diff mbox series

[v15,4/7] bus/pci: implement sigbus handler ops

Message ID 1539602847-19220-5-git-send-email-jia.guo@intel.com (mailing list archive)
State Accepted, archived
Delegated to: Thomas Monjalon
Headers
Series hot-unplug failure handle mechanism |

Checks

Context Check Description
ci/Intel-compilation fail Compilation issues
ci/checkpatch success coding style OK

Commit Message

Guo, Jia Oct. 15, 2018, 11:27 a.m. UTC 
  This patch implements the ops for the PCI bus sigbus handler. It finds the
PCI device that is being hot-unplugged and calls the relevant ops of the
hot-unplug handler to handle the hot-unplug failure of the device.

Signed-off-by: Jeff Guo <jia.guo@intel.com>
Acked-by: Shaopeng He <shaopeng.he@intel.com>
Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
---
v15->v14:
fix compling issue.
---
 drivers/bus/pci/pci_common.c | 54 ++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 54 insertions(+)

Comments

Thomas Monjalon Oct. 15, 2018, 1:41 p.m. UTC | #1 
15/10/2018 13:27, Jeff Guo:
> This patch implements the ops for the PCI bus sigbus handler. It finds the
> PCI device that is being hot-unplugged and calls the relevant ops of the
> hot-unplug handler to handle the hot-unplug failure of the device.
> 
> Signed-off-by: Jeff Guo <jia.guo@intel.com>
> Acked-by: Shaopeng He <shaopeng.he@intel.com>
> Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
> ---
> v15->v14:
> fix compling issue.
> ---
> +static struct rte_pci_device *
> +pci_find_device_by_addr(const void *failure_addr)
> +{
> +	struct rte_pci_device *pdev = NULL;
> +	uint64_t check_point, start, end, len;
> +	int i;
> +
> +	check_point = (uint64_t)(uintptr_t)failure_addr;
> +
> +	FOREACH_DEVICE_ON_PCIBUS(pdev) {
> +		for (i = 0; i != RTE_DIM(pdev->mem_resource); i++) {
> +			start = (uint64_t)(uintptr_t)pdev->mem_resource[i].addr;
> +			len = pdev->mem_resource[i].len;
> +			end = (uint64_t)(uintptr_t)RTE_PTR_ADD(start, len);

When compiling for 32-bit, there is an error:
cast to pointer from integer of different size

start is not a pointer.
I think it must be replaced by a simple addition.
	end = start + len;
Thomas Monjalon Oct. 15, 2018, 2:16 p.m. UTC | #2 
15/10/2018 15:41, Thomas Monjalon:
> 15/10/2018 13:27, Jeff Guo:
> > This patch implements the ops for the PCI bus sigbus handler. It finds the
> > PCI device that is being hot-unplugged and calls the relevant ops of the
> > hot-unplug handler to handle the hot-unplug failure of the device.
> > 
> > Signed-off-by: Jeff Guo <jia.guo@intel.com>
> > Acked-by: Shaopeng He <shaopeng.he@intel.com>
> > Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
> > ---
> > v15->v14:
> > fix compling issue.
> > ---
> > +static struct rte_pci_device *
> > +pci_find_device_by_addr(const void *failure_addr)
> > +{
> > +	struct rte_pci_device *pdev = NULL;
> > +	uint64_t check_point, start, end, len;
> > +	int i;
> > +
> > +	check_point = (uint64_t)(uintptr_t)failure_addr;
> > +
> > +	FOREACH_DEVICE_ON_PCIBUS(pdev) {
> > +		for (i = 0; i != RTE_DIM(pdev->mem_resource); i++) {
> > +			start = (uint64_t)(uintptr_t)pdev->mem_resource[i].addr;
> > +			len = pdev->mem_resource[i].len;
> > +			end = (uint64_t)(uintptr_t)RTE_PTR_ADD(start, len);
> 
> When compiling for 32-bit, there is an error:
> cast to pointer from integer of different size
> 
> start is not a pointer.
> I think it must be replaced by a simple addition.
> 	end = start + len;

I will fix it on apply.
diff mbox series

Patch

diff --git a/drivers/bus/pci/pci_common.c b/drivers/bus/pci/pci_common.c
index be7cc1f..4325b0e 100644
--- a/drivers/bus/pci/pci_common.c
+++ b/drivers/bus/pci/pci_common.c
@@ -403,6 +403,36 @@  pci_find_device(const struct rte_device *start, rte_dev_cmp_t cmp,
 	return NULL;
 }
 
+/*
+ * find the device which encounter the failure, by iterate over all device on
+ * PCI bus to check if the memory failure address is located in the range
+ * of the BARs of the device.
+ */
+static struct rte_pci_device *
+pci_find_device_by_addr(const void *failure_addr)
+{
+	struct rte_pci_device *pdev = NULL;
+	uint64_t check_point, start, end, len;
+	int i;
+
+	check_point = (uint64_t)(uintptr_t)failure_addr;
+
+	FOREACH_DEVICE_ON_PCIBUS(pdev) {
+		for (i = 0; i != RTE_DIM(pdev->mem_resource); i++) {
+			start = (uint64_t)(uintptr_t)pdev->mem_resource[i].addr;
+			len = pdev->mem_resource[i].len;
+			end = (uint64_t)(uintptr_t)RTE_PTR_ADD(start, len);
+			if (check_point >= start && check_point < end) {
+				RTE_LOG(DEBUG, EAL, "Failure address %16.16"
+					PRIx64" belongs to device %s!\n",
+					check_point, pdev->device.name);
+				return pdev;
+			}
+		}
+	}
+	return NULL;
+}
+
 static int
 pci_hot_unplug_handler(struct rte_device *dev)
 {
@@ -431,6 +461,29 @@  pci_hot_unplug_handler(struct rte_device *dev)
 }
 
 static int
+pci_sigbus_handler(const void *failure_addr)
+{
+	struct rte_pci_device *pdev = NULL;
+	int ret = 0;
+
+	pdev = pci_find_device_by_addr(failure_addr);
+	if (!pdev) {
+		/* It is a generic sigbus error, no bus would handle it. */
+		ret = 1;
+	} else {
+		/* The sigbus error is caused of hot-unplug. */
+		ret = pci_hot_unplug_handler(&pdev->device);
+		if (ret) {
+			RTE_LOG(ERR, EAL,
+				"Failed to handle hot-unplug for device %s",
+				pdev->name);
+			ret = -1;
+		}
+	}
+	return ret;
+}
+
+static int
 pci_plug(struct rte_device *dev)
 {
 	return pci_probe_all_drivers(RTE_DEV_TO_PCI(dev));
@@ -462,6 +515,7 @@  struct rte_pci_bus rte_pci_bus = {
 		.get_iommu_class = rte_pci_get_iommu_class,
 		.dev_iterate = rte_pci_dev_iterate,
 		.hot_unplug_handler = pci_hot_unplug_handler,
+		.sigbus_handler = pci_sigbus_handler,
 	},
 	.device_list = TAILQ_HEAD_INITIALIZER(rte_pci_bus.device_list),
 	.driver_list = TAILQ_HEAD_INITIALIZER(rte_pci_bus.driver_list),