linux-kernel - [PATCH V8 07/10] riscv: Add qspinlock support

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite for Android: free password hash cracker in your pocket

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <20220724122517.1019187-8-guoren@kernel.org>
Date:   Sun, 24 Jul 2022 08:25:14 -0400
From:   guoren@...nel.org
To:     palmer@...osinc.com, heiko@...ech.de, hch@...radead.org,
        arnd@...db.de, peterz@...radead.org, will@...nel.org,
        boqun.feng@...il.com, longman@...hat.com, mingo@...hat.com,
        philipp.tomsich@...ll.eu, cmuellner@...ux.com,
        linux-kernel@...r.kernel.org, David.Laight@...LAB.COM
Cc:     linux-riscv@...ts.infradead.org, linux-csky@...r.kernel.org,
        Guo Ren <guoren@...ux.alibaba.com>, Guo Ren <guoren@...nel.org>
Subject: [PATCH V8 07/10] riscv: Add qspinlock support

From: Guo Ren <guoren@...ux.alibaba.com>

Enable qspinlock by the requirements mentioned in a8ad07e5240c9
("asm-generic: qspinlock: Indicate the use of mixed-size atomics").

 - RISC-V atomic_*_release()/atomic_*_acquire() are implemented with
   own relaxed version plus acquire/release_fence for RCsc
   synchronization.

 - RISC-V LR/SC pairs could provide a strong/weak forward guarantee
   that depends on micro-architecture. And RISC-V ISA spec has given
   out several limitations to let hardware support strict forward
   guarantee (RISC-V User ISA - 8.3 Eventual Success of
   Store-Conditional Instructions). Some riscv cores such as BOOMv3
   & XiangShan could provide strict & strong forward guarantee (The
   cache line would be kept in an exclusive state for Backoff cycles,
   and only this core's interrupt could break the LR/SC pair).

 - RISC-V provides cheap atomic_fetch_or_acquire() with RCsc.

 - RISC-V only provides relaxed xchg16 to support qspinlock.

Signed-off-by: Guo Ren <guoren@...ux.alibaba.com>
Signed-off-by: Guo Ren <guoren@...nel.org>
---
 arch/riscv/Kconfig               | 16 ++++++++++++++++
 arch/riscv/include/asm/Kbuild    |  2 ++
 arch/riscv/include/asm/cmpxchg.h | 17 +++++++++++++++++
 3 files changed, 35 insertions(+)

diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index bff04916a6c5..721f098228a8 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -359,6 +359,22 @@ config NODES_SHIFT
 	  Specify the maximum number of NUMA Nodes available on the target
 	  system.  Increases memory reserved to accommodate various tables.
 
+choice
+	prompt "RISC-V spinlock type"
+	default RISCV_TICKET_SPINLOCKS
+
+config RISCV_TICKET_SPINLOCKS
+	bool "Using ticket spinlock"
+
+config RISCV_QUEUED_SPINLOCKS
+	bool "Using queued spinlock"
+	depends on SMP && MMU
+	select ARCH_USE_QUEUED_SPINLOCKS
+	help
+	  Make sure your micro arch LL/SC has a strong forward progress guarantee.
+	  Otherwise, stay at ticket-lock/combo-lock.
+endchoice
+
 config RISCV_ALTERNATIVE
 	bool
 	depends on !XIP_KERNEL
diff --git a/arch/riscv/include/asm/Kbuild b/arch/riscv/include/asm/Kbuild
index 504f8b7e72d4..2cce98c7b653 100644
--- a/arch/riscv/include/asm/Kbuild
+++ b/arch/riscv/include/asm/Kbuild
@@ -2,7 +2,9 @@
 generic-y += early_ioremap.h
 generic-y += flat.h
 generic-y += kvm_para.h
+generic-y += mcs_spinlock.h
 generic-y += parport.h
+generic-y += qspinlock.h
 generic-y += spinlock.h
 generic-y += spinlock_types.h
 generic-y += qrwlock.h
diff --git a/arch/riscv/include/asm/cmpxchg.h b/arch/riscv/include/asm/cmpxchg.h
index 67ab6375b650..6bf2726d4500 100644
--- a/arch/riscv/include/asm/cmpxchg.h
+++ b/arch/riscv/include/asm/cmpxchg.h
@@ -17,6 +17,23 @@
 	__typeof__(new) __new = (new);					\
 	__typeof__(*(ptr)) __ret;					\
 	switch (size) {							\
+	case 2: { 							\
+		u32 tmp, ret;						\
+		u32 shif = ((ulong)__ptr & 2) ? 16 : 0;			\
+		u32 mask = 0xffff << shif;				\
+		__ptr = (__typeof__(ptr))((ulong)__ptr & ~2);		\
+		__asm__ __volatile__ (					\
+			"0:	lr.w %0, %2\n"				\
+			"	and  %1, %0, %z3\n"			\
+			"	or   %1, %1, %z4\n"			\
+			"	sc.w %1, %1, %2\n"			\
+			"	bnez %1, 0b\n"				\
+			: "=&r" (ret), "=&r" (tmp), "+A" (*__ptr)	\
+			: "rJ" (~mask), "rJ" ((u32)__new << shif)	\
+			: "memory");					\
+		__ret = (__typeof__(*(ptr)))((ret & mask) >> shif);	\
+		break;							\
+	}								\
 	case 4:								\
 		__asm__ __volatile__ (					\
 			"	amoswap.w %0, %2, %1\n"			\
-- 
2.36.1