mm: move per-vma lock into vm_area_struct

Back when per-vma locks were introduces, vm_lock was moved out of
vm_area_struct in [1] because of the performance regression caused by
false cacheline sharing.  Recent investigation [2] revealed that the
regressions is limited to a rather old Broadwell microarchitecture and
even there it can be mitigated by disabling adjacent cacheline
prefetching, see [3].

Splitting single logical structure into multiple ones leads to more
complicated management, extra pointer dereferences and overall less
maintainable code.  When that split-away part is a lock, it complicates
things even further.  With no performance benefits, there are no reasons
for this split.  Merging the vm_lock back into vm_area_struct also allows
vm_area_struct to use SLAB_TYPESAFE_BY_RCU later in this patchset.  Move
vm_lock back into vm_area_struct, aligning it at the cacheline boundary
and changing the cache to be cacheline-aligned as well.  With kernel
compiled using defconfig, this causes VMA memory consumption to grow from
160 (vm_area_struct) + 40 (vm_lock) bytes to 256 bytes:

    slabinfo before:
     <name>           ... <objsize> <objperslab> <pagesperslab> : ...
     vma_lock         ...     40  102    1 : ...
     vm_area_struct   ...    160   51    2 : ...

    slabinfo after moving vm_lock:
     <name>           ... <objsize> <objperslab> <pagesperslab> : ...
     vm_area_struct   ...    256   32    2 : ...

Aggregate VMA memory consumption per 1000 VMAs grows from 50 to 64 pages,
which is 5.5MB per 100000 VMAs.  Note that the size of this structure is
dependent on the kernel configuration and typically the original size is
higher than 160 bytes.  Therefore these calculations are close to the
worst case scenario.  A more realistic vm_area_struct usage before this
change is:

     <name>           ... <objsize> <objperslab> <pagesperslab> : ...
     vma_lock         ...     40  102    1 : ...
     vm_area_struct   ...    176   46    2 : ...

Aggregate VMA memory consumption per 1000 VMAs grows from 54 to 64 pages,
which is 3.9MB per 100000 VMAs.  This memory consumption growth can be
addressed later by optimizing the vm_lock.

[1] https://lore.kernel.org/all/20230227173632.3292573-34-surenb@google.com/
[2] https://lore.kernel.org/all/ZsQyI%2F087V34JoIt@xsang-OptiPlex-9020/
[3] https://lore.kernel.org/all/CAJuCfpEisU8Lfe96AYJDZ+OM4NoPmnw9bP53cT_kbfP_pR+-2g@mail.gmail.com/

Link: https://lkml.kernel.org/r/20250213224655.1680278-3-surenb@google.com
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Reviewed-by: Shakeel Butt <shakeel.butt@linux.dev>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Liam R. Howlett <Liam.Howlett@Oracle.com>
Tested-by: Shivank Garg <shivankg@amd.com>
  Link: https://lkml.kernel.org/r/5e19ec93-8307-47c2-bb13-3ddf7150624e@amd.com
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: Lokesh Gidra <lokeshgidra@google.com>
Cc: Mateusz Guzik <mjguzik@gmail.com>
Cc: Matthew Wilcox <willy@infradead.org>
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: Peter Zijlstra (Intel) <peterz@infradead.org>
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>

1 files changed, 5 insertions, 44 deletions

diff --git a/kernel/fork.c b/kernel/fork.c
index 735405a9c5f3..bdbabe73fb29 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -436,35 +436,6 @@ static struct kmem_cache *vm_area_cachep;
 /* SLAB cache for mm_struct structures (tsk->mm) */
 static struct kmem_cache *mm_cachep;
 
-#ifdef CONFIG_PER_VMA_LOCK
-
-/* SLAB cache for vm_area_struct.lock */
-static struct kmem_cache *vma_lock_cachep;
-
-static bool vma_lock_alloc(struct vm_area_struct *vma)
-{
-	vma->vm_lock = kmem_cache_alloc(vma_lock_cachep, GFP_KERNEL);
-	if (!vma->vm_lock)
-		return false;
-
-	init_rwsem(&vma->vm_lock->lock);
-	vma->vm_lock_seq = UINT_MAX;
-
-	return true;
-}
-
-static inline void vma_lock_free(struct vm_area_struct *vma)
-{
-	kmem_cache_free(vma_lock_cachep, vma->vm_lock);
-}
-
-#else /* CONFIG_PER_VMA_LOCK */
-
-static inline bool vma_lock_alloc(struct vm_area_struct *vma) { return true; }
-static inline void vma_lock_free(struct vm_area_struct *vma) {}
-
-#endif /* CONFIG_PER_VMA_LOCK */
-
 struct vm_area_struct *vm_area_alloc(struct mm_struct *mm)
 {
 	struct vm_area_struct *vma;
@@ -474,10 +445,6 @@ struct vm_area_struct *vm_area_alloc(struct mm_struct *mm)
 		return NULL;
 
 	vma_init(vma, mm);
-	if (!vma_lock_alloc(vma)) {
-		kmem_cache_free(vm_area_cachep, vma);
-		return NULL;
-	}
 
 	return vma;
 }
@@ -496,10 +463,7 @@ struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig)
 	 * will be reinitialized.
 	 */
 	data_race(memcpy(new, orig, sizeof(*new)));
-	if (!vma_lock_alloc(new)) {
-		kmem_cache_free(vm_area_cachep, new);
-		return NULL;
-	}
+	vma_lock_init(new);
 	INIT_LIST_HEAD(&new->anon_vma_chain);
 	vma_numab_state_init(new);
 	dup_anon_vma_name(orig, new);
@@ -511,7 +475,6 @@ void __vm_area_free(struct vm_area_struct *vma)
 {
 	vma_numab_state_free(vma);
 	free_anon_vma_name(vma);
-	vma_lock_free(vma);
 	kmem_cache_free(vm_area_cachep, vma);
 }
 
@@ -522,7 +485,7 @@ static void vm_area_free_rcu_cb(struct rcu_head *head)
 						  vm_rcu);
 
 	/* The vma should not be locked while being destroyed. */
-	VM_BUG_ON_VMA(rwsem_is_locked(&vma->vm_lock->lock), vma);
+	VM_BUG_ON_VMA(rwsem_is_locked(&vma->vm_lock.lock), vma);
 	__vm_area_free(vma);
 }
 #endif
@@ -3200,11 +3163,9 @@ void __init proc_caches_init(void)
 			sizeof(struct fs_struct), 0,
 			SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT,
 			NULL);
-
-	vm_area_cachep = KMEM_CACHE(vm_area_struct, SLAB_PANIC|SLAB_ACCOUNT);
-#ifdef CONFIG_PER_VMA_LOCK
-	vma_lock_cachep = KMEM_CACHE(vma_lock, SLAB_PANIC|SLAB_ACCOUNT);
-#endif
+	vm_area_cachep = KMEM_CACHE(vm_area_struct,
+			SLAB_HWCACHE_ALIGN|SLAB_NO_MERGE|SLAB_PANIC|
+			SLAB_ACCOUNT);
 	mmap_init();
 	nsproxy_cache_init();
 }