4.9-stable review patch. If anyone has any objections, please let me know.
------------------
From: Will Deacon <will.deacon@xxxxxxx>
commit 18011eac28c7 upstream.
When unmapping the kernel at EL0, we use tpidrro_el0 as a scratch register
during exception entry from native tasks and subsequently zero it in
the kernel_ventry macro. We can therefore avoid zeroing tpidrro_el0
in the context-switch path for native tasks using the entry trampoline.
Reviewed-by: Mark Rutland <mark.rutland@xxxxxxx>
Tested-by: Laura Abbott <labbott@xxxxxxxxxx>
Tested-by: Shanker Donthineni <shankerd@xxxxxxxxxxxxxx>
Signed-off-by: Will Deacon <will.deacon@xxxxxxx>
Signed-off-by: Alex Shi <alex.shi@xxxxxxxxxx> [v4.9 backport]
Signed-off-by: Mark Rutland <mark.rutland@xxxxxxx> [v4.9 backport]
Tested-by: Will Deacon <will.deacon@xxxxxxx>
Tested-by: Greg Hackmann <ghackmann@xxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
arch/arm64/kernel/process.c | 12 ++++++------
1 file changed, 6 insertions(+), 6 deletions(-)
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -306,17 +306,17 @@ int copy_thread(unsigned long clone_flag
static void tls_thread_switch(struct task_struct *next)
{
- unsigned long tpidr, tpidrro;
+ unsigned long tpidr;
tpidr = read_sysreg(tpidr_el0);
*task_user_tls(current) = tpidr;
- tpidr = *task_user_tls(next);
- tpidrro = is_compat_thread(task_thread_info(next)) ?
- next->thread.tp_value : 0;
+ if (is_compat_thread(task_thread_info(next)))
+ write_sysreg(next->thread.tp_value, tpidrro_el0);
+ else if (!arm64_kernel_unmapped_at_el0())
+ write_sysreg(0, tpidrro_el0);
- write_sysreg(tpidr, tpidr_el0);
- write_sysreg(tpidrro, tpidrro_el0);
+ write_sysreg(*task_user_tls(next), tpidr_el0);
}
/* Restore the UAO state depending on next's addr_limit */