PCI: add support for function level reset

Sometimes, it's necessary to enable software's ability to quiesce and
reset endpoint hardware with function-level granularity, so provide
support for it.

The patch implement Function Level Reset(FLR) feature following PCI-e
spec. And this is the first step. We would add more generic method, like
D0/D3, to allow more devices support this function.

The patch contains two functions. pcie_reset_function() is the new
driver API, and, contains some action to quiesce a device.  The other
function is a helper:  pcie_execute_reset_function() just executes the
reset for a particular device function.

Current the usage model is in KVM. Function reset is necessary for
assigning device to a guest, or moving it between partitions.

For Function Level Reset(FLR), please refer to PCI Express spec chapter
6.6.2.

Signed-off-by: Sheng Yang <sheng@linux.intel.com>
Signed-off-by: Matthew Wilcox <willy@linux.intel.com>
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>

3 files changed, 102 insertions, 0 deletions

diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index aee73cf251b..533aeb5fcbe 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -18,6 +18,7 @@
 #include <linux/log2.h>
 #include <linux/pci-aspm.h>
 #include <linux/pm_wakeup.h>
+#include <linux/interrupt.h>
 #include <asm/dma.h>	/* isa_dma_bridge_buggy */
 #include "pci.h"
 
@@ -1746,6 +1747,103 @@ EXPORT_SYMBOL(pci_set_dma_seg_boundary);
 #endif
 
 /**
+ * pci_execute_reset_function() - Reset a PCI device function
+ * @dev: Device function to reset
+ *
+ * Some devices allow an individual function to be reset without affecting
+ * other functions in the same device.  The PCI device must be responsive
+ * to PCI config space in order to use this function.
+ *
+ * The device function is presumed to be unused when this function is called.
+ * Resetting the device will make the contents of PCI configuration space
+ * random, so any caller of this must be prepared to reinitialise the
+ * device including MSI, bus mastering, BARs, decoding IO and memory spaces,
+ * etc.
+ *
+ * Returns 0 if the device function was successfully reset or -ENOTTY if the
+ * device doesn't support resetting a single function.
+ */
+int pci_execute_reset_function(struct pci_dev *dev)
+{
+	u16 status;
+	u32 cap;
+	int exppos = pci_find_capability(dev, PCI_CAP_ID_EXP);
+
+	if (!exppos)
+		return -ENOTTY;
+	pci_read_config_dword(dev, exppos + PCI_EXP_DEVCAP, &cap);
+	if (!(cap & PCI_EXP_DEVCAP_FLR))
+		return -ENOTTY;
+
+	pci_block_user_cfg_access(dev);
+
+	/* Wait for Transaction Pending bit clean */
+	msleep(100);
+	pci_read_config_word(dev, exppos + PCI_EXP_DEVSTA, &status);
+	if (status & PCI_EXP_DEVSTA_TRPND) {
+		dev_info(&dev->dev, "Busy after 100ms while trying to reset; "
+			"sleeping for 1 second\n");
+		ssleep(1);
+		pci_read_config_word(dev, exppos + PCI_EXP_DEVSTA, &status);
+		if (status & PCI_EXP_DEVSTA_TRPND)
+			dev_info(&dev->dev, "Still busy after 1s; "
+				"proceeding with reset anyway\n");
+	}
+
+	pci_write_config_word(dev, exppos + PCI_EXP_DEVCTL,
+				PCI_EXP_DEVCTL_BCR_FLR);
+	mdelay(100);
+
+	pci_unblock_user_cfg_access(dev);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(pci_execute_reset_function);
+
+/**
+ * pci_reset_function() - quiesce and reset a PCI device function
+ * @dev: Device function to reset
+ *
+ * Some devices allow an individual function to be reset without affecting
+ * other functions in the same device.  The PCI device must be responsive
+ * to PCI config space in order to use this function.
+ *
+ * This function does not just reset the PCI portion of a device, but
+ * clears all the state associated with the device.  This function differs
+ * from pci_execute_reset_function in that it saves and restores device state
+ * over the reset.
+ *
+ * Returns 0 if the device function was successfully reset or -ENOTTY if the
+ * device doesn't support resetting a single function.
+ */
+int pci_reset_function(struct pci_dev *dev)
+{
+	u32 cap;
+	int exppos = pci_find_capability(dev, PCI_CAP_ID_EXP);
+	int r;
+
+	if (!exppos)
+		return -ENOTTY;
+	pci_read_config_dword(dev, exppos + PCI_EXP_DEVCAP, &cap);
+	if (!(cap & PCI_EXP_DEVCAP_FLR))
+		return -ENOTTY;
+
+	if (!dev->msi_enabled && !dev->msix_enabled)
+		disable_irq(dev->irq);
+	pci_save_state(dev);
+
+	pci_write_config_word(dev, PCI_COMMAND, PCI_COMMAND_INTX_DISABLE);
+
+	r = pci_execute_reset_function(dev);
+
+	pci_restore_state(dev);
+	if (!dev->msi_enabled && !dev->msix_enabled)
+		enable_irq(dev->irq);
+
+	return r;
+}
+EXPORT_SYMBOL_GPL(pci_reset_function);
+
+/**
  * pcix_get_max_mmrbc - get PCI-X maximum designed memory read byte count
  * @dev: PCI device to query
  *
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 085187be29c..f6f6810296e 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -626,6 +626,8 @@ int pcix_get_mmrbc(struct pci_dev *dev);
 int pcix_set_mmrbc(struct pci_dev *dev, int mmrbc);
 int pcie_get_readrq(struct pci_dev *dev);
 int pcie_set_readrq(struct pci_dev *dev, int rq);
+int pci_reset_function(struct pci_dev *dev);
+int pci_execute_reset_function(struct pci_dev *dev);
 void pci_update_resource(struct pci_dev *dev, struct resource *res, int resno);
 int __must_check pci_assign_resource(struct pci_dev *dev, int i);
 int pci_select_bars(struct pci_dev *dev, unsigned long flags);
diff --git a/include/linux/pci_regs.h b/include/linux/pci_regs.h
index eb6686b88f9..e5effd47ed7 100644
--- a/include/linux/pci_regs.h
+++ b/include/linux/pci_regs.h
@@ -377,6 +377,7 @@
 #define  PCI_EXP_DEVCAP_RBER	0x8000	/* Role-Based Error Reporting */
 #define  PCI_EXP_DEVCAP_PWR_VAL	0x3fc0000 /* Slot Power Limit Value */
 #define  PCI_EXP_DEVCAP_PWR_SCL	0xc000000 /* Slot Power Limit Scale */
+#define  PCI_EXP_DEVCAP_FLR     0x10000000 /* Function Level Reset */
 #define PCI_EXP_DEVCTL		8	/* Device Control */
 #define  PCI_EXP_DEVCTL_CERE	0x0001	/* Correctable Error Reporting En. */
 #define  PCI_EXP_DEVCTL_NFERE	0x0002	/* Non-Fatal Error Reporting Enable */
@@ -389,6 +390,7 @@
 #define  PCI_EXP_DEVCTL_AUX_PME	0x0400	/* Auxiliary Power PM Enable */
 #define  PCI_EXP_DEVCTL_NOSNOOP_EN 0x0800  /* Enable No Snoop */
 #define  PCI_EXP_DEVCTL_READRQ	0x7000	/* Max_Read_Request_Size */
+#define  PCI_EXP_DEVCTL_BCR_FLR 0x8000  /* Bridge Configuration Retry / FLR */
 #define PCI_EXP_DEVSTA		10	/* Device Status */
 #define  PCI_EXP_DEVSTA_CED	0x01	/* Correctable Error Detected */
 #define  PCI_EXP_DEVSTA_NFED	0x02	/* Non-Fatal Error Detected */