handle kernelcore=: generic

This patch adds the kernelcore= parameter for x86.

Once all patches are applied, a new command-line parameter exist and a new
sysctl.  This patch adds the necessary documentation.

From: Yasunori Goto <[email protected]>

  When "kernelcore" boot option is specified, kernel can't boot up on ia64
  because of an infinite loop.  In addition, the parsing code can be handled
  in an architecture-independent manner.

  This patch uses common code to handle the kernelcore= parameter.  It is
  only available to architectures that support arch-independent zone-sizing
  (i.e.  define CONFIG_ARCH_POPULATES_NODE_MAP).  Other architectures will
  ignore the boot parameter.

[[email protected]: make cmdline_parse_kernelcore() static]
Signed-off-by: Mel Gorman <[email protected]>
Signed-off-by: Yasunori Goto <[email protected]>
Acked-by: Andy Whitcroft <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>

Documentation/filesystems/proc.txt

@@ -1348,6 +1348,21 @@ nr_hugepages configures number of hugetlb page reserved for the system.
 hugetlb_shm_group contains group id that is allowed to create SysV shared
 memory segment using hugetlb page.
 
+hugepages_treat_as_movable
+--------------------------
+
+This parameter is only useful when kernelcore= is specified at boot time to
+create ZONE_MOVABLE for pages that may be reclaimed or migrated. Huge pages
+are not movable so are not normally allocated from ZONE_MOVABLE. A non-zero
+value written to hugepages_treat_as_movable allows huge pages to be allocated
+from ZONE_MOVABLE.
+
+Once enabled, the ZONE_MOVABLE is treated as an area of memory the huge
+pages pool can easily grow or shrink within. Assuming that applications are
+not running that mlock() a lot of memory, it is likely the huge pages pool
+can grow to the size of ZONE_MOVABLE by repeatedly entering the desired value
+into nr_hugepages and triggering page reclaim.
+
 laptop_mode
 -----------
 

Documentation/kernel-parameters.txt

@@ -817,6 +817,22 @@ and is between 256 and 4096 characters. It is defined in the file
 	js=		[HW,JOY] Analog joystick
 			See Documentation/input/joystick.txt.
 
+	kernelcore=nn[KMG]	[KNL,IA-32,IA-64,PPC,X86-64] This parameter
+			specifies the amount of memory usable by the kernel
+			for non-movable allocations.  The requested amount is
+			spread evenly throughout all nodes in the system. The
+			remaining memory in each node is used for Movable
+			pages. In the event, a node is too small to have both
+			kernelcore and Movable pages, kernelcore pages will
+			take priority and other nodes will have a larger number
+			of kernelcore pages.  The Movable zone is used for the
+			allocation of pages that may be reclaimed or moved
+			by the page migration subsystem.  This means that
+			HugeTLB pages may not be allocated from this zone.
+			Note that allocations like PTEs-from-HighMem still
+			use the HighMem zone if it exists, and the Normal
+			zone if it does not.
+
 	keepinitrd	[HW,ARM]
 
 	kstack=N	[IA-32,X86-64] Print N words from the kernel stack

Documentation/sysctl/vm.txt

@@ -38,7 +38,8 @@ Currently, these files are in /proc/sys/vm:
 
 dirty_ratio, dirty_background_ratio, dirty_expire_centisecs,
 dirty_writeback_centisecs, vfs_cache_pressure, laptop_mode,
-block_dump, swap_token_timeout, drop-caches:
+block_dump, swap_token_timeout, drop-caches,
+hugepages_treat_as_movable:
 
 See Documentation/filesystems/proc.txt
 

arch/ia64/kernel/efi.c

@@ -28,6 +28,7 @@
 #include <linux/time.h>
 #include <linux/efi.h>
 #include <linux/kexec.h>
+#include <linux/mm.h>
 
 #include <asm/io.h>
 #include <asm/kregs.h>

include/linux/mm.h

@@ -1005,7 +1005,6 @@ extern unsigned long find_max_pfn_with_active_regions(void);
 extern void free_bootmem_with_active_regions(int nid,
 						unsigned long max_low_pfn);
 extern void sparse_memory_present_with_active_regions(int nid);
-extern int cmdline_parse_kernelcore(char *p);
 #ifndef CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID
 extern int early_pfn_to_nid(unsigned long pfn);
 #endif /* CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID */

mm/page_alloc.c

@@ -3416,7 +3416,7 @@ void __init free_area_init_nodes(unsigned long *max_zone_pfn)
  * kernelcore=size sets the amount of memory for use for allocations that
  * cannot be reclaimed or migrated.
  */
-int __init cmdline_parse_kernelcore(char *p)
+static int __init cmdline_parse_kernelcore(char *p)
 {
 	unsigned long long coremem;
 	if (!p)
@@ -3430,6 +3430,9 @@ int __init cmdline_parse_kernelcore(char *p)
 
 	return 0;
 }
+
+early_param("kernelcore", cmdline_parse_kernelcore);
+
 #endif /* CONFIG_ARCH_POPULATES_NODE_MAP */
 
 /**