diff mbox series

[v1,3/6] riscv: Add vector extension XOR implementation

Message ID 20230715150032.6917-4-andy.chiu@sifive.com (mailing list archive)
State Superseded
Headers show
Series riscv: support kernel-mode Vector | expand

Checks

Context Check Description
conchuod/cover_letter success Series has a cover letter
conchuod/tree_selection success Guessed tree name to be for-next at HEAD 471aba2e4760
conchuod/fixes_present success Fixes tag not required for -next series
conchuod/maintainers_pattern success MAINTAINERS pattern errors before the patch: 4 and now 4
conchuod/verify_signedoff success Signed-off-by tag matches author and committer
conchuod/kdoc success Errors and warnings before: 0 this patch: 0
conchuod/build_rv64_clang_allmodconfig success Errors and warnings before: 9 this patch: 9
conchuod/module_param success Was 0 now: 0
conchuod/build_rv64_gcc_allmodconfig success Errors and warnings before: 9 this patch: 9
conchuod/build_rv32_defconfig success Build OK
conchuod/dtb_warn_rv64 success Errors and warnings before: 3 this patch: 3
conchuod/header_inline fail Detected static functions without inline keyword in header files: 1
conchuod/checkpatch warning WARNING: added, moved or deleted file(s), does MAINTAINERS need updating?
conchuod/build_rv64_nommu_k210_defconfig success Build OK
conchuod/verify_fixes success No Fixes tag
conchuod/build_rv64_nommu_virt_defconfig success Build OK

Commit Message

Andy Chiu July 15, 2023, 3 p.m. UTC
From: Greentime Hu <greentime.hu@sifive.com>

This patch adds support for vector optimized XOR and it is tested in
qemu.

Co-developed-by: Han-Kuan Chen <hankuan.chen@sifive.com>
Signed-off-by: Han-Kuan Chen <hankuan.chen@sifive.com>
Signed-off-by: Greentime Hu <greentime.hu@sifive.com>
Signed-off-by: Andy Chiu <andy.chiu@sifive.com>
---
 arch/riscv/include/asm/xor.h | 82 ++++++++++++++++++++++++++++++++++++
 arch/riscv/lib/Makefile      |  1 +
 arch/riscv/lib/xor.S         | 81 +++++++++++++++++++++++++++++++++++
 3 files changed, 164 insertions(+)
 create mode 100644 arch/riscv/include/asm/xor.h
 create mode 100644 arch/riscv/lib/xor.S

Comments

Conor Dooley July 17, 2023, 10:25 a.m. UTC | #1
On Sat, Jul 15, 2023 at 03:00:29PM +0000, Andy Chiu wrote:
> From: Greentime Hu <greentime.hu@sifive.com>
> 
> This patch adds support for vector optimized XOR and it is tested in
> qemu.

Since this patch was originally written, has it been tested in hardware?

> Co-developed-by: Han-Kuan Chen <hankuan.chen@sifive.com>
> Signed-off-by: Han-Kuan Chen <hankuan.chen@sifive.com>
> Signed-off-by: Greentime Hu <greentime.hu@sifive.com>
> Signed-off-by: Andy Chiu <andy.chiu@sifive.com>
> ---
>  arch/riscv/include/asm/xor.h | 82 ++++++++++++++++++++++++++++++++++++
>  arch/riscv/lib/Makefile      |  1 +
>  arch/riscv/lib/xor.S         | 81 +++++++++++++++++++++++++++++++++++
>  3 files changed, 164 insertions(+)
>  create mode 100644 arch/riscv/include/asm/xor.h
>  create mode 100644 arch/riscv/lib/xor.S
> 
> diff --git a/arch/riscv/include/asm/xor.h b/arch/riscv/include/asm/xor.h
> new file mode 100644
> index 000000000000..81b8837fa161
> --- /dev/null
> +++ b/arch/riscv/include/asm/xor.h

> +static void xor_rvv_2(unsigned long bytes, unsigned long *__restrict p1,
> +		      const unsigned long *__restrict p2)

> +static void xor_rvv_3(unsigned long bytes, unsigned long *__restrict p1,
> +		      const unsigned long *__restrict p2,
> +		      const unsigned long *__restrict p3)

> +static void xor_rvv_4(unsigned long bytes, unsigned long *__restrict p1,
> +		      const unsigned long *__restrict p2,
> +		      const unsigned long *__restrict p3,
> +		      const unsigned long *__restrict p4)

> +
> +static void xor_rvv_5(unsigned long bytes, unsigned long *__restrict p1,
> +		      const unsigned long *__restrict p2,
> +		      const unsigned long *__restrict p3,
> +		      const unsigned long *__restrict p4,
> +		      const unsigned long *__restrict p5)

> +
> +static struct xor_block_template xor_block_rvv = {
> +	.name = "rvv",
> +	.do_2 = xor_rvv_2,
> +	.do_3 = xor_rvv_3,
> +	.do_4 = xor_rvv_4,
> +	.do_5 = xor_rvv_5
> +};

Same naming scheme comments as the main vector patchset and 2/6 apply
here too.
Andy Chiu July 20, 2023, 2:56 p.m. UTC | #2
On Mon, Jul 17, 2023 at 6:26 PM Conor Dooley <conor.dooley@microchip.com> wrote:
>
> On Sat, Jul 15, 2023 at 03:00:29PM +0000, Andy Chiu wrote:
> > From: Greentime Hu <greentime.hu@sifive.com>
> >
> > This patch adds support for vector optimized XOR and it is tested in
> > qemu.
>
> Since this patch was originally written, has it been tested in hardware?

We've run it on internal FPGAs but FPGAs don't count, right?  ;)

>
> > Co-developed-by: Han-Kuan Chen <hankuan.chen@sifive.com>
> > Signed-off-by: Han-Kuan Chen <hankuan.chen@sifive.com>
> > Signed-off-by: Greentime Hu <greentime.hu@sifive.com>
> > Signed-off-by: Andy Chiu <andy.chiu@sifive.com>
> > ---
> >  arch/riscv/include/asm/xor.h | 82 ++++++++++++++++++++++++++++++++++++
> >  arch/riscv/lib/Makefile      |  1 +
> >  arch/riscv/lib/xor.S         | 81 +++++++++++++++++++++++++++++++++++
> >  3 files changed, 164 insertions(+)
> >  create mode 100644 arch/riscv/include/asm/xor.h
> >  create mode 100644 arch/riscv/lib/xor.S
> >
> > diff --git a/arch/riscv/include/asm/xor.h b/arch/riscv/include/asm/xor.h
> > new file mode 100644
> > index 000000000000..81b8837fa161
> > --- /dev/null
> > +++ b/arch/riscv/include/asm/xor.h
>
> > +static void xor_rvv_2(unsigned long bytes, unsigned long *__restrict p1,
> > +                   const unsigned long *__restrict p2)
>
> > +static void xor_rvv_3(unsigned long bytes, unsigned long *__restrict p1,
> > +                   const unsigned long *__restrict p2,
> > +                   const unsigned long *__restrict p3)
>
> > +static void xor_rvv_4(unsigned long bytes, unsigned long *__restrict p1,
> > +                   const unsigned long *__restrict p2,
> > +                   const unsigned long *__restrict p3,
> > +                   const unsigned long *__restrict p4)
>
> > +
> > +static void xor_rvv_5(unsigned long bytes, unsigned long *__restrict p1,
> > +                   const unsigned long *__restrict p2,
> > +                   const unsigned long *__restrict p3,
> > +                   const unsigned long *__restrict p4,
> > +                   const unsigned long *__restrict p5)
>
> > +
> > +static struct xor_block_template xor_block_rvv = {
> > +     .name = "rvv",
> > +     .do_2 = xor_rvv_2,
> > +     .do_3 = xor_rvv_3,
> > +     .do_4 = xor_rvv_4,
> > +     .do_5 = xor_rvv_5
> > +};
>
> Same naming scheme comments as the main vector patchset and 2/6 apply
> here too.

Yep, I'm doing s/xor_rvv/xor_vector

Thanks,
Andy
diff mbox series

Patch

diff --git a/arch/riscv/include/asm/xor.h b/arch/riscv/include/asm/xor.h
new file mode 100644
index 000000000000..81b8837fa161
--- /dev/null
+++ b/arch/riscv/include/asm/xor.h
@@ -0,0 +1,82 @@ 
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (C) 2021 SiFive
+ */
+
+#include <linux/hardirq.h>
+#include <asm-generic/xor.h>
+#ifdef CONFIG_RISCV_ISA_V
+#include <asm/vector.h>
+#include <asm/switch_to.h>
+
+void xor_regs_2_(unsigned long bytes, unsigned long *__restrict p1,
+		 const unsigned long *__restrict p2);
+void xor_regs_3_(unsigned long bytes, unsigned long *__restrict p1,
+		 const unsigned long *__restrict p2,
+		 const unsigned long *__restrict p3);
+void xor_regs_4_(unsigned long bytes, unsigned long *__restrict p1,
+		 const unsigned long *__restrict p2,
+		 const unsigned long *__restrict p3,
+		 const unsigned long *__restrict p4);
+void xor_regs_5_(unsigned long bytes, unsigned long *__restrict p1,
+		 const unsigned long *__restrict p2,
+		 const unsigned long *__restrict p3,
+		 const unsigned long *__restrict p4,
+		 const unsigned long *__restrict p5);
+
+static void xor_rvv_2(unsigned long bytes, unsigned long *__restrict p1,
+		      const unsigned long *__restrict p2)
+{
+	kernel_rvv_begin();
+	xor_regs_2_(bytes, p1, p2);
+	kernel_rvv_end();
+}
+
+static void xor_rvv_3(unsigned long bytes, unsigned long *__restrict p1,
+		      const unsigned long *__restrict p2,
+		      const unsigned long *__restrict p3)
+{
+	kernel_rvv_begin();
+	xor_regs_3_(bytes, p1, p2, p3);
+	kernel_rvv_end();
+}
+
+static void xor_rvv_4(unsigned long bytes, unsigned long *__restrict p1,
+		      const unsigned long *__restrict p2,
+		      const unsigned long *__restrict p3,
+		      const unsigned long *__restrict p4)
+{
+	kernel_rvv_begin();
+	xor_regs_4_(bytes, p1, p2, p3, p4);
+	kernel_rvv_end();
+}
+
+static void xor_rvv_5(unsigned long bytes, unsigned long *__restrict p1,
+		      const unsigned long *__restrict p2,
+		      const unsigned long *__restrict p3,
+		      const unsigned long *__restrict p4,
+		      const unsigned long *__restrict p5)
+{
+	kernel_rvv_begin();
+	xor_regs_5_(bytes, p1, p2, p3, p4, p5);
+	kernel_rvv_end();
+}
+
+static struct xor_block_template xor_block_rvv = {
+	.name = "rvv",
+	.do_2 = xor_rvv_2,
+	.do_3 = xor_rvv_3,
+	.do_4 = xor_rvv_4,
+	.do_5 = xor_rvv_5
+};
+
+#undef XOR_TRY_TEMPLATES
+#define XOR_TRY_TEMPLATES           \
+	do {        \
+		xor_speed(&xor_block_8regs);    \
+		xor_speed(&xor_block_32regs);    \
+		if (has_vector()) { \
+			xor_speed(&xor_block_rvv);\
+		} \
+	} while (0)
+#endif
diff --git a/arch/riscv/lib/Makefile b/arch/riscv/lib/Makefile
index 26cb2502ecf8..494f9cd1a00c 100644
--- a/arch/riscv/lib/Makefile
+++ b/arch/riscv/lib/Makefile
@@ -11,3 +11,4 @@  lib-$(CONFIG_64BIT)	+= tishift.o
 lib-$(CONFIG_RISCV_ISA_ZICBOZ)	+= clear_page.o
 
 obj-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o
+lib-$(CONFIG_RISCV_ISA_V)	+= xor.o
diff --git a/arch/riscv/lib/xor.S b/arch/riscv/lib/xor.S
new file mode 100644
index 000000000000..3bc059e18171
--- /dev/null
+++ b/arch/riscv/lib/xor.S
@@ -0,0 +1,81 @@ 
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (C) 2021 SiFive
+ */
+#include <linux/linkage.h>
+#include <asm-generic/export.h>
+#include <asm/asm.h>
+
+ENTRY(xor_regs_2_)
+	vsetvli a3, a0, e8, m8, ta, ma
+	vle8.v v0, (a1)
+	vle8.v v8, (a2)
+	sub a0, a0, a3
+	vxor.vv v16, v0, v8
+	add a2, a2, a3
+	vse8.v v16, (a1)
+	add a1, a1, a3
+	bnez a0, xor_regs_2_
+	ret
+END(xor_regs_2_)
+EXPORT_SYMBOL(xor_regs_2_)
+
+ENTRY(xor_regs_3_)
+	vsetvli a4, a0, e8, m8, ta, ma
+	vle8.v v0, (a1)
+	vle8.v v8, (a2)
+	sub a0, a0, a4
+	vxor.vv v0, v0, v8
+	vle8.v v16, (a3)
+	add a2, a2, a4
+	vxor.vv v16, v0, v16
+	add a3, a3, a4
+	vse8.v v16, (a1)
+	add a1, a1, a4
+	bnez a0, xor_regs_3_
+	ret
+END(xor_regs_3_)
+EXPORT_SYMBOL(xor_regs_3_)
+
+ENTRY(xor_regs_4_)
+	vsetvli a5, a0, e8, m8, ta, ma
+	vle8.v v0, (a1)
+	vle8.v v8, (a2)
+	sub a0, a0, a5
+	vxor.vv v0, v0, v8
+	vle8.v v16, (a3)
+	add a2, a2, a5
+	vxor.vv v0, v0, v16
+	vle8.v v24, (a4)
+	add a3, a3, a5
+	vxor.vv v16, v0, v24
+	add a4, a4, a5
+	vse8.v v16, (a1)
+	add a1, a1, a5
+	bnez a0, xor_regs_4_
+	ret
+END(xor_regs_4_)
+EXPORT_SYMBOL(xor_regs_4_)
+
+ENTRY(xor_regs_5_)
+	vsetvli a6, a0, e8, m8, ta, ma
+	vle8.v v0, (a1)
+	vle8.v v8, (a2)
+	sub a0, a0, a6
+	vxor.vv v0, v0, v8
+	vle8.v v16, (a3)
+	add a2, a2, a6
+	vxor.vv v0, v0, v16
+	vle8.v v24, (a4)
+	add a3, a3, a6
+	vxor.vv v0, v0, v24
+	vle8.v v8, (a5)
+	add a4, a4, a6
+	vxor.vv v16, v0, v8
+	add a5, a5, a6
+	vse8.v v16, (a1)
+	add a1, a1, a6
+	bnez a0, xor_regs_5_
+	ret
+END(xor_regs_5_)
+EXPORT_SYMBOL(xor_regs_5_)