Date:   Wed, 15 Feb 2023 21:17:25 -0800
In-Reply-To: <20230216051750.3125598-1-surenb@google.com>
Mime-Version: 1.0
References: <20230216051750.3125598-1-surenb@google.com>
Message-ID: <20230216051750.3125598-11-surenb@google.com>
Subject: [PATCH v3 10/35] mm: rcu safe VMA freeing
From:   Suren Baghdasaryan <surenb@google.com>
To:     akpm@linux-foundation.org
Cc:     michel@lespinasse.org, jglisse@google.com, mhocko@suse.com,
        vbabka@suse.cz, hannes@cmpxchg.org, mgorman@techsingularity.net,
        dave@stgolabs.net, willy@infradead.org, liam.howlett@oracle.com,
        peterz@infradead.org, ldufour@linux.ibm.com, paulmck@kernel.org,
        mingo@redhat.com, will@kernel.org, luto@kernel.org,
        songliubraving@fb.com, peterx@redhat.com, david@redhat.com,
        dhowells@redhat.com, hughd@google.com, bigeasy@linutronix.de,
        kent.overstreet@linux.dev, punit.agrawal@bytedance.com,
        lstoakes@gmail.com, peterjung1337@gmail.com, rientjes@google.com,
        chriscli@google.com, axelrasmussen@google.com, joelaf@google.com,
        minchan@google.com, rppt@kernel.org, jannh@google.com,
        shakeelb@google.com, tatashin@google.com, edumazet@google.com,
        gthelen@google.com, gurua@google.com, arjunroy@google.com,
        soheil@google.com, leewalsh@google.com, posk@google.com,
        michalechner92@googlemail.com, linux-mm@kvack.org,
        linux-arm-kernel@lists.infradead.org,
        linuxppc-dev@lists.ozlabs.org, x86@kernel.org,
        linux-kernel@vger.kernel.org, kernel-team@android.com,
        Suren Baghdasaryan <surenb@google.com>
Content-Type: text/plain; charset="UTF-8"
Precedence: bulk

From: Michel Lespinasse <michel@lespinasse.org>

This prepares for page faults handling under VMA lock, looking up VMAs
under protection of an rcu read lock, instead of the usual mmap read lock.

Signed-off-by: Michel Lespinasse <michel@lespinasse.org>
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
---
 include/linux/mm_types.h | 13 ++++++++++---
 kernel/fork.c            | 20 +++++++++++++++++++-
 2 files changed, 29 insertions(+), 4 deletions(-)

diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 3fd5305dbbf9..fb4e2afad787 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -480,9 +480,16 @@ struct anon_vma_name {
 struct vm_area_struct {
 	/* The first cache line has the info for VMA tree walking. */
 
-	unsigned long vm_start;		/* Our start address within vm_mm. */
-	unsigned long vm_end;		/* The first byte after our end address
-					   within vm_mm. */
+	union {
+		struct {
+			/* VMA covers [vm_start; vm_end) addresses within mm */
+			unsigned long vm_start;
+			unsigned long vm_end;
+		};
+#ifdef CONFIG_PER_VMA_LOCK
+		struct rcu_head vm_rcu;	/* Used for deferred freeing. */
+#endif
+	};
 
 	struct mm_struct *vm_mm;	/* The address space we belong to. */
 
diff --git a/kernel/fork.c b/kernel/fork.c
index 5f23d5e03362..314d51eb91da 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -479,12 +479,30 @@ struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig)
 	return new;
 }
 
-void vm_area_free(struct vm_area_struct *vma)
+static void __vm_area_free(struct vm_area_struct *vma)
 {
 	free_anon_vma_name(vma);
 	kmem_cache_free(vm_area_cachep, vma);
 }
 
+#ifdef CONFIG_PER_VMA_LOCK
+static void vm_area_free_rcu_cb(struct rcu_head *head)
+{
+	struct vm_area_struct *vma = container_of(head, struct vm_area_struct,
+						  vm_rcu);
+	__vm_area_free(vma);
+}
+#endif
+
+void vm_area_free(struct vm_area_struct *vma)
+{
+#ifdef CONFIG_PER_VMA_LOCK
+	call_rcu(&vma->vm_rcu, vm_area_free_rcu_cb);
+#else
+	__vm_area_free(vma);
+#endif
+}
+
 static void account_kernel_stack(struct task_struct *tsk, int account)
 {
 	if (IS_ENABLED(CONFIG_VMAP_STACK)) {
-- 
2.39.1