From: guoren@kernel.org
To: paul.walmsley@sifive.com, anup@brainfault.org,
peterz@infradead.org, mingo@redhat.com, will@kernel.org,
palmer@rivosinc.com, longman@redhat.com, boqun.feng@gmail.com,
tglx@linutronix.de, paulmck@kernel.org, rostedt@goodmis.org,
rdunlap@infradead.org, catalin.marinas@arm.com,
conor.dooley@microchip.com, xiaoguang.xing@sophgo.com,
bjorn@rivosinc.com, alexghiti@rivosinc.com,
keescook@chromium.org, greentime.hu@sifive.com,
ajones@ventanamicro.com, jszhang@kernel.org, wefu@redhat.com,
wuwei2016@iscas.ac.cn
Cc: linux-arch@vger.kernel.org, linux-riscv@lists.infradead.org,
linux-doc@vger.kernel.org, kvm@vger.kernel.org,
virtualization@lists.linux-foundation.org,
linux-csky@vger.kernel.org, Guo Ren <guoren@linux.alibaba.com>,
Guo Ren <guoren@kernel.org>
Subject: [PATCH V10 03/19] riscv: qspinlock: errata: Add ERRATA_THEAD_WRITE_ONCE fixup
Date: Wed, 2 Aug 2023 12:46:45 -0400 [thread overview]
Message-ID: <20230802164701.192791-4-guoren@kernel.org> (raw)
In-Reply-To: <20230802164701.192791-1-guoren@kernel.org>
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 --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 { \
--
2.36.1
next prev parent reply other threads:[~2023-08-02 16:49 UTC|newest]
Thread overview: 36+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-08-02 16:46 [PATCH V10 00/19] riscv: Add Native/Paravirt/CNA qspinlock support guoren
2023-08-02 16:46 ` [PATCH V10 01/19] asm-generic: ticket-lock: Reuse arch_spinlock_t of qspinlock guoren
2023-08-02 16:46 ` [PATCH V10 02/19] asm-generic: ticket-lock: Move into ticket_spinlock.h guoren
2023-08-02 16:46 ` guoren [this message]
2023-08-02 16:46 ` [PATCH V10 04/19] riscv: qspinlock: Add basic queued_spinlock support guoren
2023-08-11 19:34 ` Waiman Long
2023-08-12 0:18 ` Guo Ren
2023-08-02 16:46 ` [PATCH V10 05/19] riscv: qspinlock: Introduce combo spinlock guoren
2023-08-11 19:51 ` Waiman Long
2023-08-12 0:22 ` Guo Ren
2023-08-02 16:46 ` [PATCH V10 06/19] riscv: qspinlock: Allow force qspinlock from the command line guoren
2023-08-02 16:46 ` [PATCH V10 07/19] riscv: qspinlock: errata: Introduce ERRATA_THEAD_QSPINLOCK guoren
2023-08-04 9:05 ` Conor Dooley
2023-08-04 9:53 ` Guo Ren
2023-08-04 10:06 ` Conor Dooley
2023-08-05 1:28 ` Guo Ren
2023-08-07 5:23 ` Stefan O'Rear
2023-08-08 2:12 ` Guo Ren
2023-09-13 18:54 ` Palmer Dabbelt
2023-09-13 19:32 ` Waiman Long
2023-09-14 3:31 ` Guo Ren
2023-08-02 16:46 ` [PATCH V10 08/19] riscv: qspinlock: Use new static key for controlling call of virt_spin_lock() guoren
2023-08-02 16:46 ` [PATCH V10 09/19] RISC-V: paravirt: pvqspinlock: Add paravirt qspinlock skeleton guoren
2023-08-02 16:46 ` [PATCH V10 10/19] RISC-V: paravirt: pvqspinlock: KVM: " guoren
2023-08-02 16:46 ` [PATCH V10 11/19] RISC-V: paravirt: pvqspinlock: KVM: Implement kvm_sbi_ext_pvlock_kick_cpu() guoren
2023-08-02 16:46 ` [PATCH V10 12/19] RISC-V: paravirt: pvqspinlock: Add nopvspin kernel parameter guoren
2023-08-02 16:46 ` [PATCH V10 13/19] RISC-V: paravirt: pvqspinlock: Remove unnecessary definitions of cmpxchg & xchg guoren
2023-08-02 16:46 ` [PATCH V10 14/19] RISC-V: paravirt: pvqspinlock: Add xchg8 & cmpxchg_small support guoren
2023-08-02 16:46 ` [PATCH V10 15/19] RISC-V: paravirt: pvqspinlock: Add SBI implementation guoren
2023-08-02 16:46 ` [PATCH V10 16/19] RISC-V: paravirt: pvqspinlock: Add kconfig entry guoren
2023-08-02 16:46 ` [PATCH V10 17/19] RISC-V: paravirt: pvqspinlock: Add trace point for pv_kick/wait guoren
2023-08-02 16:47 ` [PATCH V10 18/19] locking/qspinlock: Move pv_ops into x86 directory guoren
2023-08-11 20:42 ` Waiman Long
2023-08-12 0:24 ` Guo Ren
2023-08-12 0:47 ` Waiman Long
2023-08-02 16:47 ` [PATCH V10 19/19] locking/qspinlock: riscv: Add Compact NUMA-aware lock support guoren
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20230802164701.192791-4-guoren@kernel.org \
--to=guoren@kernel.org \
--cc=ajones@ventanamicro.com \
--cc=alexghiti@rivosinc.com \
--cc=anup@brainfault.org \
--cc=bjorn@rivosinc.com \
--cc=boqun.feng@gmail.com \
--cc=catalin.marinas@arm.com \
--cc=conor.dooley@microchip.com \
--cc=greentime.hu@sifive.com \
--cc=guoren@linux.alibaba.com \
--cc=jszhang@kernel.org \
--cc=keescook@chromium.org \
--cc=kvm@vger.kernel.org \
--cc=linux-arch@vger.kernel.org \
--cc=linux-csky@vger.kernel.org \
--cc=linux-doc@vger.kernel.org \
--cc=linux-riscv@lists.infradead.org \
--cc=longman@redhat.com \
--cc=mingo@redhat.com \
--cc=palmer@rivosinc.com \
--cc=paul.walmsley@sifive.com \
--cc=paulmck@kernel.org \
--cc=peterz@infradead.org \
--cc=rdunlap@infradead.org \
--cc=rostedt@goodmis.org \
--cc=tglx@linutronix.de \
--cc=virtualization@lists.linux-foundation.org \
--cc=wefu@redhat.com \
--cc=will@kernel.org \
--cc=wuwei2016@iscas.ac.cn \
--cc=xiaoguang.xing@sophgo.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).