[Xen-devel] [PATCH v4 2/4] x86/mem_sharing: copy a page_lock version to be internal to memshr

[Tamas K Lengyel <tamas@xxxxxxxxxxxxx>]

Patch cf4b30dca0a "Add debug code to detect illegal page_lock and put_page_type
ordering" added extra sanity checking to page_lock/page_unlock for debug builds
with the assumption that no hypervisor path ever locks two pages at once.

This assumption doesn't hold during memory sharing so we copy a version of
page_lock/unlock to be used exclusively in the memory sharing subsystem
without the sanity checks.

Signed-off-by: Tamas K Lengyel <tamas@xxxxxxxxxxxxx>
Cc: George Dunlap <george.dunlap@xxxxxxxxxxxxx>
Cc: Jan Beulich <jbeulich@xxxxxxxx>
Cc: Andrew Cooper <andrew.cooper3@xxxxxxxxxx>
Cc: Wei Liu <wei.liu2@xxxxxxxxxx>
Cc: Roger Pau Monne <roger.pau@xxxxxxxxxx>
---
 xen/arch/x86/mm/mem_sharing.c | 43 +++++++++++++++++++++++++++++++----
 xen/include/asm-x86/mm.h      | 14 +-----------
 2 files changed, 40 insertions(+), 17 deletions(-)

diff --git a/xen/arch/x86/mm/mem_sharing.c b/xen/arch/x86/mm/mem_sharing.c
index 4b3a094481..baae7ceeda 100644
--- a/xen/arch/x86/mm/mem_sharing.c
+++ b/xen/arch/x86/mm/mem_sharing.c
@@ -112,13 +112,48 @@ static inline void page_sharing_dispose(struct page_info 
*page)
 
 #endif /* MEM_SHARING_AUDIT */
 
-static inline int mem_sharing_page_lock(struct page_info *pg)
+/*
+ * Private implementations of page_lock/unlock to bypass PV-only
+ * sanity checks not applicable to mem-sharing.
+ */
+static inline bool _page_lock(struct page_info *page)
 {
-    int rc;
+    unsigned long x, nx;
+
+    do {
+        while ( (x = page->u.inuse.type_info) & PGT_locked )
+            cpu_relax();
+        nx = x + (1 | PGT_locked);
+        if ( !(x & PGT_validated) ||
+             !(x & PGT_count_mask) ||
+             !(nx & PGT_count_mask) )
+            return false;
+    } while ( cmpxchg(&page->u.inuse.type_info, x, nx) != x );
+
+    return true;
+}
+
+static inline void _page_unlock(struct page_info *page)
+{
+    unsigned long x, nx, y = page->u.inuse.type_info;
+
+    do {
+        x = y;
+        ASSERT((x & PGT_count_mask) && (x & PGT_locked));
+
+        nx = x - (1 | PGT_locked);
+        /* We must not drop the last reference here. */
+        ASSERT(nx & PGT_count_mask);
+    } while ( (y = cmpxchg(&page->u.inuse.type_info, x, nx)) != x );
+}
+
+static inline bool mem_sharing_page_lock(struct page_info *pg)
+{
+    bool rc;
     pg_lock_data_t *pld = &(this_cpu(__pld));
 
     page_sharing_mm_pre_lock();
-    rc = page_lock(pg);
+    rc = _page_lock(pg);
     if ( rc )
     {
         preempt_disable();
@@ -135,7 +170,7 @@ static inline void mem_sharing_page_unlock(struct page_info 
*pg)
     page_sharing_mm_unlock(pld->mm_unlock_level, 
                            &pld->recurse_count);
     preempt_enable();
-    page_unlock(pg);
+    _page_unlock(pg);
 }
 
 static inline shr_handle_t get_next_handle(void)
diff --git a/xen/include/asm-x86/mm.h b/xen/include/asm-x86/mm.h
index 6faa563167..7dc7e33f73 100644
--- a/xen/include/asm-x86/mm.h
+++ b/xen/include/asm-x86/mm.h
@@ -356,24 +356,12 @@ struct platform_bad_page {
 const struct platform_bad_page *get_platform_badpages(unsigned int 
*array_size);
 
 /* Per page locks:
- * page_lock() is used for two purposes: pte serialization, and memory sharing.
+ * page_lock() is used for pte serialization.
  *
  * All users of page lock for pte serialization live in mm.c, use it
  * to lock a page table page during pte updates, do not take other locks within
  * the critical section delimited by page_lock/unlock, and perform no
  * nesting.
- *
- * All users of page lock for memory sharing live in mm/mem_sharing.c. 
Page_lock
- * is used in memory sharing to protect addition (share) and removal (unshare)
- * of (gfn,domain) tupples to a list of gfn's that the shared page is currently
- * backing. Nesting may happen when sharing (and locking) two pages -- deadlock
- * is avoided by locking pages in increasing order.
- * All memory sharing code paths take the p2m lock of the affected gfn before
- * taking the lock for the underlying page. We enforce ordering between 
page_lock
- * and p2m_lock using an mm-locks.h construct.
- *
- * These two users (pte serialization and memory sharing) do not collide, since
- * sharing is only supported for hvm guests, which do not perform pv pte 
updates.
  */
 int page_lock(struct page_info *page);
 void page_unlock(struct page_info *page);
-- 
2.20.1


_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxxx
https://lists.xenproject.org/mailman/listinfo/xen-devel