When the kernel is compiled with -pg for tracing GCC 4.4.x inserts
stack alignment of a function _before_ the mcount prologue if the
-march=pentium-mmx is set and -mtune=generic is not set. This breaks
the assumption of the function graph tracer which expects that the
mcount prologue
push %ebp
mov %esp, %ebp
is the first stack operation in a function because it needs to modify
the function return address on the stack to trap into the tracer
before returning to the real caller.
The generated code is:
push %edi
lea 0x8(%esp),%edi
and $0xfffffff0,%esp
pushl -0x4(%edi)
push %ebp
mov %esp,%ebp
so the tracer modifies the copy of the return address which is stored
after the stack alignment and therefor does not trap the return which
in turn breaks the call chain logic of the tracer and leads to a
kernel panic.
Aside of the fact that the generated code is horrible for no good
reason other -march -mtune options generate the expected:
push %ebp
mov %esp,%ebp
and $0xfffffff0,%esp
which does the same and keeps everything intact.
After some experimenting we found out that this problem is restricted
to gcc4.4.x and to the following -march settings:
i586, pentium, pentium-mmx, k6, k6-2, k6-3, winchip-c6, winchip2, c3,
geode
By adding -mtune=generic the code generator produces always the
expected code.
So forcing -mtune=generic when CONFIG_FUNCTION_GRAPH_TRACER=y is not
pretty, but at the moment the only way to prevent that the kernel
trips over gcc-shrooms induced code madness.
Most distro kernels have CONFIG_X86_GENERIC=y anyway which forces
-mtune=generic as well so it will not impact those.
References: http://gcc.gnu.org/bugzilla/show_bug.cgi?id=42109http://lkml.org/lkml/2009/11/19/17
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
LKML-Reference: <alpine.LFD.2.00.0911200206570.24119@localhost.localdomain>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>,
Cc: Jeff Law <law@redhat.com>
Cc: gcc@gcc.gnu.org
Cc: David Daney <ddaney@caviumnetworks.com>
Cc: Andrew Haley <aph@redhat.com>
Cc: Richard Guenther <richard.guenther@gmail.com>
Cc: stable@kernel.org
Fix panic seen on some IBM and HP systems on 2.6.32-rc6:
BUG: unable to handle kernel NULL pointer dereference at (null)
IP: [<ffffffff8120bf3f>] find_next_bit+0x77/0x9c
[...]
[<ffffffff8120bbde>] cpumask_next_and+0x2e/0x3b
[<ffffffff81225c62>] pci_device_probe+0x8e/0xf5
[<ffffffff812b9be6>] ? driver_sysfs_add+0x47/0x6c
[<ffffffff812b9da5>] driver_probe_device+0xd9/0x1f9
[<ffffffff812b9f1d>] __driver_attach+0x58/0x7c
[<ffffffff812b9ec5>] ? __driver_attach+0x0/0x7c
[<ffffffff812b9298>] bus_for_each_dev+0x54/0x89
[<ffffffff812b9b4f>] driver_attach+0x19/0x1b
[<ffffffff812b97ae>] bus_add_driver+0xd3/0x23d
[<ffffffff812ba1e7>] driver_register+0x98/0x109
[<ffffffff81225ed0>] __pci_register_driver+0x63/0xd3
[<ffffffff81072776>] ? up_read+0x26/0x2a
[<ffffffffa0081000>] ? k8temp_init+0x0/0x20 [k8temp]
[<ffffffffa008101e>] k8temp_init+0x1e/0x20 [k8temp]
[<ffffffff8100a073>] do_one_initcall+0x6d/0x185
[<ffffffff8108d765>] sys_init_module+0xd3/0x236
[<ffffffff81011ac2>] system_call_fastpath+0x16/0x1b
I put in a printk and commented out the set_dev_node()
call when and got this output:
quirk_amd_nb_node: current numa_node = 0x0, would set to val & 7 = 0x0
quirk_amd_nb_node: current numa_node = 0x0, would set to val & 7 = 0x1
quirk_amd_nb_node: current numa_node = 0x0, would set to val & 7 = 0x2
quirk_amd_nb_node: current numa_node = 0x0, would set to val & 7 = 0x3
I.e. the issue appears to be that the HW has set val to a valid
value, however, the system is only configured for a single
node -- 0, the others are offline.
Check to see if the node is actually online before setting
the numa node for an AMD northbridge in quirk_amd_nb_node().
Signed-off-by: Prarit Bhargava <prarit@redhat.com>
Cc: bhavna.sarathy@amd.com
Cc: jbarnes@virtuousgeek.org
Cc: andreas.herrmann3@amd.com
LKML-Reference: <20091112180933.12532.98685.sendpatchset@prarit.bos.redhat.com>
[ v2: clean up the code and add comments ]
Signed-off-by: Ingo Molnar <mingo@elte.hu>
COMPAT_VDSO has 2 help text blocks, but kconfig only uses the
last one found, so merge the 2 blocks.
It would be real nice if kconfig would warn about this.
Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com>
LKML-Reference: <4AF9FB6C.70003@oracle.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
The latest rev of Intel doc AP-485 details new cache descriptors
that we don't yet support. 12MB, 18MB and 24MB 24-way assoc L3
caches.
Signed-off-by: Dave Jones <davej@redhat.com>
LKML-Reference: <20091110184924.GA20337@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
This patch fixes two issues in the procfs stack information on
x86-64 linux.
The 32 bit loader compat_do_execve did not store stack
start. (this was figured out by Alexey Dobriyan).
The stack information on a x64_64 kernel always shows 0 kbyte
stack usage, because of a missing implementation of the KSTK_ESP
macro which always returned -1.
The new implementation now returns the right value.
Signed-off-by: Stefani Seibold <stefani@seibold.net>
Cc: Americo Wang <xiyou.wangcong@gmail.com>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Andrew Morton <akpm@linux-foundation.org>
LKML-Reference: <1257240160.4889.24.camel@wall-e>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Reboot does not work out of the box on my "Early 2009" Mac mini
(3,1). Detect this machine via DMI as we do for recent MacBooks.
Signed-off-by: Gottfried Haider <gottfried.haider@gmail.com>
Cc: Ozan Çağlayan <ozan@pardus.org.tr>
Cc: Paul Mackerras <paulus@samba.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
When PAE is enabled in the kernel configuration the size of
phys_addr_t differs from the size of a void pointer. The gcc
prints a warning about that in dma-debug code.
This patch fixes the warning by converting the output to
unsigned long long instead of a pointer.
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
The function iommu_feature_disable is required on system
shutdown to disable the IOMMU but it is marked as __init.
This may result in a panic if the memory is reused. This
patch fixes this bug.
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
The EFI RTC functions are only available on 32 bit. commit 7bd867df
(x86: Move get/set_wallclock to x86_platform_ops) removed the 32bit
dependency which leads to boot crashes on 64bit EFI systems.
Add the dependency back.
Solves: http://bugzilla.kernel.org/show_bug.cgi?id=14466
Tested-by: Matthew Garrett <mjg59@srcf.ucam.org>
Signed-off-by: Feng Tang <feng.tang@intel.com>
LKML-Reference: <20091020125402.028d66d5@feng-desktop>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Restoring %ebp after the call to audit_syscall_exit() is not
only unnecessary (because the register didn't get clobbered),
but in the sysenter case wasn't even doing the right thing: It
loaded %ebp from a location below the top of stack (RBP <
ARGOFFSET), i.e. arbitrary kernel data got passed back to user
mode in the register.
Signed-off-by: Jan Beulich <jbeulich@novell.com>
Acked-by: Roland McGrath <roland@redhat.com>
Cc: <stable@kernel.org>
LKML-Reference: <4AE5CC4D020000780001BD13@vpn.id2.novell.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Non-PAE 32-bit dump kernels may wrap an address around 4G and
poke unwanted space. ptes there are 32-bit long, and since
pfn << PAGE_SIZE may exceed this limit, high pfn bits are
cropped and wrong address mapped by kmap_atomic_pfn in
copy_oldmem_page.
Don't allow this behavior in non-PAE kdump kernels by checking
pfns passed into copy_oldmem_page. In the case of failure,
userspace process gets EFAULT.
[v2]
- fix comments
- move ifdefs inside the function
Signed-off-by: Jiri Slaby <jirislaby@gmail.com>
Cc: Vivek Goyal <vgoyal@redhat.com>
Cc: Eric W. Biederman <ebiederm@xmission.com>
Cc: Simon Horman <horms@verge.net.au>
Cc: Paul Mundt <lethal@linux-sh.org>
LKML-Reference: <1256551903-30567-1-git-send-email-jirislaby@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
STACKPROTECTOR_ALL has a really high overhead (runtime and stack
footprint) and is not really worth it protection wise (the
normal STACKPROTECTOR is in effect for all functions with
buffers already), so lets just remove the option entirely.
Reported-by: Dave Jones <davej@redhat.com>
Reported-by: Chuck Ebbert <cebbert@redhat.com>
Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
Cc: Eric Sandeen <sandeen@redhat.com>
LKML-Reference: <20091023073101.3dce4ebb@infradead.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
When sending a NMI_VECTOR IPI using the UV_HUB_IPI_INT register,
we need to ensure the delivery mode field of that register has
NMI delivery selected.
This makes those IPIs true NMIs, instead of flat IPIs. It
matters to reboot sequences and KGDB, both of which use NMI
IPIs.
Signed-off-by: Robin Holt <holt@sgi.com>
Acked-by: Jack Steiner <steiner@sgi.com>
Cc: Martin Hicks <mort@sgi.com>
Cc: <stable@kernel.org>
LKML-Reference: <20091020193620.877322000@alcatraz.americas.sgi.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Create an inline function to extract the pnode from a global
physical address and then convert the broadcast assist unit to
use the newly created uv_gpa_to_pnode function.
The open-coded code was wrong as well - it might explain a
few of our unexplained bau hangs.
Signed-off-by: Robin Holt <holt@sgi.com>
Acked-by: Cliff Whickman <cpw@sgi.com>
Cc: linux-mm@kvack.org
Cc: Jack Steiner <steiner@sgi.com>
LKML-Reference: <20091016112920.GZ8903@sgi.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
The MCE initialization code explicitly says it doesn't handle
asymmetric configurations where different CPUs support different
numbers of MCE banks, and it prints a big warning in that case.
Therefore, printing the "mce: CPU supports <x> MCE banks"
message into the kernel log for every CPU is pure redundancy
that clutters the log significantly for systems with lots of
CPUs.
Signed-off-by: Roland Dreier <rolandd@cisco.com>
LKML-Reference: <adaeip473qt.fsf@cisco.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
A few parts of the uv_hub_info structure are initialized
incorrectly.
- n_val is being loaded with m_val.
- gpa_mask is initialized with a bytes instead of an unsigned long.
- Handle the case where none of the alias registers are used.
Lastly I converted the bau over to using the uv_hub_info->m_val
which is the correct value.
Without this patch, booting a large configuration hits a
problem where the upper bits of the gnode affect the pnode
and the bau will not operate.
Signed-off-by: Robin Holt <holt@sgi.com>
Acked-by: Jack Steiner <steiner@sgi.com>
Cc: Cliff Whickman <cpw@sgi.com>
Cc: stable@kernel.org
LKML-Reference: <20091015224946.396355000@alcatraz.americas.sgi.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Thomas Gleixner
Prarit Bhargava
Randy Dunlap
Dave Jones
Borislav Petkov
Xiaotian Feng
Simon Kagstrom
Stefani Seibold
Ingo Molnar
Joerg Roedel
Gottfried Haider
Feng Tang
Jan Beulich
Jiri Slaby
Rusty Russell
Arjan van de Ven
Robin Holt
Roland Dreier