[PATCH] x86_64: fix overlap between pagetable with bss section v2
[PATCH] x86_64: fix overlap between pagetable with bss section v2
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=0x000f 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: - 0009bc00 (usable)
BIOS-e820: 0009bc00 - 000a (reserved)
BIOS-e820: 000e6000 - 0010 (reserved)
BIOS-e820: 0010 - dffe (usable)
BIOS-e820: dffe - dffee000 (ACPI data)
BIOS-e820: dffee000 - d050 (ACPI NVS)
BIOS-e820: d050 - e000 (reserved)
BIOS-e820: fec0 - fec01000 (reserved)
BIOS-e820: fee0 - fee01000 (reserved)
BIOS-e820: ff70 - 0001 (reserved)
BIOS-e820: 0001 - 00402000 (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 d4-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
80d40420 b rsi_table
80d40620 B krb5_seq_lock
80d40628 b i.20437
80d40630 b xprt_rdma_inline_write_padding
80d40638 b sunrpc_table_header
80d40640 b zero
80d40644 b min_memreg
80d40648 b rpcrdma_tk_lock_g
80d40650 B sctp_assocs_id_lock
80d40658 B proc_net_sctp
80d40660 B sctp_assocs_id
80d40680 B sysctl_sctp_mem
80d40690 B sysctl_sctp_rmem
80d406a0 B sysctl_sctp_wmem
80d406b0 b sctp_ctl_socket
80d406b8 b sctp_pf_inet6_specific
80d406c0 b sctp_pf_inet_specific
80d406c8 b sctp_af_v4_specific
80d406d0 b sctp_af_v6_specific
80d406d8 b sctp_rand.33270
80d406dc b sctp_memory_pressure
80d406e0 b sctp_sockets_allocated
80d406e4 b sctp_memory_allocated
80d406e8 b sctp_sysctl_header
80d406f0 b zero
80d406f4 A __bss_stop
80d406f4 A _end
need to round up table_start to PAGE_SIZE
also make the panic more informative.
Signed-off-by: Yinghai Lu <[EMAIL PROTECTED]>
Index: linux-2.6/arch/x86/kernel/e820_64.c
===
--- linux-2.6.orig/arch/x86/kernel/e820_64.c
+++ linux-2.6/arch/x86/kernel/e820_64.c
@@ -70,8 +70,8 @@ void __init reserve_early(unsigned long
for (i = 0; i < MAX_EARLY_RES && early_res[i].end; i++) {
r = _res[i];
if (end > r->start && start < r->end)
- panic("Duplicated early reservation %lx-%lx\n",
- start, end);
+ panic("Overlap early reservation %lx-%lx to %lx-%lx\n",
+ start, end, r->start, r->end);
}
if (i >= MAX_EARLY_RES)
panic("Too many early reservations");
Index: linux-2.6/arch/x86/mm/init_64.c
===
--- linux-2.6.orig/arch/x86/mm/init_64.c
+++ linux-2.6/arch/x86/mm/init_64.c
@@ -358,6 +358,13 @@ static void __init find_early_table_spac
if (table_start == -1UL)
panic("Cannot find space for the kernel page tables");
+ /*
+* when you have a lot of ram like 256g, early_table will not fit
+* into 0x8000 range, find_e820_area will find area after kerne bss
+* but the table_start is not page align, 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;
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to [EMAIL PROTECTED]
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
[PATCH] x86_64: fix overlap between pagetable with bss section v2
[PATCH] x86_64: fix overlap between pagetable with bss section v2
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=0x000f 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: - 0009bc00 (usable)
BIOS-e820: 0009bc00 - 000a (reserved)
BIOS-e820: 000e6000 - 0010 (reserved)
BIOS-e820: 0010 - dffe (usable)
BIOS-e820: dffe - dffee000 (ACPI data)
BIOS-e820: dffee000 - d050 (ACPI NVS)
BIOS-e820: d050 - e000 (reserved)
BIOS-e820: fec0 - fec01000 (reserved)
BIOS-e820: fee0 - fee01000 (reserved)
BIOS-e820: ff70 - 0001 (reserved)
BIOS-e820: 0001 - 00402000 (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 d4-e42000
Pid: 0, comm: swapper Not tainted 2.6.24-smp-g5a514e21-dirty #3
Call Trace:
[80221545] lapic_get_maxlvt+0x0/0x10
[80221657] clear_local_APIC+0x5/0xcf
[80221726] disable_local_APIC+0x5/0x17
[8021fe16] smp_send_stop+0x46/0x4c
[80235293] panic+0x94/0x13e
[80bc3b03] sctp_eps_proc_init+0x12/0x34
[80b9f1c5] reserve_early+0x30/0x6c
[80803925] init_memory_mapping+0x2cd/0x2dc
[80b9dc01] setup_arch+0x21f/0x44e
[80b978be] start_kernel+0x6f/0x2c7
[80b971cc] _sinittext+0x1cc/0x1d3
it turns out there is overlap between pgtable and bss...
in System.map we have
80d40420 b rsi_table
80d40620 B krb5_seq_lock
80d40628 b i.20437
80d40630 b xprt_rdma_inline_write_padding
80d40638 b sunrpc_table_header
80d40640 b zero
80d40644 b min_memreg
80d40648 b rpcrdma_tk_lock_g
80d40650 B sctp_assocs_id_lock
80d40658 B proc_net_sctp
80d40660 B sctp_assocs_id
80d40680 B sysctl_sctp_mem
80d40690 B sysctl_sctp_rmem
80d406a0 B sysctl_sctp_wmem
80d406b0 b sctp_ctl_socket
80d406b8 b sctp_pf_inet6_specific
80d406c0 b sctp_pf_inet_specific
80d406c8 b sctp_af_v4_specific
80d406d0 b sctp_af_v6_specific
80d406d8 b sctp_rand.33270
80d406dc b sctp_memory_pressure
80d406e0 b sctp_sockets_allocated
80d406e4 b sctp_memory_allocated
80d406e8 b sctp_sysctl_header
80d406f0 b zero
80d406f4 A __bss_stop
80d406f4 A _end
need to round up table_start to PAGE_SIZE
also make the panic more informative.
Signed-off-by: Yinghai Lu [EMAIL PROTECTED]
Index: linux-2.6/arch/x86/kernel/e820_64.c
===
--- linux-2.6.orig/arch/x86/kernel/e820_64.c
+++ linux-2.6/arch/x86/kernel/e820_64.c
@@ -70,8 +70,8 @@ void __init reserve_early(unsigned long
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(Overlap early reservation %lx-%lx to %lx-%lx\n,
+ start, end, r-start, r-end);
}
if (i = MAX_EARLY_RES)
panic(Too many early reservations);
Index: linux-2.6/arch/x86/mm/init_64.c
===
--- linux-2.6.orig/arch/x86/mm/init_64.c
+++ linux-2.6/arch/x86/mm/init_64.c
@@ -358,6 +358,13 @@ static void __init find_early_table_spac
if (table_start == -1UL)
panic(Cannot find space for the kernel page tables);
+ /*
+* when you have a lot of ram like 256g, early_table will not fit
+* into 0x8000 range, find_e820_area will find area after kerne bss
+* but the table_start is not page align, 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;
--
To unsubscribe from this list: send the line unsubscribe linux-kernel in
the body of a message to [EMAIL PROTECTED]
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
