From: Marc Zyngier <marc.zyngier@xxxxxxx> commit a8e4c0a919ae upstream. We call arm64_apply_bp_hardening() from post_ttbr_update_workaround, which has the unexpected consequence of being triggered on every exception return to userspace when ARM64_SW_TTBR0_PAN is selected, even if no context switch actually occured. This is a bit suboptimal, and it would be more logical to only invalidate the branch predictor when we actually switch to a different mm. In order to solve this, move the call to arm64_apply_bp_hardening() into check_and_switch_context(), where we're guaranteed to pick a different mm context. Acked-by: Will Deacon <will.deacon@xxxxxxx> Signed-off-by: Marc Zyngier <marc.zyngier@xxxxxxx> Signed-off-by: Catalin Marinas <catalin.marinas@xxxxxxx> Signed-off-by: Will Deacon <will.deacon@xxxxxxx> Signed-off-by: Alex Shi <alex.shi@xxxxxxxxxx> --- arch/arm64/mm/context.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/arch/arm64/mm/context.c b/arch/arm64/mm/context.c index afc9266..36416e4 100644 --- a/arch/arm64/mm/context.c +++ b/arch/arm64/mm/context.c @@ -221,6 +221,7 @@ void check_and_switch_context(struct mm_struct *mm, unsigned int cpu) raw_spin_unlock_irqrestore(&cpu_asid_lock, flags); switch_mm_fastpath: + arm64_apply_bp_hardening(); cpu_switch_mm(mm->pgd, mm); } @@ -231,8 +232,6 @@ asmlinkage void post_ttbr_update_workaround(void) "ic iallu; dsb nsh; isb", ARM64_WORKAROUND_CAVIUM_27456, CONFIG_CAVIUM_ERRATUM_27456)); - - arm64_apply_bp_hardening(); } static int asids_init(void) -- 2.7.4