| Age | Commit message (Collapse) | Author |
|---|
|
general usage
Jeff Dike <jdike@addtoit.com>,
Paolo 'Blaisorblade' Giarrusso <blaisorblade_spam@yahoo.it>,
Bodo Stroesser <bstroesser@fujitsu-siemens.com>
Adds a new ptrace(2) mode, called PTRACE_SYSEMU, resembling PTRACE_SYSCALL
except that the kernel does not execute the requested syscall; this is useful
to improve performance for virtual environments, like UML, which want to run
the syscall on their own.
In fact, using PTRACE_SYSCALL means stopping child execution twice, on entry
and on exit, and each time you also have two context switches; with SYSEMU you
avoid the 2nd stop and so save two context switches per syscall.
Also, some architectures don't have support in the host for changing the
syscall number via ptrace(), which is currently needed to skip syscall
execution (UML turns any syscall into getpid() to avoid it being executed on
the host). Fixing that is hard, while SYSEMU is easier to implement.
* This version of the patch includes some suggestions of Jeff Dike to avoid
adding any instructions to the syscall fast path, plus some other little
changes, by myself, to make it work even when the syscall is executed with
SYSENTER (but I'm unsure about them). It has been widely tested for quite a
lot of time.
* Various fixed were included to handle the various switches between
various states, i.e. when for instance a syscall entry is traced with one of
PT_SYSCALL / _SYSEMU / _SINGLESTEP and another one is used on exit.
Basically, this is done by remembering which one of them was used even after
the call to ptrace_notify().
* We're combining TIF_SYSCALL_EMU with TIF_SYSCALL_TRACE or TIF_SINGLESTEP
to make do_syscall_trace() notice that the current syscall was started with
SYSEMU on entry, so that no notification ought to be done in the exit path;
this is a bit of a hack, so this problem is solved in another way in next
patches.
* Also, the effects of the patch:
"Ptrace - i386: fix Syscall Audit interaction with singlestep"
are cancelled; they are restored back in the last patch of this series.
Detailed descriptions of the patches doing this kind of processing follow (but
I've already summed everything up).
* Fix behaviour when changing interception kind #1.
In do_syscall_trace(), we check the status of the TIF_SYSCALL_EMU flag
only after doing the debugger notification; but the debugger might have
changed the status of this flag because he continued execution with
PTRACE_SYSCALL, so this is wrong. This patch fixes it by saving the flag
status before calling ptrace_notify().
* Fix behaviour when changing interception kind #2:
avoid intercepting syscall on return when using SYSCALL again.
A guest process switching from using PTRACE_SYSEMU to PTRACE_SYSCALL
crashes.
The problem is in arch/i386/kernel/entry.S. The current SYSEMU patch
inhibits the syscall-handler to be called, but does not prevent
do_syscall_trace() to be called after this for syscall completion
interception.
The appended patch fixes this. It reuses the flag TIF_SYSCALL_EMU to
remember "we come from PTRACE_SYSEMU and now are in PTRACE_SYSCALL", since
the flag is unused in the depicted situation.
* Fix behaviour when changing interception kind #3:
avoid intercepting syscall on return when using SINGLESTEP.
When testing 2.6.9 and the skas3.v6 patch, with my latest patch and had
problems with singlestepping on UML in SKAS with SYSEMU. It looped
receiving SIGTRAPs without moving forward. EIP of the traced process was
the same for all SIGTRAPs.
What's missing is to handle switching from PTRACE_SYSCALL_EMU to
PTRACE_SINGLESTEP in a way very similar to what is done for the change from
PTRACE_SYSCALL_EMU to PTRACE_SYSCALL_TRACE.
I.e., after calling ptrace(PTRACE_SYSEMU), on the return path, the debugger is
notified and then wake ups the process; the syscall is executed (or skipped,
when do_syscall_trace() returns 0, i.e. when using PTRACE_SYSEMU), and
do_syscall_trace() is called again. Since we are on the return path of a
SYSEMU'd syscall, if the wake up is performed through ptrace(PTRACE_SYSCALL),
we must still avoid notifying the parent of the syscall exit. Now, this
behaviour is extended even to resuming with PTRACE_SINGLESTEP.
Signed-off-by: Paolo 'Blaisorblade' Giarrusso <blaisorblade@yahoo.it>
Cc: Jeff Dike <jdike@addtoit.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
|
|
Paolo 'Blaisorblade' Giarrusso <blaisorblade@yahoo.it>
Avoid giving two traps for singlestep instead of one, when syscall auditing is
enabled.
In fact no singlestep trap is sent on syscall entry, only on syscall exit, as
can be seen in entry.S:
# Note that in this mask _TIF_SINGLESTEP is not tested !!! <<<<<<<<<<<<<<
testb $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SECCOMP),TI_flags(%ebp)
jnz syscall_trace_entry
...
syscall_trace_entry:
...
call do_syscall_trace
But auditing a SINGLESTEP'ed process causes do_syscall_trace to be called, so
the tracer will get one more trap on the syscall entry path, which it
shouldn't.
Signed-off-by: Paolo 'Blaisorblade' Giarrusso <blaisorblade@yahoo.it>
CC: Roland McGrath <roland@redhat.com>
Cc: Jeff Dike <jdike@addtoit.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
|
|
The timers lack .suspend/.resume methods. Because of this, jiffies got a
big compensation after a S3 resume. And then softlockup watchdog reports
an oops. This occured with HPET enabled, but it's also possible for other
timers.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
|
|
Fix remaining bits of u32 vs. pm_message confusion. Should not break
anything.
Signed-off-by: Pavel Machek <pavel@suse.cz>
Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
|
|
Reset the ISA DMA controller into a known state after a suspend. Primary
concern was reenabling the cascading DMA channel (4).
Signed-off-by: Pierre Ossman <drzeus@drzeus.cx>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
|
|
This patch moves the common code in x86 and x86-64's semaphore.c into a
single file in lib/semaphore-sleepers.c. The arch specific asm stubs are
left in the arch tree (in semaphore.c for i386 and in the asm for x86-64).
There should be no changes in code/functionality with this patch.
Signed-off-by: Benjamin LaHaise <benjamin.c.lahaise@intel.com>
Cc: Andi Kleen <ak@muc.de>
Signed-off-by: Jeff Dike <jdike@addtoit.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
|
|
for_each_cpu walks through all processors in cpu_possible_map, which is
defined as cpu_callout_map on i386 and isn't initialised until all
processors have been booted. This breaks things which do for_each_cpu
iterations early during boot. So, define cpu_possible_map as a bitmap with
NR_CPUS bits populated. This was triggered by a patch i'm working on which
does alloc_percpu before bringing up secondary processors.
From: Alexander Nyberg <alexn@telia.com>
i386-boottime-for_each_cpu-broken.patch
i386-boottime-for_each_cpu-broken-fix.patch
The SMP version of __alloc_percpu checks the cpu_possible_map before
allocating memory for a certain cpu. With the above patches the BSP cpuid
is never set in cpu_possible_map which breaks CONFIG_SMP on uniprocessor
machines (as soon as someone tries to dereference something allocated via
__alloc_percpu, which in fact is never allocated since the cpu is not set
in cpu_possible_map).
Signed-off-by: Zwane Mwaikambo <zwane@arm.linux.org.uk>
Signed-off-by: Alexander Nyberg <alexn@telia.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
|
|
Add a clone operation for pgd updates.
This helps complete the encapsulation of updates to page tables (or pages
about to become page tables) into accessor functions rather than using
memcpy() to duplicate them. This is both generally good for consistency
and also necessary for running in a hypervisor which requires explicit
updates to page table entries.
The new function is:
clone_pgd_range(pgd_t *dst, pgd_t *src, int count);
dst - pointer to pgd range anwhere on a pgd page
src - ""
count - the number of pgds to copy.
dst and src can be on the same page, but the range must not overlap
and must not cross a page boundary.
Note that I ommitted using this call to copy pgd entries into the
software suspend page root, since this is not technically a live paging
structure, rather it is used on resume from suspend. CC'ing Pavel in case
he has any feedback on this.
Thanks to Chris Wright for noticing that this could be more optimal in
PAE compiles by eliminating the memset.
Signed-off-by: Zachary Amsden <zach@vmware.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
|
|
This patch adds a notify to the die_nmi notify that the system is about to
be taken down. If the notify is handled with a NOTIFY_STOP return, the
system is given a new lease on life.
We also change the nmi watchdog to carry on if die_nmi returns.
This give debug code a chance to a) catch watchdog timeouts and b) possibly
allow the system to continue, realizing that the time out may be due to
debugger activities such as single stepping which is usually done with
"other" cpus held.
Signed-off-by: George Anzinger<george@mvista.com>
Cc: Keith Owens <kaos@ocs.com.au>
Signed-off-by: George Anzinger <george@mvista.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
|
|
Introduce a write acessor for updating the current LDT. This is required
for hypervisors like Xen that do not allow LDT pages to be directly
written.
Testing - here's a fun little LDT test that can be trivially modified to
test limits as well.
/*
* Copyright (c) 2005, Zachary Amsden (zach@vmware.com)
* This is licensed under the GPL.
*/
#include <stdio.h>
#include <signal.h>
#include <asm/ldt.h>
#include <asm/segment.h>
#include <sys/types.h>
#include <unistd.h>
#include <sys/mman.h>
#define __KERNEL__
#include <asm/page.h>
void main(void)
{
struct user_desc desc;
char *code;
unsigned long long tsc;
code = (char *)mmap(0, 8192, PROT_EXEC|PROT_READ|PROT_WRITE,
MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
desc.entry_number = 0;
desc.base_addr = code;
desc.limit = 1;
desc.seg_32bit = 1;
desc.contents = MODIFY_LDT_CONTENTS_CODE;
desc.read_exec_only = 0;
desc.limit_in_pages = 1;
desc.seg_not_present = 0;
desc.useable = 1;
if (modify_ldt(1, &desc, sizeof(desc)) != 0) {
perror("modify_ldt");
}
printf("code base is 0x%08x\n", (unsigned)code);
code[0x0ffe] = 0x0f; /* rdtsc */
code[0x0fff] = 0x31;
code[0x1000] = 0xcb; /* lret */
__asm__ __volatile("lcall $7,$0xffe" : "=A" (tsc));
printf("TSC is 0x%016llx\n", tsc);
}
Signed-off-by: Zachary Amsden <zach@vmware.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
|
|
When reviewing GDT updates, I found the code:
set_tss_desc(cpu,t); /* This just modifies memory; ... */
per_cpu(cpu_gdt_table, cpu)[GDT_ENTRY_TSS].b &= 0xfffffdff;
This second line is unnecessary, since set_tss_desc() has already cleared
the busy bit.
Commented disassembly, line 1:
c028b8bd: 8b 0c 86 mov (%esi,%eax,4),%ecx
c028b8c0: 01 cb add %ecx,%ebx
c028b8c2: 8d 0c 39 lea (%ecx,%edi,1),%ecx
=> %ecx = per_cpu(cpu_gdt_table, cpu)
c028b8c5: 8d 91 80 00 00 00 lea 0x80(%ecx),%edx
=> %edx = &per_cpu(cpu_gdt_table, cpu)[GDT_ENTRY_TSS]
c028b8cb: 66 c7 42 00 73 20 movw $0x2073,0x0(%edx)
c028b8d1: 66 89 5a 02 mov %bx,0x2(%edx)
c028b8d5: c1 cb 10 ror $0x10,%ebx
c028b8d8: 88 5a 04 mov %bl,0x4(%edx)
c028b8db: c6 42 05 89 movb $0x89,0x5(%edx)
=> ((char *)%edx)[5] = 0x89
(equivalent) ((char *)per_cpu(cpu_gdt_table, cpu)[GDT_ENTRY_TSS])[5] = 0x89
c028b8df: c6 42 06 00 movb $0x0,0x6(%edx)
c028b8e3: 88 7a 07 mov %bh,0x7(%edx)
c028b8e6: c1 cb 10 ror $0x10,%ebx
=> other bits
Commented disassembly, line 2:
c028b8e9: 8b 14 86 mov (%esi,%eax,4),%edx
c028b8ec: 8d 04 3a lea (%edx,%edi,1),%eax
=> %eax = per_cpu(cpu_gdt_table, cpu)
c028b8ef: 81 a0 84 00 00 00 ff andl $0xfffffdff,0x84(%eax)
=> per_cpu(cpu_gdt_table, cpu)[GDT_ENTRY_TSS].b &= 0xfffffdff;
(equivalent) ((char *)per_cpu(cpu_gdt_table, cpu)[GDT_ENTRY_TSS])[5] &= 0xfd
Note that (0x89 & ~0xfd) == 0; i.e, set_tss_desc(cpu,t) has already stored
the type field in the GDT with the busy bit clear.
Eliminating redundant and obscure code is always a good thing; in fact, I
pointed out this same optimization many moons ago in arch/i386/setup.c,
back when it used to be called that.
Signed-off-by: Zachary Amsden <zach@vmware.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
|
|
The pushf/popf in switch_to are ONLY used to switch IOPL. Making this
explicit in C code is more clear. This pushf/popf pair was added as a
bugfix for leaking IOPL to unprivileged processes when using
sysenter/sysexit based system calls (sysexit does not restore flags).
When requesting an IOPL change in sys_iopl(), it is just as easy to change
the current flags and the flags in the stack image (in case an IRET is
required), but there is no reason to force an IRET if we came in from the
SYSENTER path.
This change is the minimal solution for supporting a paravirtualized Linux
kernel that allows user processes to run with I/O privilege. Other
solutions require radical rewrites of part of the low level fault / system
call handling code, or do not fully support sysenter based system calls.
Unfortunately, this added one field to the thread_struct. But as a bonus,
on P4, the fastest time measured for switch_to() went from 312 to 260
cycles, a win of about 17% in the fast case through this performance
critical path.
Signed-off-by: Zachary Amsden <zach@vmware.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
|
|
Privilege checking cleanup. Originally, these diffs were much greater, but
recent cleanups in Linux have already done much of the cleanup. I added
some explanatory comments in places where the reasoning behind certain
tests is rather subtle.
Also, in traps.c, we can skip the user_mode check in handle_BUG(). The
reason is, there are only two call chains - one via die_if_kernel() and one
via do_page_fault(), both entering from die(). Both of these paths already
ensure that a kernel mode failure has happened. Also, the original check
here, if (user_mode(regs)) was insufficient anyways, since it would not
rule out BUG faults from V8086 mode execution.
Saving the %ss segment in show_regs() rather than assuming a fixed value
also gives better information about the current kernel state in the
register dump.
Signed-off-by: Zachary Amsden <zach@vmware.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
|
|
Some more assembler cleanups I noticed along the way.
Signed-off-by: Zachary Amsden <zach@vmware.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
|
|
Also, setting PDPEs in PAE mode does not require atomic operations, since the
PDPEs are cached by the processor, and only reloaded on an explicit or
implicit reload of CR3.
Since the four PDPEs must always be present in an active root, and the kernel
PDPE is never updated, we are safe even from SMIs and interrupts / NMIs using
task gates (which reload CR3). Actually, much of this is moot, since the user
PDPEs are never updated either, and the only usage of task gates is by the
doublefault handler. It appears the only place PGDs get updated in PAE mode
is in init_low_mappings() / zap_low_mapping() for initial page table creation
and recovery from ACPI sleep state, and these sites are safe by inspection.
Getting rid of the cmpxchg8b saves code space and 720 cycles in pgd_alloc on
P4.
Signed-off-by: Zachary Amsden <zach@vmware.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
|
|
Subtle fix: load_TLS has been moved after saving %fs and %gs segments to avoid
creating non-reversible segments. This could conceivably cause a bug if the
kernel ever needed to save and restore fs/gs from the NMI handler. It
currently does not, but this is the safest approach to avoiding fs/gs
corruption. SMIs are safe, since SMI saves the descriptor hidden state.
Signed-off-by: Zachary Amsden <zach@vmware.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
|
|
register management
i386 inline assembler cleanup.
This change encapsulates descriptor and task register management. Also,
it is possible to improve assembler generation in two cases; savesegment
may store the value in a register instead of a memory location, which
allows GCC to optimize stack variables into registers, and MOV MEM, SEG
is always a 16-bit write to memory, making the casting in math-emu
unnecessary.
Signed-off-by: Zachary Amsden <zach@vmware.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
|
|
i386 arch cleanup. Introduce the serialize macro to serialize processor
state. Why the microcode update needs it I am not quite sure, since wrmsr()
is already a serializing instruction, but it is a microcode update, so I will
keep the semantic the same, since this could be a timing workaround. As far
as I can tell, this has always been there since the original microcode update
source.
Signed-off-by: Zachary Amsden <zach@vmware.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
|
|
i386 Inline asm cleanup. Use cr/dr accessor functions.
Also, a potential bugfix. Also, some CR accessors really should be volatile.
Reads from CR0 (numeric state may change in an exception handler), writes to
CR4 (flipping CR4.TSD) and reads from CR2 (page fault) prevent instruction
re-ordering. I did not add memory clobber to CR3 / CR4 / CR0 updates, as it
was not there to begin with, and in no case should kernel memory be clobbered,
except when doing a TLB flush, which already has memory clobber.
I noticed that page invalidation does not have a memory clobber. I can't find
a bug as a result, but there is definitely a potential for a bug here:
#define __flush_tlb_single(addr) \
__asm__ __volatile__("invlpg %0": :"m" (*(char *) addr))
Signed-off-by: Zachary Amsden <zach@vmware.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
|
|
This makes the vDSO use nops for all its padding around instructions,
rather than sometimes zeros, and nop-pads the end of the area containing
instructions to a 32-byte cache line, to keep text and data in separate
lines.
Signed-off-by: Roland McGrath <roland@redhat.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
|
|
This is subarch update for ES7000. I've modified platform check code and
removed unnecessary OEM table parsing for newer systems that don't use OEM
information during boot. Parsing the table in fact is causing problems,
and the platform doesn't get recognized. The patch only affects the ES7000
subach.
Signed-off-by: <Natalie.Protasevich@unisys.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
|
|
Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
|
|
i386 generic subarchitecture requires explicit dmi strings or command line
to enable bigsmp mode. The patch below removes that restriction, and uses
bigsmp as soon as it finds more than 8 logical CPUs, Intel processors and
xAPIC support.
Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
|
|
o With introduction of kexec as boot-loader, the assumption that parameter
segment will always be loaded at lower address than kernel and will be
addressable by early bootup page tables is no longer valid. In kexec on
panic case parameter segment might well be loaded beyond kernel image and
might not be addressable by early boot page tables.
o This case might hit in the scenario where user has reserved a chunk of
memory for second kernel, for example 16MB to 64MB, and has also built
second kernel for physical memory location 16MB. In this case kexec has no
choice but to load the parameter segment at a higher address than new kernel
image at safe location where new kernel does not stomp it.
o Though problem should automatically go away once relocatable kernel for i386
is in place and kexec can determine the location of new kernel at run time
and load parameter segment at lower address than kernel image. But till then
this patch can go in (assuming it does not break something else).
o This patch moves up the boot parameter saving code. Now boot parameters
are copied out in protected mode before page tables are initialized. This
will ensure that parameter segment is always addressable irrespective of
its physical location.
Signed-off-by: Vivek Goyal <vgoyal@in.ibm.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
|
|
If the virtual 86 machine reaches an instruction which raises a General
Protection Fault (such as CLI or STI), the instruction is emulated (in
handle_vm86_fault). However, the emulation ignored the TF bit, so the
hardware debug interrupt was not invoked after such an emulated instruction
(and the DOS debugger missed it).
This patch fixes the problem by emulating the hardware debug interrupt as
the last action before control is returned to the VM86 program.
Signed-off-by: Petr Tesarik <kernel@tesarici.cz>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
|
|
The memory descriptors that comprise the EFI memory map are not fixed in
stone such that the size could change in the future. This uses the memory
descriptor size obtained from EFI to iterate over the memory map entries
during boot. This enables the removal of an x86 specific pad (and ifdef)
in the EFI header. I also couldn't stomach the broken up nature of the
function to put EFI runtime calls into virtual mode any longer so I fixed
that up a bit as well.
For reference, this patch only impacts x86.
Signed-off-by: Matt Tolentino <matthew.e.tolentino@intel.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
|
|
Only use read_timer_tsc only when CPU has TSC. Thanks to Andrea for
pointing this out. Should not be issue on any platforms as all recent
systems that has HPET also has CPUs that supports TSC. The patch is still
required for correctness.
Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
|
|
This patch pushes the creation of a rare signal frame (SIGBUS or SIGSEGV)
into a separate function, thus saving stackspace in the main
do_page_fault() stackframe. The effect is 132 bytes less of stack used by
the typical do_page_fault() invocation - resulting in a denser
cache-layout.
(Another minor effect is that in case of kernel crashes that come from a
pagefault, we add less space to the already existing frame, giving the
crash functions a slightly higher chance to do their stuff without
overflowing the stack.)
(The changes also result in slightly cleaner code.)
argument bugfix from "Guillaume C." <guichaz@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
|
|
I don't think we need to call hugetlb_clean_stale_pgtable() anymore
in 2.6.13 because of the rework with free_pgtables(). It now collect
all the pte page at the time of munmap. It used to only collect page
table pages when entire one pgd can be freed and left with staled pte
pages. Not anymore with 2.6.13. This function will never be called
and We should turn it into a BUG_ON.
I also spotted two problems here, not Adam's fault :-)
(1) in huge_pte_alloc(), it looks like a bug to me that pud is not
checked before calling pmd_alloc()
(2) in hugetlb_clean_stale_pgtable(), it also missed a call to
pmd_free_tlb. I think a tlb flush is required to flush the mapping
for the page table itself when we clear out the pmd pointing to a
pte page. However, since hugetlb_clean_stale_pgtable() is never
called, so it won't trigger the bug.
Signed-off-by: Ken Chen <kenneth.w.chen@intel.com>
Cc: Adam Litke <agl@us.ibm.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
|
|
For demand faulting, we cannot assume that the page tables will be
populated. Do what the rest of the architectures do and test p?d_present()
while walking down the page table.
Signed-off-by: Adam Litke <agl@us.ibm.com>
Cc: <linux-mm@kvack.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
|
|
Initial Post (Wed, 17 Aug 2005)
This patch moves the
if (! pte_none(*pte))
hugetlb_clean_stale_pgtable(pte);
logic into huge_pte_alloc() so all of its callers can be immune to the bug
described by Kenneth Chen at http://lkml.org/lkml/2004/6/16/246
> It turns out there is a bug in hugetlb_prefault(): with 3 level page table,
> huge_pte_alloc() might return a pmd that points to a PTE page. It happens
> if the virtual address for hugetlb mmap is recycled from previously used
> normal page mmap. free_pgtables() might not scrub the pmd entry on
> munmap and hugetlb_prefault skips on any pmd presence regardless what type
> it is.
Unless I am missing something, it seems more correct to place the check inside
huge_pte_alloc() to prevent a the same bug wherever a huge pte is allocated.
It also allows checking for this condition when lazily faulting huge pages
later in the series.
Signed-off-by: Adam Litke <agl@us.ibm.com>
Cc: <linux-mm@kvack.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
|
|
With cleanups from Dave Hansen <haveblue@us.ibm.com>
SPARSEMEM_EXTREME makes mem_section a one dimensional array of pointers to
mem_sections. This two level layout scheme is able to achieve smaller
memory requirements for SPARSEMEM with the tradeoff of an additional shift
and load when fetching the memory section. The current SPARSEMEM
implementation is a one dimensional array of mem_sections which is the
default SPARSEMEM configuration. The patch attempts isolates the
implementation details of the physical layout of the sparsemem section
array.
SPARSEMEM_EXTREME requires bootmem to be functioning at the time of
memory_present() calls. This is not always feasible, so architectures
which do not need it may allocate everything statically by using
SPARSEMEM_STATIC.
Signed-off-by: Andy Whitcroft <apw@shadowen.org>
Signed-off-by: Bob Picco <bob.picco@hp.com>
Signed-off-by: Dave Hansen <haveblue@us.ibm.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
|
|
I had some time to think about PCI assign issues in 2.6.13-rc series.
The major problem here is that we call pci_assign_unassigned_resources()
way too early - at subsys_initcall level. Therefore we give no chances
to ACPI and PnP routines (called at fs_initcall level) to reserve their
respective resources properly, as the comments in drivers/pnp/system.c
and drivers/acpi/motherboard.c suggest:
/**
* Reserve motherboard resources after PCI claim BARs,
* but before PCI assign resources for uninitialized PCI devices
*/
So I moved the pci_assign_unassigned_resources() call to
pcibios_assign_resources() (fs_initcall), which should hopefully fix a
lot of problems and make PCIBIOS_MIN_IO tweaks unnecessary.
Other changes:
- remove resource assignment code from pcibios_assign_resources(), since
it duplicates pci_assign_unassigned_resources() functionality and
actually does nothing in 2.6.13;
- modify ROM assignment code as per Ben's suggestion: try to use firmware
settings by default (if PCI_ASSIGN_ROMS is not set);
- set CARDBUS_IO_SIZE back to 4K as it's a wonderful stress test for
various setups.
Confirmed by Tero Roponen <teanropo@cc.jyu.fi> (who had problems with
the 4kB CardBus IO size previously).
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
|
|
It has been reported that the way Linux handles NODEFER for signals is
not consistent with the way other Unix boxes handle it. I've written a
program to test the behavior of how this flag affects signals and had
several reports from people who ran this on various Unix boxes,
confirming that Linux seems to be unique on the way this is handled.
The way NODEFER affects signals on other Unix boxes is as follows:
1) If NODEFER is set, other signals in sa_mask are still blocked.
2) If NODEFER is set and the signal is in sa_mask, then the signal is
still blocked. (Note: this is the behavior of all tested but Linux _and_
NetBSD 2.0 *).
The way NODEFER affects signals on Linux:
1) If NODEFER is set, other signals are _not_ blocked regardless of
sa_mask (Even NetBSD doesn't do this).
2) If NODEFER is set and the signal is in sa_mask, then the signal being
handled is not blocked.
The patch converts signal handling in all current Linux architectures to
the way most Unix boxes work.
Unix boxes that were tested: DU4, AIX 5.2, Irix 6.5, NetBSD 2.0, SFU
3.5 on WinXP, AIX 5.3, Mac OSX, and of course Linux 2.6.13-rcX.
* NetBSD was the only other Unix to behave like Linux on point #2. The
main concern was brought up by point #1 which even NetBSD isn't like
Linux. So with this patch, we leave NetBSD as the lonely one that
behaves differently here with #2.
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
|
|
i386 floating-point exception handling has a bug that can cause error
code 0 to be sent instead of the proper code during signal delivery.
This is caused by unconditionally checking the IS and c1 bits from the
FPU status word when they are not always relevant. The IS bit tells
whether an exception is a stack fault and is only relevant when the
exception is IE (invalid operation.) The C1 bit determines whether a
stack fault is overflow or underflow and is only relevant when IS and IE
are set.
Signed-off-by: Chuck Ebbert <76306.1226@compuserve.com>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
|
|
I'm trying to get the nmi working with my laptop (IBM ThinkPad G41) and after
debugging it a while, I found that the nmi code doesn't want to set it up for
this particular CPU.
Here I have:
$ cat /proc/cpuinfo
processor : 0
vendor_id : GenuineIntel
cpu family : 15
model : 4
model name : Mobile Intel(R) Pentium(R) 4 CPU 3.33GHz
stepping : 1
cpu MHz : 3320.084
cache size : 1024 KB
physical id : 0
siblings : 2
core id : 0
cpu cores : 1
fdiv_bug : no
hlt_bug : no
f00f_bug : no
coma_bug : no
fpu : yes
fpu_exception : yes
cpuid level : 3
wp : yes
flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge
mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe pni
monitor ds_cpl est tm2 cid xtpr
bogomips : 6642.39
processor : 1
vendor_id : GenuineIntel
cpu family : 15
model : 4
model name : Mobile Intel(R) Pentium(R) 4 CPU 3.33GHz
stepping : 1
cpu MHz : 3320.084
cache size : 1024 KB
physical id : 0
siblings : 2
core id : 0
cpu cores : 1
fdiv_bug : no
hlt_bug : no
f00f_bug : no
coma_bug : no
fpu : yes
fpu_exception : yes
cpuid level : 3
wp : yes
flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge
mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe pni
monitor ds_cpl est tm2 cid xtpr
bogomips : 6637.46
And the following code shows:
$ cat linux-2.6.13-rc6/arch/i386/kernel/nmi.c
[...]
void setup_apic_nmi_watchdog (void)
{
switch (boot_cpu_data.x86_vendor) {
case X86_VENDOR_AMD:
if (boot_cpu_data.x86 != 6 && boot_cpu_data.x86 != 15)
return;
setup_k7_watchdog();
break;
case X86_VENDOR_INTEL:
switch (boot_cpu_data.x86) {
case 6:
if (boot_cpu_data.x86_model > 0xd)
return;
setup_p6_watchdog();
break;
case 15:
if (boot_cpu_data.x86_model > 0x3)
return;
Here I get boot_cpu_data.x86_model == 0x4. So I decided to change it and
reboot. I now seem to have a working NMI. So, unless there's something know
to be bad about this processor and the NMI. I'm submitting the following
patch.
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Acked-by: Zwane Mwaikambo <zwane@arm.linux.org.uk>
Acked-by: Mikael Pettersson <mikpe@csd.uu.se>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
|
|
Since early CPU identify is in this information is already available
Signed-off-by: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
|
|
Move the fix to align node_end_pfns to a proper location. The earlier fix
made the node_remap_start_vaddr to get misaligned causing remap_numa_kva to
barf again :-/
Signed-off-by: Ravikiran Thirumalai <kiran@scalex86.org>
Signed-off-by: Shai Fultheim <shai@scalex86.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
|
|
This patch add stubs to allow the visws subarch to link again.
Signed-off-by: Tom Duffy <thomas.duffy.99@alumni.brown.edu>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
|
|
Another x86 subarchitecture bit I missed. This adds both
machine_emergency_restart missed in my reboot fixes and
machine_shutdown needed for kexec support.
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
|
|
Here is one more bit of breakage my x86 sub-architecture
confusion caused.
Add machine_shutdown to voyager so it will compile with CONFIG_KEXEC.
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
|
|
[PATCH] i386: Implement machine_emergency_reboot
introduced this new function into arch/i386/reboot.c. However,
subarchitectures are entitled to implement their own copies of reboot.c
from which this new function is now missing.
It looks like visws will also need a similar fixup
Signed-off-by: James Bottomley <James.Bottomley@SteelEye.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
|
|
We had a user whose apps weren't working correctly because his "rtc" wasn't
working fully.
For the sake of simplicity, it seems sensible to always enable HPET RTC
emulation.
Remove a special config option for HPET_EMULATE_RTC and make it directly
depend on HPET_TIMER and RTC. This will avoid the hangs when EMULATE_RTC
is not configured and when some userlevel script depends on RTC interrupt,
as in:
http://bugzilla.kernel.org/show_bug.cgi?id=4904
Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
|
|
Fix bug found by Grant Coady <lkml@dodo.com.au>'s autobuild setup.
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
|
|
We know that the randomisation slows down some workloads on Transmeta CPUs
by quite large amounts. We think it's because the CPU needs to recode the
same x86 instructions when they pop up at a different virtual address after
a fork+exec.
So disable randomization by default on those CPUs.
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
|
|
This removes sys_set_zone_reclaim() for now. While i'm sure Martin is
trying to solve a real problem, we must not hard-code an incomplete and
insufficient approach into a syscall, because syscalls are pretty much
for eternity. I am quite strongly convinced that this syscall must not
hit v2.6.13 in its current form.
Firstly, the syscall lacks basic syscall design: e.g. it allows the
global setting of VM policy for unprivileged users. (!) [ Imagine an
Oracle installation and a SAP installation on the same NUMA box fighting
over the 'optimal' setting for this flag. What will they do? Will they
try to set the flag to their own preferred value every second or so? ]
Secondly, it was added based on a single datapoint from Martin:
http://marc.theaimsgroup.com/?l=linux-mm&m=111763597218177&w=2
where Martin characterizes the numbers the following way:
' Run-to-run variability for "make -j" is huge, so these numbers aren't
terribly useful except to see that with reclaim the benchmark still
finishes in a reasonable amount of time. '
in other words: the fundamental problem has likely not been solved, only
a tendential move into the right direction has been observed, and a
handful of numbers were picked out of a set of hugely variable results,
without showing the variability data. How much variance is there
run-to-run?
I'd really suggest to first walk the walk and see what's needed to get
stable & predictable kernel compilation numbers on that NUMA box, before
adding random syscalls to tune a particular aspect of the VM ... which
approach might not even matter once the whole picture has been analyzed
and understood!
The third, most important point is that the syscall exposes VM tuning
internals in a completely unstructured way. What sense does it make to
have a _GLOBAL_ per-node setting for 'should we go to another node for
reclaim'? If then it might make sense to do this per-app, via numalib or
so.
The change is minimalistic in that it doesnt remove the syscall and the
underlying infrastructure changes, only the user-visible changes. We
could perhaps add a CAP_SYS_ADMIN-only sysctl for this hack, a'ka
/proc/sys/vm/swappiness, but even that looks quite counterproductive
when the generic approach is that we are trying to reduce the number of
external factors in the VM balance picture.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
|
|
|
|
|
|
Add reference count and disable ACPI PCI Interrupt Link
when no device still uses it.
Warn when drivers have not released Link at suspend time.
http://bugzilla.kernel.org/show_bug.cgi?id=3469
Signed-off-by: David Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>
|
|
Otherwise a platform that supports ACPI based cpufreq
and boots up at lowest possible speed could stay there
forever. This because the governor may request max speed,
but the code doesn't update if there is no change in
speed, and it assumed the initial state of max speed.
http://bugzilla.kernel.org/show_bug.cgi?id=4634
Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>
|
