05 Sep, 2005
40 commits
-
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
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
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
Cc: Keith Owens
Signed-off-by: George Anzinger
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
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
#include
#include
#include
#include
#include
#include
#define __KERNEL__
#includevoid 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
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
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] = 0x89c028b8df: 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] &= 0xfdNote 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
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
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
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
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
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Some more assembler cleanups I noticed along the way.
Signed-off-by: Zachary Amsden
Cc: "H. Peter Anvin"
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Noticed by Chuck Ebbert: the .ldt entry of the TSS was set up incorrectly.
It never mattered since this was a leftover from old times, so remove it.Signed-off-by: Ingo Molnar
Signed-off-by: Adrian Bunk
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
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
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
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
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
GCC can generate better code around descriptor update and access functions
when there is not an explicit "eax" register constraint.Testing: You won't boot if this is messed up, since the TSS descriptor will be
corrupted. Verified the assembler and booted.Signed-off-by: Zachary Amsden
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
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
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
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
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
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
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
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
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
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:
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
The VIA VT8237's IOAPIC sends 'APIC De-Assert Messages' by default, causing
another CPU interrupt when the IRQ pin is de-asserted. This feature is
switched off by the patch to get rid of doubled ioapic level interrupt
rates.Signed-off-by: Karsten Wiese
Tested-by: Ingo Molnar
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Signed-off-by: Venkatesh Pallipadi
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
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
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
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
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
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
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
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
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
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
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
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."
Signed-off-by: Ingo Molnar
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
The LOG_BUF_SHIFT from lib/Kconfig.debug is sufficient.
Signed-off-by: Adrian Bunk
Acked-by: Paul Mundt
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Extend the compat mode kludgeology in envdev to cover MIPS as well.
Or why we should need something like is_compat_task() ...
Signed-off-by: Ralf Baechle
Cc: Vojtech Pavlik
Signed-off-by: Dmitry Torokhov
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
vr41xx doesn't need mach-vr41xx/timex.h. This patch has removed
mach-vr41xx/timex.h.Signed-off-by: Yoichi Yuasa
Cc: Ralf Baechle
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
This patch has fixed the following warnings.
arch/mips/kernel/genex.S:250:5: warning: "CONFIG_64BIT" is not defined
arch/mips/math-emu/cp1emu.c:1128:5: warning: "__mips64" is not defined
arch/mips/math-emu/cp1emu.c:1206:5: warning: "__mips64" is not defined
arch/mips/math-emu/cp1emu.c:1270:5: warning: "__mips64" is not defined
arch/mips/math-emu/cp1emu.c:323:5: warning: "__mips64" is not defined
arch/mips/math-emu/cp1emu.c:808:5: warning: "__mips64" is not defined
arch/mips/math-emu/cp1emu.c:953:5: warning: "__mips64" is not defined
arch/mips/mm/tlbex.c:519:5: warning: "CONFIG_64BIT" is not defined
include/asm/reg.h:73:5: warning: "CONFIG_64BIT" is not definedSigned-off-by: Yoichi Yuasa
Cc: Ralf Baechle
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
The addtion of SYS_SUPPORTS_*_KERNEL and CPU_SUPPORTS_*_KERNEL is halfway.
This patch has added more SYS_SUPPORTS_*_KERNEL and CPU_SUPPORTS_*_KERNEL
to arch/mips/Kconfig. Please apply.Signed-off-by: Yoichi Yuasa
Cc: Ralf Baechle
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
This patch has added pcibios_bus_to_resource to MIPS.
Signed-off-by: Yoichi Yuasa
Cc: Ralf Baechle
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Add pcibios_select_root to MIPS.
Signed-off-by: Yoichi Yuasa
Cc: Ralf Baechle
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Fix the MIPS coherency configuration such that we always keep the mapping
state in when we need to on non-coherent platforms.Signed-off-by: Ralf Baechle
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Signed-off-by: Ralf Baechle
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Start cleaning 32-bit vs. 64-bit configuration.
Signed-off-by: Ralf Baechle
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
This patch has changed from VR41XX to VR4100 series in arch/mips/Kconfig.
Signed-off-by: Yoichi Yuasa
Cc: Ralf Baechle
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
This patch has removed obsolete VRC4171 config.
Cc: Ralf Baechle
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
$ make menuconfig
scripts/kconfig/mconf arch/i386/Kconfig
drivers/char/Kconfig:847:warning: 'select' used by config symbol
'TANBAC_TB0219' refer to undefined symbol 'PCI_VR41XX'Here is a patch for this warning fix.
Signed-off-by: Yoichi Yuasa
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
This patch has added default select configs for vr41xx.
Signed-off-by: Yoichi Yuasa
Cc: Ralf Baechle
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
This patch has added TANBAC VR4131 multichip module in arch/mips/Kconfig
Signed-off-by: Yoichi Yuasa
Cc: Ralf Baechle
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
- MIPS Denmark does no longer exist; the PCI vendor ID is now owned by
MIPS Technologies.- Add ID for SOC-it, MIPS's system controller.
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
