page_alloc: add movable_memmap kernel parameter

Add functions to parse movablecore_map boot option.  Since the option
could be specified more then once, all the maps will be stored in the
global variable movablecore_map.map array.

And also, we keep the array in monotonic increasing order by start_pfn.
And merge all overlapped ranges.

Signed-off-by: Tang Chen <tangchen@cn.fujitsu.com>
Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Reviewed-by: Wen Congyang <wency@cn.fujitsu.com>
Tested-by: Lin Feng <linfeng@cn.fujitsu.com>
Cc: Wu Jianguo <wujianguo@huawei.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index d5b304c4d0869e169b0cf95cea0ef2451d373f88..71c3daa4a42c58e26fa96b2bef8358bdc8b1be90 100644 (file)
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -1644,6 +1644,23 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
                        that the amount of memory usable for all allocations
                        is not too small.
 
+       movablecore_map=nn[KMG]@ss[KMG]
+                       [KNL,X86,IA-64,PPC] This parameter is similar to
+                       memmap except it specifies the memory map of
+                       ZONE_MOVABLE.
+                       If more areas are all within one node, then from
+                       lowest ss to the end of the node will be ZONE_MOVABLE.
+                       If an area covers two or more nodes, the area from
+                       ss to the end of the 1st node will be ZONE_MOVABLE,
+                       and all the rest nodes will only have ZONE_MOVABLE.
+                       If memmap is specified at the same time, the
+                       movablecore_map will be limited within the memmap
+                       areas. If kernelcore or movablecore is also specified,
+                       movablecore_map will have higher priority to be
+                       satisfied. So the administrator should be careful that
+                       the amount of movablecore_map areas are not too large.
+                       Otherwise kernel won't have enough memory to start.
+
        MTD_Partition=  [MTD]
                        Format: <name>,<region-number>,<size>,<offset>
 

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 5ca9b9a588e1a2ff1cdfeb9836939fb3236de7fc..1c1065dbd0a270ff23cd92259a87ea1a481b5f9f 100644 (file)
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1361,6 +1361,17 @@ extern void free_bootmem_with_active_regions(int nid,
                                                unsigned long max_low_pfn);
 extern void sparse_memory_present_with_active_regions(int nid);
 
+#define MOVABLECORE_MAP_MAX MAX_NUMNODES
+struct movablecore_entry {
+       unsigned long start_pfn;    /* start pfn of memory segment */
+       unsigned long end_pfn;      /* end pfn of memory segment */
+};
+
+struct movablecore_map {
+       int nr_map;
+       struct movablecore_entry map[MOVABLECORE_MAP_MAX];
+};
+
 #endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
 
 #if !defined(CONFIG_HAVE_MEMBLOCK_NODE_MAP) && \

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index edb95fc67e70f364ed43dbff7e5f8b7d1253cdaa..24609b98330cf36e33ed3c92c293382b45ec7105 100644 (file)
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -202,6 +202,9 @@ static unsigned long __meminitdata nr_all_pages;
 static unsigned long __meminitdata dma_reserve;
 
 #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
+/* Movable memory ranges, will also be used by memblock subsystem. */
+struct movablecore_map movablecore_map;
+
 static unsigned long __meminitdata arch_zone_lowest_possible_pfn[MAX_NR_ZONES];
 static unsigned long __meminitdata arch_zone_highest_possible_pfn[MAX_NR_ZONES];
 static unsigned long __initdata required_kernelcore;
@@ -5078,6 +5081,129 @@ static int __init cmdline_parse_movablecore(char *p)
 early_param("kernelcore", cmdline_parse_kernelcore);
 early_param("movablecore", cmdline_parse_movablecore);
 
+/**
+ * insert_movablecore_map - Insert a memory range in to movablecore_map.map.
+ * @start_pfn: start pfn of the range
+ * @end_pfn: end pfn of the range
+ *
+ * This function will also merge the overlapped ranges, and sort the array
+ * by start_pfn in monotonic increasing order.
+ */
+static void __init insert_movablecore_map(unsigned long start_pfn,
+                                         unsigned long end_pfn)
+{
+       int pos, overlap;
+
+       /*
+        * pos will be at the 1st overlapped range, or the position
+        * where the element should be inserted.
+        */
+       for (pos = 0; pos < movablecore_map.nr_map; pos++)
+               if (start_pfn <= movablecore_map.map[pos].end_pfn)
+                       break;
+
+       /* If there is no overlapped range, just insert the element. */
+       if (pos == movablecore_map.nr_map ||
+           end_pfn < movablecore_map.map[pos].start_pfn) {
+               /*
+                * If pos is not the end of array, we need to move all
+                * the rest elements backward.
+                */
+               if (pos < movablecore_map.nr_map)
+                       memmove(&movablecore_map.map[pos+1],
+                               &movablecore_map.map[pos],
+                               sizeof(struct movablecore_entry) *
+                               (movablecore_map.nr_map - pos));
+               movablecore_map.map[pos].start_pfn = start_pfn;
+               movablecore_map.map[pos].end_pfn = end_pfn;
+               movablecore_map.nr_map++;
+               return;
+       }
+
+       /* overlap will be at the last overlapped range */
+       for (overlap = pos + 1; overlap < movablecore_map.nr_map; overlap++)
+               if (end_pfn < movablecore_map.map[overlap].start_pfn)
+                       break;
+
+       /*
+        * If there are more ranges overlapped, we need to merge them,
+        * and move the rest elements forward.
+        */
+       overlap--;
+       movablecore_map.map[pos].start_pfn = min(start_pfn,
+                                       movablecore_map.map[pos].start_pfn);
+       movablecore_map.map[pos].end_pfn = max(end_pfn,
+                                       movablecore_map.map[overlap].end_pfn);
+
+       if (pos != overlap && overlap + 1 != movablecore_map.nr_map)
+               memmove(&movablecore_map.map[pos+1],
+                       &movablecore_map.map[overlap+1],
+                       sizeof(struct movablecore_entry) *
+                       (movablecore_map.nr_map - overlap - 1));
+
+       movablecore_map.nr_map -= overlap - pos;
+}
+
+/**
+ * movablecore_map_add_region - Add a memory range into movablecore_map.
+ * @start: physical start address of range
+ * @end: physical end address of range
+ *
+ * This function transform the physical address into pfn, and then add the
+ * range into movablecore_map by calling insert_movablecore_map().
+ */
+static void __init movablecore_map_add_region(u64 start, u64 size)
+{
+       unsigned long start_pfn, end_pfn;
+
+       /* In case size == 0 or start + size overflows */
+       if (start + size <= start)
+               return;
+
+       if (movablecore_map.nr_map >= ARRAY_SIZE(movablecore_map.map)) {
+               pr_err("movable_memory_map: too many entries;"
+                       " ignoring [mem %#010llx-%#010llx]\n",
+                       (unsigned long long) start,
+                       (unsigned long long) (start + size - 1));
+               return;
+       }
+
+       start_pfn = PFN_DOWN(start);
+       end_pfn = PFN_UP(start + size);
+       insert_movablecore_map(start_pfn, end_pfn);
+}
+
+/*
+ * movablecore_map=nn[KMG]@ss[KMG] sets the region of memory to be used as
+ * movable memory.
+ */
+static int __init cmdline_parse_movablecore_map(char *p)
+{
+       char *oldp;
+       u64 start_at, mem_size;
+
+       if (!p)
+               goto err;
+
+       oldp = p;
+       mem_size = memparse(p, &p);
+       if (p == oldp)
+               goto err;
+
+       if (*p == '@') {
+               oldp = ++p;
+               start_at = memparse(p, &p);
+               if (p == oldp || *p != '\0')
+                       goto err;
+
+               movablecore_map_add_region(start_at, mem_size);
+               return 0;
+       }
+err:
+       return -EINVAL;
+}
+early_param("movablecore_map", cmdline_parse_movablecore_map);
+
 #endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
 
 /**