kexec load failure introduced by "x86, memblock: Replace e820_/_early string with memblock_"

kexec load failure introduced by "x86, memblock: Replace e820_/_early string with memblock_"

[caiqian]

# /sbin/kexec -p '--command-line=ro root=/dev/mapper/VolGroup-lv_root rd_LVM_LV=VolGroup/lv_root rd_LVM_LV=VolGroup/lv_swap rd_NO_LUKS rd_NO_MD rd_NO_DM LANG=en_US.UTF-8 SYSFONT=latarcyrheb-sun16 KEYBOARDTYPE=pc KEYTABLE=us rhgb quiet console=tty0 console=ttyS0,115200 crashkernel=128M irqpoll maxcpus=1 reset_devices cgroup_disable=memory ' --initrd=/boot/initrd-2.6.36-rc3+kdump.img /boot/vmlinuz-2.6.36-rc3+

BUG: unable to handle kernel paging request at ffff8800dfffe400
IP: [<ffffffff8113376b>] per_cpu_ptr_to_phys+0x3b/0x120
PGD 1a26063 PUD 1fffc067 PMD 1fffd067 PTE 0
Oops: 0000 [#1] SMP 
last sysfs file: /sys/devices/system/cpu/cpu0/crash_notes
CPU 3 
Modules linked in: ipt_REJECT nf_conntrack_ipv4 nf_defrag_ipv4 iptable_filter ip_tables ip6t_REJECT nf_conntrack_ipv6 xt_state nf_conntrack ip6table_filter ip6_tables ipv6 virtio_balloon pcspkr 8139too 8139cp mii snd_intel8x0 snd_ac97_codec ac97_bus snd_seq snd_seq_device snd_pcm snd_timer snd soundcore snd_page_alloc sg i2c_piix4 i2c_core ext4 mbcache jbd2 floppy sd_mod crc_t10dif virtio_pci virtio_ring virtio pata_acpi ata_generic ata_piix dm_mod [last unloaded: scsi_wait_scan]

Pid: 5671, comm: kexec Not tainted 2.6.35+ #11 /KVM
RIP: 0010:[<ffffffff8113376b>]  [<ffffffff8113376b>] per_cpu_ptr_to_phys+0x3b/0x120
RSP: 0018:ffff88064567fe38  EFLAGS: 00010286
RAX: ffff8800df440000 RBX: ffff8800df41d990 RCX: ffff8800df400000
RDX: ffff8800dfff6400 RSI: 0000000000001000 RDI: ffff8800df41d990
RBP: ffff88064567fe58 R08: ffffffff81651f20 R09: ffff8800df40cb38
R10: 0000000000000001 R11: 0000000000000000 R12: ffff88083dcd18e0
R13: ffff88064567ff48 R14: 0000000000001000 R15: 00007f969401b000
FS:  00007f96952e4700(0000) GS:ffff8800df4c0000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: ffff8800dfffe400 CR3: 0000000818130000 CR4: 00000000000006e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400
Process kexec (pid: 5671, threadinfo ffff88064567e000, task ffff8808ddba0180)
Stack:
 ffff88064567fe68 ffff88083d4f8000 ffff88083dcd18e0 ffff88064567ff48
<0> ffff88064567fe78 ffffffff812ea28b ffff88064567fe78 ffff88083dcd18c0
<0> ffff88064567fe88 ffffffff812e4f0f ffff88064567fee8 ffffffff811a5d11
Call Trace:
 [<ffffffff812ea28b>] show_crash_notes+0x2b/0x50
 [<ffffffff812e4f0f>] sysdev_show+0x1f/0x30
 [<ffffffff811a5d11>] sysfs_read_file+0x111/0x1f0
 [<ffffffff8113e7e5>] vfs_read+0xb5/0x1a0
 [<ffffffff810b5952>] ? audit_syscall_entry+0x252/0x280
 [<ffffffff8113e921>] sys_read+0x51/0x90
 [<ffffffff8100b072>] system_call_fastpath+0x16/0x1b
Code: 00 00 48 8b 05 bf 81 e2 00 8b 35 dd 46 9c 00 48 8b 15 0a 47 9c 00 48 89 fb 48 8b 48 18 8b 05 a5 46 9c 00 c1 e0 0c 48 98 48 01 c8 <48> 03 04 f2 48 39 c7 0f 83 a0 00 00 00 8b 05 aa 46 9c 00 48 03 
RIP  [<ffffffff8113376b>] per_cpu_ptr_to_phys+0x3b/0x120
 RSP <ffff88064567fe38>
CR2: ffff8800dfffe400
---[ end trace 1f847047fea7430c ]---

It was discovered that this commit introduced the regression,

commit a9ce6bc15100023b411f8117e53a016d61889800
Author: Yinghai Lu <yinghai@kernel.org>
Date:   Wed Aug 25 13:39:17 2010 -0700

    x86, memblock: Replace e820_/_early string with memblock_
    
    1.include linux/memblock.h directly. so later could reduce e820.h reference.
    2 this patch is done by sed scripts mainly
    
    -v2: use MEMBLOCK_ERROR instead of -1ULL or -1UL
    
    Signed-off-by: Yinghai Lu <yinghai@kernel.org>
    Signed-off-by: H. Peter Anvin <hpa@zytor.com>

diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index 8406ed7..8e4a165 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -90,7 +90,7 @@ extern void __iomem *efi_ioremap(unsigned long addr, unsigned long size,
 #endif /* CONFIG_X86_32 */
 
 extern int add_efi_memmap;
-extern void efi_reserve_early(void);
+extern void efi_memblock_x86_reserve_range(void);
 extern void efi_call_phys_prelog(void);
 extern void efi_call_phys_epilog(void);
 
diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c
index fcc3c61..d829e75 100644
--- a/arch/x86/kernel/acpi/sleep.c
+++ b/arch/x86/kernel/acpi/sleep.c
@@ -7,6 +7,7 @@
 
 #include <linux/acpi.h>
 #include <linux/bootmem.h>
+#include <linux/memblock.h>
 #include <linux/dmi.h>
 #include <linux/cpumask.h>
 #include <asm/segment.h>
@@ -125,7 +126,7 @@ void acpi_restore_state_mem(void)
  */
 void __init acpi_reserve_wakeup_memory(void)
 {
-	unsigned long mem;
+	phys_addr_t mem;
 
 	if ((&wakeup_code_end - &wakeup_code_start) > WAKEUP_SIZE) {
 		printk(KERN_ERR
@@ -133,15 +134,15 @@ void __init acpi_reserve_wakeup_memory(void)
 		return;
 	}
 
-	mem = find_e820_area(0, 1<<20, WAKEUP_SIZE, PAGE_SIZE);
+	mem = memblock_find_in_range(0, 1<<20, WAKEUP_SIZE, PAGE_SIZE);
 
-	if (mem == -1L) {
+	if (mem == MEMBLOCK_ERROR) {
 		printk(KERN_ERR "ACPI: Cannot allocate lowmem, S3 disabled.\n");
 		return;
 	}
 	acpi_realmode = (unsigned long) phys_to_virt(mem);
 	acpi_wakeup_address = mem;
-	reserve_early(mem, mem + WAKEUP_SIZE, "ACPI WAKEUP");
+	memblock_x86_reserve_range(mem, mem + WAKEUP_SIZE, "ACPI WAKEUP");
 }
 
 
diff --git a/arch/x86/kernel/apic/numaq_32.c b/arch/x86/kernel/apic/numaq_32.c
index 3e28401..960f26a 100644
--- a/arch/x86/kernel/apic/numaq_32.c
+++ b/arch/x86/kernel/apic/numaq_32.c
@@ -26,6 +26,7 @@
 #include <linux/nodemask.h>
 #include <linux/topology.h>
 #include <linux/bootmem.h>
+#include <linux/memblock.h>
 #include <linux/threads.h>
 #include <linux/cpumask.h>
 #include <linux/kernel.h>
@@ -88,7 +89,7 @@ static inline void numaq_register_node(int node, struct sys_cfg_data *scd)
 	node_end_pfn[node] =
 		 MB_TO_PAGES(eq->hi_shrd_mem_start + eq->hi_shrd_mem_size);
 
-	e820_register_active_regions(node, node_start_pfn[node],
+	memblock_x86_register_active_regions(node, node_start_pfn[node],
 						node_end_pfn[node]);
 
 	memory_present(node, node_start_pfn[node], node_end_pfn[node]);
diff --git a/arch/x86/kernel/efi.c b/arch/x86/kernel/efi.c
index c2fa9b8..0fe27d7 100644
--- a/arch/x86/kernel/efi.c
+++ b/arch/x86/kernel/efi.c
@@ -30,6 +30,7 @@
 #include <linux/init.h>
 #include <linux/efi.h>
 #include <linux/bootmem.h>
+#include <linux/memblock.h>
 #include <linux/spinlock.h>
 #include <linux/uaccess.h>
 #include <linux/time.h>
@@ -275,7 +276,7 @@ static void __init do_add_efi_memmap(void)
 	sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
 }
 
-void __init efi_reserve_early(void)
+void __init efi_memblock_x86_reserve_range(void)
 {
 	unsigned long pmap;
 
@@ -290,7 +291,7 @@ void __init efi_reserve_early(void)
 		boot_params.efi_info.efi_memdesc_size;
 	memmap.desc_version = boot_params.efi_info.efi_memdesc_version;
 	memmap.desc_size = boot_params.efi_info.efi_memdesc_size;
-	reserve_early(pmap, pmap + memmap.nr_map * memmap.desc_size,
+	memblock_x86_reserve_range(pmap, pmap + memmap.nr_map * memmap.desc_size,
 		      "EFI memmap");
 }
 
diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c
index da60aa8..74e4cf6 100644
--- a/arch/x86/kernel/head32.c
+++ b/arch/x86/kernel/head32.c
@@ -42,7 +42,7 @@ void __init i386_start_kernel(void)
 	memblock_x86_reserve_range(PAGE_SIZE, PAGE_SIZE + PAGE_SIZE, "EX TRAMPOLINE");
 #endif
 
-	reserve_early(__pa_symbol(&_text), __pa_symbol(&__bss_stop), "TEXT DATA BSS");
+	memblock_x86_reserve_range(__pa_symbol(&_text), __pa_symbol(&__bss_stop), "TEXT DATA BSS");
 
 #ifdef CONFIG_BLK_DEV_INITRD
 	/* Reserve INITRD */
@@ -51,7 +51,7 @@ void __init i386_start_kernel(void)
 		u64 ramdisk_image = boot_params.hdr.ramdisk_image;
 		u64 ramdisk_size  = boot_params.hdr.ramdisk_size;
 		u64 ramdisk_end   = PAGE_ALIGN(ramdisk_image + ramdisk_size);
-		reserve_early(ramdisk_image, ramdisk_end, "RAMDISK");
+		memblock_x86_reserve_range(ramdisk_image, ramdisk_end, "RAMDISK");
 	}
 #endif
 
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 8ee930f..97adf98 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -101,7 +101,7 @@ void __init x86_64_start_reservations(char *real_mode_data)
 
 	memblock_init();
 
-	reserve_early(__pa_symbol(&_text), __pa_symbol(&__bss_stop), "TEXT DATA BSS");
+	memblock_x86_reserve_range(__pa_symbol(&_text), __pa_symbol(&__bss_stop), "TEXT DATA BSS");
 
 #ifdef CONFIG_BLK_DEV_INITRD
 	/* Reserve INITRD */
@@ -110,7 +110,7 @@ void __init x86_64_start_reservations(char *real_mode_data)
 		unsigned long ramdisk_image = boot_params.hdr.ramdisk_image;
 		unsigned long ramdisk_size  = boot_params.hdr.ramdisk_size;
 		unsigned long ramdisk_end   = PAGE_ALIGN(ramdisk_image + ramdisk_size);
-		reserve_early(ramdisk_image, ramdisk_end, "RAMDISK");
+		memblock_x86_reserve_range(ramdisk_image, ramdisk_end, "RAMDISK");
 	}
 #endif
 
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index bbe0aaf..a4f0173 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -302,7 +302,7 @@ static inline void init_gbpages(void)
 static void __init reserve_brk(void)
 {
 	if (_brk_end > _brk_start)
-		reserve_early(__pa(_brk_start), __pa(_brk_end), "BRK");
+		memblock_x86_reserve_range(__pa(_brk_start), __pa(_brk_end), "BRK");
 
 	/* Mark brk area as locked down and no longer taking any
 	   new allocations */
@@ -324,17 +324,16 @@ static void __init relocate_initrd(void)
 	char *p, *q;
 
 	/* We need to move the initrd down into lowmem */
-	ramdisk_here = find_e820_area(0, end_of_lowmem, area_size,
+	ramdisk_here = memblock_find_in_range(0, end_of_lowmem, area_size,
 					 PAGE_SIZE);
 
-	if (ramdisk_here == -1ULL)
+	if (ramdisk_here == MEMBLOCK_ERROR)
 		panic("Cannot find place for new RAMDISK of size %lld\n",
 			 ramdisk_size);
 
 	/* Note: this includes all the lowmem currently occupied by
 	   the initrd, we rely on that fact to keep the data intact. */
-	reserve_early(ramdisk_here, ramdisk_here + area_size,
-			 "NEW RAMDISK");
+	memblock_x86_reserve_range(ramdisk_here, ramdisk_here + area_size, "NEW RAMDISK");
 	initrd_start = ramdisk_here + PAGE_OFFSET;
 	initrd_end   = initrd_start + ramdisk_size;
 	printk(KERN_INFO "Allocated new RAMDISK: %08llx - %08llx\n",
@@ -390,7 +389,7 @@ static void __init reserve_initrd(void)
 	initrd_start = 0;
 
 	if (ramdisk_size >= (end_of_lowmem>>1)) {
-		free_early(ramdisk_image, ramdisk_end);
+		memblock_x86_free_range(ramdisk_image, ramdisk_end);
 		printk(KERN_ERR "initrd too large to handle, "
 		       "disabling initrd\n");
 		return;
@@ -413,7 +412,7 @@ static void __init reserve_initrd(void)
 
 	relocate_initrd();
 
-	free_early(ramdisk_image, ramdisk_end);
+	memblock_x86_free_range(ramdisk_image, ramdisk_end);
 }
 #else
 static void __init reserve_initrd(void)
@@ -469,7 +468,7 @@ static void __init e820_reserve_setup_data(void)
 	e820_print_map("reserve setup_data");
 }
 
-static void __init reserve_early_setup_data(void)
+static void __init memblock_x86_reserve_range_setup_data(void)
 {
 	struct setup_data *data;
 	u64 pa_data;
@@ -481,7 +480,7 @@ static void __init reserve_early_setup_data(void)
 	while (pa_data) {
 		data = early_memremap(pa_data, sizeof(*data));
 		sprintf(buf, "setup data %x", data->type);
-		reserve_early(pa_data, pa_data+sizeof(*data)+data->len, buf);
+		memblock_x86_reserve_range(pa_data, pa_data+sizeof(*data)+data->len, buf);
 		pa_data = data->next;
 		early_iounmap(data, sizeof(*data));
 	}
@@ -519,23 +518,23 @@ static void __init reserve_crashkernel(void)
 	if (crash_base <= 0) {
 		const unsigned long long alignment = 16<<20;	/* 16M */
 
-		crash_base = find_e820_area(alignment, ULONG_MAX, crash_size,
+		crash_base = memblock_find_in_range(alignment, ULONG_MAX, crash_size,
 				 alignment);
-		if (crash_base == -1ULL) {
+		if (crash_base == MEMBLOCK_ERROR) {
 			pr_info("crashkernel reservation failed - No suitable area found.\n");
 			return;
 		}
 	} else {
 		unsigned long long start;
 
-		start = find_e820_area(crash_base, ULONG_MAX, crash_size,
+		start = memblock_find_in_range(crash_base, ULONG_MAX, crash_size,
 				 1<<20);
 		if (start != crash_base) {
 			pr_info("crashkernel reservation failed - memory is in use.\n");
 			return;
 		}
 	}
-	reserve_early(crash_base, crash_base + crash_size, "CRASH KERNEL");
+	memblock_x86_reserve_range(crash_base, crash_base + crash_size, "CRASH KERNEL");
 
 	printk(KERN_INFO "Reserving %ldMB of memory at %ldMB "
 			"for crashkernel (System RAM: %ldMB)\n",
@@ -786,7 +785,7 @@ void __init setup_arch(char **cmdline_p)
 #endif
 	 4)) {
 		efi_enabled = 1;
-		efi_reserve_early();
+		efi_memblock_x86_reserve_range();
 	}
 #endif
 
@@ -846,7 +845,7 @@ void __init setup_arch(char **cmdline_p)
 	vmi_activate();
 
 	/* after early param, so could get panic from serial */
-	reserve_early_setup_data();
+	memblock_x86_reserve_range_setup_data();
 
 	if (acpi_mps_check()) {
 #ifdef CONFIG_X86_LOCAL_APIC
diff --git a/arch/x86/kernel/trampoline.c b/arch/x86/kernel/trampoline.c
index c652ef6..7c2102c 100644
--- a/arch/x86/kernel/trampoline.c
+++ b/arch/x86/kernel/trampoline.c
@@ -1,7 +1,7 @@
 #include <linux/io.h>
+#include <linux/memblock.h>
 
 #include <asm/trampoline.h>
-#include <asm/e820.h>
 
 #if defined(CONFIG_X86_64) && defined(CONFIG_ACPI_SLEEP)
 #define __trampinit
@@ -16,15 +16,15 @@ unsigned char *__trampinitdata trampoline_base;
 
 void __init reserve_trampoline_memory(void)
 {
-	unsigned long mem;
+	phys_addr_t mem;
 
 	/* Has to be in very low memory so we can execute real-mode AP code. */
-	mem = find_e820_area(0, 1<<20, TRAMPOLINE_SIZE, PAGE_SIZE);
-	if (mem == -1L)
+	mem = memblock_find_in_range(0, 1<<20, TRAMPOLINE_SIZE, PAGE_SIZE);
+	if (mem == MEMBLOCK_ERROR)
 		panic("Cannot allocate trampoline\n");
 
 	trampoline_base = __va(mem);
-	reserve_early(mem, mem + TRAMPOLINE_SIZE, "TRAMPOLINE");
+	memblock_x86_reserve_range(mem, mem + TRAMPOLINE_SIZE, "TRAMPOLINE");
 }
 
 /*
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index b278535..c0e28a1 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -2,6 +2,7 @@
 #include <linux/initrd.h>
 #include <linux/ioport.h>
 #include <linux/swap.h>
+#include <linux/memblock.h>
 
 #include <asm/cacheflush.h>
 #include <asm/e820.h>
@@ -33,6 +34,7 @@ static void __init find_early_table_space(unsigned long end, int use_pse,
 					  int use_gbpages)
 {
 	unsigned long puds, pmds, ptes, tables, start;
+	phys_addr_t base;
 
 	puds = (end + PUD_SIZE - 1) >> PUD_SHIFT;
 	tables = roundup(puds * sizeof(pud_t), PAGE_SIZE);
@@ -75,12 +77,12 @@ static void __init find_early_table_space(unsigned long end, int use_pse,
 #else
 	start = 0x8000;
 #endif
-	e820_table_start = find_e820_area(start, max_pfn_mapped<<PAGE_SHIFT,
+	base = memblock_find_in_range(start, max_pfn_mapped<<PAGE_SHIFT,
 					tables, PAGE_SIZE);
-	if (e820_table_start == -1UL)
+	if (base == MEMBLOCK_ERROR)
 		panic("Cannot find space for the kernel page tables");
 
-	e820_table_start >>= PAGE_SHIFT;
+	e820_table_start = base >> PAGE_SHIFT;
 	e820_table_end = e820_table_start;
 	e820_table_top = e820_table_start + (tables >> PAGE_SHIFT);
 
@@ -299,7 +301,7 @@ unsigned long __init_refok init_memory_mapping(unsigned long start,
 	__flush_tlb_all();
 
 	if (!after_bootmem && e820_table_end > e820_table_start)
-		reserve_early(e820_table_start << PAGE_SHIFT,
+		memblock_x86_reserve_range(e820_table_start << PAGE_SHIFT,
 				 e820_table_end << PAGE_SHIFT, "PGTABLE");
 
 	if (!after_bootmem)
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 90e0545..63b09ba 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -25,6 +25,7 @@
 #include <linux/pfn.h>
 #include <linux/poison.h>
 #include <linux/bootmem.h>
+#include <linux/memblock.h>
 #include <linux/proc_fs.h>
 #include <linux/memory_hotplug.h>
 #include <linux/initrd.h>
@@ -712,14 +713,14 @@ void __init initmem_init(unsigned long start_pfn, unsigned long end_pfn,
 	highstart_pfn = highend_pfn = max_pfn;
 	if (max_pfn > max_low_pfn)
 		highstart_pfn = max_low_pfn;
-	e820_register_active_regions(0, 0, highend_pfn);
+	memblock_x86_register_active_regions(0, 0, highend_pfn);
 	sparse_memory_present_with_active_regions(0);
 	printk(KERN_NOTICE "%ldMB HIGHMEM available.\n",
 		pages_to_mb(highend_pfn - highstart_pfn));
 	num_physpages = highend_pfn;
 	high_memory = (void *) __va(highstart_pfn * PAGE_SIZE - 1) + 1;
 #else
-	e820_register_active_regions(0, 0, max_low_pfn);
+	memblock_x86_register_active_regions(0, 0, max_low_pfn);
 	sparse_memory_present_with_active_regions(0);
 	num_physpages = max_low_pfn;
 	high_memory = (void *) __va(max_low_pfn * PAGE_SIZE - 1) + 1;
@@ -776,16 +777,16 @@ void __init setup_bootmem_allocator(void)
 {
 #ifndef CONFIG_NO_BOOTMEM
 	int nodeid;
-	unsigned long bootmap_size, bootmap;
+	phys_addr_t bootmap_size, bootmap;
 	/*
 	 * Initialize the boot-time allocator (with low memory only):
 	 */
 	bootmap_size = bootmem_bootmap_pages(max_low_pfn)<<PAGE_SHIFT;
-	bootmap = find_e820_area(0, max_pfn_mapped<<PAGE_SHIFT, bootmap_size,
+	bootmap = memblock_find_in_range(0, max_pfn_mapped<<PAGE_SHIFT, bootmap_size,
 				 PAGE_SIZE);
-	if (bootmap == -1L)
+	if (bootmap == MEMBLOCK_ERROR)
 		panic("Cannot find bootmem map of size %ld\n", bootmap_size);
-	reserve_early(bootmap, bootmap + bootmap_size, "BOOTMAP");
+	memblock_x86_reserve_range(bootmap, bootmap + bootmap_size, "BOOTMAP");
 #endif
 
 	printk(KERN_INFO "  mapped low ram: 0 - %08lx\n",
@@ -1069,3 +1070,4 @@ void mark_rodata_ro(void)
 #endif
 }
 #endif
+
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 634fa08..592b236 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -21,6 +21,7 @@
 #include <linux/initrd.h>
 #include <linux/pagemap.h>
 #include <linux/bootmem.h>
+#include <linux/memblock.h>
 #include <linux/proc_fs.h>
 #include <linux/pci.h>
 #include <linux/pfn.h>
@@ -577,18 +578,18 @@ void __init initmem_init(unsigned long start_pfn, unsigned long end_pfn,
 	unsigned long bootmap_size, bootmap;
 
 	bootmap_size = bootmem_bootmap_pages(end_pfn)<<PAGE_SHIFT;
-	bootmap = find_e820_area(0, end_pfn<<PAGE_SHIFT, bootmap_size,
+	bootmap = memblock_find_in_range(0, end_pfn<<PAGE_SHIFT, bootmap_size,
 				 PAGE_SIZE);
-	if (bootmap == -1L)
+	if (bootmap == MEMBLOCK_ERROR)
 		panic("Cannot find bootmem map of size %ld\n", bootmap_size);
-	reserve_early(bootmap, bootmap + bootmap_size, "BOOTMAP");
+	memblock_x86_reserve_range(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);
+	memblock_x86_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);
+	memblock_x86_register_active_regions(0, start_pfn, end_pfn);
 #endif
 }
 #endif
diff --git a/arch/x86/mm/k8topology_64.c b/arch/x86/mm/k8topology_64.c
index 970ed57..966de93 100644
--- a/arch/x86/mm/k8topology_64.c
+++ b/arch/x86/mm/k8topology_64.c
@@ -11,6 +11,8 @@
 #include <linux/string.h>
 #include <linux/module.h>
 #include <linux/nodemask.h>
+#include <linux/memblock.h>
+
 #include <asm/io.h>
 #include <linux/pci_ids.h>
 #include <linux/acpi.h>
@@ -222,7 +224,7 @@ int __init k8_scan_nodes(void)
 	for_each_node_mask(i, node_possible_map) {
 		int j;
 
-		e820_register_active_regions(i,
+		memblock_x86_register_active_regions(i,
 				nodes[i].start >> PAGE_SHIFT,
 				nodes[i].end >> PAGE_SHIFT);
 		for (j = apicid_base; j < cores + apicid_base; j++)
diff --git a/arch/x86/mm/memtest.c b/arch/x86/mm/memtest.c
index 18d244f..92faf3a 100644
--- a/arch/x86/mm/memtest.c
+++ b/arch/x86/mm/memtest.c
@@ -6,8 +6,7 @@
 #include <linux/smp.h>
 #include <linux/init.h>
 #include <linux/pfn.h>
-
-#include <asm/e820.h>
+#include <linux/memblock.h>
 
 static u64 patterns[] __initdata = {
 	0,
@@ -35,7 +34,7 @@ static void __init reserve_bad_mem(u64 pattern, u64 start_bad, u64 end_bad)
 	       (unsigned long long) pattern,
 	       (unsigned long long) start_bad,
 	       (unsigned long long) end_bad);
-	reserve_early(start_bad, end_bad, "BAD RAM");
+	memblock_x86_reserve_range(start_bad, end_bad, "BAD RAM");
 }
 
 static void __init memtest(u64 pattern, u64 start_phys, u64 size)
@@ -74,7 +73,7 @@ static void __init do_one_pass(u64 pattern, u64 start, u64 end)
 	u64 size = 0;
 
 	while (start < end) {
-		start = find_e820_area_size(start, &size, 1);
+		start = memblock_x86_find_in_range_size(start, &size, 1);
 
 		/* done ? */
 		if (start >= end)
diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c
index 809baaa..ddf9730 100644
--- a/arch/x86/mm/numa_32.c
+++ b/arch/x86/mm/numa_32.c
@@ -24,6 +24,7 @@
 
 #include <linux/mm.h>
 #include <linux/bootmem.h>
+#include <linux/memblock.h>
 #include <linux/mmzone.h>
 #include <linux/highmem.h>
 #include <linux/initrd.h>
@@ -120,7 +121,7 @@ int __init get_memcfg_numa_flat(void)
 
 	node_start_pfn[0] = 0;
 	node_end_pfn[0] = max_pfn;
-	e820_register_active_regions(0, 0, max_pfn);
+	memblock_x86_register_active_regions(0, 0, max_pfn);
 	memory_present(0, 0, max_pfn);
 	node_remap_size[0] = node_memmap_size_bytes(0, 0, max_pfn);
 
@@ -161,14 +162,14 @@ static void __init allocate_pgdat(int nid)
 		NODE_DATA(nid) = (pg_data_t *)node_remap_start_vaddr[nid];
 	else {
 		unsigned long pgdat_phys;
-		pgdat_phys = find_e820_area(min_low_pfn<<PAGE_SHIFT,
+		pgdat_phys = memblock_find_in_range(min_low_pfn<<PAGE_SHIFT,
 				 max_pfn_mapped<<PAGE_SHIFT,
 				 sizeof(pg_data_t),
 				 PAGE_SIZE);
 		NODE_DATA(nid) = (pg_data_t *)(pfn_to_kaddr(pgdat_phys>>PAGE_SHIFT));
 		memset(buf, 0, sizeof(buf));
 		sprintf(buf, "NODE_DATA %d",  nid);
-		reserve_early(pgdat_phys, pgdat_phys + sizeof(pg_data_t), buf);
+		memblock_x86_reserve_range(pgdat_phys, pgdat_phys + sizeof(pg_data_t), buf);
 	}
 	printk(KERN_DEBUG "allocate_pgdat: node %d NODE_DATA %08lx\n",
 		nid, (unsigned long)NODE_DATA(nid));
@@ -291,15 +292,15 @@ static __init unsigned long calculate_numa_remap_pages(void)
 						 PTRS_PER_PTE);
 		node_kva_target <<= PAGE_SHIFT;
 		do {
-			node_kva_final = find_e820_area(node_kva_target,
+			node_kva_final = memblock_find_in_range(node_kva_target,
 					((u64)node_end_pfn[nid])<<PAGE_SHIFT,
 						((u64)size)<<PAGE_SHIFT,
 						LARGE_PAGE_BYTES);
 			node_kva_target -= LARGE_PAGE_BYTES;
-		} while (node_kva_final == -1ULL &&
+		} while (node_kva_final == MEMBLOCK_ERROR &&
 			 (node_kva_target>>PAGE_SHIFT) > (node_start_pfn[nid]));
 
-		if (node_kva_final == -1ULL)
+		if (node_kva_final == MEMBLOCK_ERROR)
 			panic("Can not get kva ram\n");
 
 		node_remap_size[nid] = size;
@@ -318,9 +319,9 @@ static __init unsigned long calculate_numa_remap_pages(void)
 		 *  but we could have some hole in high memory, and it will only
 		 *  check page_is_ram(pfn) && !page_is_reserved_early(pfn) to decide
 		 *  to use it as free.
-		 *  So reserve_early here, hope we don't run out of that array
+		 *  So memblock_x86_reserve_range here, hope we don't run out of that array
 		 */
-		reserve_early(node_kva_final,
+		memblock_x86_reserve_range(node_kva_final,
 			      node_kva_final+(((u64)size)<<PAGE_SHIFT),
 			      "KVA RAM");
 
@@ -367,14 +368,14 @@ void __init initmem_init(unsigned long start_pfn, unsigned long end_pfn,
 
 	kva_target_pfn = round_down(max_low_pfn - kva_pages, PTRS_PER_PTE);
 	do {
-		kva_start_pfn = find_e820_area(kva_target_pfn<<PAGE_SHIFT,
+		kva_start_pfn = memblock_find_in_range(kva_target_pfn<<PAGE_SHIFT,
 					max_low_pfn<<PAGE_SHIFT,
 					kva_pages<<PAGE_SHIFT,
 					PTRS_PER_PTE<<PAGE_SHIFT) >> PAGE_SHIFT;
 		kva_target_pfn -= PTRS_PER_PTE;
-	} while (kva_start_pfn == -1UL && kva_target_pfn > min_low_pfn);
+	} while (kva_start_pfn == MEMBLOCK_ERROR && kva_target_pfn > min_low_pfn);
 
-	if (kva_start_pfn == -1UL)
+	if (kva_start_pfn == MEMBLOCK_ERROR)
 		panic("Can not get kva space\n");
 
 	printk(KERN_INFO "kva_start_pfn ~ %lx max_low_pfn ~ %lx\n",
@@ -382,7 +383,7 @@ void __init initmem_init(unsigned long start_pfn, unsigned long end_pfn,
 	printk(KERN_INFO "max_pfn = %lx\n", max_pfn);
 
 	/* avoid clash with initrd */
-	reserve_early(kva_start_pfn<<PAGE_SHIFT,
+	memblock_x86_reserve_range(kva_start_pfn<<PAGE_SHIFT,
 		      (kva_start_pfn + kva_pages)<<PAGE_SHIFT,
 		     "KVA PG");
 #ifdef CONFIG_HIGHMEM
diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c
index 3d54f9f..984b1ff 100644
--- a/arch/x86/mm/numa_64.c
+++ b/arch/x86/mm/numa_64.c
@@ -87,16 +87,16 @@ static int __init allocate_cachealigned_memnodemap(void)
 
 	addr = 0x8000;
 	nodemap_size = roundup(sizeof(s16) * memnodemapsize, L1_CACHE_BYTES);
-	nodemap_addr = find_e820_area(addr, max_pfn<<PAGE_SHIFT,
+	nodemap_addr = memblock_find_in_range(addr, max_pfn<<PAGE_SHIFT,
 				      nodemap_size, L1_CACHE_BYTES);
-	if (nodemap_addr == -1UL) {
+	if (nodemap_addr == MEMBLOCK_ERROR) {
 		printk(KERN_ERR
 		       "NUMA: Unable to allocate Memory to Node hash map\n");
 		nodemap_addr = nodemap_size = 0;
 		return -1;
 	}
 	memnodemap = phys_to_virt(nodemap_addr);
-	reserve_early(nodemap_addr, nodemap_addr + nodemap_size, "MEMNODEMAP");
+	memblock_x86_reserve_range(nodemap_addr, nodemap_addr + nodemap_size, "MEMNODEMAP");
 
 	printk(KERN_DEBUG "NUMA: Allocated memnodemap from %lx - %lx\n",
 	       nodemap_addr, nodemap_addr + nodemap_size);
@@ -227,7 +227,7 @@ 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");
+	memblock_x86_reserve_range(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);
@@ -246,7 +246,7 @@ setup_node_bootmem(int nodeid, unsigned long start, unsigned long end)
 	 * Find a place for the bootmem map
 	 * nodedata_phys could be on other nodes by alloc_bootmem,
 	 * so need to sure bootmap_start not to be small, otherwise
-	 * early_node_mem will get that with find_e820_area instead
+	 * early_node_mem will get that with memblock_find_in_range instead
 	 * of alloc_bootmem, that could clash with reserved range
 	 */
 	bootmap_pages = bootmem_bootmap_pages(last_pfn - start_pfn);
@@ -258,12 +258,12 @@ 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)  {
-		free_early(nodedata_phys, nodedata_phys + pgdat_size);
+		memblock_x86_free_range(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),
+	memblock_x86_reserve_range(bootmap_start, bootmap_start+(bootmap_pages<<PAGE_SHIFT),
 			"BOOTMAP");
 
 	bootmap_size = init_bootmem_node(NODE_DATA(nodeid),
@@ -417,7 +417,7 @@ static int __init split_nodes_interleave(u64 addr, u64 max_addr,
 		nr_nodes = MAX_NUMNODES;
 	}
 
-	size = (max_addr - addr - e820_hole_size(addr, max_addr)) / nr_nodes;
+	size = (max_addr - addr - memblock_x86_hole_size(addr, max_addr)) / nr_nodes;
 	/*
 	 * Calculate the number of big nodes that can be allocated as a result
 	 * of consolidating the remainder.
@@ -453,7 +453,7 @@ static int __init split_nodes_interleave(u64 addr, u64 max_addr,
 			 * non-reserved memory is less than the per-node size.
 			 */
 			while (end - physnodes[i].start -
-				e820_hole_size(physnodes[i].start, end) < size) {
+				memblock_x86_hole_size(physnodes[i].start, end) < size) {
 				end += FAKE_NODE_MIN_SIZE;
 				if (end > physnodes[i].end) {
 					end = physnodes[i].end;
@@ -467,7 +467,7 @@ static int __init split_nodes_interleave(u64 addr, u64 max_addr,
 			 * this one must extend to the boundary.
 			 */
 			if (end < dma32_end && dma32_end - end -
-			    e820_hole_size(end, dma32_end) < FAKE_NODE_MIN_SIZE)
+			    memblock_x86_hole_size(end, dma32_end) < FAKE_NODE_MIN_SIZE)
 				end = dma32_end;
 
 			/*
@@ -476,7 +476,7 @@ static int __init split_nodes_interleave(u64 addr, u64 max_addr,
 			 * physical node.
 			 */
 			if (physnodes[i].end - end -
-			    e820_hole_size(end, physnodes[i].end) < size)
+			    memblock_x86_hole_size(end, physnodes[i].end) < size)
 				end = physnodes[i].end;
 
 			/*
@@ -504,7 +504,7 @@ static u64 __init find_end_of_node(u64 start, u64 max_addr, u64 size)
 {
 	u64 end = start + size;
 
-	while (end - start - e820_hole_size(start, end) < size) {
+	while (end - start - memblock_x86_hole_size(start, end) < size) {
 		end += FAKE_NODE_MIN_SIZE;
 		if (end > max_addr) {
 			end = max_addr;
@@ -533,7 +533,7 @@ static int __init split_nodes_size_interleave(u64 addr, u64 max_addr, u64 size)
 	 * creates a uniform distribution of node sizes across the entire
 	 * machine (but not necessarily over physical nodes).
 	 */
-	min_size = (max_addr - addr - e820_hole_size(addr, max_addr)) /
+	min_size = (max_addr - addr - memblock_x86_hole_size(addr, max_addr)) /
 						MAX_NUMNODES;
 	min_size = max(min_size, FAKE_NODE_MIN_SIZE);
 	if ((min_size & FAKE_NODE_MIN_HASH_MASK) < min_size)
@@ -566,7 +566,7 @@ static int __init split_nodes_size_interleave(u64 addr, u64 max_addr, u64 size)
 			 * this one must extend to the boundary.
 			 */
 			if (end < dma32_end && dma32_end - end -
-			    e820_hole_size(end, dma32_end) < FAKE_NODE_MIN_SIZE)
+			    memblock_x86_hole_size(end, dma32_end) < FAKE_NODE_MIN_SIZE)
 				end = dma32_end;
 
 			/*
@@ -575,7 +575,7 @@ static int __init split_nodes_size_interleave(u64 addr, u64 max_addr, u64 size)
 			 * physical node.
 			 */
 			if (physnodes[i].end - end -
-			    e820_hole_size(end, physnodes[i].end) < size)
+			    memblock_x86_hole_size(end, physnodes[i].end) < size)
 				end = physnodes[i].end;
 
 			/*
@@ -639,7 +639,7 @@ static int __init numa_emulation(unsigned long start_pfn,
 	 */
 	remove_all_active_ranges();
 	for_each_node_mask(i, node_possible_map) {
-		e820_register_active_regions(i, nodes[i].start >> PAGE_SHIFT,
+		memblock_x86_register_active_regions(i, nodes[i].start >> PAGE_SHIFT,
 						nodes[i].end >> PAGE_SHIFT);
 		setup_node_bootmem(i, nodes[i].start, nodes[i].end);
 	}
@@ -692,7 +692,7 @@ void __init initmem_init(unsigned long start_pfn, unsigned long last_pfn,
 	node_set(0, node_possible_map);
 	for (i = 0; i < nr_cpu_ids; i++)
 		numa_set_node(i, 0);
-	e820_register_active_regions(0, start_pfn, last_pfn);
+	memblock_x86_register_active_regions(0, start_pfn, last_pfn);
 	setup_node_bootmem(0, start_pfn << PAGE_SHIFT, last_pfn << PAGE_SHIFT);
 }
 
diff --git a/arch/x86/mm/srat_32.c b/arch/x86/mm/srat_32.c
index 9324f13..a17dffd 100644
--- a/arch/x86/mm/srat_32.c
+++ b/arch/x86/mm/srat_32.c
@@ -25,6 +25,7 @@
  */
 #include <linux/mm.h>
 #include <linux/bootmem.h>
+#include <linux/memblock.h>
 #include <linux/mmzone.h>
 #include <linux/acpi.h>
 #include <linux/nodemask.h>
@@ -264,7 +265,7 @@ int __init get_memcfg_from_srat(void)
 		if (node_read_chunk(chunk->nid, chunk))
 			continue;
 
-		e820_register_active_regions(chunk->nid, chunk->start_pfn,
+		memblock_x86_register_active_regions(chunk->nid, chunk->start_pfn,
 					     min(chunk->end_pfn, max_pfn));
 	}
 	/* for out of order entries in SRAT */
diff --git a/arch/x86/mm/srat_64.c b/arch/x86/mm/srat_64.c
index f9897f7..7f44eb6 100644
--- a/arch/x86/mm/srat_64.c
+++ b/arch/x86/mm/srat_64.c
@@ -16,6 +16,7 @@
 #include <linux/module.h>
 #include <linux/topology.h>
 #include <linux/bootmem.h>
+#include <linux/memblock.h>
 #include <linux/mm.h>
 #include <asm/proto.h>
 #include <asm/numa.h>
@@ -98,15 +99,15 @@ void __init acpi_numa_slit_init(struct acpi_table_slit *slit)
 	unsigned long phys;
 
 	length = slit->header.length;
-	phys = find_e820_area(0, max_pfn_mapped<<PAGE_SHIFT, length,
+	phys = memblock_find_in_range(0, max_pfn_mapped<<PAGE_SHIFT, length,
 		 PAGE_SIZE);
 
-	if (phys == -1L)
+	if (phys == MEMBLOCK_ERROR)
 		panic(" Can not save slit!\n");
 
 	acpi_slit = __va(phys);
 	memcpy(acpi_slit, slit, length);
-	reserve_early(phys, phys + length, "ACPI SLIT");
+	memblock_x86_reserve_range(phys, phys + length, "ACPI SLIT");
 }
 
 /* Callback for Proximity Domain -> x2APIC mapping */
@@ -324,7 +325,7 @@ static int __init nodes_cover_memory(const struct bootnode *nodes)
 			pxmram = 0;
 	}
 
-	e820ram = max_pfn - (e820_hole_size(0, max_pfn<<PAGE_SHIFT)>>PAGE_SHIFT);
+	e820ram = max_pfn - (memblock_x86_hole_size(0, max_pfn<<PAGE_SHIFT)>>PAGE_SHIFT);
 	/* We seem to lose 3 pages somewhere. Allow 1M of slack. */
 	if ((long)(e820ram - pxmram) >= (1<<(20 - PAGE_SHIFT))) {
 		printk(KERN_ERR
@@ -421,7 +422,7 @@ int __init acpi_scan_nodes(unsigned long start, unsigned long end)
 	}
 
 	for_each_node_mask(i, nodes_parsed)
-		e820_register_active_regions(i, nodes[i].start >> PAGE_SHIFT,
+		memblock_x86_register_active_regions(i, nodes[i].start >> PAGE_SHIFT,
 						nodes[i].end >> PAGE_SHIFT);
 	/* for out of order entries in SRAT */
 	sort_node_map();
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 914f046..b511f19 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -44,6 +44,7 @@
 #include <linux/bug.h>
 #include <linux/module.h>
 #include <linux/gfp.h>
+#include <linux/memblock.h>
 
 #include <asm/pgtable.h>
 #include <asm/tlbflush.h>
@@ -1735,7 +1736,7 @@ __init pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd,
 	__xen_write_cr3(true, __pa(pgd));
 	xen_mc_issue(PARAVIRT_LAZY_CPU);
 
-	reserve_early(__pa(xen_start_info->pt_base),
+	memblock_x86_reserve_range(__pa(xen_start_info->pt_base),
 		      __pa(xen_start_info->pt_base +
 			   xen_start_info->nr_pt_frames * PAGE_SIZE),
 		      "XEN PAGETABLES");
@@ -1773,7 +1774,7 @@ __init pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd,
 
 	pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE, PFN_DOWN(__pa(swapper_pg_dir)));
 
-	reserve_early(__pa(xen_start_info->pt_base),
+	memblock_x86_reserve_range(__pa(xen_start_info->pt_base),
 		      __pa(xen_start_info->pt_base +
 			   xen_start_info->nr_pt_frames * PAGE_SIZE),
 		      "XEN PAGETABLES");
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index ad0047f..2ac8f29 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -8,6 +8,7 @@
 #include <linux/sched.h>
 #include <linux/mm.h>
 #include <linux/pm.h>
+#include <linux/memblock.h>
 
 #include <asm/elf.h>
 #include <asm/vdso.h>
@@ -61,7 +62,7 @@ char * __init xen_memory_setup(void)
 	 *  - xen_start_info
 	 * See comment above "struct start_info" in <xen/interface/xen.h>
 	 */
-	reserve_early(__pa(xen_start_info->mfn_list),
+	memblock_x86_reserve_range(__pa(xen_start_info->mfn_list),
 		      __pa(xen_start_info->pt_base),
 			"XEN START INFO");
 
diff --git a/mm/bootmem.c b/mm/bootmem.c
index fda01a2..13b0caa 100644
--- a/mm/bootmem.c
+++ b/mm/bootmem.c
@@ -436,7 +436,7 @@ void __init free_bootmem_node(pg_data_t *pgdat, unsigned long physaddr,
 {
 #ifdef CONFIG_NO_BOOTMEM
 	kmemleak_free_part(__va(physaddr), size);
-	free_early(physaddr, physaddr + size);
+	memblock_x86_free_range(physaddr, physaddr + size);
 #else
 	unsigned long start, end;
 
@@ -462,7 +462,7 @@ void __init free_bootmem(unsigned long addr, unsigned long size)
 {
 #ifdef CONFIG_NO_BOOTMEM
 	kmemleak_free_part(__va(addr), size);
-	free_early(addr, addr + size);
+	memblock_x86_free_range(addr, addr + size);
 #else
 	unsigned long start, end;
 

Re: kexec load failure introduced by "x86, memblock: Replace e820_/_early string with memblock_"

[Yinghai Lu]

On 09/25/2010 08:11 PM, caiqian-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org wrote:
> # /sbin/kexec -p '--command-line=ro root=/dev/mapper/VolGroup-lv_root rd_LVM_LV=VolGroup/lv_root rd_LVM_LV=VolGroup/lv_swap rd_NO_LUKS rd_NO_MD rd_NO_DM LANG=en_US.UTF-8 SYSFONT=latarcyrheb-sun16 KEYBOARDTYPE=pc KEYTABLE=us rhgb quiet console=tty0 console=ttyS0,115200 crashkernel=128M irqpoll maxcpus=1 reset_devices cgroup_disable=memory ' --initrd=/boot/initrd-2.6.36-rc3+kdump.img /boot/vmlinuz-2.6.36-rc3+
> 
> BUG: unable to handle kernel paging request at ffff8800dfffe400
> IP: [<ffffffff8113376b>] per_cpu_ptr_to_phys+0x3b/0x120
> PGD 1a26063 PUD 1fffc067 PMD 1fffd067 PTE 0
> Oops: 0000 [#1] SMP 
> last sysfs file: /sys/devices/system/cpu/cpu0/crash_notes
> CPU 3 
> Modules linked in: ipt_REJECT nf_conntrack_ipv4 nf_defrag_ipv4 iptable_filter ip_tables ip6t_REJECT nf_conntrack_ipv6 xt_state nf_conntrack ip6table_filter ip6_tables ipv6 virtio_balloon pcspkr 8139too 8139cp mii snd_intel8x0 snd_ac97_codec ac97_bus snd_seq snd_seq_device snd_pcm snd_timer snd soundcore snd_page_alloc sg i2c_piix4 i2c_core ext4 mbcache jbd2 floppy sd_mod crc_t10dif virtio_pci virtio_ring virtio pata_acpi ata_generic ata_piix dm_mod [last unloaded: scsi_wait_scan]
> 
> Pid: 5671, comm: kexec Not tainted 2.6.35+ #11 /KVM
> RIP: 0010:[<ffffffff8113376b>]  [<ffffffff8113376b>] per_cpu_ptr_to_phys+0x3b/0x120

are you kexec from 2.6.35+ to 2.6.36-rc3+?

Yinghai

Re: kexec load failure introduced by "x86, memblock: Replace e820_/_early string with memblock_"

[CAI Qian]

----- "Yinghai Lu" <yinghai@kernel.org> wrote:

> On 09/25/2010 08:11 PM, caiqian@redhat.com wrote:
> > # /sbin/kexec -p '--command-line=ro
> root=/dev/mapper/VolGroup-lv_root rd_LVM_LV=VolGroup/lv_root
> rd_LVM_LV=VolGroup/lv_swap rd_NO_LUKS rd_NO_MD rd_NO_DM
> LANG=en_US.UTF-8 SYSFONT=latarcyrheb-sun16 KEYBOARDTYPE=pc KEYTABLE=us
> rhgb quiet console=tty0 console=ttyS0,115200 crashkernel=128M irqpoll
> maxcpus=1 reset_devices cgroup_disable=memory '
> --initrd=/boot/initrd-2.6.36-rc3+kdump.img /boot/vmlinuz-2.6.36-rc3+
> > 
> > BUG: unable to handle kernel paging request at ffff8800dfffe400
> > IP: [<ffffffff8113376b>] per_cpu_ptr_to_phys+0x3b/0x120
> > PGD 1a26063 PUD 1fffc067 PMD 1fffd067 PTE 0
> > Oops: 0000 [#1] SMP 
> > last sysfs file: /sys/devices/system/cpu/cpu0/crash_notes
> > CPU 3 
> > Modules linked in: ipt_REJECT nf_conntrack_ipv4 nf_defrag_ipv4
> iptable_filter ip_tables ip6t_REJECT nf_conntrack_ipv6 xt_state
> nf_conntrack ip6table_filter ip6_tables ipv6 virtio_balloon pcspkr
> 8139too 8139cp mii snd_intel8x0 snd_ac97_codec ac97_bus snd_seq
> snd_seq_device snd_pcm snd_timer snd soundcore snd_page_alloc sg
> i2c_piix4 i2c_core ext4 mbcache jbd2 floppy sd_mod crc_t10dif
> virtio_pci virtio_ring virtio pata_acpi ata_generic ata_piix dm_mod
> [last unloaded: scsi_wait_scan]
> > 
> > Pid: 5671, comm: kexec Not tainted 2.6.35+ #11 /KVM
> > RIP: 0010:[<ffffffff8113376b>]  [<ffffffff8113376b>]
> per_cpu_ptr_to_phys+0x3b/0x120
> 
> are you kexec from 2.6.35+ to 2.6.36-rc3+?
No, both kernels were the same version. I am sorry the above logs were misleading that were copy-and-pasted from different kernel versions.
> 
> Yinghai
> 
> _______________________________________________
> kexec mailing list
> kexec@lists.infradead.org
> http://lists.infradead.org/mailman/listinfo/kexec

Re: kexec load failure introduced by "x86, memblock: Replace e820_/_early string with memblock_"

[Yinghai Lu]

On 09/25/2010 11:55 PM, CAI Qian wrote:
>>
>> are you kexec from 2.6.35+ to 2.6.36-rc3+?
> No, both kernels were the same version. I am sorry the above logs were misleading that were copy-and-pasted from different kernel versions.

can you check tip instead of next tree?

Yinghai

Re: kexec load failure introduced by "x86, memblock: Replace e820_/_early string with memblock_"

[CAI Qian]

----- "Yinghai Lu" <yinghai@kernel.org> wrote:

> On 09/25/2010 11:55 PM, CAI Qian wrote:
> >>
> >> are you kexec from 2.6.35+ to 2.6.36-rc3+?
> > No, both kernels were the same version. I am sorry the above logs
> were misleading that were copy-and-pasted from different kernel
> versions.
> 
> can you check tip instead of next tree?
I am wondering which patches there do you think would make the regression go away?
> 
> Yinghai
> 
> _______________________________________________
> kexec mailing list
> kexec@lists.infradead.org
> http://lists.infradead.org/mailman/listinfo/kexec

Re: kexec load failure introduced by "x86, memblock: Replace e820_/_early string with memblock_"

[caiqian]

----- "Yinghai Lu" <yinghai@kernel.org> wrote:

> On 09/25/2010 11:55 PM, CAI Qian wrote:
> >>
> >> are you kexec from 2.6.35+ to 2.6.36-rc3+?
> > No, both kernels were the same version. I am sorry the above logs
> were misleading that were copy-and-pasted from different kernel
> versions.
> 
> can you check tip instead of next tree?
No dice,
# /sbin/kexec -p '--command-line=ro root=/dev/mapper/VolGroup-lv_root rd_LVM_LV=VolGroup/lv_root rd_LVM_LV=VolGroup/lv_swap rd_NO_LUKS rd_NO_MD rd_NO_DM LANG=en_US.UTF-8 SYSFONT=latarcyrheb-sun16 KEYBOARDTYPE=pc KEYTABLE=us rhgb quiet console=tty0 console=ttyS0,115200 crashkernel=128M irqpoll maxcpus=1 reset_devices cgroup_disable=memory ' --initrd=/boot/initrd-2.6.36-rc5-tip+kdump.img /boot/vmlinuz-2.6.36-rc5-tip+
Could not find a free area of memory of a000 bytes...
locate_hole failed

After reverted the whole memblock commits, it was working again,
7950c407c0288b223a200c1bba8198941599ca37
fb74fb6db91abc3c1ceeb9d2c17b44866a12c63e
f88eff74aa848e58b1ea49768c0bbb874b31357f
27de794365786b4cdc3461ed4e23af2a33f40612
9dc5d569c133819c1ce069ebb1d771c62de32580
4d5cf86ce187c0d3a4cdf233ab0cc6526ccbe01f
88ba088c18457caaf8d2e5f8d36becc731a3d4f6
edbe7d23b4482e7f33179290bcff3b1feae1c5f3
6bcc8176d07f108da3b1af17fb2c0e82c80e948e
b52c17ce854125700c4e19d4427d39bf2504ff63
e82d42be24bd5d75bf6f81045636e6ca95ab55f2
301ff3e88ef9ff4bdb92f36a3e6170fce4c9dd34
72d7c3b33c980843e756681fb4867dc1efd62a76
a9ce6bc15100023b411f8117e53a016d61889800
a587d2daebcd2bc159d4348b6a7b028950a6d803
6f2a75369e7561e800d86927ecd83c970996b21f

If used crashkernel=128M, the /proc/iomem looks like this. It used a huge offset.
00000000-00000fff : reserved
00001000-0009f3ff : System RAM
0009f400-0009ffff : reserved
000f0000-000fffff : reserved
00100000-dfffafff : System RAM
  01000000-0149a733 : Kernel code
  0149a734-01afc46f : Kernel data
  01d9c000-022b18f7 : Kernel bss
dfffb000-dfffffff : reserved
f0000000-f1ffffff : 0000:00:02.0
f2000000-f2000fff : 0000:00:02.0
f2010000-f201ffff : 0000:00:02.0
f2020000-f20200ff : 0000:00:03.0
  f2020000-f20200ff : 8139cp
f2030000-f203ffff : 0000:00:03.0
fec00000-fec003ff : IOAPIC 0
fee00000-fee00fff : Local APIC
fffbc000-ffffffff : reserved
100000000-c9fffffff : System RAM
  c98000000-c9fffffff : Crash kernel

On kernels that are working, it automatically found the offset at 32M.
00000000-0000ffff : reserved
00010000-0009f3ff : System RAM
0009f400-0009ffff : reserved
000f0000-000fffff : reserved
00100000-dfffafff : System RAM
  01000000-014250bf : Kernel code
  014250c0-018aca8f : Kernel data
  01b1f000-01ff7c07 : Kernel bss
  02000000-09ffffff : Crash kernel
dfffb000-dfffffff : reserved
f0000000-f1ffffff : 0000:00:02.0
f2000000-f2000fff : 0000:00:02.0
f2010000-f201ffff : 0000:00:02.0
f2020000-f20200ff : 0000:00:03.0
  f2020000-f20200ff : 8139cp
f2030000-f203ffff : 0000:00:03.0
fec00000-fec003ff : IOAPIC 0
fee00000-fee00fff : Local APIC
fffbc000-ffffffff : reserved
100000000-c9fffffff : System RAM

If specified a fixed offset like crashkernel=128M@32M, it failed reservation.
initial memory mapped : 0 - 20000000
init_memory_mapping: 0000000000000000-00000000dfffb000
 0000000000 - 00dfe00000 page 2M
 00dfe00000 - 00dfffb000 page 4k
kernel direct mapping tables up to dfffb000 @ 1fffa000-20000000
init_memory_mapping: 0000000100000000-0000000ca0000000
 0100000000 - 0ca0000000 page 2M
kernel direct mapping tables up to ca0000000 @ dffc7000-dfffb000
RAMDISK: 37599000 - 37ff0000
crashkernel reservation failed - memory is in use.

After reverted those commits, it looks like this,
init_memory_mapping: 0000000000000000-00000000dfffb000
 0000000000 - 00dfe00000 page 2M
 00dfe00000 - 00dfffb000 page 4k
kernel direct mapping tables up to dfffb000 @ 16000-1c000
init_memory_mapping: 0000000100000000-0000000ca0000000
 0100000000 - 0ca0000000 page 2M
kernel direct mapping tables up to ca0000000 @ 1a000-4e000
RAMDISK: 375c9000 - 37ff0000
Reserving 128MB of memory at 32MB for crashkernel (System RAM: 51712MB)

I can't tell where the memory at 32MB was used, but after reverted those commits I can see those early reservations information,
Subtract (76 early reservations)
  #1 [0001000000 - 0001ff7c08]   TEXT DATA BSS
  #2 [00375c9000 - 0037ff0000]         RAMDISK
  #3 [0001ff8000 - 0001ff8079]             BRK
  #4 [000009f400 - 00000f7fb0]   BIOS reserved
  #5 [00000f7fb0 - 00000f7fc0]    MP-table mpf
  #6 [00000f822c - 0000100000]   BIOS reserved
  #7 [00000f7fc0 - 00000f822c]    MP-table mpc
  #8 [0000010000 - 0000012000]      TRAMPOLINE
  #9 [0000012000 - 0000016000]     ACPI WAKEUP
  #10 [0000016000 - 000001a000]         PGTABLE
  #11 [000001a000 - 0000049000]         PGTABLE
  #12 [0002000000 - 000a000000]    CRASH KERNEL

But after those commits, those information was gone.

Re: kexec load failure introduced by "x86, memblock: Replace e820_/_early string with memblock_"

[Yinghai Lu]

On 09/26/2010 07:47 AM, caiqian-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org wrote:
> 
> ----- "Yinghai Lu" <yinghai-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org> wrote:
> 
>> On 09/25/2010 11:55 PM, CAI Qian wrote:
>>>>
>>>> are you kexec from 2.6.35+ to 2.6.36-rc3+?
>>> No, both kernels were the same version. I am sorry the above logs
>> were misleading that were copy-and-pasted from different kernel
>> versions.
>>
>> can you check tip instead of next tree?
> No dice,
> # /sbin/kexec -p '--command-line=ro root=/dev/mapper/VolGroup-lv_root rd_LVM_LV=VolGroup/lv_root rd_LVM_LV=VolGroup/lv_swap rd_NO_LUKS rd_NO_MD rd_NO_DM LANG=en_US.UTF-8 SYSFONT=latarcyrheb-sun16 KEYBOARDTYPE=pc KEYTABLE=us rhgb quiet console=tty0 console=ttyS0,115200 crashkernel=128M irqpoll maxcpus=1 reset_devices cgroup_disable=memory ' --initrd=/boot/initrd-2.6.36-rc5-tip+kdump.img /boot/vmlinuz-2.6.36-rc5-tip+
> Could not find a free area of memory of a000 bytes...
> locate_hole failed

looks like you need to update your kexec-tools package.

please run following scripts in first kernel.

cd /sys/firmware/memmap
for dir in * ; do
  start=$(cat $dir/start)
  end=$(cat $dir/end)
  type=$(cat $dir/type)
  printf "%016x-%016x (%s)\n" $start $[ $end +1] "$type"
done

also enable kexec debug to see what memmap kexec parse.

> 
> After reverted the whole memblock commits, it was working again,
> 7950c407c0288b223a200c1bba8198941599ca37
> fb74fb6db91abc3c1ceeb9d2c17b44866a12c63e
> f88eff74aa848e58b1ea49768c0bbb874b31357f
> 27de794365786b4cdc3461ed4e23af2a33f40612
> 9dc5d569c133819c1ce069ebb1d771c62de32580
> 4d5cf86ce187c0d3a4cdf233ab0cc6526ccbe01f
> 88ba088c18457caaf8d2e5f8d36becc731a3d4f6
> edbe7d23b4482e7f33179290bcff3b1feae1c5f3
> 6bcc8176d07f108da3b1af17fb2c0e82c80e948e
> b52c17ce854125700c4e19d4427d39bf2504ff63
> e82d42be24bd5d75bf6f81045636e6ca95ab55f2
> 301ff3e88ef9ff4bdb92f36a3e6170fce4c9dd34
> 72d7c3b33c980843e756681fb4867dc1efd62a76
> a9ce6bc15100023b411f8117e53a016d61889800
> a587d2daebcd2bc159d4348b6a7b028950a6d803
> 6f2a75369e7561e800d86927ecd83c970996b21f
> 
> If used crashkernel=128M, the /proc/iomem looks like this. It used a huge offset.
> 00000000-00000fff : reserved
> 00001000-0009f3ff : System RAM
> 0009f400-0009ffff : reserved
> 000f0000-000fffff : reserved
> 00100000-dfffafff : System RAM
>   01000000-0149a733 : Kernel code
>   0149a734-01afc46f : Kernel data
>   01d9c000-022b18f7 : Kernel bss
> dfffb000-dfffffff : reserved
> f0000000-f1ffffff : 0000:00:02.0
> f2000000-f2000fff : 0000:00:02.0
> f2010000-f201ffff : 0000:00:02.0
> f2020000-f20200ff : 0000:00:03.0
>   f2020000-f20200ff : 8139cp
> f2030000-f203ffff : 0000:00:03.0
> fec00000-fec003ff : IOAPIC 0
> fee00000-fee00fff : Local APIC
> fffbc000-ffffffff : reserved
> 100000000-c9fffffff : System RAM
>   c98000000-c9fffffff : Crash kernel
> 
> On kernels that are working, it automatically found the offset at 32M.
> 00000000-0000ffff : reserved
> 00010000-0009f3ff : System RAM
> 0009f400-0009ffff : reserved
> 000f0000-000fffff : reserved
> 00100000-dfffafff : System RAM
>   01000000-014250bf : Kernel code
>   014250c0-018aca8f : Kernel data
>   01b1f000-01ff7c07 : Kernel bss
>   02000000-09ffffff : Crash kernel
> dfffb000-dfffffff : reserved
> f0000000-f1ffffff : 0000:00:02.0
> f2000000-f2000fff : 0000:00:02.0
> f2010000-f201ffff : 0000:00:02.0
> f2020000-f20200ff : 0000:00:03.0
>   f2020000-f20200ff : 8139cp
> f2030000-f203ffff : 0000:00:03.0
> fec00000-fec003ff : IOAPIC 0
> fee00000-fee00fff : Local APIC
> fffbc000-ffffffff : reserved
> 100000000-c9fffffff : System RAM
> 
> If specified a fixed offset like crashkernel=128M@32M, it failed reservation.
> initial memory mapped : 0 - 20000000
> init_memory_mapping: 0000000000000000-00000000dfffb000
>  0000000000 - 00dfe00000 page 2M
>  00dfe00000 - 00dfffb000 page 4k
> kernel direct mapping tables up to dfffb000 @ 1fffa000-20000000
> init_memory_mapping: 0000000100000000-0000000ca0000000
>  0100000000 - 0ca0000000 page 2M
> kernel direct mapping tables up to ca0000000 @ dffc7000-dfffb000
> RAMDISK: 37599000 - 37ff0000
> crashkernel reservation failed - memory is in use.
> 
> After reverted those commits, it looks like this,
> init_memory_mapping: 0000000000000000-00000000dfffb000
>  0000000000 - 00dfe00000 page 2M
>  00dfe00000 - 00dfffb000 page 4k
> kernel direct mapping tables up to dfffb000 @ 16000-1c000
> init_memory_mapping: 0000000100000000-0000000ca0000000
>  0100000000 - 0ca0000000 page 2M
> kernel direct mapping tables up to ca0000000 @ 1a000-4e000
> RAMDISK: 375c9000 - 37ff0000
> Reserving 128MB of memory at 32MB for crashkernel (System RAM: 51712MB)

yes, default memblock find_range is top_down.

old early_res is from bottom_up.

during the convecting, we do have one x86 find_range from bottom_up, but later
it seems top_down was working on all test cases. ( 32bit etc)

Subject: [PATCH] x86, memblock: Add x86 version of memblock_find_in_range()

Generic version is going from high to low, and it seems it can not find
right area compact enough.

the x86 version will go from goal to limit and just like the way We used
for early_res

use ARCH_FIND_MEMBLOCK_AREA to select from them.

Signed-off-by: Yinghai Lu <yinghai-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org>
---
 arch/x86/Kconfig       |    8 +++++++
 arch/x86/mm/memblock.c |   54 +++++++++++++++++++++++++++++++++++++++++++++++++
 mm/memblock.c          |    2 -
 3 files changed, 63 insertions(+), 1 deletion(-)

Index: linux-2.6/arch/x86/mm/memblock.c
===================================================================
--- linux-2.6.orig/arch/x86/mm/memblock.c
+++ linux-2.6/arch/x86/mm/memblock.c
@@ -352,3 +352,57 @@ u64 __init memblock_x86_hole_size(u64 st
 
 	return end - start - ((u64)ram << PAGE_SHIFT);
 }
+
+#ifdef CONFIG_ARCH_MEMBLOCK_FIND_AREA
+/* Check for already reserved areas */
+static inline bool __init check_with_memblock_reserved(u64 *addrp, u64 size, u64 align)
+{
+	u64 addr = *addrp;
+	bool changed = false;
+	struct memblock_region *r;
+again:
+	for_each_memblock(reserved, r) {
+		if ((addr + size) > r->base && addr < (r->base + r->size)) {
+			addr = round_up(r->base + r->size, align);
+			changed = true;
+			goto again;
+		}
+	}
+
+	if (changed)
+		*addrp = addr;
+
+	return changed;
+}
+
+/*
+ * Find a free area with specified alignment in a specific range.
+ */
+u64 __init memblock_find_in_range(u64 start, u64 end, u64 size, u64 align)
+{
+	struct memblock_region *r;
+
+	for_each_memblock(memory, r) {
+		u64 ei_start = r->base;
+		u64 ei_last = ei_start + r->size;
+		u64 addr, last;
+
+		addr = round_up(ei_start, align);
+		if (addr < start)
+			addr = round_up(start, align);
+		if (addr >= ei_last)
+			continue;
+		while (check_with_memblock_reserved(&addr, size, align) && addr+size <= ei_last)
+			;
+		last = addr + size;
+		if (last > ei_last)
+			continue;
+		if (last > end)
+			continue;
+
+		return addr;
+	}
+
+	return MEMBLOCK_ERROR;
+}
+#endif
Index: linux-2.6/arch/x86/Kconfig
===================================================================
--- linux-2.6.orig/arch/x86/Kconfig
+++ linux-2.6/arch/x86/Kconfig
@@ -569,6 +569,14 @@ config PARAVIRT_DEBUG
 	  Enable to debug paravirt_ops internals.  Specifically, BUG if
 	  a paravirt_op is missing when it is called.
 
+config ARCH_MEMBLOCK_FIND_AREA
+	default y
+	bool "Use x86 own memblock_find_in_range()"
+	---help---
+	  Use memblock_find_in_range() version instead of generic version, it get free
+	  area up from low.
+	  Generic one try to get free area down from limit.
+
 config NO_BOOTMEM
 	def_bool y
 
Index: linux-2.6/mm/memblock.c
===================================================================
--- linux-2.6.orig/mm/memblock.c
+++ linux-2.6/mm/memblock.c
@@ -165,7 +165,7 @@ static phys_addr_t __init_memblock membl
 /*
  * Find a free area with specified alignment in a specific range.
  */
-u64 __init_memblock memblock_find_in_range(u64 start, u64 end, u64 size, u64 align)
+u64 __init_memblock __weak memblock_find_in_range(u64 start, u64 end, u64 size, u64 align)
 {
 	return memblock_find_base(size, align, start, end);
 }


> 
> I can't tell where the memory at 32MB was used, but after reverted those commits I can see those early reservations information,
> Subtract (76 early reservations)
>   #1 [0001000000 - 0001ff7c08]   TEXT DATA BSS
>   #2 [00375c9000 - 0037ff0000]         RAMDISK
>   #3 [0001ff8000 - 0001ff8079]             BRK
>   #4 [000009f400 - 00000f7fb0]   BIOS reserved
>   #5 [00000f7fb0 - 00000f7fc0]    MP-table mpf
>   #6 [00000f822c - 0000100000]   BIOS reserved
>   #7 [00000f7fc0 - 00000f822c]    MP-table mpc
>   #8 [0000010000 - 0000012000]      TRAMPOLINE
>   #9 [0000012000 - 0000016000]     ACPI WAKEUP
>   #10 [0000016000 - 000001a000]         PGTABLE
>   #11 [000001a000 - 0000049000]         PGTABLE
>   #12 [0002000000 - 000a000000]    CRASH KERNEL
> 
> But after those commits, those information was gone.

memblock could merge reserved area, so can not keep tags with it.

I have local patchset that could print those name tags...
please check

	git://git.kernel.org/pub/scm/linux/kernel/git/yinghai/linux-2.6-yinghai.git memblock

Yinghai

Re: kexec load failure introduced by "x86, memblock: Replace e820_/_early string with memblock_"

[caiqian]

----- "Yinghai Lu" <yinghai@kernel.org> wrote:

> On 09/26/2010 07:47 AM, caiqian@redhat.com wrote:
> > 
> > ----- "Yinghai Lu" <yinghai@kernel.org> wrote:
> > 
> >> On 09/25/2010 11:55 PM, CAI Qian wrote:
> >>>>
> >>>> are you kexec from 2.6.35+ to 2.6.36-rc3+?
> >>> No, both kernels were the same version. I am sorry the above logs
> >> were misleading that were copy-and-pasted from different kernel
> >> versions.
> >>
> >> can you check tip instead of next tree?
> > No dice,
> > # /sbin/kexec -p '--command-line=ro
> root=/dev/mapper/VolGroup-lv_root rd_LVM_LV=VolGroup/lv_root
> rd_LVM_LV=VolGroup/lv_swap rd_NO_LUKS rd_NO_MD rd_NO_DM
> LANG=en_US.UTF-8 SYSFONT=latarcyrheb-sun16 KEYBOARDTYPE=pc KEYTABLE=us
> rhgb quiet console=tty0 console=ttyS0,115200 crashkernel=128M irqpoll
> maxcpus=1 reset_devices cgroup_disable=memory '
> --initrd=/boot/initrd-2.6.36-rc5-tip+kdump.img
> /boot/vmlinuz-2.6.36-rc5-tip+
> > Could not find a free area of memory of a000 bytes...
> > locate_hole failed
> 
> looks like you need to update your kexec-tools package.
Same results using the latest kexec-tools git version.
> 
> please run following scripts in first kernel.
> 
> cd /sys/firmware/memmap
> for dir in * ; do
>   start=$(cat $dir/start)
>   end=$(cat $dir/end)
>   type=$(cat $dir/type)
>   printf "%016x-%016x (%s)\n" $start $[ $end +1] "$type"
> done
0000000000000000-000000000009f400 (System RAM)
000000000009f400-00000000000a0000 (reserved)
00000000000f0000-0000000000100000 (reserved)
0000000000100000-00000000dfffb000 (System RAM)
00000000dfffb000-00000000e0000000 (reserved)
00000000fffbc000-0000000100000000 (reserved)
0000000100000000-0000000ca0000000 (System RAM)
> 
> also enable kexec debug to see what memmap kexec parse.
-d did not help here.
# /sbin/kexec -p -d '--command-line=ro root=/dev/mapper/VolGroup-lv_root rd_LVM_LV=VolGroup/lv_root rd_LVM_LV=VolGroup/lv_swap rd_NO_LUKS rd_NO_MD rd_NO_DM LANG=en_US.UTF-8 SYSFONT=latarcyrheb-sun16 KEYBOARDTYPE=pc KEYTABLE=us rhgb quiet console=tty0 console=ttyS0,115200 crashkernel=128M irqpoll maxcpus=1 reset_devices cgroup_disable=memory ' --initrd=/boot/initrd-2.6.36-rc5-tip+kdump.img /boot/vmlinuz-2.6.36-rc5-tip+
Could not find a free area of memory of a000 bytes...
locate_hole failed
> 
> > 
> > After reverted the whole memblock commits, it was working again,
> > 7950c407c0288b223a200c1bba8198941599ca37
> > fb74fb6db91abc3c1ceeb9d2c17b44866a12c63e
> > f88eff74aa848e58b1ea49768c0bbb874b31357f
> > 27de794365786b4cdc3461ed4e23af2a33f40612
> > 9dc5d569c133819c1ce069ebb1d771c62de32580
> > 4d5cf86ce187c0d3a4cdf233ab0cc6526ccbe01f
> > 88ba088c18457caaf8d2e5f8d36becc731a3d4f6
> > edbe7d23b4482e7f33179290bcff3b1feae1c5f3
> > 6bcc8176d07f108da3b1af17fb2c0e82c80e948e
> > b52c17ce854125700c4e19d4427d39bf2504ff63
> > e82d42be24bd5d75bf6f81045636e6ca95ab55f2
> > 301ff3e88ef9ff4bdb92f36a3e6170fce4c9dd34
> > 72d7c3b33c980843e756681fb4867dc1efd62a76
> > a9ce6bc15100023b411f8117e53a016d61889800
> > a587d2daebcd2bc159d4348b6a7b028950a6d803
> > 6f2a75369e7561e800d86927ecd83c970996b21f
> > 
> > If used crashkernel=128M, the /proc/iomem looks like this. It used a
> huge offset.
> > 00000000-00000fff : reserved
> > 00001000-0009f3ff : System RAM
> > 0009f400-0009ffff : reserved
> > 000f0000-000fffff : reserved
> > 00100000-dfffafff : System RAM
> >   01000000-0149a733 : Kernel code
> >   0149a734-01afc46f : Kernel data
> >   01d9c000-022b18f7 : Kernel bss
> > dfffb000-dfffffff : reserved
> > f0000000-f1ffffff : 0000:00:02.0
> > f2000000-f2000fff : 0000:00:02.0
> > f2010000-f201ffff : 0000:00:02.0
> > f2020000-f20200ff : 0000:00:03.0
> >   f2020000-f20200ff : 8139cp
> > f2030000-f203ffff : 0000:00:03.0
> > fec00000-fec003ff : IOAPIC 0
> > fee00000-fee00fff : Local APIC
> > fffbc000-ffffffff : reserved
> > 100000000-c9fffffff : System RAM
> >   c98000000-c9fffffff : Crash kernel
> > 
> > On kernels that are working, it automatically found the offset at
> 32M.
> > 00000000-0000ffff : reserved
> > 00010000-0009f3ff : System RAM
> > 0009f400-0009ffff : reserved
> > 000f0000-000fffff : reserved
> > 00100000-dfffafff : System RAM
> >   01000000-014250bf : Kernel code
> >   014250c0-018aca8f : Kernel data
> >   01b1f000-01ff7c07 : Kernel bss
> >   02000000-09ffffff : Crash kernel
> > dfffb000-dfffffff : reserved
> > f0000000-f1ffffff : 0000:00:02.0
> > f2000000-f2000fff : 0000:00:02.0
> > f2010000-f201ffff : 0000:00:02.0
> > f2020000-f20200ff : 0000:00:03.0
> >   f2020000-f20200ff : 8139cp
> > f2030000-f203ffff : 0000:00:03.0
> > fec00000-fec003ff : IOAPIC 0
> > fee00000-fee00fff : Local APIC
> > fffbc000-ffffffff : reserved
> > 100000000-c9fffffff : System RAM
> > 
> > If specified a fixed offset like crashkernel=128M@32M, it failed
> reservation.
> > initial memory mapped : 0 - 20000000
> > init_memory_mapping: 0000000000000000-00000000dfffb000
> >  0000000000 - 00dfe00000 page 2M
> >  00dfe00000 - 00dfffb000 page 4k
> > kernel direct mapping tables up to dfffb000 @ 1fffa000-20000000
> > init_memory_mapping: 0000000100000000-0000000ca0000000
> >  0100000000 - 0ca0000000 page 2M
> > kernel direct mapping tables up to ca0000000 @ dffc7000-dfffb000
> > RAMDISK: 37599000 - 37ff0000
> > crashkernel reservation failed - memory is in use.
> > 
> > After reverted those commits, it looks like this,
> > init_memory_mapping: 0000000000000000-00000000dfffb000
> >  0000000000 - 00dfe00000 page 2M
> >  00dfe00000 - 00dfffb000 page 4k
> > kernel direct mapping tables up to dfffb000 @ 16000-1c000
> > init_memory_mapping: 0000000100000000-0000000ca0000000
> >  0100000000 - 0ca0000000 page 2M
> > kernel direct mapping tables up to ca0000000 @ 1a000-4e000
> > RAMDISK: 375c9000 - 37ff0000
> > Reserving 128MB of memory at 32MB for crashkernel (System RAM:
> 51712MB)
> 
> yes, default memblock find_range is top_down.
> 
> old early_res is from bottom_up.
> 
> during the convecting, we do have one x86 find_range from bottom_up,
> but later
> it seems top_down was working on all test cases. ( 32bit etc)
> 
> Subject: [PATCH] x86, memblock: Add x86 version of
> memblock_find_in_range()
Yes, this patch did help.
Reserving 128MB of memory at 32MB for crashkernel (System RAM: 51712MB)
> 
> Generic version is going from high to low, and it seems it can not
> find
> right area compact enough.
> 
> the x86 version will go from goal to limit and just like the way We
> used
> for early_res
> 
> use ARCH_FIND_MEMBLOCK_AREA to select from them.
> 
> Signed-off-by: Yinghai Lu <yinghai@kernel.org>
> ---
>  arch/x86/Kconfig       |    8 +++++++
>  arch/x86/mm/memblock.c |   54
> +++++++++++++++++++++++++++++++++++++++++++++++++
>  mm/memblock.c          |    2 -
>  3 files changed, 63 insertions(+), 1 deletion(-)
> 
> Index: linux-2.6/arch/x86/mm/memblock.c
> ===================================================================
> --- linux-2.6.orig/arch/x86/mm/memblock.c
> +++ linux-2.6/arch/x86/mm/memblock.c
> @@ -352,3 +352,57 @@ u64 __init memblock_x86_hole_size(u64 st
>  
>  	return end - start - ((u64)ram << PAGE_SHIFT);
>  }
> +
> +#ifdef CONFIG_ARCH_MEMBLOCK_FIND_AREA
> +/* Check for already reserved areas */
> +static inline bool __init check_with_memblock_reserved(u64 *addrp,
> u64 size, u64 align)
> +{
> +	u64 addr = *addrp;
> +	bool changed = false;
> +	struct memblock_region *r;
> +again:
> +	for_each_memblock(reserved, r) {
> +		if ((addr + size) > r->base && addr < (r->base + r->size)) {
> +			addr = round_up(r->base + r->size, align);
> +			changed = true;
> +			goto again;
> +		}
> +	}
> +
> +	if (changed)
> +		*addrp = addr;
> +
> +	return changed;
> +}
> +
> +/*
> + * Find a free area with specified alignment in a specific range.
> + */
> +u64 __init memblock_find_in_range(u64 start, u64 end, u64 size, u64
> align)
> +{
> +	struct memblock_region *r;
> +
> +	for_each_memblock(memory, r) {
> +		u64 ei_start = r->base;
> +		u64 ei_last = ei_start + r->size;
> +		u64 addr, last;
> +
> +		addr = round_up(ei_start, align);
> +		if (addr < start)
> +			addr = round_up(start, align);
> +		if (addr >= ei_last)
> +			continue;
> +		while (check_with_memblock_reserved(&addr, size, align) &&
> addr+size <= ei_last)
> +			;
> +		last = addr + size;
> +		if (last > ei_last)
> +			continue;
> +		if (last > end)
> +			continue;
> +
> +		return addr;
> +	}
> +
> +	return MEMBLOCK_ERROR;
> +}
> +#endif
> Index: linux-2.6/arch/x86/Kconfig
> ===================================================================
> --- linux-2.6.orig/arch/x86/Kconfig
> +++ linux-2.6/arch/x86/Kconfig
> @@ -569,6 +569,14 @@ config PARAVIRT_DEBUG
>  	  Enable to debug paravirt_ops internals.  Specifically, BUG if
>  	  a paravirt_op is missing when it is called.
>  
> +config ARCH_MEMBLOCK_FIND_AREA
> +	default y
> +	bool "Use x86 own memblock_find_in_range()"
> +	---help---
> +	  Use memblock_find_in_range() version instead of generic version,
> it get free
> +	  area up from low.
> +	  Generic one try to get free area down from limit.
> +
>  config NO_BOOTMEM
>  	def_bool y
>  
> Index: linux-2.6/mm/memblock.c
> ===================================================================
> --- linux-2.6.orig/mm/memblock.c
> +++ linux-2.6/mm/memblock.c
> @@ -165,7 +165,7 @@ static phys_addr_t __init_memblock membl
>  /*
>   * Find a free area with specified alignment in a specific range.
>   */
> -u64 __init_memblock memblock_find_in_range(u64 start, u64 end, u64
> size, u64 align)
> +u64 __init_memblock __weak memblock_find_in_range(u64 start, u64 end,
> u64 size, u64 align)
>  {
>  	return memblock_find_base(size, align, start, end);
>  }
> 
> 
> > 
> > I can't tell where the memory at 32MB was used, but after reverted
> those commits I can see those early reservations information,
> > Subtract (76 early reservations)
> >   #1 [0001000000 - 0001ff7c08]   TEXT DATA BSS
> >   #2 [00375c9000 - 0037ff0000]         RAMDISK
> >   #3 [0001ff8000 - 0001ff8079]             BRK
> >   #4 [000009f400 - 00000f7fb0]   BIOS reserved
> >   #5 [00000f7fb0 - 00000f7fc0]    MP-table mpf
> >   #6 [00000f822c - 0000100000]   BIOS reserved
> >   #7 [00000f7fc0 - 00000f822c]    MP-table mpc
> >   #8 [0000010000 - 0000012000]      TRAMPOLINE
> >   #9 [0000012000 - 0000016000]     ACPI WAKEUP
> >   #10 [0000016000 - 000001a000]         PGTABLE
> >   #11 [000001a000 - 0000049000]         PGTABLE
> >   #12 [0002000000 - 000a000000]    CRASH KERNEL
> > 
> > But after those commits, those information was gone.
> 
> memblock could merge reserved area, so can not keep tags with it.
> 
> I have local patchset that could print those name tags...
> please check
Looks like so.
> 
> 
> git://git.kernel.org/pub/scm/linux/kernel/git/yinghai/linux-2.6-yinghai.git
> memblock
> 
> Yinghai
> 
> _______________________________________________
> kexec mailing list
> kexec@lists.infradead.org
> http://lists.infradead.org/mailman/listinfo/kexec

Re: kexec load failure introduced by "x86, memblock: Replace e820_/_early string with memblock_"

[Yinghai Lu]

Please check this one on top of tip or next.

Thanks

Yinghai

[PATCH] x86, memblock: Fix crashkernel allocation

Cai Qian found that crashkernel is broken with x86 memblock changes
1. crashkernel=128M@32M always reported that range is used, even first kernel is small
   no one use that range
2. always get following report when using "kexec -p"
	Could not find a free area of memory of a000 bytes...
	locate_hole failed

The root cause is that generic memblock_find_in_range() will try to get range from top_down.
But crashkernel do need from low and specified range.

Let's limit the target range with rash_base + crash_size to make sure that
We get range from bottom.

Reported-and-Bisected-by: CAI Qian <caiqian-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
Signed-off-by: Yinghai Lu <yinghai-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org>

---
 arch/x86/kernel/setup.c |   19 ++++++++++++++-----
 1 file changed, 14 insertions(+), 5 deletions(-)

Index: linux-2.6/arch/x86/kernel/setup.c
===================================================================
--- linux-2.6.orig/arch/x86/kernel/setup.c
+++ linux-2.6/arch/x86/kernel/setup.c
@@ -516,19 +516,28 @@ static void __init reserve_crashkernel(v
 
 	/* 0 means: find the address automatically */
 	if (crash_base <= 0) {
+		unsigned long long start = 0;
 		const unsigned long long alignment = 16<<20;	/* 16M */
 
-		crash_base = memblock_find_in_range(alignment, ULONG_MAX, crash_size,
-				 alignment);
-		if (crash_base == MEMBLOCK_ERROR) {
+		crash_base = alignment;
+		while (crash_base < 0xffffffff) {
+			start = memblock_find_in_range(crash_base,
+				crash_base + crash_size, crash_size, alignment);
+
+			if (start == crash_base)
+				break;
+
+			crash_base += alignment;
+		}
+		if (start != crash_base) {
 			pr_info("crashkernel reservation failed - No suitable area found.\n");
 			return;
 		}
 	} else {
 		unsigned long long start;
 
-		start = memblock_find_in_range(crash_base, ULONG_MAX, crash_size,
-				 1<<20);
+		start = memblock_find_in_range(crash_base,
+				 crash_base + crash_size, crash_size, 1<<20);
 		if (start != crash_base) {
 			pr_info("crashkernel reservation failed - memory is in use.\n");
 			return;