summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/drm_cache.c
blob: 30cc59fe6ef79a8eff16c2630104f0523d52b20e (plain)
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
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
/**************************************************************************
 *
 * Copyright (c) 2006-2007 Tungsten Graphics, Inc., Cedar Park, TX., USA
 * All Rights Reserved.
 *
 * 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, sub license, 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 NON-INFRINGEMENT. IN NO EVENT SHALL
 * THE COPYRIGHT HOLDERS, AUTHORS AND/OR ITS SUPPLIERS 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.
 *
 **************************************************************************/
/*
 * Authors: Thomas Hellström <thomas-at-tungstengraphics-dot-com>
 */

#include <linux/dma-buf-map.h>
#include <linux/export.h>
#include <linux/highmem.h>
#include <linux/mem_encrypt.h>
#include <xen/xen.h>

#include <drm/drm_cache.h>

/* A small bounce buffer that fits on the stack. */
#define MEMCPY_BOUNCE_SIZE 128

#if defined(CONFIG_X86)
#include <asm/smp.h>

/*
 * clflushopt is an unordered instruction which needs fencing with mfence or
 * sfence to avoid ordering issues.  For drm_clflush_page this fencing happens
 * in the caller.
 */
static void
drm_clflush_page(struct page *page)
{
	uint8_t *page_virtual;
	unsigned int i;
	const int size = boot_cpu_data.x86_clflush_size;

	if (unlikely(page == NULL))
		return;

	page_virtual = kmap_atomic(page);
	for (i = 0; i < PAGE_SIZE; i += size)
		clflushopt(page_virtual + i);
	kunmap_atomic(page_virtual);
}

static void drm_cache_flush_clflush(struct page *pages[],
				    unsigned long num_pages)
{
	unsigned long i;

	mb(); /*Full memory barrier used before so that CLFLUSH is ordered*/
	for (i = 0; i < num_pages; i++)
		drm_clflush_page(*pages++);
	mb(); /*Also used after CLFLUSH so that all cache is flushed*/
}
#endif

/**
 * drm_clflush_pages - Flush dcache lines of a set of pages.
 * @pages: List of pages to be flushed.
 * @num_pages: Number of pages in the array.
 *
 * Flush every data cache line entry that points to an address belonging
 * to a page in the array.
 */
void
drm_clflush_pages(struct page *pages[], unsigned long num_pages)
{

#if defined(CONFIG_X86)
	if (static_cpu_has(X86_FEATURE_CLFLUSH)) {
		drm_cache_flush_clflush(pages, num_pages);
		return;
	}

	if (wbinvd_on_all_cpus())
		pr_err("Timed out waiting for cache flush\n");

#elif defined(__powerpc__)
	unsigned long i;

	for (i = 0; i < num_pages; i++) {
		struct page *page = pages[i];
		void *page_virtual;

		if (unlikely(page == NULL))
			continue;

		page_virtual = kmap_atomic(page);
		flush_dcache_range((unsigned long)page_virtual,
				   (unsigned long)page_virtual + PAGE_SIZE);
		kunmap_atomic(page_virtual);
	}
#else
	pr_err("Architecture has no drm_cache.c support\n");
	WARN_ON_ONCE(1);
#endif
}
EXPORT_SYMBOL(drm_clflush_pages);

/**
 * drm_clflush_sg - Flush dcache lines pointing to a scather-gather.
 * @st: struct sg_table.
 *
 * Flush every data cache line entry that points to an address in the
 * sg.
 */
void
drm_clflush_sg(struct sg_table *st)
{
#if defined(CONFIG_X86)
	if (static_cpu_has(X86_FEATURE_CLFLUSH)) {
		struct sg_page_iter sg_iter;

		mb(); /*CLFLUSH is ordered only by using memory barriers*/
		for_each_sgtable_page(st, &sg_iter, 0)
			drm_clflush_page(sg_page_iter_page(&sg_iter));
		mb(); /*Make sure that all cache line entry is flushed*/

		return;
	}

	if (wbinvd_on_all_cpus())
		pr_err("Timed out waiting for cache flush\n");
#else
	pr_err("Architecture has no drm_cache.c support\n");
	WARN_ON_ONCE(1);
#endif
}
EXPORT_SYMBOL(drm_clflush_sg);

/**
 * drm_clflush_virt_range - Flush dcache lines of a region
 * @addr: Initial kernel memory address.
 * @length: Region size.
 *
 * Flush every data cache line entry that points to an address in the
 * region requested.
 */
void
drm_clflush_virt_range(void *addr, unsigned long length)
{
#if defined(CONFIG_X86)
	if (static_cpu_has(X86_FEATURE_CLFLUSH)) {
		const int size = boot_cpu_data.x86_clflush_size;
		void *end = addr + length;

		addr = (void *)(((unsigned long)addr) & -size);
		mb(); /*CLFLUSH is only ordered with a full memory barrier*/
		for (; addr < end; addr += size)
			clflushopt(addr);
		clflushopt(end - 1); /* force serialisation */
		mb(); /*Ensure that every data cache line entry is flushed*/
		return;
	}

	if (wbinvd_on_all_cpus())
		pr_err("Timed out waiting for cache flush\n");
#else
	pr_err("Architecture has no drm_cache.c support\n");
	WARN_ON_ONCE(1);
#endif
}
EXPORT_SYMBOL(drm_clflush_virt_range);

bool drm_need_swiotlb(int dma_bits)
{
	struct resource *tmp;
	resource_size_t max_iomem = 0;

	/*
	 * Xen paravirtual hosts require swiotlb regardless of requested dma
	 * transfer size.
	 *
	 * NOTE: Really, what it requires is use of the dma_alloc_coherent
	 *       allocator used in ttm_dma_populate() instead of
	 *       ttm_populate_and_map_pages(), which bounce buffers so much in
	 *       Xen it leads to swiotlb buffer exhaustion.
	 */
	if (xen_pv_domain())
		return true;

	/*
	 * Enforce dma_alloc_coherent when memory encryption is active as well
	 * for the same reasons as for Xen paravirtual hosts.
	 */
	if (mem_encrypt_active())
		return true;

	for (tmp = iomem_resource.child; tmp; tmp = tmp->sibling)
		max_iomem = max(max_iomem,  tmp->end);

	return max_iomem > ((u64)1 << dma_bits);
}
EXPORT_SYMBOL(drm_need_swiotlb);

static void memcpy_fallback(struct dma_buf_map *dst,
			    const struct dma_buf_map *src,
			    unsigned long len)
{
	if (!dst->is_iomem && !src->is_iomem) {
		memcpy(dst->vaddr, src->vaddr, len);
	} else if (!src->is_iomem) {
		dma_buf_map_memcpy_to(dst, src->vaddr, len);
	} else if (!dst->is_iomem) {
		memcpy_fromio(dst->vaddr, src->vaddr_iomem, len);
	} else {
		/*
		 * Bounce size is not performance tuned, but using a
		 * bounce buffer like this is significantly faster than
		 * resorting to ioreadxx() + iowritexx().
		 */
		char bounce[MEMCPY_BOUNCE_SIZE];
		void __iomem *_src = src->vaddr_iomem;
		void __iomem *_dst = dst->vaddr_iomem;

		while (len >= MEMCPY_BOUNCE_SIZE) {
			memcpy_fromio(bounce, _src, MEMCPY_BOUNCE_SIZE);
			memcpy_toio(_dst, bounce, MEMCPY_BOUNCE_SIZE);
			_src += MEMCPY_BOUNCE_SIZE;
			_dst += MEMCPY_BOUNCE_SIZE;
			len -= MEMCPY_BOUNCE_SIZE;
		}
		if (len) {
			memcpy_fromio(bounce, _src, MEMCPY_BOUNCE_SIZE);
			memcpy_toio(_dst, bounce, MEMCPY_BOUNCE_SIZE);
		}
	}
}

#ifdef CONFIG_X86

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();
}

/*
 * __drm_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.
 */
static void __drm_memcpy_from_wc(void *dst, const void *src, unsigned long len)
{
	if (unlikely(((unsigned long)dst | (unsigned long)src | len) & 15))
		memcpy(dst, src, len);
	else if (likely(len))
		__memcpy_ntdqa(dst, src, len >> 4);
}

/**
 * drm_memcpy_from_wc - Perform the fastest available memcpy from a source
 * that may be WC.
 * @dst: The destination pointer
 * @src: The source pointer
 * @len: The size of the area o transfer in bytes
 *
 * Tries an arch optimized memcpy for prefetching reading out of a WC region,
 * and if no such beast is available, falls back to a normal memcpy.
 */
void drm_memcpy_from_wc(struct dma_buf_map *dst,
			const struct dma_buf_map *src,
			unsigned long len)
{
	if (WARN_ON(in_interrupt())) {
		memcpy_fallback(dst, src, len);
		return;
	}

	if (static_branch_likely(&has_movntdqa)) {
		__drm_memcpy_from_wc(dst->is_iomem ?
				     (void __force *)dst->vaddr_iomem :
				     dst->vaddr,
				     src->is_iomem ?
				     (void const __force *)src->vaddr_iomem :
				     src->vaddr,
				     len);
		return;
	}

	memcpy_fallback(dst, src, len);
}
EXPORT_SYMBOL(drm_memcpy_from_wc);

/*
 * drm_memcpy_init_early - One time initialization of the WC memcpy code
 */
void drm_memcpy_init_early(void)
{
	/*
	 * 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);
}
#else
void drm_memcpy_from_wc(struct dma_buf_map *dst,
			const struct dma_buf_map *src,
			unsigned long len)
{
	WARN_ON(in_interrupt());

	memcpy_fallback(dst, src, len);
}
EXPORT_SYMBOL(drm_memcpy_from_wc);

void drm_memcpy_init_early(void)
{
}
#endif /* CONFIG_X86 */