memory-hotplug: remove /sys/firmware/memmap/X sysfs

[linux-imx.git] / mm / memory_hotplug.c

diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index d04ed87bfacbab59953859f9e860acae3f6335ab..a776dbf3fa0093dbe39b9c15aea51501c5216a03 100644 (file)
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -901,8 +901,7 @@ error:
        /* rollback pgdat allocation and others */
        if (new_pgdat)
                rollback_node_hotadd(nid, pgdat);
-       if (res)
-               release_memory_resource(res);
+       release_memory_resource(res);
 
 out:
        unlock_memory_hotplug();
@@ -1381,17 +1380,26 @@ int offline_pages(unsigned long start_pfn, unsigned long nr_pages)
        return __offline_pages(start_pfn, start_pfn + nr_pages, 120 * HZ);
 }
 
-int remove_memory(u64 start, u64 size)
+/**
+ * walk_memory_range - walks through all mem sections in [start_pfn, end_pfn)
+ * @start_pfn: start pfn of the memory range
+ * @end_pfn: end pft of the memory range
+ * @arg: argument passed to func
+ * @func: callback for each memory section walked
+ *
+ * This function walks through all present mem sections in range
+ * [start_pfn, end_pfn) and call func on each mem section.
+ *
+ * Returns the return value of func.
+ */
+static int walk_memory_range(unsigned long start_pfn, unsigned long end_pfn,
+               void *arg, int (*func)(struct memory_block *, void *))
 {
        struct memory_block *mem = NULL;
        struct mem_section *section;
-       unsigned long start_pfn, end_pfn;
        unsigned long pfn, section_nr;
        int ret;
 
-       start_pfn = PFN_DOWN(start);
-       end_pfn = start_pfn + PFN_DOWN(size);
-
        for (pfn = start_pfn; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
                section_nr = pfn_to_section_nr(pfn);
                if (!present_section_nr(section_nr))
@@ -1408,7 +1416,7 @@ int remove_memory(u64 start, u64 size)
                if (!mem)
                        continue;
 
-               ret = offline_memory_block(mem);
+               ret = func(mem, arg);
                if (ret) {
                        kobject_put(&mem->dev.kobj);
                        return ret;
@@ -1420,6 +1428,95 @@ int remove_memory(u64 start, u64 size)
 
        return 0;
 }
+
+/**
+ * offline_memory_block_cb - callback function for offlining memory block
+ * @mem: the memory block to be offlined
+ * @arg: buffer to hold error msg
+ *
+ * Always return 0, and put the error msg in arg if any.
+ */
+static int offline_memory_block_cb(struct memory_block *mem, void *arg)
+{
+       int *ret = arg;
+       int error = offline_memory_block(mem);
+
+       if (error != 0 && *ret == 0)
+               *ret = error;
+
+       return 0;
+}
+
+static int is_memblock_offlined_cb(struct memory_block *mem, void *arg)
+{
+       int ret = !is_memblock_offlined(mem);
+
+       if (unlikely(ret))
+               pr_warn("removing memory fails, because memory "
+                       "[%#010llx-%#010llx] is onlined\n",
+                       PFN_PHYS(section_nr_to_pfn(mem->start_section_nr)),
+                       PFN_PHYS(section_nr_to_pfn(mem->end_section_nr + 1))-1);
+
+       return ret;
+}
+
+int __ref remove_memory(u64 start, u64 size)
+{
+       unsigned long start_pfn, end_pfn;
+       int ret = 0;
+       int retry = 1;
+
+       start_pfn = PFN_DOWN(start);
+       end_pfn = start_pfn + PFN_DOWN(size);
+
+       /*
+        * When CONFIG_MEMCG is on, one memory block may be used by other
+        * blocks to store page cgroup when onlining pages. But we don't know
+        * in what order pages are onlined. So we iterate twice to offline
+        * memory:
+        * 1st iterate: offline every non primary memory block.
+        * 2nd iterate: offline primary (i.e. first added) memory block.
+        */
+repeat:
+       walk_memory_range(start_pfn, end_pfn, &ret,
+                         offline_memory_block_cb);
+       if (ret) {
+               if (!retry)
+                       return ret;
+
+               retry = 0;
+               ret = 0;
+               goto repeat;
+       }
+
+       lock_memory_hotplug();
+
+       /*
+        * we have offlined all memory blocks like this:
+        *   1. lock memory hotplug
+        *   2. offline a memory block
+        *   3. unlock memory hotplug
+        *
+        * repeat step1-3 to offline the memory block. All memory blocks
+        * must be offlined before removing memory. But we don't hold the
+        * lock in the whole operation. So we should check whether all
+        * memory blocks are offlined.
+        */
+
+       ret = walk_memory_range(start_pfn, end_pfn, NULL,
+                               is_memblock_offlined_cb);
+       if (ret) {
+               unlock_memory_hotplug();
+               return ret;
+       }
+
+       /* remove memmap entry */
+       firmware_map_remove(start, start + size, "System RAM");
+
+       unlock_memory_hotplug();
+
+       return 0;
+}
 #else
 int offline_pages(unsigned long start_pfn, unsigned long nr_pages)
 {