powerpc/eeh: Clear frozen device state in time

The problem was reported by Carol: In the scenario of passing mlx4
adapter to guest, EEH error could be recovered successfully. When
returning the device back to host, the driver (mlx4_core.ko)
couldn't be loaded successfully because of error number -5 (-EIO)
returned from mlx4_get_ownership(), which hits offlined PCI device.
The root cause is that we missed to put the affected devices into
normal state on clearing PE isolated state right after PE reset.

The patch fixes above issue by putting the affected devices to
normal state when clearing PE isolated state in eeh_pe_state_clear().

Cc: stable@vger.kernel.org
Reported-by: Carol L. Soto <clsoto@us.ibm.com>
Signed-off-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

1 files changed, 18 insertions, 3 deletions

diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c
index 5864017..53dd091 100644
--- a/arch/powerpc/kernel/eeh_pe.c
+++ b/arch/powerpc/kernel/eeh_pe.c
@@ -584,6 +584,8 @@ static void *__eeh_pe_state_clear(void *data, void *flag)
 {
 	struct eeh_pe *pe = (struct eeh_pe *)data;
 	int state = *((int *)flag);
+	struct eeh_dev *edev, *tmp;
+	struct pci_dev *pdev;
 
 	/* Keep the state of permanently removed PE intact */
 	if ((pe->freeze_count > EEH_MAX_ALLOWED_FREEZES) &&
@@ -592,9 +594,22 @@ static void *__eeh_pe_state_clear(void *data, void *flag)
 
 	pe->state &= ~state;
 
-	/* Clear check count since last isolation */
-	if (state & EEH_PE_ISOLATED)
-		pe->check_count = 0;
+	/*
+	 * Special treatment on clearing isolated state. Clear
+	 * check count since last isolation and put all affected
+	 * devices to normal state.
+	 */
+	if (!(state & EEH_PE_ISOLATED))
+		return NULL;
+
+	pe->check_count = 0;
+	eeh_pe_for_each_dev(pe, edev, tmp) {
+		pdev = eeh_dev_to_pci_dev(edev);
+		if (!pdev)
+			continue;
+
+		pdev->error_state = pci_channel_io_normal;
+	}
 
 	return NULL;
 }