[PATCH v5 4/4] arm64: errata: Work around early CME DVMSync acknowledgement
Catalin Marinas
catalin.marinas at arm.com
Fri Apr 10 05:55:49 PDT 2026
On Fri, Apr 10, 2026 at 01:09:41PM +0100, Will Deacon wrote:
> On Tue, Apr 07, 2026 at 11:28:44AM +0100, Catalin Marinas wrote:
> > diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
> > index 489554931231..4c328b7c79ba 100644
> > --- a/arch/arm64/kernel/process.c
> > +++ b/arch/arm64/kernel/process.c
> > @@ -26,6 +26,7 @@
> > #include <linux/reboot.h>
> > #include <linux/interrupt.h>
> > #include <linux/init.h>
> > +#include <linux/cpumask.h>
> > #include <linux/cpu.h>
> > #include <linux/elfcore.h>
> > #include <linux/pm.h>
> > @@ -339,8 +340,41 @@ void flush_thread(void)
> > flush_gcs();
> > }
> >
> > +#ifdef CONFIG_ARM64_ERRATUM_4193714
> > +
> > +static void arch_dup_tlbbatch_mask(struct task_struct *dst)
> > +{
> > + /*
> > + * Clear the inherited cpumask with memset() to cover both cases where
> > + * cpumask_var_t is a pointer or an array. It will be allocated lazily
> > + * in sme_dvmsync_add_pending() if CPUMASK_OFFSTACK=y.
> > + */
> > + if (alternative_has_cap_unlikely(ARM64_WORKAROUND_4193714))
> > + memset(&dst->tlb_ubc.arch.cpumask, 0,
> > + sizeof(dst->tlb_ubc.arch.cpumask));
>
> nit: use cpumask_clear() instead?
I tried to explain in the comment above. The memset() is on purpose to
avoid #ifdef CPUMASK_OFFSTACK. When enabled, cpumask_var_t is a pointer
and we want it set to NULL (for later lazy allocation) rather than
clearing the parent's cpumask. I had the diff below initially but it
looked uglier. Or we make the erratum dependent on !CPUMASK_OFFSTACK but
it won't get compile coverage with defconfig.
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 4c328b7c79ba..9294cbd35cce 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -345,13 +345,18 @@ void flush_thread(void)
static void arch_dup_tlbbatch_mask(struct task_struct *dst)
{
/*
- * Clear the inherited cpumask with memset() to cover both cases where
- * cpumask_var_t is a pointer or an array. It will be allocated lazily
- * in sme_dvmsync_add_pending() if CPUMASK_OFFSTACK=y.
+ * Don't inherit the parent's tlbbatch cpumask.
+ *
+ * With CPUMASK_OFFSTACK=y, cpumask_var_t is a pointer. Reset it so
+ * that it will be allocated lazily in sme_dvmsync_add_pending().
*/
- if (alternative_has_cap_unlikely(ARM64_WORKAROUND_4193714))
- memset(&dst->tlb_ubc.arch.cpumask, 0,
- sizeof(dst->tlb_ubc.arch.cpumask));
+ if (alternative_has_cap_unlikely(ARM64_WORKAROUND_4193714)) {
+#ifdef CONFIG_CPUMASK_OFFSTACK
+ dst->tlb_ubc.arch.cpumask = NULL;
+#else
+ cpumask_clear(dst->tlb_ubc.arch.cpumask);
+#endif
+ }
}
static void arch_release_tlbbatch_mask(struct task_struct *tsk)
--
Catalin
More information about the linux-arm-kernel
mailing list