coherency.c 10.3 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19
/*
 * Coherency fabric (Aurora) support for Armada 370 and XP platforms.
 *
 * Copyright (C) 2012 Marvell
 *
 * Yehuda Yitschak <yehuday@marvell.com>
 * Gregory Clement <gregory.clement@free-electrons.com>
 * Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
 *
 * This file is licensed under the terms of the GNU General Public
 * License version 2.  This program is licensed "as is" without any
 * warranty of any kind, whether express or implied.
 *
 * The Armada 370 and Armada XP SOCs have a coherency fabric which is
 * responsible for ensuring hardware coherency between all CPUs and between
 * CPUs and I/O masters. This file initializes the coherency fabric and
 * supplies basic routines for configuring and controlling hardware coherency
 */

20 21
#define pr_fmt(fmt) "mvebu-coherency: " fmt

22 23 24 25 26
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/of_address.h>
#include <linux/io.h>
#include <linux/smp.h>
27 28
#include <linux/dma-mapping.h>
#include <linux/platform_device.h>
29 30 31
#include <linux/slab.h>
#include <linux/mbus.h>
#include <linux/clk.h>
32
#include <asm/smp_plat.h>
33
#include <asm/cacheflush.h>
34
#include "armada-370-xp.h"
35
#include "coherency.h"
36

37
unsigned long coherency_phys_base;
38
static void __iomem *coherency_base;
39
static void __iomem *coherency_cpu_base;
40 41 42 43

/* Coherency fabric registers */
#define COHERENCY_FABRIC_CFG_OFFSET		   0x4

44 45
#define IO_SYNC_BARRIER_CTL_OFFSET		   0x0

46
enum {
47
	COHERENCY_FABRIC_TYPE_NONE,
48
	COHERENCY_FABRIC_TYPE_ARMADA_370_XP,
49
	COHERENCY_FABRIC_TYPE_ARMADA_375,
50
	COHERENCY_FABRIC_TYPE_ARMADA_380,
51 52
};

53
static struct of_device_id of_coherency_table[] = {
54 55
	{.compatible = "marvell,coherency-fabric",
	 .data = (void *) COHERENCY_FABRIC_TYPE_ARMADA_370_XP },
56 57
	{.compatible = "marvell,armada-375-coherency-fabric",
	 .data = (void *) COHERENCY_FABRIC_TYPE_ARMADA_375 },
58 59
	{.compatible = "marvell,armada-380-coherency-fabric",
	 .data = (void *) COHERENCY_FABRIC_TYPE_ARMADA_380 },
60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76
	{ /* end of list */ },
};

/* Function defined in coherency_ll.S */
int ll_set_cpu_coherent(void __iomem *base_addr, unsigned int hw_cpu_id);

int set_cpu_coherent(unsigned int hw_cpu_id, int smp_group_id)
{
	if (!coherency_base) {
		pr_warn("Can't make CPU %d cache coherent.\n", hw_cpu_id);
		pr_warn("Coherency fabric is not initialized\n");
		return 1;
	}

	return ll_set_cpu_coherent(coherency_base, hw_cpu_id);
}

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
/*
 * The below code implements the I/O coherency workaround on Armada
 * 375. This workaround consists in using the two channels of the
 * first XOR engine to trigger a XOR transaction that serves as the
 * I/O coherency barrier.
 */

static void __iomem *xor_base, *xor_high_base;
static dma_addr_t coherency_wa_buf_phys[CONFIG_NR_CPUS];
static void *coherency_wa_buf[CONFIG_NR_CPUS];
static bool coherency_wa_enabled;

#define XOR_CONFIG(chan)            (0x10 + (chan * 4))
#define XOR_ACTIVATION(chan)        (0x20 + (chan * 4))
#define WINDOW_BAR_ENABLE(chan)     (0x240 + ((chan) << 2))
#define WINDOW_BASE(w)              (0x250 + ((w) << 2))
#define WINDOW_SIZE(w)              (0x270 + ((w) << 2))
#define WINDOW_REMAP_HIGH(w)        (0x290 + ((w) << 2))
#define WINDOW_OVERRIDE_CTRL(chan)  (0x2A0 + ((chan) << 2))
#define XOR_DEST_POINTER(chan)      (0x2B0 + (chan * 4))
#define XOR_BLOCK_SIZE(chan)        (0x2C0 + (chan * 4))
#define XOR_INIT_VALUE_LOW           0x2E0
#define XOR_INIT_VALUE_HIGH          0x2E4

static inline void mvebu_hwcc_armada375_sync_io_barrier_wa(void)
{
	int idx = smp_processor_id();

	/* Write '1' to the first word of the buffer */
	writel(0x1, coherency_wa_buf[idx]);

	/* Wait until the engine is idle */
	while ((readl(xor_base + XOR_ACTIVATION(idx)) >> 4) & 0x3)
		;

	dmb();

	/* Trigger channel */
	writel(0x1, xor_base + XOR_ACTIVATION(idx));

	/* Poll the data until it is cleared by the XOR transaction */
	while (readl(coherency_wa_buf[idx]))
		;
}

static void __init armada_375_coherency_init_wa(void)
{
	const struct mbus_dram_target_info *dram;
	struct device_node *xor_node;
	struct property *xor_status;
	struct clk *xor_clk;
	u32 win_enable = 0;
	int i;

	pr_warn("enabling coherency workaround for Armada 375 Z1, one XOR engine disabled\n");

	/*
	 * Since the workaround uses one XOR engine, we grab a
	 * reference to its Device Tree node first.
	 */
	xor_node = of_find_compatible_node(NULL, NULL, "marvell,orion-xor");
	BUG_ON(!xor_node);

	/*
	 * Then we mark it as disabled so that the real XOR driver
	 * will not use it.
	 */
	xor_status = kzalloc(sizeof(struct property), GFP_KERNEL);
	BUG_ON(!xor_status);

	xor_status->value = kstrdup("disabled", GFP_KERNEL);
	BUG_ON(!xor_status->value);

	xor_status->length = 8;
	xor_status->name = kstrdup("status", GFP_KERNEL);
	BUG_ON(!xor_status->name);

	of_update_property(xor_node, xor_status);

	/*
	 * And we remap the registers, get the clock, and do the
	 * initial configuration of the XOR engine.
	 */
	xor_base = of_iomap(xor_node, 0);
	xor_high_base = of_iomap(xor_node, 1);

	xor_clk = of_clk_get_by_name(xor_node, NULL);
	BUG_ON(!xor_clk);

	clk_prepare_enable(xor_clk);

	dram = mv_mbus_dram_info();

	for (i = 0; i < 8; i++) {
		writel(0, xor_base + WINDOW_BASE(i));
		writel(0, xor_base + WINDOW_SIZE(i));
		if (i < 4)
			writel(0, xor_base + WINDOW_REMAP_HIGH(i));
	}

	for (i = 0; i < dram->num_cs; i++) {
		const struct mbus_dram_window *cs = dram->cs + i;
		writel((cs->base & 0xffff0000) |
		       (cs->mbus_attr << 8) |
		       dram->mbus_dram_target_id, xor_base + WINDOW_BASE(i));
		writel((cs->size - 1) & 0xffff0000, xor_base + WINDOW_SIZE(i));

		win_enable |= (1 << i);
		win_enable |= 3 << (16 + (2 * i));
	}

	writel(win_enable, xor_base + WINDOW_BAR_ENABLE(0));
	writel(win_enable, xor_base + WINDOW_BAR_ENABLE(1));
	writel(0, xor_base + WINDOW_OVERRIDE_CTRL(0));
	writel(0, xor_base + WINDOW_OVERRIDE_CTRL(1));

	for (i = 0; i < CONFIG_NR_CPUS; i++) {
		coherency_wa_buf[i] = kzalloc(PAGE_SIZE, GFP_KERNEL);
		BUG_ON(!coherency_wa_buf[i]);

		/*
		 * We can't use the DMA mapping API, since we don't
		 * have a valid 'struct device' pointer
		 */
		coherency_wa_buf_phys[i] =
			virt_to_phys(coherency_wa_buf[i]);
		BUG_ON(!coherency_wa_buf_phys[i]);

		/*
		 * Configure the XOR engine for memset operation, with
		 * a 128 bytes block size
		 */
		writel(0x444, xor_base + XOR_CONFIG(i));
		writel(128, xor_base + XOR_BLOCK_SIZE(i));
		writel(coherency_wa_buf_phys[i],
		       xor_base + XOR_DEST_POINTER(i));
	}

	writel(0x0, xor_base + XOR_INIT_VALUE_LOW);
	writel(0x0, xor_base + XOR_INIT_VALUE_HIGH);

	coherency_wa_enabled = true;
}

221 222
static inline void mvebu_hwcc_sync_io_barrier(void)
{
223 224 225 226 227
	if (coherency_wa_enabled) {
		mvebu_hwcc_armada375_sync_io_barrier_wa();
		return;
	}

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
	writel(0x1, coherency_cpu_base + IO_SYNC_BARRIER_CTL_OFFSET);
	while (readl(coherency_cpu_base + IO_SYNC_BARRIER_CTL_OFFSET) & 0x1);
}

static dma_addr_t mvebu_hwcc_dma_map_page(struct device *dev, struct page *page,
				  unsigned long offset, size_t size,
				  enum dma_data_direction dir,
				  struct dma_attrs *attrs)
{
	if (dir != DMA_TO_DEVICE)
		mvebu_hwcc_sync_io_barrier();
	return pfn_to_dma(dev, page_to_pfn(page)) + offset;
}


static void mvebu_hwcc_dma_unmap_page(struct device *dev, dma_addr_t dma_handle,
			      size_t size, enum dma_data_direction dir,
			      struct dma_attrs *attrs)
{
	if (dir != DMA_TO_DEVICE)
		mvebu_hwcc_sync_io_barrier();
}

static void mvebu_hwcc_dma_sync(struct device *dev, dma_addr_t dma_handle,
			size_t size, enum dma_data_direction dir)
{
	if (dir != DMA_TO_DEVICE)
		mvebu_hwcc_sync_io_barrier();
}

static struct dma_map_ops mvebu_hwcc_dma_ops = {
	.alloc			= arm_dma_alloc,
	.free			= arm_dma_free,
	.mmap			= arm_dma_mmap,
	.map_page		= mvebu_hwcc_dma_map_page,
	.unmap_page		= mvebu_hwcc_dma_unmap_page,
	.get_sgtable		= arm_dma_get_sgtable,
	.map_sg			= arm_dma_map_sg,
	.unmap_sg		= arm_dma_unmap_sg,
	.sync_single_for_cpu	= mvebu_hwcc_dma_sync,
	.sync_single_for_device	= mvebu_hwcc_dma_sync,
	.sync_sg_for_cpu	= arm_dma_sync_sg_for_cpu,
	.sync_sg_for_device	= arm_dma_sync_sg_for_device,
	.set_dma_mask		= arm_dma_set_mask,
};

static int mvebu_hwcc_platform_notifier(struct notifier_block *nb,
				       unsigned long event, void *__dev)
{
	struct device *dev = __dev;

	if (event != BUS_NOTIFY_ADD_DEVICE)
		return NOTIFY_DONE;
	set_dma_ops(dev, &mvebu_hwcc_dma_ops);

	return NOTIFY_OK;
}

static struct notifier_block mvebu_hwcc_platform_nb = {
	.notifier_call = mvebu_hwcc_platform_notifier,
};

290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307
static void __init armada_370_coherency_init(struct device_node *np)
{
	struct resource res;

	of_address_to_resource(np, 0, &res);
	coherency_phys_base = res.start;
	/*
	 * Ensure secondary CPUs will see the updated value,
	 * which they read before they join the coherency
	 * fabric, and therefore before they are coherent with
	 * the boot CPU cache.
	 */
	sync_cache_w(&coherency_phys_base);
	coherency_base = of_iomap(np, 0);
	coherency_cpu_base = of_iomap(np, 1);
	set_cpu_coherent(cpu_logical_map(smp_processor_id()), 0);
}

308
static void __init armada_375_380_coherency_init(struct device_node *np)
309 310 311 312
{
	coherency_cpu_base = of_iomap(np, 0);
}

313
static int coherency_type(void)
314 315
{
	struct device_node *np;
316
	const struct of_device_id *match;
317

318
	np = of_find_matching_node_and_match(NULL, of_coherency_table, &match);
319
	if (np) {
320
		int type = (int) match->data;
321

322
		/* Armada 370/XP coherency works in both UP and SMP */
323
		if (type == COHERENCY_FABRIC_TYPE_ARMADA_370_XP)
324
			return type;
325

326 327 328 329
		/* Armada 375 coherency works only on SMP */
		else if (type == COHERENCY_FABRIC_TYPE_ARMADA_375 && is_smp())
			return type;

330 331 332 333
		/* Armada 380 coherency works only on SMP */
		else if (type == COHERENCY_FABRIC_TYPE_ARMADA_380 && is_smp())
			return type;

334
		of_node_put(np);
335 336
	}

337
	return COHERENCY_FABRIC_TYPE_NONE;
338
}
339

340
int coherency_available(void)
341
{
342 343 344 345 346 347
	return coherency_type() != COHERENCY_FABRIC_TYPE_NONE;
}

int __init coherency_init(void)
{
	int type = coherency_type();
348 349 350
	struct device_node *np;

	np = of_find_matching_node(NULL, of_coherency_table);
351 352 353

	if (type == COHERENCY_FABRIC_TYPE_ARMADA_370_XP)
		armada_370_coherency_init(np);
354 355 356
	else if (type == COHERENCY_FABRIC_TYPE_ARMADA_375 ||
		 type == COHERENCY_FABRIC_TYPE_ARMADA_380)
		armada_375_380_coherency_init(np);
357 358 359 360 361 362

	return 0;
}

static int __init coherency_late_init(void)
{
363 364 365 366 367 368 369 370 371 372 373
	int type = coherency_type();

	if (type == COHERENCY_FABRIC_TYPE_NONE)
		return 0;

	if (type == COHERENCY_FABRIC_TYPE_ARMADA_375)
		armada_375_coherency_init_wa();

	bus_register_notifier(&platform_bus_type,
			      &mvebu_hwcc_platform_nb);

374 375 376 377
	return 0;
}

postcore_initcall(coherency_late_init);