- reinitialize ipmi watchdog if BMC was reset

[packages/kernel.git] / kernel-small_fixes.patch

--- linux-2.6.32/drivers/infiniband/Kconfig~	2009-12-05 00:26:03.663774916 +0100
+++ linux-2.6.32/drivers/infiniband/Kconfig	2009-12-05 00:26:05.914179759 +0100
@@ -37,7 +37,6 @@
 config INFINIBAND_ADDR_TRANS
 	bool
 	depends on INET
-	depends on !(INFINIBAND = y && IPV6 = m)
 	default y
 
 source "drivers/infiniband/hw/mthca/Kconfig"
--- linux-2.6.33/scripts/mod/modpost.c~	2010-02-24 19:52:17.000000000 +0100
+++ linux-2.6.33/scripts/mod/modpost.c	2010-03-07 14:26:47.242168558 +0100
@@ -15,7 +15,8 @@
 #include <stdio.h>
 #include <ctype.h>
 #include "modpost.h"
-#include "../../include/generated/autoconf.h"
+// PLD architectures don't use CONFIG_SYMBOL_PREFIX
+//#include "../../include/generated/autoconf.h"
 #include "../../include/linux/license.h"
 
 /* Some toolchains use a `_' prefix for all user symbols. */

commit 87b09f1f25cd1e01d7c50bf423c7fe33027d7511
Author: stephen hemminger <shemminger@vyatta.com>
Date:   Fri Feb 12 06:58:00 2010 +0000

    sky2: dont enable PME legacy mode
    
    This bit is not changed by vendor driver, and should be left alone.
    The documentation implies this a debug bit.
      0 = WAKE# only asserted when VMAIN not available
      1 = WAKE# is depend on wake events and independent of VMAIN.
    
    Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
    Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git b/drivers/net/sky2.c a/drivers/net/sky2.c
index 2494842..edf37aa 100644
--- b/drivers/net/sky2.c
+++ a/drivers/net/sky2.c
@@ -733,6 +733,7 @@ static void sky2_wol_init(struct sky2_port *sky2)
 	unsigned port = sky2->port;
 	enum flow_control save_mode;
 	u16 ctrl;
+	u32 reg1;
 
 	/* Bring hardware out of reset */
 	sky2_write16(hw, B0_CTST, CS_RST_CLR);
@@ -786,6 +787,11 @@ static void sky2_wol_init(struct sky2_port *sky2)
 	/* Disable PiG firmware */
 	sky2_write16(hw, B0_CTST, Y2_HW_WOL_OFF);
 
+	/* Turn on legacy PCI-Express PME mode */
+	reg1 = sky2_pci_read32(hw, PCI_DEV_REG1);
+	reg1 |= PCI_Y2_PME_LEGACY;
+	sky2_pci_write32(hw, PCI_DEV_REG1, reg1);
+
 	/* block receiver */
 	sky2_write8(hw, SK_REG(port, RX_GMF_CTRL_T), GMF_RST_SET);
 }
On Sat, 2 Jul 2011, Andi Kleen wrote:

> > The problem is that blk_peek_request() calls scsi_prep_fn(), which 
> > does this:
> > 
> > 	struct scsi_device *sdev = q->queuedata;
> > 	int ret = BLKPREP_KILL;
> > 
> > 	if (req->cmd_type == REQ_TYPE_BLOCK_PC)
> > 		ret = scsi_setup_blk_pc_cmnd(sdev, req);
> > 	return scsi_prep_return(q, req, ret);
> > 
> > It doesn't check to see if sdev is NULL, nor does 
> > scsi_setup_blk_pc_cmnd().  That accounts for this error:
> 
> I actually added a NULL check in scsi_setup_blk_pc_cmnd early on,
> but that just caused RCU CPU stalls afterwards and then eventually
> a hung system.

The RCU problem is likely to be a separate issue.  It might even be a 
result of the use-after-free problem with the elevator.

At any rate, it's clear that the crash in the refcounting log you
posted occurred because scsi_setup_blk_pc_cmnd() called
scsi_prep_state_check(), which tried to dereference the NULL pointer.

Would you like to try this patch to see if it fixes the problem?  As I 
said before, I'm not certain it's the best thing to do, but it worked 
on my system.

Alan Stern




Index: usb-3.0/drivers/scsi/scsi_lib.c
===================================================================
--- usb-3.0.orig/drivers/scsi/scsi_lib.c
+++ usb-3.0/drivers/scsi/scsi_lib.c
@@ -1247,6 +1247,8 @@ int scsi_prep_fn(struct request_queue *q
 	struct scsi_device *sdev = q->queuedata;
 	int ret = BLKPREP_KILL;
 
+	if (!sdev)
+		return ret;
 	if (req->cmd_type == REQ_TYPE_BLOCK_PC)
 		ret = scsi_setup_blk_pc_cmnd(sdev, req);
 	return scsi_prep_return(q, req, ret);
Index: usb-3.0/drivers/scsi/scsi_sysfs.c
===================================================================
--- usb-3.0.orig/drivers/scsi/scsi_sysfs.c
+++ usb-3.0/drivers/scsi/scsi_sysfs.c
@@ -322,6 +322,8 @@ static void scsi_device_dev_release_user
 		kfree(evt);
 	}
 
+	/* Freeing the queue signals to block that we're done */
+	scsi_free_queue(sdev->request_queue);
 	blk_put_queue(sdev->request_queue);
 	/* NULL queue means the device can't be used */
 	sdev->request_queue = NULL;
@@ -936,8 +938,6 @@ void __scsi_remove_device(struct scsi_de
 	/* cause the request function to reject all I/O requests */
 	sdev->request_queue->queuedata = NULL;
 
-	/* Freeing the queue signals to block that we're done */
-	scsi_free_queue(sdev->request_queue);
 	put_device(dev);
 }
 


--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/
--- linux-3.0/scripts/kconfig/lxdialog/check-lxdialog.sh~	2011-07-22 04:17:23.000000000 +0200
+++ linux-3.0/scripts/kconfig/lxdialog/check-lxdialog.sh	2011-08-25 21:26:04.799150642 +0200
@@ -9,6 +9,12 @@
 			$cc -print-file-name=lib${lib}.${ext} | grep -q /
 			if [ $? -eq 0 ]; then
 				echo "-l${lib}"
+				for libt in tinfow tinfo ; do
+					$cc -print-file-name=lib${libt}.${ext} | grep -q /
+					if [ $? -eq 0 ]; then
+						echo "-l${libt}"
+					fi
+				done
 				exit
 			fi
 		done



commit 745718132c3c7cac98a622b610e239dcd5217f71
Author: Hannes Reinecke <hare@suse.de>
Date:   Wed Nov 9 08:39:24 2011 +0100

    [SCSI] Silencing 'killing requests for dead queue'
    
    When we tear down a device we try to flush all outstanding
    commands in scsi_free_queue(). However the check in
    scsi_request_fn() is imperfect as it only signals that
    we _might start_ aborting commands, not that we've actually
    aborted some.
    So move the printk inside the scsi_kill_request function,
    this will also give us a hint about which commands are aborted.
    
    Signed-off-by: Hannes Reinecke <hare@suse.de>
    Signed-off-by: James Bottomley <JBottomley@Parallels.com>

diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 06bc265..f85cfa6 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -1409,6 +1409,8 @@ static void scsi_kill_request(struct request *req, struct request_queue *q)
 
 	blk_start_request(req);
 
+	scmd_printk(KERN_INFO, cmd, "killing request\n");
+
 	sdev = cmd->device;
 	starget = scsi_target(sdev);
 	shost = sdev->host;
@@ -1490,7 +1492,6 @@ static void scsi_request_fn(struct request_queue *q)
 	struct request *req;
 
 	if (!sdev) {
-		printk("scsi: killing requests for dead queue\n");
 		while ((req = blk_peek_request(q)) != NULL)
 			scsi_kill_request(req, q);
 		return;
>From 4467601416e23740fc940c31b1fffacbcb69b4a0 Mon Sep 17 00:00:00 2001
From: Corey Minyard <cminyard@mvista.com>
Date: Mon, 21 Nov 2011 14:26:20 -0600
Subject: [PATCH] ipmi_watchdog: Restore settings when BMC reset

If the BMC gets reset, it will return 0x80 response errors.  In this case,
it is probably a good idea to restore the IPMI settings.
---
 drivers/char/ipmi/ipmi_watchdog.c |   41 ++++++++++++++++++++++++++++++++++--
 1 files changed, 38 insertions(+), 3 deletions(-)

diff --git a/drivers/char/ipmi/ipmi_watchdog.c b/drivers/char/ipmi/ipmi_watchdog.c
index c2917ffa..34767a6 100644
--- a/drivers/char/ipmi/ipmi_watchdog.c
+++ b/drivers/char/ipmi/ipmi_watchdog.c
@@ -139,6 +139,8 @@
 #define IPMI_WDOG_SET_TIMER		0x24
 #define IPMI_WDOG_GET_TIMER		0x25
 
+#define IPMI_WDOG_TIMER_NOT_INIT_RESP	0x80
+
 /* These are here until the real ones get into the watchdog.h interface. */
 #ifndef WDIOC_GETTIMEOUT
 #define	WDIOC_GETTIMEOUT        _IOW(WATCHDOG_IOCTL_BASE, 20, int)
@@ -596,6 +598,7 @@ static int ipmi_heartbeat(void)
 	struct kernel_ipmi_msg            msg;
 	int                               rv;
 	struct ipmi_system_interface_addr addr;
+	int				  timeout_retries = 0;
 
 	if (ipmi_ignore_heartbeat)
 		return 0;
@@ -616,6 +619,7 @@ static int ipmi_heartbeat(void)
 
 	mutex_lock(&heartbeat_lock);
 
+restart:
 	atomic_set(&heartbeat_tofree, 2);
 
 	/*
@@ -653,7 +657,33 @@ static int ipmi_heartbeat(void)
 	/* Wait for the heartbeat to be sent. */
 	wait_for_completion(&heartbeat_wait);
 
-	if (heartbeat_recv_msg.msg.data[0] != 0) {
+	if (heartbeat_recv_msg.msg.data[0] == IPMI_WDOG_TIMER_NOT_INIT_RESP)  {
+		timeout_retries++;
+		if (timeout_retries > 3) {
+			printk(KERN_ERR PFX ": Unable to restore the IPMI"
+			       " watchdog's settings, giving up.\n");
+			rv = -EIO;
+			goto out_unlock;
+		}
+
+		/*
+		 * The timer was not initialized, that means the BMC was
+		 * probably reset and lost the watchdog information.  Attempt
+		 * to restore the timer's info.  Note that we still hold
+		 * the heartbeat lock, to keep a heartbeat from happening
+		 * in this process, so must say no heartbeat to avoid a
+		 * deadlock on this mutex.
+		 */
+		rv = ipmi_set_timeout(IPMI_SET_TIMEOUT_NO_HB);
+		if (rv) {
+			printk(KERN_ERR PFX ": Unable to send the command to"
+			       " set the watchdog's settings, giving up.\n");
+			goto out_unlock;
+		}
+
+		/* We might need a new heartbeat, so do it now */
+		goto restart;
+	} else if (heartbeat_recv_msg.msg.data[0] != 0) {
 		/*
 		 * Got an error in the heartbeat response.  It was already
 		 * reported in ipmi_wdog_msg_handler, but we should return
@@ -662,6 +692,7 @@ static int ipmi_heartbeat(void)
 		rv = -EINVAL;
 	}
 
+out_unlock:
 	mutex_unlock(&heartbeat_lock);
 
 	return rv;
@@ -922,11 +953,15 @@ static struct miscdevice ipmi_wdog_miscdev = {
 static void ipmi_wdog_msg_handler(struct ipmi_recv_msg *msg,
 				  void                 *handler_data)
 {
-	if (msg->msg.data[0] != 0) {
+	if (msg->msg.cmd == IPMI_WDOG_RESET_TIMER &&
+			msg->msg.data[0] == IPMI_WDOG_TIMER_NOT_INIT_RESP)
+		printk(KERN_INFO PFX "response: The IPMI controller appears"
+		       " to have been reset, will attempt to reinitialize"
+		       " the watchdog timer\n");
+	else if (msg->msg.data[0] != 0)
 		printk(KERN_ERR PFX "response: Error %x on cmd %x\n",
 		       msg->msg.data[0],
 		       msg->msg.cmd);
-	}
 
 	ipmi_free_recv_msg(msg);
 }
-- 
1.7.4.1