[PATCH 2/5] kvx: Implement dcache invalidation primitive

[Jules Maselbas]

From: Yann Sionneau <ysionneau at kalray.eu>

Signed-off-by: Yann Sionneau <ysionneau at kalray.eu>
Signed-off-by: Jules Maselbas <jmaselbas at kalray.eu>
---
 arch/kvx/Kconfig             |  1 +
 arch/kvx/include/asm/cache.h | 13 ++++++++++
 arch/kvx/lib/Makefile        |  2 +-
 arch/kvx/lib/cache.c         | 50 ++++++++++++++++++++++++++++++++++++
 4 files changed, 65 insertions(+), 1 deletion(-)
 create mode 100644 arch/kvx/lib/cache.c

diff --git a/arch/kvx/Kconfig b/arch/kvx/Kconfig
index 8483ae6e6..4e02613ec 100644
--- a/arch/kvx/Kconfig
+++ b/arch/kvx/Kconfig
@@ -12,6 +12,7 @@ config KVX
 	select FLEXIBLE_BOOTARGS
 	select GENERIC_FIND_NEXT_BIT
 	select HAS_ARCH_SJLJ
+	select HAS_CACHE
 	select LIBFDT
 	select MFD_SYSCON
 	select OF_BAREBOX_DRIVERS
diff --git a/arch/kvx/include/asm/cache.h b/arch/kvx/include/asm/cache.h
index 3be176725..efdbcc630 100644
--- a/arch/kvx/include/asm/cache.h
+++ b/arch/kvx/include/asm/cache.h
@@ -15,4 +15,17 @@ static inline void sync_caches_for_execution(void)
 	__builtin_kvx_barrier();
 }
 
+void kvx_dcache_invalidate_mem_area(uint64_t addr, int size);
+
+static inline void sync_dcache_icache(void)
+{
+	sync_caches_for_execution();
+}
+
+static inline void dcache_inval(void)
+{
+	__builtin_kvx_fence();
+	__builtin_kvx_dinval();
+}
+
 #endif /* __KVX_CACHE_H */
diff --git a/arch/kvx/lib/Makefile b/arch/kvx/lib/Makefile
index cee08b0fa..d271ebccf 100644
--- a/arch/kvx/lib/Makefile
+++ b/arch/kvx/lib/Makefile
@@ -3,4 +3,4 @@
 # Copyright (C) 2019 Kalray Inc.
 #
 
-obj-y	+= cpuinfo.o board.o dtb.o poweroff.o bootm.o setjmp.o
+obj-y	+= cpuinfo.o board.o dtb.o poweroff.o bootm.o setjmp.o cache.o
diff --git a/arch/kvx/lib/cache.c b/arch/kvx/lib/cache.c
new file mode 100644
index 000000000..4e128891a
--- /dev/null
+++ b/arch/kvx/lib/cache.c
@@ -0,0 +1,50 @@
+// SPDX-License-Identifier: GPL-2.0-only
+// SPDX-FileCopyrightText: 2021 Yann Sionneau <ysionneau at kalray.eu>, Kalray Inc.
+
+#include <asm/cache.h>
+
+#define K1_DCACHE_REFILL         (12)
+#define K1_DCACHE_HWLOOP         (1)
+#define K1_DCACHE_REFILL_PERCENT (80)
+#define K1_DCACHE_LINE_SIZE    (64)
+#define K1_DCACHE_SIZE (128*1024)
+
+void kvx_dcache_invalidate_mem_area(uint64_t addr, int size)
+{
+	/* if hwloop iterations cost < _K1_DCACHE_REFILL_PERCENT cache refill,
+	 * use hwloop, otherwise invalid the whole cache
+	 */
+	if (size <
+	(K1_DCACHE_REFILL_PERCENT * (K1_DCACHE_REFILL * K1_DCACHE_SIZE))
+			/ (100 * (K1_DCACHE_REFILL + K1_DCACHE_HWLOOP))) {
+		/* number of lines that must be invalidated */
+		int invalid_lines = ((addr + size) -
+					(addr & (~(K1_DCACHE_LINE_SIZE - 1))));
+
+		invalid_lines = invalid_lines / K1_DCACHE_LINE_SIZE
+				+ (0 != (invalid_lines % K1_DCACHE_LINE_SIZE));
+		if (__builtin_constant_p(invalid_lines) && invalid_lines <= 2) {
+			/* when inlining (and doing constant folding),
+			 *  gcc is able to unroll small loops
+			 */
+			int i;
+
+			for (i = 0; i < invalid_lines; i++) {
+				__builtin_kvx_dinvall((void *)(addr
+						+ i * K1_DCACHE_LINE_SIZE));
+			}
+		} else if (invalid_lines > 0) {
+			__asm__ __volatile__ (
+				"loopdo %1, 0f\n;;\n"
+				"dinvall 0[%0]\n"
+				"addd %0 = %0, %2\n;;\n"
+				"0:\n"
+				: "+r"(addr)
+				: "r" (invalid_lines),
+				"i" (K1_DCACHE_LINE_SIZE)
+				: "ls", "le", "lc", "memory");
+		}
+	} else {
+		__builtin_kvx_dinval();
+	}
+}
-- 
2.17.1