19 files changed, 917 insertions, 164 deletions

diff --git a/arch/arm/mach-tegra/Makefile b/arch/arm/mach-tegra/Makefile
index 76a79b8a172..1dd2726986c 100644
--- a/arch/arm/mach-tegra/Makefile
+++ b/arch/arm/mach-tegra/Makefile
@@ -7,6 +7,7 @@ obj-y                                   += clock.o
 obj-y                                   += timer.o
 obj-y                                   += pinmux.o
 obj-y					+= fuse.o
+obj-y					+= pmc.o
 obj-$(CONFIG_CPU_IDLE)			+= cpuidle.o
 obj-$(CONFIG_CPU_IDLE)			+= sleep.o
 obj-$(CONFIG_ARCH_TEGRA_2x_SOC)		+= powergate.o
@@ -18,7 +19,7 @@ obj-$(CONFIG_ARCH_TEGRA_3x_SOC)		+= board-dt-tegra30.o
 obj-$(CONFIG_ARCH_TEGRA_3x_SOC)		+= tegra30_clocks.o
 obj-$(CONFIG_SMP)			+= platsmp.o headsmp.o
 obj-$(CONFIG_HOTPLUG_CPU)               += hotplug.o
-obj-$(CONFIG_TEGRA_SYSTEM_DMA)		+= dma.o
+obj-$(CONFIG_TEGRA_SYSTEM_DMA)		+= dma.o apbio.o
 obj-$(CONFIG_CPU_FREQ)                  += cpu-tegra.o
 obj-$(CONFIG_TEGRA_PCI)			+= pcie.o
 obj-$(CONFIG_USB_SUPPORT)		+= usb_phy.o
diff --git a/arch/arm/mach-tegra/apbio.c b/arch/arm/mach-tegra/apbio.c
new file mode 100644
index 00000000000..e75451e517b
--- /dev/null
+++ b/arch/arm/mach-tegra/apbio.c
@@ -0,0 +1,145 @@
+/*
+ * Copyright (C) 2010 NVIDIA Corporation.
+ * Copyright (C) 2010 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/io.h>
+#include <linux/dma-mapping.h>
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <linux/sched.h>
+#include <linux/mutex.h>
+
+#include <mach/dma.h>
+#include <mach/iomap.h>
+
+#include "apbio.h"
+
+static DEFINE_MUTEX(tegra_apb_dma_lock);
+
+static struct tegra_dma_channel *tegra_apb_dma;
+static u32 *tegra_apb_bb;
+static dma_addr_t tegra_apb_bb_phys;
+static DECLARE_COMPLETION(tegra_apb_wait);
+
+bool tegra_apb_init(void)
+{
+	struct tegra_dma_channel *ch;
+
+	mutex_lock(&tegra_apb_dma_lock);
+
+	/* Check to see if we raced to setup */
+	if (tegra_apb_dma)
+		goto out;
+
+	ch = tegra_dma_allocate_channel(TEGRA_DMA_MODE_ONESHOT |
+		TEGRA_DMA_SHARED);
+
+	if (!ch)
+		goto out_fail;
+
+	tegra_apb_bb = dma_alloc_coherent(NULL, sizeof(u32),
+		&tegra_apb_bb_phys, GFP_KERNEL);
+	if (!tegra_apb_bb) {
+		pr_err("%s: can not allocate bounce buffer\n", __func__);
+		tegra_dma_free_channel(ch);
+		goto out_fail;
+	}
+
+	tegra_apb_dma = ch;
+out:
+	mutex_unlock(&tegra_apb_dma_lock);
+	return true;
+
+out_fail:
+	mutex_unlock(&tegra_apb_dma_lock);
+	return false;
+}
+
+static void apb_dma_complete(struct tegra_dma_req *req)
+{
+	complete(&tegra_apb_wait);
+}
+
+u32 tegra_apb_readl(unsigned long offset)
+{
+	struct tegra_dma_req req;
+	int ret;
+
+	if (!tegra_apb_dma && !tegra_apb_init())
+		return readl(IO_TO_VIRT(offset));
+
+	mutex_lock(&tegra_apb_dma_lock);
+	req.complete = apb_dma_complete;
+	req.to_memory = 1;
+	req.dest_addr = tegra_apb_bb_phys;
+	req.dest_bus_width = 32;
+	req.dest_wrap = 1;
+	req.source_addr = offset;
+	req.source_bus_width = 32;
+	req.source_wrap = 4;
+	req.req_sel = TEGRA_DMA_REQ_SEL_CNTR;
+	req.size = 4;
+
+	INIT_COMPLETION(tegra_apb_wait);
+
+	tegra_dma_enqueue_req(tegra_apb_dma, &req);
+
+	ret = wait_for_completion_timeout(&tegra_apb_wait,
+		msecs_to_jiffies(50));
+
+	if (WARN(ret == 0, "apb read dma timed out")) {
+		tegra_dma_dequeue_req(tegra_apb_dma, &req);
+		*(u32 *)tegra_apb_bb = 0;
+	}
+
+	mutex_unlock(&tegra_apb_dma_lock);
+	return *((u32 *)tegra_apb_bb);
+}
+
+void tegra_apb_writel(u32 value, unsigned long offset)
+{
+	struct tegra_dma_req req;
+	int ret;
+
+	if (!tegra_apb_dma && !tegra_apb_init()) {
+		writel(value, IO_TO_VIRT(offset));
+		return;
+	}
+
+	mutex_lock(&tegra_apb_dma_lock);
+	*((u32 *)tegra_apb_bb) = value;
+	req.complete = apb_dma_complete;
+	req.to_memory = 0;
+	req.dest_addr = offset;
+	req.dest_wrap = 4;
+	req.dest_bus_width = 32;
+	req.source_addr = tegra_apb_bb_phys;
+	req.source_bus_width = 32;
+	req.source_wrap = 1;
+	req.req_sel = TEGRA_DMA_REQ_SEL_CNTR;
+	req.size = 4;
+
+	INIT_COMPLETION(tegra_apb_wait);
+
+	tegra_dma_enqueue_req(tegra_apb_dma, &req);
+
+	ret = wait_for_completion_timeout(&tegra_apb_wait,
+		msecs_to_jiffies(50));
+
+	if (WARN(ret == 0, "apb write dma timed out"))
+		tegra_dma_dequeue_req(tegra_apb_dma, &req);
+
+	mutex_unlock(&tegra_apb_dma_lock);
+}
diff --git a/arch/arm/mach-tegra/apbio.h b/arch/arm/mach-tegra/apbio.h
new file mode 100644
index 00000000000..8b49e8c89a6
--- /dev/null
+++ b/arch/arm/mach-tegra/apbio.h
@@ -0,0 +1,39 @@
+/*
+ * Copyright (C) 2010 NVIDIA Corporation.
+ * Copyright (C) 2010 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef __MACH_TEGRA_APBIO_H
+#define __MACH_TEGRA_APBIO_H
+
+#ifdef CONFIG_TEGRA_SYSTEM_DMA
+
+u32 tegra_apb_readl(unsigned long offset);
+void tegra_apb_writel(u32 value, unsigned long offset);
+
+#else
+#include <asm/io.h>
+#include <mach/io.h>
+
+static inline u32 tegra_apb_readl(unsigned long offset)
+{
+        return readl(IO_TO_VIRT(offset));
+}
+
+static inline void tegra_apb_writel(u32 value, unsigned long offset)
+{
+        writel(value, IO_TO_VIRT(offset));
+}
+#endif
+
+#endif
diff --git a/arch/arm/mach-tegra/board-harmony-power.c b/arch/arm/mach-tegra/board-harmony-power.c
index c0298b3f7d6..82f32300796 100644
--- a/arch/arm/mach-tegra/board-harmony-power.c
+++ b/arch/arm/mach-tegra/board-harmony-power.c
@@ -18,18 +18,13 @@
 #include <linux/i2c.h>
 #include <linux/platform_device.h>
 #include <linux/gpio.h>
-#include <linux/io.h>
 #include <linux/regulator/machine.h>
 #include <linux/mfd/tps6586x.h>
 
-#include <mach/iomap.h>
 #include <mach/irqs.h>
 
 #include "board-harmony.h"
 
-#define PMC_CTRL		0x0
-#define PMC_CTRL_INTR_LOW	(1 << 17)
-
 static struct regulator_consumer_supply tps658621_ldo0_supply[] = {
 	REGULATOR_SUPPLY("pex_clk", NULL),
 };
@@ -115,16 +110,6 @@ static struct i2c_board_info __initdata harmony_regulators[] = {
 
 int __init harmony_regulator_init(void)
 {
-	void __iomem *pmc = IO_ADDRESS(TEGRA_PMC_BASE);
-	u32 pmc_ctrl;
-
-	/*
-	 * Configure the power management controller to trigger PMU
-	 * interrupts when low
-	 */
-	pmc_ctrl = readl(pmc + PMC_CTRL);
-	writel(pmc_ctrl | PMC_CTRL_INTR_LOW, pmc + PMC_CTRL);
-
 	i2c_register_board_info(3, harmony_regulators, 1);
 
 	return 0;
diff --git a/arch/arm/mach-tegra/board-harmony.c b/arch/arm/mach-tegra/board-harmony.c
index 789bdc9e8f9..c00aadb01e0 100644
--- a/arch/arm/mach-tegra/board-harmony.c
+++ b/arch/arm/mach-tegra/board-harmony.c
@@ -101,7 +101,6 @@ static struct wm8903_platform_data harmony_wm8903_pdata = {
 static struct i2c_board_info __initdata wm8903_board_info = {
 	I2C_BOARD_INFO("wm8903", 0x1a),
 	.platform_data = &harmony_wm8903_pdata,
-	.irq = TEGRA_GPIO_TO_IRQ(TEGRA_GPIO_CDC_IRQ),
 };
 
 static void __init harmony_i2c_init(void)
@@ -111,6 +110,7 @@ static void __init harmony_i2c_init(void)
 	platform_device_register(&tegra_i2c_device3);
 	platform_device_register(&tegra_i2c_device4);
 
+	wm8903_board_info.irq = gpio_to_irq(TEGRA_GPIO_CDC_IRQ);
 	i2c_register_board_info(0, &wm8903_board_info, 1);
 }
 
diff --git a/arch/arm/mach-tegra/board-seaboard.c b/arch/arm/mach-tegra/board-seaboard.c
index ebac65f5251..d669847f048 100644
--- a/arch/arm/mach-tegra/board-seaboard.c
+++ b/arch/arm/mach-tegra/board-seaboard.c
@@ -159,7 +159,6 @@ static struct platform_device *seaboard_devices[] __initdata = {
 
 static struct i2c_board_info __initdata isl29018_device = {
 	I2C_BOARD_INFO("isl29018", 0x44),
-	.irq = TEGRA_GPIO_TO_IRQ(TEGRA_GPIO_ISL29018_IRQ),
 };
 
 static struct i2c_board_info __initdata adt7461_device = {
@@ -183,7 +182,6 @@ static struct wm8903_platform_data wm8903_pdata = {
 static struct i2c_board_info __initdata wm8903_device = {
 	I2C_BOARD_INFO("wm8903", 0x1a),
 	.platform_data = &wm8903_pdata,
-	.irq = TEGRA_GPIO_TO_IRQ(TEGRA_GPIO_CDC_IRQ),
 };
 
 static int seaboard_ehci_init(void)
@@ -214,7 +212,10 @@ static void __init seaboard_i2c_init(void)
 	gpio_request(TEGRA_GPIO_ISL29018_IRQ, "isl29018");
 	gpio_direction_input(TEGRA_GPIO_ISL29018_IRQ);
 
+	isl29018_device.irq = gpio_to_irq(TEGRA_GPIO_ISL29018_IRQ);
 	i2c_register_board_info(0, &isl29018_device, 1);
+
+	wm8903_device.irq = gpio_to_irq(TEGRA_GPIO_CDC_IRQ);
 	i2c_register_board_info(0, &wm8903_device, 1);
 
 	i2c_register_board_info(3, &adt7461_device, 1);
diff --git a/arch/arm/mach-tegra/common.c b/arch/arm/mach-tegra/common.c
index 6c93cd0e520..2f86fcca64a 100644
--- a/arch/arm/mach-tegra/common.c
+++ b/arch/arm/mach-tegra/common.c
@@ -31,6 +31,24 @@
 #include "board.h"
 #include "clock.h"
 #include "fuse.h"
+#include "pmc.h"
+
+/*
+ * Storage for debug-macro.S's state.
+ *
+ * This must be in .data not .bss so that it gets initialized each time the
+ * kernel is loaded. The data is declared here rather than debug-macro.S so
+ * that multiple inclusions of debug-macro.S point at the same data.
+ */
+#define TEGRA_DEBUG_UART_OFFSET (TEGRA_DEBUG_UART_BASE & 0xFFFF)
+u32 tegra_uart_config[3] = {
+	/* Debug UART initialization required */
+	1,
+	/* Debug UART physical address */
+	(u32)(IO_APB_PHYS + TEGRA_DEBUG_UART_OFFSET),
+	/* Debug UART virtual address */
+	(u32)(IO_APB_VIRT + TEGRA_DEBUG_UART_OFFSET),
+};
 
 #ifdef CONFIG_OF
 static const struct of_device_id tegra_dt_irq_match[] __initconst = {
@@ -99,6 +117,7 @@ void __init tegra20_init_early(void)
 	tegra2_init_clocks();
 	tegra_clk_init_from_table(tegra20_clk_init_table);
 	tegra_init_cache(0x331, 0x441);
+	tegra_pmc_init();
 }
 #endif
 #ifdef CONFIG_ARCH_TEGRA_3x_SOC
@@ -106,5 +125,6 @@ void __init tegra30_init_early(void)
 {
 	tegra30_init_clocks();
 	tegra_init_cache(0x441, 0x551);
+	tegra_pmc_init();
 }
 #endif
diff --git a/arch/arm/mach-tegra/dma.c b/arch/arm/mach-tegra/dma.c
index c0cf967e47d..abea4f6e2dd 100644
--- a/arch/arm/mach-tegra/dma.c
+++ b/arch/arm/mach-tegra/dma.c
@@ -33,6 +33,8 @@
 #include <mach/iomap.h>
 #include <mach/suspend.h>
 
+#include "apbio.h"
+
 #define APB_DMA_GEN				0x000
 #define GEN_ENABLE				(1<<31)
 
@@ -50,8 +52,6 @@
 #define CSR_ONCE				(1<<27)
 #define CSR_FLOW				(1<<21)
 #define CSR_REQ_SEL_SHIFT			16
-#define CSR_REQ_SEL_MASK			(0x1F<<CSR_REQ_SEL_SHIFT)
-#define CSR_REQ_SEL_INVALID			(31<<CSR_REQ_SEL_SHIFT)
 #define CSR_WCOUNT_SHIFT			2
 #define CSR_WCOUNT_MASK				0xFFFC
 
@@ -133,6 +133,7 @@ struct tegra_dma_channel {
 
 static bool tegra_dma_initialized;
 static DEFINE_MUTEX(tegra_dma_lock);
+static DEFINE_SPINLOCK(enable_lock);
 
 static DECLARE_BITMAP(channel_usage, NV_DMA_MAX_CHANNELS);
 static struct tegra_dma_channel dma_channels[NV_DMA_MAX_CHANNELS];
@@ -180,36 +181,94 @@ static void tegra_dma_stop(struct tegra_dma_channel *ch)
 
 static int tegra_dma_cancel(struct tegra_dma_channel *ch)
 {
-	u32 csr;
 	unsigned long irq_flags;
 
 	spin_lock_irqsave(&ch->lock, irq_flags);
 	while (!list_empty(&ch->list))
 		list_del(ch->list.next);
 
-	csr = readl(ch->addr + APB_DMA_CHAN_CSR);
-	csr &= ~CSR_REQ_SEL_MASK;
-	csr |= CSR_REQ_SEL_INVALID;
-	writel(csr, ch->addr + APB_DMA_CHAN_CSR);
-
 	tegra_dma_stop(ch);
 
 	spin_unlock_irqrestore(&ch->lock, irq_flags);
 	return 0;
 }
 
+static unsigned int get_channel_status(struct tegra_dma_channel *ch,
+			struct tegra_dma_req *req, bool is_stop_dma)
+{
+	void __iomem *addr = IO_ADDRESS(TEGRA_APB_DMA_BASE);
+	unsigned int status;
+
+	if (is_stop_dma) {
+		/*
+		 * STOP the DMA and get the transfer count.
+		 * Getting the transfer count is tricky.
+		 *  - Globally disable DMA on all channels
+		 *  - Read the channel's status register to know the number
+		 *    of pending bytes to be transfered.
+		 *  - Stop the dma channel
+		 *  - Globally re-enable DMA to resume other transfers
+		 */
+		spin_lock(&enable_lock);
+		writel(0, addr + APB_DMA_GEN);
+		udelay(20);
+		status = readl(ch->addr + APB_DMA_CHAN_STA);
+		tegra_dma_stop(ch);
+		writel(GEN_ENABLE, addr + APB_DMA_GEN);
+		spin_unlock(&enable_lock);
+		if (status & STA_ISE_EOC) {
+			pr_err("Got Dma Int here clearing");
+			writel(status, ch->addr + APB_DMA_CHAN_STA);
+		}
+		req->status = TEGRA_DMA_REQ_ERROR_ABORTED;
+	} else {
+		status = readl(ch->addr + APB_DMA_CHAN_STA);
+	}
+	return status;
+}
+
+/* should be called with the channel lock held */
+static unsigned int dma_active_count(struct tegra_dma_channel *ch,
+	struct tegra_dma_req *req, unsigned int status)
+{
+	unsigned int to_transfer;
+	unsigned int req_transfer_count;
+	unsigned int bytes_transferred;
+
+	to_transfer = ((status & STA_COUNT_MASK) >> STA_COUNT_SHIFT) + 1;
+	req_transfer_count = ch->req_transfer_count + 1;
+	bytes_transferred = req_transfer_count;
+	if (status & STA_BUSY)
+		bytes_transferred -= to_transfer;
+	/*
+	 * In continuous transfer mode, DMA only tracks the count of the
+	 * half DMA buffer. So, if the DMA already finished half the DMA
+	 * then add the half buffer to the completed count.
+	 */
+	if (ch->mode & TEGRA_DMA_MODE_CONTINOUS) {
+		if (req->buffer_status == TEGRA_DMA_REQ_BUF_STATUS_HALF_FULL)
+			bytes_transferred += req_transfer_count;
+		if (status & STA_ISE_EOC)
+			bytes_transferred += req_transfer_count;
+	}
+	bytes_transferred *= 4;
+	return bytes_transferred;
+}
+
 int tegra_dma_dequeue_req(struct tegra_dma_channel *ch,
 	struct tegra_dma_req *_req)
 {
-	unsigned int csr;
 	unsigned int status;
 	struct tegra_dma_req *req = NULL;
 	int found = 0;
 	unsigned long irq_flags;
-	int to_transfer;
-	int req_transfer_count;
+	int stop = 0;
 
 	spin_lock_irqsave(&ch->lock, irq_flags);
+
+	if (list_entry(ch->list.next, struct tegra_dma_req, node) == _req)
+		stop = 1;
+
 	list_for_each_entry(req, &ch->list, node) {
 		if (req == _req) {
 			list_del(&req->node);
@@ -222,47 +281,12 @@ int tegra_dma_dequeue_req(struct tegra_dma_channel *ch,
 		return 0;
 	}
 
-	/* STOP the DMA and get the transfer count.
-	 * Getting the transfer count is tricky.
-	 *  - Change the source selector to invalid to stop the DMA from
-	 *    FIFO to memory.
-	 *  - Read the status register to know the number of pending
-	 *    bytes to be transferred.
-	 *  - Finally stop or program the DMA to the next buffer in the
-	 *    list.
-	 */
-	csr = readl(ch->addr + APB_DMA_CHAN_CSR);
-	csr &= ~CSR_REQ_SEL_MASK;
-	csr |= CSR_REQ_SEL_INVALID;
-	writel(csr, ch->addr + APB_DMA_CHAN_CSR);
-
-	/* Get the transfer count */
-	status = readl(ch->addr + APB_DMA_CHAN_STA);
-	to_transfer = (status & STA_COUNT_MASK) >> STA_COUNT_SHIFT;
-	req_transfer_count = ch->req_transfer_count;
-	req_transfer_count += 1;
-	to_transfer += 1;
-
-	req->bytes_transferred = req_transfer_count;
-
-	if (status & STA_BUSY)
-		req->bytes_transferred -= to_transfer;
-
-	/* In continuous transfer mode, DMA only tracks the count of the
-	 * half DMA buffer. So, if the DMA already finished half the DMA
-	 * then add the half buffer to the completed count.
-	 *
-	 *	FIXME: There can be a race here. What if the req to
-	 *	dequue happens at the same time as the DMA just moved to
-	 *	the new buffer and SW didn't yet received the interrupt?
-	 */
-	if (ch->mode & TEGRA_DMA_MODE_CONTINOUS)
-		if (req->buffer_status == TEGRA_DMA_REQ_BUF_STATUS_HALF_FULL)
-			req->bytes_transferred += req_transfer_count;
+	if (!stop)
+		goto skip_stop_dma;
 
-	req->bytes_transferred *= 4;
+	status = get_channel_status(ch, req, true);
+	req->bytes_transferred = dma_active_count(ch, req, status);
 
-	tegra_dma_stop(ch);
 	if (!list_empty(&ch->list)) {
 		/* if the list is not empty, queue the next request */
 		struct tegra_dma_req *next_req;
@@ -270,6 +294,8 @@ int tegra_dma_dequeue_req(struct tegra_dma_channel *ch,
 			typeof(*next_req), node);
 		tegra_dma_update_hw(ch, next_req);
 	}
+
+skip_stop_dma:
 	req->status = -TEGRA_DMA_REQ_ERROR_ABORTED;
 
 	spin_unlock_irqrestore(&ch->lock, irq_flags);
@@ -357,7 +383,7 @@ struct tegra_dma_channel *tegra_dma_allocate_channel(int mode)
 	int channel;
 	struct tegra_dma_channel *ch = NULL;
 
-	if (WARN_ON(!tegra_dma_initialized))
+	if (!tegra_dma_initialized)
 		return NULL;
 
 	mutex_lock(&tegra_dma_lock);
diff --git a/arch/arm/mach-tegra/fuse.c b/arch/arm/mach-tegra/fuse.c
index ea49bd93c6b..c1afb273876 100644
--- a/arch/arm/mach-tegra/fuse.c
+++ b/arch/arm/mach-tegra/fuse.c
@@ -19,25 +19,75 @@
 
 #include <linux/kernel.h>
 #include <linux/io.h>
-#include <linux/module.h>
+#include <linux/export.h>
 
 #include <mach/iomap.h>
 
 #include "fuse.h"
+#include "apbio.h"
 
 #define FUSE_UID_LOW		0x108
 #define FUSE_UID_HIGH		0x10c
 #define FUSE_SKU_INFO		0x110
 #define FUSE_SPARE_BIT		0x200
 
-static inline u32 fuse_readl(unsigned long offset)
+int tegra_sku_id;
+int tegra_cpu_process_id;
+int tegra_core_process_id;
+enum tegra_revision tegra_revision;
+
+/* The BCT to use at boot is specified by board straps that can be read
+ * through a APB misc register and decoded. 2 bits, i.e. 4 possible BCTs.
+ */
+int tegra_bct_strapping;
+
+#define STRAP_OPT 0x008
+#define GMI_AD0 (1 << 4)
+#define GMI_AD1 (1 << 5)
+#define RAM_ID_MASK (GMI_AD0 | GMI_AD1)
+#define RAM_CODE_SHIFT 4
+
+static const char *tegra_revision_name[TEGRA_REVISION_MAX] = {
+	[TEGRA_REVISION_UNKNOWN] = "unknown",
+	[TEGRA_REVISION_A01]     = "A01",
+	[TEGRA_REVISION_A02]     = "A02",
+	[TEGRA_REVISION_A03]     = "A03",
+	[TEGRA_REVISION_A03p]    = "A03 prime",
+	[TEGRA_REVISION_A04]     = "A04",
+};
+
+static inline u32 tegra_fuse_readl(unsigned long offset)
+{
+	return tegra_apb_readl(TEGRA_FUSE_BASE + offset);
+}
+
+static inline bool get_spare_fuse(int bit)
 {
-	return readl(IO_TO_VIRT(TEGRA_FUSE_BASE + offset));
+	return tegra_fuse_readl(FUSE_SPARE_BIT + bit * 4);
 }
 
-static inline void fuse_writel(u32 value, unsigned long offset)
+static enum tegra_revision tegra_get_revision(void)
 {
-	writel(value, IO_TO_VIRT(TEGRA_FUSE_BASE + offset));
+	void __iomem *chip_id = IO_ADDRESS(TEGRA_APB_MISC_BASE) + 0x804;
+	u32 id = readl(chip_id);
+	u32 minor_rev = (id >> 16) & 0xf;
+	u32 chipid = (id >> 8) & 0xff;
+
+	switch (minor_rev) {
+	case 1:
+		return TEGRA_REVISION_A01;
+	case 2:
+		return TEGRA_REVISION_A02;
+	case 3:
+		if (chipid == 0x20 && (get_spare_fuse(18) || get_spare_fuse(19)))
+			return TEGRA_REVISION_A03p;
+		else
+			return TEGRA_REVISION_A03;
+	case 4:
+		return TEGRA_REVISION_A04;
+	default:
+		return TEGRA_REVISION_UNKNOWN;
+	}
 }
 
 void tegra_init_fuse(void)
@@ -46,41 +96,32 @@ void tegra_init_fuse(void)
 	reg |= 1 << 28;
 	writel(reg, IO_TO_VIRT(TEGRA_CLK_RESET_BASE + 0x48));
 
-	pr_info("Tegra SKU: %d CPU Process: %d Core Process: %d\n",
-		tegra_sku_id(), tegra_cpu_process_id(),
-		tegra_core_process_id());
+	reg = tegra_fuse_readl(FUSE_SKU_INFO);
+	tegra_sku_id = reg & 0xFF;
+
+	reg = tegra_fuse_readl(FUSE_SPARE_BIT);
+	tegra_cpu_process_id = (reg >> 6) & 3;
+
+	reg = tegra_fuse_readl(FUSE_SPARE_BIT);
+	tegra_core_process_id = (reg >> 12) & 3;
+
+	reg = tegra_apb_readl(TEGRA_APB_MISC_BASE + STRAP_OPT);
+	tegra_bct_strapping = (reg & RAM_ID_MASK) >> RAM_CODE_SHIFT;
+
+	tegra_revision = tegra_get_revision();
+
+	pr_info("Tegra Revision: %s SKU: %d CPU Process: %d Core Process: %d\n",
+		tegra_revision_name[tegra_get_revision()],
+		tegra_sku_id, tegra_cpu_process_id,
+		tegra_core_process_id);
 }
 
 unsigned long long tegra_chip_uid(void)
 {
 	unsigned long long lo, hi;
 
-	lo = fuse_readl(FUSE_UID_LOW);
-	hi = fuse_readl(FUSE_UID_HIGH);
+	lo = tegra_fuse_readl(FUSE_UID_LOW);
+	hi = tegra_fuse_readl(FUSE_UID_HIGH);
 	return (hi << 32ull) | lo;
 }
 EXPORT_SYMBOL(tegra_chip_uid);
-
-int tegra_sku_id(void)
-{
-	int sku_id;
-	u32 reg = fuse_readl(FUSE_SKU_INFO);
-	sku_id = reg & 0xFF;
-	return sku_id;
-}
-
-int tegra_cpu_process_id(void)
-{
-	int cpu_process_id;
-	u32 reg = fuse_readl(FUSE_SPARE_BIT);
-	cpu_process_id = (reg >> 6) & 3;
-	return cpu_process_id;
-}
-
-int tegra_core_process_id(void)
-{
-	int core_process_id;
-	u32 reg = fuse_readl(FUSE_SPARE_BIT);
-	core_process_id = (reg >> 12) & 3;
-	return core_process_id;
-}
diff --git a/arch/arm/mach-tegra/fuse.h b/arch/arm/mach-tegra/fuse.h
index 584b2e27dbd..d65d2abf803 100644
--- a/arch/arm/mach-tegra/fuse.h
+++ b/arch/arm/mach-tegra/fuse.h
@@ -1,6 +1,4 @@
 /*
- * arch/arm/mach-tegra/fuse.c
- *
  * Copyright (C) 2010 Google, Inc.
  *
  * Author:
@@ -17,8 +15,34 @@
  *
  */
 
+#ifndef __MACH_TEGRA_FUSE_H
+#define __MACH_TEGRA_FUSE_H
+
+enum tegra_revision {
+	TEGRA_REVISION_UNKNOWN = 0,
+	TEGRA_REVISION_A01,
+	TEGRA_REVISION_A02,
+	TEGRA_REVISION_A03,
+	TEGRA_REVISION_A03p,
+	TEGRA_REVISION_A04,
+	TEGRA_REVISION_MAX,
+};
+
+#define SKU_ID_T20	8
+#define SKU_ID_T25SE	20
+#define SKU_ID_AP25	23
+#define SKU_ID_T25	24
+#define SKU_ID_AP25E	27
+#define SKU_ID_T25E	28
+
+extern int tegra_sku_id;
+extern int tegra_cpu_process_id;
+extern int tegra_core_process_id;
+extern enum tegra_revision tegra_revision;
+
+extern int tegra_bct_strapping;
+
 unsigned long long tegra_chip_uid(void);
-int tegra_sku_id(void);
-int tegra_cpu_process_id(void);
-int tegra_core_process_id(void);
 void tegra_init_fuse(void);
+
+#endif
diff --git a/arch/arm/mach-tegra/include/mach/debug-macro.S b/arch/arm/mach-tegra/include/mach/debug-macro.S
index 619abc63aee..90069abd37b 100644
--- a/arch/arm/mach-tegra/include/mach/debug-macro.S
+++ b/arch/arm/mach-tegra/include/mach/debug-macro.S
@@ -1,11 +1,17 @@
 /*
  * arch/arm/mach-tegra/include/mach/debug-macro.S
  *
- * Copyright (C) 2010 Google, Inc.
+ * Copyright (C) 2010,2011 Google, Inc.
+ * Copyright (C) 2011-2012 NVIDIA CORPORATION. All Rights Reserved.
  *
  * Author:
  *	Colin Cross <ccross@google.com>
  *	Erik Gilling <konkers@google.com>
+ *	Doug Anderson <dianders@chromium.org>
+ *	Stephen Warren <swarren@nvidia.com>
+ *
+ * Portions based on mach-omap2's debug-macro.S
+ * Copyright (C) 1994-1999 Russell King
  *
  * This software is licensed under the terms of the GNU General Public
  * License version 2, as published by the Free Software Foundation, and
@@ -18,18 +24,78 @@
  *
  */
 
+#include <linux/serial_reg.h>
+
 #include <mach/io.h>
 #include <mach/iomap.h>
+#include <mach/irammap.h>
+
+		.macro  addruart, rp, rv, tmp
+		adr	\rp, 99f		@ actual addr of 99f
+		ldr	\rv, [\rp]		@ linked addr is stored there
+		sub	\rv, \rv, \rp		@ offset between the two
+		ldr	\rp, [\rp, #4]		@ linked tegra_uart_config
+		sub	\tmp, \rp, \rv		@ actual tegra_uart_config
+		ldr	\rp, [\tmp]		@ Load tegra_uart_config
+		cmp	\rp, #1			@ needs intitialization?
+		bne	100f			@ no; go load the addresses
+		mov	\rv, #0			@ yes; record init is done
+		str	\rv, [\tmp]
+		mov	\rp, #TEGRA_IRAM_BASE	@ See if cookie is in IRAM
+		ldr	\rv, [\rp, #TEGRA_IRAM_DEBUG_UART_OFFSET]
+		movw	\rp, #TEGRA_IRAM_DEBUG_UART_COOKIE & 0xffff
+		movt	\rp, #TEGRA_IRAM_DEBUG_UART_COOKIE >> 16
+		cmp	\rv, \rp		@ Cookie present?
+		bne	100f			@ No, use default UART
+		mov	\rp, #TEGRA_IRAM_BASE	@ Load UART address from IRAM
+		ldr	\rv, [\rp, #TEGRA_IRAM_DEBUG_UART_OFFSET + 4]
+		str	\rv, [\tmp, #4]		@ Store in tegra_uart_phys
+		sub	\rv, \rv, #IO_APB_PHYS	@ Calculate virt address
+		add	\rv, \rv, #IO_APB_VIRT
+		str	\rv, [\tmp, #8]		@ Store in tegra_uart_virt
+		b	100f
+
+		.align
+99:		.word	.
+		.word	tegra_uart_config
+		.ltorg
+
+100:		ldr	\rp, [\tmp, #4]		@ Load tegra_uart_phys
+		ldr	\rv, [\tmp, #8]		@ Load tegra_uart_virt
+		.endm
+
+#define UART_SHIFT 2
+
+/*
+ * Code below is swiped from <asm/hardware/debug-8250.S>, but add an extra
+ * check to make sure that we aren't in the CONFIG_TEGRA_DEBUG_UART_NONE case.
+ * We use the fact that all 5 valid UART addresses all have something in the
+ * 2nd-to-lowest byte.
+ */
 
-	.macro  addruart, rp, rv, tmp
-        ldr     \rp, =IO_APB_PHYS       @ physical
-        ldr     \rv, =IO_APB_VIRT        @ virtual
-	orr	\rp, \rp, #(TEGRA_DEBUG_UART_BASE & 0xFF)
-	orr	\rp, \rp, #(TEGRA_DEBUG_UART_BASE & 0xFF00)
-	orr	\rv, \rv, #(TEGRA_DEBUG_UART_BASE & 0xFF)
-	orr	\rv, \rv, #(TEGRA_DEBUG_UART_BASE & 0xFF00)
-	.endm
+		.macro	senduart, rd, rx
+		tst	\rx, #0x0000ff00
+		strneb	\rd, [\rx, #UART_TX << UART_SHIFT]
+1001:
+		.endm
 
-#define UART_SHIFT	2
-#include <asm/hardware/debug-8250.S>
+		.macro	busyuart, rd, rx
+		tst	\rx, #0x0000ff00
+		beq	1002f
+1001:		ldrb	\rd, [\rx, #UART_LSR << UART_SHIFT]
+		and	\rd, \rd, #UART_LSR_TEMT | UART_LSR_THRE
+		teq	\rd, #UART_LSR_TEMT | UART_LSR_THRE
+		bne	1001b
+1002:
+		.endm
 
+		.macro	waituart, rd, rx
+#ifdef FLOW_CONTROL
+		tst	\rx, #0x0000ff00
+		beq	1002f
+1001:		ldrb	\rd, [\rx, #UART_MSR << UART_SHIFT]
+		tst	\rd, #UART_MSR_CTS
+		beq	1001b
+1002:
+#endif
+		.endm
diff --git a/arch/arm/mach-tegra/include/mach/gpio-tegra.h b/arch/arm/mach-tegra/include/mach/gpio-tegra.h
index 87d37fdf508..6140820555e 100644
--- a/arch/arm/mach-tegra/include/mach/gpio-tegra.h
+++ b/arch/arm/mach-tegra/include/mach/gpio-tegra.h
@@ -25,8 +25,6 @@
 
 #define TEGRA_NR_GPIOS		INT_GPIO_NR
 
-#define TEGRA_GPIO_TO_IRQ(gpio) (INT_GPIO_BASE + (gpio))
-
 struct tegra_gpio_table {
 	int	gpio;	/* GPIO number */
 	bool	enable;	/* Enable for GPIO at init? */
diff --git a/arch/arm/mach-tegra/include/mach/irammap.h b/arch/arm/mach-tegra/include/mach/irammap.h
new file mode 100644
index 00000000000..0cbe6326185
--- /dev/null
+++ b/arch/arm/mach-tegra/include/mach/irammap.h
@@ -0,0 +1,35 @@
+/*
+ * Copyright (c) 2012, NVIDIA CORPORATION.  All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __MACH_TEGRA_IRAMMAP_H
+#define __MACH_TEGRA_IRAMMAP_H
+
+#include <asm/sizes.h>
+
+/* The first 1K of IRAM is permanently reserved for the CPU reset handler */
+#define TEGRA_IRAM_RESET_HANDLER_OFFSET	0
+#define TEGRA_IRAM_RESET_HANDLER_SIZE	SZ_1K
+
+/*
+ * These locations are written to by uncompress.h, and read by debug-macro.S.
+ * The first word holds the cookie value if the data is valid. The second
+ * word holds the UART physical address.
+ */
+#define TEGRA_IRAM_DEBUG_UART_OFFSET	SZ_1K
+#define TEGRA_IRAM_DEBUG_UART_SIZE	8
+#define TEGRA_IRAM_DEBUG_UART_COOKIE	0x55415254
+
+#endif
diff --git a/arch/arm/mach-tegra/include/mach/uncompress.h b/arch/arm/mach-tegra/include/mach/uncompress.h
index 4e8323770c7..5a440f315e5 100644
--- a/arch/arm/mach-tegra/include/mach/uncompress.h
+++ b/arch/arm/mach-tegra/include/mach/uncompress.h
@@ -2,10 +2,14 @@
  * arch/arm/mach-tegra/include/mach/uncompress.h
  *
  * Copyright (C) 2010 Google, Inc.
+ * Copyright (C) 2011 Google, Inc.
+ * Copyright (C) 2011-2012 NVIDIA CORPORATION. All Rights Reserved.
  *
  * Author:
  *	Colin Cross <ccross@google.com>
  *	Erik Gilling <konkers@google.com>
+ *	Doug Anderson <dianders@chromium.org>
+ *	Stephen Warren <swarren@nvidia.com>
  *
  * This software is licensed under the terms of the GNU General Public
  * License version 2, as published by the Free Software Foundation, and
@@ -25,36 +29,130 @@
 #include <linux/serial_reg.h>
 
 #include <mach/iomap.h>
+#include <mach/irammap.h>
+
+#define BIT(x) (1 << (x))
+#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0]))
+
+#define DEBUG_UART_SHIFT 2
+
+volatile u8 *uart;
 
 static void putc(int c)
 {
-	volatile u8 *uart = (volatile u8 *)TEGRA_DEBUG_UART_BASE;
-	int shift = 2;
-
 	if (uart == NULL)
 		return;
 
-	while (!(uart[UART_LSR << shift] & UART_LSR_THR