[RFC Patch 2/2] kexec: allow to shrink reserved memory

[Amerigo Wang <amwang@redhat.com>]

This patch implements 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

Signed-off-by: WANG Cong <amwang@redhat.com>
Cc: Neil Horman <nhorman@redhat.com>
Cc: Eric W. Biederman <ebiederm@xmission.com>
Cc: Andi Kleen <andi@firstfloor.org>

---
Index: linux-2.6/include/linux/kexec.h
===================================================================
--- linux-2.6.orig/include/linux/kexec.h
+++ linux-2.6/include/linux/kexec.h
@@ -158,6 +158,8 @@ unsigned long paddr_vmcoreinfo_note(void
 
 extern struct kimage *kexec_image;
 extern struct kimage *kexec_crash_image;
+extern struct resource *kexec_res;
+extern struct resource *kexec_free_res;
 
 #ifndef kexec_flush_icache_page
 #define kexec_flush_icache_page(page)
@@ -206,6 +208,7 @@ extern size_t vmcoreinfo_max_size;
 
 int __init parse_crashkernel(char *cmdline, unsigned long long system_ram,
 		unsigned long long *crash_size, unsigned long long *crash_base);
+int shrink_crash_memory(unsigned long start, unsigned long end);
 
 #else /* !CONFIG_KEXEC */
 struct pt_regs;
Index: linux-2.6/kernel/kexec.c
===================================================================
--- linux-2.6.orig/kernel/kexec.c
+++ linux-2.6/kernel/kexec.c
@@ -1130,6 +1130,51 @@ void crash_kexec(struct pt_regs *regs)
 	}
 }
 
+int shrink_crash_memory(unsigned long start, unsigned long end)
+{
+	struct page **pages;
+	int ret = 0;
+	int  npages, i;
+	unsigned long addr;
+	void *vaddr;
+
+	if (!mutex_trylock(&kexec_mutex))
+		return -EBUSY;
+
+	if (!kexec_free_res) {
+		ret = -ENOENT;
+		goto unlock;
+	}
+
+	start = roundup(start, PAGE_SIZE);
+	end = roundup(end, PAGE_SIZE) - 1;
+	npages = (end + 1 - start ) / PAGE_SIZE;
+
+	pages = kmalloc(sizeof(struct page *) * npages, GFP_KERNEL);
+	if (!pages) {
+		ret = -ENOMEM;
+		goto unlock;
+	}
+	for (i = 0; i < npages; i++) {
+		addr = start + i * PAGE_SIZE;
+		pages[i] = virt_to_page(addr);
+	}
+
+	vaddr = vm_map_ram(pages, npages, 0, PAGE_KERNEL);
+	if (!vaddr) {
+		ret = -ENOMEM;
+		goto free;
+	}
+	kexec_free_res->end = start - 1;
+	crashk_res.end = start - 1;
+
+free:
+	kfree(pages);
+unlock:
+	mutex_unlock(&kexec_mutex);
+	return ret;
+}
+
 static u32 *append_elf_note(u32 *buf, char *name, unsigned type, void *data,
 			    size_t data_len)
 {
Index: linux-2.6/kernel/ksysfs.c
===================================================================
--- linux-2.6.orig/kernel/ksysfs.c
+++ linux-2.6/kernel/ksysfs.c
@@ -100,6 +100,32 @@ static ssize_t kexec_crash_loaded_show(s
 }
 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, "%llu\n", crashk_res.end - crashk_res.start + 1);
+}
+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 (!kexec_res || !kexec_free_res)
+		return -ENOENT;
+	cnt = simple_strtoul(buf, NULL, 10);
+	if (cnt < kexec_res->end - kexec_res->start + 1)
+		return -ENOENT;
+	if (cnt > kexec_free_res->end - kexec_res->start + 1)
+		return -ENOENT;
+	cnt -= kexec_res->end - kexec_res->start + 1;
+	ret = shrink_crash_memory(kexec_free_res->start + cnt,
+		kexec_free_res->end);
+	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 +173,7 @@ 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