Commit e7f2f991 authored by Linus Torvalds's avatar Linus Torvalds
Browse files

Merge phase #5 (misc) of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

Merges oprofile, timers/hpet, x86/traps, x86/time, and x86/core misc items.

* 'x86-core-v4-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (132 commits)
  x86: change early_ioremap to use slots instead of nesting
  x86: adjust dependencies for CONFIG_X86_CMOV
  dumpstack: x86: various small unification steps, fix
  x86: remove additional_cpus
  x86: remove additional_cpus configurability
  x86: improve UP kernel when CPU-hotplug and SMP is enabled
  dumpstack: x86: various small unification steps
  dumpstack: i386: make kstack= an early boot-param and add oops=panic
  dumpstack: x86: use log_lvl and unify trace formatting
  dumptrace: x86: consistently include loglevel, print stack switch
  dumpstack: x86: add "end" parameter to valid_stack_ptr and print_context_stack
  dumpstack: x86: make printk_address equal
  dumpstack: x86: move die_nmi to dumpstack_32.c
  traps: x86: finalize unification of traps.c
  traps: x86: make traps_32.c and traps_64.c equal
  traps: x86: various noop-changes preparing for unification of traps_xx.c
  traps: x86_64: use task_pid_nr(tsk) instead of tsk->pid in do_general_protection
  traps: i386: expand clear_mem_error and remove from mach_traps.h
  traps: x86_64: make io_check_error equal to the one on i386
  traps: i386: use preempt_conditional_sti/cli in do_int3
  ...
parents 11a96d18 c00193f9
......@@ -159,8 +159,6 @@ hayes-esp.txt
- info on using the Hayes ESP serial driver.
highuid.txt
- notes on the change from 16 bit to 32 bit user/group IDs.
hpet.txt
- High Precision Event Timer Driver for Linux.
timers/
- info on the timer related topics
hw_random.txt
......
00-INDEX
- this file
highres.txt
- High resolution timers and dynamic ticks design notes
hpet.txt
- High Precision Event Timer Driver for Linux
hrtimers.txt
- subsystem for high-resolution kernel timers
timer_stats.txt
- timer usage statistics
High Precision Event Timer Driver for Linux
The High Precision Event Timer (HPET) hardware is the future replacement
for the 8254 and Real Time Clock (RTC) periodic timer functionality.
Each HPET can have up to 32 timers. It is possible to configure the
first two timers as legacy replacements for 8254 and RTC periodic timers.
A specification done by Intel and Microsoft can be found at
<http://www.intel.com/technology/architecture/hpetspec.htm>.
The High Precision Event Timer (HPET) hardware follows a specification
by Intel and Microsoft which can be found at
http://www.intel.com/technology/architecture/hpetspec.htm
Each HPET has one fixed-rate counter (at 10+ MHz, hence "High Precision")
and up to 32 comparators. Normally three or more comparators are provided,
each of which can generate oneshot interupts and at least one of which has
additional hardware to support periodic interrupts. The comparators are
also called "timers", which can be misleading since usually timers are
independent of each other ... these share a counter, complicating resets.
HPET devices can support two interrupt routing modes. In one mode, the
comparators are additional interrupt sources with no particular system
role. Many x86 BIOS writers don't route HPET interrupts at all, which
prevents use of that mode. They support the other "legacy replacement"
mode where the first two comparators block interrupts from 8254 timers
and from the RTC.
The driver supports detection of HPET driver allocation and initialization
of the HPET before the driver module_init routine is called. This enables
platform code which uses timer 0 or 1 as the main timer to intercept HPET
initialization. An example of this initialization can be found in
arch/i386/kernel/time_hpet.c.
arch/x86/kernel/hpet.c.
The driver provides two APIs which are very similar to the API found in
the rtc.c driver. There is a user space API and a kernel space API.
An example user space program is provided below.
The driver provides a userspace API which resembles the API found in the
RTC driver framework. An example user space program is provided below.
#include <stdio.h>
#include <stdlib.h>
......@@ -286,15 +297,3 @@ out:
return;
}
The kernel API has three interfaces exported from the driver:
hpet_register(struct hpet_task *tp, int periodic)
hpet_unregister(struct hpet_task *tp)
hpet_control(struct hpet_task *tp, unsigned int cmd, unsigned long arg)
The kernel module using this interface fills in the ht_func and ht_data
members of the hpet_task structure before calling hpet_register.
hpet_control simply vectors to the hpet_ioctl routine and has the same
commands and respective arguments as the user API. hpet_unregister
is used to terminate usage of the HPET timer reserved by hpet_register.
......@@ -13,6 +13,20 @@ config OPROFILE
If unsure, say N.
config OPROFILE_IBS
bool "OProfile AMD IBS support (EXPERIMENTAL)"
default n
depends on OPROFILE && SMP && X86
help
Instruction-Based Sampling (IBS) is a new profiling
technique that provides rich, precise program performance
information. IBS is introduced by AMD Family10h processors
(AMD Opteron Quad-Core processor “Barcelona”) to overcome
the limitations of conventional performance counter
sampling.
If unsure, say N.
config HAVE_OPROFILE
def_bool n
......
......@@ -38,8 +38,7 @@ config M386
- "Crusoe" for the Transmeta Crusoe series.
- "Efficeon" for the Transmeta Efficeon series.
- "Winchip-C6" for original IDT Winchip.
- "Winchip-2" for IDT Winchip 2.
- "Winchip-2A" for IDT Winchips with 3dNow! capabilities.
- "Winchip-2" for IDT Winchips with 3dNow! capabilities.
- "GeodeGX1" for Geode GX1 (Cyrix MediaGX).
- "Geode GX/LX" For AMD Geode GX and LX processors.
- "CyrixIII/VIA C3" for VIA Cyrix III or VIA C3.
......@@ -194,19 +193,11 @@ config MWINCHIPC6
treat this chip as a 586TSC with some extended instructions
and alignment requirements.
config MWINCHIP2
bool "Winchip-2"
depends on X86_32
help
Select this for an IDT Winchip-2. Linux and GCC
treat this chip as a 586TSC with some extended instructions
and alignment requirements.
config MWINCHIP3D
bool "Winchip-2A/Winchip-3"
bool "Winchip-2/Winchip-2A/Winchip-3"
depends on X86_32
help
Select this for an IDT Winchip-2A or 3. Linux and GCC
Select this for an IDT Winchip-2, 2A or 3. Linux and GCC
treat this chip as a 586TSC with some extended instructions
and alignment requirements. Also enable out of order memory
stores for this CPU, which can increase performance of some
......@@ -318,7 +309,7 @@ config X86_L1_CACHE_SHIFT
int
default "7" if MPENTIUM4 || X86_GENERIC || GENERIC_CPU || MPSC
default "4" if X86_ELAN || M486 || M386 || MGEODEGX1
default "5" if MWINCHIP3D || MWINCHIP2 || MWINCHIPC6 || MCRUSOE || MEFFICEON || MCYRIXIII || MK6 || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || M586 || MVIAC3_2 || MGEODE_LX
default "5" if MWINCHIP3D || MWINCHIPC6 || MCRUSOE || MEFFICEON || MCYRIXIII || MK6 || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || M586 || MVIAC3_2 || MGEODE_LX
default "6" if MK7 || MK8 || MPENTIUMM || MCORE2 || MVIAC7
config X86_XADD
......@@ -360,7 +351,7 @@ config X86_POPAD_OK
config X86_ALIGNMENT_16
def_bool y
depends on MWINCHIP3D || MWINCHIP2 || MWINCHIPC6 || MCYRIXIII || X86_ELAN || MK6 || M586MMX || M586TSC || M586 || M486 || MVIAC3_2 || MGEODEGX1
depends on MWINCHIP3D || MWINCHIPC6 || MCYRIXIII || X86_ELAN || MK6 || M586MMX || M586TSC || M586 || M486 || MVIAC3_2 || MGEODEGX1
config X86_INTEL_USERCOPY
def_bool y
......@@ -368,7 +359,7 @@ config X86_INTEL_USERCOPY
config X86_USE_PPRO_CHECKSUM
def_bool y
depends on MWINCHIP3D || MWINCHIP2 || MWINCHIPC6 || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MK8 || MVIAC3_2 || MEFFICEON || MGEODE_LX || MCORE2
depends on MWINCHIP3D || MWINCHIPC6 || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MK8 || MVIAC3_2 || MEFFICEON || MGEODE_LX || MCORE2
config X86_USE_3DNOW
def_bool y
......@@ -376,7 +367,7 @@ config X86_USE_3DNOW
config X86_OOSTORE
def_bool y
depends on (MWINCHIP3D || MWINCHIP2 || MWINCHIPC6) && MTRR
depends on (MWINCHIP3D || MWINCHIPC6) && MTRR
#
# P6_NOPs are a relatively minor optimization that require a family >=
......@@ -396,7 +387,7 @@ config X86_P6_NOP
config X86_TSC
def_bool y
depends on ((MWINCHIP3D || MWINCHIP2 || MCRUSOE || MEFFICEON || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || MK8 || MVIAC3_2 || MVIAC7 || MGEODEGX1 || MGEODE_LX || MCORE2) && !X86_NUMAQ) || X86_64
depends on ((MWINCHIP3D || MCRUSOE || MEFFICEON || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || MK8 || MVIAC3_2 || MVIAC7 || MGEODEGX1 || MGEODE_LX || MCORE2) && !X86_NUMAQ) || X86_64
config X86_CMPXCHG64
def_bool y
......@@ -406,7 +397,7 @@ config X86_CMPXCHG64
# generates cmov.
config X86_CMOV
def_bool y
depends on (MK7 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || X86_64)
depends on (MK8 || MK7 || MCORE2 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || MCRUSOE || MEFFICEON || X86_64)
config X86_MINIMUM_CPU_FAMILY
int
......@@ -417,7 +408,7 @@ config X86_MINIMUM_CPU_FAMILY
config X86_DEBUGCTLMSR
def_bool y
depends on !(MK6 || MWINCHIPC6 || MWINCHIP2 || MWINCHIP3D || MCYRIXIII || M586MMX || M586TSC || M586 || M486 || M386)
depends on !(MK6 || MWINCHIPC6 || MWINCHIP3D || MCYRIXIII || M586MMX || M586TSC || M586 || M486 || M386)
menuconfig PROCESSOR_SELECT
bool "Supported processor vendors" if EMBEDDED
......
......@@ -28,7 +28,6 @@ cflags-$(CONFIG_MK8) += $(call cc-option,-march=k8,-march=athlon)
cflags-$(CONFIG_MCRUSOE) += -march=i686 $(align)-functions=0 $(align)-jumps=0 $(align)-loops=0
cflags-$(CONFIG_MEFFICEON) += -march=i686 $(call tune,pentium3) $(align)-functions=0 $(align)-jumps=0 $(align)-loops=0
cflags-$(CONFIG_MWINCHIPC6) += $(call cc-option,-march=winchip-c6,-march=i586)
cflags-$(CONFIG_MWINCHIP2) += $(call cc-option,-march=winchip2,-march=i586)
cflags-$(CONFIG_MWINCHIP3D) += $(call cc-option,-march=winchip2,-march=i586)
cflags-$(CONFIG_MCYRIXIII) += $(call cc-option,-march=c3,-march=i486) $(align)-functions=0 $(align)-jumps=0 $(align)-loops=0
cflags-$(CONFIG_MVIAC3_2) += $(call cc-option,-march=c3-2,-march=i686)
......
......@@ -213,7 +213,6 @@ CONFIG_M686=y
# CONFIG_MCRUSOE is not set
# CONFIG_MEFFICEON is not set
# CONFIG_MWINCHIPC6 is not set
# CONFIG_MWINCHIP2 is not set
# CONFIG_MWINCHIP3D is not set
# CONFIG_MGEODEGX1 is not set
# CONFIG_MGEODE_LX is not set
......
......@@ -210,7 +210,6 @@ CONFIG_X86_PC=y
# CONFIG_MCRUSOE is not set
# CONFIG_MEFFICEON is not set
# CONFIG_MWINCHIPC6 is not set
# CONFIG_MWINCHIP2 is not set
# CONFIG_MWINCHIP3D is not set
# CONFIG_MGEODEGX1 is not set
# CONFIG_MGEODE_LX is not set
......
......@@ -39,11 +39,11 @@
.endm
/* clobbers %eax */
.macro CLEAR_RREGS
.macro CLEAR_RREGS _r9=rax
xorl %eax,%eax
movq %rax,R11(%rsp)
movq %rax,R10(%rsp)
movq %rax,R9(%rsp)
movq %\_r9,R9(%rsp)
movq %rax,R8(%rsp)
.endm
......@@ -52,11 +52,10 @@
* We don't reload %eax because syscall_trace_enter() returned
* the value it wants us to use in the table lookup.
*/
.macro LOAD_ARGS32 offset
movl \offset(%rsp),%r11d
movl \offset+8(%rsp),%r10d
.macro LOAD_ARGS32 offset, _r9=0
.if \_r9
movl \offset+16(%rsp),%r9d
movl \offset+24(%rsp),%r8d
.endif
movl \offset+40(%rsp),%ecx
movl \offset+48(%rsp),%edx
movl \offset+56(%rsp),%esi
......@@ -145,7 +144,7 @@ ENTRY(ia32_sysenter_target)
SAVE_ARGS 0,0,1
/* no need to do an access_ok check here because rbp has been
32bit zero extended */
1: movl (%rbp),%r9d
1: movl (%rbp),%ebp
.section __ex_table,"a"
.quad 1b,ia32_badarg
.previous
......@@ -157,7 +156,7 @@ ENTRY(ia32_sysenter_target)
cmpl $(IA32_NR_syscalls-1),%eax
ja ia32_badsys
sysenter_do_call:
IA32_ARG_FIXUP 1
IA32_ARG_FIXUP
sysenter_dispatch:
call *ia32_sys_call_table(,%rax,8)
movq %rax,RAX-ARGOFFSET(%rsp)
......@@ -234,20 +233,17 @@ sysexit_audit:
#endif
sysenter_tracesys:
xchgl %r9d,%ebp
#ifdef CONFIG_AUDITSYSCALL
testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT),TI_flags(%r10)
jz sysenter_auditsys
#endif
SAVE_REST
CLEAR_RREGS
movq %r9,R9(%rsp)
movq $-ENOSYS,RAX(%rsp)/* ptrace can change this for a bad syscall */
movq %rsp,%rdi /* &pt_regs -> arg1 */
call syscall_trace_enter
LOAD_ARGS32 ARGOFFSET /* reload args from stack in case ptrace changed it */
RESTORE_REST
xchgl %ebp,%r9d
cmpl $(IA32_NR_syscalls-1),%eax
ja int_ret_from_sys_call /* sysenter_tracesys has set RAX(%rsp) */
jmp sysenter_do_call
......@@ -314,9 +310,9 @@ ENTRY(ia32_cstar_target)
testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags(%r10)
CFI_REMEMBER_STATE
jnz cstar_tracesys
cstar_do_call:
cmpl $IA32_NR_syscalls-1,%eax
ja ia32_badsys
cstar_do_call:
IA32_ARG_FIXUP 1
cstar_dispatch:
call *ia32_sys_call_table(,%rax,8)
......@@ -357,15 +353,13 @@ cstar_tracesys:
#endif
xchgl %r9d,%ebp
SAVE_REST
CLEAR_RREGS
movq %r9,R9(%rsp)
CLEAR_RREGS r9
movq $-ENOSYS,RAX(%rsp) /* ptrace can change this for a bad syscall */
movq %rsp,%rdi /* &pt_regs -> arg1 */
call syscall_trace_enter
LOAD_ARGS32 ARGOFFSET /* reload args from stack in case ptrace changed it */
LOAD_ARGS32 ARGOFFSET, 1 /* reload args from stack in case ptrace changed it */
RESTORE_REST
xchgl %ebp,%r9d
movl RSP-ARGOFFSET(%rsp), %r8d
cmpl $(IA32_NR_syscalls-1),%eax
ja int_ret_from_sys_call /* cstar_tracesys has set RAX(%rsp) */
jmp cstar_do_call
......
......@@ -23,7 +23,7 @@ CFLAGS_hpet.o := $(nostackp)
CFLAGS_tsc.o := $(nostackp)
obj-y := process_$(BITS).o signal_$(BITS).o entry_$(BITS).o
obj-y += traps_$(BITS).o irq_$(BITS).o
obj-y += traps.o irq_$(BITS).o dumpstack_$(BITS).o
obj-y += time_$(BITS).o ioport.o ldt.o
obj-y += setup.o i8259.o irqinit_$(BITS).o setup_percpu.o
obj-$(CONFIG_X86_VISWS) += visws_quirks.o
......
......@@ -444,7 +444,7 @@ void __init alternative_instructions(void)
_text, _etext);
/* Only switch to UP mode if we don't immediately boot others */
if (num_possible_cpus() == 1 || setup_max_cpus <= 1)
if (num_present_cpus() == 1 || setup_max_cpus <= 1)
alternatives_smp_switch(0);
}
#endif
......
......@@ -295,6 +295,9 @@ static void __setup_APIC_LVTT(unsigned int clocks, int oneshot, int irqen)
*
* Vector mappings are hard coded. On K8 only offset 0 (APIC500) and
* MCE interrupts are supported. Thus MCE offset must be set to 0.
*
* If mask=1, the LVT entry does not generate interrupts while mask=0
* enables the vector. See also the BKDGs.
*/
#define APIC_EILVT_LVTOFF_MCE 0
......@@ -319,6 +322,7 @@ u8 setup_APIC_eilvt_ibs(u8 vector, u8 msg_type, u8 mask)
setup_APIC_eilvt(APIC_EILVT_LVTOFF_IBS, vector, msg_type, mask);
return APIC_EILVT_LVTOFF_IBS;
}
EXPORT_SYMBOL_GPL(setup_APIC_eilvt_ibs);
/*
* Program the next event, relative to now
......
......@@ -307,6 +307,9 @@ static void __setup_APIC_LVTT(unsigned int clocks, int oneshot, int irqen)
*
* Vector mappings are hard coded. On K8 only offset 0 (APIC500) and
* MCE interrupts are supported. Thus MCE offset must be set to 0.
*
* If mask=1, the LVT entry does not generate interrupts while mask=0
* enables the vector. See also the BKDGs.
*/
#define APIC_EILVT_LVTOFF_MCE 0
......@@ -331,6 +334,7 @@ u8 setup_APIC_eilvt_ibs(u8 vector, u8 msg_type, u8 mask)
setup_APIC_eilvt(APIC_EILVT_LVTOFF_IBS, vector, msg_type, mask);
return APIC_EILVT_LVTOFF_IBS;
}
EXPORT_SYMBOL_GPL(setup_APIC_eilvt_ibs);
/*
* Program the next event, relative to now
......
......@@ -124,18 +124,25 @@ static inline int flag_is_changeable_p(u32 flag)
{
u32 f1, f2;
asm("pushfl\n\t"
"pushfl\n\t"
"popl %0\n\t"
"movl %0,%1\n\t"
"xorl %2,%0\n\t"
"pushl %0\n\t"
"popfl\n\t"
"pushfl\n\t"
"popl %0\n\t"
"popfl\n\t"
: "=&r" (f1), "=&r" (f2)
: "ir" (flag));
/*
* Cyrix and IDT cpus allow disabling of CPUID
* so the code below may return different results
* when it is executed before and after enabling
* the CPUID. Add "volatile" to not allow gcc to
* optimize the subsequent calls to this function.
*/
asm volatile ("pushfl\n\t"
"pushfl\n\t"
"popl %0\n\t"
"movl %0,%1\n\t"
"xorl %2,%0\n\t"
"pushl %0\n\t"
"popfl\n\t"
"pushfl\n\t"
"popl %0\n\t"
"popfl\n\t"
: "=&r" (f1), "=&r" (f2)
: "ir" (flag));
return ((f1^f2) & flag) != 0;
}
......@@ -719,12 +726,24 @@ static void __cpuinit identify_cpu(struct cpuinfo_x86 *c)
#endif
}
#ifdef CONFIG_X86_64
static void vgetcpu_set_mode(void)
{
if (cpu_has(&boot_cpu_data, X86_FEATURE_RDTSCP))
vgetcpu_mode = VGETCPU_RDTSCP;
else
vgetcpu_mode = VGETCPU_LSL;
}
#endif
void __init identify_boot_cpu(void)
{
identify_cpu(&boot_cpu_data);
#ifdef CONFIG_X86_32
sysenter_setup();
enable_sep_cpu();
#else
vgetcpu_set_mode();
#endif
}
......@@ -797,7 +816,7 @@ void __cpuinit print_cpu_info(struct cpuinfo_x86 *c)
else if (c->cpuid_level >= 0)
vendor = c->x86_vendor_id;
if (vendor && strncmp(c->x86_model_id, vendor, strlen(vendor)))
if (vendor && !strstr(c->x86_model_id, vendor))
printk(KERN_CONT "%s ", vendor);
if (c->x86_model_id[0])
......
......@@ -66,6 +66,6 @@ struct tss_struct doublefault_tss __cacheline_aligned = {
.ds = __USER_DS,
.fs = __KERNEL_PERCPU,
.__cr3 = __phys_addr_const((unsigned long)swapper_pg_dir)
.__cr3 = __pa_nodebug(swapper_pg_dir),
}
};
/*
* Copyright (C) 1991, 1992 Linus Torvalds
* Copyright (C) 2000, 2001, 2002 Andi Kleen, SuSE Labs
*/
#include <linux/kallsyms.h>
#include <linux/kprobes.h>
#include <linux/uaccess.h>
#include <linux/utsname.h>
#include <linux/hardirq.h>
#include <linux/kdebug.h>
#include <linux/module.h>
#include <linux/ptrace.h>
#include <linux/kexec.h>
#include <linux/bug.h>
#include <linux/nmi.h>
#include <asm/stacktrace.h>
#define STACKSLOTS_PER_LINE 8
#define get_bp(bp) asm("movl %%ebp, %0" : "=r" (bp) :)
int panic_on_unrecovered_nmi;
int kstack_depth_to_print = 3 * STACKSLOTS_PER_LINE;
static unsigned int code_bytes = 64;
static int die_counter;
void printk_address(unsigned long address, int reliable)
{
printk(" [<%p>] %s%pS\n", (void *) address,
reliable ? "" : "? ", (void *) address);
}
static inline int valid_stack_ptr(struct thread_info *tinfo,
void *p, unsigned int size, void *end)
{
void *t = tinfo;
if (end) {
if (p < end && p >= (end-THREAD_SIZE))
return 1;
else
return 0;
}
return p > t && p < t + THREAD_SIZE - size;
}
/* The form of the top of the frame on the stack */
struct stack_frame {
struct stack_frame *next_frame;
unsigned long return_address;
};
static inline unsigned long
print_context_stack(struct thread_info *tinfo,
unsigned long *stack, unsigned long bp,
const struct stacktrace_ops *ops, void *data,
unsigned long *end)
{
struct stack_frame *frame = (struct stack_frame *)bp;
while (valid_stack_ptr(tinfo, stack, sizeof(*stack), end)) {
unsigned long addr;
addr = *stack;
if (__kernel_text_address(addr)) {
if ((unsigned long) stack == bp + sizeof(long)) {
ops->address(data, addr, 1);
frame = frame->next_frame;
bp = (unsigned long) frame;
} else {
ops->address(data, addr, bp == 0);
}
}
stack++;
}
return bp;
}
void dump_trace(struct task_struct *task, struct pt_regs *regs,
unsigned long *stack, unsigned long bp,
const struct stacktrace_ops *ops, void *data)
{
if (!task)
task = current;
if (!stack) {
unsigned long dummy;
stack = &dummy;
if (task && task != current)
stack = (unsigned long *)task->thread.sp;
}
#ifdef CONFIG_FRAME_POINTER
if (!bp) {
if (task == current) {
/* Grab bp right from our regs */
get_bp(bp);
} else {
/* bp is the last reg pushed by switch_to */
bp = *(unsigned long *) task->thread.sp;
}
}
#endif
for (;;) {
struct thread_info *context;
context = (struct thread_info *)
((unsigned long)stack & (~(THREAD_SIZE - 1)));
bp = print_context_stack(context, stack, bp, ops, data, NULL);
stack = (unsigned long *)context->previous_esp;
if (!stack)
break;
if (ops->stack(data, "IRQ") < 0)
break;
touch_nmi_watchdog();
}
}
EXPORT_SYMBOL(dump_trace);
static void
print_trace_warning_symbol(void *data, char *msg, unsigned long symbol)
{
printk(data);
print_symbol(msg, symbol);
printk("\n");
}
static void print_trace_warning(void *data, char *msg)
{
printk("%s%s\n", (char *)data, msg);
}
static int print_trace_stack(void *data, char *name)
{
printk("%s <%s> ", (char *)data, name);
return 0;
}
/*
* Print one address/symbol entries per line.
*/
static void print_trace_address(void *data, unsigned long addr, int reliable)
{
touch_nmi_watchdog();
printk(data);
printk_address(addr, reliable);
}
static const struct stacktrace_ops print_trace_ops = {
.warning = print_trace_warning,
.warning_symbol = print_trace_warning_symbol,
.stack = print_trace_stack,
.address = print_trace_address,
};
static void
show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
unsigned long *stack, unsigned long bp, char *log_lvl)
{
printk("%sCall Trace:\n", log_lvl);
dump_trace(task, regs, stack, bp, &print_trace_ops, log_lvl);
}
void show_trace(struct task_struct *task, struct pt_regs *regs,
unsigned long *stack, unsigned long bp)
{
show_trace_log_lvl(task, regs, stack, bp, "");
}
static void
show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
unsigned long *sp, unsigned long bp, char *log_lvl)
{
unsigned long *stack;
int i;
if (sp == NULL) {
if (task)
sp = (unsigned long *)task->thread.sp;
else
sp = (unsigned long *)&sp;
}
stack = sp;
for (i = 0; i < kstack_depth_to_print; i++) {
if (kstack_end(stack))
break;
if (i && ((i % STACKSLOTS_PER_LINE) == 0))
printk("\n%s", log_lvl);
printk(" %08lx", *stack++);
touch_nmi_watchdog();
}
printk("\n");
show_trace_log_lvl(task, regs, sp, bp, log_lvl);
}
void show_stack(struct task_struct *task, unsigned long *sp)
{
show_stack_log_lvl(task, NULL, sp, 0, "");
}
/*
* The architecture-independent dump_stack generator
*/
void dump_stack(void)
{
unsigned long bp = 0;
unsigned long stack;
#ifdef CONFIG_FRAME_POINTER
if (!bp)
get_bp(bp);
#endif
printk("Pid: %d, comm: %.20s %s %s %.*s\n",
current->pid, current->comm, print_tainted(),
init_utsname()->release,
(int)strcspn(init_utsname()->version, " "),
init_utsname()->version);
show_trace(NULL, NULL, &stack, bp);
}
EXPORT_SYMBOL(dump_stack);
void show_registers(struct pt_regs *regs)
{
int i;
print_modules();
__show_regs(regs, 0);
printk(KERN_EMERG "Process %.*s (pid: %d, ti=%p task=%p task.ti=%p)\n",
TASK_COMM_LEN, current->comm, task_pid_nr(current),
current_thread_info(), current, task_thread_info(current));
/*
* When in-kernel, we also print out the stack and code at the
* time of the fault..
*/
if (!user_mode_vm(regs)) {
unsigned int code_prologue = code_bytes * 43 / 64;
unsigned int code_len = code_bytes;
unsigned char c;
u8 *ip;
printk(KERN_EMERG "Stack:\n");
show_stack_log_lvl(NULL, regs, &regs->sp,
0, KERN_EMERG);
printk(KERN_EMERG "Code: ");
ip = (u8 *)regs->ip - code_prologue;
if (ip < (u8 *)PAGE_OFFSET || probe_kernel_address(ip, c)) {
/* try starting at IP */
ip = (u8 *)regs->ip;
code_len = code_len - code_prologue + 1;
}
for (i = 0; i < code_len; i++, ip++) {
if (ip < (u8 *)PAGE_OFFSET ||
probe_kernel_address(ip, c)) {
printk(" Bad EIP value.");
break;
}
if (ip == (u8 *)regs->ip)
printk("<%02x> ", c);
else
printk("%02x ", c);
}
}
printk("\n");
}
int is_valid_bugaddr(unsigned long ip)
{
unsigned short ud2;
if (ip < PAGE_OFFSET)
return 0;
if (probe_kernel_address((unsigned short *)ip, ud2))
return 0;
return ud2 == 0x0b0f;
}
static raw_spinlock_t die_lock = __RAW_SPIN_LOCK_UNLOCKED;
static int die_owner = -1;
static unsigned int die_nest_count;
unsigned __kprobes long oops_begin(void)
{
unsigned long flags;
oops_enter();
if (die_owner != raw_smp_processor_id()) {
console_verbose();
raw_local_irq_save(flags);
__raw_spin_lock(&die_lock);
die_owner = smp_processor_id();
die_nest_count = 0;
bust_spinlocks(1);
} else {
raw_local_irq_save(flags);
}
die_nest_count++;
return flags;
}
void __kprobes oops_end(unsigned long flags, struct pt_regs *regs, int signr)
{
bust_spinlocks(0);
die_owner = -1;
add_taint(TAINT_DIE);
__raw_spin_unlock(&die_lock);
raw_local_irq_restore(flags);
if (!regs)
return;
if (kexec_should_crash(current))
crash_kexec(regs);
if (in_interrupt())
panic("Fatal exception in interrupt");
if (panic_on_oops)
panic("Fatal exception");
oops_exit();
do_exit(signr);
}
int __kprobes __die(const char *str, struct pt_regs *regs, long err)
{
unsigned short ss;
unsigned long sp;
printk(KERN_EMERG "%s: %04lx [#%d] ", str, err & 0xffff, ++die_counter);
#ifdef CONFIG_PREEMPT
printk("PREEMPT ");
#endif
#ifdef CONFIG_SMP
printk("SMP ");
#endif
#ifdef CONFIG_DEBUG_PAGEALLOC
printk("DEBUG_PAGEALLOC");
#endif
printk("\n");
if (notify_die(DIE_OOPS, str, regs, err,
current->thread.trap_no, SIGSEGV) == NOTIFY_STOP)
return 1;
show_registers(regs);
/* Executive summary in case the oops scrolled away */
sp = (unsigned long) (&regs->sp);
savesegment(ss, ss);
if (user_mode(regs)) {
sp = regs->sp;
ss = regs->ss & 0xffff;
}
printk(KERN_EMERG "EIP: [<%08lx>] ", regs->ip);
print_symbol("%s", regs->ip);
printk(" SS:ESP %04x:%08lx\n", ss, sp);
return 0;
}
/*
* This is gone through when something in the kernel has done something bad
* and is about to be terminated:
*/
void die(const char *str, struct pt_regs *regs, long err)
{
unsigned long flags = oops_begin();
if (die_nest_count < 3) {
report_bug(regs->ip, regs);
if (__die(str, regs, err))
regs = NULL;
} else {
printk(KERN_EMERG "Recursive die() failure, output suppressed\n");
}
oops_end(flags, regs, SIGSEGV);
}
static DEFINE_SPINLOCK(nmi_print_lock);
void notrace __kprobes
die_nmi(char *str, struct pt_regs *regs, int do_panic)
{
if (notify_die(DIE_NMIWATCHDOG, str, regs, 0, 2, SIGINT) == NOTIFY_STOP)
return;
spin_lock(&nmi_print_lock);
/*
* We are in trouble anyway, lets at least try
* to get a message out:
*/
bust_spinlocks(1);
printk(KERN_EMERG "%s", str);
printk(" on CPU%d, ip %08lx, registers:\n",
smp_processor_id(), regs->ip);
show_registers(regs);
if (do_panic)
panic("Non maskable interrupt");
console_silent();
spin_unlock(&nmi_print_lock);
bust_spinlocks(0);
/*
* If we are in kernel we are probably nested up pretty bad
* and might aswell get out now while we still can:
*/
if (!user_mode_vm(regs)) {
current->thread.trap_no = 2;
crash_kexec(regs);
}
do_exit(SIGSEGV);
}
static int __init oops_setup(char *s)
{
if (!s)
return -EINVAL;
if (!strcmp(s, "panic"))
panic_on_oops = 1;
return 0;
}
early_param("oops", oops_setup);
static int __init kstack_setup(char *s)
{
if (!s)
return -EINVAL;
kstack_depth_to_print = simple_strtoul(s, NULL, 0);
return 0;
}
early_param("kstack", kstack_setup);
static int __init code_bytes_setup(char *s)
{
code_bytes = simple_strtoul(s, NULL, 0);
if (code_bytes > 8192)
code_bytes = 8192;
return 1;
}
__setup("code_bytes=", code_bytes_setup);
......@@ -730,6 +730,7 @@ error_code:
movl $(__USER_DS), %ecx
movl %ecx, %ds
movl %ecx, %es
TRACE_IRQS_OFF
movl %esp,%eax # pt_regs pointer
call *%edi
jmp ret_from_exception
......@@ -760,20 +761,9 @@ ENTRY(device_not_available)
RING0_INT_FRAME
pushl $-1 # mark this as an int
CFI_ADJUST_CFA_OFFSET 4
SAVE_ALL
GET_CR0_INTO_EAX
testl $0x4, %eax # EM (math emulation bit)
jne device_not_available_emulate
preempt_stop(CLBR_ANY)
call math_state_restore
jmp ret_from_exception
device_not_available_emulate:
pushl $0 # temporary storage for ORIG_EIP
pushl $do_device_not_available
CFI_ADJUST_CFA_OFFSET 4
call math_emulate
addl $4, %esp
CFI_ADJUST_CFA_OFFSET -4
jmp ret_from_exception
jmp error_code
CFI_ENDPROC
END(device_not_available)
......@@ -814,6 +804,7 @@ debug_stack_correct:
pushl $-1 # mark this as an int
CFI_ADJUST_CFA_OFFSET 4
SAVE_ALL
TRACE_IRQS_OFF
xorl %edx,%edx # error code 0
movl %esp,%eax # pt_regs pointer
call do_debug
......@@ -858,6 +849,7 @@ nmi_stack_correct:
pushl %eax
CFI_ADJUST_CFA_OFFSET 4
SAVE_ALL
TRACE_IRQS_OFF
xorl %edx,%edx # zero error code
movl %esp,%eax # pt_regs pointer
call do_nmi
......@@ -898,6 +890,7 @@ nmi_espfix_stack:
pushl %eax
CFI_ADJUST_CFA_OFFSET 4
SAVE_ALL
TRACE_IRQS_OFF
FIXUP_ESPFIX_STACK # %eax == %esp
xorl %edx,%edx # zero error code
call do_nmi
......@@ -928,6 +921,7 @@ KPROBE_ENTRY(int3)
pushl $-1 # mark this as an int
CFI_ADJUST_CFA_OFFSET 4
SAVE_ALL
TRACE_IRQS_OFF
xorl %edx,%edx # zero error code
movl %esp,%eax # pt_regs pointer
call do_int3
......@@ -1030,7 +1024,7 @@ ENTRY(machine_check)
RING0_INT_FRAME
pushl $0
CFI_ADJUST_CFA_OFFSET 4
pushl machine_check_vector
pushl $do_machine_check
CFI_ADJUST_CFA_OFFSET 4
jmp error_code
CFI_ENDPROC
......
......@@ -667,6 +667,13 @@ END(stub_rt_sigreturn)
SAVE_ARGS
leaq -ARGOFFSET(%rsp),%rdi # arg1 for handler
pushq %rbp
/*
* Save rbp twice: One is for marking the stack frame, as usual, and the
* other, to fill pt_regs properly. This is because bx comes right
* before the last saved register in that structure, and not bp. If the
* base pointer were in the place bx is today, this would not be needed.
*/
movq %rbp, -8(%rsp)
CFI_ADJUST_CFA_OFFSET 8
CFI_REL_OFFSET rbp, 0
movq %rsp,%rbp
......@@ -932,6 +939,9 @@ END(spurious_interrupt)
.if \ist
movq %gs:pda_data_offset, %rbp
.endif
.if \irqtrace
TRACE_IRQS_OFF
.endif
movq %rsp,%rdi
movq ORIG_RAX(%rsp),%rsi
movq $-1,ORIG_RAX(%rsp)
......@@ -1058,7 +1068,8 @@ KPROBE_ENTRY(error_entry)
je error_kernelspace
error_swapgs:
SWAPGS
error_sti:
error_sti:
TRACE_IRQS_OFF
movq %rdi,RDI(%rsp)
CFI_REL_OFFSET rdi,RDI
movq %rsp,%rdi
......@@ -1232,7 +1243,7 @@ ENTRY(simd_coprocessor_error)
END(simd_coprocessor_error)
ENTRY(device_not_available)
zeroentry math_state_restore
zeroentry do_device_not_available
END(device_not_available)
/* runs on exception stack */
......
......@@ -109,6 +109,7 @@ struct oem_table {
};
extern int find_unisys_acpi_oem_table(unsigned long *oem_addr);
extern void unmap_unisys_acpi_oem_table(unsigned long oem_addr);
#endif
struct mip_reg {
......@@ -243,21 +244,38 @@ parse_unisys_oem (char *oemptr)
}
#ifdef CONFIG_ACPI
int __init
find_unisys_acpi_oem_table(unsigned long *oem_addr)
static unsigned long oem_addrX;
static unsigned long oem_size;
int __init find_unisys_acpi_oem_table(unsigned long *oem_addr)
{
struct acpi_table_header *header = NULL;
int i = 0;
while (ACPI_SUCCESS(acpi_get_table("OEM1", i++, &header))) {
acpi_size tbl_size;
while (ACPI_SUCCESS(acpi_get_table_with_size("OEM1", i++, &header, &tbl_size))) {
if (!memcmp((char *) &header->oem_id, "UNISYS", 6)) {
struct oem_table *t = (struct oem_table *)header;
*oem_addr = (unsigned long)__acpi_map_table(t->OEMTableAddr,
t->OEMTableSize);
oem_addrX = t->OEMTableAddr;
oem_size = t->OEMTableSize;
early_acpi_os_unmap_memory(header, tbl_size);
*oem_addr = (unsigned long)__acpi_map_table(oem_addrX,
oem_size);
return 0;
}
early_acpi_os_unmap_memory(header, tbl_size);
}
return -1;
}
void __init unmap_unisys_acpi_oem_table(unsigned long oem_addr)
{
if (!oem_addr)
return;
__acpi_unmap_table((char *)oem_addr, oem_size);
}
#endif
static void
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment