[PATCH AUTOSEL 5.10 02/13] PCI: switchtec: Fix stdev_release() crash after surprise hot remove

[Sasha Levin]

From: Daniel Stodden <dns@xxxxxxxxxx>

[ Upstream commit df25461119d987b8c81d232cfe4411e91dcabe66 ]

A PCI device hot removal may occur while stdev->cdev is held open. The call
to stdev_release() then happens during close or exit, at a point way past
switchtec_pci_remove(). Otherwise the last ref would vanish with the
trailing put_device(), just before return.

At that later point in time, the devm cleanup has already removed the
stdev->mmio_mrpc mapping. Also, the stdev->pdev reference was not a counted
one. Therefore, in DMA mode, the iowrite32() in stdev_release() will cause
a fatal page fault, and the subsequent dma_free_coherent(), if reached,
would pass a stale &stdev->pdev->dev pointer.

Fix by moving MRPC DMA shutdown into switchtec_pci_remove(), after
stdev_kill(). Counting the stdev->pdev ref is now optional, but may prevent
future accidents.

Reproducible via the script at
https://lore.kernel.org/r/20231113212150.96410-1-dns@xxxxxxxxxx

Link: https://lore.kernel.org/r/20231122042316.91208-2-dns@xxxxxxxxxx
Signed-off-by: Daniel Stodden <dns@xxxxxxxxxx>
Signed-off-by: Bjorn Helgaas <bhelgaas@xxxxxxxxxx>
Reviewed-by: Logan Gunthorpe <logang@xxxxxxxxxxxx>
Reviewed-by: Dmitry Safonov <dima@xxxxxxxxxx>
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
---
 drivers/pci/switch/switchtec.c | 25 +++++++++++++++++--------
 1 file changed, 17 insertions(+), 8 deletions(-)

diff --git a/drivers/pci/switch/switchtec.c b/drivers/pci/switch/switchtec.c
index ba52459928f7..5cea3ad290c5 100644
--- a/drivers/pci/switch/switchtec.c
+++ b/drivers/pci/switch/switchtec.c
@@ -1251,13 +1251,6 @@ static void stdev_release(struct device *dev)
 {
 	struct switchtec_dev *stdev = to_stdev(dev);
 
-	if (stdev->dma_mrpc) {
-		iowrite32(0, &stdev->mmio_mrpc->dma_en);
-		flush_wc_buf(stdev);
-		writeq(0, &stdev->mmio_mrpc->dma_addr);
-		dma_free_coherent(&stdev->pdev->dev, sizeof(*stdev->dma_mrpc),
-				stdev->dma_mrpc, stdev->dma_mrpc_dma_addr);
-	}
 	kfree(stdev);
 }
 
@@ -1301,7 +1294,7 @@ static struct switchtec_dev *stdev_create(struct pci_dev *pdev)
 		return ERR_PTR(-ENOMEM);
 
 	stdev->alive = true;
-	stdev->pdev = pdev;
+	stdev->pdev = pci_dev_get(pdev);
 	INIT_LIST_HEAD(&stdev->mrpc_queue);
 	mutex_init(&stdev->mrpc_mutex);
 	stdev->mrpc_busy = 0;
@@ -1335,6 +1328,7 @@ static struct switchtec_dev *stdev_create(struct pci_dev *pdev)
 	return stdev;
 
 err_put:
+	pci_dev_put(stdev->pdev);
 	put_device(&stdev->dev);
 	return ERR_PTR(rc);
 }
@@ -1587,6 +1581,18 @@ static int switchtec_init_pci(struct switchtec_dev *stdev,
 	return 0;
 }
 
+static void switchtec_exit_pci(struct switchtec_dev *stdev)
+{
+	if (stdev->dma_mrpc) {
+		iowrite32(0, &stdev->mmio_mrpc->dma_en);
+		flush_wc_buf(stdev);
+		writeq(0, &stdev->mmio_mrpc->dma_addr);
+		dma_free_coherent(&stdev->pdev->dev, sizeof(*stdev->dma_mrpc),
+				  stdev->dma_mrpc, stdev->dma_mrpc_dma_addr);
+		stdev->dma_mrpc = NULL;
+	}
+}
+
 static int switchtec_pci_probe(struct pci_dev *pdev,
 			       const struct pci_device_id *id)
 {
@@ -1646,6 +1652,9 @@ static void switchtec_pci_remove(struct pci_dev *pdev)
 	ida_simple_remove(&switchtec_minor_ida, MINOR(stdev->dev.devt));
 	dev_info(&stdev->dev, "unregistered.\n");
 	stdev_kill(stdev);
+	switchtec_exit_pci(stdev);
+	pci_dev_put(stdev->pdev);
+	stdev->pdev = NULL;
 	put_device(&stdev->dev);
 }
 
-- 
2.43.0