mm, x86: Saving vmcore with non-lazy freeing of vmas

During the reading of /proc/vmcore the kernel is doing
ioremap()/iounmap() repeatedly. And the buildup of un-flushed
vm_area_struct's is causing a great deal of overhead. (rb_next()
is chewing up most of that time).

This solution is to provide function set_iounmap_nonlazy(). It
causes a subsequent call to iounmap() to immediately purge the
vma area (with try_purge_vmap_area_lazy()).

With this patch we have seen the time for writing a 250MB
compressed dump drop from 71 seconds to 44 seconds.
Signed-off-by: Cliff Wickman <cpw@sgi.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: kexec@lists.infradead.org
Cc: <stable@kernel.org>
LKML-Reference: <E1OwHZ4-0005WK-Tw@eag09.americas.sgi.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

arch/x86/include/asm/io.h

@@ -206,6 +206,7 @@ static inline void __iomem *ioremap(resource_size_t offset, unsigned long size)
 
 extern void iounmap(volatile void __iomem *addr);
 
+extern void set_iounmap_nonlazy(void);
 
 #ifdef __KERNEL__
 

arch/x86/kernel/crash_dump_64.c

@@ -46,6 +46,7 @@ ssize_t copy_oldmem_page(unsigned long pfn, char *buf,
 	} else
 		memcpy(buf, vaddr + offset, csize);
 
+	set_iounmap_nonlazy();
 	iounmap(vaddr);
 	return csize;
 }

mm/vmalloc.c

@@ -516,6 +516,15 @@ static atomic_t vmap_lazy_nr = ATOMIC_INIT(0);
 /* for per-CPU blocks */
 static void purge_fragmented_blocks_allcpus(void);
 
+/*
+ * called before a call to iounmap() if the caller wants vm_area_struct's
+ * immediately freed.
+ */
+void set_iounmap_nonlazy(void)
+{
+	atomic_set(&vmap_lazy_nr, lazy_max_pages()+1);
+}
+
 /*
  * Purges all lazily-freed vmap areas.
  *