openwrt/target/linux/bcm27xx/patches-5.10/950-0300-ARM-proc-v7-Force-misalignment-of-early-stmia.patch

61 lines
2.0 KiB
Diff
Raw Normal View History

From 9e5b2debe12d4e840a7d3ec0cf22b215396ed46e Mon Sep 17 00:00:00 2001
From: Phil Elwell <phil@raspberrypi.com>
Date: Wed, 29 Jul 2020 13:47:55 +0100
Subject: [PATCH] ARM: proc-v7: Force misalignment of early stmia
In an attempt to prevent the problem of CPUn not starting, explicitly
misalign the scratch space used to save registers acros the cache
invalidation.
Notes:
At this stage in the boot process the core is running with its cache
disabled. Before enabling the cache its contents must be explicitly
invalidated, a process that requires quite a few registers that the
caller must preserve. Evidence suggests that something is writing a
block of zeroes over that space at a time when all other cores should
be idle, possibly some kind of write-combiner, and the misalignment is
designed to disrupt any write-coalescing.
In truth, I don't understand why this patch works, and when the failure
is so random it is hard to be certain that this isn't just rolling the
dice again. One interesting test would be to change the "addeq r12, #4"s
to "addeq r12, #0"s determine see if the offset itself is significant or
just the additional code.
See: https://github.com/Hexxeh/rpi-firmware/issues/232
Signed-off-by: Phil Elwell <phil@raspberrypi.com>
---
arch/arm/mm/proc-v7.S | 6 +++++-
1 file changed, 5 insertions(+), 1 deletion(-)
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -287,6 +287,8 @@ __v7_ca17mp_setup:
mov r10, #0
1: adr r0, __v7_setup_stack_ptr
ldr r12, [r0]
+ tst r12, #0x1f
+ addeq r12, r12, #4
add r12, r12, r0 @ the local stack
stmia r12, {r1-r6, lr} @ v7_invalidate_l1 touches r0-r6
bl v7_invalidate_l1
@@ -474,6 +476,8 @@ __v7_setup:
adr r0, __v7_setup_stack_ptr
ldr r12, [r0]
add r12, r12, r0 @ the local stack
+ tst r12, #0x1f
+ addeq r12, r12, #4
stmia r12, {r1-r6, lr} @ v7_invalidate_l1 touches r0-r6
bl v7_invalidate_l1
ldmia r12, {r1-r6, lr}
@@ -557,7 +561,7 @@ ENDPROC(__v7_setup)
.bss
.align 2
__v7_setup_stack:
- .space 4 * 7 @ 7 registers
+ .space 4 * 8 @ 7 registers + 1 spare
__INITDATA