diff options
Diffstat (limited to 'arch')
| -rw-r--r-- | arch/arm/Kconfig | 7 | ||||
| -rw-r--r-- | arch/arm/include/asm/neon.h | 36 | ||||
| -rw-r--r-- | arch/arm/include/asm/xor.h | 73 | ||||
| -rw-r--r-- | arch/arm/lib/Makefile | 6 | ||||
| -rw-r--r-- | arch/arm/lib/xor-neon.c | 42 | ||||
| -rw-r--r-- | arch/arm/vfp/vfphw.S | 5 | ||||
| -rw-r--r-- | arch/arm/vfp/vfpmodule.c | 69 |
7 files changed, 237 insertions, 1 deletions
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index ba412e02ec0c..ccc388d388be 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -2176,6 +2176,13 @@ config NEON Say Y to include support code for NEON, the ARMv7 Advanced SIMD Extension. +config KERNEL_MODE_NEON + bool "Support for NEON in kernel mode" + default n + depends on NEON + help + Say Y to include support for NEON in kernel mode. + endmenu menu "Userspace binary formats" diff --git a/arch/arm/include/asm/neon.h b/arch/arm/include/asm/neon.h new file mode 100644 index 000000000000..8f730fe70093 --- /dev/null +++ b/arch/arm/include/asm/neon.h @@ -0,0 +1,36 @@ +/* + * linux/arch/arm/include/asm/neon.h + * + * Copyright (C) 2013 Linaro Ltd <ard.biesheuvel@linaro.org> + * + * 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. + */ + +#include <asm/hwcap.h> + +#define cpu_has_neon() (!!(elf_hwcap & HWCAP_NEON)) + +#ifdef __ARM_NEON__ + +/* + * If you are affected by the BUILD_BUG below, it probably means that you are + * using NEON code /and/ calling the kernel_neon_begin() function from the same + * compilation unit. To prevent issues that may arise from GCC reordering or + * generating(1) NEON instructions outside of these begin/end functions, the + * only supported way of using NEON code in the kernel is by isolating it in a + * separate compilation unit, and calling it from another unit from inside a + * kernel_neon_begin/kernel_neon_end pair. + * + * (1) Current GCC (4.7) might generate NEON instructions at O3 level if + * -mpfu=neon is set. + */ + +#define kernel_neon_begin() \ + BUILD_BUG_ON_MSG(1, "kernel_neon_begin() called from NEON code") + +#else +void kernel_neon_begin(void); +#endif +void kernel_neon_end(void); diff --git a/arch/arm/include/asm/xor.h b/arch/arm/include/asm/xor.h index 7604673dc427..4ffb26d4cad8 100644 --- a/arch/arm/include/asm/xor.h +++ b/arch/arm/include/asm/xor.h @@ -7,7 +7,10 @@ * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. */ +#include <linux/hardirq.h> #include <asm-generic/xor.h> +#include <asm/hwcap.h> +#include <asm/neon.h> #define __XOR(a1, a2) a1 ^= a2 @@ -138,4 +141,74 @@ static struct xor_block_template xor_block_arm4regs = { xor_speed(&xor_block_arm4regs); \ xor_speed(&xor_block_8regs); \ xor_speed(&xor_block_32regs); \ + NEON_TEMPLATES; \ } while (0) + +#ifdef CONFIG_KERNEL_MODE_NEON + +extern struct xor_block_template const xor_block_neon_inner; + +static void +xor_neon_2(unsigned long bytes, unsigned long *p1, unsigned long *p2) +{ + if (in_interrupt()) { + xor_arm4regs_2(bytes, p1, p2); + } else { + kernel_neon_begin(); + xor_block_neon_inner.do_2(bytes, p1, p2); + kernel_neon_end(); + } +} + +static void +xor_neon_3(unsigned long bytes, unsigned long *p1, unsigned long *p2, + unsigned long *p3) +{ + if (in_interrupt()) { + xor_arm4regs_3(bytes, p1, p2, p3); + } else { + kernel_neon_begin(); + xor_block_neon_inner.do_3(bytes, p1, p2, p3); + kernel_neon_end(); + } +} + +static void +xor_neon_4(unsigned long bytes, unsigned long *p1, unsigned long *p2, + unsigned long *p3, unsigned long *p4) +{ + if (in_interrupt()) { + xor_arm4regs_4(bytes, p1, p2, p3, p4); + } else { + kernel_neon_begin(); + xor_block_neon_inner.do_4(bytes, p1, p2, p3, p4); + kernel_neon_end(); + } +} + +static void +xor_neon_5(unsigned long bytes, unsigned long *p1, unsigned long *p2, + unsigned long *p3, unsigned long *p4, unsigned long *p5) +{ + if (in_interrupt()) { + xor_arm4regs_5(bytes, p1, p2, p3, p4, p5); + } else { + kernel_neon_begin(); + xor_block_neon_inner.do_5(bytes, p1, p2, p3, p4, p5); + kernel_neon_end(); + } +} + +static struct xor_block_template xor_block_neon = { + .name = "neon", + .do_2 = xor_neon_2, + .do_3 = xor_neon_3, + .do_4 = xor_neon_4, + .do_5 = xor_neon_5 +}; + +#define NEON_TEMPLATES \ + do { if (cpu_has_neon()) xor_speed(&xor_block_neon); } while (0) +#else +#define NEON_TEMPLATES +#endif diff --git a/arch/arm/lib/Makefile b/arch/arm/lib/Makefile index af72969820b4..aaf3a8731136 100644 --- a/arch/arm/lib/Makefile +++ b/arch/arm/lib/Makefile @@ -45,3 +45,9 @@ lib-$(CONFIG_ARCH_SHARK) += io-shark.o $(obj)/csumpartialcopy.o: $(obj)/csumpartialcopygeneric.S $(obj)/csumpartialcopyuser.o: $(obj)/csumpartialcopygeneric.S + +ifeq ($(CONFIG_KERNEL_MODE_NEON),y) + NEON_FLAGS := -mfloat-abi=softfp -mfpu=neon + CFLAGS_xor-neon.o += $(NEON_FLAGS) + lib-$(CONFIG_XOR_BLOCKS) += xor-neon.o +endif diff --git a/arch/arm/lib/xor-neon.c b/arch/arm/lib/xor-neon.c new file mode 100644 index 000000000000..f485e5a2af4b --- /dev/null +++ b/arch/arm/lib/xor-neon.c @@ -0,0 +1,42 @@ +/* + * linux/arch/arm/lib/xor-neon.c + * + * Copyright (C) 2013 Linaro Ltd <ard.biesheuvel@linaro.org> + * + * 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. + */ + +#include <linux/raid/xor.h> + +#ifndef __ARM_NEON__ +#error You should compile this file with '-mfloat-abi=softfp -mfpu=neon' +#endif + +/* + * Pull in the reference implementations while instructing GCC (through + * -ftree-vectorize) to attempt to exploit implicit parallelism and emit + * NEON instructions. + */ +#if __GNUC__ > 4 || (__GNUC__ == 4 && __GNUC_MINOR__ >= 6) +#pragma GCC optimize "tree-vectorize" +#else +/* + * While older versions of GCC do not generate incorrect code, they fail to + * recognize the parallel nature of these functions, and emit plain ARM code, + * which is known to be slower than the optimized ARM code in asm-arm/xor.h. + */ +#warning This code requires at least version 4.6 of GCC +#endif + +#pragma GCC diagnostic ignored "-Wunused-variable" +#include <asm-generic/xor.h> + +struct xor_block_template const xor_block_neon_inner = { + .name = "__inner_neon__", + .do_2 = xor_8regs_2, + .do_3 = xor_8regs_3, + .do_4 = xor_8regs_4, + .do_5 = xor_8regs_5, +}; diff --git a/arch/arm/vfp/vfphw.S b/arch/arm/vfp/vfphw.S index 8d10dc8a1e17..3e5d3115a2a6 100644 --- a/arch/arm/vfp/vfphw.S +++ b/arch/arm/vfp/vfphw.S @@ -78,6 +78,11 @@ ENTRY(vfp_support_entry) DBGSTR3 "instr %08x pc %08x state %p", r0, r2, r10 + ldr r3, [sp, #S_PSR] @ Neither lazy restore nor FP exceptions + and r3, r3, #MODE_MASK @ are supported in kernel mode + teq r3, #USR_MODE + bne vfp_kmode_exception @ Returns through lr + VFPFMRX r1, FPEXC @ Is the VFP enabled? DBGSTR1 "fpexc %08x", r1 tst r1, #FPEXC_EN diff --git a/arch/arm/vfp/vfpmodule.c b/arch/arm/vfp/vfpmodule.c index 5dfbb0b8e7f4..52b8f40b1c73 100644 --- a/arch/arm/vfp/vfpmodule.c +++ b/arch/arm/vfp/vfpmodule.c @@ -20,6 +20,7 @@ #include <linux/init.h> #include <linux/uaccess.h> #include <linux/user.h> +#include <linux/export.h> #include <asm/cp15.h> #include <asm/cputype.h> @@ -648,6 +649,72 @@ static int vfp_hotplug(struct notifier_block *b, unsigned long action, return NOTIFY_OK; } +void vfp_kmode_exception(void) +{ + /* + * If we reach this point, a floating point exception has been raised + * while running in kernel mode. If the NEON/VFP unit was enabled at the + * time, it means a VFP instruction has been issued that requires + * software assistance to complete, something which is not currently + * supported in kernel mode. + * If the NEON/VFP unit was disabled, and the location pointed to below + * is properly preceded by a call to kernel_neon_begin(), something has + * caused the task to be scheduled out and back in again. In this case, + * rebuilding and running with CONFIG_DEBUG_ATOMIC_SLEEP enabled should + * be helpful in localizing the problem. + */ + if (fmrx(FPEXC) & FPEXC_EN) + pr_crit("BUG: unsupported FP instruction in kernel mode\n"); + else + pr_crit("BUG: FP instruction issued in kernel mode with FP unit disabled\n"); +} + +#ifdef CONFIG_KERNEL_MODE_NEON + +/* + * Kernel-side NEON support functions + */ +void kernel_neon_begin(void) +{ + struct thread_info *thread = current_thread_info(); + unsigned int cpu; + u32 fpexc; + + /* + * Kernel mode NEON is only allowed outside of interrupt context + * with preemption disabled. This will make sure that the kernel + * mode NEON register contents never need to be preserved. + */ + BUG_ON(in_interrupt()); + cpu = get_cpu(); + + fpexc = fmrx(FPEXC) | FPEXC_EN; + fmxr(FPEXC, fpexc); + + /* + * Save the userland NEON/VFP state. Under UP, + * the owner could be a task other than 'current' + */ + if (vfp_state_in_hw(cpu, thread)) + vfp_save_state(&thread->vfpstate, fpexc); +#ifndef CONFIG_SMP + else if (vfp_current_hw_state[cpu] != NULL) + vfp_save_state(vfp_current_hw_state[cpu], fpexc); +#endif + vfp_current_hw_state[cpu] = NULL; +} +EXPORT_SYMBOL(kernel_neon_begin); + +void kernel_neon_end(void) +{ + /* Disable the NEON/VFP unit. */ + fmxr(FPEXC, fmrx(FPEXC) & ~FPEXC_EN); + put_cpu(); +} +EXPORT_SYMBOL(kernel_neon_end); + +#endif /* CONFIG_KERNEL_MODE_NEON */ + /* * VFP support code initialisation. */ @@ -731,4 +798,4 @@ static int __init vfp_init(void) return 0; } -late_initcall(vfp_init); +core_initcall(vfp_init); |