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>
diff --git a/mm/bootmem.c b/mm/bootmem.c
index bde170dd..fda01a2 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 @@
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(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 8c9b346..f2cd745 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3667,46 +3667,26 @@
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 == MEMBLOCK_ERROR)
+ return NULL;
- 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;
- }
-
- 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 aa33fd6..29d6cbf 100644
--- a/mm/sparse-vmemmap.c
+++ b/mm/sparse-vmemmap.c
@@ -220,18 +220,7 @@
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;
}