[PATCH v3 0/4] Consolidate IO memcpy functions

[PATCH v3 0/4] Consolidate IO memcpy functions

[Julian Vetter]

Fixed compilation problems on 32bit architectures.

Signed-off-by: Julian Vetter <jvetter@kalrayinc.com>

---
Changes for v3:
- Replaced again 'if(IS_ENABLED(CONFIG_64BIT))' by '#ifdef CONFIG_64BIT'
  because on 32bit architectures (e.g., csky), __raw_{read,write}q are
  not defined. So, it leads to compilation errors
---
Julian Vetter (4):
  Consolidate __memcpy_{to,from}io and __memset_io into a single lib
  Use generic io memcpy functions on the arm64 architecture
  Use generic io memcpy functions on the csky architecture
  Use generic io memcpy functions on the loongarch architecture

 arch/arm64/Kconfig             |   1 +
 arch/arm64/kernel/io.c         |  87 --------------------------
 arch/csky/Kconfig              |   1 +
 arch/csky/kernel/Makefile      |   2 +-
 arch/csky/kernel/io.c          |  91 ---------------------------
 arch/loongarch/Kconfig         |   1 +
 arch/loongarch/kernel/Makefile |   2 +-
 arch/loongarch/kernel/io.c     |  94 ----------------------------
 lib/Kconfig                    |   3 +
 lib/Makefile                   |   1 +
 lib/io_copy.c                  | 110 +++++++++++++++++++++++++++++++++
 11 files changed, 119 insertions(+), 274 deletions(-)
 delete mode 100644 arch/csky/kernel/io.c
 delete mode 100644 arch/loongarch/kernel/io.c
 create mode 100644 lib/io_copy.c

-- 
2.34.1

[PATCH v3 1/4] Consolidate __memcpy_{to,from}io and __memset_io into a single lib

[Julian Vetter]

Various architectures have almost the same implementations for
__memcpy_{to,from}io and __memset_io functions. So, consolidate them and
introduce a CONFIG_GENERIC_IO_COPY flag to build the given
lib/io_copy.c.

Reviewed-by: Yann Sionneau <ysionneau@kalrayinc.com>
Signed-off-by: Julian Vetter <jvetter@kalrayinc.com>
---
 lib/Kconfig   |   3 ++
 lib/Makefile  |   1 +
 lib/io_copy.c | 110 ++++++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 114 insertions(+)
 create mode 100644 lib/io_copy.c

diff --git a/lib/Kconfig b/lib/Kconfig
index b38849af6f13..741550bc3856 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -70,6 +70,9 @@ source "lib/math/Kconfig"
 config NO_GENERIC_PCI_IOPORT_MAP
 	bool
 
+config GENERIC_IO_COPY
+	bool
+
 config GENERIC_IOMAP
 	bool
 	select GENERIC_PCI_IOMAP
diff --git a/lib/Makefile b/lib/Makefile
index 322bb127b4dc..4f56ad5f9ed6 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -130,6 +130,7 @@ CFLAGS_debug_info.o += $(call cc-option, -femit-struct-debug-detailed=any)
 
 obj-y += math/ crypto/
 
+obj-$(CONFIG_GENERIC_IO_COPY) += io_copy.o
 obj-$(CONFIG_GENERIC_IOMAP) += iomap.o
 obj-$(CONFIG_HAS_IOMEM) += iomap_copy.o devres.o
 obj-$(CONFIG_CHECK_SIGNATURE) += check_signature.o
diff --git a/lib/io_copy.c b/lib/io_copy.c
new file mode 100644
index 000000000000..f44583166325
--- /dev/null
+++ b/lib/io_copy.c
@@ -0,0 +1,110 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * derived from arch/arm/kernel/io.c
+ *
+ * Copyright (C) 2024 Kalray Inc.
+ * Author(s): Julian Vetter
+ */
+
+#include <asm/unaligned.h>
+
+#include <linux/export.h>
+#include <linux/types.h>
+#include <linux/io.h>
+
+#define NATIVE_STORE_SIZE	(BITS_PER_LONG/8)
+
+void __memcpy_fromio(void *to, const volatile void __iomem *from, size_t count)
+{
+	while (count && !IS_ALIGNED((unsigned long)from, NATIVE_STORE_SIZE)) {
+		*(u8 *)to = __raw_readb(from);
+		from++;
+		to++;
+		count--;
+	}
+
+	while (count >= NATIVE_STORE_SIZE) {
+#ifdef CONFIG_64BIT
+			put_unaligned(__raw_readq(from), (uintptr_t *)to);
+#else
+			put_unaligned(__raw_readl(from), (uintptr_t *)to);
+#endif
+
+		from += NATIVE_STORE_SIZE;
+		to += NATIVE_STORE_SIZE;
+		count -= NATIVE_STORE_SIZE;
+	}
+
+	while (count) {
+		*(u8 *)to = __raw_readb(from);
+		from++;
+		to++;
+		count--;
+	}
+}
+EXPORT_SYMBOL(__memcpy_fromio);
+
+void __memcpy_toio(volatile void __iomem *to, const void *from, size_t count)
+{
+	while (count && !IS_ALIGNED((unsigned long)to, NATIVE_STORE_SIZE)) {
+		__raw_writeb(*(u8 *)from, to);
+		from++;
+		to++;
+		count--;
+	}
+
+	while (count >= NATIVE_STORE_SIZE) {
+#ifdef CONFIG_64BIT
+			__raw_writeq(get_unaligned((uintptr_t *)from), to);
+#else
+			__raw_writel(get_unaligned((uintptr_t *)from), to);
+#endif
+
+		from += NATIVE_STORE_SIZE;
+		to += NATIVE_STORE_SIZE;
+		count -= NATIVE_STORE_SIZE;
+	}
+
+	while (count) {
+		__raw_writeb(*(u8 *)from, to);
+		from++;
+		to++;
+		count--;
+	}
+}
+EXPORT_SYMBOL(__memcpy_toio);
+
+void __memset_io(volatile void __iomem *dst, int c, size_t count)
+{
+	uintptr_t qc = (u8)c;
+
+	qc |= qc << 8;
+	qc |= qc << 16;
+
+	if (IS_ENABLED(CONFIG_64BIT))
+		qc |= qc << 32;
+
+	while (count && !IS_ALIGNED((unsigned long)dst, NATIVE_STORE_SIZE)) {
+		__raw_writeb(c, dst);
+		dst++;
+		count--;
+	}
+
+	while (count >= NATIVE_STORE_SIZE) {
+#ifdef CONFIG_64BIT
+			__raw_writeq(qc, dst);
+#else
+			__raw_writel(qc, dst);
+#endif
+
+		dst += NATIVE_STORE_SIZE;
+		count -= NATIVE_STORE_SIZE;
+	}
+
+	while (count) {
+		__raw_writeb(c, dst);
+		dst++;
+		count--;
+	}
+}
+EXPORT_SYMBOL(__memset_io);
-- 
2.34.1

Re: [PATCH v3 1/4] Consolidate __memcpy_{to,from}io and __memset_io into a single lib

[Catalin Marinas]

On Tue, Sep 10, 2024 at 03:43:38PM +0200, Julian Vetter wrote:
> Various architectures have almost the same implementations for
> __memcpy_{to,from}io and __memset_io functions. So, consolidate them and
> introduce a CONFIG_GENERIC_IO_COPY flag to build the given
> lib/io_copy.c.
> 
> Reviewed-by: Yann Sionneau <ysionneau@kalrayinc.com>
> Signed-off-by: Julian Vetter <jvetter@kalrayinc.com>

The code looks correct:

Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>

[PATCH v3 2/4] Use generic io memcpy functions on the arm64 architecture

[Julian Vetter]

Use the generic __memcpy_{from,to}io and __memset_io functions on the
arm64 processor architecture.

Reviewed-by: Yann Sionneau <ysionneau@kalrayinc.com>
Signed-off-by: Julian Vetter <jvetter@kalrayinc.com>
---
 arch/arm64/Kconfig     |  1 +
 arch/arm64/kernel/io.c | 87 ------------------------------------------
 2 files changed, 1 insertion(+), 87 deletions(-)

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index a2f8ff354ca6..cfb1c729c9a1 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -140,6 +140,7 @@ config ARM64
 	select GENERIC_CPU_VULNERABILITIES
 	select GENERIC_EARLY_IOREMAP
 	select GENERIC_IDLE_POLL_SETUP
+	select GENERIC_IO_COPY
 	select GENERIC_IOREMAP
 	select GENERIC_IRQ_IPI
 	select GENERIC_IRQ_PROBE
diff --git a/arch/arm64/kernel/io.c b/arch/arm64/kernel/io.c
index ef48089fbfe1..fe86ada23c7d 100644
--- a/arch/arm64/kernel/io.c
+++ b/arch/arm64/kernel/io.c
@@ -9,34 +9,6 @@
 #include <linux/types.h>
 #include <linux/io.h>
 
-/*
- * Copy data from IO memory space to "real" memory space.
- */
-void __memcpy_fromio(void *to, const volatile void __iomem *from, size_t count)
-{
-	while (count && !IS_ALIGNED((unsigned long)from, 8)) {
-		*(u8 *)to = __raw_readb(from);
-		from++;
-		to++;
-		count--;
-	}
-
-	while (count >= 8) {
-		*(u64 *)to = __raw_readq(from);
-		from += 8;
-		to += 8;
-		count -= 8;
-	}
-
-	while (count) {
-		*(u8 *)to = __raw_readb(from);
-		from++;
-		to++;
-		count--;
-	}
-}
-EXPORT_SYMBOL(__memcpy_fromio);
-
 /*
  * This generates a memcpy that works on a from/to address which is aligned to
  * bits. Count is in terms of the number of bits sized quantities to copy. It
@@ -78,62 +50,3 @@ void __iowrite32_copy_full(void __iomem *to, const void *from, size_t count)
 	dgh();
 }
 EXPORT_SYMBOL(__iowrite32_copy_full);
-
-/*
- * Copy data from "real" memory space to IO memory space.
- */
-void __memcpy_toio(volatile void __iomem *to, const void *from, size_t count)
-{
-	while (count && !IS_ALIGNED((unsigned long)to, 8)) {
-		__raw_writeb(*(u8 *)from, to);
-		from++;
-		to++;
-		count--;
-	}
-
-	while (count >= 8) {
-		__raw_writeq(*(u64 *)from, to);
-		from += 8;
-		to += 8;
-		count -= 8;
-	}
-
-	while (count) {
-		__raw_writeb(*(u8 *)from, to);
-		from++;
-		to++;
-		count--;
-	}
-}
-EXPORT_SYMBOL(__memcpy_toio);
-
-/*
- * "memset" on IO memory space.
- */
-void __memset_io(volatile void __iomem *dst, int c, size_t count)
-{
-	u64 qc = (u8)c;
-
-	qc |= qc << 8;
-	qc |= qc << 16;
-	qc |= qc << 32;
-
-	while (count && !IS_ALIGNED((unsigned long)dst, 8)) {
-		__raw_writeb(c, dst);
-		dst++;
-		count--;
-	}
-
-	while (count >= 8) {
-		__raw_writeq(qc, dst);
-		dst += 8;
-		count -= 8;
-	}
-
-	while (count) {
-		__raw_writeb(c, dst);
-		dst++;
-		count--;
-	}
-}
-EXPORT_SYMBOL(__memset_io);
-- 
2.34.1

Re: [PATCH v3 2/4] Use generic io memcpy functions on the arm64 architecture

[Catalin Marinas]

On Tue, Sep 10, 2024 at 03:43:39PM +0200, Julian Vetter wrote:
> Use the generic __memcpy_{from,to}io and __memset_io functions on the
> arm64 processor architecture.
> 
> Reviewed-by: Yann Sionneau <ysionneau@kalrayinc.com>
> Signed-off-by: Julian Vetter <jvetter@kalrayinc.com>

Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>

[PATCH v3 3/4] Use generic io memcpy functions on the csky architecture

[Julian Vetter]

Use the generic __memcpy_{from,to}io and __memset_io functions on the
csky processor architecture.

Reviewed-by: Yann Sionneau <ysionneau@kalrayinc.com>
Signed-off-by: Julian Vetter <jvetter@kalrayinc.com>
---
 arch/csky/Kconfig         |  1 +
 arch/csky/kernel/Makefile |  2 +-
 arch/csky/kernel/io.c     | 91 ---------------------------------------
 3 files changed, 2 insertions(+), 92 deletions(-)
 delete mode 100644 arch/csky/kernel/io.c

diff --git a/arch/csky/Kconfig b/arch/csky/Kconfig
index 5479707eb5d1..59d4051b2a83 100644
--- a/arch/csky/Kconfig
+++ b/arch/csky/Kconfig
@@ -48,6 +48,7 @@ config CSKY
 	select DMA_DIRECT_REMAP
 	select IRQ_DOMAIN
 	select DW_APB_TIMER_OF
+	select GENERIC_IO_COPY
 	select GENERIC_IOREMAP
 	select GENERIC_LIB_ASHLDI3
 	select GENERIC_LIB_ASHRDI3
diff --git a/arch/csky/kernel/Makefile b/arch/csky/kernel/Makefile
index 8a868316b912..de1c3472e8f0 100644
--- a/arch/csky/kernel/Makefile
+++ b/arch/csky/kernel/Makefile
@@ -2,7 +2,7 @@
 extra-y := vmlinux.lds
 
 obj-y += head.o entry.o atomic.o signal.o traps.o irq.o time.o vdso.o vdso/
-obj-y += power.o syscall.o syscall_table.o setup.o io.o
+obj-y += power.o syscall.o syscall_table.o setup.o
 obj-y += process.o cpu-probe.o ptrace.o stacktrace.o
 obj-y += probes/
 
diff --git a/arch/csky/kernel/io.c b/arch/csky/kernel/io.c
deleted file mode 100644
index 5883f13fa2b1..000000000000
--- a/arch/csky/kernel/io.c
+++ /dev/null
@@ -1,91 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-
-#include <linux/export.h>
-#include <linux/types.h>
-#include <linux/io.h>
-
-/*
- * Copy data from IO memory space to "real" memory space.
- */
-void __memcpy_fromio(void *to, const volatile void __iomem *from, size_t count)
-{
-	while (count && !IS_ALIGNED((unsigned long)from, 4)) {
-		*(u8 *)to = __raw_readb(from);
-		from++;
-		to++;
-		count--;
-	}
-
-	while (count >= 4) {
-		*(u32 *)to = __raw_readl(from);
-		from += 4;
-		to += 4;
-		count -= 4;
-	}
-
-	while (count) {
-		*(u8 *)to = __raw_readb(from);
-		from++;
-		to++;
-		count--;
-	}
-}
-EXPORT_SYMBOL(__memcpy_fromio);
-
-/*
- * Copy data from "real" memory space to IO memory space.
- */
-void __memcpy_toio(volatile void __iomem *to, const void *from, size_t count)
-{
-	while (count && !IS_ALIGNED((unsigned long)to, 4)) {
-		__raw_writeb(*(u8 *)from, to);
-		from++;
-		to++;
-		count--;
-	}
-
-	while (count >= 4) {
-		__raw_writel(*(u32 *)from, to);
-		from += 4;
-		to += 4;
-		count -= 4;
-	}
-
-	while (count) {
-		__raw_writeb(*(u8 *)from, to);
-		from++;
-		to++;
-		count--;
-	}
-}
-EXPORT_SYMBOL(__memcpy_toio);
-
-/*
- * "memset" on IO memory space.
- */
-void __memset_io(volatile void __iomem *dst, int c, size_t count)
-{
-	u32 qc = (u8)c;
-
-	qc |= qc << 8;
-	qc |= qc << 16;
-
-	while (count && !IS_ALIGNED((unsigned long)dst, 4)) {
-		__raw_writeb(c, dst);
-		dst++;
-		count--;
-	}
-
-	while (count >= 4) {
-		__raw_writel(qc, dst);
-		dst += 4;
-		count -= 4;
-	}
-
-	while (count) {
-		__raw_writeb(c, dst);
-		dst++;
-		count--;
-	}
-}
-EXPORT_SYMBOL(__memset_io);
-- 
2.34.1

[PATCH v3 4/4] Use generic io memcpy functions on the loongarch architecture

[Julian Vetter]

Use the generic __memcpy_{from,to}io and __memset_io functions on the
loongarch processor architecture.

Reviewed-by: Yann Sionneau <ysionneau@kalrayinc.com>
Signed-off-by: Julian Vetter <jvetter@kalrayinc.com>
---
 arch/loongarch/Kconfig         |  1 +
 arch/loongarch/kernel/Makefile |  2 +-
 arch/loongarch/kernel/io.c     | 94 ----------------------------------
 3 files changed, 2 insertions(+), 95 deletions(-)
 delete mode 100644 arch/loongarch/kernel/io.c

diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig
index 70f169210b52..bc97b09efd16 100644
--- a/arch/loongarch/Kconfig
+++ b/arch/loongarch/Kconfig
@@ -84,6 +84,7 @@ config LOONGARCH
 	select GENERIC_CPU_DEVICES
 	select GENERIC_ENTRY
 	select GENERIC_GETTIMEOFDAY
+	select GENERIC_IO_COPY
 	select GENERIC_IOREMAP if !ARCH_IOREMAP
 	select GENERIC_IRQ_MULTI_HANDLER
 	select GENERIC_IRQ_PROBE
diff --git a/arch/loongarch/kernel/Makefile b/arch/loongarch/kernel/Makefile
index c9bfeda89e40..9497968ee158 100644
--- a/arch/loongarch/kernel/Makefile
+++ b/arch/loongarch/kernel/Makefile
@@ -8,7 +8,7 @@ OBJECT_FILES_NON_STANDARD_head.o := y
 extra-y		:= vmlinux.lds
 
 obj-y		+= head.o cpu-probe.o cacheinfo.o env.o setup.o entry.o genex.o \
-		   traps.o irq.o idle.o process.o dma.o mem.o io.o reset.o switch.o \
+		   traps.o irq.o idle.o process.o dma.o mem.o reset.o switch.o \
 		   elf.o syscall.o signal.o time.o topology.o inst.o ptrace.o vdso.o \
 		   alternative.o unwind.o
 
diff --git a/arch/loongarch/kernel/io.c b/arch/loongarch/kernel/io.c
deleted file mode 100644
index cb85bda5a6ad..000000000000
--- a/arch/loongarch/kernel/io.c
+++ /dev/null
@@ -1,94 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Copyright (C) 2020-2022 Loongson Technology Corporation Limited
- */
-#include <linux/export.h>
-#include <linux/types.h>
-#include <linux/io.h>
-
-/*
- * Copy data from IO memory space to "real" memory space.
- */
-void __memcpy_fromio(void *to, const volatile void __iomem *from, size_t count)
-{
-	while (count && !IS_ALIGNED((unsigned long)from, 8)) {
-		*(u8 *)to = __raw_readb(from);
-		from++;
-		to++;
-		count--;
-	}
-
-	while (count >= 8) {
-		*(u64 *)to = __raw_readq(from);
-		from += 8;
-		to += 8;
-		count -= 8;
-	}
-
-	while (count) {
-		*(u8 *)to = __raw_readb(from);
-		from++;
-		to++;
-		count--;
-	}
-}
-EXPORT_SYMBOL(__memcpy_fromio);
-
-/*
- * Copy data from "real" memory space to IO memory space.
- */
-void __memcpy_toio(volatile void __iomem *to, const void *from, size_t count)
-{
-	while (count && !IS_ALIGNED((unsigned long)to, 8)) {
-		__raw_writeb(*(u8 *)from, to);
-		from++;
-		to++;
-		count--;
-	}
-
-	while (count >= 8) {
-		__raw_writeq(*(u64 *)from, to);
-		from += 8;
-		to += 8;
-		count -= 8;
-	}
-
-	while (count) {
-		__raw_writeb(*(u8 *)from, to);
-		from++;
-		to++;
-		count--;
-	}
-}
-EXPORT_SYMBOL(__memcpy_toio);
-
-/*
- * "memset" on IO memory space.
- */
-void __memset_io(volatile void __iomem *dst, int c, size_t count)
-{
-	u64 qc = (u8)c;
-
-	qc |= qc << 8;
-	qc |= qc << 16;
-	qc |= qc << 32;
-
-	while (count && !IS_ALIGNED((unsigned long)dst, 8)) {
-		__raw_writeb(c, dst);
-		dst++;
-		count--;
-	}
-
-	while (count >= 8) {
-		__raw_writeq(qc, dst);
-		dst += 8;
-		count -= 8;
-	}
-
-	while (count) {
-		__raw_writeb(c, dst);
-		dst++;
-		count--;
-	}
-}
-EXPORT_SYMBOL(__memset_io);
-- 
2.34.1