[PATCH v16 14/16] x86/sgx: Turn on per-cgroup EPC reclamation

[Haitao Huang]

From: Kristen Carlson Accardi <kristen@xxxxxxxxxxxxxxx>

Previous patches have implemented all infrastructure needed for
per-cgroup EPC page tracking and reclaiming. But all reclaimable EPC
pages are still tracked in the global LRU as sgx_epc_page_lru() always
returns reference to the global LRU.

Change sgx_epc_page_lru() to return the LRU of the cgroup in which the
given EPC page is allocated.

Update sgx_can_reclaim_global(), to check emptiness of LRUs of all
cgroups, and update sgx_reclaim_pages_global(), to utilize
sgx_cgroup_reclaim_pages_global(), when EPC cgroup is enabled.

With these changes, the global reclamation and per-cgroup reclamation
both work properly with all pages tracked in per-cgroup LRUs.

Co-developed-by: Sean Christopherson <sean.j.christopherson@xxxxxxxxx>
Signed-off-by: Sean Christopherson <sean.j.christopherson@xxxxxxxxx>
Signed-off-by: Kristen Carlson Accardi <kristen@xxxxxxxxxxxxxxx>
Co-developed-by: Haitao Huang <haitao.huang@xxxxxxxxxxxxxxx>
Signed-off-by: Haitao Huang <haitao.huang@xxxxxxxxxxxxxxx>
Reviewed-by: Jarkko Sakkinen <jarkko@xxxxxxxxxx>
---
V16:
- Separated out the global and direct reclamation to earlier patch.(Kai)

V14:
- Update global reclamation to use the new sgx_cgroup_reclaim_pages() to
iterate cgroups at lower level if the top cgroups are too busy.

V13:
- Use IS_ENABLED(CONFIG_CGROUP_MISC) in sgx_can_reclaim_global(). (Kai)

V12:
- Remove CONFIG_CGROUP_SGX_EPC, conditional compile SGX Cgroup for
CONFIGCONFIG_CGROUPMISC. (Jarkko)

V11:
- Reword the comments for global reclamation for allocation failure
after passing cgroup charging. (Kai)
- Add stub functions to remove ifdefs in c file (Kai)
- Add more detailed comments to clarify each page belongs to one cgroup, or the
root. (Kai)

V10:
- Add comment to clarify each page belongs to one cgroup, or the root by
default. (Kai)
- Merge the changes that expose sgx_cgroup_* functions to this patch.
- Add changes for sgx_reclaim_direct() that was missed previously.

V7:
- Split this out from the big patch, #10 in V6. (Dave, Kai)
---
 arch/x86/kernel/cpu/sgx/epc_cgroup.c |  2 +-
 arch/x86/kernel/cpu/sgx/epc_cgroup.h |  6 ++++
 arch/x86/kernel/cpu/sgx/main.c       | 45 ++++++++++++++++++----------
 3 files changed, 36 insertions(+), 17 deletions(-)

diff --git a/arch/x86/kernel/cpu/sgx/epc_cgroup.c b/arch/x86/kernel/cpu/sgx/epc_cgroup.c
index b7d60b2d878d..c3f0c7bc13c6 100644
--- a/arch/x86/kernel/cpu/sgx/epc_cgroup.c
+++ b/arch/x86/kernel/cpu/sgx/epc_cgroup.c
@@ -162,7 +162,7 @@ static inline u64 sgx_cgroup_max_pages_to_root(struct sgx_cgroup *sgx_cg)
  *
  * Return: %true if all cgroups under the specified root have empty LRU lists.
  */
-static bool sgx_cgroup_lru_empty(struct misc_cg *root)
+bool sgx_cgroup_lru_empty(struct misc_cg *root)
 {
 	struct cgroup_subsys_state *css_root;
 	struct cgroup_subsys_state *pos;
diff --git a/arch/x86/kernel/cpu/sgx/epc_cgroup.h b/arch/x86/kernel/cpu/sgx/epc_cgroup.h
index cf2b946d993e..cd957cf38204 100644
--- a/arch/x86/kernel/cpu/sgx/epc_cgroup.h
+++ b/arch/x86/kernel/cpu/sgx/epc_cgroup.h
@@ -27,6 +27,11 @@ static inline int sgx_cgroup_try_charge(struct sgx_cgroup *sgx_cg, enum sgx_recl
 
 static inline void sgx_cgroup_uncharge(struct sgx_cgroup *sgx_cg) { }
 
+static inline bool sgx_cgroup_lru_empty(struct misc_cg *root)
+{
+	return true;
+}
+
 static inline int __init sgx_cgroup_init(void)
 {
 	return 0;
@@ -91,6 +96,7 @@ static inline void sgx_put_cg(struct sgx_cgroup *sgx_cg)
 
 int sgx_cgroup_try_charge(struct sgx_cgroup *sgx_cg, enum sgx_reclaim reclaim);
 void sgx_cgroup_uncharge(struct sgx_cgroup *sgx_cg);
+bool sgx_cgroup_lru_empty(struct misc_cg *root);
 void sgx_cgroup_reclaim_pages_global(struct mm_struct *charge_mm);
 void sgx_cgroup_reclaim_direct(void);
 int __init sgx_cgroup_init(void);
diff --git a/arch/x86/kernel/cpu/sgx/main.c b/arch/x86/kernel/cpu/sgx/main.c
index 9a8f91ebd21b..2a23a10d882e 100644
--- a/arch/x86/kernel/cpu/sgx/main.c
+++ b/arch/x86/kernel/cpu/sgx/main.c
@@ -32,9 +32,30 @@ static DEFINE_XARRAY(sgx_epc_address_space);
  */
 static struct sgx_epc_lru_list sgx_global_lru;
 
+/*
+ * Get the per-cgroup or global LRU list that tracks the given reclaimable page.
+ */
 static inline struct sgx_epc_lru_list *sgx_epc_page_lru(struct sgx_epc_page *epc_page)
 {
+#ifdef CONFIG_CGROUP_MISC
+	/*
+	 * epc_page->sgx_cg here is never NULL during a reclaimable epc_page's
+	 * life between sgx_alloc_epc_page() and sgx_free_epc_page():
+	 *
+	 * In sgx_alloc_epc_page(), epc_page->sgx_cg is set to the return from
+	 * sgx_get_current_cg() which is the misc cgroup of the current task, or
+	 * the root by default even if the misc cgroup is disabled by kernel
+	 * command line.
+	 *
+	 * epc_page->sgx_cg is only unset by sgx_free_epc_page().
+	 *
+	 * This function is never used before sgx_alloc_epc_page() or after
+	 * sgx_free_epc_page().
+	 */
+	return &epc_page->sgx_cg->lru;
+#else
 	return &sgx_global_lru;
+#endif
 }
 
 /*
@@ -42,14 +63,10 @@ static inline struct sgx_epc_lru_list *sgx_epc_page_lru(struct sgx_epc_page *epc
  */
 static inline bool sgx_can_reclaim_global(void)
 {
-	/*
-	 * Now all EPC pages are still tracked in the @sgx_global_lru, so only
-	 * check @sgx_global_lru.
-	 *
-	 * When EPC pages are tracked in the actual per-cgroup LRUs,
-	 * replace with sgx_cgroup_lru_empty(misc_cg_root()).
-	 */
-	return !list_empty(&sgx_global_lru.reclaimable);
+	if (IS_ENABLED(CONFIG_CGROUP_MISC))
+		return !sgx_cgroup_lru_empty(misc_cg_root());
+	else
+		return !list_empty(&sgx_global_lru.reclaimable);
 }
 
 static atomic_long_t sgx_nr_free_pages = ATOMIC_LONG_INIT(0);
@@ -411,14 +428,10 @@ static bool sgx_should_reclaim_global(unsigned long watermark)
 
 static void sgx_reclaim_pages_global(struct mm_struct *charge_mm)
 {
-	/*
-	 * Now all EPC pages are still tracked in the @sgx_global_lru.
-	 * Still reclaim from it.
-	 *
-	 * When EPC pages are tracked in the actual per-cgroup LRUs,
-	 * sgx_cgroup_reclaim_pages_global() will be called.
-	 */
-	sgx_reclaim_pages(&sgx_global_lru, charge_mm);
+	if (IS_ENABLED(CONFIG_CGROUP_MISC))
+		sgx_cgroup_reclaim_pages_global(charge_mm);
+	else
+		sgx_reclaim_pages(&sgx_global_lru, charge_mm);
 }
 
 /*
-- 
2.43.0