[PATCH] ipmi: add power cycle capability

This patch to adds "power cycle" functionality to the IPMI power off module
ipmi_poweroff.  It also contains changes to support procfs control of the
feature.

The power cycle action is considered an optional chassis control in the IPMI
specification.  However, it is definitely useful when the hardware supports
it.  A power cycle is usually required in order to reset a firmware in a bad
state.  This action is critical to allow remote management of servers.

The implementation adds power cycle as optional to the ipmi_poweroff module.
It can be modified dynamically through the proc entry mentioned above.  During
a power down and enabled, the power cycle command is sent to the BMC firmware.
 If it fails either due to non-support or some error, it will retry to send
the command as power off.

Signed-off-by: Christopher A. Poblete <Chris_Poblete@dell.com>
Signed-off-by: Corey Minyard <minyard@acm.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

4 files changed, 155 insertions, 11 deletions

diff --git a/Documentation/IPMI.txt b/Documentation/IPMI.txt
index 2f99fe6299ab..84d3d4d10c17 100644
--- a/Documentation/IPMI.txt
+++ b/Documentation/IPMI.txt
@@ -594,3 +594,23 @@ an event generator, the event receiver from the local management
 controller will be queried and the events sent to the SEL on that
 device.  Otherwise, the events go nowhere since there is nowhere to
 send them.
+
+
+Poweroff
+--------
+
+If the poweroff capability is selected, the IPMI driver will install
+a shutdown function into the standard poweroff function pointer.  This
+is in the ipmi_poweroff module.  When the system requests a powerdown,
+it will send the proper IPMI commands to do this.  This is supported on
+several platforms.
+
+There is a module parameter named "poweroff_control" that may either be zero
+(do a power down) or 2 (do a power cycle, power the system off, then power
+it on in a few seconds).  Setting ipmi_poweroff.poweroff_control=x will do
+the same thing on the kernel command line.  The parameter is also available
+via the proc filesystem in /proc/ipmi/poweroff_control.  Note that if the
+system does not support power cycling, it will always to the power off.
+
+Note that if you have ACPI enabled, the system will prefer using ACPI to
+power off.
diff --git a/drivers/char/ipmi/ipmi_msghandler.c b/drivers/char/ipmi/ipmi_msghandler.c
index ed75e96d0035..1813d0d198f1 100644
--- a/drivers/char/ipmi/ipmi_msghandler.c
+++ b/drivers/char/ipmi/ipmi_msghandler.c
@@ -54,7 +54,9 @@ static int ipmi_init_msghandler(void);
 
 static int initialized = 0;
 
-static struct proc_dir_entry *proc_ipmi_root = NULL;
+#ifdef CONFIG_PROC_FS
+struct proc_dir_entry *proc_ipmi_root = NULL;
+#endif /* CONFIG_PROC_FS */
 
 #define MAX_EVENTS_IN_QUEUE	25
 
@@ -124,11 +126,13 @@ struct ipmi_channel
 	unsigned char protocol;
 };
 
+#ifdef CONFIG_PROC_FS
 struct ipmi_proc_entry
 {
 	char                   *name;
 	struct ipmi_proc_entry *next;
 };
+#endif
 
 #define IPMI_IPMB_NUM_SEQ	64
 #define IPMI_MAX_CHANNELS       8
@@ -156,10 +160,13 @@ struct ipmi_smi
 	struct ipmi_smi_handlers *handlers;
 	void                     *send_info;
 
+#ifdef CONFIG_PROC_FS
 	/* A list of proc entries for this interface.  This does not
 	   need a lock, only one thread creates it and only one thread
 	   destroys it. */
+	spinlock_t             proc_entry_lock;
 	struct ipmi_proc_entry *proc_entries;
+#endif
 
 	/* A table of sequence numbers for this interface.  We use the
            sequence numbers for IPMB messages that go out of the
@@ -1470,8 +1477,9 @@ int ipmi_smi_add_proc_entry(ipmi_smi_t smi, char *name,
 			    read_proc_t *read_proc, write_proc_t *write_proc,
 			    void *data, struct module *owner)
 {
-	struct proc_dir_entry  *file;
 	int                    rv = 0;
+#ifdef CONFIG_PROC_FS
+	struct proc_dir_entry  *file;
 	struct ipmi_proc_entry *entry;
 
 	/* Create a list element. */
@@ -1497,10 +1505,13 @@ int ipmi_smi_add_proc_entry(ipmi_smi_t smi, char *name,
 		file->write_proc = write_proc;
 		file->owner = owner;
 
+		spin_lock(&smi->proc_entry_lock);
 		/* Stick it on the list. */
 		entry->next = smi->proc_entries;
 		smi->proc_entries = entry;
+		spin_unlock(&smi->proc_entry_lock);
 	}
+#endif /* CONFIG_PROC_FS */
 
 	return rv;
 }
@@ -1509,6 +1520,7 @@ static int add_proc_entries(ipmi_smi_t smi, int num)
 {
 	int rv = 0;
 
+#ifdef CONFIG_PROC_FS
 	sprintf(smi->proc_dir_name, "%d", num);
 	smi->proc_dir = proc_mkdir(smi->proc_dir_name, proc_ipmi_root);
 	if (!smi->proc_dir)
@@ -1531,14 +1543,17 @@ static int add_proc_entries(ipmi_smi_t smi, int num)
 		rv = ipmi_smi_add_proc_entry(smi, "version",
 					     version_file_read_proc, NULL,
 					     smi, THIS_MODULE);
+#endif /* CONFIG_PROC_FS */
 
 	return rv;
 }
 
 static void remove_proc_entries(ipmi_smi_t smi)
 {
+#ifdef CONFIG_PROC_FS
 	struct ipmi_proc_entry *entry;
 
+	spin_lock(&smi->proc_entry_lock);
 	while (smi->proc_entries) {
 		entry = smi->proc_entries;
 		smi->proc_entries = entry->next;
@@ -1547,7 +1562,9 @@ static void remove_proc_entries(ipmi_smi_t smi)
 		kfree(entry->name);
 		kfree(entry);
 	}
+	spin_unlock(&smi->proc_entry_lock);
 	remove_proc_entry(smi->proc_dir_name, proc_ipmi_root);
+#endif /* CONFIG_PROC_FS */
 }
 
 static int
@@ -1694,6 +1711,9 @@ int ipmi_register_smi(struct ipmi_smi_handlers *handlers,
 				new_intf->seq_table[j].seqid = 0;
 			}
 			new_intf->curr_seq = 0;
+#ifdef CONFIG_PROC_FS
+			spin_lock_init(&(new_intf->proc_entry_lock));
+#endif
 			spin_lock_init(&(new_intf->waiting_msgs_lock));
 			INIT_LIST_HEAD(&(new_intf->waiting_msgs));
 			spin_lock_init(&(new_intf->events_lock));
@@ -3085,6 +3105,7 @@ static int ipmi_init_msghandler(void)
 		ipmi_interfaces[i] = NULL;
 	}
 
+#ifdef CONFIG_PROC_FS
 	proc_ipmi_root = proc_mkdir("ipmi", NULL);
 	if (!proc_ipmi_root) {
 	    printk(KERN_ERR PFX "Unable to create IPMI proc dir");
@@ -3092,6 +3113,7 @@ static int ipmi_init_msghandler(void)
 	}
 
 	proc_ipmi_root->owner = THIS_MODULE;
+#endif /* CONFIG_PROC_FS */
 
 	init_timer(&ipmi_timer);
 	ipmi_timer.data = 0;
@@ -3129,7 +3151,9 @@ static __exit void cleanup_ipmi(void)
 	atomic_inc(&stop_operation);
 	del_timer_sync(&ipmi_timer);
 
+#ifdef CONFIG_PROC_FS
 	remove_proc_entry(proc_ipmi_root->name, &proc_root);
+#endif /* CONFIG_PROC_FS */
 
 	initialized = 0;
 
@@ -3170,4 +3194,5 @@ EXPORT_SYMBOL(ipmi_get_my_address);
 EXPORT_SYMBOL(ipmi_set_my_LUN);
 EXPORT_SYMBOL(ipmi_get_my_LUN);
 EXPORT_SYMBOL(ipmi_smi_add_proc_entry);
+EXPORT_SYMBOL(proc_ipmi_root);
 EXPORT_SYMBOL(ipmi_user_set_run_to_completion);
diff --git a/drivers/char/ipmi/ipmi_poweroff.c b/drivers/char/ipmi/ipmi_poweroff.c
index cb5cdc6f14bf..61329b55c4a9 100644
--- a/drivers/char/ipmi/ipmi_poweroff.c
+++ b/drivers/char/ipmi/ipmi_poweroff.c
@@ -34,6 +34,8 @@
 #include <asm/semaphore.h>
 #include <linux/kdev_t.h>
 #include <linux/module.h>
+#include <linux/moduleparam.h>
+#include <linux/proc_fs.h>
 #include <linux/string.h>
 #include <linux/ipmi.h>
 #include <linux/ipmi_smi.h>
@@ -44,6 +46,18 @@
 /* Where to we insert our poweroff function? */
 extern void (*pm_power_off)(void);
 
+/* Definitions for controlling power off (if the system supports it).  It
+ * conveniently matches the IPMI chassis control values. */
+#define IPMI_CHASSIS_POWER_DOWN		0	/* power down, the default. */
+#define IPMI_CHASSIS_POWER_CYCLE	0x02	/* power cycle */
+
+/* the IPMI data command */
+static int poweroff_control = IPMI_CHASSIS_POWER_DOWN;
+
+/* parameter definition to allow user to flag power cycle */
+module_param(poweroff_control, int, IPMI_CHASSIS_POWER_DOWN);
+MODULE_PARM_DESC(poweroff_control, " Set to 2 to enable power cycle instead of power down. Power cycle is contingent on hardware support, otherwise it defaults back to power down.");
+
 /* Stuff from the get device id command. */
 static unsigned int mfg_id;
 static unsigned int prod_id;
@@ -349,26 +363,38 @@ static void ipmi_poweroff_chassis (ipmi_user_t user)
         smi_addr.channel = IPMI_BMC_CHANNEL;
         smi_addr.lun = 0;
 
-	printk(KERN_INFO PFX "Powering down via IPMI chassis control command\n");
+ powercyclefailed:
+	printk(KERN_INFO PFX "Powering %s via IPMI chassis control command\n",
+		((poweroff_control != IPMI_CHASSIS_POWER_CYCLE) ? "down" : "cycle"));
 
 	/*
 	 * Power down
 	 */
 	send_msg.netfn = IPMI_NETFN_CHASSIS_REQUEST;
 	send_msg.cmd = IPMI_CHASSIS_CONTROL_CMD;
-	data[0] = 0; /* Power down */
+	data[0] = poweroff_control;
 	send_msg.data = data;
 	send_msg.data_len = sizeof(data);
 	rv = ipmi_request_in_rc_mode(user,
 				     (struct ipmi_addr *) &smi_addr,
 				     &send_msg);
 	if (rv) {
-		printk(KERN_ERR PFX "Unable to send chassis powerdown message,"
-		       " IPMI error 0x%x\n", rv);
-		goto out;
+		switch (poweroff_control) {
+			case IPMI_CHASSIS_POWER_CYCLE:
+				/* power cycle failed, default to power down */
+				printk(KERN_ERR PFX "Unable to send chassis power " \
+					"cycle message, IPMI error 0x%x\n", rv);
+				poweroff_control = IPMI_CHASSIS_POWER_DOWN;
+				goto powercyclefailed;
+
+			case IPMI_CHASSIS_POWER_DOWN:
+			default:
+				printk(KERN_ERR PFX "Unable to send chassis power " \
+					"down message, IPMI error 0x%x\n", rv);
+				break;
+		}
 	}
 
- out:
 	return;
 }
 
@@ -430,7 +456,8 @@ static void ipmi_po_new_smi(int if_num)
 	if (ready)
 		return;
 
-	rv = ipmi_create_user(if_num, &ipmi_poweroff_handler, NULL, &ipmi_user);
+	rv = ipmi_create_user(if_num, &ipmi_poweroff_handler, NULL,
+			      &ipmi_user);
 	if (rv) {
 		printk(KERN_ERR PFX "could not create IPMI user, error %d\n",
 		       rv);
@@ -509,21 +536,84 @@ static struct ipmi_smi_watcher smi_watcher =
 };
 
 
+#ifdef CONFIG_PROC_FS
+/* displays properties to proc */
+static int proc_read_chassctrl(char *page, char **start, off_t off, int count,
+			       int *eof, void *data)
+{
+	return sprintf(page, "%d\t[ 0=powerdown 2=powercycle ]\n",
+			poweroff_control);
+}
+
+/* process property writes from proc */
+static int proc_write_chassctrl(struct file *file, const char *buffer,
+			        unsigned long count, void *data)
+{
+	int          rv = count;
+	unsigned int newval = 0;
+
+	sscanf(buffer, "%d", &newval);
+	switch (newval) {
+		case IPMI_CHASSIS_POWER_CYCLE:
+			printk(KERN_INFO PFX "power cycle is now enabled\n");
+			poweroff_control = newval;
+			break;
+
+		case IPMI_CHASSIS_POWER_DOWN:
+			poweroff_control = IPMI_CHASSIS_POWER_DOWN;
+			break;
+
+		default:
+			rv = -EINVAL;
+			break;
+	}
+
+	return rv;
+}
+#endif /* CONFIG_PROC_FS */
+
 /*
  * Startup and shutdown functions.
  */
 static int ipmi_poweroff_init (void)
 {
-	int rv;
+	int                   rv;
+	struct proc_dir_entry *file;
 
 	printk ("Copyright (C) 2004 MontaVista Software -"
 		" IPMI Powerdown via sys_reboot version "
 		IPMI_POWEROFF_VERSION ".\n");
 
+	switch (poweroff_control) {
+		case IPMI_CHASSIS_POWER_CYCLE:
+			printk(KERN_INFO PFX "Power cycle is enabled.\n");
+			break;
+
+		case IPMI_CHASSIS_POWER_DOWN:
+		default:
+			poweroff_control = IPMI_CHASSIS_POWER_DOWN;
+			break;
+	}
+
 	rv = ipmi_smi_watcher_register(&smi_watcher);
-	if (rv)
+	if (rv) {
 		printk(KERN_ERR PFX "Unable to register SMI watcher: %d\n", rv);
+		goto out_err;
+	}
+
+#ifdef CONFIG_PROC_FS
+	file = create_proc_entry("poweroff_control", 0, proc_ipmi_root);
+	if (!file) {
+		printk(KERN_ERR PFX "Unable to create proc power control\n");
+	} else {
+		file->nlink = 1;
+		file->read_proc = proc_read_chassctrl;
+		file->write_proc = proc_write_chassctrl;
+		file->owner = THIS_MODULE;
+	}
+#endif
 
+ out_err:
 	return rv;
 }
 
@@ -532,6 +622,10 @@ static __exit void ipmi_poweroff_cleanup(void)
 {
 	int rv;
 
+#ifdef CONFIG_PROC_FS
+	remove_proc_entry("poweroff_control", proc_ipmi_root);
+#endif
+
 	ipmi_smi_watcher_unregister(&smi_watcher);
 
 	if (ready) {
diff --git a/include/linux/ipmi.h b/include/linux/ipmi.h
index 2ec265e1045f..596ca6130159 100644
--- a/include/linux/ipmi.h
+++ b/include/linux/ipmi.h
@@ -209,6 +209,11 @@ struct kernel_ipmi_msg
 #include <linux/list.h>
 #include <linux/module.h>
 
+#ifdef CONFIG_PROC_FS
+#include <linux/proc_fs.h>
+extern struct proc_dir_entry *proc_ipmi_root;
+#endif /* CONFIG_PROC_FS */
+
 /* Opaque type for a IPMI message user.  One of these is needed to
    send and receive messages. */
 typedef struct ipmi_user *ipmi_user_t;