[RFC PATCH 5/5] PCI/P2PDMA: Introduce a helper to release P2P resources

[Pranjal Shrivastava <praan@google.com>]

Introduce pci_p2pdma_remove_resource() to allow manual teardown of a
device's P2P DMA pool. The new API enables exclusive owners of a device,
such as vfio-pci, to cleanly release P2P resources during session closure
or hardware reset.

Update vfio-pci to call this function during vfio_pci_zap_bars(),
ensuring that any BARs registered with ZONE_DEVICE P2P are released.

Signed-off-by: Pranjal Shrivastava <praan@google.com>
---
 drivers/pci/p2pdma.c             | 38 ++++++++++++++++++++++++++++++++
 drivers/vfio/pci/vfio_pci_core.c |  5 +++++
 include/linux/pci-p2pdma.h       |  1 +
 3 files changed, 44 insertions(+)

diff --git a/drivers/pci/p2pdma.c b/drivers/pci/p2pdma.c
index adb17a4f6939..2a48ffefa01c 100644
--- a/drivers/pci/p2pdma.c
+++ b/drivers/pci/p2pdma.c
@@ -26,6 +26,7 @@ struct pci_p2pdma {
 	bool p2pmem_published;
 	struct xarray map_types;
 	struct p2pdma_provider mem[PCI_STD_NUM_BARS];
+	struct pci_p2pdma_pagemap *pagemaps[PCI_STD_NUM_BARS];
 };
 
 struct pci_p2pdma_pagemap {
@@ -453,6 +454,8 @@ int pci_p2pdma_add_resource(struct pci_dev *pdev, int bar, size_t size,
 	if (error)
 		goto pages_free;
 
+	p2pdma->pagemaps[bar] = p2p_pgmap;
+
 	pci_info(pdev, "added peer-to-peer DMA memory %#llx-%#llx\n",
 		 pgmap->range.start, pgmap->range.end);
 
@@ -466,6 +469,41 @@ int pci_p2pdma_add_resource(struct pci_dev *pdev, int bar, size_t size,
 }
 EXPORT_SYMBOL_GPL(pci_p2pdma_add_resource);
 
+/**
+ * pci_p2pdma_remove_resource - remove all p2p memory for a device
+ * @pdev: the device to remove the memory from
+ *
+ * Tear down the entire p2p DMA pool for the device. Zap any existinga
+ * userspace mappings of the p2pmem/allocate file
+ */
+void pci_p2pdma_remove_resource(struct pci_dev *pdev)
+{
+	struct pci_p2pdma *p2pdma;
+	int i;
+
+	p2pdma = rcu_dereference_protected(pdev->p2pdma, 1);
+	if (!p2pdma || !p2pdma->pool)
+		return;
+
+	for (i = 0; i < PCI_STD_NUM_BARS; i++) {
+		if (p2pdma->pagemaps[i]) {
+			devm_release_action(&pdev->dev, pci_p2pdma_unmap_mappings,
+					    p2pdma->pagemaps[i]);
+			devm_memunmap_pages(&pdev->dev, &p2pdma->pagemaps[i]->pgmap);
+			devm_kfree(&pdev->dev, p2pdma->pagemaps[i]);
+			p2pdma->pagemaps[i] = NULL;
+		}
+	}
+
+	gen_pool_destroy(p2pdma->pool);
+	p2pdma->pool = NULL;
+
+	sysfs_remove_group(&pdev->dev.kobj, &p2pmem_group);
+
+	pci_info(pdev, "removed all peer-to-peer DMA memory\n");
+}
+EXPORT_SYMBOL_GPL(pci_p2pdma_remove_resource);
+
 /*
  * Note this function returns the parent PCI device with a
  * reference taken. It is the caller's responsibility to drop
diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c
index 7913b8916df9..7b58cb344408 100644
--- a/drivers/vfio/pci/vfio_pci_core.c
+++ b/drivers/vfio/pci/vfio_pci_core.c
@@ -1704,6 +1704,11 @@ static void vfio_pci_zap_bars(struct vfio_pci_core_device *vdev)
 	loff_t len = end - start;
 
 	unmap_mapping_range(core_vdev->inode->i_mapping, start, len, true);
+
+	if (vdev->p2p_registered_bars) {
+		pci_p2pdma_remove_resource(vdev->pdev);
+		vdev->p2p_registered_bars = 0;
+	}
 }
 
 void vfio_pci_zap_and_down_write_memory_lock(struct vfio_pci_core_device *vdev)
diff --git a/include/linux/pci-p2pdma.h b/include/linux/pci-p2pdma.h
index 873de20a2247..14ee2e59a43e 100644
--- a/include/linux/pci-p2pdma.h
+++ b/include/linux/pci-p2pdma.h
@@ -72,6 +72,7 @@ int pcim_p2pdma_init(struct pci_dev *pdev);
 struct p2pdma_provider *pcim_p2pdma_provider(struct pci_dev *pdev, int bar);
 int pci_p2pdma_add_resource(struct pci_dev *pdev, int bar, size_t size,
 		u64 offset);
+void pci_p2pdma_remove_resource(struct pci_dev *pdev);
 int pci_p2pdma_distance_many(struct pci_dev *provider, struct device **clients,
 			     int num_clients, bool verbose);
 struct pci_dev *pci_p2pmem_find_many(struct device **clients, int num_clients);
-- 
2.54.0.1099.g489fc7bff1-goog