diff mbox

[V4,3/9] aacraid: Added EEH support

Message ID 1454107550-24173-4-git-send-email-RaghavaAditya.Renukunta@pmcs.com (mailing list archive)
State Changes Requested, archived
Headers show

Commit Message

Raghava Aditya Renukunta Jan. 29, 2016, 10:45 p.m. UTC 
From: Raghava Aditya Renukunta <raghavaaditya.renukunta@pmcs.com>

Added support for PCI EEH(extended error handling).

Changes in V2:
Made local functions static
Removed call to  aac_fib_free_tag
Set adapter_shutdown flag when PCI error detected

Changes in V3:
None

Changes in V4:
Removed setting of adapter_shutdown flag when \
PCI error detected

Signed-off-by: Raghava Aditya Renukunta <raghavaaditya.renukunta@pmcs.com>
Reviewed-by: Tomas Henzl <thenzl@redhat.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
---
 drivers/scsi/aacraid/aacraid.h |   1 +
 drivers/scsi/aacraid/linit.c   | 137 +++++++++++++++++++++++++++++++++++++++++
 2 files changed, 138 insertions(+)

Comments

kernel test robot Jan. 30, 2016, 10:52 p.m. UTC | #1 
Hi Raghava,

[auto build test ERROR on scsi/for-next]
[also build test ERROR on v4.5-rc1 next-20160129]
[if your patch is applied to the wrong git tree, please drop us a note to help improving the system]

url:    https://github.com/0day-ci/linux/commits/Raghava-Aditya-Renukunta/aacraid-Patchset-for-aacraid-driver-version-41052/20160130-064140
base:   https://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi.git for-next
config: tile-allmodconfig (attached as .config)
reproduce:
        wget https://git.kernel.org/cgit/linux/kernel/git/wfg/lkp-tests.git/plain/sbin/make.cross -O ~/bin/make.cross
        chmod +x ~/bin/make.cross
        # save the attached .config to linux build tree
        make.cross ARCH=tile 

All errors (new ones prefixed by >>):

   drivers/scsi/aacraid/linit.c: In function 'aac_pci_error_detected':
>> drivers/scsi/aacraid/linit.c:1544:3: error: implicit declaration of function 'aac_release_resources'
   drivers/scsi/aacraid/linit.c: In function 'aac_pci_resume':
>> drivers/scsi/aacraid/linit.c:1614:2: error: implicit declaration of function 'aac_acquire_resources'
   cc1: some warnings being treated as errors

vim +/aac_release_resources +1544 drivers/scsi/aacraid/linit.c

  1538			return PCI_ERS_RESULT_CAN_RECOVER;
  1539		case pci_channel_io_frozen:
  1540			aac->handle_pci_error = 1;
  1541	
  1542			scsi_block_requests(aac->scsi_host_ptr);
  1543			aac_flush_ios(aac);
> 1544			aac_release_resources(aac);
  1545	
  1546			pci_disable_pcie_error_reporting(pdev);
  1547			aac_adapter_ioremap(aac, 0);
  1548	
  1549			return PCI_ERS_RESULT_NEED_RESET;
  1550		case pci_channel_io_perm_failure:
  1551			aac->handle_pci_error = 1;
  1552	
  1553			aac_flush_ios(aac);
  1554			return PCI_ERS_RESULT_DISCONNECT;
  1555		}
  1556	
  1557		return PCI_ERS_RESULT_NEED_RESET;
  1558	}
  1559	
  1560	static pci_ers_result_t aac_pci_mmio_enabled(struct pci_dev *pdev)
  1561	{
  1562		dev_err(&pdev->dev, "aacraid: PCI error - mmio enabled\n");
  1563		return PCI_ERS_RESULT_NEED_RESET;
  1564	}
  1565	
  1566	static pci_ers_result_t aac_pci_slot_reset(struct pci_dev *pdev)
  1567	{
  1568		dev_err(&pdev->dev, "aacraid: PCI error - slot reset\n");
  1569		pci_restore_state(pdev);
  1570		if (pci_enable_device(pdev)) {
  1571			dev_warn(&pdev->dev,
  1572				"aacraid: failed to enable slave\n");
  1573			goto fail_device;
  1574		}
  1575	
  1576		pci_set_master(pdev);
  1577	
  1578		if (pci_enable_device_mem(pdev)) {
  1579			dev_err(&pdev->dev, "pci_enable_device_mem failed\n");
  1580			goto fail_device;
  1581		}
  1582	
  1583		return PCI_ERS_RESULT_RECOVERED;
  1584	
  1585	fail_device:
  1586		dev_err(&pdev->dev, "aacraid: PCI error - slot reset failed\n");
  1587		return PCI_ERS_RESULT_DISCONNECT;
  1588	}
  1589	
  1590	
  1591	static void aac_pci_resume(struct pci_dev *pdev)
  1592	{
  1593		struct Scsi_Host *shost = pci_get_drvdata(pdev);
  1594		struct scsi_device *sdev = NULL;
  1595		struct aac_dev *aac = (struct aac_dev *)shost_priv(shost);
  1596	
  1597		pci_cleanup_aer_uncorrect_error_status(pdev);
  1598	
  1599		if (aac_adapter_ioremap(aac, aac->base_size)) {
  1600	
  1601			dev_err(&pdev->dev, "aacraid: ioremap failed\n");
  1602			/* remap failed, go back ... */
  1603			aac->comm_interface = AAC_COMM_PRODUCER;
  1604			if (aac_adapter_ioremap(aac, AAC_MIN_FOOTPRINT_SIZE)) {
  1605				dev_warn(&pdev->dev,
  1606					"aacraid: unable to map adapter.\n");
  1607	
  1608				return;
  1609			}
  1610		}
  1611	
  1612		msleep(10000);
  1613	
> 1614		aac_acquire_resources(aac);
  1615	
  1616		/*
  1617		 * reset this flag to unblock ioctl() as it was set

---
0-DAY kernel test infrastructure                Open Source Technology Center
https://lists.01.org/pipermail/kbuild-all                   Intel Corporation
diff mbox

Patch

diff --git a/drivers/scsi/aacraid/aacraid.h b/drivers/scsi/aacraid/aacraid.h
index fff1306..2916288 100644
--- a/drivers/scsi/aacraid/aacraid.h
+++ b/drivers/scsi/aacraid/aacraid.h
@@ -1235,6 +1235,7 @@  struct aac_dev
 	struct msix_entry	msixentry[AAC_MAX_MSIX];
 	struct aac_msix_ctx	aac_msix[AAC_MAX_MSIX]; /* context */
 	u8			adapter_shutdown;
+	u32			handle_pci_error;
 };
 
 #define aac_adapter_interrupt(dev) \
diff --git a/drivers/scsi/aacraid/linit.c b/drivers/scsi/aacraid/linit.c
index 129a515..62ac7be 100644
--- a/drivers/scsi/aacraid/linit.c
+++ b/drivers/scsi/aacraid/linit.c
@@ -38,6 +38,7 @@ 
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/pci.h>
+#include <linux/aer.h>
 #include <linux/pci-aspm.h>
 #include <linux/slab.h>
 #include <linux/mutex.h>
@@ -1298,6 +1299,9 @@  static int aac_probe_one(struct pci_dev *pdev, const struct pci_device_id *id)
 		goto out_deinit;
 	scsi_scan_host(shost);
 
+	pci_enable_pcie_error_reporting(pdev);
+	pci_save_state(pdev);
+
 	return 0;
 
  out_deinit:
@@ -1501,6 +1505,138 @@  static void aac_remove_one(struct pci_dev *pdev)
 	}
 }
 
+static void aac_flush_ios(struct aac_dev *aac)
+{
+	int i;
+	struct scsi_cmnd *cmd;
+
+	for (i = 0; i < aac->scsi_host_ptr->can_queue; i++) {
+		cmd = (struct scsi_cmnd *)aac->fibs[i].callback_data;
+		if (cmd && (cmd->SCp.phase == AAC_OWNER_FIRMWARE)) {
+			scsi_dma_unmap(cmd);
+
+			if (aac->handle_pci_error)
+				cmd->result = DID_NO_CONNECT << 16;
+			else
+				cmd->result = DID_RESET << 16;
+
+			cmd->scsi_done(cmd);
+		}
+	}
+}
+
+static pci_ers_result_t aac_pci_error_detected(struct pci_dev *pdev,
+					enum pci_channel_state error)
+{
+	struct Scsi_Host *shost = pci_get_drvdata(pdev);
+	struct aac_dev *aac = shost_priv(shost);
+
+	dev_err(&pdev->dev, "aacraid: PCI error detected %x\n", error);
+
+	switch (error) {
+	case pci_channel_io_normal:
+		return PCI_ERS_RESULT_CAN_RECOVER;
+	case pci_channel_io_frozen:
+		aac->handle_pci_error = 1;
+
+		scsi_block_requests(aac->scsi_host_ptr);
+		aac_flush_ios(aac);
+		aac_release_resources(aac);
+
+		pci_disable_pcie_error_reporting(pdev);
+		aac_adapter_ioremap(aac, 0);
+
+		return PCI_ERS_RESULT_NEED_RESET;
+	case pci_channel_io_perm_failure:
+		aac->handle_pci_error = 1;
+
+		aac_flush_ios(aac);
+		return PCI_ERS_RESULT_DISCONNECT;
+	}
+
+	return PCI_ERS_RESULT_NEED_RESET;
+}
+
+static pci_ers_result_t aac_pci_mmio_enabled(struct pci_dev *pdev)
+{
+	dev_err(&pdev->dev, "aacraid: PCI error - mmio enabled\n");
+	return PCI_ERS_RESULT_NEED_RESET;
+}
+
+static pci_ers_result_t aac_pci_slot_reset(struct pci_dev *pdev)
+{
+	dev_err(&pdev->dev, "aacraid: PCI error - slot reset\n");
+	pci_restore_state(pdev);
+	if (pci_enable_device(pdev)) {
+		dev_warn(&pdev->dev,
+			"aacraid: failed to enable slave\n");
+		goto fail_device;
+	}
+
+	pci_set_master(pdev);
+
+	if (pci_enable_device_mem(pdev)) {
+		dev_err(&pdev->dev, "pci_enable_device_mem failed\n");
+		goto fail_device;
+	}
+
+	return PCI_ERS_RESULT_RECOVERED;
+
+fail_device:
+	dev_err(&pdev->dev, "aacraid: PCI error - slot reset failed\n");
+	return PCI_ERS_RESULT_DISCONNECT;
+}
+
+
+static void aac_pci_resume(struct pci_dev *pdev)
+{
+	struct Scsi_Host *shost = pci_get_drvdata(pdev);
+	struct scsi_device *sdev = NULL;
+	struct aac_dev *aac = (struct aac_dev *)shost_priv(shost);
+
+	pci_cleanup_aer_uncorrect_error_status(pdev);
+
+	if (aac_adapter_ioremap(aac, aac->base_size)) {
+
+		dev_err(&pdev->dev, "aacraid: ioremap failed\n");
+		/* remap failed, go back ... */
+		aac->comm_interface = AAC_COMM_PRODUCER;
+		if (aac_adapter_ioremap(aac, AAC_MIN_FOOTPRINT_SIZE)) {
+			dev_warn(&pdev->dev,
+				"aacraid: unable to map adapter.\n");
+
+			return;
+		}
+	}
+
+	msleep(10000);
+
+	aac_acquire_resources(aac);
+
+	/*
+	 * reset this flag to unblock ioctl() as it was set
+	 * at aac_send_shutdown() to block ioctls from upperlayer
+	 */
+	aac->adapter_shutdown = 0;
+	aac->handle_pci_error = 0;
+
+	shost_for_each_device(sdev, shost)
+		if (sdev->sdev_state == SDEV_OFFLINE)
+			sdev->sdev_state = SDEV_RUNNING;
+	scsi_unblock_requests(aac->scsi_host_ptr);
+	scsi_scan_host(aac->scsi_host_ptr);
+	pci_save_state(pdev);
+
+	dev_err(&pdev->dev, "aacraid: PCI error - resume\n");
+}
+
+static struct pci_error_handlers aac_pci_err_handler = {
+	.error_detected		= aac_pci_error_detected,
+	.mmio_enabled		= aac_pci_mmio_enabled,
+	.slot_reset		= aac_pci_slot_reset,
+	.resume			= aac_pci_resume,
+};
+
 static struct pci_driver aac_pci_driver = {
 	.name		= AAC_DRIVERNAME,
 	.id_table	= aac_pci_tbl,
@@ -1511,6 +1647,7 @@  static struct pci_driver aac_pci_driver = {
 	.resume		= aac_resume,
 #endif
 	.shutdown	= aac_shutdown,
+	.err_handler    = &aac_pci_err_handler,
 };
 
 static int __init aac_init(void)