arm: mvebu: Fix moving internal registers

Commit 5bb2c550b11e ("arm: mvebu: Move internal registers in
arch_very_early_init() function") moved code from file cpu.c to lowlevel.c,
which moves Marvell internal registers from address INTREG_BASE_ADDR_REG to
SOC_REGS_PHY_BASE.

But the steps describing how to do it correctly were documented only in
older U-Boot versions and commit cefd764222ee ("arm: mvebu: Fix internal
register config on A38x") probably unintentionally removed important
details about MMU from code comments around.

Commit 5bb2c550b11e ("arm: mvebu: Move internal registers in
arch_very_early_init() function") implemented code movement according to
(now incomplete) comments which resulted in semi-broken code.

The result is that I-cache is currently disabled for all Armada 38x boards
and maybe there are some other (unreported / undetected) issues.

Reimplement it correctly. First flush all caches, then disable MMU and L2
cache and then move Marvell internal registers. There is no need to
explicitly disable I-cache.

After this change lzmadec command with lzma image of 0x7000000 bytes is
doing decompression just 5 seconds. Before this change it was 30 seconds.

To make lowlevel.S code more readable, extend asm/pl310.h header file to be
compatible with assembler and use macros from this file.

Fixes: 5bb2c550b11e ("arm: mvebu: Move internal registers in arch_very_early_init() function")
Signed-off-by: Pali Rohár <pali@kernel.org>
Signed-off-by: Marek Behún <kabel@kernel.org>
Reviewed-by: Stefan Roese <sr@denx.de>

3 files changed, 34 insertions, 15 deletions

diff --git a/arch/arm/include/asm/pl310.h b/arch/arm/include/asm/pl310.h
index f69e9e45f8..9d4cd68ee4 100644
--- a/arch/arm/include/asm/pl310.h
+++ b/arch/arm/include/asm/pl310.h
@@ -7,13 +7,12 @@
 #ifndef _PL310_H_
 #define _PL310_H_
 
-#include <linux/types.h>
-
 /* Register bit fields */
 #define PL310_AUX_CTRL_ASSOCIATIVITY_MASK	(1 << 16)
 #define L2X0_DYNAMIC_CLK_GATING_EN		(1 << 1)
 #define L2X0_STNDBY_MODE_EN			(1 << 0)
 #define L2X0_CTRL_EN				1
+#define L2X0_CTRL_OFF				0x100
 
 #define L310_SHARED_ATT_OVERRIDE_ENABLE		(1 << 22)
 #define L310_AUX_CTRL_DATA_PREFETCH_MASK	(1 << 28)
@@ -27,6 +26,10 @@
 #define L2X0_CACHE_ID_RTL_MASK          0x3f
 #define L2X0_CACHE_ID_RTL_R3P2          0x8
 
+#ifndef __ASSEMBLY__
+
+#include <linux/types.h>
+
 struct pl310_regs {
 	u32 pl310_cache_id;
 	u32 pl310_cache_type;
@@ -87,3 +90,5 @@ void pl310_inval_range(u32 start, u32 end);
 void pl310_clean_inval_range(u32 start, u32 end);
 
 #endif
+
+#endif
diff --git a/arch/arm/mach-mvebu/cpu.c b/arch/arm/mach-mvebu/cpu.c
index 77e403ba73..1f8cdf8744 100644
--- a/arch/arm/mach-mvebu/cpu.c
+++ b/arch/arm/mach-mvebu/cpu.c
@@ -445,19 +445,6 @@ static void setup_usb_phys(void)
  */
 int arch_cpu_init(void)
 {
-	struct pl310_regs *const pl310 =
-		(struct pl310_regs *)CONFIG_SYS_PL310_BASE;
-
-	if (!IS_ENABLED(CONFIG_ARMADA_XP)) {
-		/*
-		 * To fully release / unlock this area from cache, we need
-		 * to flush all caches and disable the L2 cache.
-		 */
-		icache_disable();
-		dcache_disable();
-		clrbits_le32(&pl310->pl310_ctrl, L2X0_CTRL_EN);
-	}
-
 	/*
 	 * We need to call mvebu_mbus_probe() before calling
 	 * update_sdram_window_sizes() as it disables all previously
diff --git a/arch/arm/mach-mvebu/lowlevel.S b/arch/arm/mach-mvebu/lowlevel.S
index b460382c6b..60c2072c35 100644
--- a/arch/arm/mach-mvebu/lowlevel.S
+++ b/arch/arm/mach-mvebu/lowlevel.S
@@ -3,6 +3,7 @@
 #include <config.h>
 #include <linux/linkage.h>
 #include <asm/system.h>
+#include <asm/pl310.h>
 
 ENTRY(arch_very_early_init)
 #ifdef CONFIG_ARMADA_38X
@@ -11,10 +12,36 @@ ENTRY(arch_very_early_init)
 	 * register address on Armada 38x. Without this the SDRAM
 	 * located at >= 0x4000.0000 is also not accessible, as its
 	 * still locked to cache.
+	 *
+	 * So to fully release / unlock this area from cache, we need
+	 * to first flush all caches, then disable the MMU and
+	 * disable the L2 cache.
 	 */
+
+	/* Invalidate L1 I/D */
+	mov	r0, #0			@ set up for MCR
+	mcr	p15, 0, r0, c8, c7, 0	@ invalidate TLBs
+	mcr	p15, 0, r0, c7, c5, 0	@ invalidate icache
+	mcr	p15, 0, r0, c7, c5, 6	@ invalidate BP array
+	mcr	p15, 0, r0, c7, c10, 4	@ DSB
+	mcr	p15, 0, r0, c7, c5, 4	@ ISB
+
+	/* Disable MMU */
 	mrc	p15, 0, r0, c1, c0, 0
 	bic	r0, #CR_M
 	mcr	p15, 0, r0, c1, c0, 0
+
+	/*
+	 * Disable L2 cache
+	 *
+	 * NOTE: Internal registers are still at address INTREG_BASE_ADDR_REG
+	 *       but CONFIG_SYS_PL310_BASE is already calculated from base
+	 *       address SOC_REGS_PHY_BASE.
+	 */
+	ldr	r1, =(CONFIG_SYS_PL310_BASE - SOC_REGS_PHY_BASE + INTREG_BASE_ADDR_REG)
+	ldr	r0, [r1, #L2X0_CTRL_OFF]
+	bic	r0, #L2X0_CTRL_EN
+	str	r0, [r1, #L2X0_CTRL_OFF]
 #endif
 
 	/* Move internal registers from INTREG_BASE_ADDR_REG to SOC_REGS_PHY_BASE */