In CRIU, we need to be able to determine whether the page pinned by
io_uring is still present in the same range in the process VMA.
/proc/<pid>/pagemap gives us the PFN, hence using this helper we can
establish this mapping easily from the iterator side.
It is a simple wrapper over the in-kernel page_to_pfn helper, and
ensures the passed in pointer is a struct page PTR_TO_BTF_ID. This is
obtained from the bvec of io_uring_ubuf for the CRIU usecase.
Signed-off-by: Kumar Kartikeya Dwivedi <memxor@xxxxxxxxx>
---
fs/io_uring.c | 17 +++++++++++++++++
include/linux/bpf.h | 1 +
include/uapi/linux/bpf.h | 9 +++++++++
kernel/trace/bpf_trace.c | 2 ++
scripts/bpf_doc.py | 2 ++
tools/include/uapi/linux/bpf.h | 9 +++++++++
6 files changed, 40 insertions(+)
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 46a110989155..9e9df6767e29 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -11295,6 +11295,23 @@ static struct bpf_iter_reg io_uring_buf_reg_info = {
.seq_info = &bpf_io_uring_buf_seq_info,
};
+BPF_CALL_1(bpf_page_to_pfn, struct page *, page)
+{
+ /* PTR_TO_BTF_ID can be NULL */
+ if (!page)
+ return U64_MAX;
+ return page_to_pfn(page);
+}
+
+BTF_ID_LIST_SINGLE(btf_page_to_pfn_ids, struct, page)
+
+const struct bpf_func_proto bpf_page_to_pfn_proto = {
+ .func = bpf_page_to_pfn,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_BTF_ID,
+ .arg1_btf_id = &btf_page_to_pfn_ids[0],
+};
+
static int __init io_uring_iter_init(void)
{
io_uring_buf_reg_info.ctx_arg_info[0].btf_id = btf_io_uring_ids[0];
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index ddb9d4520a3f..fe7b499da781 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -2166,6 +2166,7 @@ extern const struct bpf_func_proto bpf_sk_setsockopt_proto;
extern const struct bpf_func_proto bpf_sk_getsockopt_proto;
extern const struct bpf_func_proto bpf_kallsyms_lookup_name_proto;
extern const struct bpf_func_proto bpf_find_vma_proto;
+extern const struct bpf_func_proto bpf_page_to_pfn_proto;
const struct bpf_func_proto *tracing_prog_func_proto(
enum bpf_func_id func_id, const struct bpf_prog *prog);
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 3323defa99a1..b70e9da3d722 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -4960,6 +4960,14 @@ union bpf_attr {
* **-ENOENT** if *task->mm* is NULL, or no vma contains *addr*.
* **-EBUSY** if failed to try lock mmap_lock.
* **-EINVAL** for invalid **flags**.
+ *
+ * long bpf_page_to_pfn(struct page *page)
+ * Description
+ * Obtain the page frame number (PFN) for the given *struct page*
+ * pointer.
+ * Return
+ * Page Frame Number corresponding to the page pointed to by the
+ * *struct page* pointer, or U64_MAX if pointer is NULL.
*/
#define __BPF_FUNC_MAPPER(FN) \
FN(unspec), \
@@ -5143,6 +5151,7 @@ union bpf_attr {
FN(skc_to_unix_sock), \
FN(kallsyms_lookup_name), \
FN(find_vma), \
+ FN(page_to_pfn), \
/* */
/* integer value in 'imm' field of BPF_CALL instruction selects which helper
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 25ea521fb8f1..f68a8433be1a 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -1212,6 +1212,8 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
return &bpf_find_vma_proto;
case BPF_FUNC_trace_vprintk:
return bpf_get_trace_vprintk_proto();
+ case BPF_FUNC_page_to_pfn:
+ return &bpf_page_to_pfn_proto;
default:
return bpf_base_func_proto(func_id);
}
diff --git a/scripts/bpf_doc.py b/scripts/bpf_doc.py
index a6403ddf5de7..ae68ca794980 100755
--- a/scripts/bpf_doc.py
+++ b/scripts/bpf_doc.py
@@ -549,6 +549,7 @@ class PrinterHelpers(Printer):
'struct socket',
'struct file',
'struct bpf_timer',
+ 'struct page',
]
known_types = {
'...',
@@ -598,6 +599,7 @@ class PrinterHelpers(Printer):
'struct socket',
'struct file',
'struct bpf_timer',
+ 'struct page',
}
mapped_types = {
'u8': '__u8',
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 3323defa99a1..b70e9da3d722 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -4960,6 +4960,14 @@ union bpf_attr {
* **-ENOENT** if *task->mm* is NULL, or no vma contains *addr*.
* **-EBUSY** if failed to try lock mmap_lock.
* **-EINVAL** for invalid **flags**.
+ *
+ * long bpf_page_to_pfn(struct page *page)
+ * Description
+ * Obtain the page frame number (PFN) for the given *struct page*
+ * pointer.
+ * Return
+ * Page Frame Number corresponding to the page pointed to by the
+ * *struct page* pointer, or U64_MAX if pointer is NULL.
*/
#define __BPF_FUNC_MAPPER(FN) \
FN(unspec), \
@@ -5143,6 +5151,7 @@ union bpf_attr {
FN(skc_to_unix_sock), \
FN(kallsyms_lookup_name), \
FN(find_vma), \
+ FN(page_to_pfn), \
/* */
/* integer value in 'imm' field of BPF_CALL instruction selects which helper
--
2.33.1
