[PATCH net-next v2 04/13] net: mana: swap queue sets in mana_set_priv_flags

[Long Li <longli@microsoft.com>]

MANA_PRIV_FLAG_USE_FULL_PAGE_RXBUF changes the RX buffer layout, so
toggling it rebuilds the queues. Convert that path to the pre-allocate
and swap helpers, for the same reasons as the channel count and ring
size paths: an allocation failure now returns the error with both the
queues and the flag word untouched, and the vport is never released so
RDMA cannot claim it mid-reconfiguration.

The flag word is no longer written before the rebuild and rolled back on
failure. It is passed to mana_alloc_qset() as part of the queue-set
configuration and installed by mana_publish_qset() only once the new set
is serving traffic, so there is no window where apc->priv_flags
describes queues that do not exist.

Scheduling queue_reset_work() on failure is dropped along with it. After
this patch the TX timeout handler is the only remaining user of
queue_reset_work().

The existing shortcuts are unchanged in behaviour - a down port, or a
configuration where single-buffer-per-page is already forced by a jumbo
MTU or an attached XDP program, still just records the new value - but
they now share one condition instead of being spread across the
function.

Signed-off-by: Long Li <longli@microsoft.com>
---
 .../ethernet/microsoft/mana/mana_ethtool.c    | 85 ++++++++++---------
 1 file changed, 47 insertions(+), 38 deletions(-)

diff --git a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c
index bff6f69a9457c04c3555e9ef418b0e83b8e54d0d..9392b82d3d48a2638512a53f9c004629b0c679e5 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c
@@ -891,11 +891,18 @@ static u32 mana_get_priv_flags(struct net_device *ndev)
 	return apc->priv_flags;
 }
 
+/* mana_set_priv_flags - apply a change to the driver private flags
+ *
+ * MANA_PRIV_FLAG_USE_FULL_PAGE_RXBUF changes the RX buffer layout, so the
+ * queues must be rebuilt. Uses the pre-allocate + swap path, so a failed
+ * allocation leaves both the queues and the flag word untouched.
+ */
 static int mana_set_priv_flags(struct net_device *ndev, u32 priv_flags)
 {
 	struct mana_port_context *apc = netdev_priv(ndev);
 	u32 changed = apc->priv_flags ^ priv_flags;
-	u32 old_priv_flags = apc->priv_flags;
+	struct mana_port_context *scratch;
+	struct mana_qset newq, oldq;
 	int err = 0;
 
 	if (!changed)
@@ -905,54 +912,56 @@ static int mana_set_priv_flags(struct net_device *ndev, u32 priv_flags)
 	if (priv_flags & ~GENMASK(MANA_PRIV_FLAG_MAX - 1, 0))
 		return -EINVAL;
 
-	apc->priv_flags = priv_flags;
-
-	if (changed & BIT(MANA_PRIV_FLAG_USE_FULL_PAGE_RXBUF)) {
-		if (!apc->port_is_up)
-			return 0;
-
-		/* If XDP is attached or MTU is jumbo, single-buffer-per-page
-		 * is already forced regardless of this flag. Skip the
-		 * expensive detach/attach cycle since nothing changes.
-		 */
-		if (ndev->mtu + MANA_RXBUF_PAD > PAGE_SIZE / 2 ||
-		    mana_xdp_get(apc))
-			return 0;
+	/* Only the RX buffer layout flag requires a queue rebuild. Anything
+	 * else, a down port, or a configuration where single-buffer-per-page
+	 * is already forced, just records the new value.
+	 */
+	if (!(changed & BIT(MANA_PRIV_FLAG_USE_FULL_PAGE_RXBUF)) ||
+	    !apc->port_is_up ||
+	    ndev->mtu + MANA_RXBUF_PAD > PAGE_SIZE / 2 ||
+	    mana_xdp_get(apc)) {
+		apc->priv_flags = priv_flags;
+		return 0;
+	}
 
-		/* Block RDMA from grabbing the vport during detach/attach */
-		mutex_lock(&apc->vport_mutex);
-		apc->channel_changing = true;
+	/* Block RDMA from acquiring the vport for the duration. */
+	mutex_lock(&apc->vport_mutex);
+	if (apc->channel_changing) {
 		mutex_unlock(&apc->vport_mutex);
+		return -EBUSY;
+	}
+	apc->channel_changing = true;
+	mutex_unlock(&apc->vport_mutex);
 
-		err = mana_pre_alloc_rxbufs(apc, ndev->mtu, apc->num_queues);
-		if (err) {
-			netdev_err(ndev,
-				   "Insufficient memory for new allocations\n");
-			apc->priv_flags = old_priv_flags;
-			goto clear_flag;
-		}
+	scratch = mana_qset_scratch_alloc(apc);
+	if (!scratch) {
+		err = -ENOMEM;
+		goto clear_flag;
+	}
 
-		err = mana_detach(ndev, false);
-		if (err) {
-			netdev_err(ndev, "mana_detach failed: %d\n", err);
-			apc->priv_flags = old_priv_flags;
-			goto out;
-		}
+	err = mana_alloc_qset(scratch, apc->num_queues, apc->rx_queue_size,
+			      apc->tx_queue_size, priv_flags, &newq);
+	if (err)
+		goto free_scratch; /* current qset and priv_flags untouched */
 
-		err = mana_attach(ndev);
-		if (err) {
-			netdev_err(ndev, "mana_attach failed: %d\n", err);
-			apc->priv_flags = old_priv_flags;
-		}
+	err = mana_publish_qset(apc, &newq, &oldq);
+	if (err) {
+		mana_free_qset(scratch, &newq);
+		goto free_scratch;
 	}
 
-out:
-	mana_pre_dealloc_rxbufs(apc);
+	mana_free_qset(scratch, &oldq);
+
+free_scratch:
+	/* After the caller-side cleanup above, so the EQ pool outlives the
+	 * CQs that reference it.
+	 */
+	mana_publish_close_if_needed(apc);
+	mana_qset_scratch_free(scratch);
 clear_flag:
 	mutex_lock(&apc->vport_mutex);
 	apc->channel_changing = false;
 	mutex_unlock(&apc->vport_mutex);
-
 	return err;
 }
 
-- 
2.43.0