x86: Use memblock to replace early_res

1. replace find_e820_area with memblock_find_in_range
2. replace reserve_early with memblock_x86_reserve_range
3. replace free_early with memblock_x86_free_range.
4. NO_BOOTMEM will switch to use memblock too.
5. use _e820, _early wrap in the patch, in following patch, will
   replace them all
6. because memblock_x86_free_range support partial free, we can remove some special care
7. Need to make sure that memblock_find_in_range() is called after memblock_x86_fill()
   so adjust some calling later in setup.c::setup_arch()
   -- corruption_check and mptable_update

-v2: Move reserve_brk() early
    Before fill_memblock_area, to avoid overlap between brk and memblock_find_in_range()
    that could happen We have more then 128 RAM entry in E820 tables, and
    memblock_x86_fill() could use memblock_find_in_range() to find a new place for
    memblock.memory.region array.
    and We don't need to use extend_brk() after fill_memblock_area()
    So move reserve_brk() early before fill_memblock_area().
-v3: Move find_smp_config early
    To make sure memblock_find_in_range not find wrong place, if BIOS doesn't put mptable
    in right place.
-v4: Treat RESERVED_KERN as RAM in memblock.memory. and they are already in
    memblock.reserved already..
    use __NOT_KEEP_MEMBLOCK to make sure memblock related code could be freed later.
-v5: Generic version __memblock_find_in_range() is going from high to low, and for 32bit
    active_region for 32bit does include high pages
    need to replace the limit with memblock.default_alloc_limit, aka get_max_mapped()
-v6: Use current_limit instead
-v7: check with MEMBLOCK_ERROR instead of -1ULL or -1L
-v8: Set memblock_can_resize early to handle EFI with more RAM entries
-v9: update after kmemleak changes in mainline

Suggested-by: David S. Miller <davem@davemloft.net>
Suggested-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Suggested-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>

3 files changed, 18 insertions, 46 deletions

diff --git a/mm/bootmem.c b/mm/bootmem.c
index bde170dd2fd..fda01a2c31a 100644
--- a/mm/bootmem.c
+++ b/mm/bootmem.c
@@ -15,6 +15,7 @@
 #include <linux/module.h>
 #include <linux/kmemleak.h>
 #include <linux/range.h>
+#include <linux/memblock.h>
 
 #include <asm/bug.h>
 #include <asm/io.h>
@@ -434,6 +435,7 @@ void __init free_bootmem_node(pg_data_t *pgdat, unsigned long physaddr,
 			      unsigned long size)
 {
 #ifdef CONFIG_NO_BOOTMEM
+	kmemleak_free_part(__va(physaddr), size);
 	free_early(physaddr, physaddr + size);
 #else
 	unsigned long start, end;
@@ -459,6 +461,7 @@ void __init free_bootmem_node(pg_data_t *pgdat, unsigned long physaddr,
 void __init free_bootmem(unsigned long addr, unsigned long size)
 {
 #ifdef CONFIG_NO_BOOTMEM
+	kmemleak_free_part(__va(addr), size);
 	free_early(addr, addr + size);
 #else
 	unsigned long start, end;
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 8c9b34674d8..f2cd7450fa7 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3667,46 +3667,26 @@ int __init add_from_early_node_map(struct range *range, int az,
 void * __init __alloc_memory_core_early(int nid, u64 size, u64 align,
 					u64 goal, u64 limit)
 {
-	int i;
 	void *ptr;
+	u64 addr;
 
-	if (limit > get_max_mapped())
-		limit = get_max_mapped();
+	if (limit > memblock.current_limit)
+		limit = memblock.current_limit;
 
-	/* need to go over early_node_map to find out good range for node */
-	for_each_active_range_index_in_nid(i, nid) {
-		u64 addr;
-		u64 ei_start, ei_last;
+	addr = find_memory_core_early(nid, size, align, goal, limit);
 
-		ei_last = early_node_map[i].end_pfn;
-		ei_last <<= PAGE_SHIFT;
-		ei_start = early_node_map[i].start_pfn;
-		ei_start <<= PAGE_SHIFT;
-		addr = find_early_area(ei_start, ei_last,
-					 goal, limit, size, align);
-
-		if (addr == -1ULL)
-			continue;
-
-#if 0
-		printk(KERN_DEBUG "alloc (nid=%d %llx - %llx) (%llx - %llx) %llx %llx => %llx\n",
-				nid,
-				ei_start, ei_last, goal, limit, size,
-				align, addr);
-#endif
-
-		ptr = phys_to_virt(addr);
-		memset(ptr, 0, size);
-		reserve_early_without_check(addr, addr + size, "BOOTMEM");
-		/*
-		 * The min_count is set to 0 so that bootmem allocated blocks
-		 * are never reported as leaks.
-		 */
-		kmemleak_alloc(ptr, size, 0, 0);
-		return ptr;
-	}
+	if (addr == MEMBLOCK_ERROR)
+		return NULL;
 
-	return NULL;
+	ptr = phys_to_virt(addr);
+	memset(ptr, 0, size);
+	memblock_x86_reserve_range(addr, addr + size, "BOOTMEM");
+	/*
+	 * The min_count is set to 0 so that bootmem allocated blocks
+	 * are never reported as leaks.
+	 */
+	kmemleak_alloc(ptr, size, 0, 0);
+	return ptr;
 }
 #endif
 
diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c
index aa33fd67fa4..29d6cbffb28 100644
--- a/mm/sparse-vmemmap.c
+++ b/mm/sparse-vmemmap.c
@@ -220,18 +220,7 @@ void __init sparse_mem_maps_populate_node(struct page **map_map,
 
 	if (vmemmap_buf_start) {
 		/* need to free left buf */
-#ifdef CONFIG_NO_BOOTMEM
-		free_early(__pa(vmemmap_buf_start), __pa(vmemmap_buf_end));
-		if (vmemmap_buf_start < vmemmap_buf) {
-			char name[15];
-
-			snprintf(name, sizeof(name), "MEMMAP %d", nodeid);
-			reserve_early_without_check(__pa(vmemmap_buf_start),
-						    __pa(vmemmap_buf), name);
-		}
-#else
 		free_bootmem(__pa(vmemmap_buf), vmemmap_buf_end - vmemmap_buf);
-#endif
 		vmemmap_buf = NULL;
 		vmemmap_buf_end = NULL;
 	}