[RFC] Add support for Aurora L2 Cache Controller

@@ -39,7 +39,7 @@ struct l2x0_regs l2x0_saved_regs;
 struct l2x0_of_data {
 	void (*setup)(const struct device_node *, u32 *, u32 *);
 	void (*save)(void);
-	void (*resume)(void);
+	struct outer_cache_fns outer_cache;
 };
 
 static inline void cache_wait_way(void __iomem *reg, unsigned long mask)

@@ -376,6 +376,7 @@ void __init l2x0_init(void __iomem *base, u32 aux_val, u32 aux_mask)
 		writel_relaxed(1, l2x0_base + L2X0_CTRL);
 	}
 
+#ifndef CONFIG_OF
 	outer_cache.inv_range = l2x0_inv_range;
 	outer_cache.clean_range = l2x0_clean_range;
 	outer_cache.flush_range = l2x0_flush_range;

@@ -383,6 +384,7 @@ void __init l2x0_init(void __iomem *base, u32 aux_val, u32 aux_mask)
 	outer_cache.flush_all = l2x0_flush_all;
 	outer_cache.inv_all = l2x0_inv_all;
 	outer_cache.disable = l2x0_disable;
+#endif
 
 	printk(KERN_INFO "%s cache controller enabled\n", type);
 	printk(KERN_INFO "l2x0: %d ways, CACHE_ID 0x%08x, AUX_CTRL 0x%08x, Cache size: %d B\n",

@@ -533,15 +535,34 @@ static void pl310_resume(void)
 }
 
 static const struct l2x0_of_data pl310_data = {
-	pl310_of_setup,
-	pl310_save,
-	pl310_resume,
+	.setup = pl310_of_setup,
+	.save  = pl310_save,
+	.outer_cache = {
+		.resume      = pl310_resume,
+		.inv_range   = l2x0_inv_range,
+		.clean_range = l2x0_clean_range,
+		.flush_range = l2x0_flush_range,
+		.sync        = l2x0_cache_sync,
+		.flush_all   = l2x0_flush_all,
+		.inv_all     = l2x0_inv_all,
+		.disable     = l2x0_disable,
+		.set_debug   = pl310_set_debug,
+	},
 };
 
 static const struct l2x0_of_data l2x0_data = {
-	l2x0_of_setup,
-	NULL,
-	l2x0_resume,
+	.setup = l2x0_of_setup,
+	.save  = NULL,
+	.outer_cache = {
+		.resume      = l2x0_resume,
+		.inv_range   = l2x0_inv_range,
+		.clean_range = l2x0_clean_range,
+		.flush_range = l2x0_flush_range,
+		.sync        = l2x0_cache_sync,
+		.flush_all   = l2x0_flush_all,
+		.inv_all     = l2x0_inv_all,
+		.disable     = l2x0_disable,
+	},
 };
 
 static const struct of_device_id l2x0_ids[] __initconst = {

@@ -583,7 +604,8 @@ int __init l2x0_of_init(u32 aux_val, u32 aux_mask)
 
 	l2x0_init(l2x0_base, aux_val, aux_mask);
 
-	outer_cache.resume = data->resume;
+	memcpy(&outer_cache, &data->outer_cache, sizeof(outer_cache));
+
 	return 0;
 }
 #endif

@@ -126,6 +126,7 @@ struct l2x0_regs {
 	unsigned long filter_end;
 	unsigned long prefetch_ctrl;
 	unsigned long pwr_ctrl;
+	unsigned long ctrl;
 };
 
 extern struct l2x0_regs l2x0_saved_regs;

@@ -20,6 +20,12 @@
 / {
 	model = "Marvell Armada 370 family SoC";
 	compatible = "marvell,armada370", "marvell,armada-370-xp";
+	L2: l2-cache {
+		compatible = "marvell,aurora-cache-with-outer";
+		reg = <0xd0008000 0x1000>;
+		cache-id-part = <0x100>;
+		wt-override;
+	};
 
 	mpic: interrupt-controller at d0020000 {
 	      reg = <0xd0020a00 0x1d0>,

@@ -22,6 +22,13 @@
 	model = "Marvell Armada XP family SoC";
 	compatible = "marvell,armadaxp", "marvell,armada-370-xp";
 
+	L2: l2-cache {
+		compatible = "marvell,aurora-cache-no-outer";
+		reg = <0xd0008000 0x1000>;
+		cache-id-part = <0x100>;
+		wt-override;
+	};
+
 	mpic: interrupt-controller at d0020000 {
 	      reg = <0xd0020a00 0x1d0>,
 		    <0xd0021870 0x58>;

@@ -6,6 +6,7 @@ config MACH_ARMADA_370_XP
 	bool "Marvell Armada 370 and Aramada XP boards"
 	select ARMADA_370_XP_TIMER
 	select CPU_V7
+	select CACHE_L2X0
 	help
 
 	  Say 'Y' here if you want your kernel to support boards based on

@@ -24,6 +24,7 @@
 #include <linux/irqdomain.h>
 #include <asm/mach/arch.h>
 #include <asm/exception.h>
+#include <asm/hardware/cache-l2x0.h>
 
 /* Interrupt Controller Registers Map */
 #define ARMADA_370_XP_INT_SET_MASK_OFFS		(0x48)

@@ -130,4 +131,7 @@ static const struct of_device_id mpic_of_match[] __initconst = {
 void __init armada_370_xp_init_irq(void)
 {
 	of_irq_init(mpic_of_match);
+#ifdef CONFIG_CACHE_L2X0
+	l2x0_of_init(0, ~0UL);
+#endif
 }

@@ -10,6 +10,12 @@ Required properties:
 	"arm,pl310-cache"
 	"arm,l220-cache"
 	"arm,l210-cache"
+	"marvell,aurora-cache-no-outer": Marvell Controller designed to be
+     compatible with the ARM one, with system cache mode (meaning
+     maintenance operations on L1 are broadcasted to the L2 and L2
+     performs the same operation).
+	"marvell,aurora-cache-with-outer": Marvell Controller designed to
+	be compatible with the ARM one with outer cache mode.
 - cache-unified : Specifies the cache is a unified cache.
 - cache-level : Should be set to 2 for a level 2 cache.
 - reg : Physical base address and size of cache controller's memory mapped

@@ -29,6 +35,9 @@ Optional properties:
   filter. Addresses in the filter window are directed to the M1 port. Other
   addresses will go to the M0 port.
 - interrupts : 1 combined interrupt.
+- cache-id-part: cache id part number to be used if it is not present
+  on hardware
+- wt-override: If present then L2 is forced to Write through mode
 
 Example:
 

@@ -0,0 +1,51 @@
+/*
+ * AURORA shared L2 cache controller support
+ *
+ * Copyright (C) 2012 Marvell
+ *
+ * Yehuda Yitschak <yehuday@marvell.com>
+ * Gregory CLEMENT <gregory.clement@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.
+ */
+
+#ifndef __ASM_ARM_HARDWARE_AURORA_L2_H
+#define __ASM_ARM_HARDWARE_AURORA_L2_H
+
+#define AURORA_SYNC_REG		    0x700
+#define AURORA_RANGE_BASE_ADDR_REG  0x720
+#define AURORA_FLUSH_PHY_ADDR_REG   0x7f0
+#define AURORA_INVAL_RANGE_REG	    0x774
+#define AURORA_CLEAN_RANGE_REG	    0x7b4
+#define AURORA_FLUSH_RANGE_REG	    0x7f4
+
+#define AURORA_ACR_REPLACEMENT_OFFSET	    27
+#define AURORA_ACR_REPLACEMENT_MASK	     \
+	(0x3 << AURORA_ACR_REPLACEMENT_OFFSET)
+#define AURORA_ACR_REPLACEMENT_TYPE_WAYRR    \
+	(0 << AURORA_ACR_REPLACEMENT_OFFSET)
+#define AURORA_ACR_REPLACEMENT_TYPE_LFSR     \
+	(1 << AURORA_ACR_REPLACEMENT_OFFSET)
+#define AURORA_ACR_REPLACEMENT_TYPE_SEMIPLRU \
+	(3 << AURORA_ACR_REPLACEMENT_OFFSET)
+
+#define AURORA_ACR_FORCE_WRITE_POLICY_OFFSET	0
+#define AURORA_ACR_FORCE_WRITE_POLICY_MASK	\
+	(0x3 << AURORA_ACR_FORCE_WRITE_POLICY_OFFSET)
+#define AURORA_ACR_FORCE_WRITE_POLICY_DIS	\
+	(0 << AURORA_ACR_FORCE_WRITE_POLICY_OFFSET)
+#define AURORA_ACR_FORCE_WRITE_BACK_POLICY	\
+	(1 << AURORA_ACR_FORCE_WRITE_POLICY_OFFSET)
+#define AURORA_ACR_FORCE_WRITE_THRO_POLICY	\
+	(2 << AURORA_ACR_FORCE_WRITE_POLICY_OFFSET)
+
+#define MAX_RANGE_SIZE		1024
+
+/* chose a number outside L2X0_CACHE_ID_PART_MASK to be sure to make
+ * the distinction between a number coming from hardware and a number
+ * coming from the device tree */
+#define AURORA_CACHE_ID	       0x100
+
+#endif /* __ASM_ARM_HARDWARE_AURORA_L2_H */

@@ -25,6 +25,7 @@
 
 #include <asm/cacheflush.h>
 #include <asm/hardware/cache-l2x0.h>
+#include <asm/hardware/cache-aurora-l2.h>
 
 #define CACHE_LINE_SIZE		32
 

@@ -33,6 +34,11 @@ static DEFINE_RAW_SPINLOCK(l2x0_lock);
 static u32 l2x0_way_mask;	/* Bitmask of active ways */
 static u32 l2x0_size;
 static unsigned long sync_reg_offset = L2X0_CACHE_SYNC;
+static int l2_wt_override;
+
+/* Aurora don't have the cache ID register available, so we have to
+ * pass it though the device tree */
+static u32  cache_id_part_number_from_dt;
 
 struct l2x0_regs l2x0_saved_regs;
 

@@ -275,6 +281,130 @@ static void l2x0_flush_range(unsigned long start, unsigned long end)
 	cache_sync();
 	raw_spin_unlock_irqrestore(&l2x0_lock, flags);
 }
+/*
+ * Note that the end addresses passed to Linux primitives are
+ * noninclusive, while the hardware cache range operations use
+ * inclusive start and end addresses.
+ */
+static unsigned long calc_range_end(unsigned long start, unsigned long end)
+{
+	unsigned long range_end;
+
+	BUG_ON(start & (CACHE_LINE_SIZE - 1));
+	BUG_ON(end & (CACHE_LINE_SIZE - 1));
+
+	/*
+	 * Try to process all cache lines between 'start' and 'end'.
+	 */
+	range_end = end;
+
+	/*
+	 * Limit the number of cache lines processed at once,
+	 * since cache range operations stall the CPU pipeline
+	 * until completion.
+	 */
+	if (range_end > start + MAX_RANGE_SIZE)
+		range_end = start + MAX_RANGE_SIZE;
+
+	/*
+	 * Cache range operations can't straddle a page boundary.
+	 */
+	if (range_end > (start | (PAGE_SIZE - 1)) + 1)
+		range_end = (start | (PAGE_SIZE - 1)) + 1;
+
+	return range_end;
+}
+
+static void aurora_pa_range(unsigned long start, unsigned long end,
+			unsigned long offset)
+{
+	unsigned long flags;
+
+	/*
+	 * Make sure 'start' and 'end' reference the same page, as
+	 * L2 is PIPT and range operations only do a TLB lookup on
+	 * the start address.
+	 */
+	BUG_ON((start ^ end) & ~(PAGE_SIZE - 1));
+	raw_spin_lock_irqsave(&l2x0_lock, flags);
+	writel(start, l2x0_base + AURORA_RANGE_BASE_ADDR_REG);
+	writel(end, l2x0_base + offset);
+	raw_spin_unlock_irqrestore(&l2x0_lock, flags);
+
+	cache_sync();
+}
+
+static void aurora_inv_range(unsigned long start, unsigned long end)
+{
+	/*
+	 * Clean and invalidate partial first cache line.
+	 */
+	if (start & (CACHE_LINE_SIZE - 1)) {
+		writel((start & ~(CACHE_LINE_SIZE - 1)) & ~0x1f,
+			l2x0_base + AURORA_FLUSH_PHY_ADDR_REG);
+		cache_sync();
+		start = (start | (CACHE_LINE_SIZE - 1)) + 1;
+	}
+
+	/*
+	 * Clean and invalidate partial last cache line.
+	 */
+	if (start < end && end & (CACHE_LINE_SIZE - 1)) {
+		writel((end & ~(CACHE_LINE_SIZE - 1)) & ~0x1f,
+			l2x0_base + AURORA_FLUSH_PHY_ADDR_REG);
+		cache_sync();
+		end &= ~(CACHE_LINE_SIZE - 1);
+	}
+
+	/*
+	 * Invalidate all full cache lines between 'start' and 'end'.
+	 */
+	while (start < end) {
+		unsigned long range_end = calc_range_end(start, end);
+		aurora_pa_range(start, range_end - CACHE_LINE_SIZE,
+				AURORA_INVAL_RANGE_REG);
+		start = range_end;
+	}
+
+	dsb();
+}
+
+static void aurora_clean_range(unsigned long start, unsigned long end)
+{
+	/*
+	 * If L2 is forced to WT, the L2 will always be clean and we
+	 * don't need to do anything here.
+	 */
+	if (!l2_wt_override) {
+		start &= ~(CACHE_LINE_SIZE - 1);
+		end = (end + CACHE_LINE_SIZE - 1) & ~(CACHE_LINE_SIZE - 1);
+		while (start != end) {
+			unsigned long range_end = calc_range_end(start, end);
+			aurora_pa_range(start, range_end - CACHE_LINE_SIZE,
+					AURORA_CLEAN_RANGE_REG);
+			start = range_end;
+		}
+	}
+
+	dsb();
+}
+
+static void aurora_flush_range(unsigned long start, unsigned long end)
+{
+	if (!l2_wt_override) {
+		start &= ~(CACHE_LINE_SIZE - 1);
+		end = (end + CACHE_LINE_SIZE - 1) & ~(CACHE_LINE_SIZE - 1);
+		while (start != end) {
+			unsigned long range_end = calc_range_end(start, end);
+			aurora_pa_range(start, range_end - CACHE_LINE_SIZE,
+					AURORA_FLUSH_RANGE_REG);
+			start = range_end;
+		}
+	}
+	dsb();
+}
+
+
 
 static void l2x0_disable(void)
 {

@@ -292,11 +422,18 @@ static void l2x0_unlock(u32 cache_id)
 	int lockregs;
 	int i;
 
-	if (cache_id == L2X0_CACHE_ID_PART_L310)
+	switch (cache_id) {
+	case L2X0_CACHE_ID_PART_L310:
 		lockregs = 8;
-	else
+		break;
+	case AURORA_CACHE_ID:
+		lockregs = 4;
+		break;
+	default:
 		/* L210 and unknown types */
 		lockregs = 1;
+		break;
+	}
 
 	for (i = 0; i < lockregs; i++) {
 		writel_relaxed(0x0, l2x0_base + L2X0_LOCKDOWN_WAY_D_BASE +

@@ -312,18 +449,22 @@ void __init l2x0_init(void __iomem *base, u32 aux_val, u32 aux_mask)
 	u32 cache_id;
 	u32 way_size = 0;
 	int ways;
+	int way_size_shift = 3;
 	const char *type;
 
 	l2x0_base = base;
-
-	cache_id = readl_relaxed(l2x0_base + L2X0_CACHE_ID);
+	if (cache_id_part_number_from_dt)
+		cache_id = cache_id_part_number_from_dt;
+	else
+		cache_id = readl_relaxed(l2x0_base + L2X0_CACHE_ID)
+			& L2X0_CACHE_ID_PART_MASK;
 	aux = readl_relaxed(l2x0_base + L2X0_AUX_CTRL);
 
 	aux &= aux_mask;
 	aux |= aux_val;
 
 	/* Determine the number of ways */
-	switch (cache_id & L2X0_CACHE_ID_PART_MASK) {
+	switch (cache_id) {
 	case L2X0_CACHE_ID_PART_L310:
 		if (aux & (1 << 16))
 			ways = 16;

@@ -340,6 +481,30 @@ void __init l2x0_init(void __iomem *base, u32 aux_val, u32 aux_mask)
 		ways = (aux >> 13) & 0xf;
 		type = "L210";
 		break;
+
+	case AURORA_CACHE_ID:
+		sync_reg_offset = AURORA_SYNC_REG;
+
+		switch ((aux >> 13) & 0xf) {
+		case 3:
+			ways = 4;
+			break;
+		case 7:
+			ways = 8;
+			break;
+		case 11:
+			ways = 16;
+			break;
+		case 15:
+			ways = 32;
+			break;
+		default:
+			ways = 8;
+			break;
+		}
+		way_size_shift = 2;
+		type = "Aurora";
+		break;
 	default:
 		/* Assume unknown chips have 8 ways */
 		ways = 8;

@@ -353,7 +518,8 @@ void __init l2x0_init(void __iomem *base, u32 aux_val, u32 aux_mask)
 	 * L2 cache Size =  Way size * Number of ways
 	 */
 	way_size = (aux & L2X0_AUX_CTRL_WAY_SIZE_MASK) >> 17;
-	way_size = 1 << (way_size + 3);
+	way_size = 1 << (way_size + way_size_shift);
+
 	l2x0_size = ways * way_size * SZ_1K;
 
 	/*

@@ -489,6 +655,12 @@ static void __init pl310_save(void)
 	}
 }
 
+static void aurora_save(void)
+{
+	l2x0_saved_regs.ctrl = readl_relaxed(l2x0_base + L2X0_CTRL);
+	l2x0_saved_regs.aux_ctrl = readl_relaxed(l2x0_base + L2X0_AUX_CTRL);
+}
+
 static void l2x0_resume(void)
 {
 	if (!(readl_relaxed(l2x0_base + L2X0_CTRL) & 1)) {

@@ -534,6 +706,48 @@ static void pl310_resume(void)
 	l2x0_resume();
 }
 
+static void aurora_resume(void)
+{
+	u32 u;
+
+	u = readl(l2x0_base + L2X0_CTRL);
+	if (!(u & 1)) {
+		writel(l2x0_saved_regs.aux_ctrl, l2x0_base + L2X0_AUX_CTRL);
+		writel(l2x0_saved_regs.ctrl, l2x0_base + L2X0_CTRL);
+	}
+}
+
+static void __init aurora_broadcast_l2_commands()
+{
+	__u32 u;
+	/* Enable Broadcasting of cache commands to L2*/
+	__asm__ __volatile__("mrc p15, 1, %0, c15, c2, 0" : "=r"(u));
+	u |= 0x100;		/* Set the FW bit */
+	__asm__ __volatile__("mcr p15, 1, %0, c15, c2, 0\n" : : "r"(u));
+}
+
+static void __init aurora_of_setup(const struct device_node *np,
+				u32 *aux_val, u32 *aux_mask)
+{
+	u32 val = AURORA_ACR_REPLACEMENT_TYPE_SEMIPLRU;
+	u32 mask =  AURORA_ACR_REPLACEMENT_MASK;
+
+	of_property_read_u32(np, "cache-id-part",
+			&cache_id_part_number_from_dt);
+
+	/* Determine and save the write policy */
+	l2_wt_override = of_property_read_bool(np, "wt-override");
+
+	if (l2_wt_override) {
+		val |= AURORA_ACR_FORCE_WRITE_THRO_POLICY;
+		mask |= AURORA_ACR_FORCE_WRITE_POLICY_MASK;
+	}
+
+	*aux_val &= ~mask;
+	*aux_val |= val;
+	*aux_mask &= ~mask;
+}
+
 static const struct l2x0_of_data pl310_data = {
 	.setup = pl310_of_setup,
 	.save  = pl310_save,

@@ -565,10 +779,37 @@ static const struct l2x0_of_data l2x0_data = {
 	},
 };
 
+static const struct l2x0_of_data aurora_with_outer_data = {
+	.setup = aurora_of_setup,
+	.save  = aurora_save,
+	.outer_cache = {
+		.resume      = aurora_resume,
+		.inv_range   = aurora_inv_range,
+		.clean_range = aurora_clean_range,
+		.flush_range = aurora_flush_range,
+		.sync        = l2x0_cache_sync,
+		.flush_all   = l2x0_flush_all,
+		.inv_all     = l2x0_inv_all,
+		.disable     = l2x0_disable,
+	},
+};
+
+static const struct l2x0_of_data aurora_no_outer_data = {
+	.setup = aurora_of_setup,
+	.save  = aurora_save,
+	.outer_cache = {
+		.resume      = aurora_resume,
+	},
+};
+
 static const struct of_device_id l2x0_ids[] __initconst = {
 	{ .compatible = "arm,pl310-cache", .data = (void *)&pl310_data },
 	{ .compatible = "arm,l220-cache", .data = (void *)&l2x0_data },
 	{ .compatible = "arm,l210-cache", .data = (void *)&l2x0_data },
+	{ .compatible = "marvell,aurora-cache-no-outer",
+	  .data = (void *)&aurora_no_outer_data},
+	{ .compatible = "marvell,aurora-cache-with-outer",
+	  .data = (void *)&aurora_with_outer_data},
 	{}
 };
 

@@ -597,6 +838,12 @@ int __init l2x0_of_init(u32 aux_val, u32 aux_mask)
 	if (!(readl_relaxed(l2x0_base + L2X0_CTRL) & 1)) {
 		if (data->setup)
 			data->setup(np, &aux_val, &aux_mask);
+
+
+		/* For aurora cache in no outer mode select the
+		 * correct mode using the coprocessor*/
+		if (data == &aurora_no_outer_data)
+			aurora_broadcast_l2_commands();
 	}
 
 	if (data->save)

@@ -0,0 +1,51 @@
+/*
+ * AURORA shared L2 cache controller support
+ *
+ * Copyright (C) 2012 Marvell
+ *
+ * Yehuda Yitschak <yehuday@marvell.com>
+ * Gregory CLEMENT <gregory.clement@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.
+ */
+
+#ifndef __ASM_ARM_HARDWARE_AURORA_L2_H
+#define __ASM_ARM_HARDWARE_AURORA_L2_H
+
+#define AURORA_SYNC_REG		    0x700
+#define AURORA_RANGE_BASE_ADDR_REG  0x720
+#define AURORA_FLUSH_PHY_ADDR_REG   0x7f0
+#define AURORA_INVAL_RANGE_REG	    0x774
+#define AURORA_CLEAN_RANGE_REG	    0x7b4
+#define AURORA_FLUSH_RANGE_REG	    0x7f4
+
+#define AURORA_ACR_REPLACEMENT_OFFSET	    27
+#define AURORA_ACR_REPLACEMENT_MASK	     \
+	(0x3 << AURORA_ACR_REPLACEMENT_OFFSET)
+#define AURORA_ACR_REPLACEMENT_TYPE_WAYRR    \
+	(0 << AURORA_ACR_REPLACEMENT_OFFSET)
+#define AURORA_ACR_REPLACEMENT_TYPE_LFSR     \
+	(1 << AURORA_ACR_REPLACEMENT_OFFSET)
+#define AURORA_ACR_REPLACEMENT_TYPE_SEMIPLRU \
+	(3 << AURORA_ACR_REPLACEMENT_OFFSET)
+
+#define AURORA_ACR_FORCE_WRITE_POLICY_OFFSET	0
+#define AURORA_ACR_FORCE_WRITE_POLICY_MASK	\
+	(0x3 << AURORA_ACR_FORCE_WRITE_POLICY_OFFSET)
+#define AURORA_ACR_FORCE_WRITE_POLICY_DIS	\
+	(0 << AURORA_ACR_FORCE_WRITE_POLICY_OFFSET)
+#define AURORA_ACR_FORCE_WRITE_BACK_POLICY	\
+	(1 << AURORA_ACR_FORCE_WRITE_POLICY_OFFSET)
+#define AURORA_ACR_FORCE_WRITE_THRO_POLICY	\
+	(2 << AURORA_ACR_FORCE_WRITE_POLICY_OFFSET)
+
+#define MAX_RANGE_SIZE		1024
+
+/* chose a number outside L2X0_CACHE_ID_PART_MASK to be sure to make
+ * the distinction between a number coming from hardware and a number
+ * coming from the device tree */
+#define AURORA_CACHE_ID	       0x100
+
+#endif /* __ASM_ARM_HARDWARE_AURORA_L2_H */

@@ -25,14 +25,33 @@
 
 #include <asm/cacheflush.h>
 #include <asm/hardware/cache-l2x0.h>
+#include <asm/hardware/cache-aurora-l2.h>
 
 #define CACHE_LINE_SIZE		32
 
+#ifdef CONFIG_ARM_LPAE
+/*
+ * On Aurora if LPAE is activated then when writting in a 32bits
+ * adress in regsiter actual physical address is
+ * {bits[3:0],bits[31:5],00000}. And if not bits[4:0] must be set to
+ * 0x0.
+ */
+
+#define AURORA_LPAE(addr)   ((((addr)>>32)&0xf)|((addr)&~0xf))
+#else
+#define AURORA_LPAE(addr)   (addr)
+#endif
+
 static void __iomem *l2x0_base;
 static DEFINE_RAW_SPINLOCK(l2x0_lock);
 static u32 l2x0_way_mask;	/* Bitmask of active ways */
 static u32 l2x0_size;
 static unsigned long sync_reg_offset = L2X0_CACHE_SYNC;
+static int l2_wt_override;
+
+/* Aurora don't have the cache ID register available, so we have to
+ * pass it though the device tree */
+static u32  cache_id_part_number_from_dt;
 
 struct l2x0_regs l2x0_saved_regs;
 

@@ -275,6 +294,132 @@ static void l2x0_flush_range(unsigned long start, unsigned long end)
 	cache_sync();
 	raw_spin_unlock_irqrestore(&l2x0_lock, flags);
 }
+/*
+ * Note that the end addresses passed to Linux primitives are
+ * noninclusive, while the hardware cache range operations use
+ * inclusive start and end addresses.
+ */
+static phys_addr_t calc_range_end(phys_addr_t start, phys_addr_t end)
+{
+	phys_addr_t range_end;
+
+	BUG_ON(start & (CACHE_LINE_SIZE - 1));
+	BUG_ON(end & (CACHE_LINE_SIZE - 1));
+
+	/*
+	 * Try to process all cache lines between 'start' and 'end'.
+	 */
+	range_end = end;
+
+	/*
+	 * Limit the number of cache lines processed at once,
+	 * since cache range operations stall the CPU pipeline
+	 * until completion.
+	 */
+	if (range_end > start + MAX_RANGE_SIZE)
+		range_end = start + MAX_RANGE_SIZE;
+
+	/*
+	 * Cache range operations can't straddle a page boundary.
+	 */
+	if (range_end > (start | (PAGE_SIZE - 1)) + 1)
+		range_end = (start | (PAGE_SIZE - 1)) + 1;
+
+	return range_end;
+}
+
+static void aurora_pa_range(phys_addr_t start, phys_addr_t end,
+			unsigned long offset)
+{
+	unsigned long flags;
+
+	/*
+	 * Make sure 'start' and 'end' reference the same page, as
+	 * L2 is PIPT and range operations only do a TLB lookup on
+	 * the start address.
+	 */
+	BUG_ON((start ^ end) & ~(PAGE_SIZE - 1));
+	raw_spin_lock_irqsave(&l2x0_lock, flags);
+
+
+	writel_relaxed(AURORA_LPAE(start), l2x0_base + AURORA_RANGE_BASE_ADDR_REG);
+	writel_relaxed(AURORA_LPAE(end), l2x0_base + offset);
+	raw_spin_unlock_irqrestore(&l2x0_lock, flags);
+
+	cache_sync();
+}
+
+static void aurora_inv_range(phys_addr_t start, phys_addr_t end)
+{
+	/*
+	 * Clean and invalidate partial first cache line.
+	 */
+	if (start & (CACHE_LINE_SIZE - 1)) {
+		writel_relaxed(AURORA_LPAE((start & ~(CACHE_LINE_SIZE - 1)) & ~0x1f),
+			l2x0_base + AURORA_FLUSH_PHY_ADDR_REG);
+		cache_sync();
+		start = (start | (CACHE_LINE_SIZE - 1)) + 1;
+	}
+
+	/*
+	 * Clean and invalidate partial last cache line.
+	 */
+	if (start < end && end & (CACHE_LINE_SIZE - 1)) {
+		writel_relaxed(AURORA_LPAE((end & ~(CACHE_LINE_SIZE - 1)) & ~0x1f),
+			l2x0_base + AURORA_FLUSH_PHY_ADDR_REG);
+		cache_sync();
+		end &= ~(CACHE_LINE_SIZE - 1);
+	}
+
+	/*
+	 * Invalidate all full cache lines between 'start' and 'end'.
+	 */
+	while (start < end) {
+		phys_addr_t range_end = calc_range_end(start, end);
+		aurora_pa_range(start, range_end - CACHE_LINE_SIZE,
+				AURORA_INVAL_RANGE_REG);
+		start = range_end;
+	}
+
+	dsb();
+}
+
+static void aurora_clean_range(phys_addr_t start, phys_addr_t end)
+{
+	/*
+	 * If L2 is forced to WT, the L2 will always be clean and we
+	 * don't need to do anything here.
+	 */
+	if (!l2_wt_override) {
+		start &= ~(CACHE_LINE_SIZE - 1);
+		end = (end + CACHE_LINE_SIZE - 1) & ~(CACHE_LINE_SIZE - 1);
+		while (start != end) {
+			phys_addr_t range_end = calc_range_end(start, end);
+			aurora_pa_range(start, range_end - CACHE_LINE_SIZE,
+					AURORA_CLEAN_RANGE_REG);
+			start = range_end;
+		}
+	}
+
+	dsb();
+}
+
+static void aurora_flush_range(phys_addr_t start, phys_addr_t end)
+{
+	if (!l2_wt_override) {
+		start &= ~(CACHE_LINE_SIZE - 1);
+		end = (end + CACHE_LINE_SIZE - 1) & ~(CACHE_LINE_SIZE - 1);
+		while (start != end) {
+			phys_addr_t range_end = calc_range_end(start, end);
+			aurora_pa_range(start, range_end - CACHE_LINE_SIZE,
+					AURORA_FLUSH_RANGE_REG);
+			start = range_end;
+		}
+	}
+	dsb();
+}
+
+
 
 static void l2x0_disable(void)
 {

@@ -292,11 +437,18 @@ static void l2x0_unlock(u32 cache_id)
 	int lockregs;
 	int i;
 
-	if (cache_id == L2X0_CACHE_ID_PART_L310)
+	switch (cache_id) {
+	case L2X0_CACHE_ID_PART_L310:
 		lockregs = 8;
-	else
+		break;
+	case AURORA_CACHE_ID:
+		lockregs = 4;
+		break;
+	default:
 		/* L210 and unknown types */
 		lockregs = 1;
+		break;
+	}
 
 	for (i = 0; i < lockregs; i++) {
 		writel_relaxed(0x0, l2x0_base + L2X0_LOCKDOWN_WAY_D_BASE +

@@ -312,18 +464,22 @@ void __init l2x0_init(void __iomem *base, u32 aux_val, u32 aux_mask)
 	u32 cache_id;
 	u32 way_size = 0;
 	int ways;
+	int way_size_shift = 3;
 	const char *type;
 
 	l2x0_base = base;
-
-	cache_id = readl_relaxed(l2x0_base + L2X0_CACHE_ID);
+	if (cache_id_part_number_from_dt)
+		cache_id = cache_id_part_number_from_dt;
+	else
+		cache_id = readl_relaxed(l2x0_base + L2X0_CACHE_ID)
+			& L2X0_CACHE_ID_PART_MASK;
 	aux = readl_relaxed(l2x0_base + L2X0_AUX_CTRL);
 
 	aux &= aux_mask;
 	aux |= aux_val;
 
 	/* Determine the number of ways */
-	switch (cache_id & L2X0_CACHE_ID_PART_MASK) {
+	switch (cache_id) {
 	case L2X0_CACHE_ID_PART_L310:
 		if (aux & (1 << 16))
 			ways = 16;

@@ -340,6 +496,30 @@ void __init l2x0_init(void __iomem *base, u32 aux_val, u32 aux_mask)
 		ways = (aux >> 13) & 0xf;
 		type = "L210";
 		break;
+
+	case AURORA_CACHE_ID:
+		sync_reg_offset = AURORA_SYNC_REG;
+
+		switch ((aux >> 13) & 0xf) {
+		case 3:
+			ways = 4;
+			break;
+		case 7:
+			ways = 8;
+			break;
+		case 11:
+			ways = 16;
+			break;
+		case 15:
+			ways = 32;
+			break;
+		default:
+			ways = 8;
+			break;
+		}
+		way_size_shift = 2;
+		type = "Aurora";
+		break;
 	default:
 		/* Assume unknown chips have 8 ways */
 		ways = 8;

@@ -353,7 +533,8 @@ void __init l2x0_init(void __iomem *base, u32 aux_val, u32 aux_mask)
 	 * L2 cache Size =  Way size * Number of ways
 	 */
 	way_size = (aux & L2X0_AUX_CTRL_WAY_SIZE_MASK) >> 17;
-	way_size = 1 << (way_size + 3);
+	way_size = 1 << (way_size + way_size_shift);
+
 	l2x0_size = ways * way_size * SZ_1K;
 
 	/*

@@ -489,6 +670,12 @@ static void __init pl310_save(void)
 	}
 }
 
+static void aurora_save(void)
+{
+	l2x0_saved_regs.ctrl = readl_relaxed(l2x0_base + L2X0_CTRL);
+	l2x0_saved_regs.aux_ctrl = readl_relaxed(l2x0_base + L2X0_AUX_CTRL);
+}
+
 static void l2x0_resume(void)
 {
 	if (!(readl_relaxed(l2x0_base + L2X0_CTRL) & 1)) {

@@ -534,6 +721,48 @@ static void pl310_resume(void)
 	l2x0_resume();
 }
 
+static void aurora_resume(void)
+{
+	u32 u;
+
+	u = readl(l2x0_base + L2X0_CTRL);
+	if (!(u & 1)) {
+		writel(l2x0_saved_regs.aux_ctrl, l2x0_base + L2X0_AUX_CTRL);
+		writel(l2x0_saved_regs.ctrl, l2x0_base + L2X0_CTRL);
+	}
+}
+
+static void __init aurora_broadcast_l2_commands(void)
+{
+	__u32 u;
+	/* Enable Broadcasting of cache commands to L2*/
+	__asm__ __volatile__("mrc p15, 1, %0, c15, c2, 0" : "=r"(u));
+	u |= 0x100;		/* Set the FW bit */
+	__asm__ __volatile__("mcr p15, 1, %0, c15, c2, 0\n" : : "r"(u));
+}
+
+static void __init aurora_of_setup(const struct device_node *np,
+				u32 *aux_val, u32 *aux_mask)
+{
+	u32 val = AURORA_ACR_REPLACEMENT_TYPE_SEMIPLRU;
+	u32 mask =  AURORA_ACR_REPLACEMENT_MASK;
+
+	of_property_read_u32(np, "cache-id-part",
+			&cache_id_part_number_from_dt);
+
+	/* Determine and save the write policy */
+	l2_wt_override = of_property_read_bool(np, "wt-override");
+
+	if (l2_wt_override) {
+		val |= AURORA_ACR_FORCE_WRITE_THRO_POLICY;
+		mask |= AURORA_ACR_FORCE_WRITE_POLICY_MASK;
+	}
+
+	*aux_val &= ~mask;
+	*aux_val |= val;
+	*aux_mask &= ~mask;
+}
+
 static const struct l2x0_of_data pl310_data = {
 	.setup = pl310_of_setup,
 	.save  = pl310_save,

@@ -565,10 +794,37 @@ static const struct l2x0_of_data l2x0_data = {
 	},
 };
 
+static const struct l2x0_of_data aurora_with_outer_data = {
+	.setup = aurora_of_setup,
+	.save  = aurora_save,
+	.outer_cache = {
+		.resume      = aurora_resume,
+		.inv_range   = aurora_inv_range,
+		.clean_range = aurora_clean_range,
+		.flush_range = aurora_flush_range,
+		.sync        = l2x0_cache_sync,
+		.flush_all   = l2x0_flush_all,
+		.inv_all     = l2x0_inv_all,
+		.disable     = l2x0_disable,
+	},
+};
+
+static const struct l2x0_of_data aurora_no_outer_data = {
+	.setup = aurora_of_setup,
+	.save  = aurora_save,
+	.outer_cache = {
+		.resume      = aurora_resume,
+	},
+};
+
 static const struct of_device_id l2x0_ids[] __initconst = {
 	{ .compatible = "arm,pl310-cache", .data = (void *)&pl310_data },
 	{ .compatible = "arm,l220-cache", .data = (void *)&l2x0_data },
 	{ .compatible = "arm,l210-cache", .data = (void *)&l2x0_data },
+	{ .compatible = "marvell,aurora-cache-no-outer",
+	  .data = (void *)&aurora_no_outer_data},
+	{ .compatible = "marvell,aurora-cache-with-outer",
+	  .data = (void *)&aurora_with_outer_data},
 	{}
 };