| Message ID | 1aa037705e5aa209d8b7a075873c6b4190327436.1642530802.git.reinette.chatre@intel.com |
|---|---|
| State | Superseded |
| Headers | show |
| Series | x86/sgx: Silence softlockup detection when releasing large enclaves | expand |
On Tue, 2022-01-18 at 11:14 -0800, Reinette Chatre wrote: > 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@vger.kernel.org > Fixes: 1728ab54b4be ("x86/sgx: Add a page reclaimer") > Reported-by: Vijay Dhanraj <vijay.dhanraj@intel.com> > Acked-by: Dave Hansen <dave.hansen@linux.intel.com> > Signed-off-by: Reinette Chatre <reinette.chatre@intel.com> > --- > 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 > > arch/x86/kernel/cpu/sgx/encl.c | 1 + > 1 file changed, 1 insertion(+) > > diff --git a/arch/x86/kernel/cpu/sgx/encl.c > b/arch/x86/kernel/cpu/sgx/encl.c > index 001808e3901c..ab2b79327a8a 100644 > --- a/arch/x86/kernel/cpu/sgx/encl.c > +++ b/arch/x86/kernel/cpu/sgx/encl.c > @@ -410,6 +410,7 @@ void sgx_encl_release(struct kref *ref) > } > > kfree(entry); > + cond_resched(); > } > > xa_destroy(&encl->page_array); I'd add a comment, e.g. /* Invoke scheduler to prevent soft lockups. */ Other than that makes sense. BR, Jarkko
Hi Jarkko, On 1/20/2022 5:01 AM, Jarkko Sakkinen wrote: > On Tue, 2022-01-18 at 11:14 -0800, Reinette Chatre wrote: >> 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@vger.kernel.org >> Fixes: 1728ab54b4be ("x86/sgx: Add a page reclaimer") >> Reported-by: Vijay Dhanraj <vijay.dhanraj@intel.com> >> Acked-by: Dave Hansen <dave.hansen@linux.intel.com> >> Signed-off-by: Reinette Chatre <reinette.chatre@intel.com> >> --- >> 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 >> >> arch/x86/kernel/cpu/sgx/encl.c | 1 + >> 1 file changed, 1 insertion(+) >> >> diff --git a/arch/x86/kernel/cpu/sgx/encl.c >> b/arch/x86/kernel/cpu/sgx/encl.c >> index 001808e3901c..ab2b79327a8a 100644 >> --- a/arch/x86/kernel/cpu/sgx/encl.c >> +++ b/arch/x86/kernel/cpu/sgx/encl.c >> @@ -410,6 +410,7 @@ void sgx_encl_release(struct kref *ref) >> } >> >> kfree(entry); >> + cond_resched(); >> } >> >> xa_destroy(&encl->page_array); > > I'd add a comment, e.g. > > /* Invoke scheduler to prevent soft lockups. */ I could do that. I would like to point out though that there are already six other usages of cond_resched() in the driver and it does indeed seem to be the common pattern. When adding this comment to the now seventh usage it would be the first comment documenting the usage of cond_resched() in the driver. > > Other than that makes sense. Thank you very much for taking a look. Reinette
diff --git a/arch/x86/kernel/cpu/sgx/encl.c b/arch/x86/kernel/cpu/sgx/encl.c index 001808e3901c..ab2b79327a8a 100644 --- a/arch/x86/kernel/cpu/sgx/encl.c +++ b/arch/x86/kernel/cpu/sgx/encl.c @@ -410,6 +410,7 @@ void sgx_encl_release(struct kref *ref) } kfree(entry); + cond_resched(); } xa_destroy(&encl->page_array);
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@vger.kernel.org Fixes: 1728ab54b4be ("x86/sgx: Add a page reclaimer") Reported-by: Vijay Dhanraj <vijay.dhanraj@intel.com> Acked-by: Dave Hansen <dave.hansen@linux.intel.com> Signed-off-by: Reinette Chatre <reinette.chatre@intel.com> --- 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 arch/x86/kernel/cpu/sgx/encl.c | 1 + 1 file changed, 1 insertion(+)