Merge branch 'Introduce-sendpage_ok-to-detect-misused-sendpage-in-network-related-drivers'

Coly Li says:

====================
Introduce sendpage_ok() to detect misused sendpage in network related drivers

As Sagi Grimberg suggested, the original fix is refind to a more common
inline routine:
    static inline bool sendpage_ok(struct page *page)
    {
        return  (!PageSlab(page) && page_count(page) >= 1);
    }
If sendpage_ok() returns true, the checking page can be handled by the
concrete zero-copy sendpage method in network layer.

The v10 series has 7 patches, fixes a WARN_ONCE() usage from v9 series,
- The 1st patch in this series introduces sendpage_ok() in header file
  include/linux/net.h.
- The 2nd patch adds WARN_ONCE() for improper zero-copy send in
  kernel_sendpage().
- The 3rd patch fixes the page checking issue in nvme-over-tcp driver.
- The 4th patch adds page_count check by using sendpage_ok() in
  do_tcp_sendpages() as Eric Dumazet suggested.
- The 5th and 6th patches just replace existing open coded checks with
  the inline sendpage_ok() routine.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/block/drbd/drbd_main.c

@@ -1553,7 +1553,7 @@ static int _drbd_send_page(struct drbd_peer_device *peer_device, struct page *pa
 	 * put_page(); and would cause either a VM_BUG directly, or
 	 * __page_cache_release a page that would actually still be referenced
 	 * by someone, leading to some obscure delayed Oops somewhere else. */
-	if (drbd_disable_sendpage || (page_count(page) < 1) || PageSlab(page))
+	if (drbd_disable_sendpage || !sendpage_ok(page))
 		return _drbd_no_send_page(peer_device, page, offset, size, msg_flags);
 
 	msg_flags |= MSG_NOSIGNAL;

drivers/nvme/host/tcp.c

@@ -913,12 +913,11 @@ static int nvme_tcp_try_send_data(struct nvme_tcp_request *req)
 		else
 			flags |= MSG_MORE | MSG_SENDPAGE_NOTLAST;
 
-		/* can't zcopy slab pages */
-		if (unlikely(PageSlab(page))) {
-			ret = sock_no_sendpage(queue->sock, page, offset, len,
+		if (sendpage_ok(page)) {
+			ret = kernel_sendpage(queue->sock, page, offset, len,
 					flags);
 		} else {
-			ret = kernel_sendpage(queue->sock, page, offset, len,
+			ret = sock_no_sendpage(queue->sock, page, offset, len,
 					flags);
 		}
 		if (ret <= 0)

drivers/scsi/libiscsi_tcp.c

@@ -128,7 +128,7 @@ static void iscsi_tcp_segment_map(struct iscsi_segment *segment, int recv)
 	 * coalescing neighboring slab objects into a single frag which
 	 * triggers one of hardened usercopy checks.
 	 */
-	if (!recv && page_count(sg_page(sg)) >= 1 && !PageSlab(sg_page(sg)))
+	if (!recv && sendpage_ok(sg_page(sg)))
 		return;
 
 	if (recv) {

include/linux/net.h

@@ -21,6 +21,7 @@
 #include <linux/rcupdate.h>
 #include <linux/once.h>
 #include <linux/fs.h>
+#include <linux/mm.h>
 #include <linux/sockptr.h>
 
 #include <uapi/linux/net.h>
@@ -286,6 +287,21 @@ do {									\
 #define net_get_random_once_wait(buf, nbytes)			\
 	get_random_once_wait((buf), (nbytes))
 
+/*
+ * E.g. XFS meta- & log-data is in slab pages, or bcache meta
+ * data pages, or other high order pages allocated by
+ * __get_free_pages() without __GFP_COMP, which have a page_count
+ * of 0 and/or have PageSlab() set. We cannot use send_page for
+ * those, as that does get_page(); put_page(); and would cause
+ * either a VM_BUG directly, or __page_cache_release a page that
+ * would actually still be referenced by someone, leading to some
+ * obscure delayed Oops somewhere else.
+ */
+static inline bool sendpage_ok(struct page *page)
+{
+	return !PageSlab(page) && page_count(page) >= 1;
+}
+
 int kernel_sendmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec,
 		   size_t num, size_t len);
 int kernel_sendmsg_locked(struct sock *sk, struct msghdr *msg,

net/ceph/messenger.c

@@ -575,7 +575,7 @@ static int ceph_tcp_sendpage(struct socket *sock, struct page *page,
 	 * coalescing neighboring slab objects into a single frag which
 	 * triggers one of hardened usercopy checks.
 	 */
-	if (page_count(page) >= 1 && !PageSlab(page))
+	if (sendpage_ok(page))
 		sendpage = sock->ops->sendpage;
 	else
 		sendpage = sock_no_sendpage;

net/ipv4/tcp.c

@@ -970,7 +970,8 @@ ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset,
 	long timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT);
 
 	if (IS_ENABLED(CONFIG_DEBUG_VM) &&
-	    WARN_ONCE(PageSlab(page), "page must not be a Slab one"))
+	    WARN_ONCE(!sendpage_ok(page),
+		      "page must not be a Slab one and have page_count > 0"))
 		return -EINVAL;
 
 	/* Wait for a connection to finish. One exception is TCP Fast Open

net/socket.c

@@ -3638,9 +3638,11 @@ EXPORT_SYMBOL(kernel_getpeername);
 int kernel_sendpage(struct socket *sock, struct page *page, int offset,
 		    size_t size, int flags)
 {
-	if (sock->ops->sendpage)
+	if (sock->ops->sendpage) {
+		/* Warn in case the improper page to zero-copy send */
+		WARN_ONCE(!sendpage_ok(page), "improper page for zero-copy send");
 		return sock->ops->sendpage(sock, page, offset, size, flags);
-
+	}
 	return sock_no_sendpage(sock, page, offset, size, flags);
 }
 EXPORT_SYMBOL(kernel_sendpage);