diff mbox series

[v38,16/24] x86/sgx: Add a page reclaimer

Message ID 20200915112842.897265-17-jarkko.sakkinen@linux.intel.com (mailing list archive)
State New, archived
Headers show
Series Intel SGX foundations | expand

Commit Message

Jarkko Sakkinen Sept. 15, 2020, 11:28 a.m. UTC
There is a limited amount of EPC available. Therefore, some of it must be
copied to the regular memory, and only subset kept in the SGX reserved
memory. While kernel cannot directly access enclave memory, SGX provides a
set of ENCLS leaf functions to perform reclaiming.

This commits implements a page reclaimer by using these leaf functions. It
picks the victim pages in LRU fashion from all the enclaves running in the
system. The thread ksgxswapd reclaims pages on the event when the number of
free EPC pages goes below SGX_NR_LOW_PAGES up until it reaches
SGX_NR_HIGH_PAGES.

sgx_alloc_epc_page() can optionally directly reclaim pages with @reclaim
set true. A caller must also supply owner for each page so that the
reclaimer can access the associated enclaves. This is needed for locking,
as most of the ENCLS leafs cannot be executed concurrently for an enclave.
The owner is also needed for accessing SECS, which is required to be
resident when its child pages are being reclaimed.

Cc: linux-mm@kvack.org
Acked-by: Jethro Beekman <jethro@fortanix.com>
Tested-by: Jethro Beekman <jethro@fortanix.com>
Tested-by: Jordan Hand <jorhand@linux.microsoft.com>
Tested-by: Nathaniel McCallum <npmccallum@redhat.com>
Tested-by: Chunyang Hui <sanqian.hcy@antfin.com>
Tested-by: Seth Moore <sethmo@google.com>
Co-developed-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com>
---
 arch/x86/kernel/cpu/sgx/driver.c |   1 +
 arch/x86/kernel/cpu/sgx/encl.c   | 340 +++++++++++++++++++++-
 arch/x86/kernel/cpu/sgx/encl.h   |  41 +++
 arch/x86/kernel/cpu/sgx/ioctl.c  |  77 ++++-
 arch/x86/kernel/cpu/sgx/main.c   | 464 +++++++++++++++++++++++++++++++
 arch/x86/kernel/cpu/sgx/sgx.h    |   9 +
 6 files changed, 925 insertions(+), 7 deletions(-)

Comments

Borislav Petkov Sept. 22, 2020, 10:45 a.m. UTC | #1
On Tue, Sep 15, 2020 at 02:28:34PM +0300, Jarkko Sakkinen wrote:
> There is a limited amount of EPC available. Therefore, some of it must be
> copied to the regular memory, and only subset kept in the SGX reserved
> memory. While kernel cannot directly access enclave memory, SGX provides a
> set of ENCLS leaf functions to perform reclaiming.
> 
> This commits implements a page reclaimer by using these leaf functions. It

s/This commits implements/Implement/

> picks the victim pages in LRU fashion from all the enclaves running in the
> system. The thread ksgxswapd reclaims pages on the event when the number of
> free EPC pages goes below SGX_NR_LOW_PAGES up until it reaches
> SGX_NR_HIGH_PAGES.

...

Had to grep the SDM for that "eldu" magic. It could use a comment:

/*
 * ELDU: Load an EPC page as unblocked. For more info, see "OS
 * Management of EPC Pages" in the SDM.
 */

or so, to denote what's going on here.

> +static struct sgx_epc_page *sgx_encl_eldu(struct sgx_encl_page *encl_page,
> +					  struct sgx_epc_page *secs_page)
> +{
> +	unsigned long va_offset = SGX_ENCL_PAGE_VA_OFFSET(encl_page);
> +	struct sgx_encl *encl = encl_page->encl;
> +	struct sgx_epc_page *epc_page;
> +	int ret;
> +
> +	epc_page = sgx_alloc_epc_page(encl_page, false);
> +	if (IS_ERR(epc_page))
> +		return epc_page;
> +
> +	ret = __sgx_encl_eldu(encl_page, epc_page, secs_page);
> +	if (ret) {
> +		sgx_free_epc_page(epc_page);
> +		return ERR_PTR(ret);
> +	}
> +
> +	sgx_free_va_slot(encl_page->va_page, va_offset);
> +	list_move(&encl_page->va_page->list, &encl->va_pages);
> +	encl_page->desc &= ~SGX_ENCL_PAGE_VA_OFFSET_MASK;
> +	encl_page->epc_page = epc_page;
> +
> +	return epc_page;
> +}

...

> diff --git a/arch/x86/kernel/cpu/sgx/encl.h b/arch/x86/kernel/cpu/sgx/encl.h
> index 0448d22d3010..11dcf4e7fb3e 100644
> --- a/arch/x86/kernel/cpu/sgx/encl.h
> +++ b/arch/x86/kernel/cpu/sgx/encl.h
> @@ -19,6 +19,10 @@
>  
>  /**
>   * enum sgx_encl_page_desc - defines bits for an enclave page's descriptor
> + * %SGX_ENCL_PAGE_RECLAIMED:		The page is in the process of being
> + *					reclaimed.

SGX_ENCL_PAGE_RECLAIMED means, tho, that the page has been reclaimed
already.

I guess that reads better:

+		if (entry->desc & SGX_ENCL_PAGE_BEING_RECLAIMED)
+			return ERR_PTR(-EBUSY);


> + * %SGX_ENCL_PAGE_VA_OFFSET_MASK:	Holds the offset in the Version Array
> + *					(VA) page for a swapped page.
>   * %SGX_ENCL_PAGE_ADDR_MASK:		Holds the virtual address of the page.
>   *
>   * The page address for SECS is zero and is used by the subsystem to recognize

...

> @@ -86,24 +123,34 @@ static int sgx_encl_create(struct sgx_encl *encl, struct sgx_secs *secs)
>  {
>  	unsigned long encl_size = secs->size + PAGE_SIZE;
>  	struct sgx_epc_page *secs_epc;
> +	struct sgx_va_page *va_page;
>  	struct sgx_pageinfo pginfo;
>  	struct sgx_secinfo secinfo;
>  	struct file *backing;
>  	long ret;
>  
> +	va_page = sgx_encl_grow(encl);
> +	if (IS_ERR(va_page))
> +		return PTR_ERR(va_page);
> +	else if (va_page)

Not "else" simply?

AFAICT, sgx_encl_grow() would either return an ERR_PTR or the actual
page...

Also, should the growing happen *after* the SECS validation?

> +		list_add(&va_page->list, &encl->va_pages);
> +
>  	if (sgx_validate_secs(secs)) {
>  		pr_debug("invalid SECS\n");
> -		return -EINVAL;
> +		ret = -EINVAL;
> +		goto err_out_shrink;
>  	}
>  
>  	backing = shmem_file_setup("SGX backing", encl_size + (encl_size >> 5),
>  				   VM_NORESERVE);
> -	if (IS_ERR(backing))
> -		return PTR_ERR(backing);
> +	if (IS_ERR(backing)) {
> +		ret = PTR_ERR(backing);
> +		goto err_out_shrink;
> +	}
>  
>  	encl->backing = backing;
>  
> -	secs_epc = __sgx_alloc_epc_page();
> +	secs_epc = sgx_alloc_epc_page(&encl->secs, true);
>  	if (IS_ERR(secs_epc)) {
>  		ret = PTR_ERR(secs_epc);
>  		goto err_out_backing;
> @@ -151,6 +198,9 @@ static int sgx_encl_create(struct sgx_encl *encl, struct sgx_secs *secs)
>  	fput(encl->backing);
>  	encl->backing = NULL;
>  
> +err_out_shrink:
> +	sgx_encl_shrink(encl, va_page);
> +
>  	return ret;
>  }

...


Let's add some comment blurb about "Write back/invalidate an EPC page"
to at least start to explain what that "ewb" is.

> +static void sgx_encl_ewb(struct sgx_epc_page *epc_page,
> +			 struct sgx_backing *backing)
> +{
> +	struct sgx_encl_page *encl_page = epc_page->owner;
> +	struct sgx_encl *encl = encl_page->encl;
> +	struct sgx_va_page *va_page;
> +	unsigned int va_offset;
> +	void *va_slot;
> +	int ret;
> +
> +	encl_page->desc &= ~SGX_ENCL_PAGE_RECLAIMED;
> +
> +	va_page = list_first_entry(&encl->va_pages, struct sgx_va_page,
> +				   list);
> +	va_offset = sgx_alloc_va_slot(va_page);
> +	va_slot = sgx_get_epc_addr(va_page->epc_page) + va_offset;
> +	if (sgx_va_page_full(va_page))
> +		list_move_tail(&va_page->list, &encl->va_pages);
> +
> +	ret = __sgx_encl_ewb(epc_page, va_slot, backing);
> +	if (ret == SGX_NOT_TRACKED) {
> +		ret = __etrack(sgx_get_epc_addr(encl->secs.epc_page));
> +		if (ret) {
> +			if (encls_failed(ret))
> +				ENCLS_WARN(ret, "ETRACK");
> +		}
> +
> +		ret = __sgx_encl_ewb(epc_page, va_slot, backing);
> +		if (ret == SGX_NOT_TRACKED) {
> +			/*
> +			 * Slow path, send IPIs to kick cpus out of the
> +			 * enclave.  Note, it's imperative that the cpu
> +			 * mask is generated *after* ETRACK, else we'll
> +			 * miss cpus that entered the enclave between
> +			 * generating the mask and incrementing epoch.
> +			 */
> +			on_each_cpu_mask(sgx_encl_ewb_cpumask(encl),
> +					 sgx_ipi_cb, NULL, 1);
> +			ret = __sgx_encl_ewb(epc_page, va_slot, backing);
> +		}
> +	}
> +
> +	if (ret) {
> +		if (encls_failed(ret))
> +			ENCLS_WARN(ret, "EWB");
> +
> +		sgx_free_va_slot(va_page, va_offset);
> +	} else {
> +		encl_page->desc |= va_offset;
> +		encl_page->va_page = va_page;
> +	}

...

> +static void sgx_reclaim_pages(void)
> +{
> +	struct sgx_epc_page *chunk[SGX_NR_TO_SCAN];
> +	struct sgx_backing backing[SGX_NR_TO_SCAN];
> +	struct sgx_epc_section *section;
> +	struct sgx_encl_page *encl_page;
> +	struct sgx_epc_page *epc_page;
> +	int cnt = 0;
> +	int ret;
> +	int i;
> +
> +	spin_lock(&sgx_active_page_list_lock);
> +	for (i = 0; i < SGX_NR_TO_SCAN; i++) {
> +		if (list_empty(&sgx_active_page_list))

Isn't it enough to do this once, i.e., not in the loop? You're holding
sgx_active_page_list_lock...

> +			break;
> +
> +		epc_page = list_first_entry(&sgx_active_page_list,
> +					    struct sgx_epc_page, list);
> +		list_del_init(&epc_page->list);
> +		encl_page = epc_page->owner;
> +
> +		if (kref_get_unless_zero(&encl_page->encl->refcount) != 0)
> +			chunk[cnt++] = epc_page;
> +		else
> +			/* The owner is freeing the page. No need to add the
> +			 * page back to the list of reclaimable pages.
> +			 */
> +			epc_page->desc &= ~SGX_EPC_PAGE_RECLAIMABLE;
> +	}
> +	spin_unlock(&sgx_active_page_list_lock);
> +
> +	for (i = 0; i < cnt; i++) {
> +		epc_page = chunk[i];
> +		encl_page = epc_page->owner;
> +
> +		if (!sgx_reclaimer_age(epc_page))
> +			goto skip;
> +
> +		ret = sgx_encl_get_backing(encl_page->encl,
> +					   SGX_ENCL_PAGE_INDEX(encl_page),
> +					   &backing[i]);
> +		if (ret)
> +			goto skip;
> +
> +		mutex_lock(&encl_page->encl->lock);
> +		encl_page->desc |= SGX_ENCL_PAGE_RECLAIMED;
> +		mutex_unlock(&encl_page->encl->lock);
> +		continue;
> +
> +skip:
> +		spin_lock(&sgx_active_page_list_lock);
> +		list_add_tail(&epc_page->list, &sgx_active_page_list);
> +		spin_unlock(&sgx_active_page_list_lock);
> +
> +		kref_put(&encl_page->encl->refcount, sgx_encl_release);
> +
> +		chunk[i] = NULL;
> +	}
> +
> +	for (i = 0; i < cnt; i++) {
> +		epc_page = chunk[i];
> +		if (epc_page)
> +			sgx_reclaimer_block(epc_page);
> +	}
> +
> +	for (i = 0; i < cnt; i++) {
> +		epc_page = chunk[i];
> +		if (!epc_page)
> +			continue;
> +
> +		encl_page = epc_page->owner;
> +		sgx_reclaimer_write(epc_page, &backing[i]);
> +		sgx_encl_put_backing(&backing[i], true);
> +
> +		kref_put(&encl_page->encl->refcount, sgx_encl_release);
> +		epc_page->desc &= ~SGX_EPC_PAGE_RECLAIMABLE;
> +
> +		section = sgx_get_epc_section(epc_page);
> +		spin_lock(&section->lock);
> +		list_add_tail(&epc_page->list, &section->page_list);
> +		section->free_cnt++;
> +		spin_unlock(&section->lock);
> +	}
> +}
> +
>  
>  static void sgx_sanitize_section(struct sgx_epc_section *section)

...
Jarkko Sakkinen Sept. 22, 2020, 2:03 p.m. UTC | #2
On Tue, Sep 22, 2020 at 12:45:38PM +0200, Borislav Petkov wrote:
> > + * %SGX_ENCL_PAGE_VA_OFFSET_MASK:	Holds the offset in the Version Array
> > + *					(VA) page for a swapped page.
> >   * %SGX_ENCL_PAGE_ADDR_MASK:		Holds the virtual address of the page.
> >   *
> >   * The page address for SECS is zero and is used by the subsystem to recognize
> 
> ...

So what's wrong over here?

> > @@ -86,24 +123,34 @@ static int sgx_encl_create(struct sgx_encl *encl, struct sgx_secs *secs)
> >  {
> >  	unsigned long encl_size = secs->size + PAGE_SIZE;
> >  	struct sgx_epc_page *secs_epc;
> > +	struct sgx_va_page *va_page;
> >  	struct sgx_pageinfo pginfo;
> >  	struct sgx_secinfo secinfo;
> >  	struct file *backing;
> >  	long ret;
> >  
> > +	va_page = sgx_encl_grow(encl);
> > +	if (IS_ERR(va_page))
> > +		return PTR_ERR(va_page);
> > +	else if (va_page)
> 
> Not "else" simply?
> 
> AFAICT, sgx_encl_grow() would either return an ERR_PTR or the actual
> page...
> 
> Also, should the growing happen *after* the SECS validation?

Yes, it would make sense. I'll move it.

> Let's add some comment blurb about "Write back/invalidate an EPC page"
> to at least start to explain what that "ewb" is.

OK, I'll try to write something understandable.

> > +	spin_lock(&sgx_active_page_list_lock);
> > +	for (i = 0; i < SGX_NR_TO_SCAN; i++) {
> > +		if (list_empty(&sgx_active_page_list))
> 
> Isn't it enough to do this once, i.e., not in the loop? You're holding
> sgx_active_page_list_lock...

I think that would make sense. Distantly analogous to the EINIT
discussion. Too complex code for yet to be known problem workloads I'd
say.


> >  static void sgx_sanitize_section(struct sgx_epc_section *section)
> 
> ...

Is this about documenting this function?

> -- 
> Regards/Gruss,
>     Boris.
> 
> https://people.kernel.org/tglx/notes-about-netiquette

Thanks, this was valuable feedback.

/Jarkko
Borislav Petkov Sept. 22, 2020, 2:24 p.m. UTC | #3
On Tue, Sep 22, 2020 at 05:03:23PM +0300, Jarkko Sakkinen wrote:
> On Tue, Sep 22, 2020 at 12:45:38PM +0200, Borislav Petkov wrote:
> > > + * %SGX_ENCL_PAGE_VA_OFFSET_MASK:	Holds the offset in the Version Array
> > > + *					(VA) page for a swapped page.
> > >   * %SGX_ENCL_PAGE_ADDR_MASK:		Holds the virtual address of the page.
> > >   *
> > >   * The page address for SECS is zero and is used by the subsystem to recognize
> > 
> > ...
> 
> So what's wrong over here?

Nothing - that's just an ellipsis: https://en.wikipedia.org/wiki/Ellipsis

I do that because otherwise you'd have to scroll through pages of quoted
mail for no good reason and that ain't friendly at all. And I notice
people not trimming their replies and not quoting only the text they
reply to. They should not wonder if their emails remain unread.

Thx for the rest.
Sean Christopherson Sept. 22, 2020, 4:24 p.m. UTC | #4
On Tue, Sep 22, 2020 at 12:45:38PM +0200, Borislav Petkov wrote:
> On Tue, Sep 15, 2020 at 02:28:34PM +0300, Jarkko Sakkinen wrote:
> > + * %SGX_ENCL_PAGE_VA_OFFSET_MASK:	Holds the offset in the Version Array
> > + *					(VA) page for a swapped page.
> >   * %SGX_ENCL_PAGE_ADDR_MASK:		Holds the virtual address of the page.
> >   *
> >   * The page address for SECS is zero and is used by the subsystem to recognize
> 
> ...
> 
> > @@ -86,24 +123,34 @@ static int sgx_encl_create(struct sgx_encl *encl, struct sgx_secs *secs)
> >  {
> >  	unsigned long encl_size = secs->size + PAGE_SIZE;
> >  	struct sgx_epc_page *secs_epc;
> > +	struct sgx_va_page *va_page;
> >  	struct sgx_pageinfo pginfo;
> >  	struct sgx_secinfo secinfo;
> >  	struct file *backing;
> >  	long ret;
> >  
> > +	va_page = sgx_encl_grow(encl);
> > +	if (IS_ERR(va_page))
> > +		return PTR_ERR(va_page);
> > +	else if (va_page)
> 
> Not "else" simply?
> 
> AFAICT, sgx_encl_grow() would either return an ERR_PTR or the actual
> page...
> 

The "else if" is correct.  Version Array (VA) pages have 512 slots that hold
metadata for evicted EPC pages, i.e. swapping a page out of the EPC requires
a VA slot.  For simplicity (LOL), the approach we are taking for initial
support is to reserve a VA slot when adding a page to the enclave[*].  In most
cases, reserving a slot does not require allocating a new VA page, e.g. to
reserve slots 1-511 of the "current" VA page.   The if-elif is handling the
case where the current VA page is fully reserved and a new one needs to be
allocated. The if handles the error, the elif handles success, i.e.

	if (IS_ERR(va_page)) <- needed a new VA page, allocation failed
		return PTR_ERR(va_page);
	else if (va_page)    <- needed a new VA page, allocation succeeded
		list_add(&va_page->list, &encl->va_pages);
	else
		             <- reused the current VA page

When reusing a VA page, we obviously don't want to readd the page to the list
of va_pages, and the error handling path also shouldn't free the VA page.

> Also, should the growing happen *after* the SECS validation?
> 
> > +		list_add(&va_page->list, &encl->va_pages);
> > +
> >  	if (sgx_validate_secs(secs)) {
> >  		pr_debug("invalid SECS\n");
> > -		return -EINVAL;
> > +		ret = -EINVAL;
> > +		goto err_out_shrink;
> >  	}
Borislav Petkov Sept. 22, 2020, 6:02 p.m. UTC | #5
On Tue, Sep 22, 2020 at 09:24:38AM -0700, Sean Christopherson wrote:
> The "else if" is correct.  Version Array (VA) pages have 512 slots that hold
> metadata for evicted EPC pages, i.e. swapping a page out of the EPC requires
> a VA slot.  For simplicity (LOL),

I'll say.

> the approach we are taking for initial support is to reserve a VA slot
> when adding a page to the enclave[*]. In most cases, reserving a slot
> does not require allocating a new VA page, e.g. to reserve slots 1-511
> of the "current" VA page. The if-elif is handling the case where the
> current VA page is fully reserved and a new one needs to be allocated.
> The if handles the error, the elif handles success, i.e.
> 
> 	if (IS_ERR(va_page)) <- needed a new VA page, allocation failed
> 		return PTR_ERR(va_page);
> 	else if (va_page)    <- needed a new VA page, allocation succeeded
> 		list_add(&va_page->list, &encl->va_pages);
> 	else
> 		             <- reused the current VA page

Aha, in that case va_page will be NULL but you're not using it in that
function later and that current VA page is on encl->va_pages which
others can get from there. Ok, gotcha.

Thx.
Jarkko Sakkinen Sept. 23, 2020, 2:52 p.m. UTC | #6
On Tue, Sep 22, 2020 at 04:24:13PM +0200, Borislav Petkov wrote:
> On Tue, Sep 22, 2020 at 05:03:23PM +0300, Jarkko Sakkinen wrote:
> > On Tue, Sep 22, 2020 at 12:45:38PM +0200, Borislav Petkov wrote:
> > > > + * %SGX_ENCL_PAGE_VA_OFFSET_MASK:	Holds the offset in the Version Array
> > > > + *					(VA) page for a swapped page.
> > > >   * %SGX_ENCL_PAGE_ADDR_MASK:		Holds the virtual address of the page.
> > > >   *
> > > >   * The page address for SECS is zero and is used by the subsystem to recognize
> > > 
> > > ...
> > 
> > So what's wrong over here?
> 
> Nothing - that's just an ellipsis: https://en.wikipedia.org/wiki/Ellipsis
> 
> I do that because otherwise you'd have to scroll through pages of quoted
> mail for no good reason and that ain't friendly at all. And I notice
> people not trimming their replies and not quoting only the text they
> reply to. They should not wonder if their emails remain unread.
> 
> Thx for the rest.

OK, I'm just almost paranoic in not addressing all feedback, thanks
for the explanation :-)

Like in this version, I'll try to xref all changes so it will be at
least easier spot if something is missing.

> 
> -- 
> Regards/Gruss,
>     Boris.
> 
> https://people.kernel.org/tglx/notes-about-netiquette

/Jarkko
Jarkko Sakkinen Sept. 23, 2020, 3:25 p.m. UTC | #7
> 	if (IS_ERR(va_page)) <- needed a new VA page, allocation failed
> 		return PTR_ERR(va_page);
> 	else if (va_page)    <- needed a new VA page, allocation succeeded
> 		list_add(&va_page->list, &encl->va_pages);
> 	else
> 		             <- reused the current VA page

/* else the tail page of the VA page list had free slots. */

I added this comment as "the missing branch".

/Jarkko
Sean Christopherson Sept. 29, 2020, 1:14 a.m. UTC | #8
On Tue, Sep 22, 2020 at 05:03:23PM +0300, Jarkko Sakkinen wrote:
> On Tue, Sep 22, 2020 at 12:45:38PM +0200, Borislav Petkov wrote:
> > > +	spin_lock(&sgx_active_page_list_lock);
> > > +	for (i = 0; i < SGX_NR_TO_SCAN; i++) {
> > > +		if (list_empty(&sgx_active_page_list))
> > 
> > Isn't it enough to do this once, i.e., not in the loop? You're holding
> > sgx_active_page_list_lock...

Argh, I missed this until I looked at Jarkko's updated tree.

The reason for checking list_empty() on every iteration is that the loop is
greedy, i.e. it tries to grab and reclaim up to 16 (SGX_NR_TO_SCAN) EPC pages
at a time.

> I think that would make sense. Distantly analogous to the EINIT
> discussion. Too complex code for yet to be known problem workloads I'd
> say.

Nooooo.  Please no.

This will most definitely impact workloads running a single large enclave, or a
process running multiple enclaves, as we'll lose the batching of ETRACK and IPIs.
ETRACK isn't a big deal, but the IPIs are painful and could thrash the system.
E.g. in the current code, reclaiming 10 pages from an enclave with actively
running threads will generate one round of IPIs to CPUs associated with the
enclave (based on the mm struct).  Going to per-page reclaim will likely result
in 10 rounds of IPIs as threads will reenter the enclave immediately after each
IPI wave.

Having to grab the section spinlock for every page is also (very) problematic.
Reclaiming one page at a time makes it nigh impossible for the reclaimer to
keep up as every allocation attempt acquires the spinlock.  I.e. the reclaimer
has to contend with every CPU that is faulting in an EPC page or is adding a
page to the enclave.  In my experiments with the EPC cgroup, even batching 16
pages may be insufficient to make "forward progress".  That's not an apples to
apples comparison, but it's a rough equivalent of what will happen with the
reclaim thread versus EPC page faults.  We can (and should) play with scaling
the number of reclaim threads, but at this stage, that's an exercise best left
to post-upstreaming.

I can't do A/B testing to provide numbers, because the changes in Jarkko's tree
break basic reclaim.  Which is a nice segue into my last point: this is by far
the most subtle code in the SGX code base; I really, really don't want to be
making last minute changes in this area unless they are absolutely necessary or
obviously benign.  Even if/when we get the basic reclaim functional again, and
assuming it doesn't have performance issues, I wouldn't be comfortable merging
the code without hammering it with the EPC cgroup tests for multiple days (on
top of the 1+ days to rebased the EPC cgroup).  Past testing with the cgroup
found multiple bugs with races between CPUs that required hitting a window that
was open for less than 10 instructions.
Jarkko Sakkinen Sept. 29, 2020, 3:50 a.m. UTC | #9
On Mon, Sep 28, 2020 at 06:14:39PM -0700, Sean Christopherson wrote:
> On Tue, Sep 22, 2020 at 05:03:23PM +0300, Jarkko Sakkinen wrote:
> > On Tue, Sep 22, 2020 at 12:45:38PM +0200, Borislav Petkov wrote:
> > > > +	spin_lock(&sgx_active_page_list_lock);
> > > > +	for (i = 0; i < SGX_NR_TO_SCAN; i++) {
> > > > +		if (list_empty(&sgx_active_page_list))
> > > 
> > > Isn't it enough to do this once, i.e., not in the loop? You're holding
> > > sgx_active_page_list_lock...
> 
> Argh, I missed this until I looked at Jarkko's updated tree.
> 
> The reason for checking list_empty() on every iteration is that the loop is
> greedy, i.e. it tries to grab and reclaim up to 16 (SGX_NR_TO_SCAN) EPC pages
> at a time.
> 
> > I think that would make sense. Distantly analogous to the EINIT
> > discussion. Too complex code for yet to be known problem workloads I'd
> > say.
> 
> Nooooo.  Please no.

I added this comment in the beginning of the sgx_reclaim_pages() based
on your response:

/*
 * Take a fixed number of pages from the head of the active page pool and
 * reclaim them to the enclave's private shmem files. Skip the pages, which have
 * been accessed since the last scan. Move those pages to the tail of active
 * page pool so that the pages get scanned in LRU like fashion.
 *
 * Batch process a chunk of pages (at the moment 16) in order to degrade amount
 * of IPI's and ETRACK's potentially required. sgx_encl_ewb() does degrade a bit
 * among the HW threads with three stage EWB pipeline (EWB, ETRACK + EWB and IPI
 * + EWB) but not sufficiently. Reclaiming one page at a time would also be
 * problematic as it would increase the lock contention too much, which would
 * halt forward progress.
 */

And reverted reclaimer patch as it was. Do you have anything in mind
that I should add or modify in it?

/Jarkko
Sean Christopherson Sept. 29, 2020, 8:35 a.m. UTC | #10
On Tue, Sep 29, 2020 at 06:50:10AM +0300, Jarkko Sakkinen wrote:
> On Mon, Sep 28, 2020 at 06:14:39PM -0700, Sean Christopherson wrote:
> > On Tue, Sep 22, 2020 at 05:03:23PM +0300, Jarkko Sakkinen wrote:
> > > On Tue, Sep 22, 2020 at 12:45:38PM +0200, Borislav Petkov wrote:
> > > > > +	spin_lock(&sgx_active_page_list_lock);
> > > > > +	for (i = 0; i < SGX_NR_TO_SCAN; i++) {
> > > > > +		if (list_empty(&sgx_active_page_list))
> > > > 
> > > > Isn't it enough to do this once, i.e., not in the loop? You're holding
> > > > sgx_active_page_list_lock...
> > 
> > Argh, I missed this until I looked at Jarkko's updated tree.
> > 
> > The reason for checking list_empty() on every iteration is that the loop is
> > greedy, i.e. it tries to grab and reclaim up to 16 (SGX_NR_TO_SCAN) EPC pages
> > at a time.
> > 
> > > I think that would make sense. Distantly analogous to the EINIT
> > > discussion. Too complex code for yet to be known problem workloads I'd
> > > say.
> > 
> > Nooooo.  Please no.
> 
> I added this comment in the beginning of the sgx_reclaim_pages() based
> on your response:
> 
> /*
>  * Take a fixed number of pages from the head of the active page pool and
>  * reclaim them to the enclave's private shmem files. Skip the pages, which have
>  * been accessed since the last scan. Move those pages to the tail of active
>  * page pool so that the pages get scanned in LRU like fashion.
>  *
>  * Batch process a chunk of pages (at the moment 16) in order to degrade amount
>  * of IPI's and ETRACK's potentially required. sgx_encl_ewb() does degrade a bit
>  * among the HW threads with three stage EWB pipeline (EWB, ETRACK + EWB and IPI
>  * + EWB) but not sufficiently. Reclaiming one page at a time would also be
>  * problematic as it would increase the lock contention too much, which would
>  * halt forward progress.
>  */
> 
> And reverted reclaimer patch as it was. Do you have anything in mind
> that I should add or modify in it?

Nope, can't think of anything.
diff mbox series

Patch

diff --git a/arch/x86/kernel/cpu/sgx/driver.c b/arch/x86/kernel/cpu/sgx/driver.c
index d01b28f7ce4a..0446781cc7a2 100644
--- a/arch/x86/kernel/cpu/sgx/driver.c
+++ b/arch/x86/kernel/cpu/sgx/driver.c
@@ -29,6 +29,7 @@  static int sgx_open(struct inode *inode, struct file *file)
 	atomic_set(&encl->flags, 0);
 	kref_init(&encl->refcount);
 	xa_init(&encl->page_array);
+	INIT_LIST_HEAD(&encl->va_pages);
 	mutex_init(&encl->lock);
 	INIT_LIST_HEAD(&encl->mm_list);
 	spin_lock_init(&encl->mm_lock);
diff --git a/arch/x86/kernel/cpu/sgx/encl.c b/arch/x86/kernel/cpu/sgx/encl.c
index c2c4a77af36b..11ec2df59b54 100644
--- a/arch/x86/kernel/cpu/sgx/encl.c
+++ b/arch/x86/kernel/cpu/sgx/encl.c
@@ -12,9 +12,84 @@ 
 #include "encls.h"
 #include "sgx.h"
 
+static int __sgx_encl_eldu(struct sgx_encl_page *encl_page,
+			   struct sgx_epc_page *epc_page,
+			   struct sgx_epc_page *secs_page)
+{
+	unsigned long va_offset = SGX_ENCL_PAGE_VA_OFFSET(encl_page);
+	struct sgx_encl *encl = encl_page->encl;
+	struct sgx_pageinfo pginfo;
+	struct sgx_backing b;
+	pgoff_t page_index;
+	int ret;
+
+	if (secs_page)
+		page_index = SGX_ENCL_PAGE_INDEX(encl_page);
+	else
+		page_index = PFN_DOWN(encl->size);
+
+	ret = sgx_encl_get_backing(encl, page_index, &b);
+	if (ret)
+		return ret;
+
+	pginfo.addr = SGX_ENCL_PAGE_ADDR(encl_page);
+	pginfo.contents = (unsigned long)kmap_atomic(b.contents);
+	pginfo.metadata = (unsigned long)kmap_atomic(b.pcmd) +
+			  b.pcmd_offset;
+
+	if (secs_page)
+		pginfo.secs = (u64)sgx_get_epc_addr(secs_page);
+	else
+		pginfo.secs = 0;
+
+	ret = __eldu(&pginfo, sgx_get_epc_addr(epc_page),
+		     sgx_get_epc_addr(encl_page->va_page->epc_page) +
+				      va_offset);
+	if (ret) {
+		if (encls_failed(ret))
+			ENCLS_WARN(ret, "ELDU");
+
+		ret = -EFAULT;
+	}
+
+	kunmap_atomic((void *)(unsigned long)(pginfo.metadata - b.pcmd_offset));
+	kunmap_atomic((void *)(unsigned long)pginfo.contents);
+
+	sgx_encl_put_backing(&b, false);
+
+	return ret;
+}
+
+static struct sgx_epc_page *sgx_encl_eldu(struct sgx_encl_page *encl_page,
+					  struct sgx_epc_page *secs_page)
+{
+	unsigned long va_offset = SGX_ENCL_PAGE_VA_OFFSET(encl_page);
+	struct sgx_encl *encl = encl_page->encl;
+	struct sgx_epc_page *epc_page;
+	int ret;
+
+	epc_page = sgx_alloc_epc_page(encl_page, false);
+	if (IS_ERR(epc_page))
+		return epc_page;
+
+	ret = __sgx_encl_eldu(encl_page, epc_page, secs_page);
+	if (ret) {
+		sgx_free_epc_page(epc_page);
+		return ERR_PTR(ret);
+	}
+
+	sgx_free_va_slot(encl_page->va_page, va_offset);
+	list_move(&encl_page->va_page->list, &encl->va_pages);
+	encl_page->desc &= ~SGX_ENCL_PAGE_VA_OFFSET_MASK;
+	encl_page->epc_page = epc_page;
+
+	return epc_page;
+}
+
 static struct sgx_encl_page *sgx_encl_load_page(struct sgx_encl *encl,
 						unsigned long addr)
 {
+	struct sgx_epc_page *epc_page;
 	struct sgx_encl_page *entry;
 	unsigned int flags;
 
@@ -33,10 +108,27 @@  static struct sgx_encl_page *sgx_encl_load_page(struct sgx_encl *encl,
 		return ERR_PTR(-EFAULT);
 
 	/* Page is already resident in the EPC. */
-	if (entry->epc_page)
+	if (entry->epc_page) {
+		if (entry->desc & SGX_ENCL_PAGE_RECLAIMED)
+			return ERR_PTR(-EBUSY);
+
 		return entry;
+	}
+
+	if (!(encl->secs.epc_page)) {
+		epc_page = sgx_encl_eldu(&encl->secs, NULL);
+		if (IS_ERR(epc_page))
+			return ERR_CAST(epc_page);
+	}
+
+	epc_page = sgx_encl_eldu(entry, encl->secs.epc_page);
+	if (IS_ERR(epc_page))
+		return ERR_CAST(epc_page);
 
-	return ERR_PTR(-EFAULT);
+	encl->secs_child_cnt++;
+	sgx_mark_page_reclaimable(entry->epc_page);
+
+	return entry;
 }
 
 static void sgx_mmu_notifier_release(struct mmu_notifier *mn,
@@ -132,6 +224,9 @@  int sgx_encl_mm_add(struct sgx_encl *encl, struct mm_struct *mm)
 
 	spin_lock(&encl->mm_lock);
 	list_add_rcu(&encl_mm->list, &encl->mm_list);
+	/* Pairs with smp_rmb() in sgx_reclaimer_block(). */
+	smp_wmb();
+	encl->mm_list_version++;
 	spin_unlock(&encl->mm_lock);
 
 	return 0;
@@ -179,6 +274,8 @@  static unsigned int sgx_vma_fault(struct vm_fault *vmf)
 		goto out;
 	}
 
+	sgx_encl_test_and_clear_young(vma->vm_mm, entry);
+
 out:
 	mutex_unlock(&encl->lock);
 	return ret;
@@ -280,6 +377,7 @@  int sgx_encl_find(struct mm_struct *mm, unsigned long addr,
  */
 void sgx_encl_destroy(struct sgx_encl *encl)
 {
+	struct sgx_va_page *va_page;
 	struct sgx_encl_page *entry;
 	unsigned long index;
 
@@ -287,6 +385,13 @@  void sgx_encl_destroy(struct sgx_encl *encl)
 
 	xa_for_each(&encl->page_array, index, entry) {
 		if (entry->epc_page) {
+			/*
+			 * The page and its radix tree entry cannot be freed
+			 * if the page is being held by the reclaimer.
+			 */
+			if (sgx_unmark_page_reclaimable(entry->epc_page))
+				continue;
+
 			sgx_free_epc_page(entry->epc_page);
 			encl->secs_child_cnt--;
 			entry->epc_page = NULL;
@@ -301,6 +406,19 @@  void sgx_encl_destroy(struct sgx_encl *encl)
 		sgx_free_epc_page(encl->secs.epc_page);
 		encl->secs.epc_page = NULL;
 	}
+
+	/*
+	 * The reclaimer is responsible for checking SGX_ENCL_DEAD before doing
+	 * EWB, thus it's safe to free VA pages even if the reclaimer holds a
+	 * reference to the enclave.
+	 */
+	while (!list_empty(&encl->va_pages)) {
+		va_page = list_first_entry(&encl->va_pages, struct sgx_va_page,
+					   list);
+		list_del(&va_page->list);
+		sgx_free_epc_page(va_page->epc_page);
+		kfree(va_page);
+	}
 }
 
 /**
@@ -329,3 +447,221 @@  void sgx_encl_release(struct kref *ref)
 
 	kfree(encl);
 }
+
+static struct page *sgx_encl_get_backing_page(struct sgx_encl *encl,
+					      pgoff_t index)
+{
+	struct inode *inode = encl->backing->f_path.dentry->d_inode;
+	struct address_space *mapping = inode->i_mapping;
+	gfp_t gfpmask = mapping_gfp_mask(mapping);
+
+	return shmem_read_mapping_page_gfp(mapping, index, gfpmask);
+}
+
+/**
+ * sgx_encl_get_backing() - Pin the backing storage
+ * @encl:	an enclave pointer
+ * @page_index:	enclave page index
+ * @backing:	data for accessing backing storage for the page
+ *
+ * Pin the backing storage pages for storing the encrypted contents and Paging
+ * Crypto MetaData (PCMD) of an enclave page.
+ *
+ * Return:
+ *   0 on success,
+ *   -errno otherwise.
+ */
+int sgx_encl_get_backing(struct sgx_encl *encl, unsigned long page_index,
+			 struct sgx_backing *backing)
+{
+	pgoff_t pcmd_index = PFN_DOWN(encl->size) + 1 + (page_index >> 5);
+	struct page *contents;
+	struct page *pcmd;
+
+	contents = sgx_encl_get_backing_page(encl, page_index);
+	if (IS_ERR(contents))
+		return PTR_ERR(contents);
+
+	pcmd = sgx_encl_get_backing_page(encl, pcmd_index);
+	if (IS_ERR(pcmd)) {
+		put_page(contents);
+		return PTR_ERR(pcmd);
+	}
+
+	backing->page_index = page_index;
+	backing->contents = contents;
+	backing->pcmd = pcmd;
+	backing->pcmd_offset =
+		(page_index & (PAGE_SIZE / sizeof(struct sgx_pcmd) - 1)) *
+		sizeof(struct sgx_pcmd);
+
+	return 0;
+}
+
+/**
+ * sgx_encl_put_backing() - Unpin the backing storage
+ * @backing:	data for accessing backing storage for the page
+ * @do_write:	mark pages dirty
+ */
+void sgx_encl_put_backing(struct sgx_backing *backing, bool do_write)
+{
+	if (do_write) {
+		set_page_dirty(backing->pcmd);
+		set_page_dirty(backing->contents);
+	}
+
+	put_page(backing->pcmd);
+	put_page(backing->contents);
+}
+
+static int sgx_encl_test_and_clear_young_cb(pte_t *ptep, unsigned long addr,
+					    void *data)
+{
+	pte_t pte;
+	int ret;
+
+	ret = pte_young(*ptep);
+	if (ret) {
+		pte = pte_mkold(*ptep);
+		set_pte_at((struct mm_struct *)data, addr, ptep, pte);
+	}
+
+	return ret;
+}
+
+/**
+ * sgx_encl_test_and_clear_young() - Test and reset the accessed bit
+ * @mm:		mm_struct that is checked
+ * @page:	enclave page to be tested for recent access
+ *
+ * Checks the Access (A) bit from the PTE corresponding to the enclave page and
+ * clears it.
+ *
+ * Return: 1 if the page has been recently accessed and 0 if not.
+ */
+int sgx_encl_test_and_clear_young(struct mm_struct *mm,
+				  struct sgx_encl_page *page)
+{
+	unsigned long addr = SGX_ENCL_PAGE_ADDR(page);
+	struct sgx_encl *encl = page->encl;
+	struct vm_area_struct *vma;
+	int ret;
+
+	ret = sgx_encl_find(mm, addr, &vma);
+	if (ret)
+		return 0;
+
+	if (encl != vma->vm_private_data)
+		return 0;
+
+	ret = apply_to_page_range(vma->vm_mm, addr, PAGE_SIZE,
+				  sgx_encl_test_and_clear_young_cb, vma->vm_mm);
+	if (ret < 0)
+		return 0;
+
+	return ret;
+}
+
+/**
+ * sgx_encl_reserve_page() - Reserve an enclave page
+ * @encl:	an enclave pointer
+ * @addr:	a page address
+ *
+ * Load an enclave page and lock the enclave so that the page can be used by
+ * EDBG* and EMOD*.
+ *
+ * Return:
+ *   an enclave page on success
+ *   -EFAULT	if the load fails
+ */
+struct sgx_encl_page *sgx_encl_reserve_page(struct sgx_encl *encl,
+					    unsigned long addr)
+{
+	struct sgx_encl_page *entry;
+
+	for ( ; ; ) {
+		mutex_lock(&encl->lock);
+
+		entry = sgx_encl_load_page(encl, addr);
+		if (PTR_ERR(entry) != -EBUSY)
+			break;
+
+		mutex_unlock(&encl->lock);
+	}
+
+	if (IS_ERR(entry))
+		mutex_unlock(&encl->lock);
+
+	return entry;
+}
+
+/**
+ * sgx_alloc_va_page() - Allocate a Version Array (VA) page
+ *
+ * Allocate a free EPC page and convert it to a Version Array (VA) page.
+ *
+ * Return:
+ *   a VA page,
+ *   -errno otherwise
+ */
+struct sgx_epc_page *sgx_alloc_va_page(void)
+{
+	struct sgx_epc_page *epc_page;
+	int ret;
+
+	epc_page = sgx_alloc_epc_page(NULL, true);
+	if (IS_ERR(epc_page))
+		return ERR_CAST(epc_page);
+
+	ret = __epa(sgx_get_epc_addr(epc_page));
+	if (ret) {
+		WARN_ONCE(1, "EPA returned %d (0x%x)", ret, ret);
+		sgx_free_epc_page(epc_page);
+		return ERR_PTR(-EFAULT);
+	}
+
+	return epc_page;
+}
+
+/**
+ * sgx_alloc_va_slot - allocate a VA slot
+ * @va_page:	a &struct sgx_va_page instance
+ *
+ * Allocates a slot from a &struct sgx_va_page instance.
+ *
+ * Return: offset of the slot inside the VA page
+ */
+unsigned int sgx_alloc_va_slot(struct sgx_va_page *va_page)
+{
+	int slot = find_first_zero_bit(va_page->slots, SGX_VA_SLOT_COUNT);
+
+	if (slot < SGX_VA_SLOT_COUNT)
+		set_bit(slot, va_page->slots);
+
+	return slot << 3;
+}
+
+/**
+ * sgx_free_va_slot - free a VA slot
+ * @va_page:	a &struct sgx_va_page instance
+ * @offset:	offset of the slot inside the VA page
+ *
+ * Frees a slot from a &struct sgx_va_page instance.
+ */
+void sgx_free_va_slot(struct sgx_va_page *va_page, unsigned int offset)
+{
+	clear_bit(offset >> 3, va_page->slots);
+}
+
+/**
+ * sgx_va_page_full - is the VA page full?
+ * @va_page:	a &struct sgx_va_page instance
+ *
+ * Return: true if all slots have been taken
+ */
+bool sgx_va_page_full(struct sgx_va_page *va_page)
+{
+	int slot = find_first_zero_bit(va_page->slots, SGX_VA_SLOT_COUNT);
+
+	return slot == SGX_VA_SLOT_COUNT;
+}
diff --git a/arch/x86/kernel/cpu/sgx/encl.h b/arch/x86/kernel/cpu/sgx/encl.h
index 0448d22d3010..11dcf4e7fb3e 100644
--- a/arch/x86/kernel/cpu/sgx/encl.h
+++ b/arch/x86/kernel/cpu/sgx/encl.h
@@ -19,6 +19,10 @@ 
 
 /**
  * enum sgx_encl_page_desc - defines bits for an enclave page's descriptor
+ * %SGX_ENCL_PAGE_RECLAIMED:		The page is in the process of being
+ *					reclaimed.
+ * %SGX_ENCL_PAGE_VA_OFFSET_MASK:	Holds the offset in the Version Array
+ *					(VA) page for a swapped page.
  * %SGX_ENCL_PAGE_ADDR_MASK:		Holds the virtual address of the page.
  *
  * The page address for SECS is zero and is used by the subsystem to recognize
@@ -26,16 +30,23 @@ 
  */
 enum sgx_encl_page_desc {
 	/* Bits 11:3 are available when the page is not swapped. */
+	SGX_ENCL_PAGE_RECLAIMED		= BIT(3),
+	SGX_ENCL_PAGE_VA_OFFSET_MASK	= GENMASK_ULL(11, 3),
 	SGX_ENCL_PAGE_ADDR_MASK		= PAGE_MASK,
 };
 
 #define SGX_ENCL_PAGE_ADDR(page) \
 	((page)->desc & SGX_ENCL_PAGE_ADDR_MASK)
+#define SGX_ENCL_PAGE_VA_OFFSET(page) \
+	((page)->desc & SGX_ENCL_PAGE_VA_OFFSET_MASK)
+#define SGX_ENCL_PAGE_INDEX(page) \
+	PFN_DOWN((page)->desc - (page)->encl->base)
 
 struct sgx_encl_page {
 	unsigned long desc;
 	unsigned long vm_max_prot_bits;
 	struct sgx_epc_page *epc_page;
+	struct sgx_va_page *va_page;
 	struct sgx_encl *encl;
 };
 
@@ -61,6 +72,7 @@  struct sgx_encl {
 	struct mutex lock;
 	struct list_head mm_list;
 	spinlock_t mm_lock;
+	unsigned long mm_list_version;
 	struct file *backing;
 	struct kref refcount;
 	struct srcu_struct srcu;
@@ -68,12 +80,21 @@  struct sgx_encl {
 	unsigned long size;
 	unsigned long ssaframesize;
 	struct xarray page_array;
+	struct list_head va_pages;
 	struct sgx_encl_page secs;
 	cpumask_t cpumask;
 	unsigned long attributes;
 	unsigned long attributes_mask;
 };
 
+#define SGX_VA_SLOT_COUNT 512
+
+struct sgx_va_page {
+	struct sgx_epc_page *epc_page;
+	DECLARE_BITMAP(slots, SGX_VA_SLOT_COUNT);
+	struct list_head list;
+};
+
 extern const struct vm_operations_struct sgx_vm_ops;
 
 int sgx_encl_find(struct mm_struct *mm, unsigned long addr,
@@ -84,4 +105,24 @@  int sgx_encl_mm_add(struct sgx_encl *encl, struct mm_struct *mm);
 int sgx_encl_may_map(struct sgx_encl *encl, unsigned long start,
 		     unsigned long end, unsigned long vm_flags);
 
+struct sgx_backing {
+	pgoff_t page_index;
+	struct page *contents;
+	struct page *pcmd;
+	unsigned long pcmd_offset;
+};
+
+int sgx_encl_get_backing(struct sgx_encl *encl, unsigned long page_index,
+			 struct sgx_backing *backing);
+void sgx_encl_put_backing(struct sgx_backing *backing, bool do_write);
+int sgx_encl_test_and_clear_young(struct mm_struct *mm,
+				  struct sgx_encl_page *page);
+struct sgx_encl_page *sgx_encl_reserve_page(struct sgx_encl *encl,
+					    unsigned long addr);
+
+struct sgx_epc_page *sgx_alloc_va_page(void);
+unsigned int sgx_alloc_va_slot(struct sgx_va_page *va_page);
+void sgx_free_va_slot(struct sgx_va_page *va_page, unsigned int offset);
+bool sgx_va_page_full(struct sgx_va_page *va_page);
+
 #endif /* _X86_ENCL_H */
diff --git a/arch/x86/kernel/cpu/sgx/ioctl.c b/arch/x86/kernel/cpu/sgx/ioctl.c
index 4227bca7b477..4264dc8c2a4f 100644
--- a/arch/x86/kernel/cpu/sgx/ioctl.c
+++ b/arch/x86/kernel/cpu/sgx/ioctl.c
@@ -19,6 +19,43 @@ 
 /* A per-cpu cache for the last known values of IA32_SGXLEPUBKEYHASHx MSRs. */
 static DEFINE_PER_CPU(u64 [4], sgx_lepubkeyhash_cache);
 
+static struct sgx_va_page *sgx_encl_grow(struct sgx_encl *encl)
+{
+	struct sgx_va_page *va_page = NULL;
+	void *err;
+
+	BUILD_BUG_ON(SGX_VA_SLOT_COUNT !=
+		(SGX_ENCL_PAGE_VA_OFFSET_MASK >> 3) + 1);
+
+	if (!(encl->page_cnt % SGX_VA_SLOT_COUNT)) {
+		va_page = kzalloc(sizeof(*va_page), GFP_KERNEL);
+		if (!va_page)
+			return ERR_PTR(-ENOMEM);
+
+		va_page->epc_page = sgx_alloc_va_page();
+		if (IS_ERR(va_page->epc_page)) {
+			err = ERR_CAST(va_page->epc_page);
+			kfree(va_page);
+			return err;
+		}
+
+		WARN_ON_ONCE(encl->page_cnt % SGX_VA_SLOT_COUNT);
+	}
+	encl->page_cnt++;
+	return va_page;
+}
+
+static void sgx_encl_shrink(struct sgx_encl *encl, struct sgx_va_page *va_page)
+{
+	encl->page_cnt--;
+
+	if (va_page) {
+		sgx_free_epc_page(va_page->epc_page);
+		list_del(&va_page->list);
+		kfree(va_page);
+	}
+}
+
 static u32 sgx_calc_ssa_frame_size(u32 miscselect, u64 xfrm)
 {
 	u32 size_max = PAGE_SIZE;
@@ -86,24 +123,34 @@  static int sgx_encl_create(struct sgx_encl *encl, struct sgx_secs *secs)
 {
 	unsigned long encl_size = secs->size + PAGE_SIZE;
 	struct sgx_epc_page *secs_epc;
+	struct sgx_va_page *va_page;
 	struct sgx_pageinfo pginfo;
 	struct sgx_secinfo secinfo;
 	struct file *backing;
 	long ret;
 
+	va_page = sgx_encl_grow(encl);
+	if (IS_ERR(va_page))
+		return PTR_ERR(va_page);
+	else if (va_page)
+		list_add(&va_page->list, &encl->va_pages);
+
 	if (sgx_validate_secs(secs)) {
 		pr_debug("invalid SECS\n");
-		return -EINVAL;
+		ret = -EINVAL;
+		goto err_out_shrink;
 	}
 
 	backing = shmem_file_setup("SGX backing", encl_size + (encl_size >> 5),
 				   VM_NORESERVE);
-	if (IS_ERR(backing))
-		return PTR_ERR(backing);
+	if (IS_ERR(backing)) {
+		ret = PTR_ERR(backing);
+		goto err_out_shrink;
+	}
 
 	encl->backing = backing;
 
-	secs_epc = __sgx_alloc_epc_page();
+	secs_epc = sgx_alloc_epc_page(&encl->secs, true);
 	if (IS_ERR(secs_epc)) {
 		ret = PTR_ERR(secs_epc);
 		goto err_out_backing;
@@ -151,6 +198,9 @@  static int sgx_encl_create(struct sgx_encl *encl, struct sgx_secs *secs)
 	fput(encl->backing);
 	encl->backing = NULL;
 
+err_out_shrink:
+	sgx_encl_shrink(encl, va_page);
+
 	return ret;
 }
 
@@ -323,21 +373,35 @@  static int sgx_encl_add_page(struct sgx_encl *encl, unsigned long src,
 {
 	struct sgx_encl_page *encl_page;
 	struct sgx_epc_page *epc_page;
+	struct sgx_va_page *va_page;
 	int ret;
 
 	encl_page = sgx_encl_page_alloc(encl, offset, secinfo->flags);
 	if (IS_ERR(encl_page))
 		return PTR_ERR(encl_page);
 
-	epc_page = __sgx_alloc_epc_page();
+	epc_page = sgx_alloc_epc_page(encl_page, true);
 	if (IS_ERR(epc_page)) {
 		kfree(encl_page);
 		return PTR_ERR(epc_page);
 	}
 
+	va_page = sgx_encl_grow(encl);
+	if (IS_ERR(va_page)) {
+		ret = PTR_ERR(va_page);
+		goto err_out_free;
+	}
+
 	mmap_read_lock(current->mm);
 	mutex_lock(&encl->lock);
 
+	/*
+	 * Adding to encl->va_pages must be done under encl->lock.  Ditto for
+	 * deleting (via sgx_encl_shrink()) in the error path.
+	 */
+	if (va_page)
+		list_add(&va_page->list, &encl->va_pages);
+
 	/*
 	 * Insert prior to EADD in case of OOM.  EADD modifies MRENCLAVE, i.e.
 	 * can't be gracefully unwound, while failure on EADD/EXTEND is limited
@@ -368,6 +432,7 @@  static int sgx_encl_add_page(struct sgx_encl *encl, unsigned long src,
 			goto err_out;
 	}
 
+	sgx_mark_page_reclaimable(encl_page->epc_page);
 	mutex_unlock(&encl->lock);
 	mmap_read_unlock(current->mm);
 	return ret;
@@ -376,9 +441,11 @@  static int sgx_encl_add_page(struct sgx_encl *encl, unsigned long src,
 	xa_erase(&encl->page_array, PFN_DOWN(encl_page->desc));
 
 err_out_unlock:
+	sgx_encl_shrink(encl, va_page);
 	mutex_unlock(&encl->lock);
 	mmap_read_unlock(current->mm);
 
+err_out_free:
 	sgx_free_epc_page(epc_page);
 	kfree(encl_page);
 
diff --git a/arch/x86/kernel/cpu/sgx/main.c b/arch/x86/kernel/cpu/sgx/main.c
index 4137254fb29e..3594d37d545f 100644
--- a/arch/x86/kernel/cpu/sgx/main.c
+++ b/arch/x86/kernel/cpu/sgx/main.c
@@ -16,6 +16,378 @@ 
 struct sgx_epc_section sgx_epc_sections[SGX_MAX_EPC_SECTIONS];
 static int sgx_nr_epc_sections;
 static struct task_struct *ksgxswapd_tsk;
+static DECLARE_WAIT_QUEUE_HEAD(ksgxswapd_waitq);
+static LIST_HEAD(sgx_active_page_list);
+static DEFINE_SPINLOCK(sgx_active_page_list_lock);
+
+/**
+ * sgx_mark_page_reclaimable() - Mark a page as reclaimable
+ * @page:	EPC page
+ *
+ * Mark a page as reclaimable and add it to the active page list. Pages
+ * are automatically removed from the active list when freed.
+ */
+void sgx_mark_page_reclaimable(struct sgx_epc_page *page)
+{
+	spin_lock(&sgx_active_page_list_lock);
+	page->desc |= SGX_EPC_PAGE_RECLAIMABLE;
+	list_add_tail(&page->list, &sgx_active_page_list);
+	spin_unlock(&sgx_active_page_list_lock);
+}
+
+/**
+ * sgx_unmark_page_reclaimable() - Remove a page from the reclaim list
+ * @page:	EPC page
+ *
+ * Clear the reclaimable flag and remove the page from the active page list.
+ *
+ * Return:
+ *   0 on success,
+ *   -EBUSY if the page is in the process of being reclaimed
+ */
+int sgx_unmark_page_reclaimable(struct sgx_epc_page *page)
+{
+	/*
+	 * Remove the page from the active list if necessary.  If the page
+	 * is actively being reclaimed, i.e. RECLAIMABLE is set but the
+	 * page isn't on the active list, return -EBUSY as we can't free
+	 * the page at this time since it is "owned" by the reclaimer.
+	 */
+	spin_lock(&sgx_active_page_list_lock);
+	if (page->desc & SGX_EPC_PAGE_RECLAIMABLE) {
+		if (list_empty(&page->list)) {
+			spin_unlock(&sgx_active_page_list_lock);
+			return -EBUSY;
+		}
+		list_del(&page->list);
+		page->desc &= ~SGX_EPC_PAGE_RECLAIMABLE;
+	}
+	spin_unlock(&sgx_active_page_list_lock);
+
+	return 0;
+}
+
+static bool sgx_reclaimer_age(struct sgx_epc_page *epc_page)
+{
+	struct sgx_encl_page *page = epc_page->owner;
+	struct sgx_encl *encl = page->encl;
+	struct sgx_encl_mm *encl_mm;
+	bool ret = true;
+	int idx;
+
+	idx = srcu_read_lock(&encl->srcu);
+
+	list_for_each_entry_rcu(encl_mm, &encl->mm_list, list) {
+		if (!mmget_not_zero(encl_mm->mm))
+			continue;
+
+		mmap_read_lock(encl_mm->mm);
+		ret = !sgx_encl_test_and_clear_young(encl_mm->mm, page);
+		mmap_read_unlock(encl_mm->mm);
+
+		mmput_async(encl_mm->mm);
+
+		if (!ret || (atomic_read(&encl->flags) & SGX_ENCL_DEAD))
+			break;
+	}
+
+	srcu_read_unlock(&encl->srcu, idx);
+
+	if (!ret && !(atomic_read(&encl->flags) & SGX_ENCL_DEAD))
+		return false;
+
+	return true;
+}
+
+static void sgx_reclaimer_block(struct sgx_epc_page *epc_page)
+{
+	struct sgx_encl_page *page = epc_page->owner;
+	unsigned long addr = SGX_ENCL_PAGE_ADDR(page);
+	struct sgx_encl *encl = page->encl;
+	unsigned long mm_list_version;
+	struct sgx_encl_mm *encl_mm;
+	struct vm_area_struct *vma;
+	int idx, ret;
+
+	do {
+		mm_list_version = encl->mm_list_version;
+
+		/* Pairs with smp_rmb() in sgx_encl_mm_add(). */
+		smp_rmb();
+
+		idx = srcu_read_lock(&encl->srcu);
+
+		list_for_each_entry_rcu(encl_mm, &encl->mm_list, list) {
+			if (!mmget_not_zero(encl_mm->mm))
+				continue;
+
+			mmap_read_lock(encl_mm->mm);
+
+			ret = sgx_encl_find(encl_mm->mm, addr, &vma);
+			if (!ret && encl == vma->vm_private_data)
+				zap_vma_ptes(vma, addr, PAGE_SIZE);
+
+			mmap_read_unlock(encl_mm->mm);
+
+			mmput_async(encl_mm->mm);
+		}
+
+		srcu_read_unlock(&encl->srcu, idx);
+	} while (unlikely(encl->mm_list_version != mm_list_version));
+
+	mutex_lock(&encl->lock);
+
+	if (!(atomic_read(&encl->flags) & SGX_ENCL_DEAD)) {
+		ret = __eblock(sgx_get_epc_addr(epc_page));
+		if (encls_failed(ret))
+			ENCLS_WARN(ret, "EBLOCK");
+	}
+
+	mutex_unlock(&encl->lock);
+}
+
+static int __sgx_encl_ewb(struct sgx_epc_page *epc_page, void *va_slot,
+			  struct sgx_backing *backing)
+{
+	struct sgx_pageinfo pginfo;
+	int ret;
+
+	pginfo.addr = 0;
+	pginfo.secs = 0;
+
+	pginfo.contents = (unsigned long)kmap_atomic(backing->contents);
+	pginfo.metadata = (unsigned long)kmap_atomic(backing->pcmd) +
+			  backing->pcmd_offset;
+
+	ret = __ewb(&pginfo, sgx_get_epc_addr(epc_page), va_slot);
+
+	kunmap_atomic((void *)(unsigned long)(pginfo.metadata -
+					      backing->pcmd_offset));
+	kunmap_atomic((void *)(unsigned long)pginfo.contents);
+
+	return ret;
+}
+
+static void sgx_ipi_cb(void *info)
+{
+}
+
+static const cpumask_t *sgx_encl_ewb_cpumask(struct sgx_encl *encl)
+{
+	cpumask_t *cpumask = &encl->cpumask;
+	struct sgx_encl_mm *encl_mm;
+	int idx;
+
+	/*
+	 * Can race with sgx_encl_mm_add(), but ETRACK has already been
+	 * executed, which means that the CPUs running in the new mm will enter
+	 * into the enclave with a fresh epoch.
+	 */
+	cpumask_clear(cpumask);
+
+	idx = srcu_read_lock(&encl->srcu);
+
+	list_for_each_entry_rcu(encl_mm, &encl->mm_list, list) {
+		if (!mmget_not_zero(encl_mm->mm))
+			continue;
+
+		cpumask_or(cpumask, cpumask, mm_cpumask(encl_mm->mm));
+
+		mmput_async(encl_mm->mm);
+	}
+
+	srcu_read_unlock(&encl->srcu, idx);
+
+	return cpumask;
+}
+
+static void sgx_encl_ewb(struct sgx_epc_page *epc_page,
+			 struct sgx_backing *backing)
+{
+	struct sgx_encl_page *encl_page = epc_page->owner;
+	struct sgx_encl *encl = encl_page->encl;
+	struct sgx_va_page *va_page;
+	unsigned int va_offset;
+	void *va_slot;
+	int ret;
+
+	encl_page->desc &= ~SGX_ENCL_PAGE_RECLAIMED;
+
+	va_page = list_first_entry(&encl->va_pages, struct sgx_va_page,
+				   list);
+	va_offset = sgx_alloc_va_slot(va_page);
+	va_slot = sgx_get_epc_addr(va_page->epc_page) + va_offset;
+	if (sgx_va_page_full(va_page))
+		list_move_tail(&va_page->list, &encl->va_pages);
+
+	ret = __sgx_encl_ewb(epc_page, va_slot, backing);
+	if (ret == SGX_NOT_TRACKED) {
+		ret = __etrack(sgx_get_epc_addr(encl->secs.epc_page));
+		if (ret) {
+			if (encls_failed(ret))
+				ENCLS_WARN(ret, "ETRACK");
+		}
+
+		ret = __sgx_encl_ewb(epc_page, va_slot, backing);
+		if (ret == SGX_NOT_TRACKED) {
+			/*
+			 * Slow path, send IPIs to kick cpus out of the
+			 * enclave.  Note, it's imperative that the cpu
+			 * mask is generated *after* ETRACK, else we'll
+			 * miss cpus that entered the enclave between
+			 * generating the mask and incrementing epoch.
+			 */
+			on_each_cpu_mask(sgx_encl_ewb_cpumask(encl),
+					 sgx_ipi_cb, NULL, 1);
+			ret = __sgx_encl_ewb(epc_page, va_slot, backing);
+		}
+	}
+
+	if (ret) {
+		if (encls_failed(ret))
+			ENCLS_WARN(ret, "EWB");
+
+		sgx_free_va_slot(va_page, va_offset);
+	} else {
+		encl_page->desc |= va_offset;
+		encl_page->va_page = va_page;
+	}
+}
+
+static void sgx_reclaimer_write(struct sgx_epc_page *epc_page,
+				struct sgx_backing *backing)
+{
+	struct sgx_encl_page *encl_page = epc_page->owner;
+	struct sgx_encl *encl = encl_page->encl;
+	struct sgx_backing secs_backing;
+	int ret;
+
+	mutex_lock(&encl->lock);
+
+	if (atomic_read(&encl->flags) & SGX_ENCL_DEAD) {
+		ret = __eremove(sgx_get_epc_addr(epc_page));
+		ENCLS_WARN(ret, "EREMOVE");
+	} else {
+		sgx_encl_ewb(epc_page, backing);
+	}
+
+	encl_page->epc_page = NULL;
+	encl->secs_child_cnt--;
+
+	if (!encl->secs_child_cnt) {
+		if (atomic_read(&encl->flags) & SGX_ENCL_DEAD) {
+			sgx_free_epc_page(encl->secs.epc_page);
+			encl->secs.epc_page = NULL;
+		} else if (atomic_read(&encl->flags) & SGX_ENCL_INITIALIZED) {
+			ret = sgx_encl_get_backing(encl, PFN_DOWN(encl->size),
+						   &secs_backing);
+			if (ret)
+				goto out;
+
+			sgx_encl_ewb(encl->secs.epc_page, &secs_backing);
+
+			sgx_free_epc_page(encl->secs.epc_page);
+			encl->secs.epc_page = NULL;
+
+			sgx_encl_put_backing(&secs_backing, true);
+		}
+	}
+
+out:
+	mutex_unlock(&encl->lock);
+}
+
+/*
+ * Take a fixed number of pages from the head of the active page pool and
+ * reclaim them to the enclave's private shmem files. Skip the pages, which have
+ * been accessed since the last scan. Move those pages to the tail of active
+ * page pool so that the pages get scanned in LRU like fashion.
+ */
+static void sgx_reclaim_pages(void)
+{
+	struct sgx_epc_page *chunk[SGX_NR_TO_SCAN];
+	struct sgx_backing backing[SGX_NR_TO_SCAN];
+	struct sgx_epc_section *section;
+	struct sgx_encl_page *encl_page;
+	struct sgx_epc_page *epc_page;
+	int cnt = 0;
+	int ret;
+	int i;
+
+	spin_lock(&sgx_active_page_list_lock);
+	for (i = 0; i < SGX_NR_TO_SCAN; i++) {
+		if (list_empty(&sgx_active_page_list))
+			break;
+
+		epc_page = list_first_entry(&sgx_active_page_list,
+					    struct sgx_epc_page, list);
+		list_del_init(&epc_page->list);
+		encl_page = epc_page->owner;
+
+		if (kref_get_unless_zero(&encl_page->encl->refcount) != 0)
+			chunk[cnt++] = epc_page;
+		else
+			/* The owner is freeing the page. No need to add the
+			 * page back to the list of reclaimable pages.
+			 */
+			epc_page->desc &= ~SGX_EPC_PAGE_RECLAIMABLE;
+	}
+	spin_unlock(&sgx_active_page_list_lock);
+
+	for (i = 0; i < cnt; i++) {
+		epc_page = chunk[i];
+		encl_page = epc_page->owner;
+
+		if (!sgx_reclaimer_age(epc_page))
+			goto skip;
+
+		ret = sgx_encl_get_backing(encl_page->encl,
+					   SGX_ENCL_PAGE_INDEX(encl_page),
+					   &backing[i]);
+		if (ret)
+			goto skip;
+
+		mutex_lock(&encl_page->encl->lock);
+		encl_page->desc |= SGX_ENCL_PAGE_RECLAIMED;
+		mutex_unlock(&encl_page->encl->lock);
+		continue;
+
+skip:
+		spin_lock(&sgx_active_page_list_lock);
+		list_add_tail(&epc_page->list, &sgx_active_page_list);
+		spin_unlock(&sgx_active_page_list_lock);
+
+		kref_put(&encl_page->encl->refcount, sgx_encl_release);
+
+		chunk[i] = NULL;
+	}
+
+	for (i = 0; i < cnt; i++) {
+		epc_page = chunk[i];
+		if (epc_page)
+			sgx_reclaimer_block(epc_page);
+	}
+
+	for (i = 0; i < cnt; i++) {
+		epc_page = chunk[i];
+		if (!epc_page)
+			continue;
+
+		encl_page = epc_page->owner;
+		sgx_reclaimer_write(epc_page, &backing[i]);
+		sgx_encl_put_backing(&backing[i], true);
+
+		kref_put(&encl_page->encl->refcount, sgx_encl_release);
+		epc_page->desc &= ~SGX_EPC_PAGE_RECLAIMABLE;
+
+		section = sgx_get_epc_section(epc_page);
+		spin_lock(&section->lock);
+		list_add_tail(&epc_page->list, &section->page_list);
+		section->free_cnt++;
+		spin_unlock(&section->lock);
+	}
+}
+
 
 static void sgx_sanitize_section(struct sgx_epc_section *section)
 {
@@ -44,6 +416,23 @@  static void sgx_sanitize_section(struct sgx_epc_section *section)
 	}
 }
 
+static unsigned long sgx_nr_free_pages(void)
+{
+	unsigned long cnt = 0;
+	int i;
+
+	for (i = 0; i < sgx_nr_epc_sections; i++)
+		cnt += sgx_epc_sections[i].free_cnt;
+
+	return cnt;
+}
+
+static bool sgx_should_reclaim(unsigned long watermark)
+{
+	return sgx_nr_free_pages() < watermark &&
+	       !list_empty(&sgx_active_page_list);
+}
+
 static int ksgxswapd(void *p)
 {
 	int i;
@@ -69,6 +458,20 @@  static int ksgxswapd(void *p)
 			WARN(1, "EPC section %d has unsanitized pages.\n", i);
 	}
 
+	while (!kthread_should_stop()) {
+		if (try_to_freeze())
+			continue;
+
+		wait_event_freezable(ksgxswapd_waitq,
+				     kthread_should_stop() ||
+				     sgx_should_reclaim(SGX_NR_HIGH_PAGES));
+
+		if (sgx_should_reclaim(SGX_NR_HIGH_PAGES))
+			sgx_reclaim_pages();
+
+		cond_resched();
+	}
+
 	return 0;
 }
 
@@ -94,6 +497,7 @@  static struct sgx_epc_page *__sgx_alloc_epc_page_from_section(struct sgx_epc_sec
 
 	page = list_first_entry(&section->page_list, struct sgx_epc_page, list);
 	list_del_init(&page->list);
+	section->free_cnt--;
 
 	return page;
 }
@@ -127,6 +531,57 @@  struct sgx_epc_page *__sgx_alloc_epc_page(void)
 	return ERR_PTR(-ENOMEM);
 }
 
+/**
+ * sgx_alloc_epc_page() - Allocate an EPC page
+ * @owner:	the owner of the EPC page
+ * @reclaim:	reclaim pages if necessary
+ *
+ * Iterate through EPC sections and borrow a free EPC page to the caller. When a
+ * page is no longer needed it must be released with sgx_free_epc_page(). If
+ * @reclaim is set to true, directly reclaim pages when we are out of pages. No
+ * mm's can be locked when @reclaim is set to true.
+ *
+ * Finally, wake up ksgxswapd when the number of pages goes below the watermark
+ * before returning back to the caller.
+ *
+ * Return:
+ *   an EPC page,
+ *   -errno on error
+ */
+struct sgx_epc_page *sgx_alloc_epc_page(void *owner, bool reclaim)
+{
+	struct sgx_epc_page *entry;
+
+	for ( ; ; ) {
+		entry = __sgx_alloc_epc_page();
+		if (!IS_ERR(entry)) {
+			entry->owner = owner;
+			break;
+		}
+
+		if (list_empty(&sgx_active_page_list))
+			return ERR_PTR(-ENOMEM);
+
+		if (!reclaim) {
+			entry = ERR_PTR(-EBUSY);
+			break;
+		}
+
+		if (signal_pending(current)) {
+			entry = ERR_PTR(-ERESTARTSYS);
+			break;
+		}
+
+		sgx_reclaim_pages();
+		schedule();
+	}
+
+	if (sgx_should_reclaim(SGX_NR_LOW_PAGES))
+		wake_up(&ksgxswapd_waitq);
+
+	return entry;
+}
+
 /**
  * sgx_free_epc_page() - Free an EPC page
  * @page:	an EPC page
@@ -138,12 +593,20 @@  void sgx_free_epc_page(struct sgx_epc_page *page)
 	struct sgx_epc_section *section = sgx_get_epc_section(page);
 	int ret;
 
+	/*
+	 * Don't take sgx_active_page_list_lock when asserting the page isn't
+	 * reclaimable, missing a WARN in the very rare case is preferable to
+	 * unnecessarily taking a global lock in the common case.
+	 */
+	WARN_ON_ONCE(page->desc & SGX_EPC_PAGE_RECLAIMABLE);
+
 	ret = __eremove(sgx_get_epc_addr(page));
 	if (WARN_ONCE(ret, "EREMOVE returned %d (0x%x)", ret, ret))
 		return;
 
 	spin_lock(&section->lock);
 	list_add_tail(&page->list, &section->page_list);
+	section->free_cnt++;
 	spin_unlock(&section->lock);
 }
 
@@ -194,6 +657,7 @@  static bool __init sgx_setup_epc_section(u64 addr, u64 size,
 		list_add_tail(&page->list, &section->unsanitized_page_list);
 	}
 
+	section->free_cnt = nr_pages;
 	return true;
 
 err_out:
diff --git a/arch/x86/kernel/cpu/sgx/sgx.h b/arch/x86/kernel/cpu/sgx/sgx.h
index 8d126070db1e..ec4f7b338dbe 100644
--- a/arch/x86/kernel/cpu/sgx/sgx.h
+++ b/arch/x86/kernel/cpu/sgx/sgx.h
@@ -15,6 +15,7 @@ 
 
 struct sgx_epc_page {
 	unsigned long desc;
+	struct sgx_encl_page *owner;
 	struct list_head list;
 };
 
@@ -27,6 +28,7 @@  struct sgx_epc_page {
 struct sgx_epc_section {
 	unsigned long pa;
 	void *va;
+	unsigned long free_cnt;
 	struct list_head page_list;
 	struct list_head unsanitized_page_list;
 	spinlock_t lock;
@@ -35,6 +37,10 @@  struct sgx_epc_section {
 #define SGX_EPC_SECTION_MASK		GENMASK(7, 0)
 #define SGX_MAX_EPC_SECTIONS		(SGX_EPC_SECTION_MASK + 1)
 #define SGX_MAX_ADD_PAGES_LENGTH	0x100000
+#define SGX_EPC_PAGE_RECLAIMABLE	BIT(8)
+#define SGX_NR_TO_SCAN			16
+#define SGX_NR_LOW_PAGES		32
+#define SGX_NR_HIGH_PAGES		64
 
 extern struct sgx_epc_section sgx_epc_sections[SGX_MAX_EPC_SECTIONS];
 
@@ -50,7 +56,10 @@  static inline void *sgx_get_epc_addr(struct sgx_epc_page *page)
 	return section->va + (page->desc & PAGE_MASK) - section->pa;
 }
 
+void sgx_mark_page_reclaimable(struct sgx_epc_page *page);
+int sgx_unmark_page_reclaimable(struct sgx_epc_page *page);
 struct sgx_epc_page *__sgx_alloc_epc_page(void);
+struct sgx_epc_page *sgx_alloc_epc_page(void *owner, bool reclaim);
 void sgx_free_epc_page(struct sgx_epc_page *page);
 
 #endif /* _X86_SGX_H */