af3f0704..73078cfe4029 100644
--- a/arch/riscv/include/asm/vendorid_list.h
+++ b/arch/riscv/include/asm/vendorid_list.h
@@ -8,4 +8,18 @@ 
 #define SIFIVE_VENDOR_ID	0x489
 #define THEAD_VENDOR_ID		0x5b7
 
+#ifdef CONFIG_ERRATA_SIFIVE
+#define	ERRATA_SIFIVE_CIP_453 0
+#define	ERRATA_SIFIVE_CIP_1200 1
+#define	ERRATA_SIFIVE_NUMBER 2
+#endif
+
+#ifdef CONFIG_ERRATA_THEAD
+#define	ERRATA_THEAD_PBMT 0
+#define	ERRATA_THEAD_CMO 1
+#define	ERRATA_THEAD_PMU 2
+#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 {									\