From: Konrad Rzeszutek <konradr@redhat.com>
Subject: [RHEL5] #212572 - IPMI, rolled in one.
Date: Tue, 5 Dec 2006 13:51:36 -0500
Bugzilla: 212572
Message-Id: <20061205185136.GD2828@dhcp83-171.boston.redhat.com>
Changelog: IPMI - allow multiple Baseboard Management Centers


Hey Don,

Here is the patch rolled in one. 

RHBZ#:
------
https://bugzilla.redhat.com/bugzilla/show_bug.cgi?id=212572

Description:
------------
IPMI and RHEL5 on the 4-node (and 2-node) hangs the machine. The problem
is that the IPMI code does not expect multiple Baseboard Management Center's
on the machine (each node has its own). The fixes in upstream IPMI driver (39.1)
address this problem. There are four patches that have to be applied to 
fix this hang.

This patch is for RHEL5. 

RHEL Version Found:
------------------
RHEL5 Beta2 

Upstream Status:
----------------
It is in 39.1 driver on SourceForge


Proposed Patches:
---------------


diff -uNr linux-2.6.18.i686.orig/drivers/char/ipmi/ipmi_msghandler.c linux-2.6.18.i686/drivers/char/ipmi/ipmi_msghandler.c
--- linux-2.6.18.i686.orig/drivers/char/ipmi/ipmi_msghandler.c	2006-12-04 16:35:09.000000000 -0500
+++ linux-2.6.18.i686/drivers/char/ipmi/ipmi_msghandler.c	2006-12-05 13:46:37.000000000 -0500
@@ -201,6 +201,7 @@
 
 	struct bmc_device *bmc;
 	char *my_dev_name;
+	char *sysfs_name;
 
 	/* This is the lower-layer's sender routine. */
 	struct ipmi_smi_handlers *handlers;
@@ -353,7 +354,7 @@
 };
 static DEFINE_MUTEX(ipmidriver_mutex);
 
-#define MAX_IPMI_INTERFACES 4
+#define MAX_IPMI_INTERFACES 8
 static ipmi_smi_t ipmi_interfaces[MAX_IPMI_INTERFACES];
 
 /* Directly protects the ipmi_interfaces data structure. */
@@ -1774,13 +1775,12 @@
 	struct bmc_device *bmc = dev_get_drvdata(dev);
 
 	return (bmc->id.product_id == id->product_id
-		&& bmc->id.product_id == id->product_id
 		&& bmc->id.device_id == id->device_id);
 }
 
 static struct bmc_device *ipmi_find_bmc_prod_dev_id(
 	struct device_driver *drv,
-	unsigned char product_id, unsigned char device_id)
+	unsigned int product_id, unsigned char device_id)
 {
 	struct prod_dev_id id = {
 		.product_id = product_id,
@@ -1895,12 +1895,10 @@
 			(long long) bmc->guid[8]);
 }
 
-static void
-cleanup_bmc_device(struct kref *ref)
+static void remove_files(struct bmc_device *bmc)
 {
-	struct bmc_device *bmc;
-
-	bmc = container_of(ref, struct bmc_device, refcount);
+	if (!bmc->dev)
+		return;
 
 	device_remove_file(&bmc->dev->dev,
 			   &bmc->device_id_attr);
@@ -1918,13 +1916,25 @@
 			   &bmc->manufacturer_id_attr);
 	device_remove_file(&bmc->dev->dev,
 			   &bmc->product_id_attr);
+
 	if (bmc->id.aux_firmware_revision_set)
 		device_remove_file(&bmc->dev->dev,
 				   &bmc->aux_firmware_rev_attr);
 	if (bmc->guid_set)
 		device_remove_file(&bmc->dev->dev,
 				   &bmc->guid_attr);
-	platform_device_unregister(bmc->dev);
+}
+
+static void
+cleanup_bmc_device(struct kref *ref)
+{
+	struct bmc_device *bmc;
+
+	bmc = container_of(ref, struct bmc_device, refcount);
+
+	remove_files(bmc);
+	if (bmc->dev)
+		platform_device_unregister(bmc->dev);
 	kfree(bmc);
 }
 
@@ -1932,7 +1942,11 @@
 {
 	struct bmc_device *bmc = intf->bmc;
 
-	sysfs_remove_link(&intf->si_dev->kobj, "bmc");
+	if (intf->sysfs_name) {
+		sysfs_remove_link(&intf->si_dev->kobj, intf->sysfs_name);
+		kfree(intf->sysfs_name);
+		intf->sysfs_name = NULL;
+	}
 	if (intf->my_dev_name) {
 		sysfs_remove_link(&bmc->dev->dev.kobj, intf->my_dev_name);
 		kfree(intf->my_dev_name);
@@ -1941,10 +1955,135 @@
 
 	mutex_lock(&ipmidriver_mutex);
 	kref_put(&bmc->refcount, cleanup_bmc_device);
+	intf->bmc = NULL;
 	mutex_unlock(&ipmidriver_mutex);
 }
 
-static int ipmi_bmc_register(ipmi_smi_t intf)
+static int create_files(struct bmc_device *bmc)
+{
+	int err;
+
+	bmc->device_id_attr.attr.name = "device_id";
+	bmc->device_id_attr.attr.owner = THIS_MODULE;
+	bmc->device_id_attr.attr.mode = S_IRUGO;
+	bmc->device_id_attr.show = device_id_show;
+
+	bmc->provides_dev_sdrs_attr.attr.name = "provides_device_sdrs";
+	bmc->provides_dev_sdrs_attr.attr.owner = THIS_MODULE;
+	bmc->provides_dev_sdrs_attr.attr.mode = S_IRUGO;
+	bmc->provides_dev_sdrs_attr.show = provides_dev_sdrs_show;
+
+	bmc->revision_attr.attr.name = "revision";
+	bmc->revision_attr.attr.owner = THIS_MODULE;
+	bmc->revision_attr.attr.mode = S_IRUGO;
+	bmc->revision_attr.show = revision_show;
+
+	bmc->firmware_rev_attr.attr.name = "firmware_revision";
+	bmc->firmware_rev_attr.attr.owner = THIS_MODULE;
+	bmc->firmware_rev_attr.attr.mode = S_IRUGO;
+	bmc->firmware_rev_attr.show = firmware_rev_show;
+
+	bmc->version_attr.attr.name = "ipmi_version";
+	bmc->version_attr.attr.owner = THIS_MODULE;
+	bmc->version_attr.attr.mode = S_IRUGO;
+	bmc->version_attr.show = ipmi_version_show;
+
+	bmc->add_dev_support_attr.attr.name = "additional_device_support";
+	bmc->add_dev_support_attr.attr.owner = THIS_MODULE;
+	bmc->add_dev_support_attr.attr.mode = S_IRUGO;
+	bmc->add_dev_support_attr.show = add_dev_support_show;
+
+	bmc->manufacturer_id_attr.attr.name = "manufacturer_id";
+	bmc->manufacturer_id_attr.attr.owner = THIS_MODULE;
+	bmc->manufacturer_id_attr.attr.mode = S_IRUGO;
+	bmc->manufacturer_id_attr.show = manufacturer_id_show;
+
+	bmc->product_id_attr.attr.name = "product_id";
+	bmc->product_id_attr.attr.owner = THIS_MODULE;
+	bmc->product_id_attr.attr.mode = S_IRUGO;
+	bmc->product_id_attr.show = product_id_show;
+
+	bmc->guid_attr.attr.name = "guid";
+	bmc->guid_attr.attr.owner = THIS_MODULE;
+	bmc->guid_attr.attr.mode = S_IRUGO;
+	bmc->guid_attr.show = guid_show;
+
+	bmc->aux_firmware_rev_attr.attr.name = "aux_firmware_revision";
+	bmc->aux_firmware_rev_attr.attr.owner = THIS_MODULE;
+	bmc->aux_firmware_rev_attr.attr.mode = S_IRUGO;
+	bmc->aux_firmware_rev_attr.show = aux_firmware_rev_show;
+
+	err = device_create_file(&bmc->dev->dev,
+			   &bmc->device_id_attr);
+	if (err) goto out;
+	err = device_create_file(&bmc->dev->dev,
+			   &bmc->provides_dev_sdrs_attr);
+	if (err) goto out_devid;
+	err = device_create_file(&bmc->dev->dev,
+			   &bmc->revision_attr);
+	if (err) goto out_sdrs;
+	err = device_create_file(&bmc->dev->dev,
+			   &bmc->firmware_rev_attr);
+	if (err) goto out_rev;
+	err = device_create_file(&bmc->dev->dev,
+			   &bmc->version_attr);
+	if (err) goto out_firm;
+	err = device_create_file(&bmc->dev->dev,
+			   &bmc->add_dev_support_attr);
+	if (err) goto out_version;
+	err = device_create_file(&bmc->dev->dev,
+			   &bmc->manufacturer_id_attr);
+	if (err) goto out_add_dev;
+	err = device_create_file(&bmc->dev->dev,
+			   &bmc->product_id_attr);
+	if (err) goto out_manu;
+	if (bmc->id.aux_firmware_revision_set) {
+		err = device_create_file(&bmc->dev->dev,
+				   &bmc->aux_firmware_rev_attr);
+		if (err) goto out_prod_id;
+	}
+	if (bmc->guid_set) {
+		err = device_create_file(&bmc->dev->dev,
+				   &bmc->guid_attr);
+		if (err) goto out_aux_firm;
+	}
+
+	return 0;
+
+out_aux_firm:
+	if (bmc->id.aux_firmware_revision_set)
+		device_remove_file(&bmc->dev->dev,
+				   &bmc->aux_firmware_rev_attr);
+out_prod_id:
+	device_remove_file(&bmc->dev->dev,
+			   &bmc->product_id_attr);
+out_manu:
+	device_remove_file(&bmc->dev->dev,
+			   &bmc->manufacturer_id_attr);
+out_add_dev:
+	device_remove_file(&bmc->dev->dev,
+			   &bmc->add_dev_support_attr);
+out_version:
+	device_remove_file(&bmc->dev->dev,
+			   &bmc->version_attr);
+out_firm:
+	device_remove_file(&bmc->dev->dev,
+			   &bmc->firmware_rev_attr);
+out_rev:
+	device_remove_file(&bmc->dev->dev,
+			   &bmc->revision_attr);
+out_sdrs:
+	device_remove_file(&bmc->dev->dev,
+			   &bmc->provides_dev_sdrs_attr);
+out_devid:
+	device_remove_file(&bmc->dev->dev,
+			   &bmc->device_id_attr);
+out:
+	return err;
+}
+
+static int ipmi_bmc_register(ipmi_smi_t intf, int ifnum,
+			     const char *sysfs_name)
 {
 	int               rv;
 	struct bmc_device *bmc = intf->bmc;
@@ -1984,9 +2123,39 @@
 		       bmc->id.product_id,
 		       bmc->id.device_id);
 	} else {
-		bmc->dev = platform_device_alloc("ipmi_bmc",
-						 bmc->id.device_id);
+		char name[14];
+		unsigned char orig_dev_id = bmc->id.device_id;
+		int warn_printed = 0;
+
+		snprintf(name, sizeof(name),
+			 "ipmi_bmc.%4.4x", bmc->id.product_id);
+
+		while (ipmi_find_bmc_prod_dev_id(&ipmidriver,
+						 bmc->id.product_id,
+						 bmc->id.device_id))
+		{
+			if (!warn_printed) {
+				printk(KERN_WARNING PFX
+				       "This machine has two different BMCs"
+				       " with the same product id and device"
+				       " id.  This is an error in the"
+				       " firmware, but incrementing the"
+				       " device id to work around the problem."
+				       " Prod ID = 0x%x, Dev ID = 0x%x\n",
+				       bmc->id.product_id, bmc->id.device_id);
+				warn_printed = 1;
+			}
+			bmc->id.device_id++; /* Wraps at 255 */
+			if (bmc->id.device_id == orig_dev_id) {
+				printk(KERN_ERR PFX
+				       "Out of device ids!\n");
+				break;
+			}
+		}
+
+		bmc->dev = platform_device_alloc(name, bmc->id.device_id);
 		if (!bmc->dev) {
+			mutex_unlock(&ipmidriver_mutex);
 			printk(KERN_ERR
 			       "ipmi_msghandler:"
 			       " Unable to allocate platform device\n");
@@ -1999,6 +2168,8 @@
 		rv = platform_device_register(bmc->dev);
 		mutex_unlock(&ipmidriver_mutex);
 		if (rv) {
+			platform_device_put(bmc->dev);
+			bmc->dev = NULL;
 			printk(KERN_ERR
 			       "ipmi_msghandler:"
 			       " Unable to register bmc device: %d\n",
@@ -2008,80 +2179,14 @@
 			return rv;
 		}
 
-		bmc->device_id_attr.attr.name = "device_id";
-		bmc->device_id_attr.attr.owner = THIS_MODULE;
-		bmc->device_id_attr.attr.mode = S_IRUGO;
-		bmc->device_id_attr.show = device_id_show;
-
-		bmc->provides_dev_sdrs_attr.attr.name = "provides_device_sdrs";
-		bmc->provides_dev_sdrs_attr.attr.owner = THIS_MODULE;
-		bmc->provides_dev_sdrs_attr.attr.mode = S_IRUGO;
-		bmc->provides_dev_sdrs_attr.show = provides_dev_sdrs_show;
-
-
-		bmc->revision_attr.attr.name = "revision";
-		bmc->revision_attr.attr.owner = THIS_MODULE;
-		bmc->revision_attr.attr.mode = S_IRUGO;
-		bmc->revision_attr.show = revision_show;
-
-		bmc->firmware_rev_attr.attr.name = "firmware_revision";
-		bmc->firmware_rev_attr.attr.owner = THIS_MODULE;
-		bmc->firmware_rev_attr.attr.mode = S_IRUGO;
-		bmc->firmware_rev_attr.show = firmware_rev_show;
-
-		bmc->version_attr.attr.name = "ipmi_version";
-		bmc->version_attr.attr.owner = THIS_MODULE;
-		bmc->version_attr.attr.mode = S_IRUGO;
-		bmc->version_attr.show = ipmi_version_show;
-
-		bmc->add_dev_support_attr.attr.name
-			= "additional_device_support";
-		bmc->add_dev_support_attr.attr.owner = THIS_MODULE;
-		bmc->add_dev_support_attr.attr.mode = S_IRUGO;
-		bmc->add_dev_support_attr.show = add_dev_support_show;
-
-		bmc->manufacturer_id_attr.attr.name = "manufacturer_id";
-		bmc->manufacturer_id_attr.attr.owner = THIS_MODULE;
-		bmc->manufacturer_id_attr.attr.mode = S_IRUGO;
-		bmc->manufacturer_id_attr.show = manufacturer_id_show;
-
-		bmc->product_id_attr.attr.name = "product_id";
-		bmc->product_id_attr.attr.owner = THIS_MODULE;
-		bmc->product_id_attr.attr.mode = S_IRUGO;
-		bmc->product_id_attr.show = product_id_show;
-
-		bmc->guid_attr.attr.name = "guid";
-		bmc->guid_attr.attr.owner = THIS_MODULE;
-		bmc->guid_attr.attr.mode = S_IRUGO;
-		bmc->guid_attr.show = guid_show;
-
-		bmc->aux_firmware_rev_attr.attr.name = "aux_firmware_revision";
-		bmc->aux_firmware_rev_attr.attr.owner = THIS_MODULE;
-		bmc->aux_firmware_rev_attr.attr.mode = S_IRUGO;
-		bmc->aux_firmware_rev_attr.show = aux_firmware_rev_show;
-
-		device_create_file(&bmc->dev->dev,
-				   &bmc->device_id_attr);
-		device_create_file(&bmc->dev->dev,
-				   &bmc->provides_dev_sdrs_attr);
-		device_create_file(&bmc->dev->dev,
-				   &bmc->revision_attr);
-		device_create_file(&bmc->dev->dev,
-				   &bmc->firmware_rev_attr);
-		device_create_file(&bmc->dev->dev,
-				   &bmc->version_attr);
-		device_create_file(&bmc->dev->dev,
-				   &bmc->add_dev_support_attr);
-		device_create_file(&bmc->dev->dev,
-				   &bmc->manufacturer_id_attr);
-		device_create_file(&bmc->dev->dev,
-				   &bmc->product_id_attr);
-		if (bmc->id.aux_firmware_revision_set)
-			device_create_file(&bmc->dev->dev,
-					   &bmc->aux_firmware_rev_attr);
-		if (bmc->guid_set)
-			device_create_file(&bmc->dev->dev,
-					   &bmc->guid_attr);
+		rv = create_files(bmc);
+		if (rv) {
+			mutex_lock(&ipmidriver_mutex);
+			platform_device_unregister(bmc->dev);
+			mutex_unlock(&ipmidriver_mutex);
+
+			return rv;
+		}
 
 		printk(KERN_INFO
 		       "ipmi: Found new BMC (man_id: 0x%6.6x, "
@@ -2095,29 +2200,44 @@
 	 * create symlink from system interface device to bmc device
 	 * and back.
 	 */
+	intf->sysfs_name = kstrdup(sysfs_name, GFP_KERNEL);
+	if (!intf->sysfs_name) {
+		rv = -ENOMEM;
+		printk(KERN_ERR
+		       "ipmi_msghandler: allocate link to BMC: %d\n",
+		       rv);
+		goto out_err;
+	}
+
 	rv = sysfs_create_link(&intf->si_dev->kobj,
-			       &bmc->dev->dev.kobj, "bmc");
+			       &bmc->dev->dev.kobj, intf->sysfs_name);
 	if (rv) {
+		kfree(intf->sysfs_name);
+		intf->sysfs_name = NULL;
 		printk(KERN_ERR
 		       "ipmi_msghandler: Unable to create bmc symlink: %d\n",
 		       rv);
 		goto out_err;
 	}
 
-	size = snprintf(dummy, 0, "ipmi%d", intf->intf_num);
+	size = snprintf(dummy, 0, "ipmi%d", ifnum);
 	intf->my_dev_name = kmalloc(size+1, GFP_KERNEL);
 	if (!intf->my_dev_name) {
+		kfree(intf->sysfs_name);
+		intf->sysfs_name = NULL;
 		rv = -ENOMEM;
 		printk(KERN_ERR
 		       "ipmi_msghandler: allocate link from BMC: %d\n",
 		       rv);
 		goto out_err;
 	}
-	snprintf(intf->my_dev_name, size+1, "ipmi%d", intf->intf_num);
+	snprintf(intf->my_dev_name, size+1, "ipmi%d", ifnum);
 
 	rv = sysfs_create_link(&bmc->dev->dev.kobj, &intf->si_dev->kobj,
 			       intf->my_dev_name);
 	if (rv) {
+		kfree(intf->sysfs_name);
+		intf->sysfs_name = NULL;
 		kfree(intf->my_dev_name);
 		intf->my_dev_name = NULL;
 		printk(KERN_ERR
@@ -2302,6 +2422,7 @@
 		      void		       *send_info,
 		      struct ipmi_device_id    *device_id,
 		      struct device            *si_dev,
+		      const char               *sysfs_name,
 		      unsigned char            slave_addr)
 {
 	int              i, j;
@@ -2414,7 +2535,7 @@
 	if (rv == 0)
 		rv = add_proc_entries(intf, i);
 
-	rv = ipmi_bmc_register(intf);
+	rv = ipmi_bmc_register(intf, i, sysfs_name);
 
  out:
 	if (rv) {
diff -uNr linux-2.6.18.i686.orig/drivers/char/ipmi/ipmi_si_intf.c linux-2.6.18.i686/drivers/char/ipmi/ipmi_si_intf.c
--- linux-2.6.18.i686.orig/drivers/char/ipmi/ipmi_si_intf.c	2006-12-04 16:35:09.000000000 -0500
+++ linux-2.6.18.i686/drivers/char/ipmi/ipmi_si_intf.c	2006-12-05 13:46:37.000000000 -0500
@@ -2340,6 +2340,7 @@
 			       new_smi,
 			       &new_smi->device_id,
 			       new_smi->dev,
+			       "bmc",
 			       new_smi->slave_addr);
 	if (rv) {
 		printk(KERN_ERR
diff -uNr linux-2.6.18.i686.orig/include/linux/ipmi_smi.h linux-2.6.18.i686/include/linux/ipmi_smi.h
--- linux-2.6.18.i686.orig/include/linux/ipmi_smi.h	2006-12-04 16:34:44.000000000 -0500
+++ linux-2.6.18.i686/include/linux/ipmi_smi.h	2006-12-05 13:46:37.000000000 -0500
@@ -173,6 +173,7 @@
 		      void                     *send_info,
 		      struct ipmi_device_id    *device_id,
 		      struct device            *dev,
+		      const char               *sysfs_name,
 		      unsigned char            slave_addr);
 
 /*

-- 
Konrad Rzeszutek 1-(978)-392-3903 or 1-(617)-693-1718
IBM on-site partner.