arm64: mvebu: a37xx: improve code determining memory info structures

Currently on Armada-37xx the mem_map structure is statically defined to
map first 2 GB of memory as RAM region, and system registers and PCIe
region device region.

This is insufficient for when there is more RAM or when for example the
PCIe windows is mapped to another address by the CPU Address Decoder.
In the case when the board has 4 GB RAM, on some boards the ARM Trusted
Firmware can move the PCIe window to another address, in order to
maximize possible usable RAM.

Also the dram_init and dram_init_banksize looks for information in
device-tree, and therefore different device trees are needed for boards
with different RAM sizes.

Therefore we add code that looks at how the ARM Trusted Firmware has
configured the CPU Address Decoder windows, and then we update the
mem_map structure and compute gd->ram_size and gd->bd->bi_dram bank
base addresses and sizes accordingly.

Signed-off-by: Marek Behún <marek.behun@nic.cz>
Reviewed-by: Stefan Roese <sr@denx.de>

3 files changed, 235 insertions, 26 deletions

diff --git a/arch/arm/mach-mvebu/arm64-common.c b/arch/arm/mach-mvebu/arm64-common.c
index 244ea49d8a3..34cc0479a8b 100644
--- a/arch/arm/mach-mvebu/arm64-common.c
+++ b/arch/arm/mach-mvebu/arm64-common.c
@@ -49,6 +49,8 @@ __weak int dram_init_banksize(void)
 {
 	if (CONFIG_IS_ENABLED(ARMADA_8K))
 		return a8k_dram_init_banksize();
+	else if (CONFIG_IS_ENABLED(ARMADA_3700))
+		return a3700_dram_init_banksize();
 	else
 		return fdtdec_setup_memory_banksize();
 }
@@ -61,6 +63,9 @@ __weak int dram_init(void)
 			return 0;
 	}
 
+	if (CONFIG_IS_ENABLED(ARMADA_3700))
+		return a3700_dram_init();
+
 	if (fdtdec_setup_mem_size_base() != 0)
 		return -EINVAL;
 
diff --git a/arch/arm/mach-mvebu/armada3700/cpu.c b/arch/arm/mach-mvebu/armada3700/cpu.c
index c83268181b9..959a909d8af 100644
--- a/arch/arm/mach-mvebu/armada3700/cpu.c
+++ b/arch/arm/mach-mvebu/armada3700/cpu.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0+
 /*
  * Copyright (C) 2016 Stefan Roese <sr@denx.de>
+ * Copyright (C) 2020 Marek Behun <marek.behun@nic.cz>
  */
 
 #include <common.h>
@@ -13,6 +14,7 @@
 #include <asm/arch/cpu.h>
 #include <asm/arch/soc.h>
 #include <asm/armv8/mmu.h>
+#include <sort.h>
 
 /* Armada 3700 */
 #define MVEBU_GPIO_NB_REG_BASE		(MVEBU_REGISTER(0x13800))
@@ -26,39 +28,237 @@
 #define MVEBU_NB_WARM_RST_REG		(MVEBU_GPIO_NB_REG_BASE + 0x40)
 #define MVEBU_NB_WARM_RST_MAGIC_NUM	0x1d1e
 
-static struct mm_region mvebu_mem_map[] = {
-	{
-		/* RAM */
-		.phys = 0x0UL,
-		.virt = 0x0UL,
-		.size = 0x80000000UL,
-		.attrs = PTE_BLOCK_MEMTYPE(MT_NORMAL) |
-			 PTE_BLOCK_INNER_SHARE
-	},
+/* Armada 3700 CPU Address Decoder registers */
+#define MVEBU_CPU_DEC_WIN_REG_BASE	(size_t)(MVEBU_REGISTER(0xcf00))
+#define MVEBU_CPU_DEC_WIN_CTRL(w) \
+	(MVEBU_CPU_DEC_WIN_REG_BASE + ((w) << 4))
+#define MVEBU_CPU_DEC_WIN_CTRL_EN	BIT(0)
+#define MVEBU_CPU_DEC_WIN_CTRL_TGT_MASK	0xf
+#define MVEBU_CPU_DEC_WIN_CTRL_TGT_OFFS	4
+#define MVEBU_CPU_DEC_WIN_CTRL_TGT_DRAM	0
+#define MVEBU_CPU_DEC_WIN_CTRL_TGT_PCIE	2
+#define MVEBU_CPU_DEC_WIN_SIZE(w)	(MVEBU_CPU_DEC_WIN_CTRL(w) + 0x4)
+#define MVEBU_CPU_DEC_WIN_BASE(w)	(MVEBU_CPU_DEC_WIN_CTRL(w) + 0x8)
+#define MVEBU_CPU_DEC_WIN_REMAP(w)	(MVEBU_CPU_DEC_WIN_CTRL(w) + 0xc)
+#define MVEBU_CPU_DEC_WIN_GRANULARITY	16
+#define MVEBU_CPU_DEC_WINS		5
+
+#define MAX_MEM_MAP_REGIONS		(MVEBU_CPU_DEC_WINS + 2)
+
+#define A3700_PTE_BLOCK_NORMAL \
+	(PTE_BLOCK_MEMTYPE(MT_NORMAL) | PTE_BLOCK_INNER_SHARE)
+#define A3700_PTE_BLOCK_DEVICE \
+	(PTE_BLOCK_MEMTYPE(MT_DEVICE_NGNRNE) | PTE_BLOCK_NON_SHARE)
+
+DECLARE_GLOBAL_DATA_PTR;
+
+static struct mm_region mvebu_mem_map[MAX_MEM_MAP_REGIONS] = {
 	{
-		/* SRAM, MMIO regions */
-		.phys = 0xd0000000UL,
-		.virt = 0xd0000000UL,
+		/*
+		 * SRAM, MMIO regions
+		 * Don't remove this, a3700_build_mem_map needs it.
+		 */
+		.phys = SOC_REGS_PHY_BASE,
+		.virt = SOC_REGS_PHY_BASE,
 		.size = 0x02000000UL,	/* 32MiB internal registers */
-		.attrs = PTE_BLOCK_MEMTYPE(MT_DEVICE_NGNRNE) |
-			 PTE_BLOCK_NON_SHARE
-	},
-	{
-		/* PCI regions */
-		.phys = 0xe8000000UL,
-		.virt = 0xe8000000UL,
-		.size = 0x02000000UL,	/* 32MiB master PCI space */
-		.attrs = PTE_BLOCK_MEMTYPE(MT_DEVICE_NGNRNE) |
-			 PTE_BLOCK_NON_SHARE
+		.attrs = A3700_PTE_BLOCK_DEVICE
 	},
-	{
-		/* List terminator */
-		0,
-	}
 };
 
 struct mm_region *mem_map = mvebu_mem_map;
 
+static int get_cpu_dec_win(int win, u32 *tgt, u32 *base, u32 *size)
+{
+	u32 reg;
+
+	reg = readl(MVEBU_CPU_DEC_WIN_CTRL(win));
+	if (!(reg & MVEBU_CPU_DEC_WIN_CTRL_EN))
+		return -1;
+
+	if (tgt) {
+		reg >>= MVEBU_CPU_DEC_WIN_CTRL_TGT_OFFS;
+		reg &= MVEBU_CPU_DEC_WIN_CTRL_TGT_MASK;
+		*tgt = reg;
+	}
+
+	if (base) {
+		reg = readl(MVEBU_CPU_DEC_WIN_BASE(win));
+		*base = reg << MVEBU_CPU_DEC_WIN_GRANULARITY;
+	}
+
+	if (size) {
+		/*
+		 * Window size is encoded as the number of 1s from LSB to MSB,
+		 * followed by 0s. The number of 1s specifies the size in 64 KiB
+		 * granularity.
+		 */
+		reg = readl(MVEBU_CPU_DEC_WIN_SIZE(win));
+		*size = ((reg + 1) << MVEBU_CPU_DEC_WIN_GRANULARITY);
+	}
+
+	return 0;
+}
+
+/*
+ * Builds mem_map according to CPU Address Decoder settings, which were set by
+ * the TIMH image on the Cortex-M3 secure processor, or by ARM Trusted Firmware
+ */
+static void build_mem_map(void)
+{
+	int win, region;
+
+	region = 1;
+	for (win = 0; win < MVEBU_CPU_DEC_WINS; ++win) {
+		u32 base, tgt, size;
+		u64 attrs;
+
+		/* skip disabled windows */
+		if (get_cpu_dec_win(win, &tgt, &base, &size))
+			continue;
+
+		if (tgt == MVEBU_CPU_DEC_WIN_CTRL_TGT_DRAM)
+			attrs = A3700_PTE_BLOCK_NORMAL;
+		else if (tgt == MVEBU_CPU_DEC_WIN_CTRL_TGT_PCIE)
+			attrs = A3700_PTE_BLOCK_DEVICE;
+		else
+			/* skip windows with other targets */
+			continue;
+
+		mvebu_mem_map[region].phys = base;
+		mvebu_mem_map[region].virt = base;
+		mvebu_mem_map[region].size = size;
+		mvebu_mem_map[region].attrs = attrs;
+		++region;
+	}
+
+	/* add list terminator */
+	mvebu_mem_map[region].size = 0;
+	mvebu_mem_map[region].attrs = 0;
+}
+
+void enable_caches(void)
+{
+	build_mem_map();
+
+	icache_enable();
+	dcache_enable();
+}
+
+int a3700_dram_init(void)
+{
+	int win;
+
+	gd->ram_size = 0;
+	for (win = 0; win < MVEBU_CPU_DEC_WINS; ++win) {
+		u32 base, tgt, size;
+
+		/* skip disabled windows */
+		if (get_cpu_dec_win(win, &tgt, &base, &size))
+			continue;
+
+		/* skip non-DRAM windows */
+		if (tgt != MVEBU_CPU_DEC_WIN_CTRL_TGT_DRAM)
+			continue;
+
+		/*
+		 * It is possible that one image was built for boards with
+		 * different RAM sizes, for example 512 MiB and 1 GiB.
+		 * We therefore try to determine the actual RAM size in the
+		 * window with get_ram_size.
+		 */
+		gd->ram_size += get_ram_size((void *)(size_t)base, size);
+	}
+
+	return 0;
+}
+
+struct a3700_dram_window {
+	size_t base, size;
+};
+
+static int dram_win_cmp(const void *a, const void *b)
+{
+	size_t ab, bb;
+
+	ab = ((const struct a3700_dram_window *)a)->base;
+	bb = ((const struct a3700_dram_window *)b)->base;
+
+	if (ab < bb)
+		return -1;
+	else if (ab > bb)
+		return 1;
+	else
+		return 0;
+}
+
+int a3700_dram_init_banksize(void)
+{
+	struct a3700_dram_window dram_wins[MVEBU_CPU_DEC_WINS];
+	int bank, win, ndram_wins;
+	u32 last_end;
+	size_t size;
+
+	ndram_wins = 0;
+	for (win = 0; win < MVEBU_CPU_DEC_WINS; ++win) {
+		u32 base, tgt, size;
+
+		/* skip disabled windows */
+		if (get_cpu_dec_win(win, &tgt, &base, &size))
+			continue;
+
+		/* skip non-DRAM windows */
+		if (tgt != MVEBU_CPU_DEC_WIN_CTRL_TGT_DRAM)
+			continue;
+
+		dram_wins[win].base = base;
+		dram_wins[win].size = size;
+		++ndram_wins;
+	}
+
+	qsort(dram_wins, ndram_wins, sizeof(dram_wins[0]), dram_win_cmp);
+
+	bank = 0;
+	last_end = -1;
+
+	for (win = 0; win < ndram_wins; ++win) {
+		/* again determining actual RAM size as in a3700_dram_init */
+		size = get_ram_size((void *)dram_wins[win].base,
+				    dram_wins[win].size);
+
+		/*
+		 * Check if previous window ends as the current starts. If yes,
+		 * merge these windows into one "bank". This is possible by this
+		 * simple check thanks to mem_map regions being qsorted in
+		 * build_mem_map.
+		 */
+		if (last_end == dram_wins[win].base) {
+			gd->bd->bi_dram[bank - 1].size += size;
+			last_end += size;
+		} else {
+			if (bank == CONFIG_NR_DRAM_BANKS) {
+				printf("Need more CONFIG_NR_DRAM_BANKS\n");
+				return -ENOBUFS;
+			}
+
+			gd->bd->bi_dram[bank].start = dram_wins[win].base;
+			gd->bd->bi_dram[bank].size = size;
+			last_end = dram_wins[win].base + size;
+			++bank;
+		}
+	}
+
+	/*
+	 * If there is more place for DRAM BANKS definitions than needed, fill
+	 * the rest with zeros.
+	 */
+	for (; bank < CONFIG_NR_DRAM_BANKS; ++bank) {
+		gd->bd->bi_dram[bank].start = 0;
+		gd->bd->bi_dram[bank].size = 0;
+	}
+
+	return 0;
+}
+
 void reset_cpu(ulong ignored)
 {
 	/*
diff --git a/arch/arm/mach-mvebu/include/mach/cpu.h b/arch/arm/mach-mvebu/include/mach/cpu.h
index 16d825220e0..3bb541b6ca1 100644
--- a/arch/arm/mach-mvebu/include/mach/cpu.h
+++ b/arch/arm/mach-mvebu/include/mach/cpu.h
@@ -176,6 +176,10 @@ static inline void mv_rtc_config(void) {}
 u64 a8k_dram_scan_ap_sz(void);
 int a8k_dram_init_banksize(void);
 
+/* A3700 dram functions */
+int a3700_dram_init(void);
+int a3700_dram_init_banksize(void);
+
 /*
  * get_ref_clk
  *