ARM: mvebu: implement Armada 375 coherency workaround

 * supplies basic routines for configuring and controlling hardware coherency

 */

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

#include <linux/kernel.h>

#include <linux/init.h>

#include <linux/of_address.h>

#include <linux/smp.h>

#include <linux/dma-mapping.h>

#include <linux/platform_device.h>

#include <linux/slab.h>

#include <linux/mbus.h>

#include <linux/clk.h>

#include <asm/smp_plat.h>

#include <asm/cacheflush.h>

#include "armada-370-xp.h"

	return ll_set_cpu_coherent(coherency_base, hw_cpu_id);

}

/*

 * 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;

}

static inline void mvebu_hwcc_sync_io_barrier(void)

{

	if (coherency_wa_enabled) {

		mvebu_hwcc_armada375_sync_io_barrier_wa();

		return;

	}

	writel(0x1, coherency_cpu_base + IO_SYNC_BARRIER_CTL_OFFSET);

	while (readl(coherency_cpu_base + IO_SYNC_BARRIER_CTL_OFFSET) & 0x1);

}

static int __init coherency_late_init(void)

{

	if (coherency_available())

	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);

	return 0;

}