1728ab54b4
Just like normal RAM, there is a limited amount of enclave memory available and overcommitting it is a very valuable tool to reduce resource use. Introduce a simple reclaim mechanism for enclave pages. In contrast to normal page reclaim, the kernel cannot directly access enclave memory. To get around this, the SGX architecture provides a set of functions to help. Among other things, these functions copy enclave memory to and from normal memory, encrypting it and protecting its integrity in the process. Implement a page reclaimer by using these functions. Picks victim pages in LRU fashion from all the enclaves running in the system. A new kernel thread (ksgxswapd) reclaims pages in the background based on watermarks, similar to normal kswapd. All enclave pages can be reclaimed, architecturally. But, there are some limits to this, such as the special SECS metadata page which must be reclaimed last. The page version array (used to mitigate replaying old reclaimed pages) is also architecturally reclaimable, but not yet implemented. The end result is that the vast majority of enclave pages are currently reclaimable. 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@kernel.org> Signed-off-by: Borislav Petkov <bp@suse.de> Acked-by: Jethro Beekman <jethro@fortanix.com> Link: https://lkml.kernel.org/r/20201112220135.165028-22-jarkko@kernel.org
120 lines
2.9 KiB
C
120 lines
2.9 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
/**
|
|
* Copyright(c) 2016-20 Intel Corporation.
|
|
*
|
|
* Contains the software defined data structures for enclaves.
|
|
*/
|
|
#ifndef _X86_ENCL_H
|
|
#define _X86_ENCL_H
|
|
|
|
#include <linux/cpumask.h>
|
|
#include <linux/kref.h>
|
|
#include <linux/list.h>
|
|
#include <linux/mm_types.h>
|
|
#include <linux/mmu_notifier.h>
|
|
#include <linux/mutex.h>
|
|
#include <linux/notifier.h>
|
|
#include <linux/srcu.h>
|
|
#include <linux/workqueue.h>
|
|
#include <linux/xarray.h>
|
|
#include "sgx.h"
|
|
|
|
/* 'desc' bits holding the offset in the VA (version array) page. */
|
|
#define SGX_ENCL_PAGE_VA_OFFSET_MASK GENMASK_ULL(11, 3)
|
|
|
|
/* 'desc' bit marking that the page is being reclaimed. */
|
|
#define SGX_ENCL_PAGE_BEING_RECLAIMED BIT(3)
|
|
|
|
struct sgx_encl_page {
|
|
unsigned long desc;
|
|
unsigned long vm_max_prot_bits;
|
|
struct sgx_epc_page *epc_page;
|
|
struct sgx_encl *encl;
|
|
struct sgx_va_page *va_page;
|
|
};
|
|
|
|
enum sgx_encl_flags {
|
|
SGX_ENCL_IOCTL = BIT(0),
|
|
SGX_ENCL_DEBUG = BIT(1),
|
|
SGX_ENCL_CREATED = BIT(2),
|
|
SGX_ENCL_INITIALIZED = BIT(3),
|
|
};
|
|
|
|
struct sgx_encl_mm {
|
|
struct sgx_encl *encl;
|
|
struct mm_struct *mm;
|
|
struct list_head list;
|
|
struct mmu_notifier mmu_notifier;
|
|
};
|
|
|
|
struct sgx_encl {
|
|
unsigned long base;
|
|
unsigned long size;
|
|
unsigned long flags;
|
|
unsigned int page_cnt;
|
|
unsigned int secs_child_cnt;
|
|
struct mutex lock;
|
|
struct xarray page_array;
|
|
struct sgx_encl_page secs;
|
|
unsigned long attributes;
|
|
unsigned long attributes_mask;
|
|
|
|
cpumask_t cpumask;
|
|
struct file *backing;
|
|
struct kref refcount;
|
|
struct list_head va_pages;
|
|
unsigned long mm_list_version;
|
|
struct list_head mm_list;
|
|
spinlock_t mm_lock;
|
|
struct srcu_struct srcu;
|
|
};
|
|
|
|
#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;
|
|
};
|
|
|
|
struct sgx_backing {
|
|
pgoff_t page_index;
|
|
struct page *contents;
|
|
struct page *pcmd;
|
|
unsigned long pcmd_offset;
|
|
};
|
|
|
|
extern const struct vm_operations_struct sgx_vm_ops;
|
|
|
|
static inline int sgx_encl_find(struct mm_struct *mm, unsigned long addr,
|
|
struct vm_area_struct **vma)
|
|
{
|
|
struct vm_area_struct *result;
|
|
|
|
result = find_vma(mm, addr);
|
|
if (!result || result->vm_ops != &sgx_vm_ops || addr < result->vm_start)
|
|
return -EINVAL;
|
|
|
|
*vma = result;
|
|
|
|
return 0;
|
|
}
|
|
|
|
int sgx_encl_may_map(struct sgx_encl *encl, unsigned long start,
|
|
unsigned long end, unsigned long vm_flags);
|
|
|
|
void sgx_encl_release(struct kref *ref);
|
|
int sgx_encl_mm_add(struct sgx_encl *encl, struct mm_struct *mm);
|
|
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_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 */
|