[PATCH 1/2] powerpc/pmem: Add new instructions for persistent storage and sync

[PATCH 1/2] powerpc/pmem: Add new instructions for persistent storage and sync

[Aneesh Kumar K.V]

POWER10 introduces two new variants of dcbf instructions (dcbstps and dcbfps)
that can be used to write modified locations back to persistent storage.

Additionally, POWER10 also introduce phwsync and plwsync which can be used
to establish order of these writes to persistent storage.

This patch exposes these instructions to the rest of the kernel. The existing
dcbf and hwsync instructions in P9 are adequate to enable appropriate
synchronization with OpenCAPI-hosted persistent storage. Hence the new
instructions are added as a variant of the old ones that old hardware
won't differentiate.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
---
 arch/powerpc/include/asm/ppc-opcode.h | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h
index c1df75edde44..e8ca55e5d31e 100644
--- a/arch/powerpc/include/asm/ppc-opcode.h
+++ b/arch/powerpc/include/asm/ppc-opcode.h
@@ -216,6 +216,8 @@
 #define PPC_INST_STWCX			0x7c00012d
 #define PPC_INST_LWSYNC			0x7c2004ac
 #define PPC_INST_SYNC			0x7c0004ac
+#define PPC_INST_PHWSYNC		0x7c8004ac
+#define PPC_INST_PLWSYNC		0x7ca004ac
 #define PPC_INST_SYNC_MASK		0xfc0007fe
 #define PPC_INST_ISYNC			0x4c00012c
 #define PPC_INST_LXVD2X			0x7c000698
@@ -281,6 +283,8 @@
 #define PPC_INST_TABORT			0x7c00071d
 #define PPC_INST_TSR			0x7c0005dd
 
+#define PPC_INST_DCBF			0x7c0000ac
+
 #define PPC_INST_NAP			0x4c000364
 #define PPC_INST_SLEEP			0x4c0003a4
 #define PPC_INST_WINKLE			0x4c0003e4
@@ -529,6 +533,14 @@
 #define STBCIX(s,a,b)		stringify_in_c(.long PPC_INST_STBCIX | \
 				       __PPC_RS(s) | __PPC_RA(a) | __PPC_RB(b))
 
+#define	PPC_DCBFPS(a, b)	stringify_in_c(.long PPC_INST_DCBF |	\
+				       ___PPC_RA(a) | ___PPC_RB(b) | (4 << 21))
+#define	PPC_DCBSTPS(a, b)	stringify_in_c(.long PPC_INST_DCBF |	\
+				       ___PPC_RA(a) | ___PPC_RB(b) | (6 << 21))
+
+#define	PPC_PHWSYNC()		stringify_in_c(.long PPC_INST_PHWSYNC)
+#define	PPC_PLWSYNC()		stringify_in_c(.long PPC_INST_PLWSYNC)
+
 /*
  * Define what the VSX XX1 form instructions will look like, then add
  * the 128 bit load store instructions based on that.
-- 
2.26.2

[PATCH 2/2] powerpc/pmem: Add flush routines using new pmem store and sync instruction

[Aneesh Kumar K.V]

Start using dcbstps; phwsync; sequence for flushing persistent memory range.
The new instructions are implemented as a variant of dcbf and hwsync and on
POWER9 they will be executed as those instructions.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
---
 arch/powerpc/include/asm/cacheflush.h | 31 +++++++++++++++++++++++++++
 arch/powerpc/lib/pmem.c               |  8 +++----
 2 files changed, 35 insertions(+), 4 deletions(-)

diff --git a/arch/powerpc/include/asm/cacheflush.h b/arch/powerpc/include/asm/cacheflush.h
index e92191b390f3..edb59edeeacb 100644
--- a/arch/powerpc/include/asm/cacheflush.h
+++ b/arch/powerpc/include/asm/cacheflush.h
@@ -74,6 +74,37 @@ static inline void flush_dcache_range(unsigned long start, unsigned long stop)
 
 }
 
+static inline void clean_pmem_range(unsigned long start, unsigned long stop)
+{
+	unsigned long shift = l1_dcache_shift();
+	unsigned long bytes = l1_dcache_bytes();
+	void *addr = (void *)(start & ~(bytes - 1));
+	unsigned long size = stop - (unsigned long)addr + (bytes - 1);
+	unsigned long i;
+
+	for (i = 0; i < size >> shift; i++, addr += bytes)
+		asm volatile(PPC_DCBSTPS(%0, %1): :"i"(0), "r"(addr): "memory");
+
+
+	asm volatile(PPC_PHWSYNC():::"memory");
+}
+
+static inline void flush_pmem_range(unsigned long start, unsigned long stop)
+{
+	unsigned long shift = l1_dcache_shift();
+	unsigned long bytes = l1_dcache_bytes();
+	void *addr = (void *)(start & ~(bytes - 1));
+	unsigned long size = stop - (unsigned long)addr + (bytes - 1);
+	unsigned long i;
+
+	for (i = 0; i < size >> shift; i++, addr += bytes)
+		asm volatile(PPC_DCBFPS(%0, %1): :"i"(0), "r"(addr): "memory");
+
+
+	asm volatile(PPC_PHWSYNC():::"memory");
+}
+
+
 /*
  * Write any modified data cache blocks out to memory.
  * Does not invalidate the corresponding cache lines (especially for
diff --git a/arch/powerpc/lib/pmem.c b/arch/powerpc/lib/pmem.c
index 0666a8d29596..624708bcaaad 100644
--- a/arch/powerpc/lib/pmem.c
+++ b/arch/powerpc/lib/pmem.c
@@ -15,14 +15,14 @@
 void arch_wb_cache_pmem(void *addr, size_t size)
 {
 	unsigned long start = (unsigned long) addr;
-	flush_dcache_range(start, start + size);
+	clean_pmem_range(start, start + size);
 }
 EXPORT_SYMBOL_GPL(arch_wb_cache_pmem);
 
 void arch_invalidate_pmem(void *addr, size_t size)
 {
 	unsigned long start = (unsigned long) addr;
-	flush_dcache_range(start, start + size);
+	flush_pmem_range(start, start + size);
 }
 EXPORT_SYMBOL_GPL(arch_invalidate_pmem);
 
@@ -35,7 +35,7 @@ long __copy_from_user_flushcache(void *dest, const void __user *src,
 	unsigned long copied, start = (unsigned long) dest;
 
 	copied = __copy_from_user(dest, src, size);
-	flush_dcache_range(start, start + size);
+	clean_pmem_range(start, start + size);
 
 	return copied;
 }
@@ -45,7 +45,7 @@ void *memcpy_flushcache(void *dest, const void *src, size_t size)
 	unsigned long start = (unsigned long) dest;
 
 	memcpy(dest, src, size);
-	flush_dcache_range(start, start + size);
+	clean_pmem_range(start, start + size);
 
 	return dest;
 }
-- 
2.26.2