Many Pentium M systems disable PAE but may have a functionally usable PAE
implementation. This adds the "forcepae" parameter which bypasses the boot
check for PAE, and sets the CPU as being PAE capable. Using this parameter
will taint the kernel with TAINT_CPU_OUT_OF_SPEC.
Signed-off-by: Chris Bainbridge <chris.bainbridge@gmail.com>
Link: http://lkml.kernel.org/r/20140307114040.GA4997@localhost
Acked-by: Borislav Petkov <bp@suse.de>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Rename TAINT_UNSAFE_SMP to TAINT_CPU_OUT_OF_SPEC, so we can repurpose
the flag to encompass a wider range of pushing the CPU beyond its
warrany.
Signed-off-by: Dave Jones <davej@fedoraproject.org>
Link: http://lkml.kernel.org/r/20140226154949.GA770@redhat.com
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
This replaces a decent amount of incomprehensible and buggy code
with much more straightforward code. It also brings the 32-bit vdso
more in line with the 64-bit vdsos, so maybe someday they can share
even more code.
This wastes a small amount of kernel .data and .text space, but it
avoids a couple of allocations on startup, so it should be more or
less a wash memory-wise.
Signed-off-by: Andy Lutomirski <luto@amacapital.net>
Cc: Stefani Seibold <stefani@seibold.net>
Link: http://lkml.kernel.org/r/b8093933fad09ce181edb08a61dcd5d2592e9814.1395352498.git.luto@amacapital.net
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
* pm-cpufreq: (30 commits)
intel_pstate: Set core to min P state during core offline
cpufreq: Add stop CPU callback to cpufreq_driver interface
cpufreq: Remove unnecessary braces
cpufreq: Fix checkpatch errors and warnings
cpufreq: powerpc: add cpufreq transition latency for FSL e500mc SoCs
cpufreq: remove unused notifier: CPUFREQ_{SUSPENDCHANGE|RESUMECHANGE}
cpufreq: Do not allow ->setpolicy drivers to provide ->target
cpufreq: arm_big_little: set 'physical_cluster' for each CPU
cpufreq: arm_big_little: make vexpress driver depend on bL core driver
cpufreq: SPEAr: Instantiate as platform_driver
cpufreq: Remove unnecessary variable/parameter 'frozen'
cpufreq: Remove cpufreq_generic_exit()
cpufreq: add 'freq_table' in struct cpufreq_policy
cpufreq: Reformat printk() statements
cpufreq: Tegra: Use cpufreq_generic_suspend()
cpufreq: s5pv210: Use cpufreq_generic_suspend()
cpufreq: exynos: Use cpufreq_generic_suspend()
cpufreq: Implement cpufreq_generic_suspend()
cpufreq: suspend governors on system suspend/hibernate
cpufreq: move call to __find_governor() to cpufreq_init_policy()
...
Minor cleanups:
- simplify switch statement
- add __init annotation to setup_arch_fast_hash()
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Link: http://lkml.kernel.org/r/530F09CE020000780011FBEF@nat28.tlf.novell.com
Cc: Francesco Fusco <ffusco@redhat.com>
Cc: Thomas Graf <tgraf@redhat.com>
Cc: David S. Miller <davem@davemloft.net>
Acked-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
... to match the function's parameters. While reportedly commutative,
using the proper order allows for leveraging the instruction permitting
the source operand to be in memory.
[ hpa: This code originated in the dpdk toolkit. This was a bug in dpdk
which has recently been fixed in part due to an earlier version of
this patch. ]
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Link: http://lkml.kernel.org/r/530F09B6020000780011FBEB@nat28.tlf.novell.com
Acked-by: Daniel Borkmann <dborkman@redhat.com>
Cc: Francesco Fusco <ffusco@redhat.com>
Cc: Thomas Graf <tgraf@redhat.com>
Cc: David S. Miller <davem@davemloft.net>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Just like for other ISA extension instruction uses we should check
whether the assembler actually supports them. The fallback here simply
is to encode an instruction with fixed operands (%eax and %ecx).
[ hpa: tagging for -stable as a build fix ]
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Link: http://lkml.kernel.org/r/530F0996020000780011FBE7@nat28.tlf.novell.com
Cc: Francesco Fusco <ffusco@redhat.com>
Cc: Thomas Graf <tgraf@redhat.com>
Cc: David S. Miller <davem@davemloft.net>
Acked-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Cc: <stable@vger.kernel.org> # v3.14
Resource management
- Revert "Insert GART region into resource map"
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.4.11 (GNU/Linux)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=yDUb
-----END PGP SIGNATURE-----
Merge tag 'pci-v3.14-fixes-3' of git://git.kernel.org/pub/scm/linux/kernel/git/helgaas/pci
Pull PCI resource management fix from Bjorn Helgaas:
"This is a fix for an AGP regression exposed by e501b3d87f ("agp:
Support 64-bit APBASE"), which we merged in v3.14-rc1.
We've warned about the conflict between the GART and PCI resources and
cleared out the PCI resource for a long time, but after e501b3d87f,
we still *use* that cleared-out PCI resource. I think the GART
resource is incorrect, so this patch removes it"
* tag 'pci-v3.14-fixes-3' of git://git.kernel.org/pub/scm/linux/kernel/git/helgaas/pci:
Revert "[PATCH] Insert GART region into resource map"
Currently compressed/misc.c needs to link against memset(). I think one of
the reasons of this need is inclusion of various header files which define
static inline functions and use memset() inside these. For example,
include/linux/bitmap.h
I think trying to include "../string.h" and using builtin version of memset
does not work because by the time "#define memset" shows up, it is too
late. Some other header file has already used memset() and expects to
find a definition during link phase.
Currently we have a C definitoin of memset() in misc.c. Move it to
compressed/string.c so that others can use it if need be.
Signed-off-by: Vivek Goyal <vgoyal@redhat.com>
Link: http://lkml.kernel.org/r/1395170800-11059-6-git-send-email-vgoyal@redhat.com
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Try to treat memcmp() in same way as memcpy() and memset(). Provide a
declaration in boot/string.h and by default user gets a memcmp() which
maps to builtin function.
Move optimized definition of memcmp() in boot/string.c. Now a user can
do #undef memcmp and link against string.c to use optimzied memcmp().
It also simplifies boot/compressed/string.c where we had to redefine
memcmp(). That extra definition is gone now.
Signed-off-by: Vivek Goyal <vgoyal@redhat.com>
Link: http://lkml.kernel.org/r/1395170800-11059-5-git-send-email-vgoyal@redhat.com
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Move optimized versions of memcpy to compressed/string.c This will allow
any other code to use these functions too if need be in future. Again
trying to put definition in a common place instead of hiding it in misc.c
Signed-off-by: Vivek Goyal <vgoyal@redhat.com>
Link: http://lkml.kernel.org/r/1395170800-11059-4-git-send-email-vgoyal@redhat.com
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Create a separate arch/x86/boot/string.h file to provide declaration of
some of the common string functions.
By default memcpy, memset and memcmp functions will default to gcc
builtin functions. If code wants to use an optimized version of any
of these functions, they need to #undef the respective macro and link
against a local file providing definition of undefed function.
For example, arch/x86/boot/* code links against copy.S to get memcpy()
and memcmp() definitions. arch/86/boot/compressed/* links against
compressed/string.c.
There are quite a few places in arch/x86/ where these functions are
used. Idea is to try to consilidate their declaration and possibly
definitions so that it can be reused.
I am planning to reuse boot/string.h in arch/x86/purgatory/ and use
gcc builtin functions for memcpy, memset and memcmp.
Signed-off-by: Vivek Goyal <vgoyal@redhat.com>
Link: http://lkml.kernel.org/r/1395170800-11059-3-git-send-email-vgoyal@redhat.com
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
With CONFIG_X86_32=y, string_32.h gets pulled in compressed/string.c by
"misch.h". string_32.h defines a macro to map memcmp to __builtin_memcmp().
And that macro in turn changes the name of memcmp() defined here and
converts it to __builtin_memcmp().
I thought that's not the intention though. We probably want to provide
our own optimized definition of memcmp(). If yes, then undef the memcmp
before we define a new memcmp.
Signed-off-by: Vivek Goyal <vgoyal@redhat.com>
Link: http://lkml.kernel.org/r/1395170800-11059-2-git-send-email-vgoyal@redhat.com
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
* pci/resource: (26 commits)
Revert "[PATCH] Insert GART region into resource map"
PCI: Log IDE resource quirk in dmesg
PCI: Change pci_bus_alloc_resource() type_mask to unsigned long
PCI: Check all IORESOURCE_TYPE_BITS in pci_bus_alloc_from_region()
resources: Set type in __request_region()
PCI: Don't check resource_size() in pci_bus_alloc_resource()
s390/PCI: Use generic pci_enable_resources()
tile PCI RC: Use default pcibios_enable_device()
sparc/PCI: Use default pcibios_enable_device() (Leon only)
sh/PCI: Use default pcibios_enable_device()
microblaze/PCI: Use default pcibios_enable_device()
alpha/PCI: Use default pcibios_enable_device()
PCI: Add "weak" generic pcibios_enable_device() implementation
PCI: Don't enable decoding if BAR hasn't been assigned an address
PCI: Mark 64-bit resource as IORESOURCE_UNSET if we only support 32-bit
PCI: Don't try to claim IORESOURCE_UNSET resources
PCI: Check IORESOURCE_UNSET before updating BAR
PCI: Don't clear IORESOURCE_UNSET when updating BAR
PCI: Mark resources as IORESOURCE_UNSET if we can't assign them
PCI: Remove pci_find_parent_resource() use for allocation
...
This reverts commit 56dd669a13, which makes the GART visible in
/proc/iomem. This fixes a regression: e501b3d87f ("agp: Support 64-bit
APBASE") exposed an existing problem with a conflict between the GART
region and a PCI BAR region.
The GART addresses are bus addresses, not CPU addresses, and therefore
should not be inserted in iomem_resource.
On many machines, the GART region is addressable by the CPU as well as by
an AGP master, but CPU addressability is not required by the spec. On some
of these machines, the GART is mapped by a PCI BAR, and in that case, the
PCI core automatically inserts it into iomem_resource, just as it does for
all BARs.
Inserting it here means we'll have a conflict if the PCI core later tries
to claim the GART region, so let's drop the insertion here.
The conflict indirectly causes X failures, as reported by Jouni in the
bugzilla below. We detected the conflict even before e501b3d87f, but
after it the AGP code (fix_northbridge()) uses the PCI resource (which is
zeroed because of the conflict) instead of reading the BAR again.
Conflicts:
arch/x86_64/kernel/aperture.c
Fixes: e501b3d87f agp: Support 64-bit APBASE
Link: https://bugzilla.kernel.org/show_bug.cgi?id=72201
Reported-and-tested-by: Jouni Mettälä <jtmettala@gmail.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Two cpufreq notifiers CPUFREQ_RESUMECHANGE and CPUFREQ_SUSPENDCHANGE have
not been used for some time, so remove them to clean up code a bit.
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Reviewed-by: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
[rjw: Changelog]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
This reverts commit 56dd669a13, which makes the GART visible in
/proc/iomem. This fixes a regression: e501b3d87f ("agp: Support 64-bit
APBASE") exposed an existing problem with a conflict between the GART
region and a PCI BAR region.
The GART addresses are bus addresses, not CPU addresses, and therefore
should not be inserted in iomem_resource.
On many machines, the GART region is addressable by the CPU as well as by
an AGP master, but CPU addressability is not required by the spec. On some
of these machines, the GART is mapped by a PCI BAR, and in that case, the
PCI core automatically inserts it into iomem_resource, just as it does for
all BARs.
Inserting it here means we'll have a conflict if the PCI core later tries
to claim the GART region, so let's drop the insertion here.
The conflict indirectly causes X failures, as reported by Jouni in the
bugzilla below. We detected the conflict even before e501b3d87f, but
after it the AGP code (fix_northbridge()) uses the PCI resource (which is
zeroed because of the conflict) instead of reading the BAR again.
Conflicts:
arch/x86_64/kernel/aperture.c
Fixes: e501b3d87f agp: Support 64-bit APBASE
Link: https://bugzilla.kernel.org/show_bug.cgi?id=72201
Reported-and-tested-by: Jouni Mettälä <jtmettala@gmail.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
For the 32-bit VDSO, match the 64-bit VDSO in:
1. Disable the stack protector.
2. Use -fno-omit-frame-pointer for user space debugging sanity.
3. Use -foptimize-sibling-calls like the 64-bit VDSO does.
Reported-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Stefani Seibold <stefani@seibold.net>
Link: http://lkml.kernel.org/r/1395094933-14252-13-git-send-email-stefani@seibold.net
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
By coincidence, the VVAR page is at the end of an ELF segment. As a
result, if it ends up being a partial page, the kernel loader will
leave garbage behind at the end of the vvar page. Zero-pad it to a
full page to fix this issue.
This has probably been broken since the VVAR page was introduced.
On QEMU, if you dump the run-time contents of the VVAR page, you can
find entertaining strings from seabios left behind.
It's remotely possible that this is a security bug -- conceivably
there's some BIOS out there that leaves something sensitive in the
few K of memory that is exposed to userspace.
Signed-off-by: Stefani Seibold <stefani@seibold.net>
Link: http://lkml.kernel.org/r/1395094933-14252-12-git-send-email-stefani@seibold.net
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
This patch add the VDSO time support for the IA32 Emulation Layer.
Due the nature of the kernel headers and the LP64 compiler where the
size of a long and a pointer differs against a 32 bit compiler, there
is some type hacking necessary for optimal performance.
The vsyscall_gtod_data struture must be a rearranged to serve 32- and
64-bit code access at the same time:
- The seqcount_t was replaced by an unsigned, this makes the
vsyscall_gtod_data intedepend of kernel configuration and internal functions.
- All kernel internal structures are replaced by fix size elements
which works for 32- and 64-bit access
- The inner struct clock was removed to pack the whole struct.
The "unsigned seq" would be handled by functions derivated from seqcount_t.
Signed-off-by: Stefani Seibold <stefani@seibold.net>
Link: http://lkml.kernel.org/r/1395094933-14252-11-git-send-email-stefani@seibold.net
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
This patch add the time support for 32 bit a VDSO to a 32 bit kernel.
For 32 bit programs running on a 32 bit kernel, the same mechanism is
used as for 64 bit programs running on a 64 bit kernel.
Reviewed-by: Andy Lutomirski <luto@amacapital.net>
Signed-off-by: Stefani Seibold <stefani@seibold.net>
Link: http://lkml.kernel.org/r/1395094933-14252-10-git-send-email-stefani@seibold.net
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
This patch cleans up the __vdso_gettimeofday() function a little.
It kicks out an unneeded ret local variable and makes the code faster
if only the timezone is needed (an admittedly rare case.)
Reviewed-by: Andy Lutomirski <luto@amacapital.net>
Signed-off-by: Stefani Seibold <stefani@seibold.net>
Link: http://lkml.kernel.org/r/1395094933-14252-7-git-send-email-stefani@seibold.net
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
There a currently more than 30 users of the gtod macro, so replace the
last VVAR(vsyscall_gtod_data) by gtod macro.
Reviewed-by: Andy Lutomirski <luto@amacapital.net>
Signed-off-by: Stefani Seibold <stefani@seibold.net>
Link: http://lkml.kernel.org/r/1395094933-14252-6-git-send-email-stefani@seibold.net
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
This patch is a small code cleanup for the __vdso_clock_gettime() function.
It removes the unneeded return values from do_monotonic_coarse() and
do_realtime_coarse() and add a fallback label for doing the kernel
gettimeofday() system call.
Reviewed-by: Andy Lutomirski <luto@amacapital.net>
Signed-off-by: Stefani Seibold <stefani@seibold.net>
Link: http://lkml.kernel.org/r/1395094933-14252-5-git-send-email-stefani@seibold.net
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
This intermediate patch revamps the vclock_gettime.c by moving some functions
around. It is only for spliting purpose, to make whole the 32 bit vdso timer
patch easier to review.
Reviewed-by: Andy Lutomirski <luto@amacapital.net>
Signed-off-by: Stefani Seibold <stefani@seibold.net>
Link: http://lkml.kernel.org/r/1395094933-14252-4-git-send-email-stefani@seibold.net
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
This patch move the vsyscall_gtod_data handling out of vsyscall_64.c
into an additonal file vsyscall_gtod.c to make the functionality
available for x86 32 bit kernel.
It also adds a new vsyscall_32.c which setup the VVAR page.
Reviewed-by: Andy Lutomirski <luto@amacapital.net>
Signed-off-by: Stefani Seibold <stefani@seibold.net>
Link: http://lkml.kernel.org/r/1395094933-14252-2-git-send-email-stefani@seibold.net
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
In the thunk patches the 'attr' argument was dropped to
query_variable_info(). Restore it otherwise the firmware will return
EFI_INVALID_PARAMETER.
Signed-off-by: Matt Fleming <matt.fleming@intel.com>
Dan reported that phys_efi_get_time() is doing kmalloc(..., GFP_KERNEL)
under a spinlock which is very clearly a bug. Since phys_efi_get_time()
has no users let's just delete it instead of trying to fix it.
Note that since there are no users of phys_efi_get_time(), it is not
possible to actually trigger a GFP_KERNEL alloc under the spinlock.
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Nathan Zimmer <nzimmer@sgi.com>
Cc: Matthew Garrett <mjg59@srcf.ucam.org>
Cc: Jan Beulich <JBeulich@suse.com>
Signed-off-by: Matt Fleming <matt.fleming@intel.com>
I was triggering a #GP(0) from userland when running with
CONFIG_EFI_MIXED and CONFIG_IA32_EMULATION, from what looked like
register corruption. Turns out that the mixed mode code was trashing the
contents of %ds, %es and %ss in __efi64_thunk().
Save and restore the contents of these segment registers across the call
to __efi64_thunk() so that we don't corrupt the CPU context.
Signed-off-by: Matt Fleming <matt.fleming@intel.com>
When doing nested virtualization, we may be able to read BNDCFGS but
still not be allowed to write to GUEST_BNDCFGS in the VMCS. Guard
writes to the field with vmx_mpx_supported(), and similarly hide the
MSR from userspace if the processor does not support the field.
We could work around this with the generic MSR save/load machinery,
but there is only a limited number of MSR save/load slots and it is
not really worthwhile to waste one for a scenario that should not
happen except in the nested virtualization case.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
This is simple to do, the "host" BNDCFGS is either 0 or the guest value.
However, both controls have to be present. We cannot provide MPX if
we only have one of the "load BNDCFGS" or "clear BNDCFGS" controls.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
XSAVE support for KVM is already using host_xcr0 & KVM_SUPPORTED_XCR0 as
a "dynamic" version of KVM_SUPPORTED_XCR0.
However, this is not enough because the MPX bits should not be presented
to the guest unless kvm_x86_ops confirms the support. So, replace all
instances of host_xcr0 & KVM_SUPPORTED_XCR0 with a new function
kvm_supported_xcr0() that also has this check.
Note that here:
if (xstate_bv & ~KVM_SUPPORTED_XCR0)
return -EINVAL;
if (xstate_bv & ~host_cr0)
return -EINVAL;
the code is equivalent to
if ((xstate_bv & ~KVM_SUPPORTED_XCR0) ||
(xstate_bv & ~host_cr0)
return -EINVAL;
i.e. "xstate_bv & (~KVM_SUPPORTED_XCR0 | ~host_cr0)" which is in turn
equal to "xstate_bv & ~(KVM_SUPPORTED_XCR0 & host_cr0)". So we should
also use the new function there.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Add emulation for 0x66 prefixed instruction of 0f 28 opcode
that has been added earlier.
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Pull perf fixes from Ingo Molnar:
"Misc smaller fixes"
* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
perf/x86: Fix leak in uncore_type_init failure paths
perf machine: Use map as success in ip__resolve_ams
perf symbols: Fix crash in elf_section_by_name
perf trace: Decode architecture-specific signal numbers
Pull x86 fixes from Peter Anvin:
"Two x86 fixes: Suresh's eager FPU fix, and a fix to the NUMA quirk for
AMD northbridges.
This only includes Suresh's fix patch, not the "mostly a cleanup"
patch which had __init issues"
* 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/amd/numa: Fix northbridge quirk to assign correct NUMA node
x86, fpu: Check tsk_used_math() in kernel_fpu_end() for eager FPU
For systems with multiple servers and routed fabric, all
northbridges get assigned to the first server. Fix this by also
using the node reported from the PCI bus. For single-fabric
systems, the northbriges are on PCI bus 0 by definition, which
are on NUMA node 0 by definition, so this is invarient on most
systems.
Tested on fam10h and fam15h single and multi-fabric systems and
candidate for stable.
Signed-off-by: Daniel J Blueman <daniel@numascale.com>
Acked-by: Steffen Persvold <sp@numascale.com>
Acked-by: Borislav Petkov <bp@suse.de>
Cc: <stable@vger.kernel.org>
Link: http://lkml.kernel.org/r/1394710981-3596-1-git-send-email-daniel@numascale.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Pull networking fixes from David Miller:
"I know this is a bit more than you want to see, and I've told the
wireless folks under no uncertain terms that they must severely scale
back the extent of the fixes they are submitting this late in the
game.
Anyways:
1) vmxnet3's netpoll doesn't perform the equivalent of an ISR, which
is the correct implementation, like it should. Instead it does
something like a NAPI poll operation. This leads to crashes.
From Neil Horman and Arnd Bergmann.
2) Segmentation of SKBs requires proper socket orphaning of the
fragments, otherwise we might access stale state released by the
release callbacks.
This is a 5 patch fix, but the initial patches are giving
variables and such significantly clearer names such that the
actual fix itself at the end looks trivial.
From Michael S. Tsirkin.
3) TCP control block release can deadlock if invoked from a timer on
an already "owned" socket. Fix from Eric Dumazet.
4) In the bridge multicast code, we must validate that the
destination address of general queries is the link local all-nodes
multicast address. From Linus Lüssing.
5) The x86 BPF JIT support for negative offsets puts the parameter
for the helper function call in the wrong register. Fix from
Alexei Starovoitov.
6) The descriptor type used for RTL_GIGA_MAC_VER_17 chips in the
r8169 driver is incorrect. Fix from Hayes Wang.
7) The xen-netback driver tests skb_shinfo(skb)->gso_type bits to see
if a packet is a GSO frame, but that's not the correct test. It
should use skb_is_gso(skb) instead. Fix from Wei Liu.
8) Negative msg->msg_namelen values should generate an error, from
Matthew Leach.
9) at86rf230 can deadlock because it takes the same lock from it's
ISR and it's hard_start_xmit method, without disabling interrupts
in the latter. Fix from Alexander Aring.
10) The FEC driver's restart doesn't perform operations in the correct
order, so promiscuous settings can get lost. Fix from Stefan
Wahren.
11) Fix SKB leak in SCTP cookie handling, from Daniel Borkmann.
12) Reference count and memory leak fixes in TIPC from Ying Xue and
Erik Hugne.
13) Forced eviction in inet_frag_evictor() must strictly make sure all
frags are deleted, otherwise module unload (f.e. 6lowpan) can
crash. Fix from Florian Westphal.
14) Remove assumptions in AF_UNIX's use of csum_partial() (which it
uses as a hash function), which breaks on PowerPC. From Anton
Blanchard.
The main gist of the issue is that csum_partial() is defined only
as a value that, once folded (f.e. via csum_fold()) produces a
correct 16-bit checksum. It is legitimate, therefore, for
csum_partial() to produce two different 32-bit values over the
same data if their respective alignments are different.
15) Fix endiannes bug in MAC address handling of ibmveth driver, also
from Anton Blanchard.
16) Error checks for ipv6 exthdrs offload registration are reversed,
from Anton Nayshtut.
17) Externally triggered ipv6 addrconf routes should count against the
garbage collection threshold. Fix from Sabrina Dubroca.
18) The PCI shutdown handler added to the bnx2 driver can wedge the
chip if it was not brought up earlier already, which in particular
causes the firmware to shut down the PHY. Fix from Michael Chan.
19) Adjust the sanity WARN_ON_ONCE() in qdisc_list_add() because as
currently coded it can and does trigger in legitimate situations.
From Eric Dumazet.
20) BNA driver fails to build on ARM because of a too large udelay()
call, fix from Ben Hutchings.
21) Fair-Queue qdisc holds locks during GFP_KERNEL allocations, fix
from Eric Dumazet.
22) The vlan passthrough ops added in the previous release causes a
regression in source MAC address setting of outgoing headers in
some circumstances. Fix from Peter Boström"
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (70 commits)
ipv6: Avoid unnecessary temporary addresses being generated
eth: fec: Fix lost promiscuous mode after reconnecting cable
bonding: set correct vlan id for alb xmit path
at86rf230: fix lockdep splats
net/mlx4_en: Deregister multicast vxlan steering rules when going down
vmxnet3: fix building without CONFIG_PCI_MSI
MAINTAINERS: add networking selftests to NETWORKING
net: socket: error on a negative msg_namelen
MAINTAINERS: Add tools/net to NETWORKING [GENERAL]
packet: doc: Spelling s/than/that/
net/mlx4_core: Load the IB driver when the device supports IBoE
net/mlx4_en: Handle vxlan steering rules for mac address changes
net/mlx4_core: Fix wrong dump of the vxlan offloads device capability
xen-netback: use skb_is_gso in xenvif_start_xmit
r8169: fix the incorrect tx descriptor version
tools/net/Makefile: Define PACKAGE to fix build problems
x86: bpf_jit: support negative offsets
bridge: multicast: enable snooping on general queries only
bridge: multicast: add sanity check for general query destination
tcp: tcp_release_cb() should release socket ownership
...
Checkin
b0b49f2673 x86, vdso: Remove compat vdso support
... removed the VDSO from the fixmap, and thus FIX_VDSO; remove a
stray reference in Xen.
Found by Fengguang Wu's test robot.
Reported-by: Fengguang Wu <fengguang.wu@intel.com>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: David Vrabel <david.vrabel@citrix.com>
Link: http://lkml.kernel.org/r/4bb4690899106eb11430b1186d5cc66ca9d1660c.1394751608.git.luto@amacapital.net
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
The compat vDSO is a complicated hack that's needed to maintain
compatibility with a small range of glibc versions.
This removes it and replaces it with a much simpler hack: a config
option to disable the 32-bit vDSO by default.
This also changes the default value of CONFIG_COMPAT_VDSO to n --
users configuring kernels from scratch almost certainly want that
choice.
Signed-off-by: Andy Lutomirski <luto@amacapital.net>
Link: http://lkml.kernel.org/r/4bb4690899106eb11430b1186d5cc66ca9d1660c.1394751608.git.luto@amacapital.net
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Replace somewhat arbitrary constants for bits in MSR_IA32_MISC_ENABLE
with verbose but systematic ones. Add _BIT defines for all the rest
of them, too.
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
We very often need to set or clear a bit in an MSR as a result of doing
some sort of a hardware configuration. Add generic versions of that
repeated functionality in order to save us a bunch of duplicated code in
the early CPU vendor detection/config code.
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: http://lkml.kernel.org/r/1394384725-10796-2-git-send-email-bp@alien8.de
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Many architectures have a stub cputime.h that only include the default
cputime.h
Lets remove the useless headers, we only need to mention that we want
the default headers on the Kbuild files.
Cc: Archs <linux-arch@vger.kernel.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Marcelo Tosatti <mtosatti@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Both QEMU and KVM have already accumulated a significant number of
optimizations based on the hard-coded assumption that ioapic polarity
will always use the ActiveHigh convention, where the logical and
physical states of level-triggered irq lines always match (i.e.,
active(asserted) == high == 1, inactive == low == 0). QEMU guests
are expected to follow directions given via ACPI and configure the
ioapic with polarity 0 (ActiveHigh). However, even when misbehaving
guests (e.g. OS X <= 10.9) set the ioapic polarity to 1 (ActiveLow),
QEMU will still use the ActiveHigh signaling convention when
interfacing with KVM.
This patch modifies KVM to completely ignore ioapic polarity as set by
the guest OS, enabling misbehaving guests to work alongside those which
comply with the ActiveHigh polarity specified by QEMU's ACPI tables.
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Gabriel L. Somlo <somlo@cmu.edu>
[Move documentation to KVM_IRQ_LINE, add ia64. - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
fixes Windows guests on AMD processors.
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v2.0.22 (GNU/Linux)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=gJNC
-----END PGP SIGNATURE-----
Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm
Pull KVM fixes from Paolo Bonzini:
"The ARM patch fixes a build breakage with randconfig. The x86 one
fixes Windows guests on AMD processors"
* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
KVM: SVM: fix cr8 intercept window
ARM: KVM: fix non-VGIC compilation
We always disable cr8 intercept in its handler, but only re-enable it
if handling KVM_REQ_EVENT, so there can be a window where we do not
intercept cr8 writes, which allows an interrupt to disrupt a higher
priority task.
Fix this by disabling intercepts in the same function that re-enables
them when needed. This fixes BSOD in Windows 2008.
Cc: <stable@vger.kernel.org>
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
Reviewed-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Merge the request/release callbacks which are in a separate branch for
consumption by the gpio folks.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
This patch fixes a compilation problem (unused variable) with the
new SNB/IVB/HSW uncore IMC code.
[ In -v2 we simplify the fix as suggested by Peter Zjilstra. ]
Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20140311235329.GA28624@quad
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Commit a998d43423 claimed to introduce negative offset support to x86 jit,
but it couldn't be working, since at the time of the execution
of LD+ABS or LD+IND instructions via call into
bpf_internal_load_pointer_neg_helper() the %edx (3rd argument of this func)
had junk value instead of access size in bytes (1 or 2 or 4).
Store size into %edx instead of %ecx (what original commit intended to do)
Fixes: a998d43423 ("bpf jit: Let the x86 jit handle negative offsets")
Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Cc: Jan Seiffert <kaffeemonster@googlemail.com>
Cc: Eric Dumazet <edumazet@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
For non-eager fpu mode, thread's fpu state is allocated during the first
fpu usage (in the context of device not available exception). This
(math_state_restore()) can be a blocking call and hence we enable
interrupts (which were originally disabled when the exception happened),
allocate memory and disable interrupts etc.
But the eager-fpu mode, call's the same math_state_restore() from
kernel_fpu_end(). The assumption being that tsk_used_math() is always
set for the eager-fpu mode and thus avoid the code path of enabling
interrupts, allocating fpu state using blocking call and disable
interrupts etc.
But the below issue was noticed by Maarten Baert, Nate Eldredge and
few others:
If a user process dumps core on an ecrypt fs while aesni-intel is loaded,
we get a BUG() in __find_get_block() complaining that it was called with
interrupts disabled; then all further accesses to our ecrypt fs hang
and we have to reboot.
The aesni-intel code (encrypting the core file that we are writing) needs
the FPU and quite properly wraps its code in kernel_fpu_{begin,end}(),
the latter of which calls math_state_restore(). So after kernel_fpu_end(),
interrupts may be disabled, which nobody seems to expect, and they stay
that way until we eventually get to __find_get_block() which barfs.
For eager fpu, most the time, tsk_used_math() is true. At few instances
during thread exit, signal return handling etc, tsk_used_math() might
be false.
In kernel_fpu_end(), for eager-fpu, call math_state_restore()
only if tsk_used_math() is set. Otherwise, don't bother. Kernel code
path which cleared tsk_used_math() knows what needs to be done
with the fpu state.
Reported-by: Maarten Baert <maarten-baert@hotmail.com>
Reported-by: Nate Eldredge <nate@thatsmathematics.com>
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Suresh Siddha <sbsiddha@gmail.com>
Link: http://lkml.kernel.org/r/1391410583.3801.6.camel@europa
Cc: George Spelvin <linux@horizon.com>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
This was an optimization that made memcpy type benchmarks a little
faster on ancient (Circa 1998) IDT Winchip CPUs. In real-life
workloads, it wasn't even noticable, and I doubt anyone is running
benchmarks on 16 year old silicon any more.
Given this code has likely seen very little use over the last decade,
let's just remove it.
Signed-off-by: Dave Jones <davej@fedoraproject.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Remove mc_capable() and smt_capable(). Neither is used.
Both were added by 5c45bf279d ("sched: mc/smt power savings sched
policy"). Uses of both were removed by 8e7fbcbc22 ("sched: Remove stale
power aware scheduling remnants and dysfunctional knobs").
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: David S. Miller <davem@davemloft.net>
Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Link: http://lkml.kernel.org/r/20140304210737.16893.54289.stgit@bhelgaas-glaptop.roam.corp.google.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
apic_icr_write() and its users in smpboot.c were apparently
written under the assumption that this code would only run
during early boot. But nowadays we also execute it when onlining
a CPU later on while the system is fully running. That will make
wakeup_cpu_via_init_nmi and, thus, also native_apic_icr_write
run in plain process context. If we migrate the caller to a
different CPU at the wrong time or interrupt it and write to
ICR/ICR2 to send unrelated IPIs, we can end up sending INIT,
SIPI or NMIs to wrong CPUs.
Fix this by disabling interrupts during the write to the ICR
halves and disable preemption around waiting for ICR
availability and using it.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Tested-By: Igor Mammedov <imammedo@redhat.com>
Link: http://lkml.kernel.org/r/52E6AFFE.3030004@siemens.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Commit 028a690a1e "i386: Remove unneeded test of 'task' in
dump_trace()" correctly removed the unneeded 'task != NULL'
check because it would be set to current if it was NULL.
Commit 2bc5f927d4 "i386: split out dumpstack code from
traps_32.c" moved the code from traps_32.c to its own file
dump_stack.c for preparation of the i386 / x86_64 merge.
Commit 8a541665b9 "dumpstack: x86: various small unification
steps" worked to make i386 and x86_64 dump_stack logic similar.
But this actually reverted the correct change from
028a690a1e.
Commit d0caf29250 "x86/dumpstack: Remove unneeded check in
dump_trace()" removed the unneeded "task != NULL" check for
x86_64 but left that same unneeded check for i386, that was
added because x86_64 had it!
This chain of events ironically had i386 add back the unneeded
task != NULL check because x86_64 did it, and then the fix for
x86_64 was fixed by Dan. And even more ironically, it was Dan's
smatch bot that told me that a change to dump_stack_32 I made
may be wrong if current can be NULL (it can't), as there was a
check for it by assigning task to current, and then checking if
task is NULL.
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Acked-by: Alexander van Heukelum <heukelum@fastmail.fm>
Cc: Jesper Juhl <jesper.juhl@gmail.com>
Link: http://lkml.kernel.org/r/20140307105242.79a0befd@gandalf.local.home
Signed-off-by: Ingo Molnar <mingo@kernel.org>
The error path of uncore_type_init() frees up any allocations
that were made along the way, but it relies upon type->pmus
being set, which only happens if the function succeeds. As
type->pmus remains null in this case, the call to
uncore_type_exit will do nothing.
Moving the assignment earlier will allow us to actually free
those allocations should something go awry.
Signed-off-by: Dave Jones <davej@fedoraproject.org>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20140306172028.GA552@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Commit:
411cf180fa perf/x86/uncore: fix initialization of cpumask
introduced the function uncore_cpumask_init(), which is only
called in __init intel_uncore_init(). But it is not marked
with __init, which produces the following warning:
WARNING: vmlinux.o(.text+0x2464a): Section mismatch in reference from the function uncore_cpumask_init() to the function .init.text:uncore_cpu_setup()
The function uncore_cpumask_init() references
the function __init uncore_cpu_setup().
This is often because uncore_cpumask_init lacks a __init
annotation or the annotation of uncore_cpu_setup is wrong.
This patch marks uncore_cpumask_init() with __init.
Signed-off-by: Dongsheng Yang <yangds.fnst@cn.fujitsu.com>
Acked-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Link: http://lkml.kernel.org/r/1394013516-4964-1-git-send-email-yangds.fnst@cn.fujitsu.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
When not running in guest-debug mode (i.e. the guest controls the debug
registers, having to take an exit for each DR access is a waste of time.
If the guest gets into a state where each context switch causes DR to be
saved and restored, this can take away as much as 40% of the execution
time from the guest.
If the guest is running with vcpu->arch.db == vcpu->arch.eff_db, we
can let it write freely to the debug registers and reload them on the
next exit. We still need to exit on the first access, so that the
KVM_DEBUGREG_WONT_EXIT flag is set in switch_db_regs; after that, further
accesses to the debug registers will not cause a vmexit.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Unlike other intercepts, debug register intercepts will be modified
in hot paths if the guest OS is bad or otherwise gets tricked into
doing so.
Avoid calling recalc_intercepts 16 times for debug registers.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
When preparing the VMCS02, the CPU-based execution controls is computed
by vmx_exec_control. Turn off DR access exits there, too, if the
KVM_DEBUGREG_WONT_EXIT bit is set in switch_db_regs.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
When not running in guest-debug mode (i.e. the guest controls the debug
registers, having to take an exit for each DR access is a waste of time.
If the guest gets into a state where each context switch causes DR to be
saved and restored, this can take away as much as 40% of the execution
time from the guest.
If the guest is running with vcpu->arch.db == vcpu->arch.eff_db, we
can let it write freely to the debug registers and reload them on the
next exit. We still need to exit on the first access, so that the
KVM_DEBUGREG_WONT_EXIT flag is set in switch_db_regs; after that, further
accesses to the debug registers will not cause a vmexit.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
When not running in guest-debug mode, the guest controls the debug
registers and having to take an exit for each DR access is a waste
of time. If the guest gets into a state where each context switch
causes DR to be saved and restored, this can take away as much as 40%
of the execution time from the guest.
After this patch, VMX- and SVM-specific code can set a flag in
switch_db_regs, telling vcpu_enter_guest that on the next exit the debug
registers might be dirty and need to be reloaded (syncing will be taken
care of by a new callback in kvm_x86_ops). This flag can be set on the
first access to a debug registers, so that multiple accesses to the
debug registers only cause one vmexit.
Note that since the guest will be able to read debug registers and
enable breakpoints in DR7, we need to ensure that they are synchronized
on entry to the guest---including DR6 that was not synced before.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Currently, this works even if the bit is not in "min", because the bit is always
set in MSR_IA32_VMX_ENTRY_CTLS. Mention it for the sake of documentation, and
to avoid surprises if we later switch to MSR_IA32_VMX_TRUE_ENTRY_CTLS.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
It's no longer possible to enter enable_irq_window in guest mode when
L1 intercepts external interrupts and we are entering L2. This is now
caught in vcpu_enter_guest. So we can remove the check from the VMX
version of enable_irq_window, thus the need to return an error code from
both enable_irq_window and enable_nmi_window.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
According to SDM 27.2.3, IDT vectoring information will not be valid on
vmexits caused by external NMIs. So we have to avoid creating such
scenarios by delaying EXIT_REASON_EXCEPTION_NMI injection as long as we
have a pending interrupt because that one would be migrated to L1's IDT
vectoring info on nested exit.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
We cannot rely on the hardware-provided preemption timer support because
we are holding L2 in HLT outside non-root mode. Furthermore, emulating
the preemption will resolve tick rate errata on older Intel CPUs.
The emulation is based on hrtimer which is started on L2 entry, stopped
on L2 exit and evaluated via the new check_nested_events hook. As we no
longer rely on hardware features, we can enable both the preemption
timer support and value saving unconditionally.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Move the check for leaving L2 on pending and intercepted IRQs or NMIs
from the *_allowed handler into a dedicated callback. Invoke this
callback at the relevant points before KVM checks if IRQs/NMIs can be
injected. The callback has the task to switch from L2 to L1 if needed
and inject the proper vmexit events.
The rework fixes L2 wakeups from HLT and provides the foundation for
preemption timer emulation.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
This patch restores the changes of commit dff38e3e93 "x86: Use inline
assembler instead of global register variable to get sp". They got lost
in commit 198d208df4 "x86: Keep thread_info on thread stack in x86_32"
while moving the code to arch/x86/kernel/irq_32.c.
Quoting Andi from commit dff38e3e93:
"""
LTO in gcc 4.6/47. has trouble with global register variables. They were
used to read the stack pointer. Use a simple inline assembler statement
with a mov instead.
This also helps LLVM/clang, which does not support global register
variables.
"""
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Mathias Krause <minipli@googlemail.com>
Link: http://lkml.kernel.org/r/1394178752-18047-1-git-send-email-minipli@googlemail.com
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
It's an enum, not a #define, you can't use it in asm files.
Introduced in commit 5fa10196bd ("x86: Ignore NMIs that come in during
early boot"), and sadly I didn't compile-test things like I should have
before pushing out.
My weak excuse is that the x86 tree generally doesn't introduce stupid
things like this (and the ARM pull afterwards doesn't cause me to do a
compile-test either, since I don't cross-compile).
Cc: Don Zickus <dzickus@redhat.com>
Cc: H. Peter Anvin <hpa@linux.intel.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Don Zickus reports:
A customer generated an external NMI using their iLO to test kdump
worked. Unfortunately, the machine hung. Disabling the nmi_watchdog
made things work.
I speculated the external NMI fired, caused the machine to panic (as
expected) and the perf NMI from the watchdog came in and was latched.
My guess was this somehow caused the hang.
----
It appears that the latched NMI stays latched until the early page
table generation on 64 bits, which causes exceptions to happen which
end in IRET, which re-enable NMI. Therefore, ignore NMIs that come in
during early execution, until we have proper exception handling.
Reported-and-tested-by: Don Zickus <dzickus@redhat.com>
Link: http://lkml.kernel.org/r/1394221143-29713-1-git-send-email-dzickus@redhat.com
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Cc: <stable@vger.kernel.org> # v3.5+, older with some backport effort
The dump_trace() function in dumpstack_64.c is hard to follow.
The test for exception stack is processed differently than the
test for irq stack, and the normal stack is outside completely.
By restructuring this code to have all the stacks determined by
a single function that returns an enum of the following:
STACK_IS_NORMAL
STACK_IS_EXCEPTION
STACK_IS_IRQ
STACK_IS_UNKNOWN
and has the logic of each within a switch statement.
This should make the code much easier to read and understand.
Link: http://lkml.kernel.org/r/20110806012354.684598995@goodmis.org
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Brian Gerst <brgerst@gmail.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/20140206144322.086050042@goodmis.org
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
x86_64 uses a per_cpu variable kernel_stack to always point to
the thread stack of current. This is where the thread_info is stored
and is accessed from this location even when the irq or exception stack
is in use. This removes the complexity of having to maintain the
thread info on the stack when interrupts are running and having to
copy the preempt_count and other fields to the interrupt stack.
x86_32 uses the old method of copying the thread_info from the thread
stack to the exception stack just before executing the exception.
Having the two different requires #ifdefs and also the x86_32 way
is a bit of a pain to maintain. By converting x86_32 to the same
method of x86_64, we can remove #ifdefs, clean up the x86_32 code
a little, and remove the overhead of the copy.
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Brian Gerst <brgerst@gmail.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/20110806012354.263834829@goodmis.org
Link: http://lkml.kernel.org/r/20140206144321.852942014@goodmis.org
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
The i386 thread_info contains a previous_esp field that is used
to daisy chain the different stacks for dump_stack()
(ie. irq, softirq, thread stacks).
The goal is to eventual make i386 handling of thread_info the same
as x86_64, which means that the thread_info will not be in the stack
but as a per_cpu variable. We will no longer depend on thread_info
being able to daisy chain different stacks as it will only exist
in one location (the thread stack).
By moving previous_esp to the end of thread_info and referencing
it as an offset instead of using a thread_info field, this becomes
a stepping stone to moving the thread_info.
The offset to get to the previous stack is rather ugly in this
patch, but this is only temporary and the prev_esp will be changed
in the next commit. This commit is more for sanity checks of the
change.
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Robert Richter <rric@kernel.org>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/20110806012353.891757693@goodmis.org
Link: http://lkml.kernel.org/r/20140206144321.608754481@goodmis.org
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
According to a git log -p, GET_THREAD_INFO_WITH_ESP() has only been defined
and never been used. Get rid of it.
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/20140206144321.409045251@goodmis.org
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Nothing references the supervisor_stack in the thread_info field,
and it does not exist in x86_64. To make the two more the same,
it is being removed.
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Brian Gerst <brgerst@gmail.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/20110806012353.546183789@goodmis.org
Link: http://lkml.kernel.org/r/20140206144321.203619611@goodmis.org
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Building on commit 0ac09f9f8c ("x86, trace: Fix CR2 corruption when
tracing page faults") this patch addresses another few issues:
- Now that read_cr2() is lifted into trace_do_page_fault(), we should
pass the address to trace_page_fault_entries() to avoid it
re-reading a potentially changed cr2.
- Put both trace_do_page_fault() and trace_page_fault_entries() under
CONFIG_TRACING.
- Mark both fault entry functions {,trace_}do_page_fault() as notrace
to avoid getting __mcount or other function entry trace callbacks
before we've observed CR2.
- Mark __do_page_fault() as noinline to guarantee the function tracer
does get to see the fault.
Cc: <jolsa@redhat.com>
Cc: <vincent.weaver@maine.edu>
Acked-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20140306145300.GO9987@twins.programming.kicks-ass.net
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
The preadv64/pwrite64 have been implemented for the x32 ABI, in order
to allow passing 64 bit arguments from user space without splitting
them into two 32 bit parameters, like it would be necessary for usual
compat tasks.
Howevert these two system calls are only being used for the x32 ABI,
so add __ARCH_WANT_COMPAT defines for these two compat syscalls and
make these two only visible for x86.
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Only CF9_COND is appropriate for inclusion in the default chain, not
CF9; the latter will poke that register unconditionally, whereas
CF9_COND will at least look for PCI configuration method #1 or #2
first (a weak check, but better than nothing.)
CF9 should be used for explicit system configuration (command line or
DMI) only.
Cc: Aubrey Li <aubrey.li@intel.com>
Cc: Matthew Garrett <mjg59@srcf.ucam.org>
Link: http://lkml.kernel.org/r/53130A46.1010801@linux.intel.com
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Reboot is the last service linux OS provides to the end user. We are
supposed to make this function more robust than today. This patch adds
all of the known reboot methods into the default attempt list. The
machines requiring reboot=efi or reboot=p or reboot=bios get a chance
to reboot automatically now.
If there is a new reboot method emerged, we are supposed to add it to
the default list as well, instead of adding the endless dmidecode entry.
If one method required is in the default list in this patch but the
machine reboot still hangs, that means some methods ahead of the
required method cause the system hangs, then reboot the machine by
passing reboot= arguments and submit the reboot dmidecode table quirk.
We are supposed to remove the reboot dmidecode table from the kernel,
but to be safe, we keep it. This patch prevents us from adding more.
If you happened to have a machine listed in the reboot dmidecode
table and this patch makes reboot work on your machine, please submit
a patch to remove the quirk.
The default reboot order with this patch is now:
ACPI > KBD > ACPI > KBD > EFI > CF9_COND > BIOS
Because BIOS and TRIPLE are mutually exclusive (either will either
work or hang the machine) that method is not included.
[ hpa: as with any changes to the reboot order, this patch will have
to be monitored carefully for regressions. ]
Signed-off-by: Aubrey Li <aubrey.li@intel.com>
Acked-by: Matthew Garrett <mjg59@srcf.ucam.org>
Link: http://lkml.kernel.org/r/53130A46.1010801@linux.intel.com
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Compiling last minute changes without setting the proper config
options is not really clever.
Reported-by: Fengguang Wu <fengguang.wu@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
The kbuild test robot reported the following errors, introduced with
commit 54b52d8726 ("x86/efi: Build our own EFI services pointer
table"),
arch/x86/boot/compressed/head_32.o: In function `efi32_config':
>> (.data+0x58): undefined reference to `efi_call_phys'
arch/x86/boot/compressed/head_64.o: In function `efi64_config':
>> (.data+0x90): undefined reference to `efi_call6'
Wrap the efi*_config structures in #ifdef CONFIG_EFI_STUB so that we
don't make references to EFI functions if they're not compiled in.
Signed-off-by: Matt Fleming <matt.fleming@intel.com>
Andy Lutomirski