memblock, numa: introduce flags field into memblock

There is no flag in memblock to describe what type the memory is.
Sometimes, we may use memblock to reserve some memory for special usage.
And we want to know what kind of memory it is.  So we need a way to

In hotplug environment, we want to reserve hotpluggable memory so the
kernel won't be able to use it.  And when the system is up, we have to
free these hotpluggable memory to buddy.  So we need to mark these memory
first.

In order to do so, we need to mark out these special memory in memblock.
In this patch, we introduce a new "flags" member into memblock_region:
   struct memblock_region {
           phys_addr_t base;
           phys_addr_t size;
           unsigned long flags;		/* This is new. */
   #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
           int nid;
   #endif
   };

This patch does the following things:
1) Add "flags" member to memblock_region.
2) Modify the following APIs' prototype:
	memblock_add_region()
	memblock_insert_region()
3) Add memblock_reserve_region() to support reserve memory with flags, and keep
   memblock_reserve()'s prototype unmodified.
4) Modify other APIs to support flags, but keep their prototype unmodified.

The idea is from Wen Congyang <wency@cn.fujitsu.com> and Liu Jiang <jiang.liu@huawei.com>.

Suggested-by: Wen Congyang <wency@cn.fujitsu.com>
Suggested-by: Liu Jiang <jiang.liu@huawei.com>
Signed-off-by: Tang Chen <tangchen@cn.fujitsu.com>
Reviewed-by: Zhang Yanfei <zhangyanfei@cn.fujitsu.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: "Rafael J . Wysocki" <rjw@sisk.pl>
Cc: Chen Tang <imtangchen@gmail.com>
Cc: Gong Chen <gong.chen@linux.intel.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Jiang Liu <jiang.liu@huawei.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Lai Jiangshan <laijs@cn.fujitsu.com>
Cc: Larry Woodman <lwoodman@redhat.com>
Cc: Len Brown <lenb@kernel.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Michal Nazarewicz <mina86@mina86.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Prarit Bhargava <prarit@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Taku Izumi <izumi.taku@jp.fujitsu.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Thomas Renninger <trenn@suse.de>
Cc: Toshi Kani <toshi.kani@hp.com>
Cc: Vasilis Liaskovitis <vasilis.liaskovitis@profitbricks.com>
Cc: Wanpeng Li <liwanp@linux.vnet.ibm.com>
Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Cc: Yinghai Lu <yinghai@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index 77c60e52939da9f74611e8d3443b04220396ca26..9a805ec6e7942b6e72288687c0152392bd99f038 100644 (file)
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -22,6 +22,7 @@
 struct memblock_region {
        phys_addr_t base;
        phys_addr_t size;
+       unsigned long flags;
 #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
        int nid;
 #endif

diff --git a/mm/memblock.c b/mm/memblock.c
index aab566998b61e26596f2b15a5626f1034f95bd86..270b005ca9640f9107664424c4d00035dd2d00f5 100644 (file)
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -255,6 +255,7 @@ static void __init_memblock memblock_remove_region(struct memblock_type *type, u
                type->cnt = 1;
                type->regions[0].base = 0;
                type->regions[0].size = 0;
+               type->regions[0].flags = 0;
                memblock_set_region_node(&type->regions[0], MAX_NUMNODES);
        }
 }
@@ -405,7 +406,8 @@ static void __init_memblock memblock_merge_regions(struct memblock_type *type)
 
                if (this->base + this->size != next->base ||
                    memblock_get_region_node(this) !=
-                   memblock_get_region_node(next)) {
+                   memblock_get_region_node(next) ||
+                   this->flags != next->flags) {
                        BUG_ON(this->base + this->size > next->base);
                        i++;
                        continue;
@@ -425,13 +427,15 @@ static void __init_memblock memblock_merge_regions(struct memblock_type *type)
  * @base:      base address of the new region
  * @size:      size of the new region
  * @nid:       node id of the new region
+ * @flags:     flags of the new region
  *
  * Insert new memblock region [@base,@base+@size) into @type at @idx.
  * @type must already have extra room to accomodate the new region.
  */
 static void __init_memblock memblock_insert_region(struct memblock_type *type,
                                                   int idx, phys_addr_t base,
-                                                  phys_addr_t size, int nid)
+                                                  phys_addr_t size,
+                                                  int nid, unsigned long flags)
 {
        struct memblock_region *rgn = &type->regions[idx];
 
@@ -439,6 +443,7 @@ static void __init_memblock memblock_insert_region(struct memblock_type *type,
        memmove(rgn + 1, rgn, (type->cnt - idx) * sizeof(*rgn));
        rgn->base = base;
        rgn->size = size;
+       rgn->flags = flags;
        memblock_set_region_node(rgn, nid);
        type->cnt++;
        type->total_size += size;
@@ -450,6 +455,7 @@ static void __init_memblock memblock_insert_region(struct memblock_type *type,
  * @base: base address of the new region
  * @size: size of the new region
  * @nid: nid of the new region
+ * @flags: flags of the new region
  *
  * Add new memblock region [@base,@base+@size) into @type.  The new region
  * is allowed to overlap with existing ones - overlaps don't affect already
@@ -460,7 +466,8 @@ static void __init_memblock memblock_insert_region(struct memblock_type *type,
  * 0 on success, -errno on failure.
  */
 static int __init_memblock memblock_add_region(struct memblock_type *type,
-                               phys_addr_t base, phys_addr_t size, int nid)
+                               phys_addr_t base, phys_addr_t size,
+                               int nid, unsigned long flags)
 {
        bool insert = false;
        phys_addr_t obase = base;
@@ -475,6 +482,7 @@ static int __init_memblock memblock_add_region(struct memblock_type *type,
                WARN_ON(type->cnt != 1 || type->total_size);
                type->regions[0].base = base;
                type->regions[0].size = size;
+               type->regions[0].flags = flags;
                memblock_set_region_node(&type->regions[0], nid);
                type->total_size = size;
                return 0;
@@ -505,7 +513,8 @@ repeat:
                        nr_new++;
                        if (insert)
                                memblock_insert_region(type, i++, base,
-                                                      rbase - base, nid);
+                                                      rbase - base, nid,
+                                                      flags);
                }
                /* area below @rend is dealt with, forget about it */
                base = min(rend, end);
@@ -515,7 +524,8 @@ repeat:
        if (base < end) {
                nr_new++;
                if (insert)
-                       memblock_insert_region(type, i, base, end - base, nid);
+                       memblock_insert_region(type, i, base, end - base,
+                                              nid, flags);
        }
 
        /*
@@ -537,12 +547,13 @@ repeat:
 int __init_memblock memblock_add_node(phys_addr_t base, phys_addr_t size,
                                       int nid)
 {
-       return memblock_add_region(&memblock.memory, base, size, nid);
+       return memblock_add_region(&memblock.memory, base, size, nid, 0);
 }
 
 int __init_memblock memblock_add(phys_addr_t base, phys_addr_t size)
 {
-       return memblock_add_region(&memblock.memory, base, size, MAX_NUMNODES);
+       return memblock_add_region(&memblock.memory, base, size,
+                                  MAX_NUMNODES, 0);
 }
 
 /**
@@ -597,7 +608,8 @@ static int __init_memblock memblock_isolate_range(struct memblock_type *type,
                        rgn->size -= base - rbase;
                        type->total_size -= base - rbase;
                        memblock_insert_region(type, i, rbase, base - rbase,
-                                              memblock_get_region_node(rgn));
+                                              memblock_get_region_node(rgn),
+                                              rgn->flags);
                } else if (rend > end) {
                        /*
                         * @rgn intersects from above.  Split and redo the
@@ -607,7 +619,8 @@ static int __init_memblock memblock_isolate_range(struct memblock_type *type,
                        rgn->size -= end - rbase;
                        type->total_size -= end - rbase;
                        memblock_insert_region(type, i--, rbase, end - rbase,
-                                              memblock_get_region_node(rgn));
+                                              memblock_get_region_node(rgn),
+                                              rgn->flags);
                } else {
                        /* @rgn is fully contained, record it */
                        if (!*end_rgn)
@@ -649,16 +662,24 @@ int __init_memblock memblock_free(phys_addr_t base, phys_addr_t size)
        return __memblock_remove(&memblock.reserved, base, size);
 }
 
-int __init_memblock memblock_reserve(phys_addr_t base, phys_addr_t size)
+static int __init_memblock memblock_reserve_region(phys_addr_t base,
+                                                  phys_addr_t size,
+                                                  int nid,
+                                                  unsigned long flags)
 {
        struct memblock_type *_rgn = &memblock.reserved;
 
-       memblock_dbg("memblock_reserve: [%#016llx-%#016llx] %pF\n",
+       memblock_dbg("memblock_reserve: [%#016llx-%#016llx] flags %#02lx %pF\n",
                     (unsigned long long)base,
                     (unsigned long long)base + size - 1,
-                    (void *)_RET_IP_);
+                    flags, (void *)_RET_IP_);
+
+       return memblock_add_region(_rgn, base, size, nid, flags);
+}
 
-       return memblock_add_region(_rgn, base, size, MAX_NUMNODES);
+int __init_memblock memblock_reserve(phys_addr_t base, phys_addr_t size)
+{
+       return memblock_reserve_region(base, size, MAX_NUMNODES, 0);
 }
 
 /**
@@ -1101,6 +1122,7 @@ void __init_memblock memblock_set_current_limit(phys_addr_t limit)
 static void __init_memblock memblock_dump(struct memblock_type *type, char *name)
 {
        unsigned long long base, size;
+       unsigned long flags;
        int i;
 
        pr_info(" %s.cnt  = 0x%lx\n", name, type->cnt);
@@ -1111,13 +1133,14 @@ static void __init_memblock memblock_dump(struct memblock_type *type, char *name
 
                base = rgn->base;
                size = rgn->size;
+               flags = rgn->flags;
 #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
                if (memblock_get_region_node(rgn) != MAX_NUMNODES)
                        snprintf(nid_buf, sizeof(nid_buf), " on node %d",
                                 memblock_get_region_node(rgn));
 #endif
-               pr_info(" %s[%#x]\t[%#016llx-%#016llx], %#llx bytes%s\n",
-                       name, i, base, base + size - 1, size, nid_buf);
+               pr_info(" %s[%#x]\t[%#016llx-%#016llx], %#llx bytes%s flags: %#lx\n",
+                       name, i, base, base + size - 1, size, nid_buf, flags);
        }
 }