mm: replace vm_lock and detached flag with a reference count

rw_semaphore is a sizable structure of 40 bytes and consumes considerable
space for each vm_area_struct.  However vma_lock has two important
specifics which can be used to replace rw_semaphore with a simpler
structure:

1. Readers never wait.  They try to take the vma_lock and fall back to
   mmap_lock if that fails.

2. Only one writer at a time will ever try to write-lock a vma_lock
   because writers first take mmap_lock in write mode.  Because of these
   requirements, full rw_semaphore functionality is not needed and we can
   replace rw_semaphore and the vma->detached flag with a refcount
   (vm_refcnt).

When vma is in detached state, vm_refcnt is 0 and only a call to
vma_mark_attached() can take it out of this state.  Note that unlike
before, now we enforce both vma_mark_attached() and vma_mark_detached() to
be done only after vma has been write-locked.  vma_mark_attached() changes
vm_refcnt to 1 to indicate that it has been attached to the vma tree. 
When a reader takes read lock, it increments vm_refcnt, unless the top
usable bit of vm_refcnt (0x40000000) is set, indicating presence of a
writer.  When writer takes write lock, it sets the top usable bit to
indicate its presence.  If there are readers, writer will wait using newly
introduced mm->vma_writer_wait.  Since all writers take mmap_lock in write
mode first, there can be only one writer at a time.  The last reader to
release the lock will signal the writer to wake up.  refcount might
overflow if there are many competing readers, in which case read-locking
will fail.  Readers are expected to handle such failures.

In summary:
1. all readers increment the vm_refcnt;
2. writer sets top usable (writer) bit of vm_refcnt;
3. readers cannot increment the vm_refcnt if the writer bit is set;
4. in the presence of readers, writer must wait for the vm_refcnt to drop
to 1 (plus the VMA_LOCK_OFFSET writer bit), indicating an attached vma
with no readers;
5. vm_refcnt overflow is handled by the readers.

While this vm_lock replacement does not yet result in a smaller
vm_area_struct (it stays at 256 bytes due to cacheline alignment), it
allows for further size optimization by structure member regrouping to
bring the size of vm_area_struct below 192 bytes.

[surenb@google.com: fix a crash due to vma_end_read() that should have been removed]
  Link: https://lkml.kernel.org/r/20250220200208.323769-1-surenb@google.com
Link: https://lkml.kernel.org/r/20250213224655.1680278-13-surenb@google.com
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
Suggested-by: Peter Zijlstra <peterz@infradead.org>
Suggested-by: Matthew Wilcox <willy@infradead.org>
Tested-by: Shivank Garg <shivankg@amd.com>
  Link: https://lkml.kernel.org/r/5e19ec93-8307-47c2-bb13-3ddf7150624e@amd.com
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Christian Brauner <brauner@kernel.org>
Cc: David Hildenbrand <david@redhat.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jann Horn <jannh@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Klara Modin <klarasmodin@gmail.com>
Cc: Liam R. Howlett <Liam.Howlett@Oracle.com>
Cc: Lokesh Gidra <lokeshgidra@google.com>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Mateusz Guzik <mjguzik@gmail.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Minchan Kim <minchan@google.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Pasha Tatashin <pasha.tatashin@soleen.com>
Cc: "Paul E . McKenney" <paulmck@kernel.org>
Cc: Peter Xu <peterx@redhat.com>
Cc: Shakeel Butt <shakeel.butt@linux.dev>
Cc: Sourav Panda <souravpanda@google.com>
Cc: Wei Yang <richard.weiyang@gmail.com>
Cc: Will Deacon <will@kernel.org>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

2 files changed, 35 insertions, 33 deletions

diff --git a/tools/testing/vma/linux/atomic.h b/tools/testing/vma/linux/atomic.h
index 3e1b6adc027b..788c597c4fde 100644
--- a/tools/testing/vma/linux/atomic.h
+++ b/tools/testing/vma/linux/atomic.h
@@ -9,4 +9,9 @@
 #define atomic_set(x, y) uatomic_set(x, y)
 #define U8_MAX UCHAR_MAX
 
+#ifndef atomic_cmpxchg_relaxed
+#define  atomic_cmpxchg_relaxed		uatomic_cmpxchg
+#define  atomic_cmpxchg_release         uatomic_cmpxchg
+#endif /* atomic_cmpxchg_relaxed */
+
 #endif	/* _LINUX_ATOMIC_H */
diff --git a/tools/testing/vma/vma_internal.h b/tools/testing/vma/vma_internal.h
index 34277842156c..ba838097d3f6 100644
--- a/tools/testing/vma/vma_internal.h
+++ b/tools/testing/vma/vma_internal.h
@@ -25,7 +25,7 @@
 #include <linux/maple_tree.h>
 #include <linux/mm.h>
 #include <linux/rbtree.h>
-#include <linux/rwsem.h>
+#include <linux/refcount.h>
 
 extern unsigned long stack_guard_gap;
 #ifdef CONFIG_MMU
@@ -135,10 +135,6 @@ typedef __bitwise unsigned int vm_fault_t;
  */
 #define pr_warn_once pr_err
 
-typedef struct refcount_struct {
-	atomic_t refs;
-} refcount_t;
-
 struct kref {
 	refcount_t refcount;
 };
@@ -233,15 +229,12 @@ struct mm_struct {
 	unsigned long flags; /* Must use atomic bitops to access */
 };
 
-struct vma_lock {
-	struct rw_semaphore lock;
-};
-
-
 struct file {
 	struct address_space	*f_mapping;
 };
 
+#define VMA_LOCK_OFFSET	0x40000000
+
 struct vm_area_struct {
 	/* The first cache line has the info for VMA tree walking. */
 
@@ -269,16 +262,13 @@ struct vm_area_struct {
 	};
 
 #ifdef CONFIG_PER_VMA_LOCK
-	/* Flag to indicate areas detached from the mm->mm_mt tree */
-	bool detached;
-
 	/*
 	 * Can only be written (using WRITE_ONCE()) while holding both:
 	 *  - mmap_lock (in write mode)
-	 *  - vm_lock.lock (in write mode)
+	 *  - vm_refcnt bit at VMA_LOCK_OFFSET is set
 	 * Can be read reliably while holding one of:
 	 *  - mmap_lock (in read or write mode)
-	 *  - vm_lock.lock (in read or write mode)
+	 *  - vm_refcnt bit at VMA_LOCK_OFFSET is set or vm_refcnt > 1
 	 * Can be read unreliably (using READ_ONCE()) for pessimistic bailout
 	 * while holding nothing (except RCU to keep the VMA struct allocated).
 	 *
@@ -287,7 +277,6 @@ struct vm_area_struct {
 	 * slowpath.
 	 */
 	unsigned int vm_lock_seq;
-	struct vma_lock vm_lock;
 #endif
 
 	/*
@@ -340,6 +329,10 @@ struct vm_area_struct {
 	struct vma_numab_state *numab_state;	/* NUMA Balancing state */
 #endif
 	struct vm_userfaultfd_ctx vm_userfaultfd_ctx;
+#ifdef CONFIG_PER_VMA_LOCK
+	/* Unstable RCU readers are allowed to read this. */
+	refcount_t vm_refcnt;
+#endif
 } __randomize_layout;
 
 struct vm_fault {};
@@ -464,33 +457,40 @@ static inline struct vm_area_struct *vma_next(struct vma_iterator *vmi)
 	return mas_find(&vmi->mas, ULONG_MAX);
 }
 
-static inline void vma_lock_init(struct vm_area_struct *vma)
-{
-	init_rwsem(&vma->vm_lock.lock);
-	vma->vm_lock_seq = UINT_MAX;
-}
-
+/*
+ * WARNING: to avoid racing with vma_mark_attached()/vma_mark_detached(), these
+ * assertions should be made either under mmap_write_lock or when the object
+ * has been isolated under mmap_write_lock, ensuring no competing writers.
+ */
 static inline void vma_assert_attached(struct vm_area_struct *vma)
 {
-	WARN_ON_ONCE(vma->detached);
+	WARN_ON_ONCE(!refcount_read(&vma->vm_refcnt));
 }
 
 static inline void vma_assert_detached(struct vm_area_struct *vma)
 {
-	WARN_ON_ONCE(!vma->detached);
+	WARN_ON_ONCE(refcount_read(&vma->vm_refcnt));
 }
 
 static inline void vma_assert_write_locked(struct vm_area_struct *);
 static inline void vma_mark_attached(struct vm_area_struct *vma)
 {
-	vma->detached = false;
+	vma_assert_write_locked(vma);
+	vma_assert_detached(vma);
+	refcount_set(&vma->vm_refcnt, 1);
 }
 
 static inline void vma_mark_detached(struct vm_area_struct *vma)
 {
-	/* When detaching vma should be write-locked */
 	vma_assert_write_locked(vma);
-	vma->detached = true;
+	vma_assert_attached(vma);
+	/* We are the only writer, so no need to use vma_refcount_put(). */
+	if (unlikely(!refcount_dec_and_test(&vma->vm_refcnt))) {
+		/*
+		 * Reader must have temporarily raised vm_refcnt but it will
+		 * drop it without using the vma since vma is write-locked.
+		 */
+	}
 }
 
 extern const struct vm_operations_struct vma_dummy_vm_ops;
@@ -503,9 +503,7 @@ static inline void vma_init(struct vm_area_struct *vma, struct mm_struct *mm)
 	vma->vm_mm = mm;
 	vma->vm_ops = &vma_dummy_vm_ops;
 	INIT_LIST_HEAD(&vma->anon_vma_chain);
-	/* vma is not locked, can't use vma_mark_detached() */
-	vma->detached = true;
-	vma_lock_init(vma);
+	vma->vm_lock_seq = UINT_MAX;
 }
 
 static inline struct vm_area_struct *vm_area_alloc(struct mm_struct *mm)
@@ -528,10 +526,9 @@ static inline struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig)
 		return NULL;
 
 	memcpy(new, orig, sizeof(*new));
-	vma_lock_init(new);
+	refcount_set(&new->vm_refcnt, 0);
+	new->vm_lock_seq = UINT_MAX;
 	INIT_LIST_HEAD(&new->anon_vma_chain);
-	/* vma is not locked, can't use vma_mark_detached() */
-	new->detached = true;
 
 	return new;
 }