Sometimes it's useful to amortize calls to XSAVE/XRSTOR and the related FPU/SIMD functions over a number of calls, because FPU restoration is quite expensive. This adds a simple header for carrying out this pattern: simd_context_t simd_context; simd_get(&simd_context); while ((item = get_item_from_queue()) != NULL) { encrypt_item(item, simd_context); simd_relax(&simd_context); } simd_put(&simd_context); The relaxation step ensures that we don't trample over preemption, and the get/put API should be a familiar paradigm in the kernel. On the other end, code that actually wants to use SIMD instructions can accept this as a parameter and check it via: void encrypt_item(struct item *item, simd_context_t *simd_context) { if (item->len > LARGE_FOR_SIMD && simd_use(simd_context)) wild_simd_code(item); else boring_scalar_code(item); } The actual XSAVE happens during simd_use (and only on the first time), so that if the context is never actually used, no performance penalty is hit. Signed-off-by: Jason A. Donenfeld <Jason@xxxxxxxxx> Cc: Samuel Neves <sneves@xxxxxxxxx> Cc: Andy Lutomirski <luto@xxxxxxxxxx> Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx> Cc: Greg KH <gregkh@xxxxxxxxxxxxxxxxxxx> Cc: linux-arch@xxxxxxxxxxxxxxx --- arch/alpha/include/asm/Kbuild | 5 ++- arch/arc/include/asm/Kbuild | 1 + arch/arm/include/asm/simd.h | 63 ++++++++++++++++++++++++++++++ arch/arm64/include/asm/simd.h | 51 +++++++++++++++++++++--- arch/c6x/include/asm/Kbuild | 3 +- arch/h8300/include/asm/Kbuild | 3 +- arch/hexagon/include/asm/Kbuild | 1 + arch/ia64/include/asm/Kbuild | 1 + arch/m68k/include/asm/Kbuild | 1 + arch/microblaze/include/asm/Kbuild | 1 + arch/mips/include/asm/Kbuild | 1 + arch/nds32/include/asm/Kbuild | 7 ++-- arch/nios2/include/asm/Kbuild | 1 + arch/openrisc/include/asm/Kbuild | 7 ++-- arch/parisc/include/asm/Kbuild | 1 + arch/powerpc/include/asm/Kbuild | 3 +- arch/riscv/include/asm/Kbuild | 3 +- arch/s390/include/asm/Kbuild | 3 +- arch/sh/include/asm/Kbuild | 1 + arch/sparc/include/asm/Kbuild | 1 + arch/um/include/asm/Kbuild | 3 +- arch/unicore32/include/asm/Kbuild | 1 + arch/x86/include/asm/simd.h | 44 ++++++++++++++++++++- arch/xtensa/include/asm/Kbuild | 1 + include/asm-generic/simd.h | 20 ++++++++++ include/linux/simd.h | 28 +++++++++++++ 26 files changed, 234 insertions(+), 21 deletions(-) create mode 100644 arch/arm/include/asm/simd.h create mode 100644 include/linux/simd.h diff --git a/arch/alpha/include/asm/Kbuild b/arch/alpha/include/asm/Kbuild index 0580cb8c84b2..07b2c1025d34 100644 --- a/arch/alpha/include/asm/Kbuild +++ b/arch/alpha/include/asm/Kbuild @@ -2,14 +2,15 @@ generic-y += compat.h +generic-y += current.h generic-y += exec.h generic-y += export.h generic-y += fb.h generic-y += irq_work.h +generic-y += kprobes.h generic-y += mcs_spinlock.h generic-y += mm-arch-hooks.h generic-y += preempt.h generic-y += sections.h +generic-y += simd.h generic-y += trace_clock.h -generic-y += current.h -generic-y += kprobes.h diff --git a/arch/arc/include/asm/Kbuild b/arch/arc/include/asm/Kbuild index feed50ce89fa..a7f4255f1649 100644 --- a/arch/arc/include/asm/Kbuild +++ b/arch/arc/include/asm/Kbuild @@ -22,6 +22,7 @@ generic-y += parport.h generic-y += pci.h generic-y += percpu.h generic-y += preempt.h +generic-y += simd.h generic-y += topology.h generic-y += trace_clock.h generic-y += user.h diff --git a/arch/arm/include/asm/simd.h b/arch/arm/include/asm/simd.h new file mode 100644 index 000000000000..263950dd69cb --- /dev/null +++ b/arch/arm/include/asm/simd.h @@ -0,0 +1,63 @@ +/* SPDX-License-Identifier: GPL-2.0 + * + * Copyright (C) 2015-2018 Jason A. Donenfeld <Jason@xxxxxxxxx>. All Rights Reserved. + */ + +#include <linux/simd.h> +#ifndef _ASM_SIMD_H +#define _ASM_SIMD_H + +#ifdef CONFIG_KERNEL_MODE_NEON +#include <asm/neon.h> + +static __must_check inline bool may_use_simd(void) +{ + return !in_interrupt(); +} + +static inline void simd_get(simd_context_t *ctx) +{ + *ctx = may_use_simd() ? HAVE_FULL_SIMD : HAVE_NO_SIMD; +} + +static inline void simd_put(simd_context_t *ctx) +{ + if (*ctx & HAVE_SIMD_IN_USE) + kernel_neon_end(); + *ctx = HAVE_NO_SIMD; +} + +static __must_check inline bool simd_use(simd_context_t *ctx) +{ + if (!(*ctx & HAVE_FULL_SIMD)) + return false; + if (*ctx & HAVE_SIMD_IN_USE) + return true; + kernel_neon_begin(); + *ctx |= HAVE_SIMD_IN_USE; + return true; +} + +#else + +static __must_check inline bool may_use_simd(void) +{ + return false; +} + +static inline void simd_get(simd_context_t *ctx) +{ + *ctx = HAVE_NO_SIMD; +} + +static inline void simd_put(simd_context_t *ctx) +{ +} + +static __must_check inline bool simd_use(simd_context_t *ctx) +{ + return false; +} +#endif + +#endif /* _ASM_SIMD_H */ diff --git a/arch/arm64/include/asm/simd.h b/arch/arm64/include/asm/simd.h index 6495cc51246f..a45ff1600040 100644 --- a/arch/arm64/include/asm/simd.h +++ b/arch/arm64/include/asm/simd.h @@ -1,11 +1,10 @@ -/* - * Copyright (C) 2017 Linaro Ltd. <ard.biesheuvel@xxxxxxxxxx> +/* SPDX-License-Identifier: GPL-2.0 * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License version 2 as published - * by the Free Software Foundation. + * Copyright (C) 2017 Linaro Ltd. <ard.biesheuvel@xxxxxxxxxx> + * Copyright (C) 2015-2018 Jason A. Donenfeld <Jason@xxxxxxxxx>. All Rights Reserved. */ +#include <linux/simd.h> #ifndef __ASM_SIMD_H #define __ASM_SIMD_H @@ -16,6 +15,8 @@ #include <linux/types.h> #ifdef CONFIG_KERNEL_MODE_NEON +#include <asm/neon.h> +#include <asm/simd.h> DECLARE_PER_CPU(bool, kernel_neon_busy); @@ -40,9 +41,47 @@ static __must_check inline bool may_use_simd(void) !this_cpu_read(kernel_neon_busy); } +static inline void simd_get(simd_context_t *ctx) +{ + *ctx = may_use_simd() ? HAVE_FULL_SIMD : HAVE_NO_SIMD; +} + +static inline void simd_put(simd_context_t *ctx) +{ + if (*ctx & HAVE_SIMD_IN_USE) + kernel_neon_end(); + *ctx = HAVE_NO_SIMD; +} + +static __must_check inline bool simd_use(simd_context_t *ctx) +{ + if (!(*ctx & HAVE_FULL_SIMD)) + return false; + if (*ctx & HAVE_SIMD_IN_USE) + return true; + kernel_neon_begin(); + *ctx |= HAVE_SIMD_IN_USE; + return true; +} + #else /* ! CONFIG_KERNEL_MODE_NEON */ -static __must_check inline bool may_use_simd(void) { +static __must_check inline bool may_use_simd(void) +{ + return false; +} + +static inline void simd_get(simd_context_t *ctx) +{ + *ctx = HAVE_NO_SIMD; +} + +static inline void simd_put(simd_context_t *ctx) +{ +} + +static __must_check inline bool simd_use(simd_context_t *ctx) +{ return false; } diff --git a/arch/c6x/include/asm/Kbuild b/arch/c6x/include/asm/Kbuild index 33a2c94fed0d..22f3d8333c74 100644 --- a/arch/c6x/include/asm/Kbuild +++ b/arch/c6x/include/asm/Kbuild @@ -5,8 +5,8 @@ generic-y += compat.h generic-y += current.h generic-y += device.h generic-y += div64.h -generic-y += dma.h generic-y += dma-mapping.h +generic-y += dma.h generic-y += emergency-restart.h generic-y += exec.h generic-y += extable.h @@ -30,6 +30,7 @@ generic-y += pgalloc.h generic-y += preempt.h generic-y += segment.h generic-y += serial.h +generic-y += simd.h generic-y += tlbflush.h generic-y += topology.h generic-y += trace_clock.h diff --git a/arch/h8300/include/asm/Kbuild b/arch/h8300/include/asm/Kbuild index a5d0b2991f47..f5c2f12d593e 100644 --- a/arch/h8300/include/asm/Kbuild +++ b/arch/h8300/include/asm/Kbuild @@ -8,8 +8,8 @@ generic-y += current.h generic-y += delay.h generic-y += device.h generic-y += div64.h -generic-y += dma.h generic-y += dma-mapping.h +generic-y += dma.h generic-y += emergency-restart.h generic-y += exec.h generic-y += extable.h @@ -39,6 +39,7 @@ generic-y += preempt.h generic-y += scatterlist.h generic-y += sections.h generic-y += serial.h +generic-y += simd.h generic-y += sizes.h generic-y += spinlock.h generic-y += timex.h diff --git a/arch/hexagon/include/asm/Kbuild b/arch/hexagon/include/asm/Kbuild index dd2fd9c0d292..217d4695fd8a 100644 --- a/arch/hexagon/include/asm/Kbuild +++ b/arch/hexagon/include/asm/Kbuild @@ -29,6 +29,7 @@ generic-y += rwsem.h generic-y += sections.h generic-y += segment.h generic-y += serial.h +generic-y += simd.h generic-y += sizes.h generic-y += topology.h generic-y += trace_clock.h diff --git a/arch/ia64/include/asm/Kbuild b/arch/ia64/include/asm/Kbuild index 557bbc8ba9f5..41c5ebdf79e5 100644 --- a/arch/ia64/include/asm/Kbuild +++ b/arch/ia64/include/asm/Kbuild @@ -4,6 +4,7 @@ generic-y += irq_work.h generic-y += mcs_spinlock.h generic-y += mm-arch-hooks.h generic-y += preempt.h +generic-y += simd.h generic-y += trace_clock.h generic-y += vtime.h generic-y += word-at-a-time.h diff --git a/arch/m68k/include/asm/Kbuild b/arch/m68k/include/asm/Kbuild index a4b8d3331a9e..73898dd1a4d0 100644 --- a/arch/m68k/include/asm/Kbuild +++ b/arch/m68k/include/asm/Kbuild @@ -19,6 +19,7 @@ generic-y += mm-arch-hooks.h generic-y += percpu.h generic-y += preempt.h generic-y += sections.h +generic-y += simd.h generic-y += spinlock.h generic-y += topology.h generic-y += trace_clock.h diff --git a/arch/microblaze/include/asm/Kbuild b/arch/microblaze/include/asm/Kbuild index 569ba9e670c1..7a877eea99d3 100644 --- a/arch/microblaze/include/asm/Kbuild +++ b/arch/microblaze/include/asm/Kbuild @@ -25,6 +25,7 @@ generic-y += parport.h generic-y += percpu.h generic-y += preempt.h generic-y += serial.h +generic-y += simd.h generic-y += syscalls.h generic-y += topology.h generic-y += trace_clock.h diff --git a/arch/mips/include/asm/Kbuild b/arch/mips/include/asm/Kbuild index 58351e48421e..e8868e0fb2c3 100644 --- a/arch/mips/include/asm/Kbuild +++ b/arch/mips/include/asm/Kbuild @@ -16,6 +16,7 @@ generic-y += qrwlock.h generic-y += qspinlock.h generic-y += sections.h generic-y += segment.h +generic-y += simd.h generic-y += trace_clock.h generic-y += unaligned.h generic-y += user.h diff --git a/arch/nds32/include/asm/Kbuild b/arch/nds32/include/asm/Kbuild index dbc4e5422550..603c1d020620 100644 --- a/arch/nds32/include/asm/Kbuild +++ b/arch/nds32/include/asm/Kbuild @@ -7,14 +7,14 @@ generic-y += bug.h generic-y += bugs.h generic-y += checksum.h generic-y += clkdev.h -generic-y += cmpxchg.h generic-y += cmpxchg-local.h +generic-y += cmpxchg.h generic-y += compat.h generic-y += cputime.h generic-y += device.h generic-y += div64.h -generic-y += dma.h generic-y += dma-mapping.h +generic-y += dma.h generic-y += emergency-restart.h generic-y += errno.h generic-y += exec.h @@ -46,14 +46,15 @@ generic-y += sections.h generic-y += segment.h generic-y += serial.h generic-y += shmbuf.h +generic-y += simd.h generic-y += sizes.h generic-y += stat.h generic-y += switch_to.h generic-y += timex.h generic-y += topology.h generic-y += trace_clock.h -generic-y += xor.h generic-y += unaligned.h generic-y += user.h generic-y += vga.h generic-y += word-at-a-time.h +generic-y += xor.h diff --git a/arch/nios2/include/asm/Kbuild b/arch/nios2/include/asm/Kbuild index 8fde4fa2c34f..571a9d9ad107 100644 --- a/arch/nios2/include/asm/Kbuild +++ b/arch/nios2/include/asm/Kbuild @@ -33,6 +33,7 @@ generic-y += preempt.h generic-y += sections.h generic-y += segment.h generic-y += serial.h +generic-y += simd.h generic-y += spinlock.h generic-y += topology.h generic-y += trace_clock.h diff --git a/arch/openrisc/include/asm/Kbuild b/arch/openrisc/include/asm/Kbuild index eb87cd8327c8..5e9f2f4c4d39 100644 --- a/arch/openrisc/include/asm/Kbuild +++ b/arch/openrisc/include/asm/Kbuild @@ -28,12 +28,13 @@ generic-y += module.h generic-y += pci.h generic-y += percpu.h generic-y += preempt.h -generic-y += qspinlock_types.h -generic-y += qspinlock.h -generic-y += qrwlock_types.h generic-y += qrwlock.h +generic-y += qrwlock_types.h +generic-y += qspinlock.h +generic-y += qspinlock_types.h generic-y += sections.h generic-y += segment.h +generic-y += simd.h generic-y += string.h generic-y += switch_to.h generic-y += topology.h diff --git a/arch/parisc/include/asm/Kbuild b/arch/parisc/include/asm/Kbuild index 2013d639e735..97970b4d05ab 100644 --- a/arch/parisc/include/asm/Kbuild +++ b/arch/parisc/include/asm/Kbuild @@ -17,6 +17,7 @@ generic-y += percpu.h generic-y += preempt.h generic-y += seccomp.h generic-y += segment.h +generic-y += simd.h generic-y += topology.h generic-y += trace_clock.h generic-y += user.h diff --git a/arch/powerpc/include/asm/Kbuild b/arch/powerpc/include/asm/Kbuild index 3196d227e351..64290f48e733 100644 --- a/arch/powerpc/include/asm/Kbuild +++ b/arch/powerpc/include/asm/Kbuild @@ -4,7 +4,8 @@ generic-y += irq_regs.h generic-y += irq_work.h generic-y += local64.h generic-y += mcs_spinlock.h +generic-y += msi.h generic-y += preempt.h generic-y += rwsem.h +generic-y += simd.h generic-y += vtime.h -generic-y += msi.h diff --git a/arch/riscv/include/asm/Kbuild b/arch/riscv/include/asm/Kbuild index efdbe311e936..6669b7374c0a 100644 --- a/arch/riscv/include/asm/Kbuild +++ b/arch/riscv/include/asm/Kbuild @@ -5,9 +5,9 @@ generic-y += compat.h generic-y += cputime.h generic-y += device.h generic-y += div64.h -generic-y += dma.h generic-y += dma-contiguous.h generic-y += dma-mapping.h +generic-y += dma.h generic-y += emergency-restart.h generic-y += errno.h generic-y += exec.h @@ -46,6 +46,7 @@ generic-y += setup.h generic-y += shmbuf.h generic-y += shmparam.h generic-y += signal.h +generic-y += simd.h generic-y += socket.h generic-y += sockios.h generic-y += stat.h diff --git a/arch/s390/include/asm/Kbuild b/arch/s390/include/asm/Kbuild index e3239772887a..7a26dc6ce815 100644 --- a/arch/s390/include/asm/Kbuild +++ b/arch/s390/include/asm/Kbuild @@ -7,9 +7,9 @@ generated-y += unistd_nr.h generic-y += asm-offsets.h generic-y += cacheflush.h generic-y += device.h +generic-y += div64.h generic-y += dma-contiguous.h generic-y += dma-mapping.h -generic-y += div64.h generic-y += emergency-restart.h generic-y += export.h generic-y += fb.h @@ -22,6 +22,7 @@ generic-y += mcs_spinlock.h generic-y += mm-arch-hooks.h generic-y += preempt.h generic-y += rwsem.h +generic-y += simd.h generic-y += trace_clock.h generic-y += unaligned.h generic-y += word-at-a-time.h diff --git a/arch/sh/include/asm/Kbuild b/arch/sh/include/asm/Kbuild index 6a5609a55965..8e64ff35a933 100644 --- a/arch/sh/include/asm/Kbuild +++ b/arch/sh/include/asm/Kbuild @@ -16,6 +16,7 @@ generic-y += percpu.h generic-y += preempt.h generic-y += rwsem.h generic-y += serial.h +generic-y += simd.h generic-y += sizes.h generic-y += trace_clock.h generic-y += xor.h diff --git a/arch/sparc/include/asm/Kbuild b/arch/sparc/include/asm/Kbuild index 410b263ef5c8..72b9e08fb350 100644 --- a/arch/sparc/include/asm/Kbuild +++ b/arch/sparc/include/asm/Kbuild @@ -17,5 +17,6 @@ generic-y += msi.h generic-y += preempt.h generic-y += rwsem.h generic-y += serial.h +generic-y += simd.h generic-y += trace_clock.h generic-y += word-at-a-time.h diff --git a/arch/um/include/asm/Kbuild b/arch/um/include/asm/Kbuild index b10dde6cb793..d37288b08dd2 100644 --- a/arch/um/include/asm/Kbuild +++ b/arch/um/include/asm/Kbuild @@ -16,15 +16,16 @@ generic-y += io.h generic-y += irq_regs.h generic-y += irq_work.h generic-y += kdebug.h +generic-y += kprobes.h generic-y += mcs_spinlock.h generic-y += mm-arch-hooks.h generic-y += param.h generic-y += pci.h generic-y += percpu.h generic-y += preempt.h +generic-y += simd.h generic-y += switch_to.h generic-y += topology.h generic-y += trace_clock.h generic-y += word-at-a-time.h generic-y += xor.h -generic-y += kprobes.h diff --git a/arch/unicore32/include/asm/Kbuild b/arch/unicore32/include/asm/Kbuild index bfc7abe77905..98a908720bbd 100644 --- a/arch/unicore32/include/asm/Kbuild +++ b/arch/unicore32/include/asm/Kbuild @@ -27,6 +27,7 @@ generic-y += preempt.h generic-y += sections.h generic-y += segment.h generic-y += serial.h +generic-y += simd.h generic-y += sizes.h generic-y += syscalls.h generic-y += topology.h diff --git a/arch/x86/include/asm/simd.h b/arch/x86/include/asm/simd.h index a341c878e977..4aad7f158dcb 100644 --- a/arch/x86/include/asm/simd.h +++ b/arch/x86/include/asm/simd.h @@ -1,4 +1,11 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: GPL-2.0 + * + * Copyright (C) 2015-2018 Jason A. Donenfeld <Jason@xxxxxxxxx>. All Rights Reserved. + */ + +#include <linux/simd.h> +#ifndef _ASM_SIMD_H +#define _ASM_SIMD_H #include <asm/fpu/api.h> @@ -10,3 +17,38 @@ static __must_check inline bool may_use_simd(void) { return irq_fpu_usable(); } + +static inline void simd_get(simd_context_t *ctx) +{ +#if !defined(CONFIG_UML) + *ctx = may_use_simd() ? HAVE_FULL_SIMD : HAVE_NO_SIMD; +#else + *ctx = HAVE_NO_SIMD; +#endif +} + +static inline void simd_put(simd_context_t *ctx) +{ +#if !defined(CONFIG_UML) + if (*ctx & HAVE_SIMD_IN_USE) + kernel_fpu_end(); +#endif + *ctx = HAVE_NO_SIMD; +} + +static __must_check inline bool simd_use(simd_context_t *ctx) +{ +#if !defined(CONFIG_UML) + if (!(*ctx & HAVE_FULL_SIMD)) + return false; + if (*ctx & HAVE_SIMD_IN_USE) + return true; + kernel_fpu_begin(); + *ctx |= HAVE_SIMD_IN_USE; + return true; +#else + return false; +#endif +} + +#endif /* _ASM_SIMD_H */ diff --git a/arch/xtensa/include/asm/Kbuild b/arch/xtensa/include/asm/Kbuild index 82c756431b49..7950f359649d 100644 --- a/arch/xtensa/include/asm/Kbuild +++ b/arch/xtensa/include/asm/Kbuild @@ -24,6 +24,7 @@ generic-y += percpu.h generic-y += preempt.h generic-y += rwsem.h generic-y += sections.h +generic-y += simd.h generic-y += topology.h generic-y += trace_clock.h generic-y += word-at-a-time.h diff --git a/include/asm-generic/simd.h b/include/asm-generic/simd.h index d0343d58a74a..b3dd61ac010e 100644 --- a/include/asm-generic/simd.h +++ b/include/asm-generic/simd.h @@ -1,5 +1,9 @@ /* SPDX-License-Identifier: GPL-2.0 */ +#include <linux/simd.h> +#ifndef _ASM_SIMD_H +#define _ASM_SIMD_H + #include <linux/hardirq.h> /* @@ -13,3 +17,19 @@ static __must_check inline bool may_use_simd(void) { return !in_interrupt(); } + +static inline void simd_get(simd_context_t *ctx) +{ + *ctx = HAVE_NO_SIMD; +} + +static inline void simd_put(simd_context_t *ctx) +{ +} + +static __must_check inline bool simd_use(simd_context_t *ctx) +{ + return false; +} + +#endif /* _ASM_SIMD_H */ diff --git a/include/linux/simd.h b/include/linux/simd.h new file mode 100644 index 000000000000..33bba21012ff --- /dev/null +++ b/include/linux/simd.h @@ -0,0 +1,28 @@ +/* SPDX-License-Identifier: GPL-2.0 + * + * Copyright (C) 2015-2018 Jason A. Donenfeld <Jason@xxxxxxxxx>. All Rights Reserved. + */ + +#ifndef _SIMD_H +#define _SIMD_H + +typedef enum { + HAVE_NO_SIMD = 1 << 0, + HAVE_FULL_SIMD = 1 << 1, + HAVE_SIMD_IN_USE = 1 << 31 +} simd_context_t; + +#include <linux/sched.h> +#include <asm/simd.h> + +static inline void simd_relax(simd_context_t *ctx) +{ +#ifdef CONFIG_PREEMPT + if ((*ctx & HAVE_SIMD_IN_USE) && need_resched()) { + simd_put(ctx); + simd_get(ctx); + } +#endif +} + +#endif /* _SIMD_H */ -- 2.19.0