[PATCH v3 07/28] x86/sgx: Introduce EPC page states
From: Haitao Huang
Date: Wed Jul 12 2023 - 19:02:48 EST
Use the lower 3 bits in the flags field of sgx_epc_page struct to
track EPC states in its life cycle and define an enum for possible
states. More state(s) will be added later.
Signed-off-by: Haitao Huang <haitao.huang@xxxxxxxxxxxxxxx>
V3:
- This is new in V3 to replace the bit mask based approach (requested by Jarkko)
---
arch/x86/kernel/cpu/sgx/encl.c | 10 +++----
arch/x86/kernel/cpu/sgx/ioctl.c | 6 ++--
arch/x86/kernel/cpu/sgx/main.c | 19 +++++++------
arch/x86/kernel/cpu/sgx/sgx.h | 50 +++++++++++++++++++++++++++++----
4 files changed, 63 insertions(+), 22 deletions(-)
diff --git a/arch/x86/kernel/cpu/sgx/encl.c b/arch/x86/kernel/cpu/sgx/encl.c
index edb8d8c1c229..e7319209fc4a 100644
--- a/arch/x86/kernel/cpu/sgx/encl.c
+++ b/arch/x86/kernel/cpu/sgx/encl.c
@@ -253,7 +253,7 @@ static struct sgx_encl_page *__sgx_encl_load_page(struct sgx_encl *encl,
if (IS_ERR(epc_page))
return ERR_CAST(epc_page);
sgx_record_epc_page(epc_page, SGX_EPC_OWNER_ENCL_PAGE |
- SGX_EPC_PAGE_RECLAIMER_UNTRACKED);
+ SGX_EPC_PAGE_UNRECLAIMABLE);
}
epc_page = sgx_encl_eldu(entry, encl->secs.epc_page);
@@ -262,7 +262,7 @@ static struct sgx_encl_page *__sgx_encl_load_page(struct sgx_encl *encl,
encl->secs_child_cnt++;
sgx_record_epc_page(epc_page, SGX_EPC_OWNER_ENCL_PAGE |
- SGX_EPC_PAGE_RECLAIMER_TRACKED);
+ SGX_EPC_PAGE_RECLAIMABLE);
return entry;
}
@@ -382,7 +382,7 @@ static vm_fault_t sgx_encl_eaug_page(struct vm_area_struct *vma,
encl->secs_child_cnt++;
sgx_record_epc_page(epc_page, SGX_EPC_OWNER_ENCL_PAGE |
- SGX_EPC_PAGE_RECLAIMER_TRACKED);
+ SGX_EPC_PAGE_RECLAIMABLE);
phys_addr = sgx_get_epc_phys_addr(epc_page);
/*
@@ -1242,7 +1242,7 @@ struct sgx_epc_page *sgx_alloc_va_page(struct sgx_encl *encl, bool reclaim)
return ERR_PTR(-EFAULT);
}
sgx_record_epc_page(epc_page, SGX_EPC_OWNER_ENCL |
- SGX_EPC_PAGE_RECLAIMER_UNTRACKED);
+ SGX_EPC_PAGE_UNRECLAIMABLE);
return epc_page;
}
@@ -1302,7 +1302,7 @@ void sgx_encl_free_epc_page(struct sgx_epc_page *page)
{
int ret;
- WARN_ON_ONCE(page->flags & SGX_EPC_PAGE_RECLAIMER_TRACKED);
+ WARN_ON_ONCE(page->flags & SGX_EPC_PAGE_STATE_MASK);
ret = __eremove(sgx_get_epc_virt_addr(page));
if (WARN_ONCE(ret, EREMOVE_ERROR_MESSAGE, ret, ret))
diff --git a/arch/x86/kernel/cpu/sgx/ioctl.c b/arch/x86/kernel/cpu/sgx/ioctl.c
index 4e6d0c9d043a..4f95096c9786 100644
--- a/arch/x86/kernel/cpu/sgx/ioctl.c
+++ b/arch/x86/kernel/cpu/sgx/ioctl.c
@@ -115,7 +115,7 @@ static int sgx_encl_create(struct sgx_encl *encl, struct sgx_secs *secs)
encl->attributes_mask = SGX_ATTR_UNPRIV_MASK;
sgx_record_epc_page(encl->secs.epc_page, SGX_EPC_OWNER_ENCL_PAGE |
- SGX_EPC_PAGE_RECLAIMER_UNTRACKED);
+ SGX_EPC_PAGE_UNRECLAIMABLE);
/* Set only after completion, as encl->lock has not been taken. */
set_bit(SGX_ENCL_CREATED, &encl->flags);
@@ -327,7 +327,7 @@ static int sgx_encl_add_page(struct sgx_encl *encl, unsigned long src,
}
sgx_record_epc_page(epc_page, SGX_EPC_OWNER_ENCL_PAGE |
- SGX_EPC_PAGE_RECLAIMER_TRACKED);
+ SGX_EPC_PAGE_RECLAIMABLE);
mutex_unlock(&encl->lock);
mmap_read_unlock(current->mm);
return ret;
@@ -982,7 +982,7 @@ static long sgx_enclave_modify_types(struct sgx_encl *encl,
mutex_lock(&encl->lock);
sgx_record_epc_page(entry->epc_page, SGX_EPC_OWNER_ENCL_PAGE |
- SGX_EPC_PAGE_RECLAIMER_TRACKED);
+ SGX_EPC_PAGE_RECLAIMABLE);
}
/* Change EPC type */
diff --git a/arch/x86/kernel/cpu/sgx/main.c b/arch/x86/kernel/cpu/sgx/main.c
index 9252728865fa..02c358f10383 100644
--- a/arch/x86/kernel/cpu/sgx/main.c
+++ b/arch/x86/kernel/cpu/sgx/main.c
@@ -319,7 +319,7 @@ static void sgx_reclaim_pages(void)
/* The owner is freeing the page. No need to add the
* page back to the list of reclaimable pages.
*/
- epc_page->flags &= ~SGX_EPC_PAGE_RECLAIMER_TRACKED;
+ sgx_epc_page_reset_state(epc_page);
}
spin_unlock(&sgx_global_lru.lock);
@@ -345,6 +345,7 @@ static void sgx_reclaim_pages(void)
skip:
spin_lock(&sgx_global_lru.lock);
+ sgx_epc_page_set_state(epc_page, SGX_EPC_PAGE_RECLAIMABLE);
list_add_tail(&epc_page->list, &sgx_global_lru.reclaimable);
spin_unlock(&sgx_global_lru.lock);
@@ -368,7 +369,7 @@ static void sgx_reclaim_pages(void)
sgx_reclaimer_write(epc_page, &backing[i]);
kref_put(&encl_page->encl->refcount, sgx_encl_release);
- epc_page->flags &= ~SGX_EPC_PAGE_RECLAIMER_TRACKED;
+ sgx_epc_page_reset_state(epc_page);
sgx_free_epc_page(epc_page);
}
@@ -508,9 +509,9 @@ struct sgx_epc_page *__sgx_alloc_epc_page(void)
void sgx_record_epc_page(struct sgx_epc_page *page, unsigned long flags)
{
spin_lock(&sgx_global_lru.lock);
- WARN_ON_ONCE(page->flags & SGX_EPC_PAGE_RECLAIMER_TRACKED);
+ WARN_ON_ONCE(sgx_epc_page_reclaimable(page->flags));
page->flags |= flags;
- if (flags & SGX_EPC_PAGE_RECLAIMER_TRACKED)
+ if (sgx_epc_page_reclaimable(flags))
list_add_tail(&page->list, &sgx_global_lru.reclaimable);
else
list_add_tail(&page->list, &sgx_global_lru.unreclaimable);
@@ -530,7 +531,7 @@ void sgx_record_epc_page(struct sgx_epc_page *page, unsigned long flags)
int sgx_drop_epc_page(struct sgx_epc_page *page)
{
spin_lock(&sgx_global_lru.lock);
- if (page->flags & SGX_EPC_PAGE_RECLAIMER_TRACKED) {
+ if (sgx_epc_page_reclaimable(page->flags)) {
/* The page is being reclaimed. */
if (list_empty(&page->list)) {
spin_unlock(&sgx_global_lru.lock);
@@ -538,7 +539,7 @@ int sgx_drop_epc_page(struct sgx_epc_page *page)
}
list_del(&page->list);
- page->flags &= ~SGX_EPC_PAGE_RECLAIMER_TRACKED;
+ sgx_epc_page_reset_state(page);
}
spin_unlock(&sgx_global_lru.lock);
@@ -610,6 +611,8 @@ void sgx_free_epc_page(struct sgx_epc_page *page)
struct sgx_epc_section *section = &sgx_epc_sections[page->section];
struct sgx_numa_node *node = section->node;
+ WARN_ON_ONCE(page->flags & (SGX_EPC_PAGE_STATE_MASK));
+
spin_lock(&node->lock);
page->encl_page = NULL;
@@ -617,7 +620,7 @@ void sgx_free_epc_page(struct sgx_epc_page *page)
list_add(&page->list, &node->sgx_poison_page_list);
else
list_add_tail(&page->list, &node->free_page_list);
- page->flags = SGX_EPC_PAGE_IS_FREE;
+ page->flags = SGX_EPC_PAGE_FREE;
spin_unlock(&node->lock);
atomic_long_inc(&sgx_nr_free_pages);
@@ -718,7 +721,7 @@ int arch_memory_failure(unsigned long pfn, int flags)
* If the page is on a free list, move it to the per-node
* poison page list.
*/
- if (page->flags & SGX_EPC_PAGE_IS_FREE) {
+ if (page->flags == SGX_EPC_PAGE_FREE) {
list_move(&page->list, &node->sgx_poison_page_list);
goto out;
}
diff --git a/arch/x86/kernel/cpu/sgx/sgx.h b/arch/x86/kernel/cpu/sgx/sgx.h
index 9f780b2c4cfe..057905eba466 100644
--- a/arch/x86/kernel/cpu/sgx/sgx.h
+++ b/arch/x86/kernel/cpu/sgx/sgx.h
@@ -23,14 +23,36 @@
#define SGX_NR_LOW_PAGES 32
#define SGX_NR_HIGH_PAGES 64
-/* Pages, which are not tracked by the page reclaimer. */
-#define SGX_EPC_PAGE_RECLAIMER_UNTRACKED 0
+enum sgx_epc_page_state {
+ /* Not tracked by the reclaimer:
+ * Pages allocated for virtual EPC which are never tracked by the host
+ * reclaimer; pages just allocated from free list but not yet put in
+ * use; pages just reclaimed, but not yet returned to the free list.
+ * Becomes FREE after sgx_free_epc()
+ * Becomes RECLAIMABLE or UNRECLAIMABLE after sgx_record_epc()
+ */
+ SGX_EPC_PAGE_NOT_TRACKED = 0,
+
+ /* Page is in the free list, ready for allocation
+ * Becomes NOT_TRACKED after sgx_alloc_epc_page()
+ */
+ SGX_EPC_PAGE_FREE = 1,
+
+ /* Page is in use and tracked in a reclaimable LRU list
+ * Becomes NOT_TRACKED after sgx_drop_epc()
+ */
+ SGX_EPC_PAGE_RECLAIMABLE = 2,
+
+ /* Page is in use but tracked in an unreclaimable LRU list. These are
+ * only reclaimable when the whole enclave is OOM killed or the enclave
+ * is released, e.g., VA, SECS pages
+ * Becomes NOT_TRACKED after sgx_drop_epc()
+ */
+ SGX_EPC_PAGE_UNRECLAIMABLE = 3,
-/* Pages, which are being tracked by the page reclaimer. */
-#define SGX_EPC_PAGE_RECLAIMER_TRACKED BIT(0)
+};
-/* Pages on free list */
-#define SGX_EPC_PAGE_IS_FREE BIT(1)
+#define SGX_EPC_PAGE_STATE_MASK GENMASK(2, 0)
/* flag for pages owned by a sgx_encl_page */
#define SGX_EPC_OWNER_ENCL_PAGE BIT(3)
@@ -49,6 +71,22 @@ struct sgx_epc_page {
struct list_head list;
};
+static inline void sgx_epc_page_reset_state(struct sgx_epc_page *page)
+{
+ page->flags &= ~SGX_EPC_PAGE_STATE_MASK;
+}
+
+static inline void sgx_epc_page_set_state(struct sgx_epc_page *page, unsigned long flags)
+{
+ page->flags &= ~SGX_EPC_PAGE_STATE_MASK;
+ page->flags |= (flags & SGX_EPC_PAGE_STATE_MASK);
+}
+
+static inline bool sgx_epc_page_reclaimable(unsigned long flags)
+{
+ return SGX_EPC_PAGE_RECLAIMABLE == (flags & SGX_EPC_PAGE_STATE_MASK);
+}
+
/*
* Contains the tracking data for NUMA nodes having EPC pages. Most importantly,
* the free page list local to the node is stored here.
--
2.25.1