kexec: premit reduction of the reserved memory size

Implement shrinking the reserved memory for crash kernel, if it is more
than enough.

For example, if you have already reserved 128M, now you just want 100M,
you can do:

# echo $((100*1024*1024)) > /sys/kernel/kexec_crash_size

Note, you can only do this before loading the crash kernel.

Signed-off-by: WANG Cong <amwang@redhat.com>
Cc: Neil Horman <nhorman@redhat.com>
Acked-by: Eric W. Biederman <ebiederm@xmission.com>
Cc: Andi Kleen <andi@firstfloor.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 80 insertions, 0 deletions

diff --git a/kernel/kexec.c b/kernel/kexec.c
index f336e2107f9..433e9fcc1fc 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -31,6 +31,7 @@
 #include <linux/cpu.h>
 #include <linux/console.h>
 #include <linux/vmalloc.h>
+#include <linux/swap.h>
 
 #include <asm/page.h>
 #include <asm/uaccess.h>
@@ -1082,6 +1083,64 @@ void crash_kexec(struct pt_regs *regs)
 	}
 }
 
+size_t crash_get_memory_size(void)
+{
+	size_t size;
+	mutex_lock(&kexec_mutex);
+	size = crashk_res.end - crashk_res.start + 1;
+	mutex_unlock(&kexec_mutex);
+	return size;
+}
+
+static void free_reserved_phys_range(unsigned long begin, unsigned long end)
+{
+	unsigned long addr;
+
+	for (addr = begin; addr < end; addr += PAGE_SIZE) {
+		ClearPageReserved(pfn_to_page(addr >> PAGE_SHIFT));
+		init_page_count(pfn_to_page(addr >> PAGE_SHIFT));
+		free_page((unsigned long)__va(addr));
+		totalram_pages++;
+	}
+}
+
+int crash_shrink_memory(unsigned long new_size)
+{
+	int ret = 0;
+	unsigned long start, end;
+
+	mutex_lock(&kexec_mutex);
+
+	if (kexec_crash_image) {
+		ret = -ENOENT;
+		goto unlock;
+	}
+	start = crashk_res.start;
+	end = crashk_res.end;
+
+	if (new_size >= end - start + 1) {
+		ret = -EINVAL;
+		if (new_size == end - start + 1)
+			ret = 0;
+		goto unlock;
+	}
+
+	start = roundup(start, PAGE_SIZE);
+	end = roundup(start + new_size, PAGE_SIZE);
+
+	free_reserved_phys_range(end, crashk_res.end);
+
+	if (start == end) {
+		crashk_res.end = end;
+		release_resource(&crashk_res);
+	} else
+		crashk_res.end = end - 1;
+
+unlock:
+	mutex_unlock(&kexec_mutex);
+	return ret;
+}
+
 static u32 *append_elf_note(u32 *buf, char *name, unsigned type, void *data,
 			    size_t data_len)
 {
diff --git a/kernel/ksysfs.c b/kernel/ksysfs.c
index 528dd78e7e7..3feaf5a7451 100644
--- a/kernel/ksysfs.c
+++ b/kernel/ksysfs.c
@@ -100,6 +100,26 @@ static ssize_t kexec_crash_loaded_show(struct kobject *kobj,
 }
 KERNEL_ATTR_RO(kexec_crash_loaded);
 
+static ssize_t kexec_crash_size_show(struct kobject *kobj,
+				       struct kobj_attribute *attr, char *buf)
+{
+	return sprintf(buf, "%zu\n", crash_get_memory_size());
+}
+static ssize_t kexec_crash_size_store(struct kobject *kobj,
+				   struct kobj_attribute *attr,
+				   const char *buf, size_t count)
+{
+	unsigned long cnt;
+	int ret;
+
+	if (strict_strtoul(buf, 0, &cnt))
+		return -EINVAL;
+
+	ret = crash_shrink_memory(cnt);
+	return ret < 0 ? ret : count;
+}
+KERNEL_ATTR_RW(kexec_crash_size);
+
 static ssize_t vmcoreinfo_show(struct kobject *kobj,
 			       struct kobj_attribute *attr, char *buf)
 {
@@ -147,6 +167,7 @@ static struct attribute * kernel_attrs[] = {
 #ifdef CONFIG_KEXEC
 	&kexec_loaded_attr.attr,
 	&kexec_crash_loaded_attr.attr,
+	&kexec_crash_size_attr.attr,
 	&vmcoreinfo_attr.attr,
 #endif
 	NULL