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>

diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index fe9733ffffaa426f62f2559f66a6771833d0961e..471aac313b8995aa73dce880b8f98d715e59f8d9 100644 (file)
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -42,6 +42,8 @@
 #include <asm/ppc-pci.h>
 #include <asm/eeh.h>
 
+#include "../../../drivers/pci/pci.h"
+
 /* hose_spinlock protects accesses to the the phb_bitmap. */
 static DEFINE_SPINLOCK(hose_spinlock);
 LIST_HEAD(hose_list);
@@ -1014,7 +1016,7 @@ void pcibios_setup_bus_devices(struct pci_bus *bus)
                /* Cardbus can call us to add new devices to a bus, so ignore
                 * those who are already fully discovered
                 */
-               if (dev->is_added)
+               if (pci_dev_is_added(dev))
                        continue;
 
                pcibios_setup_device(dev);

diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 5bd0eb6681bcbc12c58a21c257cf7202a2d4c5a6..70b2e1e0f23c2c58432152267ff8f23d31772c0b 100644 (file)
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -46,6 +46,7 @@
 
 #include "powernv.h"
 #include "pci.h"
+#include "../../../../drivers/pci/pci.h"
 
 #define PNV_IODA1_M64_NUM      16      /* Number of M64 BARs   */
 #define PNV_IODA1_M64_SEGS     8       /* Segments per M64 BAR */
@@ -3138,7 +3139,7 @@ static void pnv_pci_ioda_fixup_iov_resources(struct pci_dev *pdev)
        struct pci_dn *pdn;
        int mul, total_vfs;
 
-       if (!pdev->is_physfn || pdev->is_added)
+       if (!pdev->is_physfn || pci_dev_is_added(pdev))
                return;
 
        pdn = pci_get_pdn(pdev);

diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index 139f0af6c3d9126f6c766f0958429fba721a018e..8a4868a3964bae4143a79ecfd8db5780f1ee7f19 100644 (file)
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -71,6 +71,7 @@
 #include <asm/security_features.h>
 
 #include "pseries.h"
+#include "../../../../drivers/pci/pci.h"
 
 int CMO_PrPSP = -1;
 int CMO_SecPSP = -1;
@@ -664,7 +665,7 @@ static void pseries_pci_fixup_iov_resources(struct pci_dev *pdev)
        const int *indexes;
        struct device_node *dn = pci_device_to_OF_node(pdev);
 
-       if (!pdev->is_physfn || pdev->is_added)
+       if (!pdev->is_physfn || pci_dev_is_added(pdev))
                return;
        /*Firmware must support open sriov otherwise dont configure*/
        indexes = of_get_property(dn, "ibm,open-sriov-vf-bar-info", NULL);

diff --git a/drivers/pci/bus.c b/drivers/pci/bus.c
index 35b7fc87eac506faf88ab3948e136195adfec823..5cb40b2518f9376dbe7edd4bf11d303daf97c025 100644 (file)
--- 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 3a17b290df5dd74010740762eb5dc00e163b32ec..ef0b1b6ba86f8fad2a570187252e7579e12ea129 100644 (file)
--- 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 882f1f9596dfffa644e624b3a42a120999f06581..08817253c8a2fa4851330dac05d5eb9c3f8e37d4 100644 (file)
--- 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 ac876e32de4b0fe4aaebf98209590720375daa50..611adcd9c16988efad379c83200d61f378a42881 100644 (file)
--- 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 6f072eae4f7a59a5f7678a6d258bf7fe458e4c43..5e3d0dced2b8d6bbf54185612bfe896f4d2941c0 100644 (file)
--- 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)

diff --git a/include/linux/pci.h b/include/linux/pci.h
index abd5d5e17aeed8a1402176d7be6da548ac1d91c5..c133ccfa002e17362288eab00b11bc04895c6805 100644 (file)
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -368,7 +368,6 @@ struct pci_dev {
        unsigned int    transparent:1;          /* Subtractive decode bridge */
        unsigned int    multifunction:1;        /* Multi-function device */
 
-       unsigned int    is_added:1;
        unsigned int    is_busmaster:1;         /* Is busmaster */
        unsigned int    no_msi:1;               /* May not use MSI */
        unsigned int    no_64bit_msi:1;         /* May only use 32-bit MSIs */