Vivek Goyal [Thu, 7 Dec 2006 01:14:10 +0000 (02:14 +0100)]
[PATCH] relocatable kernel: Fix kallsyms on avr32 after relocatable kernel changes
o On some platforms like avr32, section init comes before .text and
not necessarily a symbol's relative position w.r.t _text is positive.
In such cases assembler detects the overflow and emits warning. This
patch fixes it.
Jan Beulich [Thu, 7 Dec 2006 01:14:09 +0000 (02:14 +0100)]
[PATCH] i386: fix MTRR code
Until not so long ago, there were system log messages pointing to
inconsistent MTRR setup of the video frame buffer caused by the way vesafb
and X worked. While vesafb was fixed meanwhile, I believe fixing it there
only hides a shortcoming in the MTRR code itself, in that that code is not
symmetric with respect to the ordering of attempts to set up two (or more)
regions where one contains the other. In the current shape, it permits
only setting up sub-regions of pre-exisiting ones. The patch below makes
this symmetric.
While working on that I noticed a few more inconsistencies in that code,
namely
- use of 'unsigned int' for sizes in many, but not all places (the patch
is converting this to use 'unsigned long' everywhere, which specifically
might be necessary for x86-64 once a processor supporting more than 44
physical address bits would become available)
- the code to correct inconsistent settings during secondary processor
startup tried (if necessary) to correct, among other things, the value
in IA32_MTRR_DEF_TYPE, however the newly computed value would never get
used (i.e. stored in the respective MSR)
- the generic range validation code checked that the end of the
to-be-added range would be above 1MB; the value checked should have been
the start of the range
- when contained regions are detected, previously this was allowed only
when the old region was uncacheable; this can be symmetric (i.e. the new
region can also be uncacheable) and even further as per Intel's
documentation write-trough and write-back for either region is also
compatible with the respective opposite in the other
Signed-off-by: Jan Beulich <jbeulich@novell.com> Signed-off-by: Andi Kleen <ak@suse.de>
Jan Beulich [Thu, 7 Dec 2006 01:14:09 +0000 (02:14 +0100)]
[PATCH] i386: clear_fixmap() should not use set_pte()
While not strictly required with the current code (as the upper half of
page table entries generated by __set_fixmap() cannot be non-zero due
to the second parameter of this function being 'unsigned long'), the
use of set_pte() in __set_fixmap() in the context of clear_fixmap() is
still improper with CONFIG_X86_PAE (see the respective comment in
include/asm-i386/pgtable-3level.h) and would turn into a bug if that
second parameter ever gets changed to a 64-bit type.
Signed-off-by: Jan Beulich <jbeulich@novell.com> Signed-off-by: Andi Kleen <ak@suse.de>
Ernie Petrides [Thu, 7 Dec 2006 01:14:09 +0000 (02:14 +0100)]
[PATCH] x86-64: fix perms/range of vsyscall vma in /proc/*/maps
The final line of /proc/<pid>/maps on x86_64 for native 64-bit
tasks shows an incorrect ending address and incorrect permissions. There
is only a single page mapped in this vsyscall region, and it is accessible
for both read and execute.
The patch below fixes this. (Since 32-bit-compat tasks have a real vma
with correct perms/range, no change is necessary for that scenario.)
Before the patch, a "cat /proc/self/maps | tail -1" shows this:
Andi Kleen [Thu, 7 Dec 2006 01:14:09 +0000 (02:14 +0100)]
[PATCH] x86-64: Add option to compile for Core2
Add an option to compile for Intel's Core 2
The Kconfig help is a mouthful due to the inventiveness of Intel's
product naming department.
Mainly for the 64bit cache line sizes because gcc doesn't support
optimizing for core2 yet. However it will and then the kernel
should be ready by passing the right option
Also fix the old MPSC help text to confirm better to reality.
Zachary Amsden [Thu, 7 Dec 2006 01:14:09 +0000 (02:14 +0100)]
[PATCH] paravirt: Add option to allow skipping the timer check
Add a way to disable the timer IRQ routing check via a boot option. The
VMI timer code uses this to avoid triggering the pester Mingo code, which
probes for some very unusual and broken motherboard routings. It fires
100% of the time when using a paravirtual delay mechanism instead of using
a realtime delay, since there is no elapsed real time, and the 4 timer IRQs
have not yet been delivered.
In addition, it is entirely possible, though improbable, that this bug
could surface on real hardware which picks a particularly bad time to enter
SMM mode, causing a long latency during one of the timer IRQs.
While here, make check_timer be __init.
Signed-off-by: Zachary Amsden <zach@vmware.com> Signed-off-by: Andi Kleen <ak@suse.de>
[chrisw: use no_timer_check to bring inline with x86_64 as per Andi's request] Signed-off-by: Chris Wright <chrisw@sous-sol.org> Cc: Andi Kleen <ak@suse.de> Signed-off-by: Andrew Morton <akpm@osdl.org>
Zachary Amsden [Thu, 7 Dec 2006 01:14:09 +0000 (02:14 +0100)]
[PATCH] paravirt: fix missing pte update
The function ptep_get_and_clear uses an atomic instruction sequence to get and
clear an active pte. Rather than add such an atomic operator to all virtual
machine implementations in paravirt-ops, it is easier to support the raw
atomic sequence and use either a trapping writable pagetable approach, or a
post-update notification. For the post update notification, we require the
pte_update function to be called after the access. Combine the 2-level and
3-level paging operators into one common function which does the post-update
notification, and rename the actual atomic sequences to raw_ptep_xxx
operators.
Signed-off-by: Zachary Amsden <zach@vmware.com> Signed-off-by: Andi Kleen <ak@suse.de> Cc: Andi Kleen <ak@muc.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Chris Wright <chrisw@sous-sol.org> Signed-off-by: Andrew Morton <akpm@osdl.org>
Zachary Amsden [Thu, 7 Dec 2006 01:14:08 +0000 (02:14 +0100)]
[PATCH] paravirt: Preparatory mmu header movement
Move header includes for the nopud / nopmd types to the location of the actual
pte / pgd type definitions. This allows generic 4-level page type code to be
written before the split 2/3 level page table headers are included.
Signed-off-by: Zachary Amsden <zach@vmware.com> Signed-off-by: Andi Kleen <ak@suse.de> Cc: Andi Kleen <ak@muc.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Chris Wright <chrisw@sous-sol.org> Signed-off-by: Andrew Morton <akpm@osdl.org>
Rusty Russell [Thu, 7 Dec 2006 01:14:08 +0000 (02:14 +0100)]
[PATCH] paravirt: Add MMU virtualization to paravirt_ops
Add the three bare TLB accessor functions to paravirt-ops. Most amusingly,
flush_tlb is redefined on SMP, so I can't call the paravirt op flush_tlb.
Instead, I chose to indicate the actual flush type, kernel (global) vs. user
(non-global). Global in this sense means using the global bit in the page
table entry, which makes TLB entries persistent across CR3 reloads, not
global as in the SMP sense of invoking remote shootdowns, so the term is
confusingly overloaded.
AK: folded in fix from Zach for PAE compilation
Signed-off-by: Zachary Amsden <zach@vmware.com> Signed-off-by: Chris Wright <chrisw@sous-sol.org> Signed-off-by: Andi Kleen <ak@suse.de> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Signed-off-by: Andrew Morton <akpm@osdl.org>
Rusty Russell [Thu, 7 Dec 2006 01:14:08 +0000 (02:14 +0100)]
[PATCH] paravirt: Add APIC accessors to paravirt-ops.
Add APIC accessors to paravirt-ops. Unfortunately, we need two write
functions, as some older broken hardware requires workarounds for
Pentium APIC errata - this is the purpose of apic_write_atomic.
AK: replaced __inline with inline
Signed-off-by: Zachary Amsden <zach@vmware.com> Signed-off-by: Chris Wright <chrisw@sous-sol.org> Signed-off-by: Andi Kleen <ak@suse.de> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Signed-off-by: Andrew Morton <akpm@osdl.org>
Rusty Russell [Thu, 7 Dec 2006 01:14:08 +0000 (02:14 +0100)]
[PATCH] paravirt: Allow disable power management under hypervisor
Two legacy power management modes are much easier to just explicitly disable
when running in paravirtualized mode - neither APM nor PnP is still relevant.
The status of ACPI is still debatable, and noacpi is still a common enough
boot parameter that it is not necessary to explicitly disable ACPI.
Signed-off-by: Zachary Amsden <zach@vmware.com> Signed-off-by: Chris Wright <chrisw@sous-sol.org> Signed-off-by: Andi Kleen <ak@suse.de> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Signed-off-by: Andrew Morton <akpm@osdl.org>
Rusty Russell [Thu, 7 Dec 2006 01:14:08 +0000 (02:14 +0100)]
[PATCH] paravirt: Allow selected bug checks to be
Allow selected bug checks to be skipped by paravirt kernels. The two most
important are the F00F workaround (which is either done by the hypervisor,
or not required), and the 'hlt' instruction check, which can break under
some hypervisors.
Signed-off-by: Zachary Amsden <zach@vmware.com> Signed-off-by: Chris Wright <chrisw@sous-sol.org> Signed-off-by: Andi Kleen <ak@suse.de> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Signed-off-by: Andrew Morton <akpm@osdl.org>
Rusty Russell [Thu, 7 Dec 2006 01:14:08 +0000 (02:14 +0100)]
[PATCH] paravirt: Patch inline replacements for paravirt intercepts
It turns out that the most called ops, by several orders of magnitude,
are the interrupt manipulation ops. These are obvious candidates for
patching, so mark them up and create infrastructure for it.
The method used is that the ops structure has a patch function, which
is called for each place which needs to be patched: this returns a
number of instructions (the rest are NOP-padded).
Usually we can spare a register (%eax) for the binary patched code to
use, but in a couple of critical places in entry.S we can't: we make
the clobbers explicit at the call site, and manually clobber the
allowed registers in debug mode as an extra check.
Rusty Russell [Thu, 7 Dec 2006 01:14:07 +0000 (02:14 +0100)]
[PATCH] paravirt: header and stubs for paravirtualisation
Create a paravirt.h header for all the critical operations which need to be
replaced with hypervisor calls, and include that instead of defining native
operations, when CONFIG_PARAVIRT.
This patch does the dumbest possible replacement of paravirtualized
instructions: calls through a "paravirt_ops" structure. Currently these are
function implementations of native hardware: hypervisors will override the ops
structure with their own variants.
All the pv-ops functions are declared "fastcall" so that a specific
register-based ABI is used, to make inlining assember easier.
And:
+From: Andy Whitcroft <apw@shadowen.org>
The paravirt ops introduce a 'weak' attribute onto memory_setup().
Code ordering leads to the following warnings on x86:
arch/i386/kernel/setup.c:651: warning: weak declaration of
`memory_setup' after first use results in unspecified behavior
Move memory_setup() to avoid this.
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au> Signed-off-by: Chris Wright <chrisw@sous-sol.org> Signed-off-by: Andi Kleen <ak@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Zachary Amsden <zach@vmware.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Andy Whitcroft <apw@shadowen.org>
[PATCH] x86-64: Make x86_64 udelay() round up instead of down.
Port two patches from i386 to x86_64 delay.c to make sure all rounding is done
upward instead of downward.
There is no sign in commit messages that the mismatch was done on purpose, and
"delay() guarantees sleeping at least for the specified time" is still a valid
rule IMHO.
The original x86 patches are both from pre-GIT era, i.e.:
Muli Ben-Yehuda [Thu, 7 Dec 2006 01:14:06 +0000 (02:14 +0100)]
[PATCH] Calgary: check BBAR ioremap success when ioremapping
This patch cleans up the previous "Use BIOS supplied BBAR information"
patch. Mostly stylistic clenaups, but also check for ioremap failure
when we ioremap the BBAR rather than when trying to use it.
Laurent Vivier [Thu, 7 Dec 2006 01:14:06 +0000 (02:14 +0100)]
[PATCH] Calgary: use BIOS supplied BBARs and topology information
Find the BBAR register address of each Calgary using the "Extended
BIOS Data Area" rather than calculating it ourselves. Also get the bus
topology (what PHB each bus is on) from Calgary rather than
calculating it ourselves.
This patch fixes http://bugzilla.kernel.org/show_bug.cgi?id=7407.
bibo,mao [Thu, 7 Dec 2006 01:14:06 +0000 (02:14 +0100)]
[PATCH] i386: Move memory map printing and other code to e820.c
This patch moves e820 memory map print and memmap boot param
parsing function from setup.c to e820.c, also adds limit_regions
and print_memory_map declaration in header file.
bibo,mao [Thu, 7 Dec 2006 01:14:06 +0000 (02:14 +0100)]
[PATCH] i386: i386 create e820.c to handle standard io/mem resources
This patch creates new file named e820.c to hanle standard io/mem
resources, moving request_standard_resources function from setup.c
to e820.c. Also this patch modifies Makfile to compile file e820.c.
Albert Cahalan [Thu, 7 Dec 2006 01:14:06 +0000 (02:14 +0100)]
[PATCH] x86-64: Support -mregparm arguments for signals with SA_SIGINFO in compat mode
The recent change to make x86_64 support i386 binaries compiled
with -mregparm=3 only covered signal handlers without SA_SIGINFO.
(the 3-arg "real-time" ones)
To be compatible with i386, both types should be supported.
Signed-off-by: Albert Cahalan <acahalan@gmail.com> Signed-off-by: Andi Kleen <ak@suse.de>
Andi Kleen [Thu, 7 Dec 2006 01:14:06 +0000 (02:14 +0100)]
[PATCH] x86-64: Try multiple timer variants in check_timer
Instead of adding all kinds of more quirks try various timer
routing variants in check_timer.
In particular this tries to handle quirks from:
- Nvidia NF2-4 reference BIOS: wrong timer override
- Asus: Wrong timer override but no HPET table
- ATI: require timer disabled in 8259
- Some boards: require timer enabled in 8259
We just try many of the the known variants in the hopefully right order
in check_timer.
Andi Kleen [Thu, 7 Dec 2006 01:14:06 +0000 (02:14 +0100)]
[PATCH] i386: Use probe_kernel_address instead of __get_user in fault paths
Makes the intention of the code cleaner to read and avoids
a potential deadlock on mmap_sem. Also change the types of
the arguments to not include __user because they're really
not user addresses.
Yinghai Lu [Thu, 7 Dec 2006 01:14:05 +0000 (02:14 +0100)]
[PATCH] x86-64: Extend clear_irq_vector
Clear the irq releated entries in irq_vector, irq_domain and vector_irq
instead of clearing irq_vector only. So when new irq is created, it
could reuse that vector. (actually is the second loop scanning from
FIRST_DEVICE_VECTOR+8). This could avoid the vectors are used up
with enough module inserting and removing
Cc: Eric W. Biedierman <ebiederm@xmission.com> Cc: Muli Ben-Yehuda <muli@il.ibm.com> Signed-off-By: Yinghai Lu <yinghai.lu@amd.com> Signed-off-by: Andi Kleen <ak@suse.de>
Vivek Goyal [Thu, 7 Dec 2006 01:14:04 +0000 (02:14 +0100)]
[PATCH] i386: extend bzImage protocol for relocatable protected mode kernel
Extend bzImage protocol to enable bootloaders to load a completely relocatable
bzImage. Now protected mode component of kernel is also relocatable and a
boot-loader can load the protected mode component at a differnt physical
address than 1MB. (If kernel was built with CONFIG_RELOCATABLE)
Kexec can make use of it to load this kernel at a different physical address
to capture kernel crash dumps.
Vivek Goyal [Thu, 7 Dec 2006 01:14:04 +0000 (02:14 +0100)]
[PATCH] i386: Implement CONFIG_PHYSICAL_ALIGN
o Now CONFIG_PHYSICAL_START is being replaced with CONFIG_PHYSICAL_ALIGN.
Hardcoding the kernel physical start value creates a problem in relocatable
kernel context due to boot loader limitations. For ex, if somebody
compiles a relocatable kernel to be run from address 4MB, but this kernel
will run from location 1MB as grub loads the kernel at physical address
1MB. Kernel thinks that I am a relocatable kernel and I should run from
the address I have been loaded at. So somebody wanting to run kernel
from 4MB alignment location (for improved performance regions) can't do
that.
o Hence, Eric proposed that probably CONFIG_PHYSICAL_ALIGN will make
more sense in relocatable kernel context. At run time kernel will move
itself to a physical addr location which meets user specified alignment
restrictions.
Vivek Goyal [Thu, 7 Dec 2006 01:14:04 +0000 (02:14 +0100)]
[PATCH] i386: Warn upon absolute relocations being present
o Relocations generated w.r.t absolute symbols are not processed as by
definition, absolute symbols are not to be relocated. Explicitly warn
user about absolutions relocations present at compile time.
o These relocations get introduced either due to linker optimizations or
some programming oversights.
o Also create a list of symbols which have been audited to be safe and
don't emit warnings for these.
This patch modifies the i386 kernel so that if CONFIG_RELOCATABLE is
selected it will be able to be loaded at any 4K aligned address below
1G. The technique used is to compile the decompressor with -fPIC and
modify it so the decompressor is fully relocatable. For the main
kernel relocations are generated. Resulting in a kernel that is relocatable
with no runtime overhead and no need to modify the source code.
A reserved 32bit word in the parameters has been assigned
to serve as a stack so we figure out where are running.
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Signed-off-by: Vivek Goyal <vgoyal@in.ibm.com> Signed-off-by: Andi Kleen <ak@suse.de>
Print the addresses of non-absolute symbols relative to _text
so that ld will generate relocations. Allowing a relocatable
kernel to relocate them. We can't actually use the symbol names
because kallsyms includes static symbols that are not exported
from their object files.
Add the _text symbol definitions to the architectures which don't
define it otherwise linker will fail.
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Signed-off-by: Vivek Goyal <vgoyal@in.ibm.com> Signed-off-by: Andi Kleen <ak@suse.de>
Defining __PHYSICAL_START and __KERNEL_START in asm-i386/page.h works but
it triggers a full kernel rebuild for the silliest of reasons. This
modifies the users to directly use CONFIG_PHYSICAL_START and linux/config.h
which prevents the full rebuild problem, which makes the code much
more maintainer and hopefully user friendly.
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Signed-off-by: Vivek Goyal <vgoyal@in.ibm.com> Signed-off-by: Andi Kleen <ak@suse.de>
[PATCH] i386: Reserve kernel memory starting from _text
Currently when we are reserving the memory the kernel text
resides in we start at __PHYSICAL_START which happens to be
correct but not very obvious. In addition when we start relocating
the kernel __PHYSICAL_START is the wrong value, as it is an
absolute symbol that does not get relocated.
By starting the reservation at __pa_symbol(_text)
the code is clearer and will be correct when relocated.
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Signed-off-by: Vivek Goyal <vgoyal@in.ibm.com> Signed-off-by: Andi Kleen <ak@suse.de>
On x86_64 we have to be careful with calculating the physical
address of kernel symbols. Both because of compiler odditities
and because the symbols live in a different range of the virtual
address space.
Having a defintition of __pa_symbol that works on both x86_64 and
i386 simplifies writing code that works for both x86_64 and
i386 that has these kinds of dependencies.
So this patch adds the trivial i386 __pa_symbol definition.
Added assembly magic similar to RELOC_HIDE as suggested by Andi Kleen.
Just picked it up from x86_64.
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Signed-off-by: Vivek Goyal <vgoyal@in.ibm.com> Signed-off-by: Andi Kleen <ak@suse.de>
Vivek Goyal [Thu, 7 Dec 2006 01:14:03 +0000 (02:14 +0100)]
[PATCH] i386: Distinguish absolute symbols
Ld knows about 2 kinds of symbols, absolute and section
relative. Section relative symbols symbols change value
when a section is moved and absolute symbols do not.
Currently in the linker script we have several labels
marking the beginning and ending of sections that
are outside of sections, making them absolute symbols.
Having a mixture of absolute and section relative
symbols refereing to the same data is currently harmless
but it is confusing.
This must be done carefully as newer revs of ld do not place
symbols that appear in sections without data and instead
ld makes those symbols global :(
My ultimate goal is to build a relocatable kernel. The
safest and least intrusive technique is to generate
relocation entries so the kernel can be relocated at load
time. The only penalty would be an increase in the size
of the kernel binary. The problem is that if absolute and
relocatable symbols are not properly specified absolute symbols
will be relocated or section relative symbols won't be, which
is fatal.
The practical motivation is that when generating kernels that
will run from a reserved area for analyzing what caused
a kernel panic, it is simpler if you don't need to hard code
the physical memory location they will run at, especially
for the distributions.
[AK: and merged:]
o Also put a message so that in future people can be aware of it and
avoid introducing absolute symbols.
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Signed-off-by: Vivek Goyal <vgoyal@in.ibm.com> Signed-off-by: Andi Kleen <ak@suse.de>
Andi Kleen [Thu, 7 Dec 2006 01:14:03 +0000 (02:14 +0100)]
[PATCH] x86: Don't use nested idle loops
Currently the idle loop has two nested loops -- one high level
in cpu_idle and in some low level idle functions another one.
Looping in the low level idle functions breaks the idle notifiers
because interrupts waking up sleep states need to execute
exit_idle() which is only in cpu_idle().
So don't do that, only loop in cpu_idle(). This only removes
code.
In some cases e.g. poll_idle the idle loop is a little longer
now because cpu_idle checks more things. I hope that isn't a problem
ACPI idle doesn't change behaviour because it never looped anyways.
[PATCH] i386: Implement smp_processor_id() with the PDA
Use the cpu_number in the PDA to implement raw_smp_processor_id. This is a
little simpler than using thread_info, though the cpu field in thread_info
cannot be removed since it is used for things other than getting the current
CPU in common code.
Signed-off-by: Jeremy Fitzhardinge <jeremy@xensource.com> Signed-off-by: Andi Kleen <ak@suse.de> Cc: Chuck Ebbert <76306.1226@compuserve.com> Cc: Zachary Amsden <zach@vmware.com> Cc: Jan Beulich <jbeulich@novell.com> Cc: Andi Kleen <ak@suse.de> Signed-off-by: Andrew Morton <akpm@osdl.org>
[PATCH] i386: Update sys_vm86 to cope with changed pt_regs and %gs usage
sys_vm86 uses a struct kernel_vm86_regs, which is identical to pt_regs, but
adds an extra space for all the segment registers. Previously this structure
was completely independent, so changes in pt_regs had to be reflected in
kernel_vm86_regs. This changes just embeds pt_regs in kernel_vm86_regs, and
makes the appropriate changes to vm86.c to deal with the new naming.
Also, since %gs is dealt with differently in the kernel, this change adjusts
vm86.c to reflect this.
While making these changes, I also cleaned up some frankly bizarre code which
was added when auditing was added to sys_vm86.
Signed-off-by: Jeremy Fitzhardinge <jeremy@xensource.com> Signed-off-by: Andi Kleen <ak@suse.de> Cc: Chuck Ebbert <76306.1226@compuserve.com> Cc: Zachary Amsden <zach@vmware.com> Cc: Jan Beulich <jbeulich@novell.com> Cc: Andi Kleen <ak@suse.de> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Jason Baron <jbaron@redhat.com> Cc: Chris Wright <chrisw@sous-sol.org> Signed-off-by: Andrew Morton <akpm@osdl.org>
[PATCH] i386: Fix places where using %gs changes the usermode ABI
There are a few places where the change in struct pt_regs and the use of %gs
affect the userspace ABI. These are primarily debugging interfaces where
thread state can be inspected or extracted.
Signed-off-by: Jeremy Fitzhardinge <jeremy@xensource.com> Signed-off-by: Andi Kleen <ak@suse.de> Cc: Chuck Ebbert <76306.1226@compuserve.com> Cc: Zachary Amsden <zach@vmware.com> Cc: Jan Beulich <jbeulich@novell.com> Cc: Andi Kleen <ak@suse.de> Signed-off-by: Andrew Morton <akpm@osdl.org>
[PATCH] i386: Use %gs as the PDA base-segment in the kernel
This patch is the meat of the PDA change. This patch makes several related
changes:
1: Most significantly, %gs is now used in the kernel. This means that on
entry, the old value of %gs is saved away, and it is reloaded with
__KERNEL_PDA.
2: entry.S constructs the stack in the shape of struct pt_regs, and this
is passed around the kernel so that the process's saved register
state can be accessed.
Unfortunately struct pt_regs doesn't currently have space for %gs
(or %fs). This patch extends pt_regs to add space for gs (no space
is allocated for %fs, since it won't be used, and it would just
complicate the code in entry.S to work around the space).
3: Because %gs is now saved on the stack like %ds, %es and the integer
registers, there are a number of places where it no longer needs to
be handled specially; namely context switch, and saving/restoring the
register state in a signal context.
4: And since kernel threads run in kernel space and call normal kernel
code, they need to be created with their %gs == __KERNEL_PDA.
Signed-off-by: Jeremy Fitzhardinge <jeremy@xensource.com> Signed-off-by: Andi Kleen <ak@suse.de> Cc: Chuck Ebbert <76306.1226@compuserve.com> Cc: Zachary Amsden <zach@vmware.com> Cc: Jan Beulich <jbeulich@novell.com> Cc: Andi Kleen <ak@suse.de> Signed-off-by: Andrew Morton <akpm@osdl.org>
When a CPU is brought up, a PDA and GDT are allocated for it. The GDT's
__KERNEL_PDA entry is pointed to the allocated PDA memory, so that all
references using this segment descriptor will refer to the PDA.
This patch rearranges CPU initialization a bit, so that the GDT/PDA are set up
as early as possible in cpu_init(). Also for secondary CPUs, GDT+PDA are
preallocated and initialized so all the secondary CPU needs to do is set up
the ldt and load %gs. This will be important once smp_processor_id() and
current use the PDA.
In all cases, the PDA is set up in head.S, before a CPU starts running C code,
so the PDA is always available.
Signed-off-by: Jeremy Fitzhardinge <jeremy@xensource.com> Signed-off-by: Andi Kleen <ak@suse.de> Cc: Chuck Ebbert <76306.1226@compuserve.com> Cc: Zachary Amsden <zach@vmware.com> Cc: Jan Beulich <jbeulich@novell.com> Cc: Andi Kleen <ak@suse.de> Cc: James Bottomley <James.Bottomley@SteelEye.com> Cc: Matt Tolentino <matthew.e.tolentino@intel.com> Signed-off-by: Andrew Morton <akpm@osdl.org>
This patch has the basic definitions of struct i386_pda, and the segment
selector in the GDT.
asm-i386/pda.h is more or less a direct copy of asm-x86_64/pda.h. The most
interesting difference is the use of _proxy_pda, which is used to give gcc a
model for the actual memory operations on the real pda structure. No actual
reference is ever made to _proxy_pda, so it is never defined.
Signed-off-by: Jeremy Fitzhardinge <jeremy@xensource.com> Signed-off-by: Andi Kleen <ak@suse.de> Cc: Chuck Ebbert <76306.1226@compuserve.com> Cc: Zachary Amsden <zach@vmware.com> Cc: Jan Beulich <jbeulich@novell.com> Cc: Andi Kleen <ak@suse.de> Signed-off-by: Andrew Morton <akpm@osdl.org>
[PATCH] i386: Use asm-offsets for the offsets of registers into the pt_regs struct
Use asm-offsets for the offsets of registers into the pt_regs struct, rather
than having hard-coded constants
I left the constants in the comments of entry.S because they're useful for
reference; the code in entry.S is very dependent on the layout of pt_regs,
even when using asm-offsets.
Signed-off-by: Jeremy Fitzhardinge <jeremy@xensource.com> Signed-off-by: Andi Kleen <ak@suse.de> Cc: Keith Owens <kaos@ocs.com.au> Signed-off-by: Andrew Morton <akpm@osdl.org>
Jan Beulich [Thu, 7 Dec 2006 01:14:02 +0000 (02:14 +0100)]
[PATCH] x86-64: miscellaneous entry.S adjustments
This patch:
- makes ret_from_sys_call no longer global (all external users were
previously switched to use int_ret_from_sys_call)
- adjusts placement of a CFI_{REMEMBER,RESTORE}_STATE pair to better
fit logic flow
- eliminates an unnecessary pair of CFI_{REMEMBER,RESTORE}_STATE
- glues together function- and unwinder-wise the previously separate
system_call and int_ret_from_sys_call function fragments
Signed-off-by: Jan Beulich <jbeulich@novell.com> Signed-off-by: Andi Kleen <ak@suse.de>
- add Intel Precise-Event Based sampling (PEBS) related MSR
- add Intel Data Save (DS) Area related MSR
- add Intel Core microarchitecure performance counter MSRs
[PATCH] x86-64: x86-64 add Intel Core related PMU MSRs definitions
Add o the x86-64 tree a bunch of MSRs related to performance
monitoring for the processors based on Intel Core microarchitecture.
It also adds some architectural MSRs for PEBS. A similar patch for i386 will
follow.
changelog:
- add Intel Precise-Event Based sampling (PEBS) related MSR
- add Intel Data Save (DS) Area related MSR
- add Intel Core microarchitecure performance counter MSRs
Aaron Durbin [Thu, 7 Dec 2006 01:14:01 +0000 (02:14 +0100)]
[PATCH] x86-64: Insert Local and IO APIC(s) into resource map
Insert the Local APIC and IO APIC(s) into the resource tree. It allows the
APIC resources to be visible within /proc/iomem. The patch also takes into
account IO APIC(s) mapped in the PCI space by deferring the insertion until
after PCI has allocated its necessary resources.
Chuck Ebbert [Thu, 7 Dec 2006 01:14:01 +0000 (02:14 +0100)]
[PATCH] i386: add sleazy FPU optimization
i386 port of the sLeAZY-fpu feature. Chuck reports that this gives him a +/-
0.4% improvement on his simple benchmark
x86_64 description follows:
Right now the kernel on x86-64 has a 100% lazy fpu behavior: after *every*
context switch a trap is taken for the first FPU use to restore the FPU
context lazily. This is of course great for applications that have very
sporadic or no FPU use (since then you avoid doing the expensive save/restore
all the time). However for very frequent FPU users... you take an extra trap
every context switch.
The patch below adds a simple heuristic to this code: After 5 consecutive
context switches of FPU use, the lazy behavior is disabled and the context
gets restored every context switch. If the app indeed uses the FPU, the trap
is avoided. (the chance of the 6th time slice using FPU after the previous 5
having done so are quite high obviously).
After 256 switches, this is reset and lazy behavior is returned (until there
are 5 consecutive ones again). The reason for this is to give apps that do
longer bursts of FPU use still the lazy behavior back after some time.
Signed-off-by: Chuck Ebbert <76306.1226@compuserve.com> Signed-off-by: Arjan van de Ven <arjan@linux.intel.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Andi Kleen <ak@suse.de>
Stas Sergeev [Thu, 7 Dec 2006 01:14:01 +0000 (02:14 +0100)]
[PATCH] i386: espfix cleanup
Clean up the espfix code:
- Introduced PER_CPU() macro to be used from asm
- Introduced GET_DESC_BASE() macro to be used from asm
- Rewrote the fixup code in asm, as calling a C code with the altered %ss
appeared to be unsafe
- No longer altering the stack from a .fixup section
- 16bit per-cpu stack is no longer used, instead the stack segment base
is patched the way so that the high word of the kernel and user %esp
are the same.
- Added the limit-patching for the espfix segment. (Chuck Ebbert)
[jeremy@goop.org: use the x86 scaling addressing mode rather than shifting] Signed-off-by: Stas Sergeev <stsp@aknet.ru> Signed-off-by: Andi Kleen <ak@suse.de> Acked-by: Zachary Amsden <zach@vmware.com> Acked-by: Chuck Ebbert <76306.1226@compuserve.com> Acked-by: Jan Beulich <jbeulich@novell.com> Cc: Andi Kleen <ak@muc.de> Signed-off-by: Jeremy Fitzhardinge <jeremy@goop.org> Signed-off-by: Andrew Morton <akpm@osdl.org>
[PATCH] i386: remove default_ldt, and simplify ldt-setting.
This patch removes the default_ldt[] array, as it has been unused since
iBCS stopped being supported. This means it is now possible to actually
set an empty LDT segment.
In order to deal with this, the set_ldt_desc/load_LDT pair has been
replaced with a single set_ldt() operation which is responsible for both
setting up the LDT descriptor in the GDT, and reloading the LDT register.
If there are no LDT entries, the LDT register is loaded with a NULL
descriptor.
Signed-off-by: Jeremy Fitzhardinge <jeremy@xensource.com> Signed-off-by: Andi Kleen <ak@suse.de> Cc: Andi Kleen <ak@suse.de> Acked-by: Zachary Amsden <zach@vmware.com> Signed-off-by: Andrew Morton <akpm@osdl.org>
[PATCH] i386: i386 add X86_FEATURE_PEBS and detection
Here is a patch (used by perfmon2) to detect the presence of the Precise Event
Based Sampling (PEBS) feature for i386. The patch also adds the cpu_has_pebs
macro.
[PATCH] i386: i386 rename X86_FEATURE_DTES to X86_FEATURE_DS
Here is a patch (used by perfmon2) that renames X86_FEATURE_DTES to
X86_FEATURE_DS to match Intel's documentation for the Debug Store save area on
i386. The patch also adds cpu_has_ds.
- rename X86_FEATURE_DTES to X86_FEATURE_DS to match documentation
[PATCH] x86-64: add X86_FEATURE_PEBS and detection
Here is a patch (used by perfmon2) to detect the presence of the
Precise Event Based Sampling (PEBS) feature for Intel 64-bit processors.
The patch also adds the cpu_has_pebs macro.
changelog:
- adds X86_FEATURE_PEBS
- adds cpu_has_pebs to test for X86_FEATURE_PEBS
[PATCH] x86-64: x86_64 rename X86_FEATURE_DTES to X86_FEATURE_DS
Here is a patch (used by perfmon2) that renamed X86_FEATURE_DTES
to X86_FEATURE_DS to match Intel's documentation for the Debug Store
save area. The patch also adds cpu_has_ds.
changelog:
- rename X86_FEATURE_DTES to X86_FEATURE_DS to match documentation
- adds cpu_has_ds to test for X86_FEATURE_DS
Dave Jones [Thu, 7 Dec 2006 01:14:00 +0000 (02:14 +0100)]
[PATCH] i386: remove pointless printk from i386 oops output
This just got removed on x86-64, do the same on 32bit.
It always annoyed me when this ate a line of oops output pushing
interesting stuff off the screen.
Signed-off-by: Dave Jones <davej@redhat.com> Signed-off-by: Andi Kleen <ak@suse.de>
projects / karo-tx-linux.git / log