x86: not use bootmem for x86

index 09b1698..669da09 100644
@@ -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",

index 712d15f..7182580 100644
@@ -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;

130 lines not on this page · raw message

new file mode 100644
index 0000000..0789f14
@@ -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

154 lines not on this page · raw message

index 46a10c8..71e0021 100644
@@ -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;

index 2356ea1..467dcac 100644
@@ -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;

@@ -172,7 +172,7 @@ 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)

@@ -206,7 +206,7 @@ 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);
 

@@ -245,7 +245,7 @@ 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.

@@ -271,13 +271,13 @@ 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;

@@ -300,7 +300,7 @@ 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);
 	}
 

index 467dcac..66a5d5a 100644
@@ -200,7 +200,7 @@ 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;

@@ -285,7 +285,8 @@ 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");
 	}

@@ -320,7 +321,8 @@ 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);
 		}
 	}

index f939d60..b267919 100644
@@ -60,6 +60,9 @@ void __devinit update_res(struct pci_root_info *info, size_t start,
 	if (start > end)
 		return;
 
+	if (start == (resource_size_t)~0)
+		return;
+
 	if (!merge)
 		goto addit;
 

index f81a2fa..145e0dd 100644
@@ -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);
 }

index 0789f14..17a23d2 100644
@@ -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

index 66a5d5a..6221720 100644
@@ -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;

@@ -341,21 +337,13 @@ 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)

index adbc23f..66d4ea0 100644
@@ -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

index 5dc9e8c..f4e8481 100644
@@ -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.

index 145e0dd..603b9ab 100644
@@ -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);
 	}
 }
 

index f7b8b98..3ab0bf4 100644
@@ -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
 	/*

index 9a0c258..2dccde0 100644
@@ -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;
 }

index 5198b9b..1ea79ad 100644
@@ -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
 

106 lines not on this page · raw message

index a1a7876..291f6d2 100644
@@ -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;

index 291f6d2..949d688 100644
@@ -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 */

index 1ea79ad..f9530eb 100644
@@ -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 */

index b10ec49..3446bed 100644
@@ -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).

98 lines not on this page · raw message

index 3232148..02f13cb 100644
@@ -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);

index ada8c20..b4a00dd 100644
@@ -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>
 

index ae5e40f..fe15cfb 100644
@@ -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 */

index 75e14e2..1aa966c 100644
@@ -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;
 

index 3ab0bf4..2c67cab 100644
@@ -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();
 

index 761249e..7d72e5f 100644
@@ -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,

194 lines not on this page · raw message

index 2c67cab..824fef7 100644
@@ -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();
 

index f9530eb..f13e5bd 100644
@@ -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();
 

index 02f13cb..a20e170 100644
@@ -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;
 }
 

index 3446bed..383daa8 100644
@@ -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,

index 60c467b..1335ad8 100644
@@ -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);

index 30fe668..eae8387 100644
@@ -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

371 lines not on this page · raw message

71 lines not on this page · raw message

index 083e7c9..841defe 100644
@@ -1929,7 +1929,10 @@ 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
 		}
 	}
 

index d9714bd..9506c39 100644
@@ -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);
 }
 
 

index 6ce4aab..0cdaf0b 100644
@@ -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))

index f13e5bd..21090d8 100644
@@ -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;
 

index 1335ad8..ede5e93 100644
@@ -1324,12 +1324,19 @@ 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);

96 lines not on this page · raw message

155 lines not on this page · raw message

index 669da09..06130b5 100644
@@ -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) {

index 155b2d6..bd6a361 100644
@@ -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);
 	}
 
 }

index 6221720..38e85b5 100644
@@ -144,7 +144,7 @@ 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));

@@ -174,7 +174,7 @@ 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 */

@@ -189,14 +189,16 @@ 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;

@@ -204,14 +206,15 @@ 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 */

@@ -266,7 +269,8 @@ 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;

@@ -283,7 +287,7 @@ 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");
 	}
 

@@ -298,7 +302,7 @@ 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);
 	}
 
 	/*

@@ -318,7 +322,7 @@ 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);
 		}
 	}

index 71e0021..74e2e61 100644
@@ -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;
 		}
 	}

index 64a5000..bb7faad 100644
@@ -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);
 	}

index 8ab9a38..e4e77ef 100644
@@ -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;
 }

index bd6a361..b7681e3 100644
@@ -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)
 {

index 5051b94..2e13544 100644
@@ -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

index b5a9896..452b7c4 100644
@@ -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

index 7d72e5f..efad699 100644
@@ -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);

new file mode 100644
index 0000000..2d43b16
@@ -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 */

560 lines not on this page · raw message

539 lines not on this page · raw message

index 3ae0051..aba02f2 100644
@@ -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;
 	}
 

index efad699..a8299e1 100644
@@ -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>
 

index 2d43b16..5a4d2eb 100644
@@ -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);
 

63 lines not on this page · raw message

60 lines not on this page · raw message

index d0a70cc..52804e9 100644
@@ -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];
 

index 52804e9..38a0c61 100644
@@ -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);
 

index 2dccde0..262867a 100644
@@ -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;
 }

index b20760c..809baaa 100644
@@ -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();

index 4009f65..6f414ed 100644
@@ -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 */

index 1221d23..8a6e583 100644
@@ -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))

index 5a4d2eb..9758f3d 100644
@@ -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);
 

index acd7be6..5c80050 100644
@@ -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
  */

index 38a0c61..e209fc4 100644
@@ -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");
 

index a8299e1..0e22296 100644
@@ -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);

deleted file mode 100644
index 9758f3d..0000000
@@ -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 */

index 5c80050..c5c52da 100644
@@ -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>
 

523 lines not on this page · raw message

new file mode 100644
index 0000000..d3dd9ea
@@ -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 */

522 lines not on this page · raw message

index c5c52da..62235e7 100644
@@ -1127,6 +1127,9 @@ void __init e820_reserve_resources_late(void)
 			end = MAX_RESOURCE_SIZE;
 		if (start >= end)
 			continue;
+		printk(KERN_DEBUG "reserve RAM buffer: %016Lx - %016Lx ",
+			       (unsigned long long) start,
+			       (unsigned long long) end);
 		reserve_region_with_split(&iomem_resource, start, end,
 					  "RAM buffer");
 	}

index 62235e7..09ca6e8 100644
@@ -509,11 +509,19 @@ u64 __init e820_remove_range(u64 start, u64 size, unsigned old_type,
 			     int checktype)
 {
 	int i;
+	u64 end;
 	u64 real_removed_size = 0;
 
 	if (size > (ULLONG_MAX - start))
 		size = ULLONG_MAX - start;
 
+	end = start + size;
+	printk(KERN_DEBUG "e820 remove range: %016Lx - %016Lx ",
+		       (unsigned long long) start,
+		       (unsigned long long) end);
+	e820_print_type(old_type);
+	printk(KERN_CONT "\n");
+
 	for (i = 0; i < e820.nr_map; i++) {
 		struct e820entry *ei = &e820.map[i];
 		u64 final_start, final_end;

index 2e13544..adedeef 100644
@@ -29,8 +29,6 @@ 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

index 452b7c4..b5a9896 100644
@@ -98,8 +98,6 @@ 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

index 824fef7..8b27c6c 100644
@@ -659,6 +659,23 @@ static struct dmi_system_id __initdata bad_bios_dmi_table[] = {
 	{}
 };
 
+static void __init e820_trim_bios_range(void)
+{
+	/*
+	 * A special case is the first 4Kb of memory;
+	 * This is a BIOS owned area, not kernel ram, but generally
+	 * not listed as such in the E820 table.
+	 */
+	e820_update_range(0, PAGE_SIZE, E820_RAM, E820_RESERVED);
+	/*
+	 * special case: Some BIOSen report the PC BIOS
+	 * area (640->1Mb) as ram even though it is not.
+	 * take them out.
+	 */
+	e820_remove_range(BIOS_BEGIN, BIOS_END - BIOS_BEGIN, E820_RAM, 1);
+	sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
+}
+
 /*
  * Determine if we were loaded by an EFI loader.  If so, then we have also been
  * passed the efi memmap, systab, etc., so we should use these data structures

@@ -822,7 +839,7 @@ void __init setup_arch(char **cmdline_p)
 	insert_resource(&iomem_resource, &data_resource);
 	insert_resource(&iomem_resource, &bss_resource);
 
-
+	e820_trim_bios_range();
 #ifdef CONFIG_X86_32
 	if (ppro_with_ram_bug()) {
 		e820_update_range(0x70000000ULL, 0x40000ULL, E820_RAM,

index 03c75ff..3c739b7 100644
@@ -29,22 +29,6 @@ int page_is_ram(unsigned long pagenr)
 	resource_size_t addr, end;
 	int i;
 
-	/*
-	 * A special case is the first 4Kb of memory;
-	 * This is a BIOS owned area, not kernel ram, but generally
-	 * not listed as such in the E820 table.
-	 */
-	if (pagenr == 0)
-		return 0;
-
-	/*
-	 * Second special case: Some BIOSen report the PC BIOS
-	 * area (640->1Mb) as ram even though it is not.
-	 */
-	if (pagenr >= (BIOS_BEGIN >> PAGE_SHIFT) &&
-		    pagenr < (BIOS_END >> PAGE_SHIFT))
-		return 0;
-
 	for (i = 0; i < e820.nr_map; i++) {
 		/*
 		 * Not usable memory:

index 7182580..645d78a 100644
@@ -16,6 +16,7 @@
 #include <asm/acpi.h>
 #include <asm/mmconfig.h>
 #include <asm/pci_x86.h>
+#include <asm/e820.h>
 
 struct pci_hostbridge_probe {
 	u32 bus;

@@ -27,23 +28,26 @@ struct pci_hostbridge_probe {
 static u64 __cpuinitdata fam10h_pci_mmconf_base;
 static int __cpuinitdata fam10h_pci_mmconf_base_status;
 
+/* only on BSP */
+static void __init_refok e820_add_mmconf_range(int busnbits)
+{
+	u64 end;
+
+	end = fam10h_pci_mmconf_base + (1ULL<<(busnbits + 20)) - 1;
+	if (!e820_all_mapped(fam10h_pci_mmconf_base, end+1, E820_RESERVED)) {
+		printk(KERN_DEBUG "Fam 10h mmconf [%llx, %llx]\n",
+				 fam10h_pci_mmconf_base, end);
+		e820_add_region(fam10h_pci_mmconf_base, 1ULL<<(busnbits + 20),
+				 E820_RESERVED);
+		sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
+	}
+}
+
 static struct pci_hostbridge_probe pci_probes[] __cpuinitdata = {
 	{ 0, 0x18, PCI_VENDOR_ID_AMD, 0x1200 },
 	{ 0xff, 0, PCI_VENDOR_ID_AMD, 0x1200 },
 };
 
-static int __cpuinit cmp_range(const void *x1, const void *x2)
-{
-	const struct range *r1 = x1;
-	const struct range *r2 = x2;
-	int start1, start2;
-
-	start1 = r1->start >> 32;
-	start2 = r2->start >> 32;
-
-	return start1 - start2;
-}
-
 /*[47:0] */
 /* need to avoid (0xfd<<32) and (0xfe<<32), ht used space */
 #define FAM10H_PCI_MMCONF_BASE (0xfcULL<<32)

@@ -115,6 +119,7 @@ static void __cpuinit get_fam10h_pci_mmconf_base(void)
 	 * above 4G
 	 */
 	hi_mmio_num = 0;
+	memset(range, 0, sizeof(range));
 	for (i = 0; i < 8; i++) {
 		u32 reg;
 		u64 start;

@@ -130,16 +135,14 @@ static void __cpuinit get_fam10h_pci_mmconf_base(void)
 		if (!end)
 			continue;
 
-		range[hi_mmio_num].start = start;
-		range[hi_mmio_num].end = end;
-		hi_mmio_num++;
+		hi_mmio_num = add_range(range, 8, hi_mmio_num, start, end);
 	}
 
 	if (!hi_mmio_num)
 		goto out;
 
 	/* sort the range */
-	sort(range, hi_mmio_num, sizeof(struct range), cmp_range, NULL);
+	sort_range(range, hi_mmio_num);
 
 	if (range[hi_mmio_num - 1].end < base)
 		goto out;

@@ -169,6 +172,7 @@ fail:
 out:
 	fam10h_pci_mmconf_base = base;
 	fam10h_pci_mmconf_base_status = 1;
+	e820_add_mmconf_range(8);
 }
 
 void __cpuinit fam10h_check_enable_mmcfg(void)

@@ -191,10 +195,12 @@ void __cpuinit fam10h_check_enable_mmcfg(void)
 		/* only trust the one handle 256 buses, if acpi=off */
 		if (!acpi_pci_disabled || busnbits >= 8) {
 			u64 base;
-			base = val & (0xffffULL << 32);
+			base = val & (FAM10H_MMIO_CONF_BASE_MASK <<
+					FAM10H_MMIO_CONF_BASE_SHIFT);
 			if (fam10h_pci_mmconf_base_status <= 0) {
 				fam10h_pci_mmconf_base = base;
 				fam10h_pci_mmconf_base_status = 1;
+				e820_add_mmconf_range(busnbits);
 				return;
 			} else if (fam10h_pci_mmconf_base ==  base)
 				return;

index 814940e..0e823c0 100644
@@ -19,7 +19,6 @@
 #include <linux/kernel_stat.h>
 #include <linux/rculist.h>
 #include <linux/hash.h>
-#include <linux/bootmem.h>
 #include <trace/events/irq.h>
 
 #include "internals.h"

@@ -87,12 +86,8 @@ void __ref init_kstat_irqs(struct irq_desc *desc, int node, int nr)
 {
 	void *ptr;
 
-	if (slab_is_available())
-		ptr = kzalloc_node(nr * sizeof(*desc->kstat_irqs),
-				   GFP_ATOMIC, node);
-	else
-		ptr = alloc_bootmem_node(NODE_DATA(node),
-				nr * sizeof(*desc->kstat_irqs));
+	ptr = kzalloc_node(nr * sizeof(*desc->kstat_irqs),
+			   GFP_ATOMIC, node);
 
 	/*
 	 * don't overwite if can not get new one

@@ -219,10 +214,7 @@ struct irq_desc * __ref irq_to_desc_alloc_node(unsigned int irq, int node)
 	if (desc)
 		goto out_unlock;
 
-	if (slab_is_available())
-		desc = kzalloc_node(sizeof(*desc), GFP_ATOMIC, node);
-	else
-		desc = alloc_bootmem_node(NODE_DATA(node), sizeof(*desc));
+	desc = kzalloc_node(sizeof(*desc), GFP_ATOMIC, node);
 
 	printk(KERN_DEBUG "  alloc irq_desc for %d on node %d\n", irq, node);
 	if (!desc) {

index dac44a9..8451878 100644
@@ -584,6 +584,7 @@ asmlinkage void __init start_kernel(void)
 		local_irq_disable();
 	}
 	rcu_init();
+	radix_tree_init();
 	/* init some links before init_ISA_irqs() */
 	early_irq_init();
 	init_IRQ();

@@ -659,7 +660,6 @@ asmlinkage void __init start_kernel(void)
 	key_init();
 	security_init();
 	vfs_caches_init(totalram_pages);
-	radix_tree_init();
 	signals_init();
 	/* rootfs populating might need page-writeback */
 	page_writeback_init();

index 0e823c0..266f798 100644
@@ -127,7 +127,7 @@ static void init_one_irq_desc(int irq, struct irq_desc *desc, int node)
  */
 DEFINE_RAW_SPINLOCK(sparse_irq_lock);
 
-struct irq_desc **irq_desc_ptrs __read_mostly;
+static struct irq_desc **irq_desc_ptrs __read_mostly;
 
 static struct irq_desc irq_desc_legacy[NR_IRQS_LEGACY] __cacheline_aligned_in_smp = {
 	[0 ... NR_IRQS_LEGACY-1] = {