Loading...
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 | /* * Copyright © 2016 Intel Corporation * * Permission is hereby granted, free of charge, to any person obtaining a * copy of this software and associated documentation files (the "Software"), * to deal in the Software without restriction, including without limitation * the rights to use, copy, modify, merge, publish, distribute, sublicense, * and/or sell copies of the Software, and to permit persons to whom the * Software is furnished to do so, subject to the following conditions: * * The above copyright notice and this permission notice (including the next * paragraph) shall be included in all copies or substantial portions of the * Software. * * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS * IN THE SOFTWARE. * */ #include <linux/kernel.h> #include <linux/string.h> #include <linux/cpufeature.h> #include <linux/bug.h> #include <linux/build_bug.h> #include <asm/fpu/api.h> #include "i915_memcpy.h" #if IS_ENABLED(CONFIG_DRM_I915_DEBUG) #define CI_BUG_ON(expr) BUG_ON(expr) #else #define CI_BUG_ON(expr) BUILD_BUG_ON_INVALID(expr) #endif static DEFINE_STATIC_KEY_FALSE(has_movntdqa); static void __memcpy_ntdqa(void *dst, const void *src, unsigned long len) { kernel_fpu_begin(); while (len >= 4) { asm("movntdqa (%0), %%xmm0\n" "movntdqa 16(%0), %%xmm1\n" "movntdqa 32(%0), %%xmm2\n" "movntdqa 48(%0), %%xmm3\n" "movaps %%xmm0, (%1)\n" "movaps %%xmm1, 16(%1)\n" "movaps %%xmm2, 32(%1)\n" "movaps %%xmm3, 48(%1)\n" :: "r" (src), "r" (dst) : "memory"); src += 64; dst += 64; len -= 4; } while (len--) { asm("movntdqa (%0), %%xmm0\n" "movaps %%xmm0, (%1)\n" :: "r" (src), "r" (dst) : "memory"); src += 16; dst += 16; } kernel_fpu_end(); } static void __memcpy_ntdqu(void *dst, const void *src, unsigned long len) { kernel_fpu_begin(); while (len >= 4) { asm("movntdqa (%0), %%xmm0\n" "movntdqa 16(%0), %%xmm1\n" "movntdqa 32(%0), %%xmm2\n" "movntdqa 48(%0), %%xmm3\n" "movups %%xmm0, (%1)\n" "movups %%xmm1, 16(%1)\n" "movups %%xmm2, 32(%1)\n" "movups %%xmm3, 48(%1)\n" :: "r" (src), "r" (dst) : "memory"); src += 64; dst += 64; len -= 4; } while (len--) { asm("movntdqa (%0), %%xmm0\n" "movups %%xmm0, (%1)\n" :: "r" (src), "r" (dst) : "memory"); src += 16; dst += 16; } kernel_fpu_end(); } /** * i915_memcpy_from_wc: perform an accelerated *aligned* read from WC * @dst: destination pointer * @src: source pointer * @len: how many bytes to copy * * i915_memcpy_from_wc copies @len bytes from @src to @dst using * non-temporal instructions where available. Note that all arguments * (@src, @dst) must be aligned to 16 bytes and @len must be a multiple * of 16. * * To test whether accelerated reads from WC are supported, use * i915_memcpy_from_wc(NULL, NULL, 0); * * Returns true if the copy was successful, false if the preconditions * are not met. */ bool i915_memcpy_from_wc(void *dst, const void *src, unsigned long len) { if (unlikely(((unsigned long)dst | (unsigned long)src | len) & 15)) return false; if (static_branch_likely(&has_movntdqa)) { if (likely(len)) __memcpy_ntdqa(dst, src, len >> 4); return true; } return false; } /** * i915_unaligned_memcpy_from_wc: perform a mostly accelerated read from WC * @dst: destination pointer * @src: source pointer * @len: how many bytes to copy * * Like i915_memcpy_from_wc(), the unaligned variant copies @len bytes from * @src to @dst using * non-temporal instructions where available, but * accepts that its arguments may not be aligned, but are valid for the * potential 16-byte read past the end. */ void i915_unaligned_memcpy_from_wc(void *dst, const void *src, unsigned long len) { unsigned long addr; CI_BUG_ON(!i915_has_memcpy_from_wc()); addr = (unsigned long)src; if (!IS_ALIGNED(addr, 16)) { unsigned long x = min(ALIGN(addr, 16) - addr, len); memcpy(dst, src, x); len -= x; dst += x; src += x; } if (likely(len)) __memcpy_ntdqu(dst, src, DIV_ROUND_UP(len, 16)); } void i915_memcpy_init_early(struct drm_i915_private *dev_priv) { /* * Some hypervisors (e.g. KVM) don't support VEX-prefix instructions * emulation. So don't enable movntdqa in hypervisor guest. */ if (static_cpu_has(X86_FEATURE_XMM4_1) && !boot_cpu_has(X86_FEATURE_HYPERVISOR)) static_branch_enable(&has_movntdqa); } |