page_alloc: add movable_memmap kernel parameter

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

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

[akpm@linux-foundation.org: improve comment]
[akpm@linux-foundation.org: checkpatch fixes]
[akpm@linux-foundation.org: remove unneeded parens]
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>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 9aa8ff3..722a741 100644 (file)
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -1640,6 +1640,23 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
                        that the amount of memory usable for all allocations
                        is not too small.
 
                        that the amount of memory usable for all allocations
                        is not too small.
 

+       movablemem_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
+                       movablemem_map will be limited within the memmap
+                       areas. If kernelcore or movablecore is also specified,
+                       movablemem_map will have higher priority to be
+                       satisfied. So the administrator should be careful that
+                       the amount of movablemem_map areas are not too large.
+                       Otherwise kernel won't have enough memory to start.
+

        MTD_Partition=  [MTD]
                        Format: <name>,<region-number>,<size>,<offset>
 
        MTD_Partition=  [MTD]
                        Format: <name>,<region-number>,<size>,<offset>
 

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 9d65949..ce9bd30 100644 (file)
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1359,6 +1359,17 @@ extern void free_bootmem_with_active_regions(int nid,
                                                unsigned long max_low_pfn);
 extern void sparse_memory_present_with_active_regions(int nid);
 
                                                unsigned long max_low_pfn);
 extern void sparse_memory_present_with_active_regions(int nid);
 

+#define MOVABLEMEM_MAP_MAX MAX_NUMNODES
+struct movablemem_entry {
+       unsigned long start_pfn;    /* start pfn of memory segment */
+       unsigned long end_pfn;      /* end pfn of memory segment (exclusive) */
+};
+
+struct movablemem_map {
+       int nr_map;
+       struct movablemem_entry map[MOVABLEMEM_MAP_MAX];
+};
+

 #endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
 
 #if !defined(CONFIG_HAVE_MEMBLOCK_NODE_MAP) && \
 #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 7039448..aa1cc5f 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
 static unsigned long __meminitdata dma_reserve;
 
 #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP

+/* Movable memory ranges, will also be used by memblock subsystem. */
+struct movablemem_map movablemem_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;
 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 +5081,134 @@ static int __init cmdline_parse_movablecore(char *p)
 early_param("kernelcore", cmdline_parse_kernelcore);
 early_param("movablecore", cmdline_parse_movablecore);
 
 early_param("kernelcore", cmdline_parse_kernelcore);
 early_param("movablecore", cmdline_parse_movablecore);
 

+/**
+ * insert_movablemem_map - Insert a memory range in to movablemem_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_movablemem_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 < movablemem_map.nr_map; pos++)
+               if (start_pfn <= movablemem_map.map[pos].end_pfn)
+                       break;
+
+       /* If there is no overlapped range, just insert the element. */
+       if (pos == movablemem_map.nr_map ||
+           end_pfn < movablemem_map.map[pos].start_pfn) {
+               /*
+                * If pos is not the end of array, we need to move all
+                * the rest elements backward.
+                */
+               if (pos < movablemem_map.nr_map)
+                       memmove(&movablemem_map.map[pos+1],
+                               &movablemem_map.map[pos],
+                               sizeof(struct movablemem_entry) *
+                               (movablemem_map.nr_map - pos));
+               movablemem_map.map[pos].start_pfn = start_pfn;
+               movablemem_map.map[pos].end_pfn = end_pfn;
+               movablemem_map.nr_map++;
+               return;
+       }
+
+       /* overlap will be at the last overlapped range */
+       for (overlap = pos + 1; overlap < movablemem_map.nr_map; overlap++)
+               if (end_pfn < movablemem_map.map[overlap].start_pfn)
+                       break;
+
+       /*
+        * If there are more ranges overlapped, we need to merge them,
+        * and move the rest elements forward.
+        */
+       overlap--;
+       movablemem_map.map[pos].start_pfn = min(start_pfn,
+                                       movablemem_map.map[pos].start_pfn);
+       movablemem_map.map[pos].end_pfn = max(end_pfn,
+                                       movablemem_map.map[overlap].end_pfn);
+
+       if (pos != overlap && overlap + 1 != movablemem_map.nr_map)
+               memmove(&movablemem_map.map[pos+1],
+                       &movablemem_map.map[overlap+1],
+                       sizeof(struct movablemem_entry) *
+                       (movablemem_map.nr_map - overlap - 1));
+
+       movablemem_map.nr_map -= overlap - pos;
+}
+
+/**
+ * movablemem_map_add_region - Add a memory range into movablemem_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 movablemem_map by calling insert_movablemem_map().
+ */
+static void __init movablemem_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 (movablemem_map.nr_map >= ARRAY_SIZE(movablemem_map.map)) {
+               pr_err("movablemem_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_movablemem_map(start_pfn, end_pfn);
+}
+
+/*
+ * cmdline_parse_movablemem_map - Parse boot option movablemem_map.
+ * @p: The boot option of the following format:
+ *     movablemem_map=nn[KMG]@ss[KMG]
+ *
+ * This option sets the memory range [ss, ss+nn) to be used as movable memory.
+ *
+ * Return: 0 on success or -EINVAL on failure.
+ */
+static int __init cmdline_parse_movablemem_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;
+
+               movablemem_map_add_region(start_at, mem_size);
+               return 0;
+       }
+err:
+       return -EINVAL;
+}
+early_param("movablemem_map", cmdline_parse_movablemem_map);
+

 #endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
 
 /**
 #endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
 
 /**