[PATCH v8 01/24] PCI: Fix race condition in pci_enable/disable_device()

[Sergei Miroshnichenko <s.miroshnichenko@xxxxxxxxx>]

This is a yet another approach to fix an old [1-2] concurrency issue, when:
 - two or more devices are being hot-added into a bridge which was
   initially empty;
 - a bridge with two or more devices is being hot-added;
 - during boot, if BIOS/bootloader/firmware doesn't pre-enable bridges.

The problem is that a bridge is reported as enabled before the MEM/IO bits
are actually written to the PCI_COMMAND register, so another driver thread
starts memory requests through the not-yet-enabled bridge:

 CPU0                                        CPU1

 pci_enable_device_mem()                     pci_enable_device_mem()
   pci_enable_bridge()                         pci_enable_bridge()
     pci_is_enabled()
       return false;
     atomic_inc_return(enable_cnt)
     Start actual enabling the bridge
     ...                                         pci_is_enabled()
     ...                                           return true;
     ...                                     Start memory requests <-- FAIL
     ...
     Set the PCI_COMMAND_MEMORY bit <-- Must wait for this

Protect the pci_enable/disable_device() and pci_enable_bridge(), which is
similar to the previous solution from commit 40f11adc7cd9 ("PCI: Avoid race
while enabling upstream bridges"), but adding a per-device mutexes and
preventing the dev->enable_cnt from from incrementing early.

CC: Srinath Mannam <srinath.mannam@xxxxxxxxxxxx>
CC: Marta Rybczynska <mrybczyn@xxxxxxxxx>
Signed-off-by: Sergei Miroshnichenko <s.miroshnichenko@xxxxxxxxx>

[1] https://lore.kernel.org/linux-pci/1501858648-22228-1-git-send-email-srinath.mannam@xxxxxxxxxxxx/T/#u
    [RFC PATCH v3] pci: Concurrency issue during pci enable bridge

[2] https://lore.kernel.org/linux-pci/744877924.5841545.1521630049567.JavaMail.zimbra@xxxxxxxxx/T/#u
    [RFC PATCH] nvme: avoid race-conditions when enabling devices
---
 drivers/pci/pci.c   | 27 +++++++++++++++++++++++----
 drivers/pci/probe.c |  1 +
 include/linux/pci.h |  1 +
 3 files changed, 25 insertions(+), 4 deletions(-)

diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 595fcf59843f..d7819be809a3 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -1733,6 +1733,8 @@ static void pci_enable_bridge(struct pci_dev *dev)
 	struct pci_dev *bridge;
 	int retval;
 
+	mutex_lock(&dev->enable_mutex);
+
 	bridge = pci_upstream_bridge(dev);
 	if (bridge)
 		pci_enable_bridge(bridge);
@@ -1740,6 +1742,7 @@ static void pci_enable_bridge(struct pci_dev *dev)
 	if (pci_is_enabled(dev)) {
 		if (!dev->is_busmaster)
 			pci_set_master(dev);
+		mutex_unlock(&dev->enable_mutex);
 		return;
 	}
 
@@ -1748,11 +1751,14 @@ static void pci_enable_bridge(struct pci_dev *dev)
 		pci_err(dev, "Error enabling bridge (%d), continuing\n",
 			retval);
 	pci_set_master(dev);
+	mutex_unlock(&dev->enable_mutex);
 }
 
 static int pci_enable_device_flags(struct pci_dev *dev, unsigned long flags)
 {
 	struct pci_dev *bridge;
+	/* Enable-locking of bridges is performed within the pci_enable_bridge() */
+	bool need_lock = !dev->subordinate;
 	int err;
 	int i, bars = 0;
 
@@ -1768,8 +1774,13 @@ static int pci_enable_device_flags(struct pci_dev *dev, unsigned long flags)
 		dev->current_state = (pmcsr & PCI_PM_CTRL_STATE_MASK);
 	}
 
-	if (atomic_inc_return(&dev->enable_cnt) > 1)
+	if (need_lock)
+		mutex_lock(&dev->enable_mutex);
+	if (pci_is_enabled(dev)) {
+		if (need_lock)
+			mutex_unlock(&dev->enable_mutex);
 		return 0;		/* already enabled */
+	}
 
 	bridge = pci_upstream_bridge(dev);
 	if (bridge)
@@ -1784,8 +1795,10 @@ static int pci_enable_device_flags(struct pci_dev *dev, unsigned long flags)
 			bars |= (1 << i);
 
 	err = do_pci_enable_device(dev, bars);
-	if (err < 0)
-		atomic_dec(&dev->enable_cnt);
+	if (err >= 0)
+		atomic_inc(&dev->enable_cnt);
+	if (need_lock)
+		mutex_unlock(&dev->enable_mutex);
 	return err;
 }
 
@@ -2029,15 +2042,21 @@ void pci_disable_device(struct pci_dev *dev)
 	if (dr)
 		dr->enabled = 0;
 
+	mutex_lock(&dev->enable_mutex);
+
 	dev_WARN_ONCE(&dev->dev, atomic_read(&dev->enable_cnt) <= 0,
 		      "disabling already-disabled device");
 
-	if (atomic_dec_return(&dev->enable_cnt) != 0)
+	if (atomic_dec_return(&dev->enable_cnt) != 0) {
+		mutex_unlock(&dev->enable_mutex);
 		return;
+	}
 
 	do_pci_disable_device(dev);
 
 	dev->is_busmaster = 0;
+
+	mutex_unlock(&dev->enable_mutex);
 }
 EXPORT_SYMBOL(pci_disable_device);
 
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index 77b8a145c39b..dd169e2935df 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -2210,6 +2210,7 @@ struct pci_dev *pci_alloc_dev(struct pci_bus *bus)
 	INIT_LIST_HEAD(&dev->bus_list);
 	dev->dev.type = &pci_dev_type;
 	dev->bus = pci_bus_get(bus);
+	mutex_init(&dev->enable_mutex);
 
 	return dev;
 }
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 83ce1cdf5676..d3c9fc20fc1f 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -431,6 +431,7 @@ struct pci_dev {
 	unsigned int	no_vf_scan:1;		/* Don't scan for VFs after IOV enablement */
 	pci_dev_flags_t dev_flags;
 	atomic_t	enable_cnt;	/* pci_enable_device has been called */
+	struct mutex	enable_mutex;
 
 	u32		saved_config_space[16]; /* Config space saved at suspend time */
 	struct hlist_head saved_cap_space;
-- 
2.24.1