[PATCH V2] x86/sgx: Silence softlockup detection when releasing large enclaves

From: Reinette Chatre
Date: Tue Jan 25 2022 - 13:25:23 EST


Vijay reported that the "unclobbered_vdso_oversubscribed" selftest
triggers the softlockup detector.

Actual SGX systems have 128GB of enclave memory or more. The
"unclobbered_vdso_oversubscribed" selftest creates one enclave which
consumes all of the enclave memory on the system. Tearing down such a
large enclave takes around a minute, most of it in the loop where
the EREMOVE instruction is applied to each individual 4k enclave page.

Spending one minute in a loop triggers the softlockup detector.

Add a cond_resched() to give other tasks a chance to run and placate
the softlockup detector.

Cc: stable@xxxxxxxxxxxxxxx
Fixes: 1728ab54b4be ("x86/sgx: Add a page reclaimer")
Reported-by: Vijay Dhanraj <vijay.dhanraj@xxxxxxxxx>
Acked-by: Dave Hansen <dave.hansen@xxxxxxxxxxxxxxx>
Signed-off-by: Reinette Chatre <reinette.chatre@xxxxxxxxx>
---
Softlockup message:

watchdog: BUG: soft lockup - CPU#7 stuck for 22s! [test_sgx:11502]
Kernel panic - not syncing: softlockup: hung tasks
<snip>
sgx_encl_release+0x86/0x1c0
sgx_release+0x11c/0x130
__fput+0xb0/0x280
____fput+0xe/0x10
task_work_run+0x6c/0xc0
exit_to_user_mode_prepare+0x1eb/0x1f0
syscall_exit_to_user_mode+0x1d/0x50
do_syscall_64+0x46/0xb0
entry_SYSCALL_64_after_hwframe+0x44/0xae

Changes since V1:
- V1: https://lore.kernel.org/lkml/1aa037705e5aa209d8b7a075873c6b4190327436.1642530802.git.reinette.chatre@xxxxxxxxx/
- Add comment provided by Jarkko.

arch/x86/kernel/cpu/sgx/encl.c | 2 ++
1 file changed, 2 insertions(+)

diff --git a/arch/x86/kernel/cpu/sgx/encl.c b/arch/x86/kernel/cpu/sgx/encl.c
index 001808e3901c..48afe96ae0f0 100644
--- a/arch/x86/kernel/cpu/sgx/encl.c
+++ b/arch/x86/kernel/cpu/sgx/encl.c
@@ -410,6 +410,8 @@ void sgx_encl_release(struct kref *ref)
}

kfree(entry);
+ /* Invoke scheduler to prevent soft lockups. */
+ cond_resched();
}

xa_destroy(&encl->page_array);
--
2.25.1