[PATCH 3/3] ARM: always call dcache_invalidate_stale before enabling D-Cache

[Ahmad Fatoum]

dcache_invalidate_stale() needs to be executed prior to enabling the
MMU. This was so far guaranteed by __barebox_arm_entry() invoking it
prior to barebox_pbl_start(), which does mmu_early_enable().

As there's more boot time to be saved by calling mmu_early_enable()
earlier, some SoC support has already started calling mmu_early_enable()
prior to barebox_pbl_start(). Should this be extended to older CPUs like
Cortex-A9, we would introduce a regression as the data cache would not be
discarded prior to enabling it.

Avoid this failure mode altogether by having dcache_invalidate_stale()
precede the code that depends on it having run.

Signed-off-by: Ahmad Fatoum <a.fatoum at pengutronix.de>
---
 arch/arm/cpu/armv7r-mpu.c  |  1 +
 arch/arm/cpu/entry_ll_32.S |  7 -------
 arch/arm/cpu/entry_ll_64.S |  7 -------
 arch/arm/cpu/mmu_32.c      |  2 ++
 arch/arm/cpu/uncompress.c  | 12 ++++++++++--
 5 files changed, 13 insertions(+), 16 deletions(-)

diff --git a/arch/arm/cpu/armv7r-mpu.c b/arch/arm/cpu/armv7r-mpu.c
index d494aec583ef..7f43d617c251 100644
--- a/arch/arm/cpu/armv7r-mpu.c
+++ b/arch/arm/cpu/armv7r-mpu.c
@@ -34,6 +34,7 @@
 
 void armv7r_cache_enable(void)
 {
+	dcache_invalidate_stale();
 	set_cr(get_cr() | CR_C);
 }
 
diff --git a/arch/arm/cpu/entry_ll_32.S b/arch/arm/cpu/entry_ll_32.S
index eb1793b54e66..981722ab7b05 100644
--- a/arch/arm/cpu/entry_ll_32.S
+++ b/arch/arm/cpu/entry_ll_32.S
@@ -12,12 +12,5 @@
 .section .text.__barebox_arm_entry
 ENTRY(__barebox_arm_entry)
 	mov	sp, r3
-	mov	r4, r0
-	mov	r5, r1
-	mov	r6, r2
-	bl	dcache_invalidate_stale
-	mov	r0, r4
-	mov	r1, r5
-	mov	r2, r6
 	b	barebox_pbl_start
 ENDPROC(__barebox_arm_entry)
diff --git a/arch/arm/cpu/entry_ll_64.S b/arch/arm/cpu/entry_ll_64.S
index 3404f6d05802..71fb74b48f7e 100644
--- a/arch/arm/cpu/entry_ll_64.S
+++ b/arch/arm/cpu/entry_ll_64.S
@@ -12,12 +12,5 @@
 .section .text.__barebox_arm_entry
 ENTRY(__barebox_arm_entry)
 	mov	sp, x3
-	mov	x19, x0
-	mov	x20, x1
-	mov	x21, x2
-	bl	dcache_invalidate_stale
-	mov	x0, x19
-	mov	x1, x20
-	mov	x2, x21
 	b	barebox_pbl_start
 ENDPROC(__barebox_arm_entry)
diff --git a/arch/arm/cpu/mmu_32.c b/arch/arm/cpu/mmu_32.c
index efdb867532f9..e8c4ae2cc259 100644
--- a/arch/arm/cpu/mmu_32.c
+++ b/arch/arm/cpu/mmu_32.c
@@ -613,6 +613,8 @@ void mmu_early_enable(unsigned long membase, unsigned long memsize)
 
 	pr_debug("enabling MMU, ttb @ 0x%p\n", ttb);
 
+	dcache_invalidate_stale();
+
 	if (get_cr() & CR_M)
 		return;
 
diff --git a/arch/arm/cpu/uncompress.c b/arch/arm/cpu/uncompress.c
index 8f0d0f55f862..13cfaff18350 100644
--- a/arch/arm/cpu/uncompress.c
+++ b/arch/arm/cpu/uncompress.c
@@ -85,10 +85,18 @@ void __noreturn barebox_pbl_start(unsigned long membase, unsigned long memsize,
 #ifdef DEBUG
 	print_pbl_mem_layout(membase, endmem, barebox_base);
 #endif
-	if (IS_ENABLED(CONFIG_MMU))
+
+	/* Enable Caches to speed up the decompression below. */
+	if (IS_ENABLED(CONFIG_MMU)) {
 		mmu_early_enable(membase, memsize);
-	else if (IS_ENABLED(CONFIG_ARMV7R_MPU))
+	} else if (IS_ENABLED(CONFIG_ARMV7R_MPU)) {
 		armv7r_cache_enable();
+	} else {
+		/* Even if we don't use the cache right now, it may be used later.
+		 * Some CPUs may boot up with dirty cache lines, get rid of them.
+		 */
+		dcache_invalidate_stale();
+	}
 
 	pr_debug("uncompressing barebox ELF at 0x%p (size 0x%08x) to 0x%08lx (uncompressed size: 0x%08x)\n",
 			pg_start, pg_len, barebox_base, uncompressed_len);
-- 
2.47.3