Re: [PATCH V3 19/30] x86/sgx: Free up EPC pages directly to support large page ranges

[Reinette Chatre]

Hi Jarkko,

On 4/5/2022 12:11 AM, Jarkko Sakkinen wrote:
> On Mon, Apr 04, 2022 at 09:49:27AM -0700, Reinette Chatre wrote:
>> The page reclaimer ensures availability of EPC pages across all
>> enclaves. In support of this it runs independently from the
>> individual enclaves in order to take locks from the different
>> enclaves as it writes pages to swap.
>>
>> When needing to load a page from swap an EPC page needs to be
>> available for its contents to be loaded into. Loading an existing
>> enclave page from swap does not reclaim EPC pages directly if
>> none are available, instead the reclaimer is woken when the
>> available EPC pages are found to be below a watermark.
>>
>> When iterating over a large number of pages in an oversubscribed
>> environment there is a race between the reclaimer woken up and
>> EPC pages reclaimed fast enough for the page operations to proceed.
>>
>> Ensure there are EPC pages available before attempting to load
>> a page that may potentially be pulled from swap into an available
>> EPC page.
>>
>> Signed-off-by: Reinette Chatre <reinette.chatre@xxxxxxxxx>
>> ---
>> No changes since V2
>>
>> Changes since v1:
>> - Reword commit message.
>>
>>  arch/x86/kernel/cpu/sgx/ioctl.c | 6 ++++++
>>  arch/x86/kernel/cpu/sgx/main.c  | 6 ++++++
>>  arch/x86/kernel/cpu/sgx/sgx.h   | 1 +
>>  3 files changed, 13 insertions(+)
>>
>> diff --git a/arch/x86/kernel/cpu/sgx/ioctl.c b/arch/x86/kernel/cpu/sgx/ioctl.c
>> index 515e1961cc02..f88bc1236276 100644
>> --- a/arch/x86/kernel/cpu/sgx/ioctl.c
>> +++ b/arch/x86/kernel/cpu/sgx/ioctl.c
>> @@ -777,6 +777,8 @@ sgx_enclave_restrict_permissions(struct sgx_encl *encl,
>>  	for (c = 0 ; c < modp->length; c += PAGE_SIZE) {
>>  		addr = encl->base + modp->offset + c;
>>  
>> +		sgx_direct_reclaim();
>> +
>>  		mutex_lock(&encl->lock);
>>  
>>  		entry = sgx_encl_load_page(encl, addr);
>> @@ -934,6 +936,8 @@ static long sgx_enclave_modify_type(struct sgx_encl *encl,
>>  	for (c = 0 ; c < modt->length; c += PAGE_SIZE) {
>>  		addr = encl->base + modt->offset + c;
>>  
>> +		sgx_direct_reclaim();
>> +
>>  		mutex_lock(&encl->lock);
>>  
>>  		entry = sgx_encl_load_page(encl, addr);
>> @@ -1129,6 +1133,8 @@ static long sgx_encl_remove_pages(struct sgx_encl *encl,
>>  	for (c = 0 ; c < params->length; c += PAGE_SIZE) {
>>  		addr = encl->base + params->offset + c;
>>  
>> +		sgx_direct_reclaim();
>> +
>>  		mutex_lock(&encl->lock);
>>  
>>  		entry = sgx_encl_load_page(encl, addr);
>> diff --git a/arch/x86/kernel/cpu/sgx/main.c b/arch/x86/kernel/cpu/sgx/main.c
>> index 6e2cb7564080..545da16bb3ea 100644
>> --- a/arch/x86/kernel/cpu/sgx/main.c
>> +++ b/arch/x86/kernel/cpu/sgx/main.c
>> @@ -370,6 +370,12 @@ static bool sgx_should_reclaim(unsigned long watermark)
>>  	       !list_empty(&sgx_active_page_list);
>>  }
>>  
>> +void sgx_direct_reclaim(void)
>> +{
>> +	if (sgx_should_reclaim(SGX_NR_LOW_PAGES))
>> +		sgx_reclaim_pages();
>> +}
> 
> Please, instead open code this to both locations - not enough redundancy
> to be worth of new function. Causes only unnecessary cross-referencing
> when maintaining. Otherwise, I agree with the idea.
> 

hmmm, that means the heart of the reclaimer (sgx_reclaim_pages()) would be
made available for direct use from everywhere in the driver. I will look into this.

Reinette