PCI: Fix is_added/is_busmaster race condition

When a PCI device is detected, pdev->is_added is set to 1 and proc and
sysfs entries are created.

When the device is removed, pdev->is_added is checked for one and then
device is detached with clearing of proc and sys entries and at end,
pdev->is_added is set to 0.

is_added and is_busmaster are bit fields in pci_dev structure sharing same
memory location.

A strange issue was observed with multiple removal and rescan of a PCIe
NVMe device using sysfs commands where is_added flag was observed as zero
instead of one while removing device and proc,sys entries are not cleared.
This causes issue in later device addition with warning message
"proc_dir_entry" already registered.

Debugging revealed a race condition between the PCI core setting the
is_added bit in pci_bus_add_device() and the NVMe driver reset work-queue
setting the is_busmaster bit in pci_set_master().  As these fields are not
handled atomically, that clears the is_added bit.

Move the is_added bit to a separate private flag variable and use atomic
functions to set and retrieve the device addition state.  This avoids the
race because is_added no longer shares a memory location with is_busmaster.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=200283
Signed-off-by: Hari Vyas <hari.vyas@broadcom.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Lukas Wunner <lukas@wunner.de>
Acked-by: Michael Ellerman <mpe@ellerman.id.au>

5 files changed, 20 insertions, 8 deletions

diff --git a/drivers/pci/bus.c b/drivers/pci/bus.c
index 35b7fc87eac5..5cb40b2518f9 100644
--- a/drivers/pci/bus.c
+++ b/drivers/pci/bus.c
@@ -330,7 +330,7 @@ void pci_bus_add_device(struct pci_dev *dev)
 		return;
 	}
 
-	dev->is_added = 1;
+	pci_dev_assign_added(dev, true);
 }
 EXPORT_SYMBOL_GPL(pci_bus_add_device);
 
@@ -347,14 +347,14 @@ void pci_bus_add_devices(const struct pci_bus *bus)
 
 	list_for_each_entry(dev, &bus->devices, bus_list) {
 		/* Skip already-added devices */
-		if (dev->is_added)
+		if (pci_dev_is_added(dev))
 			continue;
 		pci_bus_add_device(dev);
 	}
 
 	list_for_each_entry(dev, &bus->devices, bus_list) {
 		/* Skip if device attach failed */
-		if (!dev->is_added)
+		if (!pci_dev_is_added(dev))
 			continue;
 		child = dev->subordinate;
 		if (child)
diff --git a/drivers/pci/hotplug/acpiphp_glue.c b/drivers/pci/hotplug/acpiphp_glue.c
index 3a17b290df5d..ef0b1b6ba86f 100644
--- a/drivers/pci/hotplug/acpiphp_glue.c
+++ b/drivers/pci/hotplug/acpiphp_glue.c
@@ -509,7 +509,7 @@ static void enable_slot(struct acpiphp_slot *slot)
 
 	list_for_each_entry(dev, &bus->devices, bus_list) {
 		/* Assume that newly added devices are powered on already. */
-		if (!dev->is_added)
+		if (!pci_dev_is_added(dev))
 			dev->current_state = PCI_D0;
 	}
 
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index 882f1f9596df..08817253c8a2 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -288,6 +288,7 @@ struct pci_sriov {
 
 /* pci_dev priv_flags */
 #define PCI_DEV_DISCONNECTED 0
+#define PCI_DEV_ADDED 1
 
 static inline int pci_dev_set_disconnected(struct pci_dev *dev, void *unused)
 {
@@ -300,6 +301,16 @@ static inline bool pci_dev_is_disconnected(const struct pci_dev *dev)
 	return test_bit(PCI_DEV_DISCONNECTED, &dev->priv_flags);
 }
 
+static inline void pci_dev_assign_added(struct pci_dev *dev, bool added)
+{
+	assign_bit(PCI_DEV_ADDED, &dev->priv_flags, added);
+}
+
+static inline bool pci_dev_is_added(const struct pci_dev *dev)
+{
+	return test_bit(PCI_DEV_ADDED, &dev->priv_flags);
+}
+
 #ifdef CONFIG_PCI_ATS
 void pci_restore_ats_state(struct pci_dev *dev);
 #else
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index ac876e32de4b..611adcd9c169 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -2433,13 +2433,13 @@ int pci_scan_slot(struct pci_bus *bus, int devfn)
 	dev = pci_scan_single_device(bus, devfn);
 	if (!dev)
 		return 0;
-	if (!dev->is_added)
+	if (!pci_dev_is_added(dev))
 		nr++;
 
 	for (fn = next_fn(bus, dev, 0); fn > 0; fn = next_fn(bus, dev, fn)) {
 		dev = pci_scan_single_device(bus, devfn + fn);
 		if (dev) {
-			if (!dev->is_added)
+			if (!pci_dev_is_added(dev))
 				nr++;
 			dev->multifunction = 1;
 		}
diff --git a/drivers/pci/remove.c b/drivers/pci/remove.c
index 6f072eae4f7a..5e3d0dced2b8 100644
--- a/drivers/pci/remove.c
+++ b/drivers/pci/remove.c
@@ -19,11 +19,12 @@ static void pci_stop_dev(struct pci_dev *dev)
 {
 	pci_pme_active(dev, false);
 
-	if (dev->is_added) {
+	if (pci_dev_is_added(dev)) {
 		device_release_driver(&dev->dev);
 		pci_proc_detach_device(dev);
 		pci_remove_sysfs_dev_files(dev);
-		dev->is_added = 0;
+
+		pci_dev_assign_added(dev, false);
 	}
 
 	if (dev->bus->self)