From 9198715763e8d0fd7fb7578c07916a5313e28b9d Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Wed, 30 Jan 2008 13:34:12 +0100 Subject: x86: fix overlap between pagetable with bss section one early crash on one 8 node 256g machine: Command line: console=uart8250,io,0x3f8,115200n8 initrd=kernel.org/mydisk11_x86_64.gz rw root=/dev/ram0 debug initcall_debug apic=debug acpi.debug_level=0x0000000f pci=routeirq ip=dhcp load_ramdisk=1 ramdisk_size=131072 BOOT_IMAGE=kernel.org/bzImage_2.6.25_k8.1 BIOS-provided physical RAM map: BIOS-e820: 0000000000000000 - 000000000009bc00 (usable) BIOS-e820: 000000000009bc00 - 00000000000a0000 (reserved) BIOS-e820: 00000000000e6000 - 0000000000100000 (reserved) BIOS-e820: 0000000000100000 - 00000000dffe0000 (usable) BIOS-e820: 00000000dffe0000 - 00000000dffee000 (ACPI data) BIOS-e820: 00000000dffee000 - 00000000dffff050 (ACPI NVS) BIOS-e820: 00000000dffff050 - 00000000e0000000 (reserved) BIOS-e820: 00000000fec00000 - 00000000fec01000 (reserved) BIOS-e820: 00000000fee00000 - 00000000fee01000 (reserved) BIOS-e820: 00000000ff700000 - 0000000100000000 (reserved) BIOS-e820: 0000000100000000 - 0000004020000000 (usable) Early serial console at I/O port 0x3f8 (options '115200n8') console [uart0] enabled end_pfn_map = 67239936 Kernel panic - not syncing: Duplicated early reservation d40000-e42000 Pid: 0, comm: swapper Not tainted 2.6.24-smp-g5a514e21-dirty #3 Call Trace: [] lapic_get_maxlvt+0x0/0x10 [] clear_local_APIC+0x5/0xcf [] disable_local_APIC+0x5/0x17 [] smp_send_stop+0x46/0x4c [] panic+0x94/0x13e [] sctp_eps_proc_init+0x12/0x34 [] reserve_early+0x30/0x6c [] init_memory_mapping+0x2cd/0x2dc [] setup_arch+0x21f/0x44e [] start_kernel+0x6f/0x2c7 [] _sinittext+0x1cc/0x1d3 it turns out there is overlap between pgtable and bss... in System.map we have ffffffff80d40420 b rsi_table ffffffff80d40620 B krb5_seq_lock ffffffff80d40628 b i.20437 ffffffff80d40630 b xprt_rdma_inline_write_padding ffffffff80d40638 b sunrpc_table_header ffffffff80d40640 b zero ffffffff80d40644 b min_memreg ffffffff80d40648 b rpcrdma_tk_lock_g ffffffff80d40650 B sctp_assocs_id_lock ffffffff80d40658 B proc_net_sctp ffffffff80d40660 B sctp_assocs_id ffffffff80d40680 B sysctl_sctp_mem ffffffff80d40690 B sysctl_sctp_rmem ffffffff80d406a0 B sysctl_sctp_wmem ffffffff80d406b0 b sctp_ctl_socket ffffffff80d406b8 b sctp_pf_inet6_specific ffffffff80d406c0 b sctp_pf_inet_specific ffffffff80d406c8 b sctp_af_v4_specific ffffffff80d406d0 b sctp_af_v6_specific ffffffff80d406d8 b sctp_rand.33270 ffffffff80d406dc b sctp_memory_pressure ffffffff80d406e0 b sctp_sockets_allocated ffffffff80d406e4 b sctp_memory_allocated ffffffff80d406e8 b sctp_sysctl_header ffffffff80d406f0 b zero ffffffff80d406f4 A __bss_stop ffffffff80d406f4 A _end need to round up table_start to PAGE_SIZE. also make the panic more informative. Signed-off-by: Yinghai Lu Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- arch/x86/kernel/e820_64.c | 4 ++-- arch/x86/mm/init_64.c | 7 +++++++ 2 files changed, 9 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/e820_64.c b/arch/x86/kernel/e820_64.c index f8b7bebb434..c617174e896 100644 --- a/arch/x86/kernel/e820_64.c +++ b/arch/x86/kernel/e820_64.c @@ -70,8 +70,8 @@ void __init reserve_early(unsigned long start, unsigned long end) for (i = 0; i < MAX_EARLY_RES && early_res[i].end; i++) { r = &early_res[i]; if (end > r->start && start < r->end) - panic("Duplicated early reservation %lx-%lx\n", - start, end); + panic("Overlapping early reservations %lx-%lx to %lx-%lx\n", + start, end, r->start, r->end); } if (i >= MAX_EARLY_RES) panic("Too many early reservations"); diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index a9527264459..cc50a13ce8d 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -358,6 +358,13 @@ static void __init find_early_table_space(unsigned long end) if (table_start == -1UL) panic("Cannot find space for the kernel page tables"); + /* + * When you have a lot of RAM like 256GB, early_table will not fit + * into 0x8000 range, find_e820_area() will find area after kernel + * bss but the table_start is not page aligned, so need to round it + * up to avoid overlap with bss: + */ + table_start = round_up(table_start, PAGE_SIZE); table_start >>= PAGE_SHIFT; table_end = table_start; -- cgit v1.2.3