diff mbox series

[v4,11/15] riscv: Add support for kernel-mode FPU

Message ID 20240329072441.591471-12-samuel.holland@sifive.com (mailing list archive)
State New, archived
Headers show
Series Unified cross-architecture kernel-mode FPU API | expand

Commit Message

Samuel Holland March 29, 2024, 7:18 a.m. UTC
This is motivated by the amdgpu DRM driver, which needs floating-point
code to support recent hardware. That code is not performance-critical,
so only provide a minimal non-preemptible implementation for now.

Support is limited to riscv64 because riscv32 requires runtime (libgcc)
assistance to convert between doubles and 64-bit integers.

Acked-by: Palmer Dabbelt <palmer@rivosinc.com>
Reviewed-by: Palmer Dabbelt <palmer@rivosinc.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Samuel Holland <samuel.holland@sifive.com>
---

(no changes since v3)

Changes in v3:
 - Limit riscv ARCH_HAS_KERNEL_FPU_SUPPORT to 64BIT

Changes in v2:
 - Remove RISC-V architecture-specific preprocessor check

 arch/riscv/Kconfig                  |  1 +
 arch/riscv/Makefile                 |  3 +++
 arch/riscv/include/asm/fpu.h        | 16 ++++++++++++++++
 arch/riscv/kernel/Makefile          |  1 +
 arch/riscv/kernel/kernel_mode_fpu.c | 28 ++++++++++++++++++++++++++++
 5 files changed, 49 insertions(+)
 create mode 100644 arch/riscv/include/asm/fpu.h
 create mode 100644 arch/riscv/kernel/kernel_mode_fpu.c
diff mbox series

Patch

diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index be09c8836d56..3bcd0d250810 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -27,6 +27,7 @@  config RISCV
 	select ARCH_HAS_GCOV_PROFILE_ALL
 	select ARCH_HAS_GIGANTIC_PAGE
 	select ARCH_HAS_KCOV
+	select ARCH_HAS_KERNEL_FPU_SUPPORT if 64BIT && FPU
 	select ARCH_HAS_MEMBARRIER_CALLBACKS
 	select ARCH_HAS_MEMBARRIER_SYNC_CORE
 	select ARCH_HAS_MMIOWB
diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile
index 252d63942f34..76ff4033c854 100644
--- a/arch/riscv/Makefile
+++ b/arch/riscv/Makefile
@@ -84,6 +84,9 @@  KBUILD_CFLAGS += -march=$(shell echo $(riscv-march-y) | sed -E 's/(rv32ima|rv64i
 
 KBUILD_AFLAGS += -march=$(riscv-march-y)
 
+# For C code built with floating-point support, exclude V but keep F and D.
+CC_FLAGS_FPU  := -march=$(shell echo $(riscv-march-y) | sed -E 's/(rv32ima|rv64ima)([^v_]*)v?/\1\2/')
+
 KBUILD_CFLAGS += -mno-save-restore
 KBUILD_CFLAGS += -DCONFIG_PAGE_OFFSET=$(CONFIG_PAGE_OFFSET)
 
diff --git a/arch/riscv/include/asm/fpu.h b/arch/riscv/include/asm/fpu.h
new file mode 100644
index 000000000000..91c04c244e12
--- /dev/null
+++ b/arch/riscv/include/asm/fpu.h
@@ -0,0 +1,16 @@ 
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2023 SiFive
+ */
+
+#ifndef _ASM_RISCV_FPU_H
+#define _ASM_RISCV_FPU_H
+
+#include <asm/switch_to.h>
+
+#define kernel_fpu_available()	has_fpu()
+
+void kernel_fpu_begin(void);
+void kernel_fpu_end(void);
+
+#endif /* ! _ASM_RISCV_FPU_H */
diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile
index 81d94a8ee10f..5b243d46f4b1 100644
--- a/arch/riscv/kernel/Makefile
+++ b/arch/riscv/kernel/Makefile
@@ -67,6 +67,7 @@  obj-$(CONFIG_RISCV_MISALIGNED)	+= unaligned_access_speed.o
 obj-$(CONFIG_RISCV_PROBE_UNALIGNED_ACCESS)	+= copy-unaligned.o
 
 obj-$(CONFIG_FPU)		+= fpu.o
+obj-$(CONFIG_FPU)		+= kernel_mode_fpu.o
 obj-$(CONFIG_RISCV_ISA_V)	+= vector.o
 obj-$(CONFIG_RISCV_ISA_V)	+= kernel_mode_vector.o
 obj-$(CONFIG_SMP)		+= smpboot.o
diff --git a/arch/riscv/kernel/kernel_mode_fpu.c b/arch/riscv/kernel/kernel_mode_fpu.c
new file mode 100644
index 000000000000..0ac8348876c4
--- /dev/null
+++ b/arch/riscv/kernel/kernel_mode_fpu.c
@@ -0,0 +1,28 @@ 
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2023 SiFive
+ */
+
+#include <linux/export.h>
+#include <linux/preempt.h>
+
+#include <asm/csr.h>
+#include <asm/fpu.h>
+#include <asm/processor.h>
+#include <asm/switch_to.h>
+
+void kernel_fpu_begin(void)
+{
+	preempt_disable();
+	fstate_save(current, task_pt_regs(current));
+	csr_set(CSR_SSTATUS, SR_FS);
+}
+EXPORT_SYMBOL_GPL(kernel_fpu_begin);
+
+void kernel_fpu_end(void)
+{
+	csr_clear(CSR_SSTATUS, SR_FS);
+	fstate_restore(current, task_pt_regs(current));
+	preempt_enable();
+}
+EXPORT_SYMBOL_GPL(kernel_fpu_end);