MIPS: Loongson: Introduce and use loongson_llsc_mb()

On the Loongson-2G/2H/3A/3B there is a hardware flaw that ll/sc and
lld/scd is very weak ordering. We should add sync instructions "before
each ll/lld" and "at the branch-target between ll/sc" to workaround.
Otherwise, this flaw will cause deadlock occasionally (e.g. when doing
heavy load test with LTP).

Below is the explaination of CPU designer:

"For Loongson 3 family, when a memory access instruction (load, store,
or prefetch)'s executing occurs between the execution of LL and SC, the
success or failure of SC is not predictable. Although programmer would
not insert memory access instructions between LL and SC, the memory
instructions before LL in program-order, may dynamically executed
between the execution of LL/SC, so a memory fence (SYNC) is needed
before LL/LLD to avoid this situation.

Since Loongson-3A R2 (3A2000), we have improved our hardware design to
handle this case. But we later deduce a rarely circumstance that some
speculatively executed memory instructions due to branch misprediction
between LL/SC still fall into the above case, so a memory fence (SYNC)
at branch-target (if its target is not between LL/SC) is needed for
Loongson 3A1000, 3B1500, 3A2000 and 3A3000.

Our processor is continually evolving and we aim to to remove all these
workaround-SYNCs around LL/SC for new-come processor."

Here is an example:

Both cpu1 and cpu2 simutaneously run atomic_add by 1 on same atomic var,
this bug cause both 'sc' run by two cpus (in atomic_add) succeed at same
time('sc' return 1), and the variable is only *added by 1*, sometimes,
which is wrong and unacceptable(it should be added by 2).

Why disable fix-loongson3-llsc in compiler?
Because compiler fix will cause problems in kernel's __ex_table section.

This patch fix all the cases in kernel, but:

+. the fix at the end of futex_atomic_cmpxchg_inatomic is for branch-target
of 'bne', there other cases which smp_mb__before_llsc() and smp_llsc_mb() fix
the ll and branch-target coincidently such as atomic_sub_if_positive/
cmpxchg/xchg, just like this one.

+. Loongson 3 does support CONFIG_EDAC_ATOMIC_SCRUB, so no need to touch
edac.h

+. local_ops and cmpxchg_local should not be affected by this bug since
only the owner can write.

+. mips_atomic_set for syscall.c is deprecated and rarely used, just let
it go

Signed-off-by: Huacai Chen <chenhc@lemote.com>
Signed-off-by: Huang Pei <huangpei@loongson.cn>
[paul.burton@mips.com:
  - Simplify the addition of -mno-fix-loongson3-llsc to cflags, and add
    a comment describing why it's there.
  - Make loongson_llsc_mb() a no-op when
    CONFIG_CPU_LOONGSON3_WORKAROUNDS=n, rather than a compiler memory
    barrier.
  - Add a comment describing the bug & how loongson_llsc_mb() helps
    in asm/barrier.h.]
Signed-off-by: Paul Burton <paul.burton@mips.com>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: ambrosehua@gmail.com
Cc: Steven J . Hill <Steven.Hill@cavium.com>
Cc: linux-mips@linux-mips.org
Cc: Fuxin Zhang <zhangfx@lemote.com>
Cc: Zhangjin Wu <wuzhangjin@gmail.com>
Cc: Li Xuefeng <lixuefeng@loongson.cn>
Cc: Xu Chenghua <xuchenghua@loongson.cn>

5 files changed, 52 insertions, 0 deletions

diff --git a/arch/mips/include/asm/atomic.h b/arch/mips/include/asm/atomic.h
index 43fcd35e2957..94096299fc56 100644
--- a/arch/mips/include/asm/atomic.h
+++ b/arch/mips/include/asm/atomic.h
@@ -58,6 +58,7 @@ static __inline__ void atomic_##op(int i, atomic_t * v)			      \
 	if (kernel_uses_llsc) {						      \
 		int temp;						      \
 									      \
+		loongson_llsc_mb();					      \
 		__asm__ __volatile__(					      \
 		"	.set	push					\n"   \
 		"	.set	"MIPS_ISA_LEVEL"			\n"   \
@@ -85,6 +86,7 @@ static __inline__ int atomic_##op##_return_relaxed(int i, atomic_t * v)	      \
 	if (kernel_uses_llsc) {						      \
 		int temp;						      \
 									      \
+		loongson_llsc_mb();					      \
 		__asm__ __volatile__(					      \
 		"	.set	push					\n"   \
 		"	.set	"MIPS_ISA_LEVEL"			\n"   \
@@ -118,6 +120,7 @@ static __inline__ int atomic_fetch_##op##_relaxed(int i, atomic_t * v)	      \
 	if (kernel_uses_llsc) {						      \
 		int temp;						      \
 									      \
+		loongson_llsc_mb();					      \
 		__asm__ __volatile__(					      \
 		"	.set	push					\n"   \
 		"	.set	"MIPS_ISA_LEVEL"			\n"   \
@@ -256,6 +259,7 @@ static __inline__ void atomic64_##op(long i, atomic64_t * v)		      \
 	if (kernel_uses_llsc) {						      \
 		long temp;						      \
 									      \
+		loongson_llsc_mb();					      \
 		__asm__ __volatile__(					      \
 		"	.set	push					\n"   \
 		"	.set	"MIPS_ISA_LEVEL"			\n"   \
@@ -283,6 +287,7 @@ static __inline__ long atomic64_##op##_return_relaxed(long i, atomic64_t * v) \
 	if (kernel_uses_llsc) {						      \
 		long temp;						      \
 									      \
+		loongson_llsc_mb();					      \
 		__asm__ __volatile__(					      \
 		"	.set	push					\n"   \
 		"	.set	"MIPS_ISA_LEVEL"			\n"   \
@@ -316,6 +321,7 @@ static __inline__ long atomic64_fetch_##op##_relaxed(long i, atomic64_t * v)  \
 	if (kernel_uses_llsc) {						      \
 		long temp;						      \
 									      \
+		loongson_llsc_mb();					      \
 		__asm__ __volatile__(					      \
 		"	.set	push					\n"   \
 		"	.set	"MIPS_ISA_LEVEL"			\n"   \
diff --git a/arch/mips/include/asm/barrier.h b/arch/mips/include/asm/barrier.h
index a5eb1bb199a7..b7f6ac5e513c 100644
--- a/arch/mips/include/asm/barrier.h
+++ b/arch/mips/include/asm/barrier.h
@@ -222,6 +222,42 @@
 #define __smp_mb__before_atomic()	__smp_mb__before_llsc()
 #define __smp_mb__after_atomic()	smp_llsc_mb()
 
+/*
+ * Some Loongson 3 CPUs have a bug wherein execution of a memory access (load,
+ * store or pref) in between an ll & sc can cause the sc instruction to
+ * erroneously succeed, breaking atomicity. Whilst it's unusual to write code
+ * containing such sequences, this bug bites harder than we might otherwise
+ * expect due to reordering & speculation:
+ *
+ * 1) A memory access appearing prior to the ll in program order may actually
+ *    be executed after the ll - this is the reordering case.
+ *
+ *    In order to avoid this we need to place a memory barrier (ie. a sync
+ *    instruction) prior to every ll instruction, in between it & any earlier
+ *    memory access instructions. Many of these cases are already covered by
+ *    smp_mb__before_llsc() but for the remaining cases, typically ones in
+ *    which multiple CPUs may operate on a memory location but ordering is not
+ *    usually guaranteed, we use loongson_llsc_mb() below.
+ *
+ *    This reordering case is fixed by 3A R2 CPUs, ie. 3A2000 models and later.
+ *
+ * 2) If a conditional branch exists between an ll & sc with a target outside
+ *    of the ll-sc loop, for example an exit upon value mismatch in cmpxchg()
+ *    or similar, then misprediction of the branch may allow speculative
+ *    execution of memory accesses from outside of the ll-sc loop.
+ *
+ *    In order to avoid this we need a memory barrier (ie. a sync instruction)
+ *    at each affected branch target, for which we also use loongson_llsc_mb()
+ *    defined below.
+ *
+ *    This case affects all current Loongson 3 CPUs.
+ */
+#ifdef CONFIG_CPU_LOONGSON3_WORKAROUNDS /* Loongson-3's LLSC workaround */
+#define loongson_llsc_mb()	__asm__ __volatile__(__WEAK_LLSC_MB : : :"memory")
+#else
+#define loongson_llsc_mb()	do { } while (0)
+#endif
+
 #include <asm-generic/barrier.h>
 
 #endif /* __ASM_BARRIER_H */
diff --git a/arch/mips/include/asm/bitops.h b/arch/mips/include/asm/bitops.h
index c4675957b21b..830c93a010c3 100644
--- a/arch/mips/include/asm/bitops.h
+++ b/arch/mips/include/asm/bitops.h
@@ -69,6 +69,7 @@ static inline void set_bit(unsigned long nr, volatile unsigned long *addr)
 		: "ir" (1UL << bit), GCC_OFF_SMALL_ASM() (*m));
 #if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6)
 	} else if (kernel_uses_llsc && __builtin_constant_p(bit)) {
+		loongson_llsc_mb();
 		do {
 			__asm__ __volatile__(
 			"	" __LL "%0, %1		# set_bit	\n"
@@ -79,6 +80,7 @@ static inline void set_bit(unsigned long nr, volatile unsigned long *addr)
 		} while (unlikely(!temp));
 #endif /* CONFIG_CPU_MIPSR2 || CONFIG_CPU_MIPSR6 */
 	} else if (kernel_uses_llsc) {
+		loongson_llsc_mb();
 		do {
 			__asm__ __volatile__(
 			"	.set	push				\n"
@@ -123,6 +125,7 @@ static inline void clear_bit(unsigned long nr, volatile unsigned long *addr)
 		: "ir" (~(1UL << bit)));
 #if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6)
 	} else if (kernel_uses_llsc && __builtin_constant_p(bit)) {
+		loongson_llsc_mb();
 		do {
 			__asm__ __volatile__(
 			"	" __LL "%0, %1		# clear_bit	\n"
@@ -133,6 +136,7 @@ static inline void clear_bit(unsigned long nr, volatile unsigned long *addr)
 		} while (unlikely(!temp));
 #endif /* CONFIG_CPU_MIPSR2 || CONFIG_CPU_MIPSR6 */
 	} else if (kernel_uses_llsc) {
+		loongson_llsc_mb();
 		do {
 			__asm__ __volatile__(
 			"	.set	push				\n"
@@ -193,6 +197,7 @@ static inline void change_bit(unsigned long nr, volatile unsigned long *addr)
 		unsigned long *m = ((unsigned long *) addr) + (nr >> SZLONG_LOG);
 		unsigned long temp;
 
+		loongson_llsc_mb();
 		do {
 			__asm__ __volatile__(
 			"	.set	push				\n"
diff --git a/arch/mips/include/asm/futex.h b/arch/mips/include/asm/futex.h
index c14d798f3888..b83b0397462d 100644
--- a/arch/mips/include/asm/futex.h
+++ b/arch/mips/include/asm/futex.h
@@ -50,6 +50,7 @@
 		  "i" (-EFAULT)						\
 		: "memory");						\
 	} else if (cpu_has_llsc) {					\
+		loongson_llsc_mb();					\
 		__asm__ __volatile__(					\
 		"	.set	push				\n"	\
 		"	.set	noat				\n"	\
@@ -163,6 +164,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 		  "i" (-EFAULT)
 		: "memory");
 	} else if (cpu_has_llsc) {
+		loongson_llsc_mb();
 		__asm__ __volatile__(
 		"# futex_atomic_cmpxchg_inatomic			\n"
 		"	.set	push					\n"
@@ -192,6 +194,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 		: GCC_OFF_SMALL_ASM() (*uaddr), "Jr" (oldval), "Jr" (newval),
 		  "i" (-EFAULT)
 		: "memory");
+		loongson_llsc_mb();
 	} else
 		return -ENOSYS;
 
diff --git a/arch/mips/include/asm/pgtable.h b/arch/mips/include/asm/pgtable.h
index 57933fc8fd98..910851c62db3 100644
--- a/arch/mips/include/asm/pgtable.h
+++ b/arch/mips/include/asm/pgtable.h
@@ -228,6 +228,7 @@ static inline void set_pte(pte_t *ptep, pte_t pteval)
 			: [buddy] "+m" (buddy->pte), [tmp] "=&r" (tmp)
 			: [global] "r" (page_global));
 		} else if (kernel_uses_llsc) {
+			loongson_llsc_mb();
 			__asm__ __volatile__ (
 			"	.set	push				\n"
 			"	.set	"MIPS_ISA_ARCH_LEVEL"		\n"
@@ -242,6 +243,7 @@ static inline void set_pte(pte_t *ptep, pte_t pteval)
 			"	.set	pop				\n"
 			: [buddy] "+m" (buddy->pte), [tmp] "=&r" (tmp)
 			: [global] "r" (page_global));
+			loongson_llsc_mb();
 		}
 #else /* !CONFIG_SMP */
 		if (pte_none(*buddy))