serial: 8250_pci: Detach low-level driver during PCI error recovery

commit f209fa03fc9d131b3108c2e4936181eabab87416 upstream.

During a PCI error recovery, like the ones provoked by EEH in the ppc64
platform, all IO to the device must be blocked while the recovery is
completed.  Current 8250_pci implementation only suspends the port
instead of detaching it, which doesn't prevent incoming accesses like
TIOCMGET and TIOCMSET calls from reaching the device.  Those end up
racing with the EEH recovery, crashing it.  Similar races were also
observed when opening the device and when shutting it down during
recovery.

This patch implements a more robust IO blockage for the 8250_pci
recovery by unregistering the port at the beginning of the procedure and
re-adding it afterwards.  Since the port is detached from the uart
layer, we can be sure that no request will make through to the device
during recovery.  This is similar to the solution used by the JSM serial
driver.

I thank Peter Hurley <peter@hurleysoftware.com> for valuable input on
this one over one year ago.

Signed-off-by: Gabriel Krisman Bertazi <krisman@linux.vnet.ibm.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Willy Tarreau <w@1wt.eu>

diff --git a/drivers/tty/serial/8250/8250_pci.c b/drivers/tty/serial/8250/8250_pci.c
index 98b8423793fd09f1a486a92fbd2118aa910da279..9243dd729dd4914054310cde00b983d186cdc449 100644 (file)
--- a/drivers/tty/serial/8250/8250_pci.c
+++ b/drivers/tty/serial/8250/8250_pci.c
@@ -55,6 +55,7 @@ struct serial_private {
        unsigned int            nr;
        void __iomem            *remapped_bar[PCI_NUM_BAR_RESOURCES];
        struct pci_serial_quirk *quirk;
+       const struct pciserial_board *board;
        int                     line[0];
 };
 
@@ -3374,6 +3375,7 @@ pciserial_init_ports(struct pci_dev *dev, const struct pciserial_board *board)
                }
        }
        priv->nr = i;
+       priv->board = board;
        return priv;
 
 err_deinit:
@@ -3384,7 +3386,7 @@ err_out:
 }
 EXPORT_SYMBOL_GPL(pciserial_init_ports);
 
-void pciserial_remove_ports(struct serial_private *priv)
+void pciserial_detach_ports(struct serial_private *priv)
 {
        struct pci_serial_quirk *quirk;
        int i;
@@ -3404,7 +3406,11 @@ void pciserial_remove_ports(struct serial_private *priv)
        quirk = find_quirk(priv->dev);
        if (quirk->exit)
                quirk->exit(priv->dev);
+}
 
+void pciserial_remove_ports(struct serial_private *priv)
+{
+       pciserial_detach_ports(priv);
        kfree(priv);
 }
 EXPORT_SYMBOL_GPL(pciserial_remove_ports);
@@ -4943,7 +4949,7 @@ static pci_ers_result_t serial8250_io_error_detected(struct pci_dev *dev,
                return PCI_ERS_RESULT_DISCONNECT;
 
        if (priv)
-               pciserial_suspend_ports(priv);
+               pciserial_detach_ports(priv);
 
        pci_disable_device(dev);
 
@@ -4968,9 +4974,18 @@ static pci_ers_result_t serial8250_io_slot_reset(struct pci_dev *dev)
 static void serial8250_io_resume(struct pci_dev *dev)
 {
        struct serial_private *priv = pci_get_drvdata(dev);
+       const struct pciserial_board *board;
 
-       if (priv)
-               pciserial_resume_ports(priv);
+       if (!priv)
+               return;
+
+       board = priv->board;
+       kfree(priv);
+       priv = pciserial_init_ports(dev, board);
+
+       if (!IS_ERR(priv)) {
+               pci_set_drvdata(dev, priv);
+       }
 }
 
 static const struct pci_error_handlers serial8250_err_handler = {