From 958fb3c51295764599d6abce87e1a01ace897a3e Mon Sep 17 00:00:00 2001
From: Chen Gong <gong.chen@linux.intel.com>
Date: Tue, 5 Jun 2012 10:35:02 +0800
Subject: [PATCH 01/11] x86/mce: Fix the MCE poll timer logic
In commit 82f7af09 ("x86/mce: Cleanup timer mess), Thomas just
forgot the "/ 2" there while cleaning up.
Signed-off-by: Chen Gong <gong.chen@linux.intel.com>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Cc: bp@amd64.org
Cc: tony.luck@intel.com
Link: http://lkml.kernel.org/r/1338863702-9245-1-git-send-email-gong.chen@linux.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
arch/x86/kernel/cpu/mcheck/mce.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 0a687fd185e6..a97f3c4a3946 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -1274,7 +1274,7 @@ static void mce_timer_fn(unsigned long data)
*/
iv = __this_cpu_read(mce_next_interval);
if (mce_notify_irq())
- iv = max(iv, (unsigned long) HZ/100);
+ iv = max(iv / 2, (unsigned long) HZ/100);
else
iv = min(iv * 2, round_jiffies_relative(check_interval * HZ));
__this_cpu_write(mce_next_interval, iv);
From 1a87fc1ec7b05b9bc60df9dc52297d4c225d7f1a Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Wed, 6 Jun 2012 11:33:21 +0200
Subject: [PATCH 02/11] x86: mce: Add the dropped timer interval init back
commit 82f7af09 ("x86/mce: Cleanup timer mess) dropped the
initialization of the per cpu timer interval. Duh :(
Restore the previous behaviour.
Reported-by: Chen Gong <gong.chen@linux.intel.com>
Cc: bp@amd64.org
Cc: tony.luck@intel.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
arch/x86/kernel/cpu/mcheck/mce.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index a97f3c4a3946..da27c5d2168a 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -1557,7 +1557,7 @@ static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c)
static void __mcheck_cpu_init_timer(void)
{
struct timer_list *t = &__get_cpu_var(mce_timer);
- unsigned long iv = __this_cpu_read(mce_next_interval);
+ unsigned long iv = check_interval * HZ;
setup_timer(t, mce_timer_fn, smp_processor_id());
From aff5a62d52ff03956ff6992b9fe4b561fd855804 Mon Sep 17 00:00:00 2001
From: Xiaotian Feng <xtfeng@gmail.com>
Date: Tue, 5 Jun 2012 15:00:31 -0400
Subject: [PATCH 03/11] x86/gart: Fix kmemleak warning
aperture_64.c now is using memblock, the previous
kmemleak_ignore() for alloc_bootmem() should be removed then.
Otherwise, with kmemleak enabled, kernel will throw warnings
like:
[ 0.000000] kmemleak: Trying to color unknown object at 0xffff8800c4000000 as Black
[ 0.000000] Pid: 0, comm: swapper/0 Not tainted 3.5.0-rc1-next-20120605+ #130
[ 0.000000] Call Trace:
[ 0.000000] [<ffffffff811b27e6>] paint_ptr+0x66/0xc0
[ 0.000000] [<ffffffff816b90fb>] kmemleak_ignore+0x2b/0x60
[ 0.000000] [<ffffffff81ef7bc0>] kmemleak_init+0x217/0x2c1
[ 0.000000] [<ffffffff81ed2b97>] start_kernel+0x32d/0x3eb
[ 0.000000] [<ffffffff81ed25e4>] ? repair_env_string+0x5a/0x5a
[ 0.000000] [<ffffffff81ed2356>] x86_64_start_reservations+0x131/0x135
[ 0.000000] [<ffffffff81ed2120>] ? early_idt_handlers+0x120/0x120
[ 0.000000] [<ffffffff81ed245c>] x86_64_start_kernel+0x102/0x111
[ 0.000000] kmemleak: Early log backtrace:
[ 0.000000] [<ffffffff816b911b>] kmemleak_ignore+0x4b/0x60
[ 0.000000] [<ffffffff81ee6a38>] gart_iommu_hole_init+0x3e7/0x547
[ 0.000000] [<ffffffff81edb20b>] pci_iommu_alloc+0x44/0x6f
[ 0.000000] [<ffffffff81ee81ad>] mem_init+0x19/0xec
[ 0.000000] [<ffffffff81ed2a54>] start_kernel+0x1ea/0x3eb
[ 0.000000] [<ffffffff81ed2356>] x86_64_start_reservations+0x131/0x135
[ 0.000000] [<ffffffff81ed245c>] x86_64_start_kernel+0x102/0x111
[ 0.000000] [<ffffffffffffffff>] 0xffffffffffffffff
Signed-off-by: Xiaotian Feng <dannyfeng@tencent.com>
Cc: Xiaotian Feng <xtfeng@gmail.com>
Cc: Tejun Heo <tj@kernel.org>
Link: http://lkml.kernel.org/r/1338922831-2847-1-git-send-email-xtfeng@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
arch/x86/kernel/aperture_64.c | 6 ------
1 file changed, 6 deletions(-)
diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c
index 6e76c191a835..d5fd66f0d4cd 100644
--- a/arch/x86/kernel/aperture_64.c
+++ b/arch/x86/kernel/aperture_64.c
@@ -20,7 +20,6 @@
#include <linux/bitops.h>
#include <linux/ioport.h>
#include <linux/suspend.h>
-#include <linux/kmemleak.h>
#include <asm/e820.h>
#include <asm/io.h>
#include <asm/iommu.h>
@@ -95,11 +94,6 @@ static u32 __init allocate_aperture(void)
return 0;
}
memblock_reserve(addr, aper_size);
- /*
- * Kmemleak should not scan this block as it may not be mapped via the
- * kernel direct mapping.
- */
- kmemleak_ignore(phys_to_virt(addr));
printk(KERN_INFO "Mapping aperture over %d KB of RAM @ %lx\n",
aper_size >> 10, addr);
insert_aperture_resource((u32)addr, aper_size);
From 4af463d28f1a026e25c0b879fac2a0d2b7bff599 Mon Sep 17 00:00:00 2001
From: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Date: Mon, 4 Jun 2012 11:42:32 +0900
Subject: [PATCH 04/11] x86/numa: Set numa_nodes_parsed at
acpi_numa_memory_affinity_init()
When hot-adding a CPU, the system outputs following messages
since node_to_cpumask_map[2] was not allocated memory.
Booting Node 2 Processor 32 APIC 0xc0
node_to_cpumask_map[2] NULL
Pid: 0, comm: swapper/32 Tainted: G A 3.3.5-acd #21
Call Trace:
[<ffffffff81048845>] debug_cpumask_set_cpu+0x155/0x160
[<ffffffff8105e28a>] ? add_timer_on+0xaa/0x120
[<ffffffff8150665f>] numa_add_cpu+0x1e/0x22
[<ffffffff815020bb>] identify_cpu+0x1df/0x1e4
[<ffffffff815020d6>] identify_econdary_cpu+0x16/0x1d
[<ffffffff81504614>] smp_store_cpu_info+0x3c/0x3e
[<ffffffff81505263>] smp_callin+0x139/0x1be
[<ffffffff815052fb>] start_secondary+0x13/0xeb
The reason is that the bit of node 2 was not set at
numa_nodes_parsed. numa_nodes_parsed is set by only
acpi_numa_processor_affinity_init /
acpi_numa_x2apic_affinity_init. Thus even if hot-added memory
which is same PXM as hot-added CPU is written in ACPI SRAT
Table, if the hot-added CPU is not written in ACPI SRAT table,
numa_nodes_parsed is not set.
But according to ACPI Spec Rev 5.0, it says about ACPI SRAT
table as follows: This optional table provides information that
allows OSPM to associate processors and memory ranges, including
ranges of memory provided by hot-added memory devices, with
system localities / proximity domains and clock domains.
It means that ACPI SRAT table only provides information for CPUs
present at boot time and for memory including hot-added memory.
So hot-added memory is written in ACPI SRAT table, but hot-added
CPU is not written in it. Thus numa_nodes_parsed should be set
by not only acpi_numa_processor_affinity_init /
acpi_numa_x2apic_affinity_init but also
acpi_numa_memory_affinity_init for the case.
Additionally, if system has cpuless memory node,
acpi_numa_processor_affinity_init /
acpi_numa_x2apic_affinity_init cannot set numa_nodes_parseds
since these functions cannot find cpu description for the node.
In this case, numa_nodes_parsed needs to be set by
acpi_numa_memory_affinity_init.
Signed-off-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Acked-by: David Rientjes <rientjes@google.com>
Acked-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: liuj97@gmail.com
Cc: kosaki.motohiro@gmail.com
Link: http://lkml.kernel.org/r/4FCC2098.4030007@jp.fujitsu.com
[ merged it ]
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
arch/x86/mm/srat.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/arch/x86/mm/srat.c b/arch/x86/mm/srat.c
index 732af3a96183..4599c3e8bcb6 100644
--- a/arch/x86/mm/srat.c
+++ b/arch/x86/mm/srat.c
@@ -176,6 +176,8 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma)
return;
}
+ node_set(node, numa_nodes_parsed);
+
printk(KERN_INFO "SRAT: Node %u PXM %u [mem %#010Lx-%#010Lx]\n",
node, pxm,
(unsigned long long) start, (unsigned long long) end - 1);
From 7071f6b2889bb41bea61891d8a3e6e70517ef5e6 Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <sebastian@breakpoint.cc>
Date: Thu, 31 May 2012 23:20:25 +0200
Subject: [PATCH 05/11] x86/intel/moorestown: Change intel_scu_devices_create()
to __devinit
The allmodconfig hits:
WARNING: vmlinux.o(.text+0x6553d): Section mismatch in
reference from the function intel_scu_devices_create() to the
function .devinit.text: spi_register_board_info()
[...]
This patch marks intel_scu_devices_create() as devinit because
it only calls a devinit function, spi_register_board_info().
Signed-off-by: Sebastian Andrzej Siewior <sebastian@breakpoint.cc>
Cc: Alan Cox <alan@linux.intel.com>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Mika Westerberg <mika.westerberg@linux.intel.com>
Cc: Samuel Ortiz <sameo@linux.intel.com>
Cc: Feng Tang <feng.tang@intel.com>
Link: http://lkml.kernel.org/r/20120531212025.GA8519@breakpoint.cc
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
arch/x86/platform/mrst/mrst.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/x86/platform/mrst/mrst.c b/arch/x86/platform/mrst/mrst.c
index e31bcd8f2eee..fd41a9262d65 100644
--- a/arch/x86/platform/mrst/mrst.c
+++ b/arch/x86/platform/mrst/mrst.c
@@ -782,7 +782,7 @@ BLOCKING_NOTIFIER_HEAD(intel_scu_notifier);
EXPORT_SYMBOL_GPL(intel_scu_notifier);
/* Called by IPC driver */
-void intel_scu_devices_create(void)
+void __devinit intel_scu_devices_create(void)
{
int i;
From 55c844a4dd16a4d1fdc0cf2a283ec631a02ec448 Mon Sep 17 00:00:00 2001
From: Feng Tang <feng.tang@intel.com>
Date: Wed, 30 May 2012 23:15:41 +0800
Subject: [PATCH 06/11] x86/reboot: Fix a warning message triggered by
stop_other_cpus()
When rebooting our 24 CPU Westmere servers with 3.4-rc6, we
always see this warning msg:
Restarting system.
machine restart
------------[ cut here ]------------
WARNING: at arch/x86/kernel/smp.c:125
native_smp_send_reschedule+0x74/0xa7() Hardware name: X8DTN
Modules linked in: igb [last unloaded: scsi_wait_scan]
Pid: 1, comm: systemd-shutdow Not tainted 3.4.0-rc6+ #22
Call Trace:
<IRQ> [<ffffffff8102a41f>] warn_slowpath_common+0x7e/0x96
[<ffffffff8102a44c>] warn_slowpath_null+0x15/0x17
[<ffffffff81018cf7>] native_smp_send_reschedule+0x74/0xa7
[<ffffffff810561c1>] trigger_load_balance+0x279/0x2a6
[<ffffffff81050112>] scheduler_tick+0xe0/0xe9
[<ffffffff81036768>] update_process_times+0x60/0x70
[<ffffffff81062f2f>] tick_sched_timer+0x68/0x92
[<ffffffff81046e33>] __run_hrtimer+0xb3/0x13c
[<ffffffff81062ec7>] ? tick_nohz_handler+0xd0/0xd0
[<ffffffff810474f2>] hrtimer_interrupt+0xdb/0x198
[<ffffffff81019a35>] smp_apic_timer_interrupt+0x81/0x94
[<ffffffff81655187>] apic_timer_interrupt+0x67/0x70
<EOI> [<ffffffff8101a3c4>] ? default_send_IPI_mask_allbutself_phys+0xb4/0xc4
[<ffffffff8101c680>] physflat_send_IPI_allbutself+0x12/0x14
[<ffffffff81018db4>] native_nmi_stop_other_cpus+0x8a/0xd6
[<ffffffff810188ba>] native_machine_shutdown+0x50/0x67
[<ffffffff81018926>] machine_shutdown+0xa/0xc
[<ffffffff8101897e>] native_machine_restart+0x20/0x32
[<ffffffff810189b0>] machine_restart+0xa/0xc
[<ffffffff8103b196>] kernel_restart+0x47/0x4c
[<ffffffff8103b2e6>] sys_reboot+0x13e/0x17c
[<ffffffff8164e436>] ? _raw_spin_unlock_bh+0x10/0x12
[<ffffffff810fcac9>] ? bdi_queue_work+0xcf/0xd8
[<ffffffff810fe82f>] ? __bdi_start_writeback+0xae/0xb7
[<ffffffff810e0d64>] ? iterate_supers+0xa3/0xb7
[<ffffffff816547a2>] system_call_fastpath+0x16/0x1b
---[ end trace 320af5cb1cb60c5b ]---
The root cause seems to be the
default_send_IPI_mask_allbutself_phys() takes quite some time (I
measured it could be several ms) to complete sending NMIs to all
the other 23 CPUs, and for HZ=250/1000 system, the time is long
enough for a timer interrupt to happen, which will in turn
trigger to kick load balance to a stopped CPU and cause this
warning in native_smp_send_reschedule().
So disabling the local irq before stop_other_cpu() can fix this
problem (tested 25 times reboot ok), and it is fine as there
should be nobody caring the timer interrupt in such reboot
stage.
The latest 3.4 kernel slightly changes this behavior by sending
REBOOT_VECTOR first and only send NMI_VECTOR if the REBOOT_VCTOR
fails, and this patch is still needed to prevent the problem.
Signed-off-by: Feng Tang <feng.tang@intel.com>
Acked-by: Don Zickus <dzickus@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20120530231541.4c13433a@feng-i7
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
arch/x86/kernel/reboot.c | 6 ++++--
1 file changed, 4 insertions(+), 2 deletions(-)
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 79c45af81604..25b48edb847c 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -639,9 +639,11 @@ void native_machine_shutdown(void)
set_cpus_allowed_ptr(current, cpumask_of(reboot_cpu_id));
/*
- * O.K Now that I'm on the appropriate processor,
- * stop all of the others.
+ * O.K Now that I'm on the appropriate processor, stop all of the
+ * others. Also disable the local irq to not receive the per-cpu
+ * timer interrupt which may trigger scheduler's load balance.
*/
+ local_irq_disable();
stop_other_cpus();
#endif
From f6175f5bfb4c9f2ed32758c95f765b529b1a7f15 Mon Sep 17 00:00:00 2001
From: Tomoki Sekiyama <tomoki.sekiyama.qu@hitachi.com>
Date: Mon, 28 May 2012 18:09:18 +0900
Subject: [PATCH 07/11] x86/ioapic: Fix NULL pointer dereference on CPU hotplug
after disabling irqs
In current Linux, percpu variable `vector_irq' is not cleared on
offlined cpus while disabling devices' irqs. If the cpu that has
the disabled irqs in vector_irq is hotplugged,
__setup_vector_irq() hits invalid irq vector and may crash.
This bug can be reproduced as following;
# echo 0 > /sys/devices/system/cpu/cpu7/online
# modprobe -r some_driver_using_interrupts # vector_irq@cpu7 uncleared
# echo 1 > /sys/devices/system/cpu/cpu7/online # kernel may crash
This patch fixes this bug by clearing vector_irq in
__clear_irq_vector() even if the cpu is offlined.
Signed-off-by: Tomoki Sekiyama <tomoki.sekiyama.qu@hitachi.com>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Cc: yrl.pp-manager.tt@hitachi.com
Cc: ltc-kernel@ml.yrl.intra.hitachi.co.jp
Cc: Suresh Siddha <suresh.b.siddha@intel.com>
Cc: Yinghai Lu <yinghai@kernel.org>
Cc: Alexander Gordeev <agordeev@redhat.com>
Link: http://lkml.kernel.org/r/4FC340BE.7080101@hitachi.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
arch/x86/kernel/apic/io_apic.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index ac96561d1a99..5f0ff597437c 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -1195,7 +1195,7 @@ static void __clear_irq_vector(int irq, struct irq_cfg *cfg)
BUG_ON(!cfg->vector);
vector = cfg->vector;
- for_each_cpu_and(cpu, cfg->domain, cpu_online_mask)
+ for_each_cpu(cpu, cfg->domain)
per_cpu(vector_irq, cpu)[vector] = -1;
cfg->vector = 0;
@@ -1203,7 +1203,7 @@ static void __clear_irq_vector(int irq, struct irq_cfg *cfg)
if (likely(!cfg->move_in_progress))
return;
- for_each_cpu_and(cpu, cfg->old_domain, cpu_online_mask) {
+ for_each_cpu(cpu, cfg->old_domain) {
for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS;
vector++) {
if (per_cpu(vector_irq, cpu)[vector] != irq)
From 743628e868c5992354fc80b4d1e9a6143da1c0e6 Mon Sep 17 00:00:00 2001
From: Jordan Justen <jordan.l.justen@intel.com>
Date: Thu, 7 Jun 2012 09:05:21 -0700
Subject: [PATCH 08/11] x86, efi stub: Add .reloc section back into image
Some UEFI firmware will not load a .efi with a .reloc section
with a size of 0.
Therefore, we create a .efi image with 4 main areas and 3 sections.
1. PE/COFF file header
2. .setup section (covers all setup code following the first sector)
3. .reloc section (contains 1 dummy reloc entry, created in build.c)
4. .text section (covers the remaining kernel image)
To make room for the new .setup section data, the header
bugger_off_msg had to be shortened.
Reported-by: Henrik Rydberg <rydberg@euromail.se>
Signed-off-by: Jordan Justen <jordan.l.justen@intel.com>
Link: http://lkml.kernel.org/r/1339085121-12760-1-git-send-email-jordan.l.justen@intel.com
Tested-by: Lee G Rosenbaum <lee.g.rosenbaum@intel.com>
Tested-by: Henrik Rydberg <rydberg@euromail.se>
Cc: Matt Fleming <matt.fleming@intel.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
---
arch/x86/boot/header.S | 42 ++++++---
arch/x86/boot/tools/build.c | 172 +++++++++++++++++++++++-------------
2 files changed, 140 insertions(+), 74 deletions(-)
diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S
index 8bbea6aa40d9..efe5acfc79c3 100644
--- a/arch/x86/boot/header.S
+++ b/arch/x86/boot/header.S
@@ -94,10 +94,10 @@ bs_die:
.section ".bsdata", "a"
bugger_off_msg:
- .ascii "Direct booting from floppy is no longer supported.\r\n"
- .ascii "Please use a boot loader program instead.\r\n"
+ .ascii "Direct floppy boot is not supported. "
+ .ascii "Use a boot loader program instead.\r\n"
.ascii "\n"
- .ascii "Remove disk and press any key to reboot . . .\r\n"
+ .ascii "Remove disk and press any key to reboot ...\r\n"
.byte 0
#ifdef CONFIG_EFI_STUB
@@ -111,7 +111,7 @@ coff_header:
#else
.word 0x8664 # x86-64
#endif
- .word 2 # nr_sections
+ .word 3 # nr_sections
.long 0 # TimeDateStamp
.long 0 # PointerToSymbolTable
.long 1 # NumberOfSymbols
@@ -158,8 +158,8 @@ extra_header_fields:
#else
.quad 0 # ImageBase
#endif
- .long 0x1000 # SectionAlignment
- .long 0x200 # FileAlignment
+ .long 0x20 # SectionAlignment
+ .long 0x20 # FileAlignment
.word 0 # MajorOperatingSystemVersion
.word 0 # MinorOperatingSystemVersion
.word 0 # MajorImageVersion
@@ -200,8 +200,10 @@ extra_header_fields:
# Section table
section_table:
- .ascii ".text"
- .byte 0
+ #
+ # The offset & size fields are filled in by build.c.
+ #
+ .ascii ".setup"
.byte 0
.byte 0
.long 0
@@ -217,9 +219,8 @@ section_table:
#
# The EFI application loader requires a relocation section
- # because EFI applications must be relocatable. But since
- # we don't need the loader to fixup any relocs for us, we
- # just create an empty (zero-length) .reloc section header.
+ # because EFI applications must be relocatable. The .reloc
+ # offset & size fields are filled in by build.c.
#
.ascii ".reloc"
.byte 0
@@ -233,6 +234,25 @@ section_table:
.word 0 # NumberOfRelocations
.word 0 # NumberOfLineNumbers
.long 0x42100040 # Characteristics (section flags)
+
+ #
+ # The offset & size fields are filled in by build.c.
+ #
+ .ascii ".text"
+ .byte 0
+ .byte 0
+ .byte 0
+ .long 0
+ .long 0x0 # startup_{32,64}
+ .long 0 # Size of initialized data
+ # on disk
+ .long 0x0 # startup_{32,64}
+ .long 0 # PointerToRelocations
+ .long 0 # PointerToLineNumbers
+ .word 0 # NumberOfRelocations
+ .word 0 # NumberOfLineNumbers
+ .long 0x60500020 # Characteristics (section flags)
+
#endif /* CONFIG_EFI_STUB */
# Kernel attributes; used by setup. This is part 1 of the
diff --git a/arch/x86/boot/tools/build.c b/arch/x86/boot/tools/build.c
index 3f61f6e2b46f..4b8e165ee572 100644
--- a/arch/x86/boot/tools/build.c
+++ b/arch/x86/boot/tools/build.c
@@ -50,6 +50,8 @@ typedef unsigned int u32;
u8 buf[SETUP_SECT_MAX*512];
int is_big_kernel;
+#define PECOFF_RELOC_RESERVE 0x20
+
/*----------------------------------------------------------------------*/
static const u32 crctab32[] = {
@@ -133,11 +135,103 @@ static void usage(void)
die("Usage: build setup system [> image]");
}
+#ifdef CONFIG_EFI_STUB
+
+static void update_pecoff_section_header(char *section_name, u32 offset, u32 size)
+{
+ unsigned int pe_header;
+ unsigned short num_sections;
+ u8 *section;
+
+ pe_header = get_unaligned_le32(&buf[0x3c]);
+ num_sections = get_unaligned_le16(&buf[pe_header + 6]);
+
+#ifdef CONFIG_X86_32
+ section = &buf[pe_header + 0xa8];
+#else
+ section = &buf[pe_header + 0xb8];
+#endif
+
+ while (num_sections > 0) {
+ if (strncmp((char*)section, section_name, 8) == 0) {
+ /* section header size field */
+ put_unaligned_le32(size, section + 0x8);
+
+ /* section header vma field */
+ put_unaligned_le32(offset, section + 0xc);
+
+ /* section header 'size of initialised data' field */
+ put_unaligned_le32(size, section + 0x10);
+
+ /* section header 'file offset' field */
+ put_unaligned_le32(offset, section + 0x14);
+
+ break;
+ }
+ section += 0x28;
+ num_sections--;
+ }
+}
+
+static void update_pecoff_setup_and_reloc(unsigned int size)
+{
+ u32 setup_offset = 0x200;
+ u32 reloc_offset = size - PECOFF_RELOC_RESERVE;
+ u32 setup_size = reloc_offset - setup_offset;
+
+ update_pecoff_section_header(".setup", setup_offset, setup_size);
+ update_pecoff_section_header(".reloc", reloc_offset, PECOFF_RELOC_RESERVE);
+
+ /*
+ * Modify .reloc section contents with a single entry. The
+ * relocation is applied to offset 10 of the relocation section.
+ */
+ put_unaligned_le32(reloc_offset + 10, &buf[reloc_offset]);
+ put_unaligned_le32(10, &buf[reloc_offset + 4]);
+}
+
+static void update_pecoff_text(unsigned int text_start, unsigned int file_sz)
+{
+ unsigned int pe_header;
+ unsigned int text_sz = file_sz - text_start;
+
+ pe_header = get_unaligned_le32(&buf[0x3c]);
+
+ /* Size of image */
+ put_unaligned_le32(file_sz, &buf[pe_header + 0x50]);
+
+ /*
+ * Size of code: Subtract the size of the first sector (512 bytes)
+ * which includes the header.
+ */
+ put_unaligned_le32(file_sz - 512, &buf[pe_header + 0x1c]);
+
+#ifdef CONFIG_X86_32
+ /*
+ * Address of entry point.
+ *
+ * The EFI stub entry point is +16 bytes from the start of
+ * the .text section.
+ */
+ put_unaligned_le32(text_start + 16, &buf[pe_header + 0x28]);
+#else
+ /*
+ * Address of entry point. startup_32 is at the beginning and
+ * the 64-bit entry point (startup_64) is always 512 bytes
+ * after. The EFI stub entry point is 16 bytes after that, as
+ * the first instruction allows legacy loaders to jump over
+ * the EFI stub initialisation
+ */
+ put_unaligned_le32(text_start + 528, &buf[pe_header + 0x28]);
+#endif /* CONFIG_X86_32 */
+
+ update_pecoff_section_header(".text", text_start, text_sz);
+}
+
+#endif /* CONFIG_EFI_STUB */
+
int main(int argc, char ** argv)
{
-#ifdef CONFIG_EFI_STUB
- unsigned int file_sz, pe_header;
-#endif
unsigned int i, sz, setup_sectors;
int c;
u32 sys_size;
@@ -163,6 +257,12 @@ int main(int argc, char ** argv)
die("Boot block hasn't got boot flag (0xAA55)");
fclose(file);
+#ifdef CONFIG_EFI_STUB
+ /* Reserve 0x20 bytes for .reloc section */
+ memset(buf+c, 0, PECOFF_RELOC_RESERVE);
+ c += PECOFF_RELOC_RESERVE;
+#endif
+
/* Pad unused space with zeros */
setup_sectors = (c + 511) / 512;
if (setup_sectors < SETUP_SECT_MIN)
@@ -170,6 +270,10 @@ int main(int argc, char ** argv)
i = setup_sectors*512;
memset(buf+c, 0, i-c);
+#ifdef CONFIG_EFI_STUB
+ update_pecoff_setup_and_reloc(i);
+#endif
+
/* Set the default root device */
put_unaligned_le16(DEFAULT_ROOT_DEV, &buf[508]);
@@ -194,66 +298,8 @@ int main(int argc, char ** argv)
put_unaligned_le32(sys_size, &buf[0x1f4]);
#ifdef CONFIG_EFI_STUB
- file_sz = sz + i + ((sys_size * 16) - sz);
-
- pe_header = get_unaligned_le32(&buf[0x3c]);
-
- /* Size of image */
- put_unaligned_le32(file_sz, &buf[pe_header + 0x50]);
-
- /*
- * Subtract the size of the first section (512 bytes) which
- * includes the header and .reloc section. The remaining size
- * is that of the .text section.
- */
- file_sz -= 512;
-
- /* Size of code */
- put_unaligned_le32(file_sz, &buf[pe_header + 0x1c]);
-
-#ifdef CONFIG_X86_32
- /*
- * Address of entry point.
- *
- * The EFI stub entry point is +16 bytes from the start of
- * the .text section.
- */
- put_unaligned_le32(i + 16, &buf[pe_header + 0x28]);
-
- /* .text size */
- put_unaligned_le32(file_sz, &buf[pe_header + 0xb0]);
-
- /* .text vma */
- put_unaligned_le32(0x200, &buf[pe_header + 0xb4]);
-
- /* .text size of initialised data */
- put_unaligned_le32(file_sz, &buf[pe_header + 0xb8]);
-
- /* .text file offset */
- put_unaligned_le32(0x200, &buf[pe_header + 0xbc]);
-#else
- /*
- * Address of entry point. startup_32 is at the beginning and
- * the 64-bit entry point (startup_64) is always 512 bytes
- * after. The EFI stub entry point is 16 bytes after that, as
- * the first instruction allows legacy loaders to jump over
- * the EFI stub initialisation
- */
- put_unaligned_le32(i + 528, &buf[pe_header + 0x28]);
-
- /* .text size */
- put_unaligned_le32(file_sz, &buf[pe_header + 0xc0]);
-
- /* .text vma */
- put_unaligned_le32(0x200, &buf[pe_header + 0xc4]);
-
- /* .text size of initialised data */
- put_unaligned_le32(file_sz, &buf[pe_header + 0xc8]);
-
- /* .text file offset */
- put_unaligned_le32(0x200, &buf[pe_header + 0xcc]);
-#endif /* CONFIG_X86_32 */
-#endif /* CONFIG_EFI_STUB */
+ update_pecoff_text(setup_sectors * 512, sz + i + ((sys_size * 16) - sz));
+#endif
crc = partial_crc32(buf, i, crc);
if (fwrite(buf, 1, i, stdout) != i)
From bd2753b2dda7bb43c7468826de75f49c6a7e8965 Mon Sep 17 00:00:00 2001
From: Yinghai Lu <yinghai@kernel.org>
Date: Wed, 6 Jun 2012 10:55:40 -0700
Subject: [PATCH 09/11] x86/mm: Only add extra pages count for the first memory
range during pre-allocation early page table space
Robin found this regression:
| I just tried to boot an 8TB system. It fails very early in boot with:
| Kernel panic - not syncing: Cannot find space for the kernel page tables
git bisect commit 722bc6b16771ed80871e1fd81c86d3627dda2ac8.
A git revert of that commit does boot past that point on the 8TB
configuration.
That commit will add up extra pages for all memory range even
above 4g.
Try to limit that extra page count adding to first entry only.
Bisected-by: Robin Holt <holt@sgi.com>
Tested-by: Robin Holt <holt@sgi.com>
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Cc: WANG Cong <xiyou.wangcong@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/CAE9FiQUj3wyzQxtq9yzBNc9u220p8JZ1FYHG7t%3DMOzJ%3D9BZMYA@mail.gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
arch/x86/mm/init.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 97141c26a13a..bc4e9d84157f 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -62,7 +62,8 @@ static void __init find_early_table_space(struct map_range *mr, unsigned long en
extra += PMD_SIZE;
#endif
/* The first 2/4M doesn't use large pages. */
- extra += mr->end - mr->start;
+ if (mr->start < PMD_SIZE)
+ extra += mr->end - mr->start;
ptes = (extra + PAGE_SIZE - 1) >> PAGE_SHIFT;
} else
From d5d2d2eea84b0d8450b082edbc3dbde41fb8bfd8 Mon Sep 17 00:00:00 2001
From: Cliff Wickman <cpw@sgi.com>
Date: Thu, 7 Jun 2012 08:31:40 -0500
Subject: [PATCH 10/11] x86/uv: Fix UV2 BAU legacy mode
The SGI Altix UV2 BAU (Broadcast Assist Unit) as used for
tlb-shootdown (selective broadcast mode) always uses UV2
broadcast descriptor format. There is no need to clear the
'legacy' (UV1) mode, because the hardware always uses UV2 mode
for selective broadcast.
But the BIOS uses general broadcast and legacy mode, and the
hardware pays attention to the legacy mode bit for general
broadcast. So the kernel must not clear that mode bit.
Signed-off-by: Cliff Wickman <cpw@sgi.com>
Cc: <stable@kernel.org>
Link: http://lkml.kernel.org/r/E1SccoO-0002Lh-Cb@eag09.americas.sgi.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
arch/x86/include/asm/uv/uv_bau.h | 1 -
arch/x86/platform/uv/tlb_uv.c | 1 -
2 files changed, 2 deletions(-)
diff --git a/arch/x86/include/asm/uv/uv_bau.h b/arch/x86/include/asm/uv/uv_bau.h
index becf47b81735..6149b476d9df 100644
--- a/arch/x86/include/asm/uv/uv_bau.h
+++ b/arch/x86/include/asm/uv/uv_bau.h
@@ -149,7 +149,6 @@
/* 4 bits of software ack period */
#define UV2_ACK_MASK 0x7UL
#define UV2_ACK_UNITS_SHFT 3
-#define UV2_LEG_SHFT UV2H_LB_BAU_MISC_CONTROL_USE_LEGACY_DESCRIPTOR_FORMATS_SHFT
#define UV2_EXT_SHFT UV2H_LB_BAU_MISC_CONTROL_ENABLE_EXTENDED_SB_STATUS_SHFT
/*
diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c
index 3ae0e61abd23..59880afa851f 100644
--- a/arch/x86/platform/uv/tlb_uv.c
+++ b/arch/x86/platform/uv/tlb_uv.c
@@ -1295,7 +1295,6 @@ static void __init enable_timeouts(void)
*/
mmr_image |= (1L << SOFTACK_MSHIFT);
if (is_uv2_hub()) {
- mmr_image &= ~(1L << UV2_LEG_SHFT);
mmr_image |= (1L << UV2_EXT_SHFT);
}
write_mmr_misc_control(pnode, mmr_image);
From eeaaa96a3a2134a174100afd129bb0891d05f4b2 Mon Sep 17 00:00:00 2001
From: Don Zickus <dzickus@redhat.com>
Date: Wed, 6 Jun 2012 10:05:42 -0400
Subject: [PATCH 11/11] x86/nmi: Fix section mismatch warnings on 32-bit
It was reported that compiling for 32-bit caused a bunch of
section mismatch warnings:
VDSOSYM arch/x86/vdso/vdso32-syms.lds
LD arch/x86/vdso/built-in.o
LD arch/x86/built-in.o
WARNING: arch/x86/built-in.o(.data+0x5af0): Section mismatch in
reference from the variable test_nmi_ipi_callback_na.10451 to
the function .init.text:test_nmi_ipi_callback() [...]
WARNING: arch/x86/built-in.o(.data+0x5b04): Section mismatch in
reference from the variable nmi_unk_cb_na.10399 to the function
.init.text:nmi_unk_cb() The variable nmi_unk_cb_na.10399
references the function __init nmi_unk_cb() [...]
Both of these are attributed to the internal representation of
the nmiaction struct created during register_nmi_handler. The
reason for this is that those structs are not defined in the
init section whereas the rest of the code in nmi_selftest.c is.
To resolve this, I created a new #define,
register_nmi_handler_initonly, that tags the struct as
__initdata to resolve the mismatch. This #define should only be
used in rare situations where the register/unregister is called
during init of the kernel.
Big thanks to Jan Beulich for decoding this for me as I didn't
have a clue what was going on.
Reported-by: Witold Baryluk <baryluk@smp.if.uj.edu.pl>
Tested-by: Witold Baryluk <baryluk@smp.if.uj.edu.pl>
Cc: Jan Beulich <JBeulich@suse.com>
Signed-off-by: Don Zickus <dzickus@redhat.com>
Link: http://lkml.kernel.org/r/1338991542-23000-1-git-send-email-dzickus@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
arch/x86/include/asm/nmi.h | 14 ++++++++++++++
arch/x86/kernel/nmi_selftest.c | 4 ++--
2 files changed, 16 insertions(+), 2 deletions(-)
diff --git a/arch/x86/include/asm/nmi.h b/arch/x86/include/asm/nmi.h
index 0e3793b821ef..dc580c42851c 100644
--- a/arch/x86/include/asm/nmi.h
+++ b/arch/x86/include/asm/nmi.h
@@ -54,6 +54,20 @@ struct nmiaction {
__register_nmi_handler((t), &fn##_na); \
})
+/*
+ * For special handlers that register/unregister in the
+ * init section only. This should be considered rare.
+ */
+#define register_nmi_handler_initonly(t, fn, fg, n) \
+({ \
+ static struct nmiaction fn##_na __initdata = { \
+ .handler = (fn), \
+ .name = (n), \
+ .flags = (fg), \
+ }; \
+ __register_nmi_handler((t), &fn##_na); \
+})
+
int __register_nmi_handler(unsigned int, struct nmiaction *);
void unregister_nmi_handler(unsigned int, const char *);
diff --git a/arch/x86/kernel/nmi_selftest.c b/arch/x86/kernel/nmi_selftest.c
index e31bf8d5c4d2..149b8d9c6ad4 100644
--- a/arch/x86/kernel/nmi_selftest.c
+++ b/arch/x86/kernel/nmi_selftest.c
@@ -42,7 +42,7 @@ static int __init nmi_unk_cb(unsigned int val, struct pt_regs *regs)
static void __init init_nmi_testsuite(void)
{
/* trap all the unknown NMIs we may generate */
- register_nmi_handler(NMI_UNKNOWN, nmi_unk_cb, 0, "nmi_selftest_unk");
+ register_nmi_handler_initonly(NMI_UNKNOWN, nmi_unk_cb, 0, "nmi_selftest_unk");
}
static void __init cleanup_nmi_testsuite(void)
@@ -64,7 +64,7 @@ static void __init test_nmi_ipi(struct cpumask *mask)
{
unsigned long timeout;
- if (register_nmi_handler(NMI_LOCAL, test_nmi_ipi_callback,
+ if (register_nmi_handler_initonly(NMI_LOCAL, test_nmi_ipi_callback,
NMI_FLAG_FIRST, "nmi_selftest")) {
nmi_fail = FAILURE;
return;