PCI: switch pci_{enable,disable}_device() to be nestable

Changes the pci_{enable,disable}_device() functions to work in a
nested basis, so that eg, three calls to enable_device() require three
calls to disable_device().

The reason for this is to simplify PCI drivers for
multi-interface/capability devices. These are devices that cram more
than one interface in a single function. A relevant example of that is
the Wireless [USB] Host Controller Interface (similar to EHCI) [see
http://www.intel.com/technology/comms/wusb/whci.htm]. 

In these kind of devices, multiple interfaces are accessed through a
single bar and IRQ line. For that, the drivers map only the smallest
area of the bar to access their register banks and use shared IRQ
handlers. 

However, because the order at which those drivers load cannot be known
ahead of time, the sequence in which the calls to pci_enable_device()
and pci_disable_device() cannot be predicted. Thus:

1. driverA     starts     pci_enable_device()
2. driverB     starts     pci_enable_device()
3. driverA     shutdown   pci_disable_device()
4. driverB     shutdown   pci_disable_device()

between steps 3 and 4, driver B would loose access to it's device,
even if it didn't intend to.

By using this modification, the device won't be disabled until all the
callers to enable() have called disable().

This is implemented by replacing 'struct pci_dev->is_enabled' from a
bitfield to an atomic use count. Each caller to enable increments it,
each caller to disable decrements it. When the count increments from 0
to 1, __pci_enable_device() is called to actually enable the
device. When it drops to zero, pci_disable_device() actually does the
disabling.

We keep the backend __pci_enable_device() for pci_default_resume() to
use and also change the sysfs method implementation, so that userspace
enabling/disabling the device doesn't disable it one time too much.

Signed-off-by: Inaky Perez-Gonzalez <inaky@linux.intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

drivers/pci/pci-driver.c

@@ -329,8 +329,8 @@ static int pci_default_resume(struct pci_dev *pci_dev)
 	/* restore the PCI config space */
 	pci_restore_state(pci_dev);
 	/* if the device was enabled before suspend, reenable */
-	if (pci_dev->is_enabled)
-		retval = pci_enable_device(pci_dev);
+	if (atomic_read(&pci_dev->enable_cnt))
+		retval = __pci_enable_device(pci_dev);
 	/* if the device was busmaster before the suspend, make it busmaster again */
 	if (pci_dev->is_busmaster)
 		pci_set_master(pci_dev);

drivers/pci/pci-sysfs.c

@@ -42,7 +42,6 @@ pci_config_attr(subsystem_vendor, "0x%04x\n");
 pci_config_attr(subsystem_device, "0x%04x\n");
 pci_config_attr(class, "0x%06x\n");
 pci_config_attr(irq, "%u\n");
-pci_config_attr(is_enabled, "%u\n");
 
 static ssize_t broken_parity_status_show(struct device *dev,
 					 struct device_attribute *attr,
@@ -112,26 +111,36 @@ static ssize_t modalias_show(struct device *dev, struct device_attribute *attr,
 		       (u8)(pci_dev->class >> 16), (u8)(pci_dev->class >> 8),
 		       (u8)(pci_dev->class));
 }
-static ssize_t
-is_enabled_store(struct device *dev, struct device_attribute *attr,
-		const char *buf, size_t count)
+
+static ssize_t is_enabled_store(struct device *dev,
+				struct device_attribute *attr, const char *buf,
+				size_t count)
 {
+	ssize_t result = -EINVAL;
 	struct pci_dev *pdev = to_pci_dev(dev);
-	int retval = 0;
 
 	/* this can crash the machine when done on the "wrong" device */
 	if (!capable(CAP_SYS_ADMIN))
 		return count;
 
-	if (*buf == '0')
-		pci_disable_device(pdev);
+	if (*buf == '0') {
+		if (atomic_read(&pdev->enable_cnt) != 0)
+			pci_disable_device(pdev);
+		else
+			result = -EIO;
+	} else if (*buf == '1')
+		result = pci_enable_device(pdev);
 
-	if (*buf == '1')
-		retval = pci_enable_device(pdev);
+	return result < 0 ? result : count;
+}
 
-	if (retval)
-		return retval;
-	return count;
+static ssize_t is_enabled_show(struct device *dev,
+			       struct device_attribute *attr, char *buf)
+{
+	struct pci_dev *pdev;
+
+	pdev = to_pci_dev (dev);
+	return sprintf (buf, "%u\n", atomic_read(&pdev->enable_cnt));
 }
 
 static ssize_t

drivers/pci/pci.c

@@ -611,6 +611,29 @@ pci_enable_device_bars(struct pci_dev *dev, int bars)
 	return 0;
 }
 
+/**
+ * __pci_enable_device - Initialize device before it's used by a driver.
+ * @dev: PCI device to be initialized
+ *
+ *  Initialize device before it's used by a driver. Ask low-level code
+ *  to enable I/O and memory. Wake up the device if it was suspended.
+ *  Beware, this function can fail.
+ *
+ * Note this function is a backend and is not supposed to be called by
+ * normal code, use pci_enable_device() instead.
+ */
+int
+__pci_enable_device(struct pci_dev *dev)
+{
+	int err;
+
+	err = pci_enable_device_bars(dev, (1 << PCI_NUM_RESOURCES) - 1);
+	if (err)
+		return err;
+	pci_fixup_device(pci_fixup_enable, dev);
+	return 0;
+}
+
 /**
  * pci_enable_device - Initialize device before it's used by a driver.
  * @dev: PCI device to be initialized
@@ -618,21 +641,19 @@ pci_enable_device_bars(struct pci_dev *dev, int bars)
  *  Initialize device before it's used by a driver. Ask low-level code
  *  to enable I/O and memory. Wake up the device if it was suspended.
  *  Beware, this function can fail.
+ *
+ *  Note we don't actually enable the device many times if we call
+ *  this function repeatedly (we just increment the count).
  */
-int
-pci_enable_device(struct pci_dev *dev)
+int pci_enable_device(struct pci_dev *dev)
 {
-	int err;
-
-	if (dev->is_enabled)
-		return 0;
-
-	err = pci_enable_device_bars(dev, (1 << PCI_NUM_RESOURCES) - 1);
-	if (err)
-		return err;
-	pci_fixup_device(pci_fixup_enable, dev);
-	dev->is_enabled = 1;
-	return 0;
+	int result;
+	if (atomic_add_return(1, &dev->enable_cnt) > 1)
+		return 0;		/* already enabled */
+	result = __pci_enable_device(dev);
+	if (result < 0)
+		atomic_dec(&dev->enable_cnt);
+	return result;
 }
 
 /**
@@ -651,12 +672,18 @@ void __attribute__ ((weak)) pcibios_disable_device (struct pci_dev *dev) {}
  *
  * Signal to the system that the PCI device is not in use by the system
  * anymore.  This only involves disabling PCI bus-mastering, if active.
+ *
+ * Note we don't actually disable the device until all callers of
+ * pci_device_enable() have called pci_device_disable().
  */
 void
 pci_disable_device(struct pci_dev *dev)
 {
 	u16 pci_command;
 
+	if (atomic_sub_return(1, &dev->enable_cnt) != 0)
+		return;
+
 	if (dev->msi_enabled)
 		disable_msi_mode(dev, pci_find_capability(dev, PCI_CAP_ID_MSI),
 			PCI_CAP_ID_MSI);
@@ -672,7 +699,6 @@ pci_disable_device(struct pci_dev *dev)
 	dev->is_busmaster = 0;
 
 	pcibios_disable_device(dev);
-	dev->is_enabled = 0;
 }
 
 /**

drivers/pci/pci.h

@@ -1,5 +1,6 @@
 /* Functions internal to the PCI core code */
 
+extern int __must_check __pci_enable_device(struct pci_dev *);
 extern int pci_uevent(struct device *dev, char **envp, int num_envp,
 		      char *buffer, int buffer_size);
 extern int pci_create_sysfs_dev_files(struct pci_dev *pdev);

include/linux/pci.h

@@ -51,6 +51,7 @@
 #include <linux/list.h>
 #include <linux/compiler.h>
 #include <linux/errno.h>
+#include <asm/atomic.h>
 #include <linux/device.h>
 
 /* File state for mmap()s on /proc/bus/pci/X/Y */
@@ -159,7 +160,6 @@ struct pci_dev {
 	unsigned int	transparent:1;	/* Transparent PCI bridge */
 	unsigned int	multifunction:1;/* Part of multi-function device */
 	/* keep track of device state */
-	unsigned int	is_enabled:1;	/* pci_enable_device has been called */
 	unsigned int	is_busmaster:1; /* device is busmaster */
 	unsigned int	no_msi:1;	/* device may not use msi */
 	unsigned int	no_d1d2:1;   /* only allow d0 or d3 */
@@ -167,6 +167,7 @@ struct pci_dev {
 	unsigned int	broken_parity_status:1;	/* Device generates false positive parity */
 	unsigned int 	msi_enabled:1;
 	unsigned int	msix_enabled:1;
+	atomic_t	enable_cnt;	/* pci_enable_device has been called */
 
 	u32		saved_config_space[16]; /* config space saved at suspend time */
 	struct hlist_head saved_cap_space;