sync: rvck92: riscv: Add qspinlock support

Documentation/features/locking/queued-spinlocks/arch-support.txt

@@ -21,7 +21,7 @@
     |    openrisc: |  ok  |
     |      parisc: | TODO |
     |     powerpc: |  ok  |
-    |       riscv: | TODO |
+    |       riscv: |  ok  |
     |        s390: | TODO |
     |          sh: | TODO |
     |       sparc: |  ok  |

arch/riscv/Kconfig

@@ -67,6 +67,7 @@ config RISCV
 	select ARCH_WANT_LD_ORPHAN_WARN if !XIP_KERNEL
 	select ARCH_WANT_OPTIMIZE_HUGETLB_VMEMMAP
 	select ARCH_WANTS_THP_SWAP if HAVE_ARCH_TRANSPARENT_HUGEPAGE
+	select ARCH_WEAK_RELEASE_ACQUIRE if ARCH_USE_QUEUED_SPINLOCKS
 	select BINFMT_FLAT_NO_DATA_START_OFFSET if !MMU
 	select BUILDTIME_TABLE_SORT if MMU
 	select CLINT_TIMER if !MMU
@@ -98,6 +99,7 @@ config RISCV
 	select GENERIC_VDSO_TIME_NS if HAVE_GENERIC_VDSO
 	select HARDIRQS_SW_RESEND
 	select HAS_IOPORT if MMU
+	select HAVE_ALIGNED_STRUCT_PAGE
 	select HAVE_ARCH_AUDITSYSCALL
 	select HAVE_ARCH_HUGE_VMALLOC if HAVE_ARCH_HUGE_VMAP
 	select HAVE_ARCH_HUGE_VMAP if MMU && 64BIT && !XIP_KERNEL
@@ -461,6 +463,39 @@ 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_COMBO_SPINLOCKS
+
+config RISCV_TICKET_SPINLOCKS
+	bool "Using ticket spinlock"
+
+config RISCV_QUEUED_SPINLOCKS
+	bool "Using queued spinlock"
+	depends on SMP && MMU && NONPORTABLE
+	select ARCH_USE_QUEUED_SPINLOCKS
+	help
+	  The queued spinlock implementation requires the forward progress
+	  guarantee of cmpxchg()/xchg() atomic operations: CAS with Zabha or
+	  LR/SC with Ziccrse provide such guarantee.
+
+	  Select this if and only if Zabha or Ziccrse is available on your
+	  platform, RISCV_QUEUED_SPINLOCKS must not be selected for platforms
+	  without one of those extensions.
+
+	  If unsure, select RISCV_COMBO_SPINLOCKS, which will use qspinlocks
+	  when supported and otherwise ticket spinlocks.
+
+config RISCV_COMBO_SPINLOCKS
+	bool "Using combo spinlock"
+	depends on SMP && MMU
+	select ARCH_USE_QUEUED_SPINLOCKS
+	help
+	  Embed both queued spinlock and ticket lock so that the spinlock
+	  implementation can be chosen at runtime.
+
+endchoice
+
 config RISCV_ALTERNATIVE
 	bool
 	depends on !XIP_KERNEL

arch/riscv/include/asm/Kbuild

@@ -2,10 +2,12 @@
 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 += spinlock.h
 generic-y += spinlock_types.h
+generic-y += ticket_spinlock.h
 generic-y += qrwlock.h
 generic-y += qrwlock_types.h
+generic-y += qspinlock.h
 generic-y += user.h
 generic-y += vmlinux.lds.h

arch/riscv/include/asm/cmpxchg.h

@@ -14,29 +14,41 @@
 #include <asm/insn-def.h>
 #include <asm/cpufeature-macros.h>
 
-#define __arch_xchg_masked(sc_sfx, prepend, append, r, p, n)		\
-({									\
-	u32 *__ptr32b = (u32 *)((ulong)(p) & ~0x3);			\
-	ulong __s = ((ulong)(p) & (0x4 - sizeof(*p))) * BITS_PER_BYTE;	\
-	ulong __mask = GENMASK(((sizeof(*p)) * BITS_PER_BYTE) - 1, 0)	\
-			<< __s;						\
-	ulong __newx = (ulong)(n) << __s;				\
-	ulong __retx;							\
-	ulong __rc;							\
-									\
-	__asm__ __volatile__ (						\
-	       prepend							\
-	       "0:	lr.w %0, %2\n"					\
-	       "	and  %1, %0, %z4\n"				\
-	       "	or   %1, %1, %z3\n"				\
-	       "	sc.w" sc_sfx " %1, %1, %2\n"			\
-	       "	bnez %1, 0b\n"					\
-	       append							\
-	       : "=&r" (__retx), "=&r" (__rc), "+A" (*(__ptr32b))	\
-	       : "rJ" (__newx), "rJ" (~__mask)				\
-	       : "memory");						\
-									\
-	r = (__typeof__(*(p)))((__retx & __mask) >> __s);		\
+#define __arch_xchg_masked(sc_sfx, swap_sfx, prepend, sc_append,		\
+			   swap_append, r, p, n)				\
+({										\
+	if (IS_ENABLED(CONFIG_RISCV_ISA_ZABHA) &&				\
+	    riscv_has_extension_unlikely(RISCV_ISA_EXT_ZABHA)) {		\
+		__asm__ __volatile__ (						\
+			prepend							\
+			"	amoswap" swap_sfx " %0, %z2, %1\n"		\
+			swap_append						\
+			: "=&r" (r), "+A" (*(p))				\
+			: "rJ" (n)						\
+			: "memory");						\
+	} else {								\
+		u32 *__ptr32b = (u32 *)((ulong)(p) & ~0x3);			\
+		ulong __s = ((ulong)(p) & (0x4 - sizeof(*p))) * BITS_PER_BYTE;	\
+		ulong __mask = GENMASK(((sizeof(*p)) * BITS_PER_BYTE) - 1, 0)	\
+				<< __s;						\
+		ulong __newx = (ulong)(n) << __s;				\
+		ulong __retx;							\
+		ulong __rc;							\
+										\
+		__asm__ __volatile__ (						\
+		       prepend							\
+		       "0:	lr.w %0, %2\n"					\
+		       "	and  %1, %0, %z4\n"				\
+		       "	or   %1, %1, %z3\n"				\
+		       "	sc.w" sc_sfx " %1, %1, %2\n"			\
+		       "	bnez %1, 0b\n"					\
+		       sc_append						\
+		       : "=&r" (__retx), "=&r" (__rc), "+A" (*(__ptr32b))	\
+		       : "rJ" (__newx), "rJ" (~__mask)				\
+		       : "memory");						\
+										\
+		r = (__typeof__(*(p)))((__retx & __mask) >> __s);		\
+	}									\
 })
 
 #define __arch_xchg(sfx, prepend, append, r, p, n)			\
@@ -59,8 +71,13 @@
 									\
 	switch (sizeof(*__ptr)) {					\
 	case 1:								\
+		__arch_xchg_masked(sc_sfx, ".b" swap_sfx,		\
+				   prepend, sc_append, swap_append,	\
+				   __ret, __ptr, __new);		\
+		break;							\
 	case 2:								\
-		__arch_xchg_masked(sc_sfx, prepend, sc_append,		\
+		__arch_xchg_masked(sc_sfx, ".h" swap_sfx,		\
+				   prepend, sc_append, swap_append,	\
 				   __ret, __ptr, __new);		\
 		break;							\
 	case 4:								\
@@ -107,8 +124,10 @@
  * store NEW in MEM.  Return the initial value in MEM.  Success is
  * indicated by comparing RETURN with OLD.
  */
-
-#define __arch_cmpxchg_masked(sc_sfx, cas_sfx, prepend, append, r, p, o, n)	\
+#define __arch_cmpxchg_masked(sc_sfx, cas_sfx,					\
+			      sc_prepend, sc_append,				\
+			      cas_prepend, cas_append,				\
+			      r, p, o, n)					\
 ({										\
 	if (IS_ENABLED(CONFIG_RISCV_ISA_ZABHA) &&				\
 	    IS_ENABLED(CONFIG_RISCV_ISA_ZACAS) &&				\
@@ -117,9 +136,9 @@
 		r = o;								\
 										\
 		__asm__ __volatile__ (						\
-			prepend							\
+			cas_prepend							\
 			"	amocas" cas_sfx " %0, %z2, %1\n"		\
-			append							\
+			cas_append							\
 			: "+&r" (r), "+A" (*(p))				\
 			: "rJ" (n)						\
 			: "memory");						\
@@ -134,15 +153,15 @@
 		ulong __rc;							\
 										\
 		__asm__ __volatile__ (						\
-			prepend							\
+			sc_prepend							\
 			"0:	lr.w %0, %2\n"					\
 			"	and  %1, %0, %z5\n"				\
 			"	bne  %1, %z3, 1f\n"				\
 			"	and  %1, %0, %z6\n"				\
 			"	or   %1, %1, %z4\n"				\
 			"	sc.w" sc_sfx " %1, %1, %2\n"			\
 			"	bnez %1, 0b\n"					\
-			append							\
+			sc_append							\
 			"1:\n"							\
 			: "=&r" (__retx), "=&r" (__rc), "+A" (*(__ptr32b))	\
 			: "rJ" ((long)__oldx), "rJ" (__newx),			\
@@ -153,37 +172,42 @@
 	}									\
 })
 
-#define __arch_cmpxchg(lr_sfx, sc_cas_sfx, prepend, append, r, p, co, o, n)	\
+#define __arch_cmpxchg(lr_sfx, sc_sfx, cas_sfx,				\
+		       sc_prepend, sc_append,				\
+		       cas_prepend, cas_append,				\
+		       r, p, co, o, n)					\
 ({									\
 	if (IS_ENABLED(CONFIG_RISCV_ISA_ZACAS) &&			\
 	    riscv_has_extension_unlikely(RISCV_ISA_EXT_ZACAS)) {	\
 		r = o;							\
 									\
 		__asm__ __volatile__ (					\
-			prepend						\
-			"	amocas" sc_cas_sfx " %0, %z2, %1\n"	\
-			append						\
+			cas_prepend					\
+			"	amocas" cas_sfx " %0, %z2, %1\n"	\
+			cas_append					\
 			: "+&r" (r), "+A" (*(p))			\
 			: "rJ" (n)					\
 			: "memory");					\
 	} else {							\
 		register unsigned int __rc;				\
 									\
 		__asm__ __volatile__ (					\
-			prepend						\
+			sc_prepend					\
 			"0:	lr" lr_sfx " %0, %2\n"			\
 			"	bne  %0, %z3, 1f\n"			\
-			"	sc" sc_cas_sfx " %1, %z4, %2\n"		\
+			"	sc" sc_sfx " %1, %z4, %2\n"		\
 			"	bnez %1, 0b\n"				\
-			append						\
+			sc_append					\
 			"1:\n"						\
 			: "=&r" (r), "=&r" (__rc), "+A" (*(p))		\
 			: "rJ" (co o), "rJ" (n)				\
 			: "memory");					\
 	}								\
 })
 
-#define _arch_cmpxchg(ptr, old, new, sc_cas_sfx, prepend, append)	\
+#define _arch_cmpxchg(ptr, old, new, sc_sfx, cas_sfx,			\
+		      sc_prepend, sc_append,				\
+		      cas_prepend, cas_append)				\
 ({									\
 	__typeof__(ptr) __ptr = (ptr);					\
 	__typeof__(*(__ptr)) __old = (old);				\
@@ -192,40 +216,69 @@
 									\
 	switch (sizeof(*__ptr)) {					\
 	case 1:								\
-		__arch_cmpxchg_masked(sc_cas_sfx, ".b" sc_cas_sfx,	\
-					prepend, append,		\
-					__ret, __ptr, __old, __new);    \
+		__arch_cmpxchg_masked(sc_sfx, ".b" cas_sfx,		\
+				      sc_prepend, sc_append,		\
+				      cas_prepend, cas_append,		\
+				      __ret, __ptr, __old, __new);	\
 		break;							\
 	case 2:								\
-		__arch_cmpxchg_masked(sc_cas_sfx, ".h" sc_cas_sfx,	\
-					prepend, append,		\
-					__ret, __ptr, __old, __new);	\
+		__arch_cmpxchg_masked(sc_sfx, ".h" cas_sfx,		\
+				      sc_prepend, sc_append,		\
+				      cas_prepend, cas_append,		\
+				      __ret, __ptr, __old, __new);	\
 		break;							\
 	case 4:								\
-		__arch_cmpxchg(".w", ".w" sc_cas_sfx, prepend, append,	\
-				__ret, __ptr, (long), __old, __new);	\
+		__arch_cmpxchg(".w", ".w" sc_sfx, ".w" cas_sfx,		\
+			       sc_prepend, sc_append,			\
+			       cas_prepend, cas_append,			\
+			       __ret, __ptr, (long), __old, __new);	\
 		break;							\
 	case 8:								\
-		__arch_cmpxchg(".d", ".d" sc_cas_sfx, prepend, append,	\
-				__ret, __ptr, /**/, __old, __new);	\
+		__arch_cmpxchg(".d", ".d" sc_sfx, ".d" cas_sfx,		\
+			       sc_prepend, sc_append,			\
+			       cas_prepend, cas_append,			\
+			       __ret, __ptr, /**/, __old, __new);	\
 		break;							\
 	default:							\
 		BUILD_BUG();						\
 	}								\
 	(__typeof__(*(__ptr)))__ret;					\
 })
 
+/*
+ * These macros are here to improve the readability of the arch_cmpxchg_XXX()
+ * macros.
+ */
+#define SC_SFX(x)	x
+#define CAS_SFX(x)	x
+#define SC_PREPEND(x)	x
+#define SC_APPEND(x)	x
+#define CAS_PREPEND(x)	x
+#define CAS_APPEND(x)	x
+
 #define arch_cmpxchg_relaxed(ptr, o, n)					\
-	_arch_cmpxchg((ptr), (o), (n), "", "", "")
+	_arch_cmpxchg((ptr), (o), (n),					\
+		      SC_SFX(""), CAS_SFX(""),				\
+		      SC_PREPEND(""), SC_APPEND(""),			\
+		      CAS_PREPEND(""), CAS_APPEND(""))
 
 #define arch_cmpxchg_acquire(ptr, o, n)					\
-	_arch_cmpxchg((ptr), (o), (n), "", "", RISCV_ACQUIRE_BARRIER)
+	_arch_cmpxchg((ptr), (o), (n),					\
+		      SC_SFX(""), CAS_SFX(""),				\
+		      SC_PREPEND(""), SC_APPEND(RISCV_ACQUIRE_BARRIER),	\
+		      CAS_PREPEND(""), CAS_APPEND(RISCV_ACQUIRE_BARRIER))
 
 #define arch_cmpxchg_release(ptr, o, n)					\
-	_arch_cmpxchg((ptr), (o), (n), "", RISCV_RELEASE_BARRIER, "")
+	_arch_cmpxchg((ptr), (o), (n),					\
+		      SC_SFX(""), CAS_SFX(""),				\
+		      SC_PREPEND(RISCV_RELEASE_BARRIER), SC_APPEND(""),	\
+		      CAS_PREPEND(RISCV_RELEASE_BARRIER), CAS_APPEND(""))
 
 #define arch_cmpxchg(ptr, o, n)						\
-	_arch_cmpxchg((ptr), (o), (n), ".rl", "", "	fence rw, rw\n")
+	_arch_cmpxchg((ptr), (o), (n),					\
+		      SC_SFX(".rl"), CAS_SFX(".aqrl"),			\
+		      SC_PREPEND(""), SC_APPEND(RISCV_FULL_BARRIER),	\
+		      CAS_PREPEND(""), CAS_APPEND(""))
 
 #define arch_cmpxchg_local(ptr, o, n)					\
 	arch_cmpxchg_relaxed((ptr), (o), (n))
@@ -260,6 +313,44 @@
 	arch_cmpxchg_release((ptr), (o), (n));				\
 })
 
+#if defined(CONFIG_64BIT) && defined(CONFIG_RISCV_ISA_ZACAS)
+
+#define system_has_cmpxchg128()        riscv_has_extension_unlikely(RISCV_ISA_EXT_ZACAS)
+
+union __u128_halves {
+	u128 full;
+	struct {
+		u64 low, high;
+	};
+};
+
+#define __arch_cmpxchg128(p, o, n, cas_sfx)					\
+({										\
+	__typeof__(*(p)) __o = (o);                                             \
+	union __u128_halves __hn = { .full = (n) };				\
+	union __u128_halves __ho = { .full = (__o) };				\
+	register unsigned long t1 asm ("t1") = __hn.low;			\
+	register unsigned long t2 asm ("t2") = __hn.high;			\
+	register unsigned long t3 asm ("t3") = __ho.low;			\
+	register unsigned long t4 asm ("t4") = __ho.high;			\
+										\
+	__asm__ __volatile__ (							\
+		 "       amocas.q" cas_sfx " %0, %z3, %2"			\
+		 : "+&r" (t3), "+&r" (t4), "+A" (*(p))				\
+		 : "rJ" (t1), "rJ" (t2)						\
+		 : "memory");							\
+										\
+		 ((u128)t4 << 64) | t3;						\
+})
+
+#define arch_cmpxchg128(ptr, o, n)						\
+	__arch_cmpxchg128((ptr), (o), (n), ".aqrl")
+
+#define arch_cmpxchg128_local(ptr, o, n)					\
+	__arch_cmpxchg128((ptr), (o), (n), "")
+
+#endif /* CONFIG_64BIT && CONFIG_RISCV_ISA_ZACAS */
+
 #ifdef CONFIG_RISCV_ISA_ZAWRS
 /*
  * Despite wrs.nto being "WRS-with-no-timeout", in the absence of changes to

arch/riscv/include/asm/kvm_host.h

@@ -69,6 +69,7 @@ struct kvm_vcpu_stat {
 	struct kvm_vcpu_stat_generic generic;
 	u64 ecall_exit_stat;
 	u64 wfi_exit_stat;
+	u64 wrs_exit_stat;
 	u64 mmio_exit_user;
 	u64 mmio_exit_kernel;
 	u64 csr_exit_user;