X-Git-Url: https://err.no/cgi-bin/gitweb.cgi?a=blobdiff_plain;f=kernel%2Fkexec.c;h=c8a4370e2a34e94b2e391fada22fec051b162195;hb=191cd582500f49b32a63040fedeebb0168c720af;hp=e9f1b4ea504d920bd514deb8868536fd10de77bb;hpb=a9e82d3a02247af6b729be0a963862d70cb25bf9;p=linux-2.6

diff --git a/kernel/kexec.c b/kernel/kexec.c
index e9f1b4ea50..c8a4370e2a 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -24,12 +24,17 @@
 #include <linux/utsrelease.h>
 #include <linux/utsname.h>
 #include <linux/numa.h>
+#include <linux/suspend.h>
+#include <linux/device.h>
+#include <linux/freezer.h>
+#include <linux/pm.h>
+#include <linux/cpu.h>
+#include <linux/console.h>
 
 #include <asm/page.h>
 #include <asm/uaccess.h>
 #include <asm/io.h>
 #include <asm/system.h>
-#include <asm/semaphore.h>
 #include <asm/sections.h>
 
 /* Per cpu memory for storing cpu states in case of system crash. */
@@ -51,7 +56,7 @@ struct resource crashk_res = {
 
 int kexec_should_crash(struct task_struct *p)
 {
-	if (in_interrupt() || !p->pid || is_init(p) || panic_on_oops)
+	if (in_interrupt() || !p->pid || is_global_init(p) || panic_on_oops)
 		return 1;
 	return 0;
 }
@@ -243,6 +248,12 @@ static int kimage_normal_alloc(struct kimage **rimage, unsigned long entry,
 		goto out;
 	}
 
+	image->swap_page = kimage_alloc_control_pages(image, 0);
+	if (!image->swap_page) {
+		printk(KERN_ERR "Could not allocate swap buffer\n");
+		goto out;
+	}
+
 	result = 0;
  out:
 	if (result == 0)
@@ -590,14 +601,12 @@ static void kimage_free_extra_pages(struct kimage *image)
 	kimage_free_page_list(&image->unuseable_pages);
 
 }
-static int kimage_terminate(struct kimage *image)
+static void kimage_terminate(struct kimage *image)
 {
 	if (*image->entry != 0)
 		image->entry++;
 
 	*image->entry = IND_DONE;
-
-	return 0;
 }
 
 #define for_each_kimage_entry(image, ptr, entry) \
@@ -989,6 +998,8 @@ asmlinkage long sys_kexec_load(unsigned long entry, unsigned long nr_segments,
 		if (result)
 			goto out;
 
+		if (flags & KEXEC_PRESERVE_CONTEXT)
+			image->preserve_context = 1;
 		result = machine_kexec_prepare(image);
 		if (result)
 			goto out;
@@ -998,9 +1009,7 @@ asmlinkage long sys_kexec_load(unsigned long entry, unsigned long nr_segments,
 			if (result)
 				goto out;
 		}
-		result = kimage_terminate(image);
-		if (result)
-			goto out;
+		kimage_terminate(image);
 	}
 	/* Install the new kernel, and  Uninstall the old */
 	image = xchg(dest_image, image);
@@ -1146,6 +1155,172 @@ static int __init crash_notes_memory_init(void)
 }
 module_init(crash_notes_memory_init)
 
+
+/*
+ * parsing the "crashkernel" commandline
+ *
+ * this code is intended to be called from architecture specific code
+ */
+
+
+/*
+ * This function parses command lines in the format
+ *
+ *   crashkernel=ramsize-range:size[,...][@offset]
+ *
+ * The function returns 0 on success and -EINVAL on failure.
+ */
+static int __init parse_crashkernel_mem(char 			*cmdline,
+					unsigned long long	system_ram,
+					unsigned long long	*crash_size,
+					unsigned long long	*crash_base)
+{
+	char *cur = cmdline, *tmp;
+
+	/* for each entry of the comma-separated list */
+	do {
+		unsigned long long start, end = ULLONG_MAX, size;
+
+		/* get the start of the range */
+		start = memparse(cur, &tmp);
+		if (cur == tmp) {
+			pr_warning("crashkernel: Memory value expected\n");
+			return -EINVAL;
+		}
+		cur = tmp;
+		if (*cur != '-') {
+			pr_warning("crashkernel: '-' expected\n");
+			return -EINVAL;
+		}
+		cur++;
+
+		/* if no ':' is here, than we read the end */
+		if (*cur != ':') {
+			end = memparse(cur, &tmp);
+			if (cur == tmp) {
+				pr_warning("crashkernel: Memory "
+						"value expected\n");
+				return -EINVAL;
+			}
+			cur = tmp;
+			if (end <= start) {
+				pr_warning("crashkernel: end <= start\n");
+				return -EINVAL;
+			}
+		}
+
+		if (*cur != ':') {
+			pr_warning("crashkernel: ':' expected\n");
+			return -EINVAL;
+		}
+		cur++;
+
+		size = memparse(cur, &tmp);
+		if (cur == tmp) {
+			pr_warning("Memory value expected\n");
+			return -EINVAL;
+		}
+		cur = tmp;
+		if (size >= system_ram) {
+			pr_warning("crashkernel: invalid size\n");
+			return -EINVAL;
+		}
+
+		/* match ? */
+		if (system_ram >= start && system_ram < end) {
+			*crash_size = size;
+			break;
+		}
+	} while (*cur++ == ',');
+
+	if (*crash_size > 0) {
+		while (*cur != ' ' && *cur != '@')
+			cur++;
+		if (*cur == '@') {
+			cur++;
+			*crash_base = memparse(cur, &tmp);
+			if (cur == tmp) {
+				pr_warning("Memory value expected "
+						"after '@'\n");
+				return -EINVAL;
+			}
+		}
+	}
+
+	return 0;
+}
+
+/*
+ * That function parses "simple" (old) crashkernel command lines like
+ *
+ * 	crashkernel=size[@offset]
+ *
+ * It returns 0 on success and -EINVAL on failure.
+ */
+static int __init parse_crashkernel_simple(char 		*cmdline,
+					   unsigned long long 	*crash_size,
+					   unsigned long long 	*crash_base)
+{
+	char *cur = cmdline;
+
+	*crash_size = memparse(cmdline, &cur);
+	if (cmdline == cur) {
+		pr_warning("crashkernel: memory value expected\n");
+		return -EINVAL;
+	}
+
+	if (*cur == '@')
+		*crash_base = memparse(cur+1, &cur);
+
+	return 0;
+}
+
+/*
+ * That function is the entry point for command line parsing and should be
+ * called from the arch-specific code.
+ */
+int __init parse_crashkernel(char 		 *cmdline,
+			     unsigned long long system_ram,
+			     unsigned long long *crash_size,
+			     unsigned long long *crash_base)
+{
+	char 	*p = cmdline, *ck_cmdline = NULL;
+	char	*first_colon, *first_space;
+
+	BUG_ON(!crash_size || !crash_base);
+	*crash_size = 0;
+	*crash_base = 0;
+
+	/* find crashkernel and use the last one if there are more */
+	p = strstr(p, "crashkernel=");
+	while (p) {
+		ck_cmdline = p;
+		p = strstr(p+1, "crashkernel=");
+	}
+
+	if (!ck_cmdline)
+		return -EINVAL;
+
+	ck_cmdline += 12; /* strlen("crashkernel=") */
+
+	/*
+	 * if the commandline contains a ':', then that's the extended
+	 * syntax -- if not, it must be the classic syntax
+	 */
+	first_colon = strchr(ck_cmdline, ':');
+	first_space = strchr(ck_cmdline, ' ');
+	if (first_colon && (!first_space || first_colon < first_space))
+		return parse_crashkernel_mem(ck_cmdline, system_ram,
+				crash_size, crash_base);
+	else
+		return parse_crashkernel_simple(ck_cmdline, crash_size,
+				crash_base);
+
+	return 0;
+}
+
+
+
 void crash_save_vmcoreinfo(void)
 {
 	u32 *buf;
@@ -1195,8 +1370,8 @@ unsigned long __attribute__ ((weak)) paddr_vmcoreinfo_note(void)
 
 static int __init crash_save_vmcoreinfo_init(void)
 {
-	vmcoreinfo_append_str("OSRELEASE=%s\n", init_uts_ns.name.release);
-	vmcoreinfo_append_str("PAGESIZE=%ld\n", PAGE_SIZE);
+	VMCOREINFO_OSRELEASE(init_uts_ns.name.release);
+	VMCOREINFO_PAGESIZE(PAGE_SIZE);
 
 	VMCOREINFO_SYMBOL(init_uts_ns);
 	VMCOREINFO_SYMBOL(node_online_map);
@@ -1210,15 +1385,15 @@ static int __init crash_save_vmcoreinfo_init(void)
 #ifdef CONFIG_SPARSEMEM
 	VMCOREINFO_SYMBOL(mem_section);
 	VMCOREINFO_LENGTH(mem_section, NR_SECTION_ROOTS);
-	VMCOREINFO_SIZE(mem_section);
+	VMCOREINFO_STRUCT_SIZE(mem_section);
 	VMCOREINFO_OFFSET(mem_section, section_mem_map);
 #endif
-	VMCOREINFO_SIZE(page);
-	VMCOREINFO_SIZE(pglist_data);
-	VMCOREINFO_SIZE(zone);
-	VMCOREINFO_SIZE(free_area);
-	VMCOREINFO_SIZE(list_head);
-	VMCOREINFO_TYPEDEF_SIZE(nodemask_t);
+	VMCOREINFO_STRUCT_SIZE(page);
+	VMCOREINFO_STRUCT_SIZE(pglist_data);
+	VMCOREINFO_STRUCT_SIZE(zone);
+	VMCOREINFO_STRUCT_SIZE(free_area);
+	VMCOREINFO_STRUCT_SIZE(list_head);
+	VMCOREINFO_SIZE(nodemask_t);
 	VMCOREINFO_OFFSET(page, flags);
 	VMCOREINFO_OFFSET(page, _count);
 	VMCOREINFO_OFFSET(page, mapping);
@@ -1238,7 +1413,11 @@ static int __init crash_save_vmcoreinfo_init(void)
 	VMCOREINFO_OFFSET(list_head, next);
 	VMCOREINFO_OFFSET(list_head, prev);
 	VMCOREINFO_LENGTH(zone.free_area, MAX_ORDER);
+	VMCOREINFO_LENGTH(free_area.free_list, MIGRATE_TYPES);
 	VMCOREINFO_NUMBER(NR_FREE_PAGES);
+	VMCOREINFO_NUMBER(PG_lru);
+	VMCOREINFO_NUMBER(PG_private);
+	VMCOREINFO_NUMBER(PG_swapcache);
 
 	arch_crash_save_vmcoreinfo();
 
@@ -1246,3 +1425,85 @@ static int __init crash_save_vmcoreinfo_init(void)
 }
 
 module_init(crash_save_vmcoreinfo_init)
+
+/**
+ *	kernel_kexec - reboot the system
+ *
+ *	Move into place and start executing a preloaded standalone
+ *	executable.  If nothing was preloaded return an error.
+ */
+int kernel_kexec(void)
+{
+	int error = 0;
+
+	if (xchg(&kexec_lock, 1))
+		return -EBUSY;
+	if (!kexec_image) {
+		error = -EINVAL;
+		goto Unlock;
+	}
+
+	if (kexec_image->preserve_context) {
+#ifdef CONFIG_KEXEC_JUMP
+		mutex_lock(&pm_mutex);
+		pm_prepare_console();
+		error = freeze_processes();
+		if (error) {
+			error = -EBUSY;
+			goto Restore_console;
+		}
+		suspend_console();
+		error = device_suspend(PMSG_FREEZE);
+		if (error)
+			goto Resume_console;
+		error = disable_nonboot_cpus();
+		if (error)
+			goto Resume_devices;
+		local_irq_disable();
+		/* At this point, device_suspend() has been called,
+		 * but *not* device_power_down(). We *must*
+		 * device_power_down() now.  Otherwise, drivers for
+		 * some devices (e.g. interrupt controllers) become
+		 * desynchronized with the actual state of the
+		 * hardware at resume time, and evil weirdness ensues.
+		 */
+		error = device_power_down(PMSG_FREEZE);
+		if (error)
+			goto Enable_irqs;
+		save_processor_state();
+#endif
+	} else {
+		blocking_notifier_call_chain(&reboot_notifier_list,
+					     SYS_RESTART, NULL);
+		system_state = SYSTEM_RESTART;
+		device_shutdown();
+		sysdev_shutdown();
+		printk(KERN_EMERG "Starting new kernel\n");
+		machine_shutdown();
+	}
+
+	machine_kexec(kexec_image);
+
+	if (kexec_image->preserve_context) {
+#ifdef CONFIG_KEXEC_JUMP
+		restore_processor_state();
+		device_power_up(PMSG_RESTORE);
+ Enable_irqs:
+		local_irq_enable();
+		enable_nonboot_cpus();
+ Resume_devices:
+		device_resume(PMSG_RESTORE);
+ Resume_console:
+		resume_console();
+		thaw_processes();
+ Restore_console:
+		pm_restore_console();
+		mutex_unlock(&pm_mutex);
+#endif
+	}
+
+ Unlock:
+	xchg(&kexec_lock, 0);
+
+	return error;
+}