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>

8 files changed, 107 insertions, 137 deletions

diff --git a/arch/x86/kernel/check.c b/arch/x86/kernel/check.c
index fc999e6..13a3891 100644
--- a/arch/x86/kernel/check.c
+++ b/arch/x86/kernel/check.c
@@ -2,7 +2,8 @@
 #include <linux/sched.h>
 #include <linux/kthread.h>
 #include <linux/workqueue.h>
-#include <asm/e820.h>
+#include <linux/memblock.h>
+
 #include <asm/proto.h>
 
 /*
@@ -18,10 +19,12 @@ static int __read_mostly memory_corruption_check = -1;
 static unsigned __read_mostly corruption_check_size = 64*1024;
 static unsigned __read_mostly corruption_check_period = 60; /* seconds */
 
-static struct e820entry scan_areas[MAX_SCAN_AREAS];
+static struct scan_area {
+	u64 addr;
+	u64 size;
+} scan_areas[MAX_SCAN_AREAS];
 static int num_scan_areas;
 
-
 static __init int set_corruption_check(char *arg)
 {
 	char *end;
@@ -81,9 +84,9 @@ void __init setup_bios_corruption_check(void)
 
 	while (addr < corruption_check_size && num_scan_areas < MAX_SCAN_AREAS) {
 		u64 size;
-		addr = find_e820_area_size(addr, &size, PAGE_SIZE);
+		addr = memblock_x86_find_in_range_size(addr, &size, PAGE_SIZE);
 
-		if (!(addr + 1))
+		if (addr == MEMBLOCK_ERROR)
 			break;
 
 		if (addr >= corruption_check_size)
@@ -92,7 +95,7 @@ void __init setup_bios_corruption_check(void)
 		if ((addr + size) > corruption_check_size)
 			size = corruption_check_size - addr;
 
-		e820_update_range(addr, size, E820_RAM, E820_RESERVED);
+		memblock_x86_reserve_range(addr, addr + size, "SCAN RAM");
 		scan_areas[num_scan_areas].addr = addr;
 		scan_areas[num_scan_areas].size = size;
 		num_scan_areas++;
@@ -105,7 +108,6 @@ void __init setup_bios_corruption_check(void)
 
 	printk(KERN_INFO "Scanning %d areas for low memory corruption\n",
 	       num_scan_areas);
-	update_e820();
 }
 
 
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 0d6fc71..a9221d1 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -15,6 +15,7 @@
 #include <linux/pfn.h>
 #include <linux/suspend.h>
 #include <linux/firmware-map.h>
+#include <linux/memblock.h>
 
 #include <asm/e820.h>
 #include <asm/proto.h>
@@ -742,69 +743,29 @@ core_initcall(e820_mark_nvs_memory);
  */
 u64 __init find_e820_area(u64 start, u64 end, u64 size, u64 align)
 {
-	int i;
-
-	for (i = 0; i < e820.nr_map; i++) {
-		struct e820entry *ei = &e820.map[i];
-		u64 addr;
-		u64 ei_start, ei_last;
+	u64 mem = memblock_find_in_range(start, end, size, align);
 
-		if (ei->type != E820_RAM)
-			continue;
-
-		ei_last = ei->addr + ei->size;
-		ei_start = ei->addr;
-		addr = find_early_area(ei_start, ei_last, start, end,
-					 size, align);
-
-		if (addr != -1ULL)
-			return addr;
-	}
-	return -1ULL;
-}
+	if (mem == MEMBLOCK_ERROR)
+		return -1ULL;
 
-u64 __init find_fw_memmap_area(u64 start, u64 end, u64 size, u64 align)
-{
-	return find_e820_area(start, end, size, align);
+	return mem;
 }
 
-u64 __init get_max_mapped(void)
-{
-	u64 end = max_pfn_mapped;
-
-	end <<= PAGE_SHIFT;
-
-	return end;
-}
 /*
  * Find next free range after *start
  */
 u64 __init find_e820_area_size(u64 start, u64 *sizep, u64 align)
 {
-	int i;
+	u64 mem = memblock_x86_find_in_range_size(start, sizep, align);
 
-	for (i = 0; i < e820.nr_map; i++) {
-		struct e820entry *ei = &e820.map[i];
-		u64 addr;
-		u64 ei_start, ei_last;
-
-		if (ei->type != E820_RAM)
-			continue;
-
-		ei_last = ei->addr + ei->size;
-		ei_start = ei->addr;
-		addr = find_early_area_size(ei_start, ei_last, start,
-					 sizep, align);
+	if (mem == MEMBLOCK_ERROR)
+		return -1ULL
 
-		if (addr != -1ULL)
-			return addr;
-	}
-
-	return -1ULL;
+	return mem;
 }
 
 /*
- * pre allocated 4k and reserved it in e820
+ * pre allocated 4k and reserved it in memblock and e820_saved
  */
 u64 __init early_reserve_e820(u64 startt, u64 sizet, u64 align)
 {
@@ -813,8 +774,8 @@ u64 __init early_reserve_e820(u64 startt, u64 sizet, u64 align)
 	u64 start;
 
 	for (start = startt; ; start += size) {
-		start = find_e820_area_size(start, &size, align);
-		if (!(start + 1))
+		start = memblock_x86_find_in_range_size(start, &size, align);
+		if (start == MEMBLOCK_ERROR)
 			return 0;
 		if (size >= sizet)
 			break;
@@ -830,10 +791,9 @@ u64 __init early_reserve_e820(u64 startt, u64 sizet, u64 align)
 	addr = round_down(start + size - sizet, align);
 	if (addr < start)
 		return 0;
-	e820_update_range(addr, sizet, E820_RAM, E820_RESERVED);
+	memblock_x86_reserve_range(addr, addr + sizet, "new next");
 	e820_update_range_saved(addr, sizet, E820_RAM, E820_RESERVED);
-	printk(KERN_INFO "update e820 for early_reserve_e820\n");
-	update_e820();
+	printk(KERN_INFO "update e820_saved for early_reserve_e820\n");
 	update_e820_saved();
 
 	return addr;
@@ -895,52 +855,12 @@ unsigned long __init e820_end_of_low_ram_pfn(void)
 {
 	return e820_end_pfn(1UL<<(32 - PAGE_SHIFT), E820_RAM);
 }
-/*
- * Finds an active region in the address range from start_pfn to last_pfn and
- * returns its range in ei_startpfn and ei_endpfn for the e820 entry.
- */
-int __init e820_find_active_region(const struct e820entry *ei,
-				  unsigned long start_pfn,
-				  unsigned long last_pfn,
-				  unsigned long *ei_startpfn,
-				  unsigned long *ei_endpfn)
-{
-	u64 align = PAGE_SIZE;
-
-	*ei_startpfn = round_up(ei->addr, align) >> PAGE_SHIFT;
-	*ei_endpfn = round_down(ei->addr + ei->size, align) >> PAGE_SHIFT;
-
-	/* Skip map entries smaller than a page */
-	if (*ei_startpfn >= *ei_endpfn)
-		return 0;
-
-	/* Skip if map is outside the node */
-	if (ei->type != E820_RAM || *ei_endpfn <= start_pfn ||
-				    *ei_startpfn >= last_pfn)
-		return 0;
-
-	/* Check for overlaps */
-	if (*ei_startpfn < start_pfn)
-		*ei_startpfn = start_pfn;
-	if (*ei_endpfn > last_pfn)
-		*ei_endpfn = last_pfn;
-
-	return 1;
-}
 
 /* Walk the e820 map and register active regions within a node */
 void __init e820_register_active_regions(int nid, unsigned long start_pfn,
 					 unsigned long last_pfn)
 {
-	unsigned long ei_startpfn;
-	unsigned long ei_endpfn;
-	int i;
-
-	for (i = 0; i < e820.nr_map; i++)
-		if (e820_find_active_region(&e820.map[i],
-					    start_pfn, last_pfn,
-					    &ei_startpfn, &ei_endpfn))
-			add_active_range(nid, ei_startpfn, ei_endpfn);
+	memblock_x86_register_active_regions(nid, start_pfn, last_pfn);
 }
 
 /*
@@ -950,18 +870,16 @@ void __init e820_register_active_regions(int nid, unsigned long start_pfn,
  */
 u64 __init e820_hole_size(u64 start, u64 end)
 {
-	unsigned long start_pfn = start >> PAGE_SHIFT;
-	unsigned long last_pfn = end >> PAGE_SHIFT;
-	unsigned long ei_startpfn, ei_endpfn, ram = 0;
-	int i;
+	return memblock_x86_hole_size(start, end);
+}
 
-	for (i = 0; i < e820.nr_map; i++) {
-		if (e820_find_active_region(&e820.map[i],
-					    start_pfn, last_pfn,
-					    &ei_startpfn, &ei_endpfn))
-			ram += ei_endpfn - ei_startpfn;
-	}
-	return end - start - ((u64)ram << PAGE_SHIFT);
+void reserve_early(u64 start, u64 end, char *name)
+{
+	memblock_x86_reserve_range(start, end, name);
+}
+void free_early(u64 start, u64 end)
+{
+	memblock_x86_free_range(start, end);
 }
 
 static void early_panic(char *msg)
@@ -1210,3 +1128,32 @@ void __init setup_memory_map(void)
 	printk(KERN_INFO "BIOS-provided physical RAM map:\n");
 	e820_print_map(who);
 }
+
+void __init memblock_x86_fill(void)
+{
+	int i;
+	u64 end;
+
+	/*
+	 * EFI may have more than 128 entries
+	 * We are safe to enable resizing, beause memblock_x86_fill()
+	 * is rather later for x86
+	 */
+	memblock_can_resize = 1;
+
+	for (i = 0; i < e820.nr_map; i++) {
+		struct e820entry *ei = &e820.map[i];
+
+		end = ei->addr + ei->size;
+		if (end != (resource_size_t)end)
+			continue;
+
+		if (ei->type != E820_RAM && ei->type != E820_RESERVED_KERN)
+			continue;
+
+		memblock_add(ei->addr, ei->size);
+	}
+
+	memblock_analyze();
+	memblock_dump_all();
+}
diff --git a/arch/x86/kernel/head.c b/arch/x86/kernel/head.c
index 3e66bd3..af0699b 100644
--- a/arch/x86/kernel/head.c
+++ b/arch/x86/kernel/head.c
@@ -1,5 +1,6 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
+#include <linux/memblock.h>
 
 #include <asm/setup.h>
 #include <asm/bios_ebda.h>
@@ -51,5 +52,5 @@ void __init reserve_ebda_region(void)
 		lowmem = 0x9f000;
 
 	/* reserve all memory between lowmem and the 1MB mark */
-	reserve_early_overlap_ok(lowmem, 0x100000, "BIOS reserved");
+	memblock_x86_reserve_range(lowmem, 0x100000, "* BIOS reserved");
 }
diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c
index b2e2460..da60aa8 100644
--- a/arch/x86/kernel/head32.c
+++ b/arch/x86/kernel/head32.c
@@ -8,6 +8,7 @@
 #include <linux/init.h>
 #include <linux/start_kernel.h>
 #include <linux/mm.h>
+#include <linux/memblock.h>
 
 #include <asm/setup.h>
 #include <asm/sections.h>
@@ -30,14 +31,15 @@ static void __init i386_default_early_setup(void)
 
 void __init i386_start_kernel(void)
 {
+	memblock_init();
+
 #ifdef CONFIG_X86_TRAMPOLINE
 	/*
 	 * But first pinch a few for the stack/trampoline stuff
 	 * FIXME: Don't need the extra page at 4K, but need to fix
 	 * trampoline before removing it. (see the GDT stuff)
 	 */
-	reserve_early_overlap_ok(PAGE_SIZE, PAGE_SIZE + PAGE_SIZE,
-					 "EX TRAMPOLINE");
+	memblock_x86_reserve_range(PAGE_SIZE, PAGE_SIZE + PAGE_SIZE, "EX TRAMPOLINE");
 #endif
 
 	reserve_early(__pa_symbol(&_text), __pa_symbol(&__bss_stop), "TEXT DATA BSS");
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 7147143..8ee930f 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -12,6 +12,7 @@
 #include <linux/percpu.h>
 #include <linux/start_kernel.h>
 #include <linux/io.h>
+#include <linux/memblock.h>
 
 #include <asm/processor.h>
 #include <asm/proto.h>
@@ -98,6 +99,8 @@ void __init x86_64_start_reservations(char *real_mode_data)
 {
 	copy_bootdata(__va(real_mode_data));
 
+	memblock_init();
+
 	reserve_early(__pa_symbol(&_text), __pa_symbol(&__bss_stop), "TEXT DATA BSS");
 
 #ifdef CONFIG_BLK_DEV_INITRD
diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c
index d86dbf7..8252545 100644
--- a/arch/x86/kernel/mpparse.c
+++ b/arch/x86/kernel/mpparse.c
@@ -11,6 +11,7 @@
 #include <linux/init.h>
 #include <linux/delay.h>
 #include <linux/bootmem.h>
+#include <linux/memblock.h>
 #include <linux/kernel_stat.h>
 #include <linux/mc146818rtc.h>
 #include <linux/bitops.h>
@@ -641,7 +642,7 @@ static void __init smp_reserve_memory(struct mpf_intel *mpf)
 {
 	unsigned long size = get_mpc_size(mpf->physptr);
 
-	reserve_early_overlap_ok(mpf->physptr, mpf->physptr+size, "MP-table mpc");
+	memblock_x86_reserve_range(mpf->physptr, mpf->physptr+size, "* MP-table mpc");
 }
 
 static int __init smp_scan_config(unsigned long base, unsigned long length)
@@ -670,7 +671,7 @@ static int __init smp_scan_config(unsigned long base, unsigned long length)
 			       mpf, (u64)virt_to_phys(mpf));
 
 			mem = virt_to_phys(mpf);
-			reserve_early_overlap_ok(mem, mem + sizeof(*mpf), "MP-table mpf");
+			memblock_x86_reserve_range(mem, mem + sizeof(*mpf), "* MP-table mpf");
 			if (mpf->physptr)
 				smp_reserve_memory(mpf);
 
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index b4ae4ac..bbe0aaf 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -31,6 +31,7 @@
 #include <linux/apm_bios.h>
 #include <linux/initrd.h>
 #include <linux/bootmem.h>
+#include <linux/memblock.h>
 #include <linux/seq_file.h>
 #include <linux/console.h>
 #include <linux/mca.h>
@@ -614,7 +615,7 @@ static __init void reserve_ibft_region(void)
 	addr = find_ibft_region(&size);
 
 	if (size)
-		reserve_early_overlap_ok(addr, addr + size, "ibft");
+		memblock_x86_reserve_range(addr, addr + size, "* ibft");
 }
 
 #ifdef CONFIG_X86_RESERVE_LOW_64K
@@ -708,6 +709,15 @@ static void __init trim_bios_range(void)
 	sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
 }
 
+static u64 __init get_max_mapped(void)
+{
+	u64 end = max_pfn_mapped;
+
+	end <<= PAGE_SHIFT;
+
+	return end;
+}
+
 /*
  * Determine if we were loaded by an EFI loader.  If so, then we have also been
  * passed the efi memmap, systab, etc., so we should use these data structures
@@ -891,8 +901,6 @@ void __init setup_arch(char **cmdline_p)
 	 */
 	max_pfn = e820_end_of_ram_pfn();
 
-	/* preallocate 4k for mptable mpc */
-	early_reserve_e820_mpc_new();
 	/* update e820 for memory not covered by WB MTRRs */
 	mtrr_bp_init();
 	if (mtrr_trim_uncached_memory(max_pfn))
@@ -917,15 +925,6 @@ void __init setup_arch(char **cmdline_p)
 	max_pfn_mapped = KERNEL_IMAGE_SIZE >> PAGE_SHIFT;
 #endif
 
-#ifdef CONFIG_X86_CHECK_BIOS_CORRUPTION
-	setup_bios_corruption_check();
-#endif
-
-	printk(KERN_DEBUG "initial memory mapped : 0 - %08lx\n",
-			max_pfn_mapped<<PAGE_SHIFT);
-
-	reserve_brk();
-
 	/*
 	 * Find and reserve possible boot-time SMP configuration:
 	 */
@@ -933,6 +932,26 @@ void __init setup_arch(char **cmdline_p)
 
 	reserve_ibft_region();
 
+	/*
+	 * Need to conclude brk, before memblock_x86_fill()
+	 *  it could use memblock_find_in_range, could overlap with
+	 *  brk area.
+	 */
+	reserve_brk();
+
+	memblock.current_limit = get_max_mapped();
+	memblock_x86_fill();
+
+	/* preallocate 4k for mptable mpc */
+	early_reserve_e820_mpc_new();
+
+#ifdef CONFIG_X86_CHECK_BIOS_CORRUPTION
+	setup_bios_corruption_check();
+#endif
+
+	printk(KERN_DEBUG "initial memory mapped : 0 - %08lx\n",
+			max_pfn_mapped<<PAGE_SHIFT);
+
 	reserve_trampoline_memory();
 
 #ifdef CONFIG_ACPI_SLEEP
@@ -956,6 +975,7 @@ void __init setup_arch(char **cmdline_p)
 		max_low_pfn = max_pfn;
 	}
 #endif
+	memblock.current_limit = get_max_mapped();
 
 	/*
 	 * NOTE: On x86-32, only from this point on, fixmaps are ready for use.
@@ -995,7 +1015,7 @@ void __init setup_arch(char **cmdline_p)
 
 	initmem_init(0, max_pfn, acpi, k8);
 #ifndef CONFIG_NO_BOOTMEM
-	early_res_to_bootmem(0, max_low_pfn<<PAGE_SHIFT);
+	memblock_x86_to_bootmem(0, max_low_pfn<<PAGE_SHIFT);
 #endif
 
 	dma32_reserve_bootmem();
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index a60df9a..42e2633 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -131,13 +131,7 @@ static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, size_t align)
 
 static void __init pcpu_fc_free(void *ptr, size_t size)
 {
-#ifdef CONFIG_NO_BOOTMEM
-	u64 start = __pa(ptr);
-	u64 end = start + size;
-	free_early_partial(start, end);
-#else
 	free_bootmem(__pa(ptr), size);
-#endif
 }
 
 static int __init pcpu_cpu_distance(unsigned int from, unsigned int to)