armv8: Add mmu support

Add support for initializing and enabling mmu for armv8. Using 64KiB granule and
33 bits per VA, thus total VA address space is 6GiB. PA Range is 64GiB. Makes
use of memrange library to get a list of all the mmap regions from the SoC to
initialize XLAT table.
Currently, all calculations in mmu.h are based on the assumptions that max 33
bits are used in VA and granule size is 64KiB. Changes in these assumptions will
have to reflect in the dependent calculations as well.

BUG=chrome-os-partner:30688
BRANCH=None
TEST=Compiles rush successfully and boots until "payload not found". Goes past
all the earlier alignment errors.

Original-Change-Id: Iac1df15f0b81dcf64484a56b94f51357bcd67cc2
Original-Signed-off-by: Furquan Shaikh <furquan@google.com>
Original-Reviewed-on: https://chromium-review.googlesource.com/208761
Original-Tested-by: Furquan Shaikh <furquan@chromium.org>
Original-Reviewed-by: Aaron Durbin <adurbin@chromium.org>
Original-Commit-Queue: Furquan Shaikh <furquan@chromium.org>
(cherry picked from commit 6fe96360c03342115f849074f9e45a2c4e210705)
Signed-off-by: Marc Jones <marc.jones@se-eng.com>

Change-Id: I5360a3be95f198bd0b4f79b62f31228cc7a9c285
Reviewed-on: http://review.coreboot.org/8646
Reviewed-by: Furquan Shaikh <furquan@google.com>
Tested-by: build bot (Jenkins)

3 files changed, 479 insertions, 0 deletions

diff --git a/src/arch/arm64/armv8/Makefile.inc b/src/arch/arm64/armv8/Makefile.inc
index ca4562b1a8..4cbb6e90c0 100644
--- a/src/arch/arm64/armv8/Makefile.inc
+++ b/src/arch/arm64/armv8/Makefile.inc
@@ -69,6 +69,7 @@ ramstage-y += cache.c
 ramstage-y += cpu.S
 ramstage-y += exception.c
 ramstage-y += exception_asm.S
+ramstage-y += mmu.c
 
 ramstage-c-ccopts += $(armv8_flags)
 ramstage-S-ccopts += $(armv8_asm_flags)
diff --git a/src/arch/arm64/armv8/mmu.c b/src/arch/arm64/armv8/mmu.c
new file mode 100644
index 0000000000..e1f088e102
--- /dev/null
+++ b/src/arch/arm64/armv8/mmu.c
@@ -0,0 +1,313 @@
+/*
+ * This file is part of the coreboot project.
+ *
+ * Copyright 2014 Google Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. The name of the author may not be used to endorse or promote products
+ *    derived from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED.  IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE.
+ */
+
+#include <stdlib.h>
+#include <stdint.h>
+#include <string.h>
+
+#include <cbmem.h>
+#include <console/console.h>
+
+#include <memrange.h>
+#include <arch/mmu.h>
+#include <arch/lib_helpers.h>
+#include <arch/cache.h>
+
+/* Maximum number of XLAT Tables available based on ttb buffer size */
+static unsigned int max_tables;
+/* Address of ttb buffer */
+static uint64_t *xlat_addr;
+
+static const uint64_t level_to_addr_mask[] = {
+	L1_ADDR_MASK,
+	L2_ADDR_MASK,
+	L3_ADDR_MASK,
+};
+
+static const uint64_t level_to_addr_shift[] = {
+	L1_ADDR_SHIFT,
+	L2_ADDR_SHIFT,
+	L3_ADDR_SHIFT,
+};
+
+/* Func : get_block_attr
+ * Desc : Get block descriptor attributes based on the value of tag in memrange
+ * region
+ */
+static uint64_t get_block_attr(unsigned long tag)
+{
+	uint64_t attr;
+
+	attr = (tag & MA_NS)? BLOCK_NS : 0;
+	attr |= (tag & MA_RO)? BLOCK_AP_RO : BLOCK_AP_RW;
+	attr |= BLOCK_ACCESS;
+	attr |= (tag & MA_MEM)? (BLOCK_INDEX_MEM_NORMAL << BLOCK_INDEX_SHIFT) :
+		(BLOCK_INDEX_MEM_DEV_NGNRNE << BLOCK_INDEX_SHIFT);
+
+	return attr;
+}
+
+/* Func : get_index_from_addr
+ * Desc : Get index into table at a given level using appropriate bits from the
+ * base address
+ */
+static uint64_t get_index_from_addr(uint64_t addr, uint8_t level)
+{
+	uint64_t mask = level_to_addr_mask[level-1];
+	uint8_t shift = level_to_addr_shift[level-1];
+
+	return ((addr & mask) >> shift);
+}
+
+/* Func : table_desc_valid
+ * Desc : Check if a table entry contains valid desc
+ */
+static uint64_t table_desc_valid(uint64_t desc)
+{
+	return((desc & TABLE_DESC) == TABLE_DESC);
+}
+
+/* Func : get_new_table
+ * Desc : Return the next free XLAT table from ttb buffer
+ */
+static uint64_t *get_new_table(void)
+{
+	static int free_idx = 1;
+	uint64_t *new;
+
+	if (free_idx >= max_tables) {
+		printk(BIOS_ERR,"ARM64 MMU: No free table\n");
+		return NULL;
+	}
+
+	new = (uint64_t*)((unsigned char *)xlat_addr + free_idx * GRANULE_SIZE);
+	free_idx++;
+
+	memset(new, 0, GRANULE_SIZE);
+
+	return new;
+}
+
+/* Func : get_table_from_desc
+ * Desc : Get next level table address from table descriptor
+ */
+static uint64_t *get_table_from_desc(uint64_t desc)
+{
+	uint64_t *ptr = (uint64_t*)(desc & XLAT_TABLE_MASK);
+	return ptr;
+}
+
+/* Func: get_next_level_table
+ * Desc: Check if the table entry is a valid descriptor. If not, allocate new
+ * table, update the entry and return the table addr. If valid, return the addr
+ */
+static uint64_t *get_next_level_table(uint64_t *ptr)
+{
+	uint64_t desc = *ptr;
+
+	if (!table_desc_valid(desc)) {
+		uint64_t *new_table = get_new_table();
+		if (new_table == NULL)
+			return NULL;
+		desc = ((uint64_t)new_table) | TABLE_DESC;
+		*ptr = desc;
+	}
+	return get_table_from_desc(desc);
+}
+
+/* Func : init_xlat_table
+ * Desc : Given a base address and size, it identifies the indices within
+ * different level XLAT tables which map the given base addr. Similar to table
+ * walk, except that all invalid entries during the walk are updated
+ * accordingly. On success, it returns the size of the block/page addressed by
+ * the final table
+ */
+static uint64_t init_xlat_table(uint64_t base_addr,
+				uint64_t size,
+				uint64_t tag)
+{
+	uint64_t l1_index = get_index_from_addr(base_addr,1);
+	uint64_t l2_index = get_index_from_addr(base_addr,2);
+	uint64_t l3_index = get_index_from_addr(base_addr,3);
+	uint64_t *table = xlat_addr;
+	uint64_t desc;
+	uint64_t attr = get_block_attr(tag);
+
+	/* L1 table lookup */
+	/* If VA has bits more than 41, lookup starts at L1 */
+	if (l1_index) {
+		table = get_next_level_table(&table[l1_index]);
+		if (!table)
+			return 0;
+	}
+
+	/* L2 table lookup */
+	/* If lookup was performed at L1, L2 table addr is obtained from L1 desc
+	   else, lookup starts at ttbr address */
+	if (!l3_index && (size >= L2_XLAT_SIZE)) {
+		/* If block address is aligned and size is greater than or equal
+		   to 512MiB i.e. size addressed by each L2 entry, we can
+		   directly store a block desc */
+		desc = base_addr | BLOCK_DESC | attr;
+		table[l2_index] = desc;
+		/* L3 lookup is not required */
+		return L2_XLAT_SIZE;
+	} else {
+		/* L2 entry stores a table descriptor */
+		table = get_next_level_table(&table[l2_index]);
+		if (!table)
+			return 0;
+	}
+
+	/* L3 table lookup */
+	desc = base_addr | PAGE_DESC | attr;
+	table[l3_index] = desc;
+	return L3_XLAT_SIZE;
+}
+
+/* Func : sanity_check
+ * Desc : Check if the address is aligned and size is atleast the granule size
+ */
+static uint64_t sanity_check(uint64_t addr,
+			     uint64_t size)
+{
+	/* Address should be atleast 64 KiB aligned */
+	if (addr & GRANULE_SIZE_MASK)
+		return 1;
+
+	/* Size should be atleast granule size */
+	if (size < GRANULE_SIZE)
+		return 1;
+
+	return 0;
+}
+
+/* Func : init_mmap_entry
+ * Desc : For each mmap entry, this function calls init_xlat_table with the base
+ * address. Based on size returned from init_xlat_table, base_addr is updated
+ * and subsequent calls are made for initializing the xlat table until the whole
+ * region is initialized.
+ */
+static void init_mmap_entry(struct range_entry *r)
+{
+	uint64_t base_addr = range_entry_base(r);
+	uint64_t size      = range_entry_size(r);
+	uint64_t tag       = range_entry_tag(r);
+	uint64_t temp_size = size;
+
+	while (temp_size) {
+		uint64_t ret;
+
+		if (sanity_check(base_addr,temp_size)) {
+			printk(BIOS_ERR, "ARM64 MMU: sanity check failed\n");
+			return;
+		}
+
+		ret = init_xlat_table(base_addr + (size - temp_size),
+				      temp_size,tag);
+
+		if (ret == 0)
+			return;
+
+		temp_size -= ret;
+	}
+}
+
+/* Func : mmu_init
+ * Desc : Initialize mmu based on the mmap_ranges passed. ttb_buffer is used as
+ * the base address for xlat tables. ttb_size defines the max number of tables
+ * that can be used
+ */
+void mmu_init(struct memranges *mmap_ranges,
+	      uint64_t *ttb_buffer,
+	      uint64_t ttb_size)
+{
+	struct range_entry *mmap_entry;
+
+	if (sanity_check((uint64_t)ttb_buffer, ttb_size)) {
+		printk(BIOS_ERR, "ARM64: Sanity failed for ttb\n");
+		return;
+	}
+
+	memset((void*)ttb_buffer, 0, GRANULE_SIZE);
+	max_tables = (ttb_size >> GRANULE_SIZE_SHIFT);
+	xlat_addr = ttb_buffer;
+
+	printk(BIOS_DEBUG, "ARM64: TTB_BUFFER: 0x%p Max Tables: %d\n",
+	       (void*)xlat_addr, max_tables);
+
+	memranges_each_entry(mmap_entry, mmap_ranges) {
+		init_mmap_entry(mmap_entry);
+	}
+	printk(BIOS_DEBUG, "ARM64: MMU init done\n");
+}
+
+static uint32_t is_mmu_enabled(void)
+{
+	uint32_t sctlr;
+
+	sctlr = raw_read_sctlr_el3();
+
+	return (sctlr & SCTLR_M);
+}
+
+void mmu_enable(uint64_t ttbr)
+{
+	uint32_t sctlr;
+
+	/* Initialize MAIR indices */
+	raw_write_mair_el3(MAIR_ATTRIBUTES);
+
+	/* Invalidate TLBs */
+	tlbiall_el3();
+
+	/* Initialize TCR flags */
+	raw_write_tcr_el3(TCR_TOSZ | TCR_IRGN0_NM_WBWAC | TCR_ORGN0_NM_WBWAC |
+			  TCR_SH0_IS | TCR_TG0_64KB | TCR_PS_64GB |
+			  TCR_TBI_USED);
+
+	/* Initialize TTBR */
+	raw_write_ttbr0_el3(ttbr);
+
+	/* Ensure all translation table writes are committed before enabling MMU */
+	dsb();
+	isb();
+
+	/* Enable MMU */
+	sctlr = raw_read_sctlr_el3();
+	sctlr |= SCTLR_C | SCTLR_M | SCTLR_I;
+	raw_write_sctlr_el3(sctlr);
+
+	isb();
+
+	if (is_mmu_enabled())
+		printk(BIOS_DEBUG, "ARM64: MMU enable done\n");
+	else
+		printk(BIOS_DEBUG, "ARM64: MMU enable failed\n");
+}
diff --git a/src/arch/arm64/include/armv8/arch/mmu.h b/src/arch/arm64/include/armv8/arch/mmu.h
new file mode 100644
index 0000000000..f5f60a100c
--- /dev/null
+++ b/src/arch/arm64/include/armv8/arch/mmu.h
@@ -0,0 +1,165 @@
+/*
+ * This file is part of the coreboot project.
+ *
+ * Copyright 2014 Google Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
+ */
+
+#ifndef __ARCH_ARM64_MMU_H__
+#define __ARCH_ARM64_MMU_H__
+
+#include <memrange.h>
+
+/* IMPORTANT!!!!!!!
+ * Assumptions made:
+ * Granule size is 64KiB
+ * BITS per Virtual address is 33
+ * All the calculations for tables L1,L2 and L3 are based on these assumptions
+ * If these values are changed, recalculate the other macros as well
+ */
+
+
+/* Memory attributes for mmap regions
+ * These attributes act as tag values for memrange regions
+ */
+
+/* Normal memory / device */
+#define MA_MEM                     (1 << 0)
+#define MA_DEV                     (0 << 0)
+
+/* Secure / non-secure */
+#define MA_NS                      (1 << 1)
+#define MA_S                       (0 << 1)
+
+/* Read only / Read-write */
+#define MA_RO                      (1 << 2)
+#define MA_RW                      (0 << 2)
+
+/* Descriptor attributes */
+
+#define INVALID_DESC               0x0
+#define BLOCK_DESC                 0x1
+#define TABLE_DESC                 0x3
+#define PAGE_DESC                  0x3
+
+/* Block descriptor */
+#define BLOCK_NS                   (1 << 5)
+
+#define BLOCK_AP_RW                (0 << 7)
+#define BLOCK_AP_RO                (1 << 7)
+
+#define BLOCK_ACCESS               (1 << 10)
+
+/* XLAT Table Init Attributes */
+
+#define VA_START                   0x0
+/* If BITS_PER_VA or GRANULE_SIZE are changed, recalculate and change the
+   macros following them */
+#define BITS_PER_VA                33
+/* Granule size of 64KB is being used */
+#define GRANULE_SIZE_SHIFT         16
+#define GRANULE_SIZE               (1 << GRANULE_SIZE_SHIFT)
+#define XLAT_TABLE_MASK            ~(0xffffUL)
+#define GRANULE_SIZE_MASK          ((1 << 16) - 1)
+
+#define L1_ADDR_SHIFT              42
+#define L2_ADDR_SHIFT              29
+#define L3_ADDR_SHIFT              16
+
+#define L1_ADDR_MASK               (0UL << L1_ADDR_SHIFT)
+#define L2_ADDR_MASK               (0xfUL << L2_ADDR_SHIFT)
+#define L3_ADDR_MASK               (0x1fffUL << L3_ADDR_SHIFT)
+
+/* Dependent on BITS_PER_VA and GRANULE_SIZE */
+#define INIT_LEVEL                 2
+#define XLAT_MAX_LEVEL             3
+
+/* Each entry in XLAT table is 8 bytes */
+#define XLAT_ENTRY_SHIFT           3
+#define XLAT_ENTRY_SIZE            (1 << XLAT_ENTRY_SHIFT)
+
+#define XLAT_TABLE_SHIFT           GRANULE_SIZE_SHIFT
+#define XLAT_TABLE_SIZE            (1 << XLAT_TABLE_SHIFT)
+
+#define XLAT_NUM_ENTRIES_SHIFT     (XLAT_TABLE_SHIFT - XLAT_ENTRY_SHIFT)
+#define XLAT_NUM_ENTRIES           (1 << XLAT_NUM_ENTRIES_SHIFT)
+
+#define L3_XLAT_SIZE_SHIFT         (GRANULE_SIZE_SHIFT)
+#define L2_XLAT_SIZE_SHIFT         (GRANULE_SIZE_SHIFT + XLAT_NUM_ENTRIES_SHIFT)
+#define L1_XLAT_SIZE_SHIFT         (GRANULE_SIZE_SHIFT + XLAT_NUM_ENTRIES_SHIFT)
+
+/* These macros give the size of the region addressed by each entry of a xlat
+   table at any given level */
+#define L3_XLAT_SIZE               (1 << L3_XLAT_SIZE_SHIFT)
+#define L2_XLAT_SIZE               (1 << L2_XLAT_SIZE_SHIFT)
+#define L1_XLAT_SIZE               (1 << L1_XLAT_SIZE_SHIFT)
+
+/* Block indices required for MAIR */
+#define BLOCK_INDEX_MEM_DEV_NGNRNE 0
+#define BLOCK_INDEX_MEM_DEV_NGNRE  1
+#define BLOCK_INDEX_MEM_DEV_GRE    2
+#define BLOCK_INDEX_MEM_NORMAL_NC  3
+#define BLOCK_INDEX_MEM_NORMAL     4
+
+#define BLOCK_INDEX_SHIFT          2
+
+/* MAIR attributes */
+#define MAIR_ATTRIBUTES            ((0x00 << (BLOCK_INDEX_MEM_DEV_NGNRNE*8)) | \
+				    (0x04 << (BLOCK_INDEX_MEM_DEV_NGNRE*8))  | \
+				    (0x0c << (BLOCK_INDEX_MEM_DEV_GRE*8))    | \
+				    (0x44 << (BLOCK_INDEX_MEM_NORMAL_NC*8))  | \
+				    (0xffUL << (BLOCK_INDEX_MEM_NORMAL*8)))
+
+/* TCR attributes */
+#define TCR_TOSZ                   (64 - BITS_PER_VA)
+
+#define TCR_IRGN0_SHIFT            8
+#define TCR_IRGN0_NM_NC            (0x00 << TCR_IRGN0_SHIFT)
+#define TCR_IRGN0_NM_WBWAC         (0x01 << TCR_IRGN0_SHIFT)
+#define TCR_IRGN0_NM_WTC           (0x02 << TCR_IRGN0_SHIFT)
+#define TCR_IRGN0_NM_WBNWAC        (0x03 << TCR_IRGN0_SHIFT)
+
+#define TCR_ORGN0_SHIFT            10
+#define TCR_ORGN0_NM_NC            (0x00 << TCR_ORGN0_SHIFT)
+#define TCR_ORGN0_NM_WBWAC         (0x01 << TCR_ORGN0_SHIFT)
+#define TCR_ORGN0_NM_WTC           (0x02 << TCR_ORGN0_SHIFT)
+#define TCR_ORGN0_NM_WBNWAC        (0x03 << TCR_ORGN0_SHIFT)
+
+#define TCR_SH0_SHIFT              12
+#define TCR_SH0_NC                 (0x0 << TCR_SH0_SHIFT)
+#define TCR_SH0_OS                 (0x2 << TCR_SH0_SHIFT)
+#define TCR_SH0_IS                 (0x3 << TCR_SH0_SHIFT)
+
+#define TCR_TG0_SHIFT              14
+#define TCR_TG0_4KB                (0x0 << TCR_TG0_SHIFT)
+#define TCR_TG0_64KB               (0x1 << TCR_TG0_SHIFT)
+#define TCR_TG0_16KB               (0x2 << TCR_TG0_SHIFT)
+
+#define TCR_PS_SHIFT               16
+#define TCR_PS_4GB                 (0x0 << TCR_PS_SHIFT)
+#define TCR_PS_64GB                (0x1 << TCR_PS_SHIFT)
+#define TCR_PS_1TB                 (0x2 << TCR_PS_SHIFT)
+#define TCR_PS_4TB                 (0x3 << TCR_PS_SHIFT)
+#define TCR_PS_16TB                (0x4 << TCR_PS_SHIFT)
+#define TCR_PS_256TB               (0x5 << TCR_PS_SHIFT)
+
+#define TCR_TBI_SHIFT              20
+#define TCR_TBI_USED               (0x0 << TCR_TBI_SHIFT)
+#define TCR_TBI_IGNORED            (0x1 << TCR_TBI_SHIFT)
+
+void mmu_init(struct memranges *,uint64_t *,uint64_t);
+void mmu_enable(uint64_t);
+
+#endif // __ARCH_ARM64_MMU_H__