[PATCH -v3 0/29] x86: use early_res instead of bootmem before slab

[PATCH -v3 0/29] x86: use early_res instead of bootmem before slab

[Yinghai Lu]

please check the patches regarding with early_res and bootmem

and at last it will use early_res instead of bootmem with x86 64bits

1-3 should be for 2.6.33

4 and 5: two are needed for some amd_bus.c/intel_bus.c cleaning up patches too.
so put other x86/pci related into this series, hope that is ok to Jesse.

-v2: allocate vmemmap on one node together, and also seperate early_res
-v3: make x86 32 bit support early_res to use bootmem too
     move related early_res to kernel/
     sparse vmemmap together: address Ingo.

Thanks

Yinghai

[PATCH 01/29] x86: fix size for ex trampoline with 32bit

[Yinghai Lu]

fix for error that is introduced by
| x86: Use find_e820() instead of hard coded trampoline address

it should end with PAGE_SIZE + PAGE_SIZE

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
---
 arch/x86/kernel/e820.c |    4 ++--
 1 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 05ed7ab..a1a7876 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -733,13 +733,13 @@ struct early_res {
 };
 static struct early_res early_res[MAX_EARLY_RES] __initdata = {
 	{ 0, PAGE_SIZE, "BIOS data page", 1 },	/* BIOS data page */
-#ifdef CONFIG_X86_32
+#if defined(CONFIG_X86_32) && defined(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)
 	 */
-	{ PAGE_SIZE, PAGE_SIZE, "EX TRAMPOLINE", 1 },
+	{ PAGE_SIZE, PAGE_SIZE + PAGE_SIZE, "EX TRAMPOLINE", 1 },
 #endif
 
 	{}
-- 
1.6.4.2

[PATCH 02/29] x86/pci: intel ioh bus num reg accessing fix

[Yinghai Lu]

it is above 0x100, so if mmconf is not enable, need to skip it

Reported-by: Jens Axboe <jens.axboe@oracle.com>
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
---
 arch/x86/pci/intel_bus.c |    4 ++++
 1 files changed, 4 insertions(+), 0 deletions(-)

diff --git a/arch/x86/pci/intel_bus.c b/arch/x86/pci/intel_bus.c
index b7a55dc..baf283a 100644
--- a/arch/x86/pci/intel_bus.c
+++ b/arch/x86/pci/intel_bus.c
@@ -49,6 +49,10 @@ static void __devinit pci_root_bus_res(struct pci_dev *dev)
 	u64 mmioh_base, mmioh_end;
 	int bus_base, bus_end;
 
+	/* some sys doesn't get mmconf enabled */
+	if (dev->cfg_size < 0x200)
+		return;
+
 	if (pci_root_num >= PCI_ROOT_NR) {
 		printk(KERN_DEBUG "intel_bus.c: PCI_ROOT_NR is too small\n");
 		return;
-- 
1.6.4.2

Re: [PATCH 02/29] x86/pci: intel ioh bus num reg accessing fix

[Konrad Rzeszutek Wilk]

On Sun, Jan 03, 2010 at 07:04:40PM -0800, Yinghai Lu wrote:
> it is above 0x100, so if mmconf is not enable, need to skip it
> 
> Reported-by: Jens Axboe <jens.axboe@oracle.com>
> Signed-off-by: Yinghai Lu <yinghai@kernel.org>
> ---
>  arch/x86/pci/intel_bus.c |    4 ++++
>  1 files changed, 4 insertions(+), 0 deletions(-)
> 
> diff --git a/arch/x86/pci/intel_bus.c b/arch/x86/pci/intel_bus.c
> index b7a55dc..baf283a 100644
> --- a/arch/x86/pci/intel_bus.c
> +++ b/arch/x86/pci/intel_bus.c
> @@ -49,6 +49,10 @@ static void __devinit pci_root_bus_res(struct pci_dev *dev)
>  	u64 mmioh_base, mmioh_end;
>  	int bus_base, bus_end;
>  
> +	/* some sys doesn't get mmconf enabled */
> +	if (dev->cfg_size < 0x200)

Here we check under the 512 index.. but the comment states
that the check should be above 256 index? Should the comment say
"it is above 0x200, so if mmconf.."?

[PATCH 03/29] x86/pci: don't check mmconf again if it is from MSR with amd faml0h

[Yinghai Lu]

for AMD Fam10h, it we read mmconf from MSR early, we should just trust it
because we check it and correct it already.

so skip the reject check there.

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
---
 arch/x86/pci/mmconfig-shared.c |   10 +++++++++-
 1 files changed, 9 insertions(+), 1 deletions(-)

diff --git a/arch/x86/pci/mmconfig-shared.c b/arch/x86/pci/mmconfig-shared.c
index b19d1e5..bcce99b 100644
--- a/arch/x86/pci/mmconfig-shared.c
+++ b/arch/x86/pci/mmconfig-shared.c
@@ -168,6 +168,7 @@ static const char __init *pci_mmcfg_intel_945(void)
 	return "Intel Corporation 945G/GZ/P/PL Express Memory Controller Hub";
 }
 
+static int __initdata amd_fam10h_mmconf_found_via_hostbridge;
 static const char __init *pci_mmcfg_amd_fam10h(void)
 {
 	u32 low, high, address;
@@ -215,6 +216,8 @@ static const char __init *pci_mmcfg_amd_fam10h(void)
 			return NULL;
 		}
 
+	amd_fam10h_mmconf_found_via_hostbridge = 1;
+
 	return "AMD Family 10h NB";
 }
 
@@ -606,7 +609,12 @@ static void __init __pci_mmcfg_init(int early)
 	if (!known_bridge)
 		acpi_sfi_table_parse(ACPI_SIG_MCFG, pci_parse_mcfg);
 
-	pci_mmcfg_reject_broken(early);
+	/*
+	 * if it is amd fam10h, and that is read from msr,
+	 * we don't need check them again.
+	 */
+	if (!amd_fam10h_mmconf_found_via_hostbridge)
+		pci_mmcfg_reject_broken(early);
 
 	if (list_empty(&pci_mmcfg_list))
 		return;
-- 
1.6.4.2

[PATCH 04/29] x86: move range related operation to one file

[Yinghai Lu]

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
---
 arch/x86/kernel/cpu/mtrr/cleanup.c |  180 +++---------------------------------
 arch/x86/kernel/mmconf-fam10h_64.c |    7 +-
 arch/x86/pci/amd_bus.c             |   70 ++------------
 include/linux/range.h              |   22 +++++
 kernel/Makefile                    |    2 +-
 kernel/range.c                     |  154 ++++++++++++++++++++++++++++++
 6 files changed, 205 insertions(+), 230 deletions(-)
 create mode 100644 include/linux/range.h
 create mode 100644 kernel/range.c

diff --git a/arch/x86/kernel/cpu/mtrr/cleanup.c b/arch/x86/kernel/cpu/mtrr/cleanup.c
index 09b1698..669da09 100644
--- a/arch/x86/kernel/cpu/mtrr/cleanup.c
+++ b/arch/x86/kernel/cpu/mtrr/cleanup.c
@@ -22,10 +22,10 @@
 #include <linux/pci.h>
 #include <linux/smp.h>
 #include <linux/cpu.h>
-#include <linux/sort.h>
 #include <linux/mutex.h>
 #include <linux/uaccess.h>
 #include <linux/kvm_para.h>
+#include <linux/range.h>
 
 #include <asm/processor.h>
 #include <asm/e820.h>
@@ -34,11 +34,6 @@
 
 #include "mtrr.h"
 
-struct res_range {
-	unsigned long	start;
-	unsigned long	end;
-};
-
 struct var_mtrr_range_state {
 	unsigned long	base_pfn;
 	unsigned long	size_pfn;
@@ -56,7 +51,7 @@ struct var_mtrr_state {
 /* Should be related to MTRR_VAR_RANGES nums */
 #define RANGE_NUM				256
 
-static struct res_range __initdata		range[RANGE_NUM];
+static struct range __initdata		range[RANGE_NUM];
 static int __initdata				nr_range;
 
 static struct var_mtrr_range_state __initdata	range_state[RANGE_NUM];
@@ -64,152 +59,11 @@ static struct var_mtrr_range_state __initdata	range_state[RANGE_NUM];
 static int __initdata debug_print;
 #define Dprintk(x...) do { if (debug_print) printk(KERN_DEBUG x); } while (0)
 
-
-static int __init
-add_range(struct res_range *range, int nr_range,
-	  unsigned long start, unsigned long end)
-{
-	/* Out of slots: */
-	if (nr_range >= RANGE_NUM)
-		return nr_range;
-
-	range[nr_range].start = start;
-	range[nr_range].end = end;
-
-	nr_range++;
-
-	return nr_range;
-}
-
-static int __init
-add_range_with_merge(struct res_range *range, int nr_range,
-		     unsigned long start, unsigned long end)
-{
-	int i;
-
-	/* Try to merge it with old one: */
-	for (i = 0; i < nr_range; i++) {
-		unsigned long final_start, final_end;
-		unsigned long common_start, common_end;
-
-		if (!range[i].end)
-			continue;
-
-		common_start = max(range[i].start, start);
-		common_end = min(range[i].end, end);
-		if (common_start > common_end + 1)
-			continue;
-
-		final_start = min(range[i].start, start);
-		final_end = max(range[i].end, end);
-
-		range[i].start = final_start;
-		range[i].end =  final_end;
-		return nr_range;
-	}
-
-	/* Need to add it: */
-	return add_range(range, nr_range, start, end);
-}
-
-static void __init
-subtract_range(struct res_range *range, unsigned long start, unsigned long end)
-{
-	int i, j;
-
-	for (j = 0; j < RANGE_NUM; j++) {
-		if (!range[j].end)
-			continue;
-
-		if (start <= range[j].start && end >= range[j].end) {
-			range[j].start = 0;
-			range[j].end = 0;
-			continue;
-		}
-
-		if (start <= range[j].start && end < range[j].end &&
-		    range[j].start < end + 1) {
-			range[j].start = end + 1;
-			continue;
-		}
-
-
-		if (start > range[j].start && end >= range[j].end &&
-		    range[j].end > start - 1) {
-			range[j].end = start - 1;
-			continue;
-		}
-
-		if (start > range[j].start && end < range[j].end) {
-			/* Find the new spare: */
-			for (i = 0; i < RANGE_NUM; i++) {
-				if (range[i].end == 0)
-					break;
-			}
-			if (i < RANGE_NUM) {
-				range[i].end = range[j].end;
-				range[i].start = end + 1;
-			} else {
-				printk(KERN_ERR "run of slot in ranges\n");
-			}
-			range[j].end = start - 1;
-			continue;
-		}
-	}
-}
-
-static int __init cmp_range(const void *x1, const void *x2)
-{
-	const struct res_range *r1 = x1;
-	const struct res_range *r2 = x2;
-	long start1, start2;
-
-	start1 = r1->start;
-	start2 = r2->start;
-
-	return start1 - start2;
-}
-
-static int __init clean_sort_range(struct res_range *range, int az)
-{
-	int i, j, k = az - 1, nr_range = 0;
-
-	for (i = 0; i < k; i++) {
-		if (range[i].end)
-			continue;
-		for (j = k; j > i; j--) {
-			if (range[j].end) {
-				k = j;
-				break;
-			}
-		}
-		if (j == i)
-			break;
-		range[i].start = range[k].start;
-		range[i].end   = range[k].end;
-		range[k].start = 0;
-		range[k].end   = 0;
-		k--;
-	}
-	/* count it */
-	for (i = 0; i < az; i++) {
-		if (!range[i].end) {
-			nr_range = i;
-			break;
-		}
-	}
-
-	/* sort them */
-	sort(range, nr_range, sizeof(struct res_range), cmp_range, NULL);
-
-	return nr_range;
-}
-
 #define BIOS_BUG_MSG KERN_WARNING \
 	"WARNING: BIOS bug: VAR MTRR %d contains strange UC entry under 1M, check with your system vendor!\n"
 
 static int __init
-x86_get_mtrr_mem_range(struct res_range *range, int nr_range,
+x86_get_mtrr_mem_range(struct range *range, int nr_range,
 		       unsigned long extra_remove_base,
 		       unsigned long extra_remove_size)
 {
@@ -223,13 +77,13 @@ x86_get_mtrr_mem_range(struct res_range *range, int nr_range,
 			continue;
 		base = range_state[i].base_pfn;
 		size = range_state[i].size_pfn;
-		nr_range = add_range_with_merge(range, nr_range, base,
-						base + size - 1);
+		nr_range = add_range_with_merge(range, RANGE_NUM, nr_range,
+						base, base + size - 1);
 	}
 	if (debug_print) {
 		printk(KERN_DEBUG "After WB checking\n");
 		for (i = 0; i < nr_range; i++)
-			printk(KERN_DEBUG "MTRR MAP PFN: %016lx - %016lx\n",
+			printk(KERN_DEBUG "MTRR MAP PFN: %016llx - %016llx\n",
 				 range[i].start, range[i].end + 1);
 	}
 
@@ -252,10 +106,10 @@ x86_get_mtrr_mem_range(struct res_range *range, int nr_range,
 			size -= (1<<(20-PAGE_SHIFT)) - base;
 			base = 1<<(20-PAGE_SHIFT);
 		}
-		subtract_range(range, base, base + size - 1);
+		subtract_range(range, RANGE_NUM, base, base + size - 1);
 	}
 	if (extra_remove_size)
-		subtract_range(range, extra_remove_base,
+		subtract_range(range, RANGE_NUM, extra_remove_base,
 				 extra_remove_base + extra_remove_size  - 1);
 
 	if  (debug_print) {
@@ -263,7 +117,7 @@ x86_get_mtrr_mem_range(struct res_range *range, int nr_range,
 		for (i = 0; i < RANGE_NUM; i++) {
 			if (!range[i].end)
 				continue;
-			printk(KERN_DEBUG "MTRR MAP PFN: %016lx - %016lx\n",
+			printk(KERN_DEBUG "MTRR MAP PFN: %016llx - %016llx\n",
 				 range[i].start, range[i].end + 1);
 		}
 	}
@@ -273,20 +127,16 @@ x86_get_mtrr_mem_range(struct res_range *range, int nr_range,
 	if  (debug_print) {
 		printk(KERN_DEBUG "After sorting\n");
 		for (i = 0; i < nr_range; i++)
-			printk(KERN_DEBUG "MTRR MAP PFN: %016lx - %016lx\n",
+			printk(KERN_DEBUG "MTRR MAP PFN: %016llx - %016llx\n",
 				 range[i].start, range[i].end + 1);
 	}
 
-	/* clear those is not used */
-	for (i = nr_range; i < RANGE_NUM; i++)
-		memset(&range[i], 0, sizeof(range[i]));
-
 	return nr_range;
 }
 
 #ifdef CONFIG_MTRR_SANITIZER
 
-static unsigned long __init sum_ranges(struct res_range *range, int nr_range)
+static unsigned long __init sum_ranges(struct range *range, int nr_range)
 {
 	unsigned long sum = 0;
 	int i;
@@ -621,7 +471,7 @@ static int __init parse_mtrr_spare_reg(char *arg)
 early_param("mtrr_spare_reg_nr", parse_mtrr_spare_reg);
 
 static int __init
-x86_setup_var_mtrrs(struct res_range *range, int nr_range,
+x86_setup_var_mtrrs(struct range *range, int nr_range,
 		    u64 chunk_size, u64 gran_size)
 {
 	struct var_mtrr_state var_state;
@@ -742,7 +592,7 @@ mtrr_calc_range_state(u64 chunk_size, u64 gran_size,
 		      unsigned long x_remove_base,
 		      unsigned long x_remove_size, int i)
 {
-	static struct res_range range_new[RANGE_NUM];
+	static struct range range_new[RANGE_NUM];
 	unsigned long range_sums_new;
 	static int nr_range_new;
 	int num_reg;
@@ -869,10 +719,10 @@ int __init mtrr_cleanup(unsigned address_bits)
 	 * [0, 1M) should always be covered by var mtrr with WB
 	 * and fixed mtrrs should take effect before var mtrr for it:
 	 */
-	nr_range = add_range_with_merge(range, nr_range, 0,
+	nr_range = add_range_with_merge(range, RANGE_NUM, nr_range, 0,
 					(1ULL<<(20 - PAGE_SHIFT)) - 1);
 	/* Sort the ranges: */
-	sort(range, nr_range, sizeof(struct res_range), cmp_range, NULL);
+	sort_range(range, nr_range);
 
 	range_sums = sum_ranges(range, nr_range);
 	printk(KERN_INFO "total RAM covered: %ldM\n",
diff --git a/arch/x86/kernel/mmconf-fam10h_64.c b/arch/x86/kernel/mmconf-fam10h_64.c
index 712d15f..7182580 100644
--- a/arch/x86/kernel/mmconf-fam10h_64.c
+++ b/arch/x86/kernel/mmconf-fam10h_64.c
@@ -7,6 +7,8 @@
 #include <linux/string.h>
 #include <linux/pci.h>
 #include <linux/dmi.h>
+#include <linux/range.h>
+
 #include <asm/pci-direct.h>
 #include <linux/sort.h>
 #include <asm/io.h>
@@ -30,11 +32,6 @@ static struct pci_hostbridge_probe pci_probes[] __cpuinitdata = {
 	{ 0xff, 0, PCI_VENDOR_ID_AMD, 0x1200 },
 };
 
-struct range {
-	u64 start;
-	u64 end;
-};
-
 static int __cpuinit cmp_range(const void *x1, const void *x2)
 {
 	const struct range *r1 = x1;
diff --git a/arch/x86/pci/amd_bus.c b/arch/x86/pci/amd_bus.c
index 95ecbd4..2356ea1 100644
--- a/arch/x86/pci/amd_bus.c
+++ b/arch/x86/pci/amd_bus.c
@@ -2,6 +2,8 @@
 #include <linux/pci.h>
 #include <linux/topology.h>
 #include <linux/cpu.h>
+#include <linux/range.h>
+
 #include <asm/pci_x86.h>
 
 #ifdef CONFIG_X86_64
@@ -17,58 +19,6 @@
 
 #ifdef CONFIG_X86_64
 
-#define RANGE_NUM 16
-
-struct res_range {
-	size_t start;
-	size_t end;
-};
-
-static void __init update_range(struct res_range *range, size_t start,
-				size_t end)
-{
-	int i;
-	int j;
-
-	for (j = 0; j < RANGE_NUM; j++) {
-		if (!range[j].end)
-			continue;
-
-		if (start <= range[j].start && end >= range[j].end) {
-			range[j].start = 0;
-			range[j].end = 0;
-			continue;
-		}
-
-		if (start <= range[j].start && end < range[j].end && range[j].start < end + 1) {
-			range[j].start = end + 1;
-			continue;
-		}
-
-
-		if (start > range[j].start && end >= range[j].end && range[j].end > start - 1) {
-			range[j].end = start - 1;
-			continue;
-		}
-
-		if (start > range[j].start && end < range[j].end) {
-			/* find the new spare */
-			for (i = 0; i < RANGE_NUM; i++) {
-				if (range[i].end == 0)
-					break;
-			}
-			if (i < RANGE_NUM) {
-				range[i].end = range[j].end;
-				range[i].start = end + 1;
-			} else {
-				printk(KERN_ERR "run of slot in ranges\n");
-			}
-			range[j].end = start - 1;
-			continue;
-		}
-	}
-}
-
 struct pci_hostbridge_probe {
 	u32 bus;
 	u32 slot;
@@ -111,6 +61,8 @@ static void __init get_pci_mmcfg_amd_fam10h_range(void)
 	fam10h_mmconf_end = base + (1ULL<<(segn_busn_bits + 20)) - 1;
 }
 
+#define RANGE_NUM 16
+
 /**
  * early_fill_mp_bus_to_node()
  * called before pcibios_scan_root and pci_scan_bus
@@ -132,7 +84,7 @@ static int __init early_fill_mp_bus_info(void)
 	struct resource *res;
 	size_t start;
 	size_t end;
-	struct res_range range[RANGE_NUM];
+	struct range range[RANGE_NUM];
 	u64 val;
 	u32 address;
 
@@ -226,7 +178,7 @@ static int __init early_fill_mp_bus_info(void)
 		if (end > 0xffff)
 			end = 0xffff;
 		update_res(info, start, end, IORESOURCE_IO, 1);
-		update_range(range, start, end);
+		subtract_range(range, RANGE_NUM, start, end);
 	}
 	/* add left over io port range to def node/link, [0, 0xffff] */
 	/* find the position */
@@ -256,14 +208,14 @@ static int __init early_fill_mp_bus_info(void)
 	end = (val & 0xffffff800000ULL);
 	printk(KERN_INFO "TOM: %016lx aka %ldM\n", end, end>>20);
 	if (end < (1ULL<<32))
-		update_range(range, 0, end - 1);
+		subtract_range(range, RANGE_NUM, 0, end - 1);
 
 	/* get mmconfig */
 	get_pci_mmcfg_amd_fam10h_range();
 	/* need to take out mmconf range */
 	if (fam10h_mmconf_end) {
 		printk(KERN_DEBUG "Fam 10h mmconf [%llx, %llx]\n", fam10h_mmconf_start, fam10h_mmconf_end);
-		update_range(range, fam10h_mmconf_start, fam10h_mmconf_end);
+		subtract_range(range, RANGE_NUM, fam10h_mmconf_start, fam10h_mmconf_end);
 	}
 
 	/* mmio resource */
@@ -318,7 +270,7 @@ static int __init early_fill_mp_bus_info(void)
 				/* we got a hole */
 				endx = fam10h_mmconf_start - 1;
 				update_res(info, start, endx, IORESOURCE_MEM, 0);
-				update_range(range, start, endx);
+				subtract_range(range, RANGE_NUM, start, endx);
 				printk(KERN_CONT " ==> [%llx, %llx]", (u64)start, endx);
 				start = fam10h_mmconf_end + 1;
 				changed = 1;
@@ -334,7 +286,7 @@ static int __init early_fill_mp_bus_info(void)
 		}
 
 		update_res(info, start, end, IORESOURCE_MEM, 1);
-		update_range(range, start, end);
+		subtract_range(range, RANGE_NUM, start, end);
 		printk(KERN_CONT "\n");
 	}
 
@@ -349,7 +301,7 @@ static int __init early_fill_mp_bus_info(void)
 		rdmsrl(address, val);
 		end = (val & 0xffffff800000ULL);
 		printk(KERN_INFO "TOM2: %016lx aka %ldM\n", end, end>>20);
-		update_range(range, 1ULL<<32, end - 1);
+		subtract_range(range, RANGE_NUM, 1ULL<<32, end - 1);
 	}
 
 	/*
diff --git a/include/linux/range.h b/include/linux/range.h
new file mode 100644
index 0000000..0789f14
--- /dev/null
+++ b/include/linux/range.h
@@ -0,0 +1,22 @@
+#ifndef _LINUX_RANGE_H
+#define _LINUX_RANGE_H
+
+struct range {
+	u64   start;
+	u64   end;
+};
+
+int add_range(struct range *range, int az, int nr_range,
+		u64 start, u64 end);
+
+
+int add_range_with_merge(struct range *range, int az, int nr_range,
+				u64 start, u64 end);
+
+void subtract_range(struct range *range, int az, u64 start, u64 end);
+
+int clean_sort_range(struct range *range, int az);
+
+void sort_range(struct range *range, int nr_range);
+
+#endif
diff --git a/kernel/Makefile b/kernel/Makefile
index 864ff75..ad47330 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -10,7 +10,7 @@ obj-y     = sched.o fork.o exec_domain.o panic.o printk.o \
 	    kthread.o wait.o kfifo.o sys_ni.o posix-cpu-timers.o mutex.o \
 	    hrtimer.o rwsem.o nsproxy.o srcu.o semaphore.o \
 	    notifier.o ksysfs.o pm_qos_params.o sched_clock.o cred.o \
-	    async.o
+	    async.o range.o
 obj-y += groups.o
 
 ifdef CONFIG_FUNCTION_TRACER
diff --git a/kernel/range.c b/kernel/range.c
new file mode 100644
index 0000000..46a10c8
--- /dev/null
+++ b/kernel/range.c
@@ -0,0 +1,154 @@
+/*
+ * Range add and subtract
+ */
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/sort.h>
+
+#include <linux/range.h>
+
+#ifndef ARRAY_SIZE
+#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
+#endif
+
+int add_range(struct range *range, int az, int nr_range, u64 start, u64 end)
+{
+	/* Out of slots: */
+	if (nr_range >= az)
+		return nr_range;
+
+	range[nr_range].start = start;
+	range[nr_range].end = end;
+
+	nr_range++;
+
+	return nr_range;
+}
+
+int add_range_with_merge(struct range *range, int az, int nr_range,
+		     u64 start, u64 end)
+{
+	int i;
+
+	/* Try to merge it with old one: */
+	for (i = 0; i < nr_range; i++) {
+		u64 final_start, final_end;
+		u64 common_start, common_end;
+
+		if (!range[i].end)
+			continue;
+
+		common_start = max(range[i].start, start);
+		common_end = min(range[i].end, end);
+		if (common_start > common_end + 1)
+			continue;
+
+		final_start = min(range[i].start, start);
+		final_end = max(range[i].end, end);
+
+		range[i].start = final_start;
+		range[i].end =  final_end;
+		return nr_range;
+	}
+
+	/* Need to add it: */
+	return add_range(range, az, nr_range, start, end);
+}
+
+void subtract_range(struct range *range, int az, u64 start, u64 end)
+{
+	int i, j;
+
+	for (j = 0; j < az; j++) {
+		if (!range[j].end)
+			continue;
+
+		if (start <= range[j].start && end >= range[j].end) {
+			range[j].start = 0;
+			range[j].end = 0;
+			continue;
+		}
+
+		if (start <= range[j].start && end < range[j].end &&
+		    range[j].start < end + 1) {
+			range[j].start = end + 1;
+			continue;
+		}
+
+
+		if (start > range[j].start && end >= range[j].end &&
+		    range[j].end > start - 1) {
+			range[j].end = start - 1;
+			continue;
+		}
+
+		if (start > range[j].start && end < range[j].end) {
+			/* Find the new spare: */
+			for (i = 0; i < az; i++) {
+				if (range[i].end == 0)
+					break;
+			}
+			if (i < az) {
+				range[i].end = range[j].end;
+				range[i].start = end + 1;
+			} else {
+				printk(KERN_ERR "run of slot in ranges\n");
+			}
+			range[j].end = start - 1;
+			continue;
+		}
+	}
+}
+
+static int cmp_range(const void *x1, const void *x2)
+{
+	const struct range *r1 = x1;
+	const struct range *r2 = x2;
+	s64 start1, start2;
+
+	start1 = r1->start;
+	start2 = r2->start;
+
+	return start1 - start2;
+}
+
+int clean_sort_range(struct range *range, int az)
+{
+	int i, j, k = az - 1, nr_range = 0;
+
+	for (i = 0; i < k; i++) {
+		if (range[i].end)
+			continue;
+		for (j = k; j > i; j--) {
+			if (range[j].end) {
+				k = j;
+				break;
+			}
+		}
+		if (j == i)
+			break;
+		range[i].start = range[k].start;
+		range[i].end   = range[k].end;
+		range[k].start = 0;
+		range[k].end   = 0;
+		k--;
+	}
+	/* count it */
+	for (i = 0; i < az; i++) {
+		if (!range[i].end) {
+			nr_range = i;
+			break;
+		}
+	}
+
+	/* sort them */
+	sort(range, nr_range, sizeof(struct range), cmp_range, NULL);
+
+	return nr_range;
+}
+
+void sort_range(struct range *range, int nr_range)
+{
+	/* sort them */
+	sort(range, nr_range, sizeof(struct range), cmp_range, NULL);
+}
-- 
1.6.4.2

[PATCH 05/29] x86: check range in update range

[Yinghai Lu]

fend off wrong range

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
---
 kernel/range.c |    9 +++++++++
 1 files changed, 9 insertions(+), 0 deletions(-)

diff --git a/kernel/range.c b/kernel/range.c
index 46a10c8..71e0021 100644
--- a/kernel/range.c
+++ b/kernel/range.c
@@ -13,6 +13,9 @@
 
 int add_range(struct range *range, int az, int nr_range, u64 start, u64 end)
 {
+	if (start > end)
+		return nr_range;
+
 	/* Out of slots: */
 	if (nr_range >= az)
 		return nr_range;
@@ -30,6 +33,9 @@ int add_range_with_merge(struct range *range, int az, int nr_range,
 {
 	int i;
 
+	if (start > end)
+		return nr_range;
+
 	/* Try to merge it with old one: */
 	for (i = 0; i < nr_range; i++) {
 		u64 final_start, final_end;
@@ -59,6 +65,9 @@ void subtract_range(struct range *range, int az, u64 start, u64 end)
 {
 	int i, j;
 
+	if (start > end)
+		return;
+
 	for (j = 0; j < az; j++) {
 		if (!range[j].end)
 			continue;
-- 
1.6.4.2

[PATCH 06/29] x86/pci: use resource_size_t in update_res

[Yinghai Lu]

prepare to enable 32bit intel and amd bus

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
---
 arch/x86/pci/bus_numa.c |   16 ++++++++--------
 arch/x86/pci/bus_numa.h |    4 ++--
 2 files changed, 10 insertions(+), 10 deletions(-)

diff --git a/arch/x86/pci/bus_numa.c b/arch/x86/pci/bus_numa.c
index f939d60..30f65ce 100644
--- a/arch/x86/pci/bus_numa.c
+++ b/arch/x86/pci/bus_numa.c
@@ -51,8 +51,8 @@ void x86_pci_root_bus_res_quirks(struct pci_bus *b)
 	}
 }
 
-void __devinit update_res(struct pci_root_info *info, size_t start,
-			      size_t end, unsigned long flags, int merge)
+void __devinit update_res(struct pci_root_info *info, resource_size_t start,
+			  resource_size_t end, unsigned long flags, int merge)
 {
 	int i;
 	struct resource *res;
@@ -65,20 +65,20 @@ void __devinit update_res(struct pci_root_info *info, size_t start,
 
 	/* try to merge it with old one */
 	for (i = 0; i < info->res_num; i++) {
-		size_t final_start, final_end;
-		size_t common_start, common_end;
+		resource_size_t final_start, final_end;
+		resource_size_t common_start, common_end;
 
 		res = &info->res[i];
 		if (res->flags != flags)
 			continue;
 
-		common_start = max((size_t)res->start, start);
-		common_end = min((size_t)res->end, end);
+		common_start = max(res->start, start);
+		common_end = min(res->end, end);
 		if (common_start > common_end + 1)
 			continue;
 
-		final_start = min((size_t)res->start, start);
-		final_end = max((size_t)res->end, end);
+		final_start = min(res->start, start);
+		final_end = max(res->end, end);
 
 		res->start = final_start;
 		res->end = final_end;
diff --git a/arch/x86/pci/bus_numa.h b/arch/x86/pci/bus_numa.h
index adbc23f..374ecc5 100644
--- a/arch/x86/pci/bus_numa.h
+++ b/arch/x86/pci/bus_numa.h
@@ -22,6 +22,6 @@ extern int pci_root_num;
 extern struct pci_root_info pci_root_info[PCI_ROOT_NR];
 extern int found_all_numa_early;
 
-extern void update_res(struct pci_root_info *info, size_t start,
-			      size_t end, unsigned long flags, int merge);
+extern void update_res(struct pci_root_info *info, resource_size_t start,
+		      resource_size_t end, unsigned long flags, int merge);
 #endif
-- 
1.6.4.2

[PATCH 07/29] x86/pci: amd one chain system to use pci read out res

[Yinghai Lu]

found MSI amd k8 based laptops is hiding [0x70000000, 0x80000000) RAM from
e820.

enable amd one chain even for all.

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
---
 arch/x86/pci/amd_bus.c  |    7 ++++---
 arch/x86/pci/bus_numa.c |    5 -----
 arch/x86/pci/bus_numa.h |    1 -
 3 files changed, 4 insertions(+), 9 deletions(-)

diff --git a/arch/x86/pci/amd_bus.c b/arch/x86/pci/amd_bus.c
index 2356ea1..e467071 100644
--- a/arch/x86/pci/amd_bus.c
+++ b/arch/x86/pci/amd_bus.c
@@ -87,11 +87,12 @@ static int __init early_fill_mp_bus_info(void)
 	struct range range[RANGE_NUM];
 	u64 val;
 	u32 address;
+	int found;
 
 	if (!early_pci_allowed())
 		return -1;
 
-	found_all_numa_early = 0;
+	found = 0;
 	for (i = 0; i < ARRAY_SIZE(pci_probes); i++) {
 		u32 id;
 		u16 device;
@@ -105,12 +106,12 @@ static int __init early_fill_mp_bus_info(void)
 		device = (id>>16) & 0xffff;
 		if (pci_probes[i].vendor == vendor &&
 		    pci_probes[i].device == device) {
-			found_all_numa_early = 1;
+			found = 1;
 			break;
 		}
 	}
 
-	if (!found_all_numa_early)
+	if (!found)
 		return 0;
 
 	pci_root_num = 0;
diff --git a/arch/x86/pci/bus_numa.c b/arch/x86/pci/bus_numa.c
index 30f65ce..3411687 100644
--- a/arch/x86/pci/bus_numa.c
+++ b/arch/x86/pci/bus_numa.c
@@ -5,7 +5,6 @@
 
 int pci_root_num;
 struct pci_root_info pci_root_info[PCI_ROOT_NR];
-int found_all_numa_early;
 
 void x86_pci_root_bus_res_quirks(struct pci_bus *b)
 {
@@ -21,10 +20,6 @@ void x86_pci_root_bus_res_quirks(struct pci_bus *b)
 	if (!pci_root_num)
 		return;
 
-	/* for amd, if only one root bus, don't need to do anything */
-	if (pci_root_num < 2 && found_all_numa_early)
-		return;
-
 	for (i = 0; i < pci_root_num; i++) {
 		if (pci_root_info[i].bus_min == b->number)
 			break;
diff --git a/arch/x86/pci/bus_numa.h b/arch/x86/pci/bus_numa.h
index 374ecc5..f63e802 100644
--- a/arch/x86/pci/bus_numa.h
+++ b/arch/x86/pci/bus_numa.h
@@ -20,7 +20,6 @@ struct pci_root_info {
 #define PCI_ROOT_NR 4
 extern int pci_root_num;
 extern struct pci_root_info pci_root_info[PCI_ROOT_NR];
-extern int found_all_numa_early;
 
 extern void update_res(struct pci_root_info *info, resource_size_t start,
 		      resource_size_t end, unsigned long flags, int merge);
-- 
1.6.4.2

[PATCH 08/29] x86/pci: use u64 instead of size_t in amd_bus.c

[Yinghai Lu]

prepare to enable it for 32bit

-v2: remove not needed cast

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
---
 arch/x86/pci/amd_bus.c |   16 ++++++++--------
 1 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/arch/x86/pci/amd_bus.c b/arch/x86/pci/amd_bus.c
index e467071..e8bb553 100644
--- a/arch/x86/pci/amd_bus.c
+++ b/arch/x86/pci/amd_bus.c
@@ -82,8 +82,8 @@ static int __init early_fill_mp_bus_info(void)
 	struct pci_root_info *info;
 	u32 reg;
 	struct resource *res;
-	size_t start;
-	size_t end;
+	u64 start;
+	u64 end;
 	struct range range[RANGE_NUM];
 	u64 val;
 	u32 address;
@@ -173,7 +173,7 @@ static int __init early_fill_mp_bus_info(void)
 
 		info = &pci_root_info[j];
 		printk(KERN_DEBUG "node %d link %d: io port [%llx, %llx]\n",
-		       node, link, (u64)start, (u64)end);
+		       node, link, start, end);
 
 		/* kernel only handle 16 bit only */
 		if (end > 0xffff)
@@ -207,7 +207,7 @@ static int __init early_fill_mp_bus_info(void)
 	address = MSR_K8_TOP_MEM1;
 	rdmsrl(address, val);
 	end = (val & 0xffffff800000ULL);
-	printk(KERN_INFO "TOM: %016lx aka %ldM\n", end, end>>20);
+	printk(KERN_INFO "TOM: %016llx aka %lldM\n", end, end>>20);
 	if (end < (1ULL<<32))
 		subtract_range(range, RANGE_NUM, 0, end - 1);
 
@@ -246,7 +246,7 @@ static int __init early_fill_mp_bus_info(void)
 		info = &pci_root_info[j];
 
 		printk(KERN_DEBUG "node %d link %d: mmio [%llx, %llx]",
-		       node, link, (u64)start, (u64)end);
+		       node, link, start, end);
 		/*
 		 * some sick allocation would have range overlap with fam10h
 		 * mmconf range, so need to update start and end.
@@ -272,13 +272,13 @@ static int __init early_fill_mp_bus_info(void)
 				endx = fam10h_mmconf_start - 1;
 				update_res(info, start, endx, IORESOURCE_MEM, 0);
 				subtract_range(range, RANGE_NUM, start, endx);
-				printk(KERN_CONT " ==> [%llx, %llx]", (u64)start, endx);
+				printk(KERN_CONT " ==> [%llx, %llx]", start, endx);
 				start = fam10h_mmconf_end + 1;
 				changed = 1;
 			}
 			if (changed) {
 				if (start <= end) {
-					printk(KERN_CONT " %s [%llx, %llx]", endx?"and":"==>", (u64)start, (u64)end);
+					printk(KERN_CONT " %s [%llx, %llx]", endx?"and":"==>", start, end);
 				} else {
 					printk(KERN_CONT "%s\n", endx?"":" ==> none");
 					continue;
@@ -301,7 +301,7 @@ static int __init early_fill_mp_bus_info(void)
 		address = MSR_K8_TOP_MEM2;
 		rdmsrl(address, val);
 		end = (val & 0xffffff800000ULL);
-		printk(KERN_INFO "TOM2: %016lx aka %ldM\n", end, end>>20);
+		printk(KERN_INFO "TOM2: %016llx aka %lldM\n", end, end>>20);
 		subtract_range(range, RANGE_NUM, 1ULL<<32, end - 1);
 	}
 
-- 
1.6.4.2

[PATCH 09/29] x86/pci: add cap_resource

[Yinghai Lu]

prepare for 32bit pci root bus

-v2: hpa said we should compare with (resource_size_t)~0

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
---
 arch/x86/pci/amd_bus.c   |    8 +++++---
 arch/x86/pci/bus_numa.c  |    3 +++
 arch/x86/pci/intel_bus.c |    5 ++++-
 include/linux/range.h    |    8 ++++++++
 4 files changed, 20 insertions(+), 4 deletions(-)

diff --git a/arch/x86/pci/amd_bus.c b/arch/x86/pci/amd_bus.c
index e8bb553..9bcb6fe 100644
--- a/arch/x86/pci/amd_bus.c
+++ b/arch/x86/pci/amd_bus.c
@@ -201,7 +201,7 @@ static int __init early_fill_mp_bus_info(void)
 
 	memset(range, 0, sizeof(range));
 	/* 0xfd00000000-0xffffffffff for HT */
-	range[0].end = (0xfdULL<<32) - 1;
+	range[0].end = cap_resource((0xfdULL<<32) - 1);
 
 	/* need to take out [0, TOM) for RAM*/
 	address = MSR_K8_TOP_MEM1;
@@ -286,7 +286,8 @@ static int __init early_fill_mp_bus_info(void)
 			}
 		}
 
-		update_res(info, start, end, IORESOURCE_MEM, 1);
+		update_res(info, cap_resource(start), cap_resource(end),
+				 IORESOURCE_MEM, 1);
 		subtract_range(range, RANGE_NUM, start, end);
 		printk(KERN_CONT "\n");
 	}
@@ -321,7 +322,8 @@ static int __init early_fill_mp_bus_info(void)
 			if (!range[i].end)
 				continue;
 
-			update_res(info, range[i].start, range[i].end,
+			update_res(info, cap_resource(range[i].start),
+				   cap_resource(range[i].end),
 				   IORESOURCE_MEM, 1);
 		}
 	}
diff --git a/arch/x86/pci/bus_numa.c b/arch/x86/pci/bus_numa.c
index 3411687..65dda4e 100644
--- a/arch/x86/pci/bus_numa.c
+++ b/arch/x86/pci/bus_numa.c
@@ -55,6 +55,9 @@ void __devinit update_res(struct pci_root_info *info, resource_size_t start,
 	if (start > end)
 		return;
 
+	if (start == (resource_size_t)~0)
+		return;
+
 	if (!merge)
 		goto addit;
 
diff --git a/arch/x86/pci/intel_bus.c b/arch/x86/pci/intel_bus.c
index baf283a..1f15df9 100644
--- a/arch/x86/pci/intel_bus.c
+++ b/arch/x86/pci/intel_bus.c
@@ -6,6 +6,8 @@
 #include <linux/dmi.h>
 #include <linux/pci.h>
 #include <linux/init.h>
+#include <linux/range.h>
+
 #include <asm/pci_x86.h>
 
 #include "bus_numa.h"
@@ -85,7 +87,8 @@ static void __devinit pci_root_bus_res(struct pci_dev *dev)
 	mmioh_base |= ((u64)(dword & 0x7ffff)) << 32;
 	pci_read_config_dword(dev, IOH_LMMIOH_LIMITU, &dword);
 	mmioh_end |= ((u64)(dword & 0x7ffff)) << 32;
-	update_res(info, mmioh_base, mmioh_end, IORESOURCE_MEM, 0);
+	update_res(info, cap_resource(mmioh_base), cap_resource(mmioh_end),
+			 IORESOURCE_MEM, 0);
 
 	print_ioh_resources(info);
 }
diff --git a/include/linux/range.h b/include/linux/range.h
index 0789f14..17a23d2 100644
--- a/include/linux/range.h
+++ b/include/linux/range.h
@@ -19,4 +19,12 @@ int clean_sort_range(struct range *range, int az);
 
 void sort_range(struct range *range, int nr_range);
 
+
+static inline resource_size_t cap_resource(u64 val)
+{
+	if (val > (resource_size_t)~0)
+		return (resource_size_t)~0;
+	else
+		return val;
+}
 #endif
-- 
1.6.4.2

[PATCH 10/29] x86/pci: enable pci root res read out for 32bit too

[Yinghai Lu]

should be good for 32bit too.

-v3: cast res->start

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
---
 arch/x86/pci/Makefile    |    3 +--
 arch/x86/pci/amd_bus.c   |   14 +-------------
 arch/x86/pci/bus_numa.h  |    4 ++--
 arch/x86/pci/i386.c      |    4 ----
 arch/x86/pci/intel_bus.c |    2 +-
 5 files changed, 5 insertions(+), 22 deletions(-)

diff --git a/arch/x86/pci/Makefile b/arch/x86/pci/Makefile
index 564b008..30e55d7 100644
--- a/arch/x86/pci/Makefile
+++ b/arch/x86/pci/Makefile
@@ -14,8 +14,7 @@ obj-$(CONFIG_X86_VISWS)		+= visws.o
 obj-$(CONFIG_X86_NUMAQ)		+= numaq_32.o
 
 obj-y				+= common.o early.o
-obj-y				+= amd_bus.o
-obj-$(CONFIG_X86_64)		+= bus_numa.o intel_bus.o
+obj-y				+= amd_bus.o bus_numa.o intel_bus.o
 
 ifeq ($(CONFIG_PCI_DEBUG),y)
 EXTRA_CFLAGS += -DDEBUG
diff --git a/arch/x86/pci/amd_bus.c b/arch/x86/pci/amd_bus.c
index 9bcb6fe..ef4b3e7 100644
--- a/arch/x86/pci/amd_bus.c
+++ b/arch/x86/pci/amd_bus.c
@@ -6,9 +6,7 @@
 
 #include <asm/pci_x86.h>
 
-#ifdef CONFIG_X86_64
 #include <asm/pci-direct.h>
-#endif
 
 #include "bus_numa.h"
 
@@ -17,8 +15,6 @@
  * also get peer root bus resource for io,mmio
  */
 
-#ifdef CONFIG_X86_64
-
 struct pci_hostbridge_probe {
 	u32 bus;
 	u32 slot;
@@ -342,21 +338,13 @@ static int __init early_fill_mp_bus_info(void)
 			printk(KERN_DEBUG "bus: %02x index %x %s: [%llx, %llx]\n",
 			       busnum, j,
 			       (res->flags & IORESOURCE_IO)?"io port":"mmio",
-			       res->start, res->end);
+			       (u64)res->start, (u64)res->end);
 		}
 	}
 
 	return 0;
 }
 
-#else  /* !CONFIG_X86_64 */
-
-static int __init early_fill_mp_bus_info(void) { return 0; }
-
-#endif /* !CONFIG_X86_64 */
-
-/* common 32/64 bit code */
-
 #define ENABLE_CF8_EXT_CFG      (1ULL << 46)
 
 static void enable_pci_io_ecs(void *unused)
diff --git a/arch/x86/pci/bus_numa.h b/arch/x86/pci/bus_numa.h
index f63e802..08d8e15 100644
--- a/arch/x86/pci/bus_numa.h
+++ b/arch/x86/pci/bus_numa.h
@@ -1,5 +1,5 @@
-#ifdef CONFIG_X86_64
-
+#ifndef __BUS_NUMA_H
+#define __BUS_NUMA_H
 /*
  * sub bus (transparent) will use entres from 3 to store extra from
  * root, so need to make sure we have enough slot there, Should we
diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c
index 5dc9e8c..f4e8481 100644
--- a/arch/x86/pci/i386.c
+++ b/arch/x86/pci/i386.c
@@ -257,10 +257,6 @@ void __init pcibios_resource_survey(void)
  */
 fs_initcall(pcibios_assign_resources);
 
-void __weak x86_pci_root_bus_res_quirks(struct pci_bus *b)
-{
-}
-
 /*
  *  If we set up a device for bus mastering, we need to check the latency
  *  timer as certain crappy BIOSes forget to set it properly.
diff --git a/arch/x86/pci/intel_bus.c b/arch/x86/pci/intel_bus.c
index 1f15df9..6167be9 100644
--- a/arch/x86/pci/intel_bus.c
+++ b/arch/x86/pci/intel_bus.c
@@ -30,7 +30,7 @@ static inline void print_ioh_resources(struct pci_root_info *info)
 			busnum, i,
 			(res->flags & IORESOURCE_IO) ? "io port" :
 							"mmio",
-			res->start, res->end);
+			(u64)res->start, (u64)res->end);
 	}
 }
 
-- 
1.6.4.2

[PATCH 11/29] x86: call early_res_to_bootmem one time

[Yinghai Lu]

simplify setup_node_mem, do use bootmem from other node.
instead just find_e820_area in early_node_mem.

so we can keep the boundary between early_res and boot mem more clear.
and only call civertion one time instead of for all nodes.

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
---
 arch/x86/kernel/setup.c |    1 +
 arch/x86/mm/init_32.c   |    1 -
 arch/x86/mm/init_64.c   |    3 +-
 arch/x86/mm/numa_64.c   |   62 +++++++++++++++-------------------------------
 4 files changed, 22 insertions(+), 45 deletions(-)

diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index f7b8b98..3ab0bf4 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -942,6 +942,7 @@ void __init setup_arch(char **cmdline_p)
 #endif
 
 	initmem_init(0, max_pfn, acpi, k8);
+	early_res_to_bootmem(0, max_low_pfn<<PAGE_SHIFT);
 
 #ifdef CONFIG_X86_64
 	/*
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index c973f8e..3c4fe2a 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -764,7 +764,6 @@ static unsigned long __init setup_node_bootmem(int nodeid,
 	printk(KERN_INFO "  node %d bootmap %08lx - %08lx\n",
 		 nodeid, bootmap, bootmap + bootmap_size);
 	free_bootmem_with_active_regions(nodeid, end_pfn);
-	early_res_to_bootmem(start_pfn<<PAGE_SHIFT, end_pfn<<PAGE_SHIFT);
 
 	return bootmap + bootmap_size;
 }
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 5198b9b..1ea79ad 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -578,13 +578,12 @@ void __init initmem_init(unsigned long start_pfn, unsigned long end_pfn,
 				 PAGE_SIZE);
 	if (bootmap == -1L)
 		panic("Cannot find bootmem map of size %ld\n", bootmap_size);
+	reserve_early(bootmap, bootmap + bootmap_size, "BOOTMAP");
 	/* don't touch min_low_pfn */
 	bootmap_size = init_bootmem_node(NODE_DATA(0), bootmap >> PAGE_SHIFT,
 					 0, end_pfn);
 	e820_register_active_regions(0, start_pfn, end_pfn);
 	free_bootmem_with_active_regions(0, end_pfn);
-	early_res_to_bootmem(0, end_pfn<<PAGE_SHIFT);
-	reserve_bootmem(bootmap, bootmap_size, BOOTMEM_DEFAULT);
 }
 #endif
 
diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c
index 83bbc70..3232148 100644
--- a/arch/x86/mm/numa_64.c
+++ b/arch/x86/mm/numa_64.c
@@ -164,18 +164,21 @@ static void * __init early_node_mem(int nodeid, unsigned long start,
 				    unsigned long align)
 {
 	unsigned long mem = find_e820_area(start, end, size, align);
-	void *ptr;
 
 	if (mem != -1L)
 		return __va(mem);
 
-	ptr = __alloc_bootmem_nopanic(size, align, __pa(MAX_DMA_ADDRESS));
-	if (ptr == NULL) {
-		printk(KERN_ERR "Cannot find %lu bytes in node %d\n",
+
+	start = __pa(MAX_DMA_ADDRESS);
+	end = max_low_pfn_mapped << PAGE_SHIFT;
+	mem = find_e820_area(start, end, size, align);
+	if (mem != -1L)
+		return __va(mem);
+
+	printk(KERN_ERR "Cannot find %lu bytes in node %d\n",
 		       size, nodeid);
-		return NULL;
-	}
-	return ptr;
+
+	return NULL;
 }
 
 /* Initialize bootmem allocator for a node */
@@ -211,8 +214,12 @@ setup_node_bootmem(int nodeid, unsigned long start, unsigned long end)
 	if (node_data[nodeid] == NULL)
 		return;
 	nodedata_phys = __pa(node_data[nodeid]);
+	reserve_early(nodedata_phys, nodedata_phys + pgdat_size, "NODE_DATA");
 	printk(KERN_INFO "  NODE_DATA [%016lx - %016lx]\n", nodedata_phys,
 		nodedata_phys + pgdat_size - 1);
+	nid = phys_to_nid(nodedata_phys);
+	if (nid != nodeid)
+		printk(KERN_INFO "    NODE_DATA(%d) on node %d\n", nodeid, nid);
 
 	memset(NODE_DATA(nodeid), 0, sizeof(pg_data_t));
 	NODE_DATA(nodeid)->bdata = &bootmem_node_data[nodeid];
@@ -227,11 +234,7 @@ setup_node_bootmem(int nodeid, unsigned long start, unsigned long end)
 	 * of alloc_bootmem, that could clash with reserved range
 	 */
 	bootmap_pages = bootmem_bootmap_pages(last_pfn - start_pfn);
-	nid = phys_to_nid(nodedata_phys);
-	if (nid == nodeid)
-		bootmap_start = roundup(nodedata_phys + pgdat_size, PAGE_SIZE);
-	else
-		bootmap_start = roundup(start, PAGE_SIZE);
+	bootmap_start = roundup(nodedata_phys + pgdat_size, PAGE_SIZE);
 	/*
 	 * SMP_CACHE_BYTES could be enough, but init_bootmem_node like
 	 * to use that to align to PAGE_SIZE
@@ -239,18 +242,13 @@ setup_node_bootmem(int nodeid, unsigned long start, unsigned long end)
 	bootmap = early_node_mem(nodeid, bootmap_start, end,
 				 bootmap_pages<<PAGE_SHIFT, PAGE_SIZE);
 	if (bootmap == NULL)  {
-		if (nodedata_phys < start || nodedata_phys >= end) {
-			/*
-			 * only need to free it if it is from other node
-			 * bootmem
-			 */
-			if (nid != nodeid)
-				free_bootmem(nodedata_phys, pgdat_size);
-		}
+		free_early(nodedata_phys, nodedata_phys + pgdat_size);
 		node_data[nodeid] = NULL;
 		return;
 	}
 	bootmap_start = __pa(bootmap);
+	reserve_early(bootmap_start, bootmap_start+(bootmap_pages<<PAGE_SHIFT),
+			"BOOTMAP");
 
 	bootmap_size = init_bootmem_node(NODE_DATA(nodeid),
 					 bootmap_start >> PAGE_SHIFT,
@@ -259,31 +257,11 @@ setup_node_bootmem(int nodeid, unsigned long start, unsigned long end)
 	printk(KERN_INFO "  bootmap [%016lx -  %016lx] pages %lx\n",
 		 bootmap_start, bootmap_start + bootmap_size - 1,
 		 bootmap_pages);
-
-	free_bootmem_with_active_regions(nodeid, end);
-
-	/*
-	 * convert early reserve to bootmem reserve earlier
-	 * otherwise early_node_mem could use early reserved mem
-	 * on previous node
-	 */
-	early_res_to_bootmem(start, end);
-
-	/*
-	 * in some case early_node_mem could use alloc_bootmem
-	 * to get range on other node, don't reserve that again
-	 */
-	if (nid != nodeid)
-		printk(KERN_INFO "    NODE_DATA(%d) on node %d\n", nodeid, nid);
-	else
-		reserve_bootmem_node(NODE_DATA(nodeid), nodedata_phys,
-					pgdat_size, BOOTMEM_DEFAULT);
 	nid = phys_to_nid(bootmap_start);
 	if (nid != nodeid)
 		printk(KERN_INFO "    bootmap(%d) on node %d\n", nodeid, nid);
-	else
-		reserve_bootmem_node(NODE_DATA(nodeid), bootmap_start,
-				 bootmap_pages<<PAGE_SHIFT, BOOTMEM_DEFAULT);
+
+	free_bootmem_with_active_regions(nodeid, end);
 
 	node_set_online(nodeid);
 }
-- 
1.6.4.2

[PATCH 12/29] x86: introduce max_early_res and early_res_count

[Yinghai Lu]

to prepare allocate early res array from fine_e820_area

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
---
 arch/x86/kernel/e820.c |   47 ++++++++++++++++++++++++++++++++---------------
 1 files changed, 32 insertions(+), 15 deletions(-)

diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index a1a7876..291f6d2 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -724,14 +724,18 @@ core_initcall(e820_mark_nvs_memory);
 /*
  * Early reserved memory areas.
  */
-#define MAX_EARLY_RES 32
+/*
+ * need to make sure this one is bigger enough before
+ * find_e820_area could be used
+ */
+#define MAX_EARLY_RES_X 32
 
 struct early_res {
 	u64 start, end;
-	char name[16];
+	char name[15];
 	char overlap_ok;
 };
-static struct early_res early_res[MAX_EARLY_RES] __initdata = {
+static struct early_res early_res_x[MAX_EARLY_RES_X] __initdata = {
 	{ 0, PAGE_SIZE, "BIOS data page", 1 },	/* BIOS data page */
 #if defined(CONFIG_X86_32) && defined(CONFIG_X86_TRAMPOLINE)
 	/*
@@ -745,12 +749,22 @@ static struct early_res early_res[MAX_EARLY_RES] __initdata = {
 	{}
 };
 
+static int max_early_res __initdata = MAX_EARLY_RES_X;
+static struct early_res *early_res __initdata = &early_res_x[0];
+static int early_res_count __initdata =
+#ifdef CONFIG_X86_32
+	2
+#else
+	1
+#endif
+	;
+
 static int __init find_overlapped_early(u64 start, u64 end)
 {
 	int i;
 	struct early_res *r;
 
-	for (i = 0; i < MAX_EARLY_RES && early_res[i].end; i++) {
+	for (i = 0; i < max_early_res && early_res[i].end; i++) {
 		r = &early_res[i];
 		if (end > r->start && start < r->end)
 			break;
@@ -768,13 +782,14 @@ static void __init drop_range(int i)
 {
 	int j;
 
-	for (j = i + 1; j < MAX_EARLY_RES && early_res[j].end; j++)
+	for (j = i + 1; j < max_early_res && early_res[j].end; j++)
 		;
 
 	memmove(&early_res[i], &early_res[i + 1],
 	       (j - 1 - i) * sizeof(struct early_res));
 
 	early_res[j - 1].end = 0;
+	early_res_count--;
 }
 
 /*
@@ -793,9 +808,9 @@ static void __init drop_overlaps_that_are_ok(u64 start, u64 end)
 	struct early_res *r;
 	u64 lower_start, lower_end;
 	u64 upper_start, upper_end;
-	char name[16];
+	char name[15];
 
-	for (i = 0; i < MAX_EARLY_RES && early_res[i].end; i++) {
+	for (i = 0; i < max_early_res && early_res[i].end; i++) {
 		r = &early_res[i];
 
 		/* Continue past non-overlapping ranges */
@@ -851,7 +866,7 @@ static void __init __reserve_early(u64 start, u64 end, char *name,
 	struct early_res *r;
 
 	i = find_overlapped_early(start, end);
-	if (i >= MAX_EARLY_RES)
+	if (i >= max_early_res)
 		panic("Too many early reservations");
 	r = &early_res[i];
 	if (r->end)
@@ -864,6 +879,7 @@ static void __init __reserve_early(u64 start, u64 end, char *name,
 	r->overlap_ok = overlap_ok;
 	if (name)
 		strncpy(r->name, name, sizeof(r->name) - 1);
+	early_res_count++;
 }
 
 /*
@@ -916,7 +932,7 @@ void __init free_early(u64 start, u64 end)
 
 	i = find_overlapped_early(start, end);
 	r = &early_res[i];
-	if (i >= MAX_EARLY_RES || r->end != end || r->start != start)
+	if (i >= max_early_res || r->end != end || r->start != start)
 		panic("free_early on not reserved area: %llx-%llx!",
 			 start, end - 1);
 
@@ -927,14 +943,15 @@ void __init early_res_to_bootmem(u64 start, u64 end)
 {
 	int i, count;
 	u64 final_start, final_end;
+	int idx = 0;
 
 	count  = 0;
-	for (i = 0; i < MAX_EARLY_RES && early_res[i].end; i++)
+	for (i = 0; i < max_early_res && early_res[i].end; i++)
 		count++;
 
-	printk(KERN_INFO "(%d early reservations) ==> bootmem [%010llx - %010llx]\n",
-			 count, start, end);
-	for (i = 0; i < count; i++) {
+	printk(KERN_INFO "(%d/%d early reservations) ==> bootmem [%010llx - %010llx]\n",
+			 count - idx, max_early_res, start, end);
+	for (i = idx; i < count; i++) {
 		struct early_res *r = &early_res[i];
 		printk(KERN_INFO "  #%d [%010llx - %010llx] %16s", i,
 			r->start, r->end, r->name);
@@ -961,7 +978,7 @@ static inline int __init bad_addr(u64 *addrp, u64 size, u64 align)
 again:
 	i = find_overlapped_early(addr, addr + size);
 	r = &early_res[i];
-	if (i < MAX_EARLY_RES && r->end) {
+	if (i < max_early_res && r->end) {
 		*addrp = addr = round_up(r->end, align);
 		changed = 1;
 		goto again;
@@ -978,7 +995,7 @@ static inline int __init bad_addr_size(u64 *addrp, u64 *sizep, u64 align)
 	int changed = 0;
 again:
 	last = addr + size;
-	for (i = 0; i < MAX_EARLY_RES && early_res[i].end; i++) {
+	for (i = 0; i < max_early_res && early_res[i].end; i++) {
 		struct early_res *r = &early_res[i];
 		if (last > r->start && addr < r->start) {
 			size = r->start - addr;
-- 
1.6.4.2

[PATCH 13/29] x86: dynamic increase early_res array size

[Yinghai Lu]

use early_res_count to track the num, and use find_e820 to get new buffer.
and copy from old to new one.

also clear early_res to prevent later invalid using

-v2 _check_and_double_early_res should take new start

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
---
 arch/x86/kernel/e820.c |   53 ++++++++++++++++++++++++++++++++++++++++++++++++
 1 files changed, 53 insertions(+), 0 deletions(-)

diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 291f6d2..949d688 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -908,6 +908,48 @@ void __init reserve_early_overlap_ok(u64 start, u64 end, char *name)
 	__reserve_early(start, end, name, 1);
 }
 
+static void __init __check_and_double_early_res(u64 start)
+{
+	u64 end, size, mem;
+	struct early_res *new;
+
+	/* do we have enough slots left ? */
+	if ((max_early_res - early_res_count) > max(max_early_res/8, 2))
+		return;
+
+	/* double it */
+	end = max_pfn_mapped << PAGE_SHIFT;
+	size = sizeof(struct early_res) * max_early_res * 2;
+	mem = find_e820_area(start, end, size, sizeof(struct early_res));
+
+	if (mem == -1ULL)
+		panic("can not find more space for early_res array");
+
+	new = __va(mem);
+	/* save the first one for own */
+	new[0].start = mem;
+	new[0].end = mem + size;
+	new[0].overlap_ok = 0;
+	/* copy old to new */
+	if (early_res == early_res_x) {
+		memcpy(&new[1], &early_res[0],
+			 sizeof(struct early_res) * max_early_res);
+		memset(&new[max_early_res+1], 0,
+			 sizeof(struct early_res) * (max_early_res - 1));
+		early_res_count++;
+	} else {
+		memcpy(&new[1], &early_res[1],
+			 sizeof(struct early_res) * (max_early_res - 1));
+		memset(&new[max_early_res], 0,
+			 sizeof(struct early_res) * max_early_res);
+	}
+	memset(&early_res[0], 0, sizeof(struct early_res) * max_early_res);
+	early_res = new;
+	max_early_res *= 2;
+	printk(KERN_DEBUG "early_res array is doubled to %d at [%llx - %llx]\n",
+		max_early_res, mem, mem + size - 1);
+}
+
 /*
  * Most early reservations come here.
  *
@@ -921,6 +963,8 @@ void __init reserve_early(u64 start, u64 end, char *name)
 	if (start >= end)
 		return;
 
+	__check_and_double_early_res(end);
+
 	drop_overlaps_that_are_ok(start, end);
 	__reserve_early(start, end, name, 0);
 }
@@ -949,6 +993,10 @@ void __init early_res_to_bootmem(u64 start, u64 end)
 	for (i = 0; i < max_early_res && early_res[i].end; i++)
 		count++;
 
+	/* need to skip first one ?*/
+	if (early_res != early_res_x)
+		idx = 1;
+
 	printk(KERN_INFO "(%d/%d early reservations) ==> bootmem [%010llx - %010llx]\n",
 			 count - idx, max_early_res, start, end);
 	for (i = idx; i < count; i++) {
@@ -966,6 +1014,11 @@ void __init early_res_to_bootmem(u64 start, u64 end)
 		reserve_bootmem_generic(final_start, final_end - final_start,
 				BOOTMEM_DEFAULT);
 	}
+	/* clear them */
+	memset(&early_res[0], 0, sizeof(struct early_res) * max_early_res);
+	early_res = NULL;
+	max_early_res = 0;
+	early_res_count = 0;
 }
 
 /* Check for already reserved areas */
-- 
1.6.4.2

[PATCH 14/29] x86: print bootmem free before pci_iommu_alloc and free_all_bootmem -v2

[Yinghai Lu]

so we could double check if we have enough low pages later

-v2: fix errors checkpatch.pl reported

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
---
 arch/x86/mm/init_64.c   |    2 +
 include/linux/bootmem.h |    2 +
 mm/bootmem.c            |   92 +++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 96 insertions(+), 0 deletions(-)

diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 1ea79ad..f9530eb 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -654,6 +654,8 @@ void __init mem_init(void)
 	long codesize, reservedpages, datasize, initsize;
 	unsigned long absent_pages;
 
+	print_bootmem_free();
+
 	pci_iommu_alloc();
 
 	/* clear_bss() already clear the empty_zero_page */
diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h
index b10ec49..3446bed 100644
--- a/include/linux/bootmem.h
+++ b/include/linux/bootmem.h
@@ -55,6 +55,8 @@ extern void free_bootmem_node(pg_data_t *pgdat,
 extern void free_bootmem(unsigned long addr, unsigned long size);
 extern void free_bootmem_late(unsigned long addr, unsigned long size);
 
+void print_bootmem_free(void);
+
 /*
  * Flags for reserve_bootmem (also if CONFIG_HAVE_ARCH_BOOTMEM_NODE,
  * the architecture-specific code should honor this).
diff --git a/mm/bootmem.c b/mm/bootmem.c
index 7d14868..eec89ed 100644
--- a/mm/bootmem.c
+++ b/mm/bootmem.c
@@ -267,6 +267,98 @@ static void __init __free(bootmem_data_t *bdata,
 			BUG();
 }
 
+static void __init print_all_bootmem_free_core(bootmem_data_t *bdata)
+{
+	int aligned;
+	unsigned long *map;
+	unsigned long start, end, count = 0;
+	unsigned long free_start = -1UL, free_end = 0;
+
+	if (!bdata->node_bootmem_map)
+		return;
+
+	start = bdata->node_min_pfn;
+	end = bdata->node_low_pfn;
+
+	/*
+	 * If the start is aligned to the machines wordsize, we might
+	 * be able to count it in bulks of that order.
+	 */
+	aligned = !(start & (BITS_PER_LONG - 1));
+
+	printk(KERN_DEBUG "nid=%td start=0x%010lx end=0x%010lx aligned=%d\n",
+		bdata - bootmem_node_data, start, end, aligned);
+	map = bdata->node_bootmem_map;
+
+	while (start < end) {
+		unsigned long idx, vec;
+
+		idx = start - bdata->node_min_pfn;
+		vec = ~map[idx / BITS_PER_LONG];
+
+		if (aligned && vec == ~0UL && start + BITS_PER_LONG < end) {
+			if (free_start == -1UL) {
+				free_start = idx;
+				free_end = free_start + BITS_PER_LONG;
+			} else {
+				if (free_end == idx) {
+					free_end += BITS_PER_LONG;
+				} else {
+					/* there is gap, print old */
+					printk(KERN_DEBUG "  free [0x%010lx - 0x%010lx]\n",
+							free_start + bdata->node_min_pfn,
+							free_end + bdata->node_min_pfn);
+					free_start = idx;
+					free_end = idx + BITS_PER_LONG;
+				}
+			}
+			count += BITS_PER_LONG;
+		} else {
+			unsigned long off = 0;
+
+			while (vec && off < BITS_PER_LONG) {
+				if (vec & 1) {
+					if (free_start == -1UL) {
+						free_start = idx + off;
+						free_end = free_start + 1;
+					} else {
+						if (free_end == (idx + off)) {
+							free_end++;
+						} else {
+							/* there is gap, print old */
+							printk(KERN_DEBUG "  free [0x%010lx - 0x%010lx]\n",
+								free_start + bdata->node_min_pfn,
+								free_end + bdata->node_min_pfn);
+							free_start = idx + off;
+							free_end = free_start + 1;
+						}
+					}
+					count++;
+				}
+				vec >>= 1;
+				off++;
+			}
+		}
+		start += BITS_PER_LONG;
+	}
+
+	/* last one */
+	if (free_start != -1UL)
+		printk(KERN_DEBUG "  free [0x%010lx - 0x%010lx]\n",
+			free_start + bdata->node_min_pfn,
+			free_end + bdata->node_min_pfn);
+	printk(KERN_DEBUG "  total free 0x%010lx\n", count);
+}
+
+void __init print_bootmem_free(void)
+{
+	bootmem_data_t *bdata;
+
+	list_for_each_entry(bdata, &bdata_list, list) {
+		print_all_bootmem_free_core(bdata);
+	}
+}
+
 static int __init __reserve(bootmem_data_t *bdata, unsigned long sidx,
 			unsigned long eidx, int flags)
 {
-- 
1.6.4.2

[PATCH 15/29] x86: make early_node_mem get mem > 4g if possible

[Yinghai Lu]

so we could put pgdata for the node high, and later sparse
vmmap will get the section nr that need.

with this patch will make <4g ram will not use sparse vmmap

before this patch, will get, before swiotlb try get bootmem
[    0.000000] nid=1 start=0 end=2080000 aligned=1
[    0.000000]   free [10 - 96]
[    0.000000]   free [b12 - 1000]
[    0.000000]   free [359f - 38a3]
[    0.000000]   free [38b5 - 3a00]
[    0.000000]   free [41e01 - 42000]
[    0.000000]   free [73dde - 73e00]
[    0.000000]   free [73fdd - 74000]
[    0.000000]   free [741dd - 74200]
[    0.000000]   free [743dd - 74400]
[    0.000000]   free [745dd - 74600]
[    0.000000]   free [747dd - 74800]
[    0.000000]   free [749dd - 74a00]
[    0.000000]   free [74bdd - 74c00]
[    0.000000]   free [74ddd - 74e00]
[    0.000000]   free [74fdd - 75000]
[    0.000000]   free [751dd - 75200]
[    0.000000]   free [753dd - 75400]
[    0.000000]   free [755dd - 75600]
[    0.000000]   free [757dd - 75800]
[    0.000000]   free [759dd - 75a00]
[    0.000000]   free [75bdd - 7bf5f]
[    0.000000]   free [7f730 - 7f750]
[    0.000000]   free [100000 - 2080000]
[    0.000000]   total free 1f87170
[   93.301474] Placing 64MB software IO TLB between ffff880075bdd000 - ffff880079bdd000
[   93.311814] software IO TLB at phys 0x75bdd000 - 0x79bdd000

with this patch will get: before swiotlb try get bootmem
[    0.000000] nid=1 start=0 end=2080000 aligned=1
[    0.000000]   free [a - 96]
[    0.000000]   free [702 - 1000]
[    0.000000]   free [359f - 3600]
[    0.000000]   free [37de - 3800]
[    0.000000]   free [39dd - 3a00]
[    0.000000]   free [3bdd - 3c00]
[    0.000000]   free [3ddd - 3e00]
[    0.000000]   free [3fdd - 4000]
[    0.000000]   free [41dd - 4200]
[    0.000000]   free [43dd - 4400]
[    0.000000]   free [45dd - 4600]
[    0.000000]   free [47dd - 4800]
[    0.000000]   free [49dd - 4a00]
[    0.000000]   free [4bdd - 4c00]
[    0.000000]   free [4ddd - 4e00]
[    0.000000]   free [4fdd - 5000]
[    0.000000]   free [51dd - 5200]
[    0.000000]   free [53dd - 5400]
[    0.000000]   free [55dd - 7bf5f]
[    0.000000]   free [7f730 - 7f750]
[    0.000000]   free [100428 - 100600]
[    0.000000]   free [13ea01 - 13ec00]
[    0.000000]   free [170800 - 2080000]
[    0.000000]   total free 1f87170

[   92.689485] PCI-DMA: Using software bounce buffering for IO (SWIOTLB)
[   92.699799] Placing 64MB software IO TLB between ffff8800055dd000 - ffff8800095dd000
[   92.710916] software IO TLB at phys 0x55dd000 - 0x95dd000

so will get enough space below 4G, aka pfn 0x100000

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
---
 arch/x86/mm/numa_64.c |   23 ++++++++++++++++++-----
 1 files changed, 18 insertions(+), 5 deletions(-)

diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c
index 3232148..02f13cb 100644
--- a/arch/x86/mm/numa_64.c
+++ b/arch/x86/mm/numa_64.c
@@ -163,14 +163,27 @@ static void * __init early_node_mem(int nodeid, unsigned long start,
 				    unsigned long end, unsigned long size,
 				    unsigned long align)
 {
-	unsigned long mem = find_e820_area(start, end, size, align);
+	unsigned long mem;
 
+	/*
+	 * put it on high as possible
+	 * something will go with NODE_DATA
+	 */
+	if (start < (MAX_DMA_PFN<<PAGE_SHIFT))
+		start = MAX_DMA_PFN<<PAGE_SHIFT;
+	if (start < (MAX_DMA32_PFN<<PAGE_SHIFT) &&
+	    end > (MAX_DMA32_PFN<<PAGE_SHIFT))
+		start = MAX_DMA32_PFN<<PAGE_SHIFT;
+	mem = find_e820_area(start, end, size, align);
 	if (mem != -1L)
 		return __va(mem);
 
-
-	start = __pa(MAX_DMA_ADDRESS);
-	end = max_low_pfn_mapped << PAGE_SHIFT;
+	/* extend the search scope */
+	end = max_pfn_mapped << PAGE_SHIFT;
+	if (end > (MAX_DMA32_PFN<<PAGE_SHIFT))
+		start = MAX_DMA32_PFN<<PAGE_SHIFT;
+	else
+		start = MAX_DMA_PFN<<PAGE_SHIFT;
 	mem = find_e820_area(start, end, size, align);
 	if (mem != -1L)
 		return __va(mem);
-- 
1.6.4.2

[PATCH 16/29] x86: only call dma32_reserve_bootmem 64bit !CONFIG_NUMA

[Yinghai Lu]

64bit NUMA already make enough space under 4G with new early_node_mem

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
---
 arch/x86/include/asm/pci.h    |    2 ++
 arch/x86/include/asm/pci_64.h |    2 --
 arch/x86/kernel/pci-dma.c     |   13 ++++++++++---
 arch/x86/kernel/setup.c       |    7 -------
 4 files changed, 12 insertions(+), 12 deletions(-)

diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h
index ada8c20..b4a00dd 100644
--- a/arch/x86/include/asm/pci.h
+++ b/arch/x86/include/asm/pci.h
@@ -124,6 +124,8 @@ extern void pci_iommu_alloc(void);
 #include "pci_64.h"
 #endif
 
+void dma32_reserve_bootmem(void);
+
 /* implement the pci_ DMA API in terms of the generic device dma_ one */
 #include <asm-generic/pci-dma-compat.h>
 
diff --git a/arch/x86/include/asm/pci_64.h b/arch/x86/include/asm/pci_64.h
index ae5e40f..fe15cfb 100644
--- a/arch/x86/include/asm/pci_64.h
+++ b/arch/x86/include/asm/pci_64.h
@@ -22,8 +22,6 @@ extern int (*pci_config_read)(int seg, int bus, int dev, int fn,
 extern int (*pci_config_write)(int seg, int bus, int dev, int fn,
 			       int reg, int len, u32 value);
 
-extern void dma32_reserve_bootmem(void);
-
 #endif /* __KERNEL__ */
 
 #endif /* _ASM_X86_PCI_64_H */
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index 75e14e2..1aa966c 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -65,7 +65,7 @@ int dma_set_mask(struct device *dev, u64 mask)
 }
 EXPORT_SYMBOL(dma_set_mask);
 
-#ifdef CONFIG_X86_64
+#if defined(CONFIG_X86_64) && !defined(CONFIG_NUMA)
 static __initdata void *dma32_bootmem_ptr;
 static unsigned long dma32_bootmem_size __initdata = (128ULL<<20);
 
@@ -116,14 +116,21 @@ static void __init dma32_free_bootmem(void)
 	dma32_bootmem_ptr = NULL;
 	dma32_bootmem_size = 0;
 }
+#else
+void __init dma32_reserve_bootmem(void)
+{
+}
+static void __init dma32_free_bootmem(void)
+{
+}
+
 #endif
 
 void __init pci_iommu_alloc(void)
 {
-#ifdef CONFIG_X86_64
 	/* free the range so iommu could get some range less than 4G */
 	dma32_free_bootmem();
-#endif
+
 	if (pci_swiotlb_detect())
 		goto out;
 
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 3ab0bf4..2c67cab 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -944,14 +944,7 @@ void __init setup_arch(char **cmdline_p)
 	initmem_init(0, max_pfn, acpi, k8);
 	early_res_to_bootmem(0, max_low_pfn<<PAGE_SHIFT);
 
-#ifdef CONFIG_X86_64
-	/*
-	 * dma32_reserve_bootmem() allocates bootmem which may conflict
-	 * with the crashkernel command line, so do that after
-	 * reserve_crashkernel()
-	 */
 	dma32_reserve_bootmem();
-#endif
 
 	reserve_ibft_region();
 
-- 
1.6.4.2

[PATCH 17/29] x86: make 64 bit use early_res instead of bootmem before slab

[Yinghai Lu]

finally we can use early_res to replace bootmem for x86_64 now.

still can use CONFIG_NO_BOOTMEM to enable it or not

-v2: fix 32bit compiling about MAX_DMA32_PFN

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
---
 arch/x86/Kconfig            |    7 ++
 arch/x86/include/asm/e820.h |    6 ++
 arch/x86/kernel/e820.c      |  159 ++++++++++++++++++++++++++++++++---
 arch/x86/kernel/setup.c     |    2 +
 arch/x86/mm/init_64.c       |    7 ++-
 arch/x86/mm/numa_64.c       |   20 ++++-
 include/linux/bootmem.h     |    7 ++
 include/linux/mm.h          |    5 +
 include/linux/mmzone.h      |    2 +
 mm/bootmem.c                |  195 ++++++++++++++++++++++++++++++++++++++++++-
 mm/page_alloc.c             |   59 +++++++++++++-
 mm/percpu.c                 |    3 +
 mm/sparse-vmemmap.c         |    2 +-
 13 files changed, 450 insertions(+), 24 deletions(-)

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index cbc1b98..ffb025c 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -567,6 +567,13 @@ config PARAVIRT_DEBUG
 	  Enable to debug paravirt_ops internals.  Specifically, BUG if
 	  a paravirt_op is missing when it is called.
 
+config NO_BOOTMEM
+	default y
+	bool "Disable Bootmem code"
+	depends on X86_64
+	---help---
+	  use early_res directly instead of bootmem before slab is ready.
+
 config MEMTEST
 	bool "Memtest"
 	---help---
diff --git a/arch/x86/include/asm/e820.h b/arch/x86/include/asm/e820.h
index 761249e..7d72e5f 100644
--- a/arch/x86/include/asm/e820.h
+++ b/arch/x86/include/asm/e820.h
@@ -117,6 +117,12 @@ extern void free_early(u64 start, u64 end);
 extern void early_res_to_bootmem(u64 start, u64 end);
 extern u64 early_reserve_e820(u64 startt, u64 sizet, u64 align);
 
+void reserve_early_without_check(u64 start, u64 end, char *name);
+u64 find_early_area(u64 ei_start, u64 ei_last, u64 start, u64 end,
+			 u64 size, u64 align);
+#include <linux/range.h>
+int get_free_all_memory_range(struct range **rangep, int nodeid);
+
 extern unsigned long e820_end_of_ram_pfn(void);
 extern unsigned long e820_end_of_low_ram_pfn(void);
 extern int e820_find_active_region(const struct e820entry *ei,
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 949d688..155b2d6 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -969,6 +969,25 @@ void __init reserve_early(u64 start, u64 end, char *name)
 	__reserve_early(start, end, name, 0);
 }
 
+void __init reserve_early_without_check(u64 start, u64 end, char *name)
+{
+	struct early_res *r;
+
+	if (start >= end)
+		return;
+
+	__check_and_double_early_res(end);
+
+	r = &early_res[early_res_count];
+
+	r->start = start;
+	r->end = end;
+	r->overlap_ok = 0;
+	if (name)
+		strncpy(r->name, name, sizeof(r->name) - 1);
+	early_res_count++;
+}
+
 void __init free_early(u64 start, u64 end)
 {
 	struct early_res *r;
@@ -983,6 +1002,94 @@ void __init free_early(u64 start, u64 end)
 	drop_range(i);
 }
 
+#ifdef CONFIG_NO_BOOTMEM
+static void __init subtract_early_res(struct range *range, int az)
+{
+	int i, count;
+	u64 final_start, final_end;
+	int idx = 0;
+
+	count  = 0;
+	for (i = 0; i < max_early_res && early_res[i].end; i++)
+		count++;
+
+	/* need to skip first one ?*/
+	if (early_res != early_res_x)
+		idx = 1;
+
+#if 1
+	printk(KERN_INFO "Subtract (%d early reservations)\n", count);
+#endif
+	for (i = idx; i < count; i++) {
+		struct early_res *r = &early_res[i];
+#if 0
+		printk(KERN_INFO "  #%d [%010llx - %010llx] %15s", i,
+			r->start, r->end, r->name);
+#endif
+		final_start = PFN_DOWN(r->start);
+		final_end = PFN_UP(r->end);
+		if (final_start >= final_end) {
+#if 0
+			printk(KERN_CONT "\n");
+#endif
+			continue;
+		}
+#if 0
+		printk(KERN_CONT " subtract pfn [%010llx - %010llx]\n",
+			final_start, final_end);
+#endif
+		subtract_range(range, az, final_start, final_end - 1);
+	}
+
+}
+
+int __init get_free_all_memory_range(struct range **rangep, int nodeid)
+{
+	int i, count;
+	u64 start = 0, end;
+	u64 size;
+	u64 mem;
+	struct range *range;
+	int nr_range;
+
+	count  = 0;
+	for (i = 0; i < max_early_res && early_res[i].end; i++)
+		count++;
+
+	count *= 2;
+
+	size = sizeof(struct range) * count;
+#ifdef MAX_DMA32_PFN
+	if (max_pfn_mapped > MAX_DMA32_PFN)
+		start = MAX_DMA32_PFN << PAGE_SHIFT;
+#endif
+	end = max_pfn_mapped << PAGE_SHIFT;
+	mem = find_e820_area(start, end, size, sizeof(struct range));
+	if (mem == -1ULL)
+		panic("can not find more space for range free");
+
+	range = __va(mem);
+	/* use early_node_map[] and early_res to get range array at first */
+	memset(range, 0, size);
+	nr_range = 0;
+
+	/* need to go over early_node_map to find out good range for node */
+	nr_range = add_from_early_node_map(range, count, nr_range, nodeid);
+	subtract_early_res(range, count);
+	nr_range = clean_sort_range(range, count);
+
+	/* need to clear it ? */
+	if (nodeid == MAX_NUMNODES) {
+		memset(&early_res[0], 0,
+			 sizeof(struct early_res) * max_early_res);
+		early_res = NULL;
+		max_early_res = 0;
+	}
+
+	*rangep = range;
+	return nr_range;
+}
+#else
 void __init early_res_to_bootmem(u64 start, u64 end)
 {
 	int i, count;
@@ -1020,6 +1127,7 @@ void __init early_res_to_bootmem(u64 start, u64 end)
 	max_early_res = 0;
 	early_res_count = 0;
 }
+#endif
 
 /* Check for already reserved areas */
 static inline int __init bad_addr(u64 *addrp, u64 size, u64 align)
@@ -1075,6 +1183,35 @@ again:
 
 /*
  * Find a free area with specified alignment in a specific range.
+ * only with the area.between start to end is active range from early_node_map
+ * so they are good as RAM
+ */
+u64 __init find_early_area(u64 ei_start, u64 ei_last, u64 start, u64 end,
+			 u64 size, u64 align)
+{
+	u64 addr, last;
+
+	addr = round_up(ei_start, align);
+	if (addr < start)
+		addr = round_up(start, align);
+	if (addr >= ei_last)
+		goto out;
+	while (bad_addr(&addr, size, align) && addr+size <= ei_last)
+		;
+	last = addr + size;
+	if (last > ei_last)
+		goto out;
+	if (last > end)
+		goto out;
+
+	return addr;
+
+out:
+	return -1ULL;
+}
+
+/*
+ * Find a free area with specified alignment in a specific range.
  */
 u64 __init find_e820_area(u64 start, u64 end, u64 size, u64 align)
 {
@@ -1082,24 +1219,20 @@ u64 __init find_e820_area(u64 start, u64 end, u64 size, u64 align)
 
 	for (i = 0; i < e820.nr_map; i++) {
 		struct e820entry *ei = &e820.map[i];
-		u64 addr, last;
-		u64 ei_last;
+		u64 addr;
+		u64 ei_start, ei_last;
 
 		if (ei->type != E820_RAM)
 			continue;
-		addr = round_up(ei->addr, align);
+
 		ei_last = ei->addr + ei->size;
-		if (addr < start)
-			addr = round_up(start, align);
-		if (addr >= ei_last)
-			continue;
-		while (bad_addr(&addr, size, align) && addr+size <= ei_last)
-			;
-		last = addr + size;
-		if (last > ei_last)
-			continue;
-		if (last > end)
+		ei_start = ei->addr;
+		addr = find_early_area(ei_start, ei_last, start, end,
+					 size, align);
+
+		if (addr == -1ULL)
 			continue;
+
 		return addr;
 	}
 	return -1ULL;
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 2c67cab..824fef7 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -942,7 +942,9 @@ void __init setup_arch(char **cmdline_p)
 #endif
 
 	initmem_init(0, max_pfn, acpi, k8);
+#ifndef CONFIG_NO_BOOTMEM
 	early_res_to_bootmem(0, max_low_pfn<<PAGE_SHIFT);
+#endif
 
 	dma32_reserve_bootmem();
 
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index f9530eb..f13e5bd 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -571,6 +571,7 @@ kernel_physical_mapping_init(unsigned long start,
 void __init initmem_init(unsigned long start_pfn, unsigned long end_pfn,
 				int acpi, int k8)
 {
+#ifndef CONFIG_NO_BOOTMEM
 	unsigned long bootmap_size, bootmap;
 
 	bootmap_size = bootmem_bootmap_pages(end_pfn)<<PAGE_SHIFT;
@@ -582,8 +583,10 @@ void __init initmem_init(unsigned long start_pfn, unsigned long end_pfn,
 	/* don't touch min_low_pfn */
 	bootmap_size = init_bootmem_node(NODE_DATA(0), bootmap >> PAGE_SHIFT,
 					 0, end_pfn);
-	e820_register_active_regions(0, start_pfn, end_pfn);
 	free_bootmem_with_active_regions(0, end_pfn);
+#else
+	e820_register_active_regions(0, start_pfn, end_pfn);
+#endif
 }
 #endif
 
@@ -654,7 +657,9 @@ void __init mem_init(void)
 	long codesize, reservedpages, datasize, initsize;
 	unsigned long absent_pages;
 
+#ifndef CONFIG_NO_BOOTMEM
 	print_bootmem_free();
+#endif
 
 	pci_iommu_alloc();
 
diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c
index 02f13cb..a20e170 100644
--- a/arch/x86/mm/numa_64.c
+++ b/arch/x86/mm/numa_64.c
@@ -198,11 +198,13 @@ static void * __init early_node_mem(int nodeid, unsigned long start,
 void __init
 setup_node_bootmem(int nodeid, unsigned long start, unsigned long end)
 {
-	unsigned long start_pfn, last_pfn, bootmap_pages, bootmap_size;
+	unsigned long start_pfn, last_pfn, nodedata_phys;
 	const int pgdat_size = roundup(sizeof(pg_data_t), PAGE_SIZE);
-	unsigned long bootmap_start, nodedata_phys;
-	void *bootmap;
 	int nid;
+#ifndef CONFIG_NO_BOOTMEM
+	unsigned long bootmap_start, bootmap_pages, bootmap_size;
+	void *bootmap;
+#endif
 
 	if (!end)
 		return;
@@ -216,7 +218,7 @@ setup_node_bootmem(int nodeid, unsigned long start, unsigned long end)
 
 	start = roundup(start, ZONE_ALIGN);
 
-	printk(KERN_INFO "Bootmem setup node %d %016lx-%016lx\n", nodeid,
+	printk(KERN_INFO "Initmem setup node %d %016lx-%016lx\n", nodeid,
 	       start, end);
 
 	start_pfn = start >> PAGE_SHIFT;
@@ -235,10 +237,13 @@ setup_node_bootmem(int nodeid, unsigned long start, unsigned long end)
 		printk(KERN_INFO "    NODE_DATA(%d) on node %d\n", nodeid, nid);
 
 	memset(NODE_DATA(nodeid), 0, sizeof(pg_data_t));
-	NODE_DATA(nodeid)->bdata = &bootmem_node_data[nodeid];
+	NODE_DATA(nodeid)->node_id = nodeid;
 	NODE_DATA(nodeid)->node_start_pfn = start_pfn;
 	NODE_DATA(nodeid)->node_spanned_pages = last_pfn - start_pfn;
 
+#ifndef CONFIG_NO_BOOTMEM
+	NODE_DATA(nodeid)->bdata = &bootmem_node_data[nodeid];
+
 	/*
 	 * Find a place for the bootmem map
 	 * nodedata_phys could be on other nodes by alloc_bootmem,
@@ -275,6 +280,7 @@ setup_node_bootmem(int nodeid, unsigned long start, unsigned long end)
 		printk(KERN_INFO "    bootmap(%d) on node %d\n", nodeid, nid);
 
 	free_bootmem_with_active_regions(nodeid, end);
+#endif
 
 	node_set_online(nodeid);
 }
@@ -733,6 +739,10 @@ unsigned long __init numa_free_all_bootmem(void)
 	for_each_online_node(i)
 		pages += free_all_bootmem_node(NODE_DATA(i));
 
+#ifdef CONFIG_NO_BOOTMEM
+	pages += free_all_memory_core_early(MAX_NUMNODES);
+#endif
+
 	return pages;
 }
 
diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h
index 3446bed..383daa8 100644
--- a/include/linux/bootmem.h
+++ b/include/linux/bootmem.h
@@ -23,6 +23,7 @@ extern unsigned long max_pfn;
 extern unsigned long saved_max_pfn;
 #endif
 
+#ifndef CONFIG_NO_BOOTMEM
 /*
  * node_bootmem_map is a map pointer - the bits represent all physical 
  * memory pages (including holes) on the node.
@@ -37,6 +38,7 @@ typedef struct bootmem_data {
 } bootmem_data_t;
 
 extern bootmem_data_t bootmem_node_data[];
+#endif
 
 extern unsigned long bootmem_bootmap_pages(unsigned long);
 
@@ -46,6 +48,7 @@ extern unsigned long init_bootmem_node(pg_data_t *pgdat,
 				       unsigned long endpfn);
 extern unsigned long init_bootmem(unsigned long addr, unsigned long memend);
 
+unsigned long free_all_memory_core_early(int nodeid);
 extern unsigned long free_all_bootmem_node(pg_data_t *pgdat);
 extern unsigned long free_all_bootmem(void);
 
@@ -86,6 +89,10 @@ extern void *__alloc_bootmem_node(pg_data_t *pgdat,
 				  unsigned long size,
 				  unsigned long align,
 				  unsigned long goal);
+void *__alloc_bootmem_node_high(pg_data_t *pgdat,
+				  unsigned long size,
+				  unsigned long align,
+				  unsigned long goal);
 extern void *__alloc_bootmem_node_nopanic(pg_data_t *pgdat,
 				  unsigned long size,
 				  unsigned long align,
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 2265f28..c94ce6c 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -12,6 +12,7 @@
 #include <linux/prio_tree.h>
 #include <linux/debug_locks.h>
 #include <linux/mm_types.h>
+#include <linux/range.h>
 
 struct mempolicy;
 struct anon_vma;
@@ -1047,6 +1048,10 @@ extern void get_pfn_range_for_nid(unsigned int nid,
 extern unsigned long find_min_pfn_with_active_regions(void);
 extern void free_bootmem_with_active_regions(int nid,
 						unsigned long max_low_pfn);
+int add_from_early_node_map(struct range *range, int az,
+				   int nr_range, int nid);
+void *__alloc_memory_core_early(int nodeid, u64 size, u64 align,
+				 u64 goal, u64 limit);
 typedef int (*work_fn_t)(unsigned long, unsigned long, void *);
 extern void work_with_active_regions(int nid, work_fn_t work_fn, void *data);
 extern void sparse_memory_present_with_active_regions(int nid);
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 30fe668..eae8387 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -620,7 +620,9 @@ typedef struct pglist_data {
 	struct page_cgroup *node_page_cgroup;
 #endif
 #endif
+#ifndef CONFIG_NO_BOOTMEM
 	struct bootmem_data *bdata;
+#endif
 #ifdef CONFIG_MEMORY_HOTPLUG
 	/*
 	 * Must be held any time you expect node_start_pfn, node_present_pages
diff --git a/mm/bootmem.c b/mm/bootmem.c
index eec89ed..64a5000 100644
--- a/mm/bootmem.c
+++ b/mm/bootmem.c
@@ -13,6 +13,7 @@
 #include <linux/bootmem.h>
 #include <linux/module.h>
 #include <linux/kmemleak.h>
+#include <linux/range.h>
 
 #include <asm/bug.h>
 #include <asm/io.h>
@@ -32,6 +33,7 @@ unsigned long max_pfn;
 unsigned long saved_max_pfn;
 #endif
 
+#ifndef CONFIG_NO_BOOTMEM
 bootmem_data_t bootmem_node_data[MAX_NUMNODES] __initdata;
 
 static struct list_head bdata_list __initdata = LIST_HEAD_INIT(bdata_list);
@@ -142,7 +144,7 @@ unsigned long __init init_bootmem(unsigned long start, unsigned long pages)
 	min_low_pfn = start;
 	return init_bootmem_core(NODE_DATA(0)->bdata, start, 0, pages);
 }
-
+#endif
 /*
  * free_bootmem_late - free bootmem pages directly to page allocator
  * @addr: starting address of the range
@@ -167,6 +169,60 @@ void __init free_bootmem_late(unsigned long addr, unsigned long size)
 	}
 }
 
+#ifdef CONFIG_NO_BOOTMEM
+static void __init __free_pages_memory(unsigned long start, unsigned long end)
+{
+	int i;
+	unsigned long start_aligned, end_aligned;
+	int order = ilog2(BITS_PER_LONG);
+
+	start_aligned = (start + (BITS_PER_LONG - 1)) & ~(BITS_PER_LONG - 1);
+	end_aligned = end & ~(BITS_PER_LONG - 1);
+
+	if (end_aligned <= start_aligned) {
+#if 1
+		printk(KERN_DEBUG " %lx - %lx\n", start, end);
+#endif
+		for (i = start; i < end; i++)
+			__free_pages_bootmem(pfn_to_page(i), 0);
+
+		return;
+	}
+
+#if 1
+	printk(KERN_DEBUG " %lx %lx - %lx %lx\n",
+		 start, start_aligned, end_aligned, end);
+#endif
+	for (i = start; i < start_aligned; i++)
+		__free_pages_bootmem(pfn_to_page(i), 0);
+
+	for (i = start_aligned; i < end_aligned; i += BITS_PER_LONG)
+		__free_pages_bootmem(pfn_to_page(i), order);
+
+	for (i = end_aligned; i < end; i++)
+		__free_pages_bootmem(pfn_to_page(i), 0);
+}
+
+unsigned long __init free_all_memory_core_early(int nodeid)
+{
+	int i;
+	u64 start, end;
+	unsigned long count = 0;
+	struct range *range = NULL;
+	int nr_range;
+
+	nr_range = get_free_all_memory_range(&range, nodeid);
+
+	for (i = 0; i < nr_range; i++) {
+		start = range[i].start;
+		end = range[i].end + 1;
+		count += end - start;
+		__free_pages_memory(start, end);
+	}
+
+	return count;
+}
+#else
 static unsigned long __init free_all_bootmem_core(bootmem_data_t *bdata)
 {
 	int aligned;
@@ -227,6 +283,7 @@ static unsigned long __init free_all_bootmem_core(bootmem_data_t *bdata)
 
 	return count;
 }
+#endif
 
 /**
  * free_all_bootmem_node - release a node's free pages to the buddy allocator
@@ -237,7 +294,12 @@ static unsigned long __init free_all_bootmem_core(bootmem_data_t *bdata)
 unsigned long __init free_all_bootmem_node(pg_data_t *pgdat)
 {
 	register_page_bootmem_info_node(pgdat);
+#ifdef CONFIG_NO_BOOTMEM
+	/* free_all_memory_core_early(MAX_NUMNODES) will be called later */
+	return 0;
+#else
 	return free_all_bootmem_core(pgdat->bdata);
+#endif
 }
 
 /**
@@ -247,9 +309,14 @@ unsigned long __init free_all_bootmem_node(pg_data_t *pgdat)
  */
 unsigned long __init free_all_bootmem(void)
 {
+#ifdef CONFIG_NO_BOOTMEM
+	return free_all_memory_core_early(NODE_DATA(0)->node_id);
+#else
 	return free_all_bootmem_core(NODE_DATA(0)->bdata);
+#endif
 }
 
+#ifndef CONFIG_NO_BOOTMEM
 static void __init __free(bootmem_data_t *bdata,
 			unsigned long sidx, unsigned long eidx)
 {
@@ -436,6 +503,7 @@ static int __init mark_bootmem(unsigned long start, unsigned long end,
 	}
 	BUG();
 }
+#endif
 
 /**
  * free_bootmem_node - mark a page range as usable
@@ -450,6 +518,12 @@ static int __init mark_bootmem(unsigned long start, unsigned long end,
 void __init free_bootmem_node(pg_data_t *pgdat, unsigned long physaddr,
 			      unsigned long size)
 {
+#ifdef CONFIG_NO_BOOTMEM
+	free_early(physaddr, physaddr + size);
+#if 0
+	printk(KERN_DEBUG "free %lx %lx\n", physaddr, size);
+#endif
+#else
 	unsigned long start, end;
 
 	kmemleak_free_part(__va(physaddr), size);
@@ -458,6 +532,7 @@ void __init free_bootmem_node(pg_data_t *pgdat, unsigned long physaddr,
 	end = PFN_DOWN(physaddr + size);
 
 	mark_bootmem_node(pgdat->bdata, start, end, 0, 0);
+#endif
 }
 
 /**
@@ -471,6 +546,12 @@ 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
+	free_early(addr, addr + size);
+#if 0
+	printk(KERN_DEBUG "free %lx %lx\n", addr, size);
+#endif
+#else
 	unsigned long start, end;
 
 	kmemleak_free_part(__va(addr), size);
@@ -479,6 +560,7 @@ void __init free_bootmem(unsigned long addr, unsigned long size)
 	end = PFN_DOWN(addr + size);
 
 	mark_bootmem(start, end, 0, 0);
+#endif
 }
 
 /**
@@ -495,12 +577,17 @@ void __init free_bootmem(unsigned long addr, unsigned long size)
 int __init reserve_bootmem_node(pg_data_t *pgdat, unsigned long physaddr,
 				 unsigned long size, int flags)
 {
+#ifdef CONFIG_NO_BOOTMEM
+	panic("no bootmem");
+	return 0;
+#else
 	unsigned long start, end;
 
 	start = PFN_DOWN(physaddr);
 	end = PFN_UP(physaddr + size);
 
 	return mark_bootmem_node(pgdat->bdata, start, end, 1, flags);
+#endif
 }
 
 /**
@@ -516,14 +603,20 @@ int __init reserve_bootmem_node(pg_data_t *pgdat, unsigned long physaddr,
 int __init reserve_bootmem(unsigned long addr, unsigned long size,
 			    int flags)
 {
+#ifdef CONFIG_NO_BOOTMEM
+	panic("no bootmem");
+	return 0;
+#else
 	unsigned long start, end;
 
 	start = PFN_DOWN(addr);
 	end = PFN_UP(addr + size);
 
 	return mark_bootmem(start, end, 1, flags);
+#endif
 }
 
+#ifndef CONFIG_NO_BOOTMEM
 static unsigned long __init align_idx(struct bootmem_data *bdata,
 				      unsigned long idx, unsigned long step)
 {
@@ -674,12 +767,33 @@ static void * __init alloc_arch_preferred_bootmem(bootmem_data_t *bdata,
 #endif
 	return NULL;
 }
+#endif
 
 static void * __init ___alloc_bootmem_nopanic(unsigned long size,
 					unsigned long align,
 					unsigned long goal,
 					unsigned long limit)
 {
+#ifdef CONFIG_NO_BOOTMEM
+	void *ptr;
+
+	if (WARN_ON_ONCE(slab_is_available()))
+		return kzalloc(size, GFP_NOWAIT);
+
+restart:
+
+	ptr = __alloc_memory_core_early(MAX_NUMNODES, size, align, goal, limit);
+
+	if (ptr)
+		return ptr;
+
+	if (goal != 0) {
+		goal = 0;
+		goto restart;
+	}
+
+	return NULL;
+#else
 	bootmem_data_t *bdata;
 	void *region;
 
@@ -705,6 +819,7 @@ restart:
 	}
 
 	return NULL;
+#endif
 }
 
 /**
@@ -723,7 +838,13 @@ restart:
 void * __init __alloc_bootmem_nopanic(unsigned long size, unsigned long align,
 					unsigned long goal)
 {
-	return ___alloc_bootmem_nopanic(size, align, goal, 0);
+	unsigned long limit = 0;
+
+#ifdef CONFIG_NO_BOOTMEM
+	limit = -1UL;
+#endif
+
+	return ___alloc_bootmem_nopanic(size, align, goal, limit);
 }
 
 static void * __init ___alloc_bootmem(unsigned long size, unsigned long align,
@@ -757,9 +878,16 @@ static void * __init ___alloc_bootmem(unsigned long size, unsigned long align,
 void * __init __alloc_bootmem(unsigned long size, unsigned long align,
 			      unsigned long goal)
 {
-	return ___alloc_bootmem(size, align, goal, 0);
+	unsigned long limit = 0;
+
+#ifdef CONFIG_NO_BOOTMEM
+	limit = -1UL;
+#endif
+
+	return ___alloc_bootmem(size, align, goal, limit);
 }
 
+#ifndef CONFIG_NO_BOOTMEM
 static void * __init ___alloc_bootmem_node(bootmem_data_t *bdata,
 				unsigned long size, unsigned long align,
 				unsigned long goal, unsigned long limit)
@@ -776,6 +904,7 @@ static void * __init ___alloc_bootmem_node(bootmem_data_t *bdata,
 
 	return ___alloc_bootmem(size, align, goal, limit);
 }
+#endif
 
 /**
  * __alloc_bootmem_node - allocate boot memory from a specific node
@@ -798,7 +927,46 @@ void * __init __alloc_bootmem_node(pg_data_t *pgdat, unsigned long size,
 	if (WARN_ON_ONCE(slab_is_available()))
 		return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id);
 
+#ifdef CONFIG_NO_BOOTMEM
+	return __alloc_memory_core_early(pgdat->node_id, size, align,
+					 goal, -1ULL);
+#else
 	return ___alloc_bootmem_node(pgdat->bdata, size, align, goal, 0);
+#endif
+}
+
+void * __init __alloc_bootmem_node_high(pg_data_t *pgdat, unsigned long size,
+				   unsigned long align, unsigned long goal)
+{
+#ifdef MAX_DMA32_PFN
+	unsigned long end_pfn;
+
+	if (WARN_ON_ONCE(slab_is_available()))
+		return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id);
+
+	/* update goal according ...MAX_DMA32_PFN */
+	end_pfn = pgdat->node_start_pfn + pgdat->node_spanned_pages;
+
+	if (end_pfn > MAX_DMA32_PFN + (128 >> (20 - PAGE_SHIFT)) &&
+	    (goal >> PAGE_SHIFT) < MAX_DMA32_PFN) {
+		void *ptr;
+		unsigned long new_goal;
+
+		new_goal = MAX_DMA32_PFN << PAGE_SHIFT;
+#ifdef CONFIG_NO_BOOTMEM
+		ptr =  __alloc_memory_core_early(pgdat->node_id, size, align,
+						 new_goal, -1ULL);
+#else
+		ptr = alloc_bootmem_core(pgdat->bdata, size, align,
+						 new_goal, 0);
+#endif
+		if (ptr)
+			return ptr;
+	}
+#endif
+
+	return __alloc_bootmem_node(pgdat, size, align, goal);
+
 }
 
 #ifdef CONFIG_SPARSEMEM
@@ -812,6 +980,16 @@ void * __init __alloc_bootmem_node(pg_data_t *pgdat, unsigned long size,
 void * __init alloc_bootmem_section(unsigned long size,
 				    unsigned long section_nr)
 {
+#ifdef CONFIG_NO_BOOTMEM
+	unsigned long pfn, goal, limit;
+
+	pfn = section_nr_to_pfn(section_nr);
+	goal = pfn << PAGE_SHIFT;
+	limit = section_nr_to_pfn(section_nr + 1) << PAGE_SHIFT;
+
+	return __alloc_memory_core_early(early_pfn_to_nid(pfn), size,
+					 SMP_CACHE_BYTES, goal, limit);
+#else
 	bootmem_data_t *bdata;
 	unsigned long pfn, goal, limit;
 
@@ -821,6 +999,7 @@ void * __init alloc_bootmem_section(unsigned long size,
 	bdata = &bootmem_node_data[early_pfn_to_nid(pfn)];
 
 	return alloc_bootmem_core(bdata, size, SMP_CACHE_BYTES, goal, limit);
+#endif
 }
 #endif
 
@@ -832,11 +1011,16 @@ void * __init __alloc_bootmem_node_nopanic(pg_data_t *pgdat, unsigned long size,
 	if (WARN_ON_ONCE(slab_is_available()))
 		return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id);
 
+#ifdef CONFIG_NO_BOOTMEM
+	ptr =  __alloc_memory_core_early(pgdat->node_id, size, align,
+						 goal, -1ULL);
+#else
 	ptr = alloc_arch_preferred_bootmem(pgdat->bdata, size, align, goal, 0);
 	if (ptr)
 		return ptr;
 
 	ptr = alloc_bootmem_core(pgdat->bdata, size, align, goal, 0);
+#endif
 	if (ptr)
 		return ptr;
 
@@ -887,6 +1071,11 @@ void * __init __alloc_bootmem_low_node(pg_data_t *pgdat, unsigned long size,
 	if (WARN_ON_ONCE(slab_is_available()))
 		return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id);
 
+#ifdef CONFIG_NO_BOOTMEM
+	return __alloc_memory_core_early(pgdat->node_id, size, align,
+				goal, ARCH_LOW_ADDRESS_LIMIT);
+#else
 	return ___alloc_bootmem_node(pgdat->bdata, size, align,
 				goal, ARCH_LOW_ADDRESS_LIMIT);
+#endif
 }
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 4e9f5cc..2ca7b0f 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3434,6 +3434,59 @@ void __init free_bootmem_with_active_regions(int nid,
 	}
 }
 
+int __init add_from_early_node_map(struct range *range, int az,
+				   int nr_range, int nid)
+{
+	int i;
+	u64 start, end;
+
+	/* need to go over early_node_map to find out good range for node */
+	for_each_active_range_index_in_nid(i, nid) {
+		start = early_node_map[i].start_pfn;
+		end = early_node_map[i].end_pfn;
+		nr_range = add_range(range, az, nr_range, start, end - 1);
+	}
+	return nr_range;
+}
+
+void * __init __alloc_memory_core_early(int nid, u64 size, u64 align,
+					u64 goal, u64 limit)
+{
+	int i;
+	void *ptr;
+
+	/* 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;
+
+		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");
+		return ptr;
+	}
+
+	return NULL;
+}
+
+
 void __init work_with_active_regions(int nid, work_fn_t work_fn, void *data)
 {
 	int i;
@@ -4466,7 +4519,11 @@ void __init set_dma_reserve(unsigned long new_dma_reserve)
 }
 
 #ifndef CONFIG_NEED_MULTIPLE_NODES
-struct pglist_data __refdata contig_page_data = { .bdata = &bootmem_node_data[0] };
+struct pglist_data __refdata contig_page_data = {
+#ifndef CONFIG_NO_BOOTMEM
+ .bdata = &bootmem_node_data[0]
+#endif
+ };
 EXPORT_SYMBOL(contig_page_data);
 #endif
 
diff --git a/mm/percpu.c b/mm/percpu.c
index 442010c..48bb212 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -1927,7 +1927,10 @@ int __init pcpu_embed_first_chunk(size_t reserved_size, ssize_t dyn_size,
 			}
 			/* copy and return the unused part */
 			memcpy(ptr, __per_cpu_load, ai->static_size);
+#ifndef CONFIG_NO_BOOTMEM
+			/* fix partial free ! */
 			free_fn(ptr + size_sum, ai->unit_size - size_sum);
+#endif
 		}
 	}
 
diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c
index d9714bd..9506c39 100644
--- a/mm/sparse-vmemmap.c
+++ b/mm/sparse-vmemmap.c
@@ -40,7 +40,7 @@ static void * __init_refok __earlyonly_bootmem_alloc(int node,
 				unsigned long align,
 				unsigned long goal)
 {
-	return __alloc_bootmem_node(NODE_DATA(node), size, align, goal);
+	return __alloc_bootmem_node_high(NODE_DATA(node), size, align, goal);
 }
 
 
-- 
1.6.4.2

[PATCH 18/29] sparsemem: put usemap for one node together

[Yinghai Lu]

could save some buf instead of applying one by one

could help that system that is going to use early_res instead of bootmem
less entries in early_res make search more faster on system with more memory.

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
---
 mm/sparse.c |   84 ++++++++++++++++++++++++++++++++++++++++++++++------------
 1 files changed, 66 insertions(+), 18 deletions(-)

diff --git a/mm/sparse.c b/mm/sparse.c
index 6ce4aab..0cdaf0b 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -271,7 +271,8 @@ static unsigned long *__kmalloc_section_usemap(void)
 
 #ifdef CONFIG_MEMORY_HOTREMOVE
 static unsigned long * __init
-sparse_early_usemap_alloc_pgdat_section(struct pglist_data *pgdat)
+sparse_early_usemaps_alloc_pgdat_section(struct pglist_data *pgdat,
+					 unsigned long count)
 {
 	unsigned long section_nr;
 
@@ -286,7 +287,7 @@ sparse_early_usemap_alloc_pgdat_section(struct pglist_data *pgdat)
 	 * this problem.
 	 */
 	section_nr = pfn_to_section_nr(__pa(pgdat) >> PAGE_SHIFT);
-	return alloc_bootmem_section(usemap_size(), section_nr);
+	return alloc_bootmem_section(usemap_size() * count, section_nr);
 }
 
 static void __init check_usemap_section_nr(int nid, unsigned long *usemap)
@@ -329,7 +330,8 @@ static void __init check_usemap_section_nr(int nid, unsigned long *usemap)
 }
 #else
 static unsigned long * __init
-sparse_early_usemap_alloc_pgdat_section(struct pglist_data *pgdat)
+sparse_early_usemaps_alloc_pgdat_section(struct pglist_data *pgdat,
+					 unsigned long count)
 {
 	return NULL;
 }
@@ -339,27 +341,40 @@ static void __init check_usemap_section_nr(int nid, unsigned long *usemap)
 }
 #endif /* CONFIG_MEMORY_HOTREMOVE */
 
-static unsigned long *__init sparse_early_usemap_alloc(unsigned long pnum)
+static void __init sparse_early_usemaps_alloc_node(unsigned long**usemap_map,
+				 unsigned long pnum_begin,
+				 unsigned long pnum_end,
+				 unsigned long usemap_count, int nodeid)
 {
-	unsigned long *usemap;
-	struct mem_section *ms = __nr_to_section(pnum);
-	int nid = sparse_early_nid(ms);
-
-	usemap = sparse_early_usemap_alloc_pgdat_section(NODE_DATA(nid));
-	if (usemap)
-		return usemap;
+	void *usemap;
+	unsigned long pnum;
+	int size = usemap_size();
 
-	usemap = alloc_bootmem_node(NODE_DATA(nid), usemap_size());
+	usemap = sparse_early_usemaps_alloc_pgdat_section(NODE_DATA(nodeid),
+								 usemap_count);
 	if (usemap) {
-		check_usemap_section_nr(nid, usemap);
-		return usemap;
+		for (pnum = pnum_begin; pnum < pnum_end; pnum++) {
+			if (!present_section_nr(pnum))
+				continue;
+			usemap_map[pnum] = usemap;
+			usemap += size;
+		}
+		return;
 	}
 
-	/* Stupid: suppress gcc warning for SPARSEMEM && !NUMA */
-	nid = 0;
+	usemap = alloc_bootmem_node(NODE_DATA(nodeid), size * usemap_count);
+	if (usemap) {
+		for (pnum = pnum_begin; pnum < pnum_end; pnum++) {
+			if (!present_section_nr(pnum))
+				continue;
+			usemap_map[pnum] = usemap;
+			usemap += size;
+			check_usemap_section_nr(nodeid, usemap_map[pnum]);
+		}
+		return;
+	}
 
 	printk(KERN_WARNING "%s: allocation failed\n", __func__);
-	return NULL;
 }
 
 #ifndef CONFIG_SPARSEMEM_VMEMMAP
@@ -396,6 +411,7 @@ static struct page __init *sparse_early_mem_map_alloc(unsigned long pnum)
 void __attribute__((weak)) __meminit vmemmap_populate_print_last(void)
 {
 }
+
 /*
  * Allocate the accumulated non-linear sections, allocate a mem_map
  * for each and record the physical to section mapping.
@@ -407,6 +423,9 @@ void __init sparse_init(void)
 	unsigned long *usemap;
 	unsigned long **usemap_map;
 	int size;
+	int nodeid_begin = 0;
+	unsigned long pnum_begin = 0;
+	unsigned long usemap_count;
 
 	/*
 	 * map is using big page (aka 2M in x86 64 bit)
@@ -425,10 +444,39 @@ void __init sparse_init(void)
 		panic("can not allocate usemap_map\n");
 
 	for (pnum = 0; pnum < NR_MEM_SECTIONS; pnum++) {
+		struct mem_section *ms;
+
 		if (!present_section_nr(pnum))
 			continue;
-		usemap_map[pnum] = sparse_early_usemap_alloc(pnum);
+		ms = __nr_to_section(pnum);
+		nodeid_begin = sparse_early_nid(ms);
+		pnum_begin = pnum;
+		break;
+	}
+	usemap_count = 1;
+	for (pnum = pnum_begin + 1; pnum < NR_MEM_SECTIONS; pnum++) {
+		struct mem_section *ms;
+		int nodeid;
+
+		if (!present_section_nr(pnum))
+			continue;
+		ms = __nr_to_section(pnum);
+		nodeid = sparse_early_nid(ms);
+		if (nodeid == nodeid_begin) {
+			usemap_count++;
+			continue;
+		}
+		/* ok, we need to take cake of from pnum_begin to pnum - 1*/
+		sparse_early_usemaps_alloc_node(usemap_map, pnum_begin, pnum,
+						 usemap_count, nodeid_begin);
+		/* new start, update count etc*/
+		nodeid_begin = nodeid;
+		pnum_begin = pnum;
+		usemap_count = 1;
 	}
+	/* ok, last chunk */
+	sparse_early_usemaps_alloc_node(usemap_map, pnum_begin, NR_MEM_SECTIONS,
+					 usemap_count, nodeid_begin);
 
 	for (pnum = 0; pnum < NR_MEM_SECTIONS; pnum++) {
 		if (!present_section_nr(pnum))
-- 
1.6.4.2

[PATCH 19/29] sparsemem: put mem map for one node together.

[Yinghai Lu]

add vmemmap_alloc_block_buf for mem map only.

it will fallback old wayif can not get that big.

before this patch, when node have 128g ram installed, memmap are split into
 two parts or more.
[    0.000000]  [ffffea0000000000-ffffea003fffffff] PMD -> [ffff880100600000-ffff88013e9fffff] on node 1
[    0.000000]  [ffffea0040000000-ffffea006fffffff] PMD -> [ffff88013ec00000-ffff88016ebfffff] on node 1
[    0.000000]  [ffffea0070000000-ffffea007fffffff] PMD -> [ffff882000600000-ffff8820105fffff] on node 0
[    0.000000]  [ffffea0080000000-ffffea00bfffffff] PMD -> [ffff882010800000-ffff8820507fffff] on node 0
[    0.000000]  [ffffea00c0000000-ffffea00dfffffff] PMD -> [ffff882050a00000-ffff8820709fffff] on node 0
[    0.000000]  [ffffea00e0000000-ffffea00ffffffff] PMD -> [ffff884000600000-ffff8840205fffff] on node 2
[    0.000000]  [ffffea0100000000-ffffea013fffffff] PMD -> [ffff884020800000-ffff8840607fffff] on node 2
[    0.000000]  [ffffea0140000000-ffffea014fffffff] PMD -> [ffff884060a00000-ffff8840709fffff] on node 2
[    0.000000]  [ffffea0150000000-ffffea017fffffff] PMD -> [ffff886000600000-ffff8860305fffff] on node 3
[    0.000000]  [ffffea0180000000-ffffea01bfffffff] PMD -> [ffff886030800000-ffff8860707fffff] on node 3
[    0.000000]  [ffffea01c0000000-ffffea01ffffffff] PMD -> [ffff888000600000-ffff8880405fffff] on node 4
[    0.000000]  [ffffea0200000000-ffffea022fffffff] PMD -> [ffff888040800000-ffff8880707fffff] on node 4
[    0.000000]  [ffffea0230000000-ffffea023fffffff] PMD -> [ffff88a000600000-ffff88a0105fffff] on node 5
[    0.000000]  [ffffea0240000000-ffffea027fffffff] PMD -> [ffff88a010800000-ffff88a0507fffff] on node 5
[    0.000000]  [ffffea0280000000-ffffea029fffffff] PMD -> [ffff88a050a00000-ffff88a0709fffff] on node 5
[    0.000000]  [ffffea02a0000000-ffffea02bfffffff] PMD -> [ffff88c000600000-ffff88c0205fffff] on node 6
[    0.000000]  [ffffea02c0000000-ffffea02ffffffff] PMD -> [ffff88c020800000-ffff88c0607fffff] on node 6
[    0.000000]  [ffffea0300000000-ffffea030fffffff] PMD -> [ffff88c060a00000-ffff88c0709fffff] on node 6
[    0.000000]  [ffffea0310000000-ffffea033fffffff] PMD -> [ffff88e000600000-ffff88e0305fffff] on node 7
[    0.000000]  [ffffea0340000000-ffffea037fffffff] PMD -> [ffff88e030800000-ffff88e0707fffff] on node 7

after patch will get
[    0.000000]  [ffffea0000000000-ffffea006fffffff] PMD -> [ffff880100200000-ffff88016e5fffff] on node 0
[    0.000000]  [ffffea0070000000-ffffea00dfffffff] PMD -> [ffff882000200000-ffff8820701fffff] on node 1
[    0.000000]  [ffffea00e0000000-ffffea014fffffff] PMD -> [ffff884000200000-ffff8840701fffff] on node 2
[    0.000000]  [ffffea0150000000-ffffea01bfffffff] PMD -> [ffff886000200000-ffff8860701fffff] on node 3
[    0.000000]  [ffffea01c0000000-ffffea022fffffff] PMD -> [ffff888000200000-ffff8880701fffff] on node 4
[    0.000000]  [ffffea0230000000-ffffea029fffffff] PMD -> [ffff88a000200000-ffff88a0701fffff] on node 5
[    0.000000]  [ffffea02a0000000-ffffea030fffffff] PMD -> [ffff88c000200000-ffff88c0701fffff] on node 6
[    0.000000]  [ffffea0310000000-ffffea037fffffff] PMD -> [ffff88e000200000-ffff88e0701fffff] on node 7


-v2: change buf to vmemmap_buf instead according to Ingo
     also add CONFIG_SPARSEMEM_ALLOC_MEM_MAP_TOGETHER according to Ingo

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
---
 arch/x86/mm/init_64.c |    2 +-
 include/linux/mm.h    |    7 +++
 mm/Kconfig            |    4 ++
 mm/sparse-vmemmap.c   |   75 ++++++++++++++++++++++++++++++++-
 mm/sparse.c           |  111 ++++++++++++++++++++++++++++++++++++++++++++++++-
 5 files changed, 196 insertions(+), 3 deletions(-)

diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index f13e5bd..21090d8 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -961,7 +961,7 @@ vmemmap_populate(struct page *start_page, unsigned long size, int node)
 			if (pmd_none(*pmd)) {
 				pte_t entry;
 
-				p = vmemmap_alloc_block(PMD_SIZE, node);
+				p = vmemmap_alloc_block_buf(PMD_SIZE, node);
 				if (!p)
 					return -ENOMEM;
 
diff --git a/include/linux/mm.h b/include/linux/mm.h
index c94ce6c..814cb8f 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1323,12 +1323,19 @@ extern int randomize_va_space;
 const char * arch_vma_name(struct vm_area_struct *vma);
 void print_vma_addr(char *prefix, unsigned long rip);
 
+void sparse_mem_maps_populate_node(struct page **map_map,
+				   unsigned long pnum_begin,
+				   unsigned long pnum_end,
+				   unsigned long map_count,
+				   int nodeid);
+
 struct page *sparse_mem_map_populate(unsigned long pnum, int nid);
 pgd_t *vmemmap_pgd_populate(unsigned long addr, int node);
 pud_t *vmemmap_pud_populate(pgd_t *pgd, unsigned long addr, int node);
 pmd_t *vmemmap_pmd_populate(pud_t *pud, unsigned long addr, int node);
 pte_t *vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node);
 void *vmemmap_alloc_block(unsigned long size, int node);
+void *vmemmap_alloc_block_buf(unsigned long size, int node);
 void vmemmap_verify(pte_t *, int, unsigned long, unsigned long);
 int vmemmap_populate_basepages(struct page *start_page,
 						unsigned long pages, int node);
diff --git a/mm/Kconfig b/mm/Kconfig
index 28212b8..d84cdab 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -115,6 +115,10 @@ config SPARSEMEM_EXTREME
 config SPARSEMEM_VMEMMAP_ENABLE
 	bool
 
+config SPARSEMEM_ALLOC_MEM_MAP_TOGETHER
+	def_bool y
+	depends on SPARSEMEM && X86_64
+
 config SPARSEMEM_VMEMMAP
 	bool "Sparse Memory virtual memmap"
 	depends on SPARSEMEM && SPARSEMEM_VMEMMAP_ENABLE
diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c
index 9506c39..6b4be75 100644
--- a/mm/sparse-vmemmap.c
+++ b/mm/sparse-vmemmap.c
@@ -43,6 +43,8 @@ static void * __init_refok __earlyonly_bootmem_alloc(int node,
 	return __alloc_bootmem_node_high(NODE_DATA(node), size, align, goal);
 }
 
+static void *vmemmap_buf;
+static void *vmemmap_buf_end;
 
 void * __meminit vmemmap_alloc_block(unsigned long size, int node)
 {
@@ -64,6 +66,24 @@ void * __meminit vmemmap_alloc_block(unsigned long size, int node)
 				__pa(MAX_DMA_ADDRESS));
 }
 
+/* need to make sure size is all the same during early stage */
+void * __meminit vmemmap_alloc_block_buf(unsigned long size, int node)
+{
+	void *ptr;
+
+	if (!vmemmap_buf)
+		return vmemmap_alloc_block(size, node);
+
+	/* take the from buf */
+	ptr = (void *)ALIGN((unsigned long)vmemmap_buf, size);
+	if (ptr + size > vmemmap_buf_end)
+		return vmemmap_alloc_block(size, node);
+
+	vmemmap_buf = ptr + size;
+
+	return ptr;
+}
+
 void __meminit vmemmap_verify(pte_t *pte, int node,
 				unsigned long start, unsigned long end)
 {
@@ -80,7 +100,7 @@ pte_t * __meminit vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node)
 	pte_t *pte = pte_offset_kernel(pmd, addr);
 	if (pte_none(*pte)) {
 		pte_t entry;
-		void *p = vmemmap_alloc_block(PAGE_SIZE, node);
+		void *p = vmemmap_alloc_block_buf(PAGE_SIZE, node);
 		if (!p)
 			return NULL;
 		entry = pfn_pte(__pa(p) >> PAGE_SHIFT, PAGE_KERNEL);
@@ -163,3 +183,56 @@ struct page * __meminit sparse_mem_map_populate(unsigned long pnum, int nid)
 
 	return map;
 }
+
+void __init sparse_mem_maps_populate_node(struct page **map_map,
+					  unsigned long pnum_begin,
+					  unsigned long pnum_end,
+					  unsigned long map_count, int nodeid)
+{
+	unsigned long pnum;
+	unsigned long size = sizeof(struct page) * PAGES_PER_SECTION;
+	void *vmemmap_buf_start;
+
+	size = ALIGN(size, PMD_SIZE);
+	vmemmap_buf_start = __earlyonly_bootmem_alloc(nodeid, size * map_count,
+			 PMD_SIZE, __pa(MAX_DMA_ADDRESS));
+
+	if (vmemmap_buf_start) {
+		vmemmap_buf = vmemmap_buf_start;
+		vmemmap_buf_end = vmemmap_buf_start + size * map_count;
+	}
+
+	for (pnum = pnum_begin; pnum < pnum_end; pnum++) {
+		struct mem_section *ms;
+
+		if (!present_section_nr(pnum))
+			continue;
+
+		map_map[pnum] = sparse_mem_map_populate(pnum, nodeid);
+		if (map_map[pnum])
+			continue;
+		ms = __nr_to_section(pnum);
+		printk(KERN_ERR "%s: sparsemem memory map backing failed "
+			"some memory will not be available.\n", __func__);
+		ms->section_mem_map = 0;
+	}
+
+	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];
+
+			memset(name, 0, sizeof(name));
+			snprintf(name, 15, "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;
+	}
+}
diff --git a/mm/sparse.c b/mm/sparse.c
index 0cdaf0b..9b6b93a 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -390,8 +390,65 @@ struct page __init *sparse_mem_map_populate(unsigned long pnum, int nid)
 		       PAGE_ALIGN(sizeof(struct page) * PAGES_PER_SECTION));
 	return map;
 }
+void __init sparse_mem_maps_populate_node(struct page **map_map,
+					  unsigned long pnum_begin,
+					  unsigned long pnum_end,
+					  unsigned long map_count, int nodeid)
+{
+	void *map;
+	unsigned long pnum;
+	unsigned long size = sizeof(struct page) * PAGES_PER_SECTION;
+
+	map = alloc_remap(nodeid, size * map_count);
+	if (map) {
+		for (pnum = pnum_begin; pnum < pnum_end; pnum++) {
+			if (!present_section_nr(pnum))
+				continue;
+			map_map[pnum] = map;
+			map += size;
+		}
+		return;
+	}
+
+	size = PAGE_ALIGN(size);
+	map = alloc_bootmem_pages_node(NODE_DATA(nodeid), size * map_count);
+	if (map) {
+		for (pnum = pnum_begin; pnum < pnum_end; pnum++) {
+			if (!present_section_nr(pnum))
+				continue;
+			map_map[pnum] = map;
+			map += size;
+		}
+		return;
+	}
+
+	/* fallback */
+	for (pnum = pnum_begin; pnum < pnum_end; pnum++) {
+		struct mem_section *ms;
+
+		if (!present_section_nr(pnum))
+			continue;
+		map_map[pnum] = sparse_mem_map_populate(pnum, nodeid);
+		if (map_map[pnum])
+			continue;
+		ms = __nr_to_section(pnum);
+		printk(KERN_ERR "%s: sparsemem memory map backing failed "
+			"some memory will not be available.\n", __func__);
+		ms->section_mem_map = 0;
+	}
+}
 #endif /* !CONFIG_SPARSEMEM_VMEMMAP */
 
+static void __init sparse_early_mem_maps_alloc_node(struct page **map_map,
+				 unsigned long pnum_begin,
+				 unsigned long pnum_end,
+				 unsigned long map_count, int nodeid)
+{
+	sparse_mem_maps_populate_node(map_map, pnum_begin, pnum_end,
+					 map_count, nodeid);
+}
+
+#ifndef CONFIG_SPARSEMEM_ALLOC_MEM_MAP_TOGETHER
 static struct page __init *sparse_early_mem_map_alloc(unsigned long pnum)
 {
 	struct page *map;
@@ -407,6 +464,7 @@ static struct page __init *sparse_early_mem_map_alloc(unsigned long pnum)
 	ms->section_mem_map = 0;
 	return NULL;
 }
+#endif
 
 void __attribute__((weak)) __meminit vmemmap_populate_print_last(void)
 {
@@ -420,12 +478,14 @@ void __init sparse_init(void)
 {
 	unsigned long pnum;
 	struct page *map;
+	struct page **map_map;
 	unsigned long *usemap;
 	unsigned long **usemap_map;
-	int size;
+	int size, size2;
 	int nodeid_begin = 0;
 	unsigned long pnum_begin = 0;
 	unsigned long usemap_count;
+	unsigned long map_count;
 
 	/*
 	 * map is using big page (aka 2M in x86 64 bit)
@@ -478,6 +538,48 @@ void __init sparse_init(void)
 	sparse_early_usemaps_alloc_node(usemap_map, pnum_begin, NR_MEM_SECTIONS,
 					 usemap_count, nodeid_begin);
 
+#ifdef CONFIG_SPARSEMEM_ALLOC_MEM_MAP_TOGETHER
+	size2 = sizeof(struct page *) * NR_MEM_SECTIONS;
+	map_map = alloc_bootmem(size2);
+	if (!map_map)
+		panic("can not allocate map_map\n");
+
+	for (pnum = 0; pnum < NR_MEM_SECTIONS; pnum++) {
+		struct mem_section *ms;
+
+		if (!present_section_nr(pnum))
+			continue;
+		ms = __nr_to_section(pnum);
+		nodeid_begin = sparse_early_nid(ms);
+		pnum_begin = pnum;
+		break;
+	}
+	map_count = 1;
+	for (pnum = pnum_begin + 1; pnum < NR_MEM_SECTIONS; pnum++) {
+		struct mem_section *ms;
+		int nodeid;
+
+		if (!present_section_nr(pnum))
+			continue;
+		ms = __nr_to_section(pnum);
+		nodeid = sparse_early_nid(ms);
+		if (nodeid == nodeid_begin) {
+			map_count++;
+			continue;
+		}
+		/* ok, we need to take cake of from pnum_begin to pnum - 1*/
+		sparse_early_mem_maps_alloc_node(map_map, pnum_begin, pnum,
+						 map_count, nodeid_begin);
+		/* new start, update count etc*/
+		nodeid_begin = nodeid;
+		pnum_begin = pnum;
+		map_count = 1;
+	}
+	/* ok, last chunk */
+	sparse_early_mem_maps_alloc_node(map_map, pnum_begin, NR_MEM_SECTIONS,
+					 map_count, nodeid_begin);
+#endif
+
 	for (pnum = 0; pnum < NR_MEM_SECTIONS; pnum++) {
 		if (!present_section_nr(pnum))
 			continue;
@@ -486,7 +588,11 @@ void __init sparse_init(void)
 		if (!usemap)
 			continue;
 
+#ifdef CONFIG_SPARSEMEM_ALLOC_MEM_MAP_TOGETHER
+		map = map_map[pnum];
+#else
 		map = sparse_early_mem_map_alloc(pnum);
+#endif
 		if (!map)
 			continue;
 
@@ -496,6 +602,9 @@ void __init sparse_init(void)
 
 	vmemmap_populate_print_last();
 
+#ifdef CONFIG_SPARSEMEM_ALLOC_MEM_MAP_TOGETHER
+	free_bootmem(__pa(map_map), size2);
+#endif
 	free_bootmem(__pa(usemap_map), size);
 }
 
-- 
1.6.4.2

[PATCH 20/29] x86: change range end to start+size

[Yinghai Lu]

so make interface more consistent with early_res.
later we can share some code with early_res.

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
---
 arch/x86/kernel/cpu/mtrr/cleanup.c |   32 ++++++++++++++++----------------
 arch/x86/kernel/e820.c             |    2 +-
 arch/x86/pci/amd_bus.c             |   24 ++++++++++++++----------
 kernel/range.c                     |   20 ++++++++++----------
 mm/bootmem.c                       |    2 +-
 mm/page_alloc.c                    |    2 +-
 6 files changed, 43 insertions(+), 39 deletions(-)

diff --git a/arch/x86/kernel/cpu/mtrr/cleanup.c b/arch/x86/kernel/cpu/mtrr/cleanup.c
index 669da09..06130b5 100644
--- a/arch/x86/kernel/cpu/mtrr/cleanup.c
+++ b/arch/x86/kernel/cpu/mtrr/cleanup.c
@@ -78,13 +78,13 @@ x86_get_mtrr_mem_range(struct range *range, int nr_range,
 		base = range_state[i].base_pfn;
 		size = range_state[i].size_pfn;
 		nr_range = add_range_with_merge(range, RANGE_NUM, nr_range,
-						base, base + size - 1);
+						base, base + size);
 	}
 	if (debug_print) {
 		printk(KERN_DEBUG "After WB checking\n");
 		for (i = 0; i < nr_range; i++)
 			printk(KERN_DEBUG "MTRR MAP PFN: %016llx - %016llx\n",
-				 range[i].start, range[i].end + 1);
+				 range[i].start, range[i].end);
 	}
 
 	/* Take out UC ranges: */
@@ -106,11 +106,11 @@ x86_get_mtrr_mem_range(struct range *range, int nr_range,
 			size -= (1<<(20-PAGE_SHIFT)) - base;
 			base = 1<<(20-PAGE_SHIFT);
 		}
-		subtract_range(range, RANGE_NUM, base, base + size - 1);
+		subtract_range(range, RANGE_NUM, base, base + size);
 	}
 	if (extra_remove_size)
 		subtract_range(range, RANGE_NUM, extra_remove_base,
-				 extra_remove_base + extra_remove_size  - 1);
+				 extra_remove_base + extra_remove_size);
 
 	if  (debug_print) {
 		printk(KERN_DEBUG "After UC checking\n");
@@ -118,7 +118,7 @@ x86_get_mtrr_mem_range(struct range *range, int nr_range,
 			if (!range[i].end)
 				continue;
 			printk(KERN_DEBUG "MTRR MAP PFN: %016llx - %016llx\n",
-				 range[i].start, range[i].end + 1);
+				 range[i].start, range[i].end);
 		}
 	}
 
@@ -128,7 +128,7 @@ x86_get_mtrr_mem_range(struct range *range, int nr_range,
 		printk(KERN_DEBUG "After sorting\n");
 		for (i = 0; i < nr_range; i++)
 			printk(KERN_DEBUG "MTRR MAP PFN: %016llx - %016llx\n",
-				 range[i].start, range[i].end + 1);
+				 range[i].start, range[i].end);
 	}
 
 	return nr_range;
@@ -142,7 +142,7 @@ static unsigned long __init sum_ranges(struct range *range, int nr_range)
 	int i;
 
 	for (i = 0; i < nr_range; i++)
-		sum += range[i].end + 1 - range[i].start;
+		sum += range[i].end - range[i].start;
 
 	return sum;
 }
@@ -489,7 +489,7 @@ x86_setup_var_mtrrs(struct range *range, int nr_range,
 	/* Write the range: */
 	for (i = 0; i < nr_range; i++) {
 		set_var_mtrr_range(&var_state, range[i].start,
-				   range[i].end - range[i].start + 1);
+				   range[i].end - range[i].start);
 	}
 
 	/* Write the last range: */
@@ -720,7 +720,7 @@ int __init mtrr_cleanup(unsigned address_bits)
 	 * and fixed mtrrs should take effect before var mtrr for it:
 	 */
 	nr_range = add_range_with_merge(range, RANGE_NUM, nr_range, 0,
-					(1ULL<<(20 - PAGE_SHIFT)) - 1);
+					1ULL<<(20 - PAGE_SHIFT));
 	/* Sort the ranges: */
 	sort_range(range, nr_range);
 
@@ -939,9 +939,9 @@ int __init mtrr_trim_uncached_memory(unsigned long end_pfn)
 	nr_range = 0;
 	if (mtrr_tom2) {
 		range[nr_range].start = (1ULL<<(32 - PAGE_SHIFT));
-		range[nr_range].end = (mtrr_tom2 >> PAGE_SHIFT) - 1;
-		if (highest_pfn < range[nr_range].end + 1)
-			highest_pfn = range[nr_range].end + 1;
+		range[nr_range].end = mtrr_tom2 >> PAGE_SHIFT;
+		if (highest_pfn < range[nr_range].end)
+			highest_pfn = range[nr_range].end;
 		nr_range++;
 	}
 	nr_range = x86_get_mtrr_mem_range(range, nr_range, 0, 0);
@@ -953,15 +953,15 @@ int __init mtrr_trim_uncached_memory(unsigned long end_pfn)
 
 	/* Check the holes: */
 	for (i = 0; i < nr_range - 1; i++) {
-		if (range[i].end + 1 < range[i+1].start)
-			total_trim_size += real_trim_memory(range[i].end + 1,
+		if (range[i].end < range[i+1].start)
+			total_trim_size += real_trim_memory(range[i].end,
 							    range[i+1].start);
 	}
 
 	/* Check the top: */
 	i = nr_range - 1;
-	if (range[i].end + 1 < end_pfn)
-		total_trim_size += real_trim_memory(range[i].end + 1,
+	if (range[i].end < end_pfn)
+		total_trim_size += real_trim_memory(range[i].end,
 							 end_pfn);
 
 	if (total_trim_size) {
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 155b2d6..bd6a361 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -1038,7 +1038,7 @@ static void __init subtract_early_res(struct range *range, int az)
 		printk(KERN_CONT " subtract pfn [%010llx - %010llx]\n",
 			final_start, final_end);
 #endif
-		subtract_range(range, az, final_start, final_end - 1);
+		subtract_range(range, az, final_start, final_end);
 	}
 
 }
diff --git a/arch/x86/pci/amd_bus.c b/arch/x86/pci/amd_bus.c
index ef4b3e7..05cb9ae 100644
--- a/arch/x86/pci/amd_bus.c
+++ b/arch/x86/pci/amd_bus.c
@@ -145,7 +145,7 @@ static int __init early_fill_mp_bus_info(void)
 	def_link = (reg >> 8) & 0x03;
 
 	memset(range, 0, sizeof(range));
-	range[0].end = 0xffff;
+	add_range(range, RANGE_NUM, 0, 0, 0xffff + 1);
 	/* io port resource */
 	for (i = 0; i < 4; i++) {
 		reg = read_pci_config(bus, slot, 1, 0xc0 + (i << 3));
@@ -175,7 +175,7 @@ static int __init early_fill_mp_bus_info(void)
 		if (end > 0xffff)
 			end = 0xffff;
 		update_res(info, start, end, IORESOURCE_IO, 1);
-		subtract_range(range, RANGE_NUM, start, end);
+		subtract_range(range, RANGE_NUM, start, end + 1);
 	}
 	/* add left over io port range to def node/link, [0, 0xffff] */
 	/* find the position */
@@ -190,14 +190,16 @@ static int __init early_fill_mp_bus_info(void)
 			if (!range[i].end)
 				continue;
 
-			update_res(info, range[i].start, range[i].end,
+			update_res(info, range[i].start, range[i].end - 1,
 				   IORESOURCE_IO, 1);
 		}
 	}
 
 	memset(range, 0, sizeof(range));
 	/* 0xfd00000000-0xffffffffff for HT */
-	range[0].end = cap_resource((0xfdULL<<32) - 1);
+	end = cap_resource((0xfdULL<<32) - 1);
+	end++;
+	add_range(range, RANGE_NUM, 0, 0, end);
 
 	/* need to take out [0, TOM) for RAM*/
 	address = MSR_K8_TOP_MEM1;
@@ -205,14 +207,15 @@ static int __init early_fill_mp_bus_info(void)
 	end = (val & 0xffffff800000ULL);
 	printk(KERN_INFO "TOM: %016llx aka %lldM\n", end, end>>20);
 	if (end < (1ULL<<32))
-		subtract_range(range, RANGE_NUM, 0, end - 1);
+		subtract_range(range, RANGE_NUM, 0, end);
 
 	/* get mmconfig */
 	get_pci_mmcfg_amd_fam10h_range();
 	/* need to take out mmconf range */
 	if (fam10h_mmconf_end) {
 		printk(KERN_DEBUG "Fam 10h mmconf [%llx, %llx]\n", fam10h_mmconf_start, fam10h_mmconf_end);
-		subtract_range(range, RANGE_NUM, fam10h_mmconf_start, fam10h_mmconf_end);
+		subtract_range(range, RANGE_NUM, fam10h_mmconf_start,
+				 fam10h_mmconf_end + 1);
 	}
 
 	/* mmio resource */
@@ -267,7 +270,8 @@ static int __init early_fill_mp_bus_info(void)
 				/* we got a hole */
 				endx = fam10h_mmconf_start - 1;
 				update_res(info, start, endx, IORESOURCE_MEM, 0);
-				subtract_range(range, RANGE_NUM, start, endx);
+				subtract_range(range, RANGE_NUM, start,
+						 endx + 1);
 				printk(KERN_CONT " ==> [%llx, %llx]", start, endx);
 				start = fam10h_mmconf_end + 1;
 				changed = 1;
@@ -284,7 +288,7 @@ static int __init early_fill_mp_bus_info(void)
 
 		update_res(info, cap_resource(start), cap_resource(end),
 				 IORESOURCE_MEM, 1);
-		subtract_range(range, RANGE_NUM, start, end);
+		subtract_range(range, RANGE_NUM, start, end + 1);
 		printk(KERN_CONT "\n");
 	}
 
@@ -299,7 +303,7 @@ static int __init early_fill_mp_bus_info(void)
 		rdmsrl(address, val);
 		end = (val & 0xffffff800000ULL);
 		printk(KERN_INFO "TOM2: %016llx aka %lldM\n", end, end>>20);
-		subtract_range(range, RANGE_NUM, 1ULL<<32, end - 1);
+		subtract_range(range, RANGE_NUM, 1ULL<<32, end);
 	}
 
 	/*
@@ -319,7 +323,7 @@ static int __init early_fill_mp_bus_info(void)
 				continue;
 
 			update_res(info, cap_resource(range[i].start),
-				   cap_resource(range[i].end),
+				   cap_resource(range[i].end - 1),
 				   IORESOURCE_MEM, 1);
 		}
 	}
diff --git a/kernel/range.c b/kernel/range.c
index 71e0021..74e2e61 100644
--- a/kernel/range.c
+++ b/kernel/range.c
@@ -13,7 +13,7 @@
 
 int add_range(struct range *range, int az, int nr_range, u64 start, u64 end)
 {
-	if (start > end)
+	if (start >= end)
 		return nr_range;
 
 	/* Out of slots: */
@@ -33,7 +33,7 @@ int add_range_with_merge(struct range *range, int az, int nr_range,
 {
 	int i;
 
-	if (start > end)
+	if (start >= end)
 		return nr_range;
 
 	/* Try to merge it with old one: */
@@ -46,7 +46,7 @@ int add_range_with_merge(struct range *range, int az, int nr_range,
 
 		common_start = max(range[i].start, start);
 		common_end = min(range[i].end, end);
-		if (common_start > common_end + 1)
+		if (common_start > common_end)
 			continue;
 
 		final_start = min(range[i].start, start);
@@ -65,7 +65,7 @@ void subtract_range(struct range *range, int az, u64 start, u64 end)
 {
 	int i, j;
 
-	if (start > end)
+	if (start >= end)
 		return;
 
 	for (j = 0; j < az; j++) {
@@ -79,15 +79,15 @@ void subtract_range(struct range *range, int az, u64 start, u64 end)
 		}
 
 		if (start <= range[j].start && end < range[j].end &&
-		    range[j].start < end + 1) {
-			range[j].start = end + 1;
+		    range[j].start < end) {
+			range[j].start = end;
 			continue;
 		}
 
 
 		if (start > range[j].start && end >= range[j].end &&
-		    range[j].end > start - 1) {
-			range[j].end = start - 1;
+		    range[j].end > start) {
+			range[j].end = start;
 			continue;
 		}
 
@@ -99,11 +99,11 @@ void subtract_range(struct range *range, int az, u64 start, u64 end)
 			}
 			if (i < az) {
 				range[i].end = range[j].end;
-				range[i].start = end + 1;
+				range[i].start = end;
 			} else {
 				printk(KERN_ERR "run of slot in ranges\n");
 			}
-			range[j].end = start - 1;
+			range[j].end = start;
 			continue;
 		}
 	}
diff --git a/mm/bootmem.c b/mm/bootmem.c
index 64a5000..bb7faad 100644
--- a/mm/bootmem.c
+++ b/mm/bootmem.c
@@ -215,7 +215,7 @@ unsigned long __init free_all_memory_core_early(int nodeid)
 
 	for (i = 0; i < nr_range; i++) {
 		start = range[i].start;
-		end = range[i].end + 1;
+		end = range[i].end;
 		count += end - start;
 		__free_pages_memory(start, end);
 	}
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 2ca7b0f..e0ea57a 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3444,7 +3444,7 @@ int __init add_from_early_node_map(struct range *range, int az,
 	for_each_active_range_index_in_nid(i, nid) {
 		start = early_node_map[i].start_pfn;
 		end = early_node_map[i].end_pfn;
-		nr_range = add_range(range, az, nr_range, start, end - 1);
+		nr_range = add_range(range, az, nr_range, start, end);
 	}
 	return nr_range;
 }
-- 
1.6.4.2

[PATCH 21/29] x86: move bios page reserve early to head32/64.c

[Yinghai Lu]

so prepare to make one more clean early_res.c

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
---
 arch/x86/kernel/e820.c   |   22 ++--------------------
 arch/x86/kernel/head32.c |   12 ++++++++++++
 arch/x86/kernel/head64.c |    2 ++
 3 files changed, 16 insertions(+), 20 deletions(-)

diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index bd6a361..b7681e3 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -735,29 +735,11 @@ struct early_res {
 	char name[15];
 	char overlap_ok;
 };
-static struct early_res early_res_x[MAX_EARLY_RES_X] __initdata = {
-	{ 0, PAGE_SIZE, "BIOS data page", 1 },	/* BIOS data page */
-#if defined(CONFIG_X86_32) && defined(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)
-	 */
-	{ PAGE_SIZE, PAGE_SIZE + PAGE_SIZE, "EX TRAMPOLINE", 1 },
-#endif
-
-	{}
-};
+static struct early_res early_res_x[MAX_EARLY_RES_X] __initdata;
 
 static int max_early_res __initdata = MAX_EARLY_RES_X;
 static struct early_res *early_res __initdata = &early_res_x[0];
-static int early_res_count __initdata =
-#ifdef CONFIG_X86_32
-	2
-#else
-	1
-#endif
-	;
+static int early_res_count __initdata;
 
 static int __init find_overlapped_early(u64 start, u64 end)
 {
diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c
index 5051b94..2e13544 100644
--- a/arch/x86/kernel/head32.c
+++ b/arch/x86/kernel/head32.c
@@ -29,6 +29,18 @@ static void __init i386_default_early_setup(void)
 
 void __init i386_start_kernel(void)
 {
+	reserve_early_overlap_ok(0, PAGE_SIZE, "BIOS data page");
+
+#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");
+#endif
+
 	reserve_early(__pa_symbol(&_text), __pa_symbol(&__bss_stop), "TEXT DATA BSS");
 
 #ifdef CONFIG_BLK_DEV_INITRD
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index b5a9896..452b7c4 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -98,6 +98,8 @@ void __init x86_64_start_reservations(char *real_mode_data)
 {
 	copy_bootdata(__va(real_mode_data));
 
+	reserve_early_overlap_ok(0, PAGE_SIZE, "BIOS data page");
+
 	reserve_early(__pa_symbol(&_text), __pa_symbol(&__bss_stop), "TEXT DATA BSS");
 
 #ifdef CONFIG_BLK_DEV_INITRD
-- 
1.6.4.2

[PATCH 22/29] x86: seperate early_res related code from e820.c

[Yinghai Lu]

to make e820.c smaller.

-v2: fix 32bit compiling with MAX_DMA32_PFN

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
---
 arch/x86/include/asm/e820.h      |   13 +-
 arch/x86/include/asm/early_res.h |   20 ++
 arch/x86/kernel/Makefile         |    2 +-
 arch/x86/kernel/e820.c           |  541 +-------------------------------------
 arch/x86/kernel/early_res.c      |  539 +++++++++++++++++++++++++++++++++++++
 5 files changed, 562 insertions(+), 553 deletions(-)
 create mode 100644 arch/x86/include/asm/early_res.h
 create mode 100644 arch/x86/kernel/early_res.c

diff --git a/arch/x86/include/asm/e820.h b/arch/x86/include/asm/e820.h
index 7d72e5f..efad699 100644
--- a/arch/x86/include/asm/e820.h
+++ b/arch/x86/include/asm/e820.h
@@ -109,19 +109,8 @@ static inline void early_memtest(unsigned long start, unsigned long end)
 
 extern unsigned long end_user_pfn;
 
-extern u64 find_e820_area(u64 start, u64 end, u64 size, u64 align);
-extern u64 find_e820_area_size(u64 start, u64 *sizep, u64 align);
-extern void reserve_early(u64 start, u64 end, char *name);
-extern void reserve_early_overlap_ok(u64 start, u64 end, char *name);
-extern void free_early(u64 start, u64 end);
-extern void early_res_to_bootmem(u64 start, u64 end);
 extern u64 early_reserve_e820(u64 startt, u64 sizet, u64 align);
-
-void reserve_early_without_check(u64 start, u64 end, char *name);
-u64 find_early_area(u64 ei_start, u64 ei_last, u64 start, u64 end,
-			 u64 size, u64 align);
-#include <linux/range.h>
-int get_free_all_memory_range(struct range **rangep, int nodeid);
+#include <asm/early_res.h>
 
 extern unsigned long e820_end_of_ram_pfn(void);
 extern unsigned long e820_end_of_low_ram_pfn(void);
diff --git a/arch/x86/include/asm/early_res.h b/arch/x86/include/asm/early_res.h
new file mode 100644
index 0000000..2d43b16
--- /dev/null
+++ b/arch/x86/include/asm/early_res.h
@@ -0,0 +1,20 @@
+#ifndef _ASM_X86_EARLY_RES_H
+#define _ASM_X86_EARLY_RES_H
+#ifdef __KERNEL__
+
+extern u64 find_e820_area(u64 start, u64 end, u64 size, u64 align);
+extern u64 find_e820_area_size(u64 start, u64 *sizep, u64 align);
+extern void reserve_early(u64 start, u64 end, char *name);
+extern void reserve_early_overlap_ok(u64 start, u64 end, char *name);
+extern void free_early(u64 start, u64 end);
+extern void early_res_to_bootmem(u64 start, u64 end);
+
+void reserve_early_without_check(u64 start, u64 end, char *name);
+u64 find_early_area(u64 ei_start, u64 ei_last, u64 start, u64 end,
+			 u64 size, u64 align);
+#include <linux/range.h>
+int get_free_all_memory_range(struct range **rangep, int nodeid);
+
+#endif /* __KERNEL__ */
+
+#endif /* _ASM_X86_EARLY_RES_H */
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index d87f09b..f5fb9f0 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -38,7 +38,7 @@ obj-$(CONFIG_X86_32)	+= probe_roms_32.o
 obj-$(CONFIG_X86_32)	+= sys_i386_32.o i386_ksyms_32.o
 obj-$(CONFIG_X86_64)	+= sys_x86_64.o x8664_ksyms_64.o
 obj-$(CONFIG_X86_64)	+= syscall_64.o vsyscall_64.o
-obj-y			+= bootflag.o e820.o
+obj-y			+= bootflag.o e820.o early_res.o
 obj-y			+= pci-dma.o quirks.o i8237.o topology.o kdebugfs.o
 obj-y			+= alternative.o i8253.o pci-nommu.o hw_breakpoint.o
 obj-y			+= tsc.o io_delay.o rtc.o
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index b7681e3..27a756e 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -12,21 +12,14 @@
 #include <linux/types.h>
 #include <linux/init.h>
 #include <linux/bootmem.h>
-#include <linux/ioport.h>
-#include <linux/string.h>
-#include <linux/kexec.h>
-#include <linux/module.h>
-#include <linux/mm.h>
 #include <linux/pfn.h>
 #include <linux/suspend.h>
 #include <linux/firmware-map.h>
 
-#include <asm/pgtable.h>
-#include <asm/page.h>
 #include <asm/e820.h>
+#include <asm/early_res.h>
 #include <asm/proto.h>
 #include <asm/setup.h>
-#include <asm/trampoline.h>
 
 /*
  * The e820 map is the map that gets modified e.g. with command line parameters
@@ -722,538 +715,6 @@ core_initcall(e820_mark_nvs_memory);
 #endif
 
 /*
- * Early reserved memory areas.
- */
-/*
- * need to make sure this one is bigger enough before
- * find_e820_area could be used
- */
-#define MAX_EARLY_RES_X 32
-
-struct early_res {
-	u64 start, end;
-	char name[15];
-	char overlap_ok;
-};
-static struct early_res early_res_x[MAX_EARLY_RES_X] __initdata;
-
-static int max_early_res __initdata = MAX_EARLY_RES_X;
-static struct early_res *early_res __initdata = &early_res_x[0];
-static int early_res_count __initdata;
-
-static int __init find_overlapped_early(u64 start, u64 end)
-{
-	int i;
-	struct early_res *r;
-
-	for (i = 0; i < max_early_res && early_res[i].end; i++) {
-		r = &early_res[i];
-		if (end > r->start && start < r->end)
-			break;
-	}
-
-	return i;
-}
-
-/*
- * Drop the i-th range from the early reservation map,
- * by copying any higher ranges down one over it, and
- * clearing what had been the last slot.
- */
-static void __init drop_range(int i)
-{
-	int j;
-
-	for (j = i + 1; j < max_early_res && early_res[j].end; j++)
-		;
-
-	memmove(&early_res[i], &early_res[i + 1],
-	       (j - 1 - i) * sizeof(struct early_res));
-
-	early_res[j - 1].end = 0;
-	early_res_count--;
-}
-
-/*
- * Split any existing ranges that:
- *  1) are marked 'overlap_ok', and
- *  2) overlap with the stated range [start, end)
- * into whatever portion (if any) of the existing range is entirely
- * below or entirely above the stated range.  Drop the portion
- * of the existing range that overlaps with the stated range,
- * which will allow the caller of this routine to then add that
- * stated range without conflicting with any existing range.
- */
-static void __init drop_overlaps_that_are_ok(u64 start, u64 end)
-{
-	int i;
-	struct early_res *r;
-	u64 lower_start, lower_end;
-	u64 upper_start, upper_end;
-	char name[15];
-
-	for (i = 0; i < max_early_res && early_res[i].end; i++) {
-		r = &early_res[i];
-
-		/* Continue past non-overlapping ranges */
-		if (end <= r->start || start >= r->end)
-			continue;
-
-		/*
-		 * Leave non-ok overlaps as is; let caller
-		 * panic "Overlapping early reservations"
-		 * when it hits this overlap.
-		 */
-		if (!r->overlap_ok)
-			return;
-
-		/*
-		 * We have an ok overlap.  We will drop it from the early
-		 * reservation map, and add back in any non-overlapping
-		 * portions (lower or upper) as separate, overlap_ok,
-		 * non-overlapping ranges.
-		 */
-
-		/* 1. Note any non-overlapping (lower or upper) ranges. */
-		strncpy(name, r->name, sizeof(name) - 1);
-
-		lower_start = lower_end = 0;
-		upper_start = upper_end = 0;
-		if (r->start < start) {
-		 	lower_start = r->start;
-			lower_end = start;
-		}
-		if (r->end > end) {
-			upper_start = end;
-			upper_end = r->end;
-		}
-
-		/* 2. Drop the original ok overlapping range */
-		drop_range(i);
-
-		i--;		/* resume for-loop on copied down entry */
-
-		/* 3. Add back in any non-overlapping ranges. */
-		if (lower_end)
-			reserve_early_overlap_ok(lower_start, lower_end, name);
-		if (upper_end)
-			reserve_early_overlap_ok(upper_start, upper_end, name);
-	}
-}
-
-static void __init __reserve_early(u64 start, u64 end, char *name,
-						int overlap_ok)
-{
-	int i;
-	struct early_res *r;
-
-	i = find_overlapped_early(start, end);
-	if (i >= max_early_res)
-		panic("Too many early reservations");
-	r = &early_res[i];
-	if (r->end)
-		panic("Overlapping early reservations "
-		      "%llx-%llx %s to %llx-%llx %s\n",
-		      start, end - 1, name?name:"", r->start,
-		      r->end - 1, r->name);
-	r->start = start;
-	r->end = end;
-	r->overlap_ok = overlap_ok;
-	if (name)
-		strncpy(r->name, name, sizeof(r->name) - 1);
-	early_res_count++;
-}
-
-/*
- * A few early reservtations come here.
- *
- * The 'overlap_ok' in the name of this routine does -not- mean it
- * is ok for these reservations to overlap an earlier reservation.
- * Rather it means that it is ok for subsequent reservations to
- * overlap this one.
- *
- * Use this entry point to reserve early ranges when you are doing
- * so out of "Paranoia", reserving perhaps more memory than you need,
- * just in case, and don't mind a subsequent overlapping reservation
- * that is known to be needed.
- *
- * The drop_overlaps_that_are_ok() call here isn't really needed.
- * It would be needed if we had two colliding 'overlap_ok'
- * reservations, so that the second such would not panic on the
- * overlap with the first.  We don't have any such as of this
- * writing, but might as well tolerate such if it happens in
- * the future.
- */
-void __init reserve_early_overlap_ok(u64 start, u64 end, char *name)
-{
-	drop_overlaps_that_are_ok(start, end);
-	__reserve_early(start, end, name, 1);
-}
-
-static void __init __check_and_double_early_res(u64 start)
-{
-	u64 end, size, mem;
-	struct early_res *new;
-
-	/* do we have enough slots left ? */
-	if ((max_early_res - early_res_count) > max(max_early_res/8, 2))
-		return;
-
-	/* double it */
-	end = max_pfn_mapped << PAGE_SHIFT;
-	size = sizeof(struct early_res) * max_early_res * 2;
-	mem = find_e820_area(start, end, size, sizeof(struct early_res));
-
-	if (mem == -1ULL)
-		panic("can not find more space for early_res array");
-
-	new = __va(mem);
-	/* save the first one for own */
-	new[0].start = mem;
-	new[0].end = mem + size;
-	new[0].overlap_ok = 0;
-	/* copy old to new */
-	if (early_res == early_res_x) {
-		memcpy(&new[1], &early_res[0],
-			 sizeof(struct early_res) * max_early_res);
-		memset(&new[max_early_res+1], 0,
-			 sizeof(struct early_res) * (max_early_res - 1));
-		early_res_count++;
-	} else {
-		memcpy(&new[1], &early_res[1],
-			 sizeof(struct early_res) * (max_early_res - 1));
-		memset(&new[max_early_res], 0,
-			 sizeof(struct early_res) * max_early_res);
-	}
-	memset(&early_res[0], 0, sizeof(struct early_res) * max_early_res);
-	early_res = new;
-	max_early_res *= 2;
-	printk(KERN_DEBUG "early_res array is doubled to %d at [%llx - %llx]\n",
-		max_early_res, mem, mem + size - 1);
-}
-
-/*
- * Most early reservations come here.
- *
- * We first have drop_overlaps_that_are_ok() drop any pre-existing
- * 'overlap_ok' ranges, so that we can then reserve this memory
- * range without risk of panic'ing on an overlapping overlap_ok
- * early reservation.
- */
-void __init reserve_early(u64 start, u64 end, char *name)
-{
-	if (start >= end)
-		return;
-
-	__check_and_double_early_res(end);
-
-	drop_overlaps_that_are_ok(start, end);
-	__reserve_early(start, end, name, 0);
-}
-
-void __init reserve_early_without_check(u64 start, u64 end, char *name)
-{
-	struct early_res *r;
-
-	if (start >= end)
-		return;
-
-	__check_and_double_early_res(end);
-
-	r = &early_res[early_res_count];
-
-	r->start = start;
-	r->end = end;
-	r->overlap_ok = 0;
-	if (name)
-		strncpy(r->name, name, sizeof(r->name) - 1);
-	early_res_count++;
-}
-
-void __init free_early(u64 start, u64 end)
-{
-	struct early_res *r;
-	int i;
-
-	i = find_overlapped_early(start, end);
-	r = &early_res[i];
-	if (i >= max_early_res || r->end != end || r->start != start)
-		panic("free_early on not reserved area: %llx-%llx!",
-			 start, end - 1);
-
-	drop_range(i);
-}
-
-#ifdef CONFIG_NO_BOOTMEM
-static void __init subtract_early_res(struct range *range, int az)
-{
-	int i, count;
-	u64 final_start, final_end;
-	int idx = 0;
-
-	count  = 0;
-	for (i = 0; i < max_early_res && early_res[i].end; i++)
-		count++;
-
-	/* need to skip first one ?*/
-	if (early_res != early_res_x)
-		idx = 1;
-
-#if 1
-	printk(KERN_INFO "Subtract (%d early reservations)\n", count);
-#endif
-	for (i = idx; i < count; i++) {
-		struct early_res *r = &early_res[i];
-#if 0
-		printk(KERN_INFO "  #%d [%010llx - %010llx] %15s", i,
-			r->start, r->end, r->name);
-#endif
-		final_start = PFN_DOWN(r->start);
-		final_end = PFN_UP(r->end);
-		if (final_start >= final_end) {
-#if 0
-			printk(KERN_CONT "\n");
-#endif
-			continue;
-		}
-#if 0
-		printk(KERN_CONT " subtract pfn [%010llx - %010llx]\n",
-			final_start, final_end);
-#endif
-		subtract_range(range, az, final_start, final_end);
-	}
-
-}
-
-int __init get_free_all_memory_range(struct range **rangep, int nodeid)
-{
-	int i, count;
-	u64 start = 0, end;
-	u64 size;
-	u64 mem;
-	struct range *range;
-	int nr_range;
-
-	count  = 0;
-	for (i = 0; i < max_early_res && early_res[i].end; i++)
-		count++;
-
-	count *= 2;
-
-	size = sizeof(struct range) * count;
-#ifdef MAX_DMA32_PFN
-	if (max_pfn_mapped > MAX_DMA32_PFN)
-		start = MAX_DMA32_PFN << PAGE_SHIFT;
-#endif
-	end = max_pfn_mapped << PAGE_SHIFT;
-	mem = find_e820_area(start, end, size, sizeof(struct range));
-	if (mem == -1ULL)
-		panic("can not find more space for range free");
-
-	range = __va(mem);
-	/* use early_node_map[] and early_res to get range array at first */
-	memset(range, 0, size);
-	nr_range = 0;
-
-	/* need to go over early_node_map to find out good range for node */
-	nr_range = add_from_early_node_map(range, count, nr_range, nodeid);
-	subtract_early_res(range, count);
-	nr_range = clean_sort_range(range, count);
-
-	/* need to clear it ? */
-	if (nodeid == MAX_NUMNODES) {
-		memset(&early_res[0], 0,
-			 sizeof(struct early_res) * max_early_res);
-		early_res = NULL;
-		max_early_res = 0;
-	}
-
-	*rangep = range;
-	return nr_range;
-}
-#else
-void __init early_res_to_bootmem(u64 start, u64 end)
-{
-	int i, count;
-	u64 final_start, final_end;
-	int idx = 0;
-
-	count  = 0;
-	for (i = 0; i < max_early_res && early_res[i].end; i++)
-		count++;
-
-	/* need to skip first one ?*/
-	if (early_res != early_res_x)
-		idx = 1;
-
-	printk(KERN_INFO "(%d/%d early reservations) ==> bootmem [%010llx - %010llx]\n",
-			 count - idx, max_early_res, start, end);
-	for (i = idx; i < count; i++) {
-		struct early_res *r = &early_res[i];
-		printk(KERN_INFO "  #%d [%010llx - %010llx] %16s", i,
-			r->start, r->end, r->name);
-		final_start = max(start, r->start);
-		final_end = min(end, r->end);
-		if (final_start >= final_end) {
-			printk(KERN_CONT "\n");
-			continue;
-		}
-		printk(KERN_CONT " ==> [%010llx - %010llx]\n",
-			final_start, final_end);
-		reserve_bootmem_generic(final_start, final_end - final_start,
-				BOOTMEM_DEFAULT);
-	}
-	/* clear them */
-	memset(&early_res[0], 0, sizeof(struct early_res) * max_early_res);
-	early_res = NULL;
-	max_early_res = 0;
-	early_res_count = 0;
-}
-#endif
-
-/* Check for already reserved areas */
-static inline int __init bad_addr(u64 *addrp, u64 size, u64 align)
-{
-	int i;
-	u64 addr = *addrp;
-	int changed = 0;
-	struct early_res *r;
-again:
-	i = find_overlapped_early(addr, addr + size);
-	r = &early_res[i];
-	if (i < max_early_res && r->end) {
-		*addrp = addr = round_up(r->end, align);
-		changed = 1;
-		goto again;
-	}
-	return changed;
-}
-
-/* Check for already reserved areas */
-static inline int __init bad_addr_size(u64 *addrp, u64 *sizep, u64 align)
-{
-	int i;
-	u64 addr = *addrp, last;
-	u64 size = *sizep;
-	int changed = 0;
-again:
-	last = addr + size;
-	for (i = 0; i < max_early_res && early_res[i].end; i++) {
-		struct early_res *r = &early_res[i];
-		if (last > r->start && addr < r->start) {
-			size = r->start - addr;
-			changed = 1;
-			goto again;
-		}
-		if (last > r->end && addr < r->end) {
-			addr = round_up(r->end, align);
-			size = last - addr;
-			changed = 1;
-			goto again;
-		}
-		if (last <= r->end && addr >= r->start) {
-			(*sizep)++;
-			return 0;
-		}
-	}
-	if (changed) {
-		*addrp = addr;
-		*sizep = size;
-	}
-	return changed;
-}
-
-/*
- * Find a free area with specified alignment in a specific range.
- * only with the area.between start to end is active range from early_node_map
- * so they are good as RAM
- */
-u64 __init find_early_area(u64 ei_start, u64 ei_last, u64 start, u64 end,
-			 u64 size, u64 align)
-{
-	u64 addr, last;
-
-	addr = round_up(ei_start, align);
-	if (addr < start)
-		addr = round_up(start, align);
-	if (addr >= ei_last)
-		goto out;
-	while (bad_addr(&addr, size, align) && addr+size <= ei_last)
-		;
-	last = addr + size;
-	if (last > ei_last)
-		goto out;
-	if (last > end)
-		goto out;
-
-	return addr;
-
-out:
-	return -1ULL;
-}
-
-/*
- * Find a free area with specified alignment in a specific range.
- */
-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;
-
-		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)
-			continue;
-
-		return addr;
-	}
-	return -1ULL;
-}
-
-/*
- * Find next free range after *start
- */
-u64 __init find_e820_area_size(u64 start, u64 *sizep, u64 align)
-{
-	int i;
-
-	for (i = 0; i < e820.nr_map; i++) {
-		struct e820entry *ei = &e820.map[i];
-		u64 addr, last;
-		u64 ei_last;
-
-		if (ei->type != E820_RAM)
-			continue;
-		addr = round_up(ei->addr, align);
-		ei_last = ei->addr + ei->size;
-		if (addr < start)
-			addr = round_up(start, align);
-		if (addr >= ei_last)
-			continue;
-		*sizep = ei_last - addr;
-		while (bad_addr_size(&addr, sizep, align) &&
-			addr + *sizep <= ei_last)
-			;
-		last = addr + *sizep;
-		if (last > ei_last)
-			continue;
-		return addr;
-	}
-
-	return -1ULL;
-}
-
-/*
  * pre allocated 4k and reserved it in e820
  */
 u64 __init early_reserve_e820(u64 startt, u64 sizet, u64 align)
diff --git a/arch/x86/kernel/early_res.c b/arch/x86/kernel/early_res.c
new file mode 100644
index 0000000..3ae0051
--- /dev/null
+++ b/arch/x86/kernel/early_res.c
@@ -0,0 +1,539 @@
+/*
+ * early_res, could be used to replace bootmem
+ */
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/init.h>
+#include <linux/bootmem.h>
+#include <linux/mm.h>
+
+#include <asm/e820.h>
+#include <asm/early_res.h>
+#include <asm/proto.h>
+
+/*
+ * Early reserved memory areas.
+ */
+/*
+ * need to make sure this one is bigger enough before
+ * find_e820_area could be used
+ */
+#define MAX_EARLY_RES_X 32
+
+struct early_res {
+	u64 start, end;
+	char name[15];
+	char overlap_ok;
+};
+static struct early_res early_res_x[MAX_EARLY_RES_X] __initdata;
+
+static int max_early_res __initdata = MAX_EARLY_RES_X;
+static struct early_res *early_res __initdata = &early_res_x[0];
+static int early_res_count __initdata;
+
+static int __init find_overlapped_early(u64 start, u64 end)
+{
+	int i;
+	struct early_res *r;
+
+	for (i = 0; i < max_early_res && early_res[i].end; i++) {
+		r = &early_res[i];
+		if (end > r->start && start < r->end)
+			break;
+	}
+
+	return i;
+}
+
+/*
+ * Drop the i-th range from the early reservation map,
+ * by copying any higher ranges down one over it, and
+ * clearing what had been the last slot.
+ */
+static void __init drop_range(int i)
+{
+	int j;
+
+	for (j = i + 1; j < max_early_res && early_res[j].end; j++)
+		;
+
+	memmove(&early_res[i], &early_res[i + 1],
+	       (j - 1 - i) * sizeof(struct early_res));
+
+	early_res[j - 1].end = 0;
+	early_res_count--;
+}
+
+/*
+ * Split any existing ranges that:
+ *  1) are marked 'overlap_ok', and
+ *  2) overlap with the stated range [start, end)
+ * into whatever portion (if any) of the existing range is entirely
+ * below or entirely above the stated range.  Drop the portion
+ * of the existing range that overlaps with the stated range,
+ * which will allow the caller of this routine to then add that
+ * stated range without conflicting with any existing range.
+ */
+static void __init drop_overlaps_that_are_ok(u64 start, u64 end)
+{
+	int i;
+	struct early_res *r;
+	u64 lower_start, lower_end;
+	u64 upper_start, upper_end;
+	char name[15];
+
+	for (i = 0; i < max_early_res && early_res[i].end; i++) {
+		r = &early_res[i];
+
+		/* Continue past non-overlapping ranges */
+		if (end <= r->start || start >= r->end)
+			continue;
+
+		/*
+		 * Leave non-ok overlaps as is; let caller
+		 * panic "Overlapping early reservations"
+		 * when it hits this overlap.
+		 */
+		if (!r->overlap_ok)
+			return;
+
+		/*
+		 * We have an ok overlap.  We will drop it from the early
+		 * reservation map, and add back in any non-overlapping
+		 * portions (lower or upper) as separate, overlap_ok,
+		 * non-overlapping ranges.
+		 */
+
+		/* 1. Note any non-overlapping (lower or upper) ranges. */
+		strncpy(name, r->name, sizeof(name) - 1);
+
+		lower_start = lower_end = 0;
+		upper_start = upper_end = 0;
+		if (r->start < start) {
+			lower_start = r->start;
+			lower_end = start;
+		}
+		if (r->end > end) {
+			upper_start = end;
+			upper_end = r->end;
+		}
+
+		/* 2. Drop the original ok overlapping range */
+		drop_range(i);
+
+		i--;		/* resume for-loop on copied down entry */
+
+		/* 3. Add back in any non-overlapping ranges. */
+		if (lower_end)
+			reserve_early_overlap_ok(lower_start, lower_end, name);
+		if (upper_end)
+			reserve_early_overlap_ok(upper_start, upper_end, name);
+	}
+}
+
+static void __init __reserve_early(u64 start, u64 end, char *name,
+						int overlap_ok)
+{
+	int i;
+	struct early_res *r;
+
+	i = find_overlapped_early(start, end);
+	if (i >= max_early_res)
+		panic("Too many early reservations");
+	r = &early_res[i];
+	if (r->end)
+		panic("Overlapping early reservations "
+		      "%llx-%llx %s to %llx-%llx %s\n",
+		      start, end - 1, name ? name : "", r->start,
+		      r->end - 1, r->name);
+	r->start = start;
+	r->end = end;
+	r->overlap_ok = overlap_ok;
+	if (name)
+		strncpy(r->name, name, sizeof(r->name) - 1);
+	early_res_count++;
+}
+
+/*
+ * A few early reservtations come here.
+ *
+ * The 'overlap_ok' in the name of this routine does -not- mean it
+ * is ok for these reservations to overlap an earlier reservation.
+ * Rather it means that it is ok for subsequent reservations to
+ * overlap this one.
+ *
+ * Use this entry point to reserve early ranges when you are doing
+ * so out of "Paranoia", reserving perhaps more memory than you need,
+ * just in case, and don't mind a subsequent overlapping reservation
+ * that is known to be needed.
+ *
+ * The drop_overlaps_that_are_ok() call here isn't really needed.
+ * It would be needed if we had two colliding 'overlap_ok'
+ * reservations, so that the second such would not panic on the
+ * overlap with the first.  We don't have any such as of this
+ * writing, but might as well tolerate such if it happens in
+ * the future.
+ */
+void __init reserve_early_overlap_ok(u64 start, u64 end, char *name)
+{
+	drop_overlaps_that_are_ok(start, end);
+	__reserve_early(start, end, name, 1);
+}
+
+static void __init __check_and_double_early_res(u64 start)
+{
+	u64 end, size, mem;
+	struct early_res *new;
+
+	/* do we have enough slots left ? */
+	if ((max_early_res - early_res_count) > max(max_early_res/8, 2))
+		return;
+
+	/* double it */
+	end = max_pfn_mapped << PAGE_SHIFT;
+	size = sizeof(struct early_res) * max_early_res * 2;
+	mem = find_e820_area(start, end, size, sizeof(struct early_res));
+
+	if (mem == -1ULL)
+		panic("can not find more space for early_res array");
+
+	new = __va(mem);
+	/* save the first one for own */
+	new[0].start = mem;
+	new[0].end = mem + size;
+	new[0].overlap_ok = 0;
+	/* copy old to new */
+	if (early_res == early_res_x) {
+		memcpy(&new[1], &early_res[0],
+			 sizeof(struct early_res) * max_early_res);
+		memset(&new[max_early_res+1], 0,
+			 sizeof(struct early_res) * (max_early_res - 1));
+		early_res_count++;
+	} else {
+		memcpy(&new[1], &early_res[1],
+			 sizeof(struct early_res) * (max_early_res - 1));
+		memset(&new[max_early_res], 0,
+			 sizeof(struct early_res) * max_early_res);
+	}
+	memset(&early_res[0], 0, sizeof(struct early_res) * max_early_res);
+	early_res = new;
+	max_early_res *= 2;
+	printk(KERN_DEBUG "early_res array is doubled to %d at [%llx - %llx]\n",
+		max_early_res, mem, mem + size - 1);
+}
+
+/*
+ * Most early reservations come here.
+ *
+ * We first have drop_overlaps_that_are_ok() drop any pre-existing
+ * 'overlap_ok' ranges, so that we can then reserve this memory
+ * range without risk of panic'ing on an overlapping overlap_ok
+ * early reservation.
+ */
+void __init reserve_early(u64 start, u64 end, char *name)
+{
+	if (start >= end)
+		return;
+
+	__check_and_double_early_res(end);
+
+	drop_overlaps_that_are_ok(start, end);
+	__reserve_early(start, end, name, 0);
+}
+
+void __init reserve_early_without_check(u64 start, u64 end, char *name)
+{
+	struct early_res *r;
+
+	if (start >= end)
+		return;
+
+	__check_and_double_early_res(end);
+
+	r = &early_res[early_res_count];
+
+	r->start = start;
+	r->end = end;
+	r->overlap_ok = 0;
+	if (name)
+		strncpy(r->name, name, sizeof(r->name) - 1);
+	early_res_count++;
+}
+
+void __init free_early(u64 start, u64 end)
+{
+	struct early_res *r;
+	int i;
+
+	i = find_overlapped_early(start, end);
+	r = &early_res[i];
+	if (i >= max_early_res || r->end != end || r->start != start)
+		panic("free_early on not reserved area: %llx-%llx!",
+			 start, end - 1);
+
+	drop_range(i);
+}
+
+#ifdef CONFIG_NO_BOOTMEM
+static void __init subtract_early_res(struct range *range, int az)
+{
+	int i, count;
+	u64 final_start, final_end;
+	int idx = 0;
+
+	count  = 0;
+	for (i = 0; i < max_early_res && early_res[i].end; i++)
+		count++;
+
+	/* need to skip first one ?*/
+	if (early_res != early_res_x)
+		idx = 1;
+
+#define DEBUG_PRINT_EARLY_RES 1
+
+#if DEBUG_PRINT_EARLY_RES
+	printk(KERN_INFO "Subtract (%d early reservations)\n", count);
+#endif
+	for (i = idx; i < count; i++) {
+		struct early_res *r = &early_res[i];
+#if DEBUG_PRINT_EARLY_RES
+		printk(KERN_INFO "  #%d [%010llx - %010llx] %15s\n", i,
+			r->start, r->end, r->name);
+#endif
+		final_start = PFN_DOWN(r->start);
+		final_end = PFN_UP(r->end);
+		if (final_start >= final_end)
+			continue;
+		subtract_range(range, az, final_start, final_end);
+	}
+
+}
+
+int __init get_free_all_memory_range(struct range **rangep, int nodeid)
+{
+	int i, count;
+	u64 start = 0, end;
+	u64 size;
+	u64 mem;
+	struct range *range;
+	int nr_range;
+
+	count  = 0;
+	for (i = 0; i < max_early_res && early_res[i].end; i++)
+		count++;
+
+	count *= 2;
+
+	size = sizeof(struct range) * count;
+#ifdef MAX_DMA32_PFN
+	if (max_pfn_mapped > MAX_DMA32_PFN)
+		start = MAX_DMA32_PFN << PAGE_SHIFT;
+#endif
+	end = max_pfn_mapped << PAGE_SHIFT;
+	mem = find_e820_area(start, end, size, sizeof(struct range));
+	if (mem == -1ULL)
+		panic("can not find more space for range free");
+
+	range = __va(mem);
+	/* use early_node_map[] and early_res to get range array at first */
+	memset(range, 0, size);
+	nr_range = 0;
+
+	/* need to go over early_node_map to find out good range for node */
+	nr_range = add_from_early_node_map(range, count, nr_range, nodeid);
+	subtract_early_res(range, count);
+	nr_range = clean_sort_range(range, count);
+
+	/* need to clear it ? */
+	if (nodeid == MAX_NUMNODES) {
+		memset(&early_res[0], 0,
+			 sizeof(struct early_res) * max_early_res);
+		early_res = NULL;
+		max_early_res = 0;
+	}
+
+	*rangep = range;
+	return nr_range;
+}
+#else
+void __init early_res_to_bootmem(u64 start, u64 end)
+{
+	int i, count;
+	u64 final_start, final_end;
+	int idx = 0;
+
+	count  = 0;
+	for (i = 0; i < max_early_res && early_res[i].end; i++)
+		count++;
+
+	/* need to skip first one ?*/
+	if (early_res != early_res_x)
+		idx = 1;
+
+	printk(KERN_INFO "(%d/%d early reservations) ==> bootmem [%010llx - %010llx]\n",
+			 count - idx, max_early_res, start, end);
+	for (i = idx; i < count; i++) {
+		struct early_res *r = &early_res[i];
+		printk(KERN_INFO "  #%d [%010llx - %010llx] %16s", i,
+			r->start, r->end, r->name);
+		final_start = max(start, r->start);
+		final_end = min(end, r->end);
+		if (final_start >= final_end) {
+			printk(KERN_CONT "\n");
+			continue;
+		}
+		printk(KERN_CONT " ==> [%010llx - %010llx]\n",
+			final_start, final_end);
+		reserve_bootmem_generic(final_start, final_end - final_start,
+				BOOTMEM_DEFAULT);
+	}
+	/* clear them */
+	memset(&early_res[0], 0, sizeof(struct early_res) * max_early_res);
+	early_res = NULL;
+	max_early_res = 0;
+	early_res_count = 0;
+}
+#endif
+
+/* Check for already reserved areas */
+static inline int __init bad_addr(u64 *addrp, u64 size, u64 align)
+{
+	int i;
+	u64 addr = *addrp;
+	int changed = 0;
+	struct early_res *r;
+again:
+	i = find_overlapped_early(addr, addr + size);
+	r = &early_res[i];
+	if (i < max_early_res && r->end) {
+		*addrp = addr = round_up(r->end, align);
+		changed = 1;
+		goto again;
+	}
+	return changed;
+}
+
+/* Check for already reserved areas */
+static inline int __init bad_addr_size(u64 *addrp, u64 *sizep, u64 align)
+{
+	int i;
+	u64 addr = *addrp, last;
+	u64 size = *sizep;
+	int changed = 0;
+again:
+	last = addr + size;
+	for (i = 0; i < max_early_res && early_res[i].end; i++) {
+		struct early_res *r = &early_res[i];
+		if (last > r->start && addr < r->start) {
+			size = r->start - addr;
+			changed = 1;
+			goto again;
+		}
+		if (last > r->end && addr < r->end) {
+			addr = round_up(r->end, align);
+			size = last - addr;
+			changed = 1;
+			goto again;
+		}
+		if (last <= r->end && addr >= r->start) {
+			(*sizep)++;
+			return 0;
+		}
+	}
+	if (changed) {
+		*addrp = addr;
+		*sizep = size;
+	}
+	return changed;
+}
+
+/*
+ * Find a free area with specified alignment in a specific range.
+ * only with the area.between start to end is active range from early_node_map
+ * so they are good as RAM
+ */
+u64 __init find_early_area(u64 ei_start, u64 ei_last, u64 start, u64 end,
+			 u64 size, u64 align)
+{
+	u64 addr, last;
+
+	addr = round_up(ei_start, align);
+	if (addr < start)
+		addr = round_up(start, align);
+	if (addr >= ei_last)
+		goto out;
+	while (bad_addr(&addr, size, align) && addr+size <= ei_last)
+		;
+	last = addr + size;
+	if (last > ei_last)
+		goto out;
+	if (last > end)
+		goto out;
+
+	return addr;
+
+out:
+	return -1ULL;
+}
+
+/*
+ * Find a free area with specified alignment in a specific range.
+ */
+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;
+
+		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)
+			continue;
+
+		return addr;
+	}
+	return -1ULL;
+}
+
+/*
+ * Find next free range after *start
+ */
+u64 __init find_e820_area_size(u64 start, u64 *sizep, u64 align)
+{
+	int i;
+
+	for (i = 0; i < e820.nr_map; i++) {
+		struct e820entry *ei = &e820.map[i];
+		u64 addr, last;
+		u64 ei_last;
+
+		if (ei->type != E820_RAM)
+			continue;
+		addr = round_up(ei->addr, align);
+		ei_last = ei->addr + ei->size;
+		if (addr < start)
+			addr = round_up(start, align);
+		if (addr >= ei_last)
+			continue;
+		*sizep = ei_last - addr;
+		while (bad_addr_size(&addr, sizep, align) &&
+			addr + *sizep <= ei_last)
+			;
+		last = addr + *sizep;
+		if (last > ei_last)
+			continue;
+		return addr;
+	}
+
+	return -1ULL;
+}
+
-- 
1.6.4.2

[PATCH 23/29] x86: add find_early_area_size

[Yinghai Lu]

prepare to move bck find_e820_area_size back to e820.c

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
---
 arch/x86/kernel/early_res.c |   45 ++++++++++++++++++++++++++++++------------
 1 files changed, 32 insertions(+), 13 deletions(-)

diff --git a/arch/x86/kernel/early_res.c b/arch/x86/kernel/early_res.c
index 3ae0051..aba02f2 100644
--- a/arch/x86/kernel/early_res.c
+++ b/arch/x86/kernel/early_res.c
@@ -476,6 +476,29 @@ out:
 	return -1ULL;
 }
 
+u64 __init find_early_area_size(u64 ei_start, u64 ei_last, u64 start,
+			 u64 *sizep, u64 align)
+{
+	u64 addr, last;
+
+	addr = round_up(ei_start, align);
+	if (addr < start)
+		addr = round_up(start, align);
+	if (addr >= ei_last)
+		goto out;
+	*sizep = ei_last - addr;
+	while (bad_addr_size(&addr, sizep, align) && addr + *sizep <= ei_last)
+		;
+	last = addr + *sizep;
+	if (last > ei_last)
+		goto out;
+
+	return addr;
+
+out:
+	return -1ULL;
+}
+
 /*
  * Find a free area with specified alignment in a specific range.
  */
@@ -513,24 +536,20 @@ u64 __init find_e820_area_size(u64 start, u64 *sizep, u64 align)
 
 	for (i = 0; i < e820.nr_map; i++) {
 		struct e820entry *ei = &e820.map[i];
-		u64 addr, last;
-		u64 ei_last;
+		u64 addr;
+		u64 ei_start, ei_last;
 
 		if (ei->type != E820_RAM)
 			continue;
-		addr = round_up(ei->addr, align);
+
 		ei_last = ei->addr + ei->size;
-		if (addr < start)
-			addr = round_up(start, align);
-		if (addr >= ei_last)
-			continue;
-		*sizep = ei_last - addr;
-		while (bad_addr_size(&addr, sizep, align) &&
-			addr + *sizep <= ei_last)
-			;
-		last = addr + *sizep;
-		if (last > ei_last)
+		ei_start = ei->addr;
+		addr = find_early_area_size(ei_start, ei_last, start,
+					 sizep, align);
+
+		if (addr == -1ULL)
 			continue;
+
 		return addr;
 	}
 
-- 
1.6.4.2

[PATCH 24/29] x86: move back find_e820_area to e820.c

[Yinghai Lu]

make early_res.c more clean, so later could move it to /kernel

Signed-off: Yinghai Lu <yinghai@kernel.org>
---
 arch/x86/include/asm/e820.h      |    2 +
 arch/x86/include/asm/early_res.h |    4 +-
 arch/x86/kernel/e820.c           |   57 ++++++++++++++++++++++++++++++++++++++
 arch/x86/kernel/early_res.c      |   56 -------------------------------------
 4 files changed, 61 insertions(+), 58 deletions(-)

diff --git a/arch/x86/include/asm/e820.h b/arch/x86/include/asm/e820.h
index efad699..a8299e1 100644
--- a/arch/x86/include/asm/e820.h
+++ b/arch/x86/include/asm/e820.h
@@ -109,6 +109,8 @@ static inline void early_memtest(unsigned long start, unsigned long end)
 
 extern unsigned long end_user_pfn;
 
+extern u64 find_e820_area(u64 start, u64 end, u64 size, u64 align);
+extern u64 find_e820_area_size(u64 start, u64 *sizep, u64 align);
 extern u64 early_reserve_e820(u64 startt, u64 sizet, u64 align);
 #include <asm/early_res.h>
 
diff --git a/arch/x86/include/asm/early_res.h b/arch/x86/include/asm/early_res.h
index 2d43b16..5a4d2eb 100644
--- a/arch/x86/include/asm/early_res.h
+++ b/arch/x86/include/asm/early_res.h
@@ -2,8 +2,6 @@
 #define _ASM_X86_EARLY_RES_H
 #ifdef __KERNEL__
 
-extern u64 find_e820_area(u64 start, u64 end, u64 size, u64 align);
-extern u64 find_e820_area_size(u64 start, u64 *sizep, u64 align);
 extern void reserve_early(u64 start, u64 end, char *name);
 extern void reserve_early_overlap_ok(u64 start, u64 end, char *name);
 extern void free_early(u64 start, u64 end);
@@ -12,6 +10,8 @@ extern void early_res_to_bootmem(u64 start, u64 end);
 void reserve_early_without_check(u64 start, u64 end, char *name);
 u64 find_early_area(u64 ei_start, u64 ei_last, u64 start, u64 end,
 			 u64 size, u64 align);
+u64 find_early_area_size(u64 ei_start, u64 ei_last, u64 start,
+			 u64 *sizep, u64 align);
 #include <linux/range.h>
 int get_free_all_memory_range(struct range **rangep, int nodeid);
 
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 27a756e..acd7be6 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -715,6 +715,63 @@ core_initcall(e820_mark_nvs_memory);
 #endif
 
 /*
+ * Find a free area with specified alignment in a specific range.
+ */
+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;
+
+		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)
+			continue;
+
+		return addr;
+	}
+	return -1ULL;
+}
+
+/*
+ * Find next free range after *start
+ */
+u64 __init find_e820_area_size(u64 start, u64 *sizep, 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;
+
+		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 (addr == -1ULL)
+			continue;
+
+		return addr;
+	}
+
+	return -1ULL;
+}
+
+/*
  * pre allocated 4k and reserved it in e820
  */
 u64 __init early_reserve_e820(u64 startt, u64 sizet, u64 align)
diff --git a/arch/x86/kernel/early_res.c b/arch/x86/kernel/early_res.c
index aba02f2..d0a70cc 100644
--- a/arch/x86/kernel/early_res.c
+++ b/arch/x86/kernel/early_res.c
@@ -499,60 +499,4 @@ out:
 	return -1ULL;
 }
 
-/*
- * Find a free area with specified alignment in a specific range.
- */
-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;
-
-		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)
-			continue;
-
-		return addr;
-	}
-	return -1ULL;
-}
-
-/*
- * Find next free range after *start
- */
-u64 __init find_e820_area_size(u64 start, u64 *sizep, 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;
-
-		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 (addr == -1ULL)
-			continue;
-
-		return addr;
-	}
-
-	return -1ULL;
-}
 
-- 
1.6.4.2

[PATCH 25/29] early_res: enhance check_and_double_early_res

[Yinghai Lu]

to make it always try to start from low at first.

so make it more safe for early_memtest to reserve bad range.
aka put new early_res to range that is already tested.

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
---
 arch/x86/kernel/early_res.c |   27 ++++++++++++++++++++-------
 1 files changed, 20 insertions(+), 7 deletions(-)

diff --git a/arch/x86/kernel/early_res.c b/arch/x86/kernel/early_res.c
index d0a70cc..52804e9 100644
--- a/arch/x86/kernel/early_res.c
+++ b/arch/x86/kernel/early_res.c
@@ -180,9 +180,9 @@ void __init reserve_early_overlap_ok(u64 start, u64 end, char *name)
 	__reserve_early(start, end, name, 1);
 }
 
-static void __init __check_and_double_early_res(u64 start)
+static void __init __check_and_double_early_res(u64 ex_start, u64 ex_end)
 {
-	u64 end, size, mem;
+	u64 start, end, size, mem;
 	struct early_res *new;
 
 	/* do we have enough slots left ? */
@@ -190,10 +190,23 @@ static void __init __check_and_double_early_res(u64 start)
 		return;
 
 	/* double it */
-	end = max_pfn_mapped << PAGE_SHIFT;
+	mem = -1ULL;
 	size = sizeof(struct early_res) * max_early_res * 2;
-	mem = find_e820_area(start, end, size, sizeof(struct early_res));
-
+	if (early_res == early_res_x)
+		start = 0;
+	else
+		start = early_res[0].end;
+	end = ex_start;
+	if (start + size < end)
+		mem = find_e820_area(start, end, size,
+					 sizeof(struct early_res));
+	if (mem == -1ULL) {
+		start = ex_end;
+		end = max_pfn_mapped << PAGE_SHIFT;
+		if (start + size < end)
+			mem = find_e820_area(start, end, size,
+						 sizeof(struct early_res));
+	}
 	if (mem == -1ULL)
 		panic("can not find more space for early_res array");
 
@@ -235,7 +248,7 @@ void __init reserve_early(u64 start, u64 end, char *name)
 	if (start >= end)
 		return;
 
-	__check_and_double_early_res(end);
+	__check_and_double_early_res(start, end);
 
 	drop_overlaps_that_are_ok(start, end);
 	__reserve_early(start, end, name, 0);
@@ -248,7 +261,7 @@ void __init reserve_early_without_check(u64 start, u64 end, char *name)
 	if (start >= end)
 		return;
 
-	__check_and_double_early_res(end);
+	__check_and_double_early_res(start, end);
 
 	r = &early_res[early_res_count];
 
-- 
1.6.4.2

[PATCH 26/29] x86: make 32bit support NO_BOOTMEM

[Yinghai Lu]

let's make 32bit consistent with 64bit

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
---
 arch/x86/Kconfig            |    1 -
 arch/x86/kernel/early_res.c |    3 +++
 arch/x86/mm/init_32.c       |    6 ++++++
 arch/x86/mm/numa_32.c       |    3 +++
 4 files changed, 12 insertions(+), 1 deletions(-)

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index ffb025c..8f9e065 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -570,7 +570,6 @@ config PARAVIRT_DEBUG
 config NO_BOOTMEM
 	default y
 	bool "Disable Bootmem code"
-	depends on X86_64
 	---help---
 	  use early_res directly instead of bootmem before slab is ready.
 
diff --git a/arch/x86/kernel/early_res.c b/arch/x86/kernel/early_res.c
index 52804e9..38a0c61 100644
--- a/arch/x86/kernel/early_res.c
+++ b/arch/x86/kernel/early_res.c
@@ -354,6 +354,9 @@ int __init get_free_all_memory_range(struct range **rangep, int nodeid)
 
 	/* need to go over early_node_map to find out good range for node */
 	nr_range = add_from_early_node_map(range, count, nr_range, nodeid);
+#ifdef CONFIG_X86_32
+	subtract_range(range, count, max_low_pfn, -1UL);
+#endif
 	subtract_early_res(range, count);
 	nr_range = clean_sort_range(range, count);
 
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 3c4fe2a..033eb18 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -748,6 +748,7 @@ static void __init zone_sizes_init(void)
 	free_area_init_nodes(max_zone_pfns);
 }
 
+#ifndef CONFIG_NO_BOOTMEM
 static unsigned long __init setup_node_bootmem(int nodeid,
 				 unsigned long start_pfn,
 				 unsigned long end_pfn,
@@ -767,9 +768,11 @@ static unsigned long __init setup_node_bootmem(int nodeid,
 
 	return bootmap + bootmap_size;
 }
+#endif
 
 void __init setup_bootmem_allocator(void)
 {
+#ifndef CONFIG_NO_BOOTMEM
 	int nodeid;
 	unsigned long bootmap_size, bootmap;
 	/*
@@ -781,11 +784,13 @@ void __init setup_bootmem_allocator(void)
 	if (bootmap == -1L)
 		panic("Cannot find bootmem map of size %ld\n", bootmap_size);
 	reserve_early(bootmap, bootmap + bootmap_size, "BOOTMAP");
+#endif
 
 	printk(KERN_INFO "  mapped low ram: 0 - %08lx\n",
 		 max_pfn_mapped<<PAGE_SHIFT);
 	printk(KERN_INFO "  low ram: 0 - %08lx\n", max_low_pfn<<PAGE_SHIFT);
 
+#ifndef CONFIG_NO_BOOTMEM
 	for_each_online_node(nodeid) {
 		 unsigned long start_pfn, end_pfn;
 
@@ -803,6 +808,7 @@ void __init setup_bootmem_allocator(void)
 		bootmap = setup_node_bootmem(nodeid, start_pfn, end_pfn,
 						 bootmap);
 	}
+#endif
 
 	after_bootmem = 1;
 }
diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c
index b20760c..809baaa 100644
--- a/arch/x86/mm/numa_32.c
+++ b/arch/x86/mm/numa_32.c
@@ -418,7 +418,10 @@ void __init initmem_init(unsigned long start_pfn, unsigned long end_pfn,
 
 	for_each_online_node(nid) {
 		memset(NODE_DATA(nid), 0, sizeof(struct pglist_data));
+		NODE_DATA(nid)->node_id = nid;
+#ifndef CONFIG_NO_BOOTMEM
 		NODE_DATA(nid)->bdata = &bootmem_node_data[nid];
+#endif
 	}
 
 	setup_bootmem_allocator();
-- 
1.6.4.2

[PATCH 27/29] move round_up/down to kernel.h

[Yinghai Lu]

prepare to early_res moving up

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
---
 arch/x86/include/asm/proto.h |   10 ----------
 include/linux/kernel.h       |   10 ++++++++++
 2 files changed, 10 insertions(+), 10 deletions(-)

diff --git a/arch/x86/include/asm/proto.h b/arch/x86/include/asm/proto.h
index 4009f65..6f414ed 100644
--- a/arch/x86/include/asm/proto.h
+++ b/arch/x86/include/asm/proto.h
@@ -23,14 +23,4 @@ extern int reboot_force;
 
 long do_arch_prctl(struct task_struct *task, int code, unsigned long addr);
 
-/*
- * This looks more complex than it should be. But we need to
- * get the type for the ~ right in round_down (it needs to be
- * as wide as the result!), and we want to evaluate the macro
- * arguments just once each.
- */
-#define __round_mask(x,y) ((__typeof__(x))((y)-1))
-#define round_up(x,y) ((((x)-1) | __round_mask(x,y))+1)
-#define round_down(x,y) ((x) & ~__round_mask(x,y))
-
 #endif /* _ASM_X86_PROTO_H */
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 785d7d1..9e1e9ef 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -44,6 +44,16 @@ extern const char linux_proc_banner[];
 
 #define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0]) + __must_be_array(arr))
 
+/*
+ * This looks more complex than it should be. But we need to
+ * get the type for the ~ right in round_down (it needs to be
+ * as wide as the result!), and we want to evaluate the macro
+ * arguments just once each.
+ */
+#define __round_mask(x,y) ((__typeof__(x))((y)-1))
+#define round_up(x,y) ((((x)-1) | __round_mask(x,y))+1)
+#define round_down(x,y) ((x) & ~__round_mask(x,y))
+
 #define FIELD_SIZEOF(t, f) (sizeof(((t*)0)->f))
 #define DIV_ROUND_UP(n,d) (((n) + (d) - 1) / (d))
 #define roundup(x, y) ((((x) + ((y) - 1)) / (y)) * (y))
-- 
1.6.4.2

[PATCH 28/29] x86: add find_fw_memmap_area

[Yinghai Lu]

so could move early_res up

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
---
 arch/x86/include/asm/early_res.h |    1 +
 arch/x86/kernel/e820.c           |    4 ++++
 arch/x86/kernel/early_res.c      |   17 +++++++++++------
 3 files changed, 16 insertions(+), 6 deletions(-)

diff --git a/arch/x86/include/asm/early_res.h b/arch/x86/include/asm/early_res.h
index 5a4d2eb..9758f3d 100644
--- a/arch/x86/include/asm/early_res.h
+++ b/arch/x86/include/asm/early_res.h
@@ -12,6 +12,7 @@ u64 find_early_area(u64 ei_start, u64 ei_last, u64 start, u64 end,
 			 u64 size, u64 align);
 u64 find_early_area_size(u64 ei_start, u64 ei_last, u64 start,
 			 u64 *sizep, u64 align);
+u64 find_fw_memmap_area(u64 start, u64 end, u64 size, u64 align);
 #include <linux/range.h>
 int get_free_all_memory_range(struct range **rangep, int nodeid);
 
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index acd7be6..5c80050 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -742,6 +742,10 @@ u64 __init find_e820_area(u64 start, u64 end, u64 size, u64 align)
 	return -1ULL;
 }
 
+u64 __init find_fw_memmap_area(u64 start, u64 end, u64 size, u64 align)
+{
+	return find_e820_area(start, end, size, align);
+}
 /*
  * Find next free range after *start
  */
diff --git a/arch/x86/kernel/early_res.c b/arch/x86/kernel/early_res.c
index 38a0c61..e209fc4 100644
--- a/arch/x86/kernel/early_res.c
+++ b/arch/x86/kernel/early_res.c
@@ -7,16 +7,14 @@
 #include <linux/bootmem.h>
 #include <linux/mm.h>
 
-#include <asm/e820.h>
 #include <asm/early_res.h>
-#include <asm/proto.h>
 
 /*
  * Early reserved memory areas.
  */
 /*
  * need to make sure this one is bigger enough before
- * find_e820_area could be used
+ * find_fw_memmap_area could be used
  */
 #define MAX_EARLY_RES_X 32
 
@@ -180,6 +178,13 @@ void __init reserve_early_overlap_ok(u64 start, u64 end, char *name)
 	__reserve_early(start, end, name, 1);
 }
 
+u64 __init __weak find_fw_memmap_area(u64 start, u64 end, u64 size, u64 align)
+{
+	panic("should have find_fw_memmap_area defined with arch");
+
+	return -1ULL;
+}
+
 static void __init __check_and_double_early_res(u64 ex_start, u64 ex_end)
 {
 	u64 start, end, size, mem;
@@ -198,13 +203,13 @@ static void __init __check_and_double_early_res(u64 ex_start, u64 ex_end)
 		start = early_res[0].end;
 	end = ex_start;
 	if (start + size < end)
-		mem = find_e820_area(start, end, size,
+		mem = find_fw_memmap_area(start, end, size,
 					 sizeof(struct early_res));
 	if (mem == -1ULL) {
 		start = ex_end;
 		end = max_pfn_mapped << PAGE_SHIFT;
 		if (start + size < end)
-			mem = find_e820_area(start, end, size,
+			mem = find_fw_memmap_area(start, end, size,
 						 sizeof(struct early_res));
 	}
 	if (mem == -1ULL)
@@ -343,7 +348,7 @@ int __init get_free_all_memory_range(struct range **rangep, int nodeid)
 		start = MAX_DMA32_PFN << PAGE_SHIFT;
 #endif
 	end = max_pfn_mapped << PAGE_SHIFT;
-	mem = find_e820_area(start, end, size, sizeof(struct range));
+	mem = find_fw_memmap_area(start, end, size, sizeof(struct range));
 	if (mem == -1ULL)
 		panic("can not find more space for range free");
 
-- 
1.6.4.2

[PATCH 29/29] core: move early_res

[Yinghai Lu]

from arch/x86 to kernel/

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
---
 arch/x86/include/asm/e820.h      |    2 +-
 arch/x86/include/asm/early_res.h |   21 --
 arch/x86/kernel/Makefile         |    2 +-
 arch/x86/kernel/e820.c           |    1 -
 arch/x86/kernel/early_res.c      |  523 --------------------------------------
 include/linux/early_res.h        |   21 ++
 kernel/Makefile                  |    2 +-
 kernel/early_res.c               |  522 +++++++++++++++++++++++++++++++++++++
 8 files changed, 546 insertions(+), 548 deletions(-)
 delete mode 100644 arch/x86/include/asm/early_res.h
 delete mode 100644 arch/x86/kernel/early_res.c
 create mode 100644 include/linux/early_res.h
 create mode 100644 kernel/early_res.c

diff --git a/arch/x86/include/asm/e820.h b/arch/x86/include/asm/e820.h
index a8299e1..0e22296 100644
--- a/arch/x86/include/asm/e820.h
+++ b/arch/x86/include/asm/e820.h
@@ -112,7 +112,7 @@ extern unsigned long end_user_pfn;
 extern u64 find_e820_area(u64 start, u64 end, u64 size, u64 align);
 extern u64 find_e820_area_size(u64 start, u64 *sizep, u64 align);
 extern u64 early_reserve_e820(u64 startt, u64 sizet, u64 align);
-#include <asm/early_res.h>
+#include <linux/early_res.h>
 
 extern unsigned long e820_end_of_ram_pfn(void);
 extern unsigned long e820_end_of_low_ram_pfn(void);
diff --git a/arch/x86/include/asm/early_res.h b/arch/x86/include/asm/early_res.h
deleted file mode 100644
index 9758f3d..0000000
--- a/arch/x86/include/asm/early_res.h
+++ /dev/null
@@ -1,21 +0,0 @@
-#ifndef _ASM_X86_EARLY_RES_H
-#define _ASM_X86_EARLY_RES_H
-#ifdef __KERNEL__
-
-extern void reserve_early(u64 start, u64 end, char *name);
-extern void reserve_early_overlap_ok(u64 start, u64 end, char *name);
-extern void free_early(u64 start, u64 end);
-extern void early_res_to_bootmem(u64 start, u64 end);
-
-void reserve_early_without_check(u64 start, u64 end, char *name);
-u64 find_early_area(u64 ei_start, u64 ei_last, u64 start, u64 end,
-			 u64 size, u64 align);
-u64 find_early_area_size(u64 ei_start, u64 ei_last, u64 start,
-			 u64 *sizep, u64 align);
-u64 find_fw_memmap_area(u64 start, u64 end, u64 size, u64 align);
-#include <linux/range.h>
-int get_free_all_memory_range(struct range **rangep, int nodeid);
-
-#endif /* __KERNEL__ */
-
-#endif /* _ASM_X86_EARLY_RES_H */
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index f5fb9f0..d87f09b 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -38,7 +38,7 @@ obj-$(CONFIG_X86_32)	+= probe_roms_32.o
 obj-$(CONFIG_X86_32)	+= sys_i386_32.o i386_ksyms_32.o
 obj-$(CONFIG_X86_64)	+= sys_x86_64.o x8664_ksyms_64.o
 obj-$(CONFIG_X86_64)	+= syscall_64.o vsyscall_64.o
-obj-y			+= bootflag.o e820.o early_res.o
+obj-y			+= bootflag.o e820.o
 obj-y			+= pci-dma.o quirks.o i8237.o topology.o kdebugfs.o
 obj-y			+= alternative.o i8253.o pci-nommu.o hw_breakpoint.o
 obj-y			+= tsc.o io_delay.o rtc.o
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 5c80050..c5c52da 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -17,7 +17,6 @@
 #include <linux/firmware-map.h>
 
 #include <asm/e820.h>
-#include <asm/early_res.h>
 #include <asm/proto.h>
 #include <asm/setup.h>
 
diff --git a/arch/x86/kernel/early_res.c b/arch/x86/kernel/early_res.c
deleted file mode 100644
index e209fc4..0000000
--- a/arch/x86/kernel/early_res.c
+++ /dev/null
@@ -1,523 +0,0 @@
-/*
- * early_res, could be used to replace bootmem
- */
-#include <linux/kernel.h>
-#include <linux/types.h>
-#include <linux/init.h>
-#include <linux/bootmem.h>
-#include <linux/mm.h>
-
-#include <asm/early_res.h>
-
-/*
- * Early reserved memory areas.
- */
-/*
- * need to make sure this one is bigger enough before
- * find_fw_memmap_area could be used
- */
-#define MAX_EARLY_RES_X 32
-
-struct early_res {
-	u64 start, end;
-	char name[15];
-	char overlap_ok;
-};
-static struct early_res early_res_x[MAX_EARLY_RES_X] __initdata;
-
-static int max_early_res __initdata = MAX_EARLY_RES_X;
-static struct early_res *early_res __initdata = &early_res_x[0];
-static int early_res_count __initdata;
-
-static int __init find_overlapped_early(u64 start, u64 end)
-{
-	int i;
-	struct early_res *r;
-
-	for (i = 0; i < max_early_res && early_res[i].end; i++) {
-		r = &early_res[i];
-		if (end > r->start && start < r->end)
-			break;
-	}
-
-	return i;
-}
-
-/*
- * Drop the i-th range from the early reservation map,
- * by copying any higher ranges down one over it, and
- * clearing what had been the last slot.
- */
-static void __init drop_range(int i)
-{
-	int j;
-
-	for (j = i + 1; j < max_early_res && early_res[j].end; j++)
-		;
-
-	memmove(&early_res[i], &early_res[i + 1],
-	       (j - 1 - i) * sizeof(struct early_res));
-
-	early_res[j - 1].end = 0;
-	early_res_count--;
-}
-
-/*
- * Split any existing ranges that:
- *  1) are marked 'overlap_ok', and
- *  2) overlap with the stated range [start, end)
- * into whatever portion (if any) of the existing range is entirely
- * below or entirely above the stated range.  Drop the portion
- * of the existing range that overlaps with the stated range,
- * which will allow the caller of this routine to then add that
- * stated range without conflicting with any existing range.
- */
-static void __init drop_overlaps_that_are_ok(u64 start, u64 end)
-{
-	int i;
-	struct early_res *r;
-	u64 lower_start, lower_end;
-	u64 upper_start, upper_end;
-	char name[15];
-
-	for (i = 0; i < max_early_res && early_res[i].end; i++) {
-		r = &early_res[i];
-
-		/* Continue past non-overlapping ranges */
-		if (end <= r->start || start >= r->end)
-			continue;
-
-		/*
-		 * Leave non-ok overlaps as is; let caller
-		 * panic "Overlapping early reservations"
-		 * when it hits this overlap.
-		 */
-		if (!r->overlap_ok)
-			return;
-
-		/*
-		 * We have an ok overlap.  We will drop it from the early
-		 * reservation map, and add back in any non-overlapping
-		 * portions (lower or upper) as separate, overlap_ok,
-		 * non-overlapping ranges.
-		 */
-
-		/* 1. Note any non-overlapping (lower or upper) ranges. */
-		strncpy(name, r->name, sizeof(name) - 1);
-
-		lower_start = lower_end = 0;
-		upper_start = upper_end = 0;
-		if (r->start < start) {
-			lower_start = r->start;
-			lower_end = start;
-		}
-		if (r->end > end) {
-			upper_start = end;
-			upper_end = r->end;
-		}
-
-		/* 2. Drop the original ok overlapping range */
-		drop_range(i);
-
-		i--;		/* resume for-loop on copied down entry */
-
-		/* 3. Add back in any non-overlapping ranges. */
-		if (lower_end)
-			reserve_early_overlap_ok(lower_start, lower_end, name);
-		if (upper_end)
-			reserve_early_overlap_ok(upper_start, upper_end, name);
-	}
-}
-
-static void __init __reserve_early(u64 start, u64 end, char *name,
-						int overlap_ok)
-{
-	int i;
-	struct early_res *r;
-
-	i = find_overlapped_early(start, end);
-	if (i >= max_early_res)
-		panic("Too many early reservations");
-	r = &early_res[i];
-	if (r->end)
-		panic("Overlapping early reservations "
-		      "%llx-%llx %s to %llx-%llx %s\n",
-		      start, end - 1, name ? name : "", r->start,
-		      r->end - 1, r->name);
-	r->start = start;
-	r->end = end;
-	r->overlap_ok = overlap_ok;
-	if (name)
-		strncpy(r->name, name, sizeof(r->name) - 1);
-	early_res_count++;
-}
-
-/*
- * A few early reservtations come here.
- *
- * The 'overlap_ok' in the name of this routine does -not- mean it
- * is ok for these reservations to overlap an earlier reservation.
- * Rather it means that it is ok for subsequent reservations to
- * overlap this one.
- *
- * Use this entry point to reserve early ranges when you are doing
- * so out of "Paranoia", reserving perhaps more memory than you need,
- * just in case, and don't mind a subsequent overlapping reservation
- * that is known to be needed.
- *
- * The drop_overlaps_that_are_ok() call here isn't really needed.
- * It would be needed if we had two colliding 'overlap_ok'
- * reservations, so that the second such would not panic on the
- * overlap with the first.  We don't have any such as of this
- * writing, but might as well tolerate such if it happens in
- * the future.
- */
-void __init reserve_early_overlap_ok(u64 start, u64 end, char *name)
-{
-	drop_overlaps_that_are_ok(start, end);
-	__reserve_early(start, end, name, 1);
-}
-
-u64 __init __weak find_fw_memmap_area(u64 start, u64 end, u64 size, u64 align)
-{
-	panic("should have find_fw_memmap_area defined with arch");
-
-	return -1ULL;
-}
-
-static void __init __check_and_double_early_res(u64 ex_start, u64 ex_end)
-{
-	u64 start, end, size, mem;
-	struct early_res *new;
-
-	/* do we have enough slots left ? */
-	if ((max_early_res - early_res_count) > max(max_early_res/8, 2))
-		return;
-
-	/* double it */
-	mem = -1ULL;
-	size = sizeof(struct early_res) * max_early_res * 2;
-	if (early_res == early_res_x)
-		start = 0;
-	else
-		start = early_res[0].end;
-	end = ex_start;
-	if (start + size < end)
-		mem = find_fw_memmap_area(start, end, size,
-					 sizeof(struct early_res));
-	if (mem == -1ULL) {
-		start = ex_end;
-		end = max_pfn_mapped << PAGE_SHIFT;
-		if (start + size < end)
-			mem = find_fw_memmap_area(start, end, size,
-						 sizeof(struct early_res));
-	}
-	if (mem == -1ULL)
-		panic("can not find more space for early_res array");
-
-	new = __va(mem);
-	/* save the first one for own */
-	new[0].start = mem;
-	new[0].end = mem + size;
-	new[0].overlap_ok = 0;
-	/* copy old to new */
-	if (early_res == early_res_x) {
-		memcpy(&new[1], &early_res[0],
-			 sizeof(struct early_res) * max_early_res);
-		memset(&new[max_early_res+1], 0,
-			 sizeof(struct early_res) * (max_early_res - 1));
-		early_res_count++;
-	} else {
-		memcpy(&new[1], &early_res[1],
-			 sizeof(struct early_res) * (max_early_res - 1));
-		memset(&new[max_early_res], 0,
-			 sizeof(struct early_res) * max_early_res);
-	}
-	memset(&early_res[0], 0, sizeof(struct early_res) * max_early_res);
-	early_res = new;
-	max_early_res *= 2;
-	printk(KERN_DEBUG "early_res array is doubled to %d at [%llx - %llx]\n",
-		max_early_res, mem, mem + size - 1);
-}
-
-/*
- * Most early reservations come here.
- *
- * We first have drop_overlaps_that_are_ok() drop any pre-existing
- * 'overlap_ok' ranges, so that we can then reserve this memory
- * range without risk of panic'ing on an overlapping overlap_ok
- * early reservation.
- */
-void __init reserve_early(u64 start, u64 end, char *name)
-{
-	if (start >= end)
-		return;
-
-	__check_and_double_early_res(start, end);
-
-	drop_overlaps_that_are_ok(start, end);
-	__reserve_early(start, end, name, 0);
-}
-
-void __init reserve_early_without_check(u64 start, u64 end, char *name)
-{
-	struct early_res *r;
-
-	if (start >= end)
-		return;
-
-	__check_and_double_early_res(start, end);
-
-	r = &early_res[early_res_count];
-
-	r->start = start;
-	r->end = end;
-	r->overlap_ok = 0;
-	if (name)
-		strncpy(r->name, name, sizeof(r->name) - 1);
-	early_res_count++;
-}
-
-void __init free_early(u64 start, u64 end)
-{
-	struct early_res *r;
-	int i;
-
-	i = find_overlapped_early(start, end);
-	r = &early_res[i];
-	if (i >= max_early_res || r->end != end || r->start != start)
-		panic("free_early on not reserved area: %llx-%llx!",
-			 start, end - 1);
-
-	drop_range(i);
-}
-
-#ifdef CONFIG_NO_BOOTMEM
-static void __init subtract_early_res(struct range *range, int az)
-{
-	int i, count;
-	u64 final_start, final_end;
-	int idx = 0;
-
-	count  = 0;
-	for (i = 0; i < max_early_res && early_res[i].end; i++)
-		count++;
-
-	/* need to skip first one ?*/
-	if (early_res != early_res_x)
-		idx = 1;
-
-#define DEBUG_PRINT_EARLY_RES 1
-
-#if DEBUG_PRINT_EARLY_RES
-	printk(KERN_INFO "Subtract (%d early reservations)\n", count);
-#endif
-	for (i = idx; i < count; i++) {
-		struct early_res *r = &early_res[i];
-#if DEBUG_PRINT_EARLY_RES
-		printk(KERN_INFO "  #%d [%010llx - %010llx] %15s\n", i,
-			r->start, r->end, r->name);
-#endif
-		final_start = PFN_DOWN(r->start);
-		final_end = PFN_UP(r->end);
-		if (final_start >= final_end)
-			continue;
-		subtract_range(range, az, final_start, final_end);
-	}
-
-}
-
-int __init get_free_all_memory_range(struct range **rangep, int nodeid)
-{
-	int i, count;
-	u64 start = 0, end;
-	u64 size;
-	u64 mem;
-	struct range *range;
-	int nr_range;
-
-	count  = 0;
-	for (i = 0; i < max_early_res && early_res[i].end; i++)
-		count++;
-
-	count *= 2;
-
-	size = sizeof(struct range) * count;
-#ifdef MAX_DMA32_PFN
-	if (max_pfn_mapped > MAX_DMA32_PFN)
-		start = MAX_DMA32_PFN << PAGE_SHIFT;
-#endif
-	end = max_pfn_mapped << PAGE_SHIFT;
-	mem = find_fw_memmap_area(start, end, size, sizeof(struct range));
-	if (mem == -1ULL)
-		panic("can not find more space for range free");
-
-	range = __va(mem);
-	/* use early_node_map[] and early_res to get range array at first */
-	memset(range, 0, size);
-	nr_range = 0;
-
-	/* need to go over early_node_map to find out good range for node */
-	nr_range = add_from_early_node_map(range, count, nr_range, nodeid);
-#ifdef CONFIG_X86_32
-	subtract_range(range, count, max_low_pfn, -1UL);
-#endif
-	subtract_early_res(range, count);
-	nr_range = clean_sort_range(range, count);
-
-	/* need to clear it ? */
-	if (nodeid == MAX_NUMNODES) {
-		memset(&early_res[0], 0,
-			 sizeof(struct early_res) * max_early_res);
-		early_res = NULL;
-		max_early_res = 0;
-	}
-
-	*rangep = range;
-	return nr_range;
-}
-#else
-void __init early_res_to_bootmem(u64 start, u64 end)
-{
-	int i, count;
-	u64 final_start, final_end;
-	int idx = 0;
-
-	count  = 0;
-	for (i = 0; i < max_early_res && early_res[i].end; i++)
-		count++;
-
-	/* need to skip first one ?*/
-	if (early_res != early_res_x)
-		idx = 1;
-
-	printk(KERN_INFO "(%d/%d early reservations) ==> bootmem [%010llx - %010llx]\n",
-			 count - idx, max_early_res, start, end);
-	for (i = idx; i < count; i++) {
-		struct early_res *r = &early_res[i];
-		printk(KERN_INFO "  #%d [%010llx - %010llx] %16s", i,
-			r->start, r->end, r->name);
-		final_start = max(start, r->start);
-		final_end = min(end, r->end);
-		if (final_start >= final_end) {
-			printk(KERN_CONT "\n");
-			continue;
-		}
-		printk(KERN_CONT " ==> [%010llx - %010llx]\n",
-			final_start, final_end);
-		reserve_bootmem_generic(final_start, final_end - final_start,
-				BOOTMEM_DEFAULT);
-	}
-	/* clear them */
-	memset(&early_res[0], 0, sizeof(struct early_res) * max_early_res);
-	early_res = NULL;
-	max_early_res = 0;
-	early_res_count = 0;
-}
-#endif
-
-/* Check for already reserved areas */
-static inline int __init bad_addr(u64 *addrp, u64 size, u64 align)
-{
-	int i;
-	u64 addr = *addrp;
-	int changed = 0;
-	struct early_res *r;
-again:
-	i = find_overlapped_early(addr, addr + size);
-	r = &early_res[i];
-	if (i < max_early_res && r->end) {
-		*addrp = addr = round_up(r->end, align);
-		changed = 1;
-		goto again;
-	}
-	return changed;
-}
-
-/* Check for already reserved areas */
-static inline int __init bad_addr_size(u64 *addrp, u64 *sizep, u64 align)
-{
-	int i;
-	u64 addr = *addrp, last;
-	u64 size = *sizep;
-	int changed = 0;
-again:
-	last = addr + size;
-	for (i = 0; i < max_early_res && early_res[i].end; i++) {
-		struct early_res *r = &early_res[i];
-		if (last > r->start && addr < r->start) {
-			size = r->start - addr;
-			changed = 1;
-			goto again;
-		}
-		if (last > r->end && addr < r->end) {
-			addr = round_up(r->end, align);
-			size = last - addr;
-			changed = 1;
-			goto again;
-		}
-		if (last <= r->end && addr >= r->start) {
-			(*sizep)++;
-			return 0;
-		}
-	}
-	if (changed) {
-		*addrp = addr;
-		*sizep = size;
-	}
-	return changed;
-}
-
-/*
- * Find a free area with specified alignment in a specific range.
- * only with the area.between start to end is active range from early_node_map
- * so they are good as RAM
- */
-u64 __init find_early_area(u64 ei_start, u64 ei_last, u64 start, u64 end,
-			 u64 size, u64 align)
-{
-	u64 addr, last;
-
-	addr = round_up(ei_start, align);
-	if (addr < start)
-		addr = round_up(start, align);
-	if (addr >= ei_last)
-		goto out;
-	while (bad_addr(&addr, size, align) && addr+size <= ei_last)
-		;
-	last = addr + size;
-	if (last > ei_last)
-		goto out;
-	if (last > end)
-		goto out;
-
-	return addr;
-
-out:
-	return -1ULL;
-}
-
-u64 __init find_early_area_size(u64 ei_start, u64 ei_last, u64 start,
-			 u64 *sizep, u64 align)
-{
-	u64 addr, last;
-
-	addr = round_up(ei_start, align);
-	if (addr < start)
-		addr = round_up(start, align);
-	if (addr >= ei_last)
-		goto out;
-	*sizep = ei_last - addr;
-	while (bad_addr_size(&addr, sizep, align) && addr + *sizep <= ei_last)
-		;
-	last = addr + *sizep;
-	if (last > ei_last)
-		goto out;
-
-	return addr;
-
-out:
-	return -1ULL;
-}
-
-
diff --git a/include/linux/early_res.h b/include/linux/early_res.h
new file mode 100644
index 0000000..d3dd9ea
--- /dev/null
+++ b/include/linux/early_res.h
@@ -0,0 +1,21 @@
+#ifndef _LINUX_EARLY_RES_H
+#define _LINUX_EARLY_RES_H
+#ifdef __KERNEL__
+
+extern void reserve_early(u64 start, u64 end, char *name);
+extern void reserve_early_overlap_ok(u64 start, u64 end, char *name);
+extern void free_early(u64 start, u64 end);
+extern void early_res_to_bootmem(u64 start, u64 end);
+
+void reserve_early_without_check(u64 start, u64 end, char *name);
+u64 find_early_area(u64 ei_start, u64 ei_last, u64 start, u64 end,
+			 u64 size, u64 align);
+u64 find_early_area_size(u64 ei_start, u64 ei_last, u64 start,
+			 u64 *sizep, u64 align);
+u64 find_fw_memmap_area(u64 start, u64 end, u64 size, u64 align);
+#include <linux/range.h>
+int get_free_all_memory_range(struct range **rangep, int nodeid);
+
+#endif /* __KERNEL__ */
+
+#endif /* _LINUX_EARLY_RES_H */
diff --git a/kernel/Makefile b/kernel/Makefile
index ad47330..82f7cae 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -10,7 +10,7 @@ obj-y     = sched.o fork.o exec_domain.o panic.o printk.o \
 	    kthread.o wait.o kfifo.o sys_ni.o posix-cpu-timers.o mutex.o \
 	    hrtimer.o rwsem.o nsproxy.o srcu.o semaphore.o \
 	    notifier.o ksysfs.o pm_qos_params.o sched_clock.o cred.o \
-	    async.o range.o
+	    async.o range.o early_res.o
 obj-y += groups.o
 
 ifdef CONFIG_FUNCTION_TRACER
diff --git a/kernel/early_res.c b/kernel/early_res.c
new file mode 100644
index 0000000..4fd02b7
--- /dev/null
+++ b/kernel/early_res.c
@@ -0,0 +1,522 @@
+/*
+ * early_res, could be used to replace bootmem
+ */
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/init.h>
+#include <linux/bootmem.h>
+#include <linux/mm.h>
+#include <linux/early_res.h>
+
+/*
+ * Early reserved memory areas.
+ */
+/*
+ * need to make sure this one is bigger enough before
+ * find_fw_memmap_area could be used
+ */
+#define MAX_EARLY_RES_X 32
+
+struct early_res {
+	u64 start, end;
+	char name[15];
+	char overlap_ok;
+};
+static struct early_res early_res_x[MAX_EARLY_RES_X] __initdata;
+
+static int max_early_res __initdata = MAX_EARLY_RES_X;
+static struct early_res *early_res __initdata = &early_res_x[0];
+static int early_res_count __initdata;
+
+static int __init find_overlapped_early(u64 start, u64 end)
+{
+	int i;
+	struct early_res *r;
+
+	for (i = 0; i < max_early_res && early_res[i].end; i++) {
+		r = &early_res[i];
+		if (end > r->start && start < r->end)
+			break;
+	}
+
+	return i;
+}
+
+/*
+ * Drop the i-th range from the early reservation map,
+ * by copying any higher ranges down one over it, and
+ * clearing what had been the last slot.
+ */
+static void __init drop_range(int i)
+{
+	int j;
+
+	for (j = i + 1; j < max_early_res && early_res[j].end; j++)
+		;
+
+	memmove(&early_res[i], &early_res[i + 1],
+	       (j - 1 - i) * sizeof(struct early_res));
+
+	early_res[j - 1].end = 0;
+	early_res_count--;
+}
+
+/*
+ * Split any existing ranges that:
+ *  1) are marked 'overlap_ok', and
+ *  2) overlap with the stated range [start, end)
+ * into whatever portion (if any) of the existing range is entirely
+ * below or entirely above the stated range.  Drop the portion
+ * of the existing range that overlaps with the stated range,
+ * which will allow the caller of this routine to then add that
+ * stated range without conflicting with any existing range.
+ */
+static void __init drop_overlaps_that_are_ok(u64 start, u64 end)
+{
+	int i;
+	struct early_res *r;
+	u64 lower_start, lower_end;
+	u64 upper_start, upper_end;
+	char name[15];
+
+	for (i = 0; i < max_early_res && early_res[i].end; i++) {
+		r = &early_res[i];
+
+		/* Continue past non-overlapping ranges */
+		if (end <= r->start || start >= r->end)
+			continue;
+
+		/*
+		 * Leave non-ok overlaps as is; let caller
+		 * panic "Overlapping early reservations"
+		 * when it hits this overlap.
+		 */
+		if (!r->overlap_ok)
+			return;
+
+		/*
+		 * We have an ok overlap.  We will drop it from the early
+		 * reservation map, and add back in any non-overlapping
+		 * portions (lower or upper) as separate, overlap_ok,
+		 * non-overlapping ranges.
+		 */
+
+		/* 1. Note any non-overlapping (lower or upper) ranges. */
+		strncpy(name, r->name, sizeof(name) - 1);
+
+		lower_start = lower_end = 0;
+		upper_start = upper_end = 0;
+		if (r->start < start) {
+			lower_start = r->start;
+			lower_end = start;
+		}
+		if (r->end > end) {
+			upper_start = end;
+			upper_end = r->end;
+		}
+
+		/* 2. Drop the original ok overlapping range */
+		drop_range(i);
+
+		i--;		/* resume for-loop on copied down entry */
+
+		/* 3. Add back in any non-overlapping ranges. */
+		if (lower_end)
+			reserve_early_overlap_ok(lower_start, lower_end, name);
+		if (upper_end)
+			reserve_early_overlap_ok(upper_start, upper_end, name);
+	}
+}
+
+static void __init __reserve_early(u64 start, u64 end, char *name,
+						int overlap_ok)
+{
+	int i;
+	struct early_res *r;
+
+	i = find_overlapped_early(start, end);
+	if (i >= max_early_res)
+		panic("Too many early reservations");
+	r = &early_res[i];
+	if (r->end)
+		panic("Overlapping early reservations "
+		      "%llx-%llx %s to %llx-%llx %s\n",
+		      start, end - 1, name ? name : "", r->start,
+		      r->end - 1, r->name);
+	r->start = start;
+	r->end = end;
+	r->overlap_ok = overlap_ok;
+	if (name)
+		strncpy(r->name, name, sizeof(r->name) - 1);
+	early_res_count++;
+}
+
+/*
+ * A few early reservtations come here.
+ *
+ * The 'overlap_ok' in the name of this routine does -not- mean it
+ * is ok for these reservations to overlap an earlier reservation.
+ * Rather it means that it is ok for subsequent reservations to
+ * overlap this one.
+ *
+ * Use this entry point to reserve early ranges when you are doing
+ * so out of "Paranoia", reserving perhaps more memory than you need,
+ * just in case, and don't mind a subsequent overlapping reservation
+ * that is known to be needed.
+ *
+ * The drop_overlaps_that_are_ok() call here isn't really needed.
+ * It would be needed if we had two colliding 'overlap_ok'
+ * reservations, so that the second such would not panic on the
+ * overlap with the first.  We don't have any such as of this
+ * writing, but might as well tolerate such if it happens in
+ * the future.
+ */
+void __init reserve_early_overlap_ok(u64 start, u64 end, char *name)
+{
+	drop_overlaps_that_are_ok(start, end);
+	__reserve_early(start, end, name, 1);
+}
+
+u64 __init __weak find_fw_memmap_area(u64 start, u64 end, u64 size, u64 align)
+{
+	panic("should have find_fw_memmap_area defined with arch");
+
+	return -1ULL;
+}
+
+static void __init __check_and_double_early_res(u64 ex_start, u64 ex_end)
+{
+	u64 start, end, size, mem;
+	struct early_res *new;
+
+	/* do we have enough slots left ? */
+	if ((max_early_res - early_res_count) > max(max_early_res/8, 2))
+		return;
+
+	/* double it */
+	mem = -1ULL;
+	size = sizeof(struct early_res) * max_early_res * 2;
+	if (early_res == early_res_x)
+		start = 0;
+	else
+		start = early_res[0].end;
+	end = ex_start;
+	if (start + size < end)
+		mem = find_fw_memmap_area(start, end, size,
+					 sizeof(struct early_res));
+	if (mem == -1ULL) {
+		start = ex_end;
+		end = max_pfn_mapped << PAGE_SHIFT;
+		if (start + size < end)
+			mem = find_fw_memmap_area(start, end, size,
+						 sizeof(struct early_res));
+	}
+	if (mem == -1ULL)
+		panic("can not find more space for early_res array");
+
+	new = __va(mem);
+	/* save the first one for own */
+	new[0].start = mem;
+	new[0].end = mem + size;
+	new[0].overlap_ok = 0;
+	/* copy old to new */
+	if (early_res == early_res_x) {
+		memcpy(&new[1], &early_res[0],
+			 sizeof(struct early_res) * max_early_res);
+		memset(&new[max_early_res+1], 0,
+			 sizeof(struct early_res) * (max_early_res - 1));
+		early_res_count++;
+	} else {
+		memcpy(&new[1], &early_res[1],
+			 sizeof(struct early_res) * (max_early_res - 1));
+		memset(&new[max_early_res], 0,
+			 sizeof(struct early_res) * max_early_res);
+	}
+	memset(&early_res[0], 0, sizeof(struct early_res) * max_early_res);
+	early_res = new;
+	max_early_res *= 2;
+	printk(KERN_DEBUG "early_res array is doubled to %d at [%llx - %llx]\n",
+		max_early_res, mem, mem + size - 1);
+}
+
+/*
+ * Most early reservations come here.
+ *
+ * We first have drop_overlaps_that_are_ok() drop any pre-existing
+ * 'overlap_ok' ranges, so that we can then reserve this memory
+ * range without risk of panic'ing on an overlapping overlap_ok
+ * early reservation.
+ */
+void __init reserve_early(u64 start, u64 end, char *name)
+{
+	if (start >= end)
+		return;
+
+	__check_and_double_early_res(start, end);
+
+	drop_overlaps_that_are_ok(start, end);
+	__reserve_early(start, end, name, 0);
+}
+
+void __init reserve_early_without_check(u64 start, u64 end, char *name)
+{
+	struct early_res *r;
+
+	if (start >= end)
+		return;
+
+	__check_and_double_early_res(start, end);
+
+	r = &early_res[early_res_count];
+
+	r->start = start;
+	r->end = end;
+	r->overlap_ok = 0;
+	if (name)
+		strncpy(r->name, name, sizeof(r->name) - 1);
+	early_res_count++;
+}
+
+void __init free_early(u64 start, u64 end)
+{
+	struct early_res *r;
+	int i;
+
+	i = find_overlapped_early(start, end);
+	r = &early_res[i];
+	if (i >= max_early_res || r->end != end || r->start != start)
+		panic("free_early on not reserved area: %llx-%llx!",
+			 start, end - 1);
+
+	drop_range(i);
+}
+
+#ifdef CONFIG_NO_BOOTMEM
+static void __init subtract_early_res(struct range *range, int az)
+{
+	int i, count;
+	u64 final_start, final_end;
+	int idx = 0;
+
+	count  = 0;
+	for (i = 0; i < max_early_res && early_res[i].end; i++)
+		count++;
+
+	/* need to skip first one ?*/
+	if (early_res != early_res_x)
+		idx = 1;
+
+#define DEBUG_PRINT_EARLY_RES 1
+
+#if DEBUG_PRINT_EARLY_RES
+	printk(KERN_INFO "Subtract (%d early reservations)\n", count);
+#endif
+	for (i = idx; i < count; i++) {
+		struct early_res *r = &early_res[i];
+#if DEBUG_PRINT_EARLY_RES
+		printk(KERN_INFO "  #%d [%010llx - %010llx] %15s\n", i,
+			r->start, r->end, r->name);
+#endif
+		final_start = PFN_DOWN(r->start);
+		final_end = PFN_UP(r->end);
+		if (final_start >= final_end)
+			continue;
+		subtract_range(range, az, final_start, final_end);
+	}
+
+}
+
+int __init get_free_all_memory_range(struct range **rangep, int nodeid)
+{
+	int i, count;
+	u64 start = 0, end;
+	u64 size;
+	u64 mem;
+	struct range *range;
+	int nr_range;
+
+	count  = 0;
+	for (i = 0; i < max_early_res && early_res[i].end; i++)
+		count++;
+
+	count *= 2;
+
+	size = sizeof(struct range) * count;
+#ifdef MAX_DMA32_PFN
+	if (max_pfn_mapped > MAX_DMA32_PFN)
+		start = MAX_DMA32_PFN << PAGE_SHIFT;
+#endif
+	end = max_pfn_mapped << PAGE_SHIFT;
+	mem = find_fw_memmap_area(start, end, size, sizeof(struct range));
+	if (mem == -1ULL)
+		panic("can not find more space for range free");
+
+	range = __va(mem);
+	/* use early_node_map[] and early_res to get range array at first */
+	memset(range, 0, size);
+	nr_range = 0;
+
+	/* need to go over early_node_map to find out good range for node */
+	nr_range = add_from_early_node_map(range, count, nr_range, nodeid);
+#ifdef CONFIG_X86_32
+	subtract_range(range, count, max_low_pfn, -1UL);
+#endif
+	subtract_early_res(range, count);
+	nr_range = clean_sort_range(range, count);
+
+	/* need to clear it ? */
+	if (nodeid == MAX_NUMNODES) {
+		memset(&early_res[0], 0,
+			 sizeof(struct early_res) * max_early_res);
+		early_res = NULL;
+		max_early_res = 0;
+	}
+
+	*rangep = range;
+	return nr_range;
+}
+#else
+void __init early_res_to_bootmem(u64 start, u64 end)
+{
+	int i, count;
+	u64 final_start, final_end;
+	int idx = 0;
+
+	count  = 0;
+	for (i = 0; i < max_early_res && early_res[i].end; i++)
+		count++;
+
+	/* need to skip first one ?*/
+	if (early_res != early_res_x)
+		idx = 1;
+
+	printk(KERN_INFO "(%d/%d early reservations) ==> bootmem [%010llx - %010llx]\n",
+			 count - idx, max_early_res, start, end);
+	for (i = idx; i < count; i++) {
+		struct early_res *r = &early_res[i];
+		printk(KERN_INFO "  #%d [%010llx - %010llx] %16s", i,
+			r->start, r->end, r->name);
+		final_start = max(start, r->start);
+		final_end = min(end, r->end);
+		if (final_start >= final_end) {
+			printk(KERN_CONT "\n");
+			continue;
+		}
+		printk(KERN_CONT " ==> [%010llx - %010llx]\n",
+			final_start, final_end);
+		reserve_bootmem_generic(final_start, final_end - final_start,
+				BOOTMEM_DEFAULT);
+	}
+	/* clear them */
+	memset(&early_res[0], 0, sizeof(struct early_res) * max_early_res);
+	early_res = NULL;
+	max_early_res = 0;
+	early_res_count = 0;
+}
+#endif
+
+/* Check for already reserved areas */
+static inline int __init bad_addr(u64 *addrp, u64 size, u64 align)
+{
+	int i;
+	u64 addr = *addrp;
+	int changed = 0;
+	struct early_res *r;
+again:
+	i = find_overlapped_early(addr, addr + size);
+	r = &early_res[i];
+	if (i < max_early_res && r->end) {
+		*addrp = addr = round_up(r->end, align);
+		changed = 1;
+		goto again;
+	}
+	return changed;
+}
+
+/* Check for already reserved areas */
+static inline int __init bad_addr_size(u64 *addrp, u64 *sizep, u64 align)
+{
+	int i;
+	u64 addr = *addrp, last;
+	u64 size = *sizep;
+	int changed = 0;
+again:
+	last = addr + size;
+	for (i = 0; i < max_early_res && early_res[i].end; i++) {
+		struct early_res *r = &early_res[i];
+		if (last > r->start && addr < r->start) {
+			size = r->start - addr;
+			changed = 1;
+			goto again;
+		}
+		if (last > r->end && addr < r->end) {
+			addr = round_up(r->end, align);
+			size = last - addr;
+			changed = 1;
+			goto again;
+		}
+		if (last <= r->end && addr >= r->start) {
+			(*sizep)++;
+			return 0;
+		}
+	}
+	if (changed) {
+		*addrp = addr;
+		*sizep = size;
+	}
+	return changed;
+}
+
+/*
+ * Find a free area with specified alignment in a specific range.
+ * only with the area.between start to end is active range from early_node_map
+ * so they are good as RAM
+ */
+u64 __init find_early_area(u64 ei_start, u64 ei_last, u64 start, u64 end,
+			 u64 size, u64 align)
+{
+	u64 addr, last;
+
+	addr = round_up(ei_start, align);
+	if (addr < start)
+		addr = round_up(start, align);
+	if (addr >= ei_last)
+		goto out;
+	while (bad_addr(&addr, size, align) && addr+size <= ei_last)
+		;
+	last = addr + size;
+	if (last > ei_last)
+		goto out;
+	if (last > end)
+		goto out;
+
+	return addr;
+
+out:
+	return -1ULL;
+}
+
+u64 __init find_early_area_size(u64 ei_start, u64 ei_last, u64 start,
+			 u64 *sizep, u64 align)
+{
+	u64 addr, last;
+
+	addr = round_up(ei_start, align);
+	if (addr < start)
+		addr = round_up(start, align);
+	if (addr >= ei_last)
+		goto out;
+	*sizep = ei_last - addr;
+	while (bad_addr_size(&addr, sizep, align) && addr + *sizep <= ei_last)
+		;
+	last = addr + *sizep;
+	if (last > ei_last)
+		goto out;
+
+	return addr;
+
+out:
+	return -1ULL;
+}
+
+
-- 
1.6.4.2