[PATCH v11 mm-new 06/10] mm: bpf-thp: add support for global mode

[Yafang Shao <laoar.shao@gmail.com>]

The per-process BPF-THP mode is unsuitable for managing shared resources
such as shmem THP and file-backed THP. This aligns with known cgroup
limitations for similar scenarios [0].

Introduce a global BPF-THP mode to address this gap. When registered:
- All existing per-process instances are disabled
- New per-process registrations are blocked
- Existing per-process instances remain registered (no forced unregistration)

The global mode takes precedence over per-process instances. Updates are
type-isolated: global instances can only be updated by new global
instances, and per-process instances by new per-process instances.

Link: https://lore.kernel.org/linux-mm/YwNold0GMOappUxc@slm.duckdns.org/ [0]

Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
---
 mm/huge_memory_bpf.c | 109 ++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 107 insertions(+), 2 deletions(-)

diff --git a/mm/huge_memory_bpf.c b/mm/huge_memory_bpf.c
index e8894c10d1d9..cad1ca6f59a4 100644
--- a/mm/huge_memory_bpf.c
+++ b/mm/huge_memory_bpf.c
@@ -33,6 +33,28 @@ struct bpf_thp_ops {
 };
 
 static DEFINE_SPINLOCK(thp_ops_lock);
+static struct bpf_thp_ops __rcu *bpf_thp_global; /* global mode */
+
+static unsigned long
+bpf_hook_thp_get_orders_global(struct vm_area_struct *vma,
+			       enum tva_type type,
+			       unsigned long orders)
+{
+	thp_order_fn_t *bpf_hook_thp_get_order;
+	int bpf_order;
+
+	rcu_read_lock();
+	bpf_hook_thp_get_order = rcu_dereference(bpf_thp_global->thp_get_order);
+	if (!bpf_hook_thp_get_order)
+		goto out;
+
+	bpf_order = bpf_hook_thp_get_order(vma, type, orders);
+	orders &= BIT(bpf_order);
+
+out:
+	rcu_read_unlock();
+	return orders;
+}
 
 unsigned long bpf_hook_thp_get_orders(struct vm_area_struct *vma,
 				      enum tva_type type,
@@ -45,6 +67,10 @@ unsigned long bpf_hook_thp_get_orders(struct vm_area_struct *vma,
 	if (!mm)
 		return orders;
 
+	/* Global BPF-THP takes precedence over per-process BPF-THP. */
+	if (rcu_access_pointer(bpf_thp_global))
+		return bpf_hook_thp_get_orders_global(vma, type, orders);
+
 	rcu_read_lock();
 	bpf_thp = rcu_dereference(mm->bpf_mm.bpf_thp);
 	if (!bpf_thp || !bpf_thp->thp_get_order)
@@ -177,6 +203,23 @@ static int bpf_thp_init_member(const struct btf_type *t,
 	return 0;
 }
 
+static int bpf_thp_reg_gloabl(void *kdata, struct bpf_link *link)
+{
+	struct bpf_thp_ops *ops = kdata;
+
+	/* Protect the global pointer bpf_thp_global from concurrent writes. */
+	spin_lock(&thp_ops_lock);
+	/* Only one instance is allowed. */
+	if (rcu_access_pointer(bpf_thp_global)) {
+		spin_unlock(&thp_ops_lock);
+		return -EBUSY;
+	}
+
+	rcu_assign_pointer(bpf_thp_global, ops);
+	spin_unlock(&thp_ops_lock);
+	return 0;
+}
+
 static int bpf_thp_reg(void *kdata, struct bpf_link *link)
 {
 	struct bpf_thp_ops *bpf_thp = kdata;
@@ -187,6 +230,11 @@ static int bpf_thp_reg(void *kdata, struct bpf_link *link)
 	pid_t pid;
 
 	pid = bpf_thp->pid;
+
+	/* Fallback to global mode if pid is not set. */
+	if (!pid)
+		return bpf_thp_reg_gloabl(kdata, link);
+
 	p = find_get_task_by_vpid(pid);
 	if (!p)
 		return -ESRCH;
@@ -207,8 +255,10 @@ static int bpf_thp_reg(void *kdata, struct bpf_link *link)
 	 * might register this task simultaneously.
 	 */
 	spin_lock(&thp_ops_lock);
-	/* Each process is exclusively managed by a single BPF-THP. */
-	if (rcu_access_pointer(mm->bpf_mm.bpf_thp))
+	/* Each process is exclusively managed by a single BPF-THP.
+	 * Global mode disables per-process instances.
+	 */
+	if (rcu_access_pointer(mm->bpf_mm.bpf_thp) || rcu_access_pointer(bpf_thp_global))
 		goto out_lock;
 	err = 0;
 	rcu_assign_pointer(mm->bpf_mm.bpf_thp, bpf_thp);
@@ -224,12 +274,33 @@ static int bpf_thp_reg(void *kdata, struct bpf_link *link)
 	return err;
 }
 
+static void bpf_thp_unreg_global(void *kdata, struct bpf_link *link)
+{
+	struct bpf_thp_ops *bpf_thp;
+
+	spin_lock(&thp_ops_lock);
+	if (!rcu_access_pointer(bpf_thp_global)) {
+		spin_unlock(&thp_ops_lock);
+		return;
+	}
+
+	bpf_thp = rcu_replace_pointer(bpf_thp_global, NULL,
+				      lockdep_is_held(&thp_ops_lock));
+	WARN_ON_ONCE(!bpf_thp);
+	spin_unlock(&thp_ops_lock);
+
+	synchronize_rcu();
+}
+
 static void bpf_thp_unreg(void *kdata, struct bpf_link *link)
 {
 	struct bpf_thp_ops *bpf_thp = kdata;
 	struct bpf_mm_ops *bpf_mm;
 	struct list_head *pos, *n;
 
+	if (!bpf_thp->pid)
+		return bpf_thp_unreg_global(kdata, link);
+
 	spin_lock(&thp_ops_lock);
 	list_for_each_safe(pos, n, &bpf_thp->mm_list) {
 		bpf_mm = list_entry(pos, struct bpf_mm_ops, bpf_thp_list);
@@ -242,6 +313,31 @@ static void bpf_thp_unreg(void *kdata, struct bpf_link *link)
 	synchronize_rcu();
 }
 
+static int bpf_thp_update_global(void *kdata, void *old_kdata, struct bpf_link *link)
+{
+	struct bpf_thp_ops *old_bpf_thp = old_kdata;
+	struct bpf_thp_ops *bpf_thp = kdata;
+	struct bpf_thp_ops *old_global;
+
+	if (!old_bpf_thp || !bpf_thp)
+		return -EINVAL;
+
+	spin_lock(&thp_ops_lock);
+	/* BPF-THP global instance has already been removed. */
+	if (!rcu_access_pointer(bpf_thp_global)) {
+		spin_unlock(&thp_ops_lock);
+		return -ENOENT;
+	}
+
+	old_global = rcu_replace_pointer(bpf_thp_global, bpf_thp,
+					 lockdep_is_held(&thp_ops_lock));
+	WARN_ON_ONCE(!old_global);
+	spin_unlock(&thp_ops_lock);
+
+	synchronize_rcu();
+	return 0;
+}
+
 static int bpf_thp_update(void *kdata, void *old_kdata, struct bpf_link *link)
 {
 	struct bpf_thp_ops *old_bpf_thp = old_kdata;
@@ -249,6 +345,15 @@ static int bpf_thp_update(void *kdata, void *old_kdata, struct bpf_link *link)
 	struct bpf_mm_ops *bpf_mm;
 	struct list_head *pos, *n;
 
+	/* Updates are confined to instances of the same scope:
+	 * global to global, process-local to process-local.
+	 */
+	if (!!old_bpf_thp->pid != !!bpf_thp->pid)
+		return -EINVAL;
+
+	if (!old_bpf_thp->pid)
+		return bpf_thp_update_global(kdata, old_kdata, link);
+
 	INIT_LIST_HEAD(&bpf_thp->mm_list);
 
 	/* Could be optimized to a per-instance lock if this lock becomes a bottleneck. */
-- 
2.47.3