net: skmsg: preserve sg.copy across SG transforms

The sk_msg sg.copy bitmap is part of the scatterlist entry ownership
state. A set bit tells sk_msg_compute_data_pointers() not to expose the
entry through writable BPF ctx->data. This protects entries backed by
pages that are not private to the sk_msg, such as splice-backed file
page-cache pages.

Several sk_msg transform paths move, copy, split, or compact
msg->sg.data[] entries without moving the matching sg.copy bit. This can
make an externally backed entry arrive at a new slot with a clear copy
bit. A later SK_MSG verdict can then expose sg_virt(sge) as writable
ctx->data and BPF stores can modify the original page cache.

Keep sg.copy synchronized with sg.data[] whenever entries are
transferred, shifted, split, or copied into a new sk_msg. Clear the bit
when an entry is replaced by a newly allocated private page or freed.
This covers the BPF pull/push/pop helpers, sk_msg_shift_left/right(),
sk_msg_xfer(), and tls_split_open_record(), including the partial tail
entry created during TLS open-record splitting.

Fixes: d3b18ad31f93 ("tls: add bpf support to sk_msg handling")
Cc: stable@vger.kernel.org
Reported-by: Yiming Qian <yimingqian591@gmail.com>
Reported-by: Keenan Dong <keenanat2000@gmail.com>
Signed-off-by: Yiming Qian <yimingqian591@gmail.com>
Link: https://patch.msgid.link/20260610062137.49075-1-yimingqian591@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 11 insertions, 4 deletions

diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h
index 19f4f253b4f9..937823856de5 100644
--- a/include/linux/skmsg.h
+++ b/include/linux/skmsg.h
@@ -4,6 +4,7 @@
 #ifndef _LINUX_SKMSG_H
 #define _LINUX_SKMSG_H
 
+#include <linux/bitops.h>
 #include <linux/bpf.h>
 #include <linux/filter.h>
 #include <linux/scatterlist.h>
@@ -199,11 +200,14 @@ static inline void sk_msg_xfer(struct sk_msg *dst, struct sk_msg *src,
 			       int which, u32 size)
 {
 	dst->sg.data[which] = src->sg.data[which];
+	__assign_bit(which, dst->sg.copy, test_bit(which, src->sg.copy));
 	dst->sg.data[which].length  = size;
 	dst->sg.size		   += size;
 	src->sg.size		   -= size;
 	src->sg.data[which].length -= size;
 	src->sg.data[which].offset += size;
+	if (!src->sg.data[which].length)
+		__clear_bit(which, src->sg.copy);
 }
 
 static inline void sk_msg_xfer_full(struct sk_msg *dst, struct sk_msg *src)
@@ -273,16 +277,19 @@ static inline void sk_msg_page_add(struct sk_msg *msg, struct page *page,
 static inline void sk_msg_sg_copy(struct sk_msg *msg, u32 i, bool copy_state)
 {
 	do {
-		if (copy_state)
-			__set_bit(i, msg->sg.copy);
-		else
-			__clear_bit(i, msg->sg.copy);
+		__assign_bit(i, msg->sg.copy, copy_state);
 		sk_msg_iter_var_next(i);
 		if (i == msg->sg.end)
 			break;
 	} while (1);
 }
 
+static inline void sk_msg_sg_copy_assign(struct sk_msg *dst, u32 dst_i,
+					 const struct sk_msg *src, u32 src_i)
+{
+	__assign_bit(dst_i, dst->sg.copy, test_bit(src_i, src->sg.copy));
+}
+
 static inline void sk_msg_sg_copy_set(struct sk_msg *msg, u32 start)
 {
 	sk_msg_sg_copy(msg, start, true);