[RFC PATCH v2 3/5] mm: thp: add struct ops for BPF based THP adjustment

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

This patch introduces a minimal struct_ops for BPF-based THP adjustment.

Currently, only a single BPF program can be attached. Support for multiple
attachments will be added in the future.

Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
---
 include/linux/huge_mm.h |  13 +----
 mm/Makefile             |   3 +
 mm/bpf_thp.c            | 120 ++++++++++++++++++++++++++++++++++++++++
 3 files changed, 124 insertions(+), 12 deletions(-)
 create mode 100644 mm/bpf_thp.c

diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index fedb5b014d9a..a75f5f902af0 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -193,18 +193,7 @@ static inline bool hugepage_global_always(void)
 			(1<<TRANSPARENT_HUGEPAGE_FLAG);
 }
 
-static inline bool hugepage_bpf_allowable(void)
-{
-	/* Works only for BPF mode */
-	if (!(transparent_hugepage_flags & (1<<TRANSPARENT_HUGEPAGE_REQ_BPF_FLAG)))
-		return 0;
-
-	/* No BPF program is attached */
-	if (!(transparent_hugepage_flags & (1<<TRANSPARENT_HUGEPAGE_BPF_ATTACHED)))
-		return 0;
-	/* We will add struct ops in the future */
-	return 1;
-}
+bool hugepage_bpf_allowable(void);
 
 static inline bool hugepaged_bpf_allowable(void)
 {
diff --git a/mm/Makefile b/mm/Makefile
index e7f6bbf8ae5f..c355f9426c93 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -99,6 +99,9 @@ obj-$(CONFIG_MIGRATION) += migrate.o
 obj-$(CONFIG_NUMA) += memory-tiers.o
 obj-$(CONFIG_DEVICE_MIGRATION) += migrate_device.o
 obj-$(CONFIG_TRANSPARENT_HUGEPAGE) += huge_memory.o khugepaged.o
+ifdef CONFIG_BPF_SYSCALL
+obj-$(CONFIG_TRANSPARENT_HUGEPAGE) += bpf_thp.o
+endif
 obj-$(CONFIG_PAGE_COUNTER) += page_counter.o
 obj-$(CONFIG_MEMCG_V1) += memcontrol-v1.o
 obj-$(CONFIG_MEMCG) += memcontrol.o vmpressure.o
diff --git a/mm/bpf_thp.c b/mm/bpf_thp.c
new file mode 100644
index 000000000000..690980cdb4da
--- /dev/null
+++ b/mm/bpf_thp.c
@@ -0,0 +1,120 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <linux/btf.h>
+#include <linux/huge_mm.h>
+
+struct bpf_thp_ops {
+	/**
+	 * @thp_bpf_allowable: Determines whether a task is permitted to
+	 * allocate a THP when it is allocating anon memory.
+	 *
+	 * Return: %true if THP allocation is allowed, %false otherwise.
+	 */
+	bool (*thp_bpf_allowable)(void);
+};
+
+static struct bpf_thp_ops bpf_thp;
+
+bool hugepage_bpf_allowable(void)
+{
+	/* Works only for "bpf" mode */
+	if (!(transparent_hugepage_flags & (1<<TRANSPARENT_HUGEPAGE_REQ_BPF_FLAG)))
+		return 0;
+
+	/* No BPF program is attached */
+	if (!(transparent_hugepage_flags & (1<<TRANSPARENT_HUGEPAGE_BPF_ATTACHED)))
+		return 0;
+
+	/* BPF adjustment hook */
+	if (bpf_thp.thp_bpf_allowable)
+		return bpf_thp.thp_bpf_allowable();
+	return 0;
+}
+
+static bool bpf_thp_ops_is_valid_access(int off, int size,
+					enum bpf_access_type type,
+					const struct bpf_prog *prog,
+					struct bpf_insn_access_aux *info)
+{
+	return bpf_tracing_btf_ctx_access(off, size, type, prog, info);
+}
+
+static const struct bpf_func_proto *
+bpf_thp_get_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
+{
+	return bpf_base_func_proto(func_id, prog);
+}
+
+static const struct bpf_verifier_ops thp_bpf_verifier_ops = {
+	.get_func_proto = bpf_thp_get_func_proto,
+	.is_valid_access = bpf_thp_ops_is_valid_access,
+};
+
+static int bpf_thp_reg(void *kdata, struct bpf_link *link)
+{
+	struct bpf_thp_ops *ops = kdata;
+
+	/* TODO: add support for multiple attaches */
+	if (test_and_set_bit(TRANSPARENT_HUGEPAGE_BPF_ATTACHED,
+		&transparent_hugepage_flags))
+		return -EOPNOTSUPP;
+	bpf_thp.thp_bpf_allowable = ops->thp_bpf_allowable;
+	return 0;
+}
+
+static void bpf_thp_unreg(void *kdata, struct bpf_link *link)
+{
+	clear_bit(TRANSPARENT_HUGEPAGE_BPF_ATTACHED, &transparent_hugepage_flags);
+	bpf_thp.thp_bpf_allowable = NULL;
+}
+
+static int bpf_thp_check_member(const struct btf_type *t,
+				const struct btf_member *member,
+				const struct bpf_prog *prog)
+{
+	return 0;
+}
+
+static int bpf_thp_init_member(const struct btf_type *t,
+			       const struct btf_member *member,
+			       void *kdata, const void *udata)
+{
+	return 0;
+}
+
+static int bpf_thp_init(struct btf *btf)
+{
+	return 0;
+}
+
+static bool thp_bpf_allowable(void)
+{
+	return 0;
+}
+
+static struct bpf_thp_ops __bpf_thp_ops = {
+	.thp_bpf_allowable = thp_bpf_allowable,
+};
+
+static struct bpf_struct_ops bpf_bpf_thp_ops = {
+	.verifier_ops = &thp_bpf_verifier_ops,
+	.init = bpf_thp_init,
+	.check_member = bpf_thp_check_member,
+	.init_member = bpf_thp_init_member,
+	.reg = bpf_thp_reg,
+	.unreg = bpf_thp_unreg,
+	.name = "bpf_thp_ops",
+	.cfi_stubs = &__bpf_thp_ops,
+	.owner = THIS_MODULE,
+};
+
+static int __init bpf_thp_ops_init(void)
+{
+	int err = register_bpf_struct_ops(&bpf_bpf_thp_ops, bpf_thp_ops);
+
+	if (err)
+		pr_err("bpf_thp: Failed to register struct_ops (%d)\n", err);
+	return err;
+}
+late_initcall(bpf_thp_ops_init);
-- 
2.43.5