Adding upstream version 6.9.7.upstream/6.9.7

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

1 files changed, 129 insertions, 18 deletions

diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index c5a9a483fb..f53ca4f7fc 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -37,6 +37,7 @@
 #include <linux/seq_file.h>
 #include <linux/compat.h>
 #include <linux/rculist.h>
+#include <linux/capability.h>
 #include <net/busy_poll.h>
 
 /*
@@ -206,7 +207,7 @@ struct eventpoll {
 	 */
 	struct epitem *ovflist;
 
-	/* wakeup_source used when ep_scan_ready_list is running */
+	/* wakeup_source used when ep_send_events or __ep_eventpoll_poll is running */
 	struct wakeup_source *ws;
 
 	/* The user that created the eventpoll descriptor */
@@ -227,6 +228,11 @@ struct eventpoll {
 #ifdef CONFIG_NET_RX_BUSY_POLL
 	/* used to track busy poll napi_id */
 	unsigned int napi_id;
+	/* busy poll timeout */
+	u32 busy_poll_usecs;
+	/* busy poll packet budget */
+	u16 busy_poll_budget;
+	bool prefer_busy_poll;
 #endif
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
@@ -387,11 +393,41 @@ static inline int ep_events_available(struct eventpoll *ep)
 }
 
 #ifdef CONFIG_NET_RX_BUSY_POLL
+/**
+ * busy_loop_ep_timeout - check if busy poll has timed out. The timeout value
+ * from the epoll instance ep is preferred, but if it is not set fallback to
+ * the system-wide global via busy_loop_timeout.
+ *
+ * @start_time: The start time used to compute the remaining time until timeout.
+ * @ep: Pointer to the eventpoll context.
+ *
+ * Return: true if the timeout has expired, false otherwise.
+ */
+static bool busy_loop_ep_timeout(unsigned long start_time,
+				 struct eventpoll *ep)
+{
+	unsigned long bp_usec = READ_ONCE(ep->busy_poll_usecs);
+
+	if (bp_usec) {
+		unsigned long end_time = start_time + bp_usec;
+		unsigned long now = busy_loop_current_time();
+
+		return time_after(now, end_time);
+	} else {
+		return busy_loop_timeout(start_time);
+	}
+}
+
+static bool ep_busy_loop_on(struct eventpoll *ep)
+{
+	return !!ep->busy_poll_usecs || net_busy_loop_on();
+}
+
 static bool ep_busy_loop_end(void *p, unsigned long start_time)
 {
 	struct eventpoll *ep = p;
 
-	return ep_events_available(ep) || busy_loop_timeout(start_time);
+	return ep_events_available(ep) || busy_loop_ep_timeout(start_time, ep);
 }
 
 /*
@@ -403,10 +439,15 @@ static bool ep_busy_loop_end(void *p, unsigned long start_time)
 static bool ep_busy_loop(struct eventpoll *ep, int nonblock)
 {
 	unsigned int napi_id = READ_ONCE(ep->napi_id);
+	u16 budget = READ_ONCE(ep->busy_poll_budget);
+	bool prefer_busy_poll = READ_ONCE(ep->prefer_busy_poll);
 
-	if ((napi_id >= MIN_NAPI_ID) && net_busy_loop_on()) {
-		napi_busy_loop(napi_id, nonblock ? NULL : ep_busy_loop_end, ep, false,
-			       BUSY_POLL_BUDGET);
+	if (!budget)
+		budget = BUSY_POLL_BUDGET;
+
+	if (napi_id >= MIN_NAPI_ID && ep_busy_loop_on(ep)) {
+		napi_busy_loop(napi_id, nonblock ? NULL : ep_busy_loop_end,
+			       ep, prefer_busy_poll, budget);
 		if (ep_events_available(ep))
 			return true;
 		/*
@@ -425,12 +466,12 @@ static bool ep_busy_loop(struct eventpoll *ep, int nonblock)
  */
 static inline void ep_set_busy_poll_napi_id(struct epitem *epi)
 {
-	struct eventpoll *ep;
+	struct eventpoll *ep = epi->ep;
 	unsigned int napi_id;
 	struct socket *sock;
 	struct sock *sk;
 
-	if (!net_busy_loop_on())
+	if (!ep_busy_loop_on(ep))
 		return;
 
 	sock = sock_from_file(epi->ffd.file);
@@ -442,7 +483,6 @@ static inline void ep_set_busy_poll_napi_id(struct epitem *epi)
 		return;
 
 	napi_id = READ_ONCE(sk->sk_napi_id);
-	ep = epi->ep;
 
 	/* Non-NAPI IDs can be rejected
 	 *	or
@@ -455,6 +495,49 @@ static inline void ep_set_busy_poll_napi_id(struct epitem *epi)
 	ep->napi_id = napi_id;
 }
 
+static long ep_eventpoll_bp_ioctl(struct file *file, unsigned int cmd,
+				  unsigned long arg)
+{
+	struct eventpoll *ep = file->private_data;
+	void __user *uarg = (void __user *)arg;
+	struct epoll_params epoll_params;
+
+	switch (cmd) {
+	case EPIOCSPARAMS:
+		if (copy_from_user(&epoll_params, uarg, sizeof(epoll_params)))
+			return -EFAULT;
+
+		/* pad byte must be zero */
+		if (epoll_params.__pad)
+			return -EINVAL;
+
+		if (epoll_params.busy_poll_usecs > S32_MAX)
+			return -EINVAL;
+
+		if (epoll_params.prefer_busy_poll > 1)
+			return -EINVAL;
+
+		if (epoll_params.busy_poll_budget > NAPI_POLL_WEIGHT &&
+		    !capable(CAP_NET_ADMIN))
+			return -EPERM;
+
+		WRITE_ONCE(ep->busy_poll_usecs, epoll_params.busy_poll_usecs);
+		WRITE_ONCE(ep->busy_poll_budget, epoll_params.busy_poll_budget);
+		WRITE_ONCE(ep->prefer_busy_poll, epoll_params.prefer_busy_poll);
+		return 0;
+	case EPIOCGPARAMS:
+		memset(&epoll_params, 0, sizeof(epoll_params));
+		epoll_params.busy_poll_usecs = READ_ONCE(ep->busy_poll_usecs);
+		epoll_params.busy_poll_budget = READ_ONCE(ep->busy_poll_budget);
+		epoll_params.prefer_busy_poll = READ_ONCE(ep->prefer_busy_poll);
+		if (copy_to_user(uarg, &epoll_params, sizeof(epoll_params)))
+			return -EFAULT;
+		return 0;
+	default:
+		return -ENOIOCTLCMD;
+	}
+}
+
 #else
 
 static inline bool ep_busy_loop(struct eventpoll *ep, int nonblock)
@@ -466,6 +549,12 @@ static inline void ep_set_busy_poll_napi_id(struct epitem *epi)
 {
 }
 
+static long ep_eventpoll_bp_ioctl(struct file *file, unsigned int cmd,
+				  unsigned long arg)
+{
+	return -EOPNOTSUPP;
+}
+
 #endif /* CONFIG_NET_RX_BUSY_POLL */
 
 /*
@@ -678,12 +767,6 @@ static void ep_done_scan(struct eventpoll *ep,
 	write_unlock_irq(&ep->lock);
 }
 
-static void epi_rcu_free(struct rcu_head *head)
-{
-	struct epitem *epi = container_of(head, struct epitem, rcu);
-	kmem_cache_free(epi_cache, epi);
-}
-
 static void ep_get(struct eventpoll *ep)
 {
 	refcount_inc(&ep->refcount);
@@ -767,7 +850,7 @@ static bool __ep_remove(struct eventpoll *ep, struct epitem *epi, bool force)
 	 * ep->mtx. The rcu read side, reverse_path_check_proc(), does not make
 	 * use of the rbn field.
 	 */
-	call_rcu(&epi->rcu, epi_rcu_free);
+	kfree_rcu(epi, rcu);
 
 	percpu_counter_dec(&ep->user->epoll_watches);
 	return ep_refcount_dec_and_test(ep);
@@ -825,6 +908,27 @@ static void ep_clear_and_put(struct eventpoll *ep)
 		ep_free(ep);
 }
 
+static long ep_eventpoll_ioctl(struct file *file, unsigned int cmd,
+			       unsigned long arg)
+{
+	int ret;
+
+	if (!is_file_epoll(file))
+		return -EINVAL;
+
+	switch (cmd) {
+	case EPIOCSPARAMS:
+	case EPIOCGPARAMS:
+		ret = ep_eventpoll_bp_ioctl(file, cmd, arg);
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	}
+
+	return ret;
+}
+
 static int ep_eventpoll_release(struct inode *inode, struct file *file)
 {
 	struct eventpoll *ep = file->private_data;
@@ -967,6 +1071,8 @@ static const struct file_operations eventpoll_fops = {
 	.release	= ep_eventpoll_release,
 	.poll		= ep_eventpoll_poll,
 	.llseek		= noop_llseek,
+	.unlocked_ioctl	= ep_eventpoll_ioctl,
+	.compat_ioctl   = compat_ptr_ioctl,
 };
 
 /*
@@ -1189,7 +1295,7 @@ static inline bool chain_epi_lockless(struct epitem *epi)
  * This callback takes a read lock in order not to contend with concurrent
  * events from another file descriptor, thus all modifications to ->rdllist
  * or ->ovflist are lockless.  Read lock is paired with the write lock from
- * ep_scan_ready_list(), which stops all list modifications and guarantees
+ * ep_start/done_scan(), which stops all list modifications and guarantees
  * that lists state is seen correctly.
  *
  * Another thing worth to mention is that ep_poll_callback() can be called
@@ -1787,7 +1893,7 @@ static int ep_send_events(struct eventpoll *ep,
 			 * availability. At this point, no one can insert
 			 * into ep->rdllist besides us. The epoll_ctl()
 			 * callers are locked out by
-			 * ep_scan_ready_list() holding "mtx" and the
+			 * ep_send_events() holding "mtx" and the
 			 * poll callback will queue them in ep->ovflist.
 			 */
 			list_add_tail(&epi->rdllink, &ep->rdllist);
@@ -1940,7 +2046,7 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
 		__set_current_state(TASK_INTERRUPTIBLE);
 
 		/*
-		 * Do the final check under the lock. ep_scan_ready_list()
+		 * Do the final check under the lock. ep_start/done_scan()
 		 * plays with two lists (->rdllist and ->ovflist) and there
 		 * is always a race when both lists are empty for short
 		 * period of time although events are pending, so lock is
@@ -2094,6 +2200,11 @@ static int do_epoll_create(int flags)
 		error = PTR_ERR(file);
 		goto out_free_fd;
 	}
+#ifdef CONFIG_NET_RX_BUSY_POLL
+	ep->busy_poll_usecs = 0;
+	ep->busy_poll_budget = 0;
+	ep->prefer_busy_poll = false;
+#endif
 	ep->file = file;
 	fd_install(fd, file);
 	return fd;