Patch "ARM: invalidate L1 before enabling coherency" has been added to the 4.1-stable tree
Subsystems (2)
This is a note to let you know that I've just added the patch titled
ARM: invalidate L1 before enabling coherency
to the 4.1-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
arm-invalidate-l1-before-enabling-coherency.patch
and it can be found in the queue-4.1 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree, please let <[email protected]> know about it.
Quoted 1 line
From
bac51ad9d14f6baed3730ef53bedc1eb2238563aMon Sep 17 00:00:00 2001
From: Russell King <[email protected]>
Date: Thu, 9 Jul 2015 00:30:24 +0100
Subject: ARM: invalidate L1 before enabling coherency
From: Russell King <[email protected]>
commit bac51ad9d14f6baed3730ef53bedc1eb2238563a upstream.
We must invalidate the L1 cache before enabling coherency, otherwise secondary CPUs can inject invalid cache lines into the coherent CPU cluster, which could then be migrated to other CPUs. This fixes a recent regression with SoCFPGA randomly failing to boot.
--- arch/arm/mm/proc-v7.S | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-)
arch/arm/mm/proc-v7.S +9 -5
@@ -268,7 +268,10 @@ __v7_ca15mp_setup: __v7_b15mp_setup: __v7_ca17mp_setup: mov r10, #0 -1: +1: adr r12, __v7_setup_stack @ the local stack + stmia r12, {r0-r5, lr} @ v7_invalidate_l1 touches r0-r6 + bl v7_invalidate_l1 + ldmia r12, {r0-r5, lr} #ifdef CONFIG_SMP ALT_SMP(mrc p15, 0, r0, c1, c0, 1) ALT_UP(mov r0, #(1 << 6)) @ fake it for UP
@@ -277,7 +280,7 @@ __v7_ca17mp_setup: orreq r0, r0, r10 @ Enable CPU-specific SMP bits mcreq p15, 0, r0, c1, c0, 1 #endif - b __v7_setup + b __v7_setup_cont __v7_pj4b_setup: #ifdef CONFIG_CPU_PJ4B
@@ -335,10 +338,11 @@ __v7_pj4b_setup: __v7_setup: adr r12, __v7_setup_stack @ the local stack - stmia r12, {r0-r5, r7, r9, r11, lr} + stmia r12, {r0-r5, lr} @ v7_invalidate_l1 touches r0-r6 bl v7_invalidate_l1 - ldmia r12, {r0-r5, r7, r9, r11, lr} + ldmia r12, {r0-r5, lr} +__v7_setup_cont: mrc p15, 0, r0, c0, c0, 0 @ read main ID register and r10, r0, #0xff000000 @ ARM? teq r10, #0x41000000
@@ -460,7 +464,7 @@ ENDPROC(__v7_setup) .align 2 __v7_setup_stack: - .space 4 * 11 @ 11 registers + .space 4 * 7 @ 12 registers __INITDATA
Patches currently in stable-queue which might be from [email protected] are
queue-4.1/arm-invalidate-l1-before-enabling-coherency.patch queue-4.1/arm-8384-1-vdso-force-use-of-bfd-linker.patch queue-4.1/arm-8385-1-vdso-group-link-options.patch queue-4.1/arm-v7-setup-function-should-invalidate-l1-cache.patch