From 119e9db233ad0f4cbd4cfb9f9385a7bca378b37d Mon Sep 17 00:00:00 2001
From: Zeng Chi <zengchi@kylinos.cn>
Date: Mon, 21 Sep 2026 18:24:42 +0800
Subject: KVM: Don't pre-reserve xarray entries when storing empty/NULL
 attributes

Skip the xarray reservation loop when clearing all memory attributes, as
storing NULL only erases the entry and never needs to allocate, so no
reservation (and no cleanup of a failed one) is required in that case.

Suggested-by: Sean Christopherson <seanjc@google.com>
Cc: David Ballesteros <davimaba.v@proton.me>
Signed-off-by: Zeng Chi <zengchi@kylinos.cn>
Link: https://patch.msgid.link/20260921102442.1232375-1-zeng_chi911@163.com
[sean: split to separate patch]
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 io_uring/advise.c | 108 ++++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 108 insertions(+)
 create mode 100644 io_uring/advise.c

(limited to 'io_uring/advise.c')

diff --git a/io_uring/advise.c b/io_uring/advise.c
new file mode 100644
index 000000000..0073f74e3
--- /dev/null
+++ b/io_uring/advise.c
@@ -0,0 +1,108 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/file.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <linux/namei.h>
+#include <linux/io_uring.h>
+
+#include <uapi/linux/fadvise.h>
+#include <uapi/linux/io_uring.h>
+
+#include "io_uring.h"
+#include "advise.h"
+
+struct io_fadvise {
+	struct file			*file;
+	u64				offset;
+	u64				len;
+	u32				advice;
+};
+
+struct io_madvise {
+	struct file			*file;
+	u64				addr;
+	u64				len;
+	u32				advice;
+};
+
+int io_madvise_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+#if defined(CONFIG_ADVISE_SYSCALLS) && defined(CONFIG_MMU)
+	struct io_madvise *ma = io_kiocb_to_cmd(req, struct io_madvise);
+
+	if (sqe->buf_index || sqe->splice_fd_in)
+		return -EINVAL;
+
+	ma->addr = READ_ONCE(sqe->addr);
+	ma->len = READ_ONCE(sqe->off);
+	if (!ma->len)
+		ma->len = READ_ONCE(sqe->len);
+	ma->advice = READ_ONCE(sqe->fadvise_advice);
+	req->flags |= REQ_F_FORCE_ASYNC;
+	return 0;
+#else
+	return -EOPNOTSUPP;
+#endif
+}
+
+int io_madvise(struct io_kiocb *req, unsigned int issue_flags)
+{
+#if defined(CONFIG_ADVISE_SYSCALLS) && defined(CONFIG_MMU)
+	struct io_madvise *ma = io_kiocb_to_cmd(req, struct io_madvise);
+	int ret;
+
+	WARN_ON_ONCE(issue_flags & IO_URING_F_NONBLOCK);
+
+	ret = do_madvise(current->mm, ma->addr, ma->len, ma->advice);
+	io_req_set_res(req, ret, 0);
+	return IOU_COMPLETE;
+#else
+	return -EOPNOTSUPP;
+#endif
+}
+
+static bool io_fadvise_force_async(struct io_fadvise *fa)
+{
+	switch (fa->advice) {
+	case POSIX_FADV_NORMAL:
+	case POSIX_FADV_RANDOM:
+	case POSIX_FADV_SEQUENTIAL:
+		return false;
+	default:
+		return true;
+	}
+}
+
+int io_fadvise_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+	struct io_fadvise *fa = io_kiocb_to_cmd(req, struct io_fadvise);
+
+	if (sqe->buf_index || sqe->splice_fd_in)
+		return -EINVAL;
+
+	fa->offset = READ_ONCE(sqe->off);
+	fa->len = READ_ONCE(sqe->addr);
+	if (!fa->len)
+		fa->len = READ_ONCE(sqe->len);
+	fa->advice = READ_ONCE(sqe->fadvise_advice);
+	if (io_fadvise_force_async(fa))
+		req->flags |= REQ_F_FORCE_ASYNC;
+	return 0;
+}
+
+int io_fadvise(struct io_kiocb *req, unsigned int issue_flags)
+{
+	struct io_fadvise *fa = io_kiocb_to_cmd(req, struct io_fadvise);
+	int ret;
+
+	WARN_ON_ONCE(issue_flags & IO_URING_F_NONBLOCK && io_fadvise_force_async(fa));
+
+	ret = vfs_fadvise(req->file, fa->offset, fa->len, fa->advice);
+	if (ret < 0)
+		req_set_fail(req);
+	io_req_set_res(req, ret, 0);
+	return IOU_COMPLETE;
+}
-- 
cgit v1.3.1