From: "Jan Beulich" <[email protected]>
.. when dumping register state. This is particularly useful when gcc
managed to tail-call optimize an indirect call which happens to hit a
NULL (or otherwise invalid) pointer.
The result is unreliable because interrupts happening inbetween can mess
it up
AK: added some warnings that the result can be unreliable
Signed-off-by: Jan Beulich <[email protected]>
Signed-off-by: Andi Kleen <[email protected]>
Documentation/kernel-parameters.txt | 3 +++
arch/i386/kernel/cpu/amd.c | 4 ++++
arch/i386/kernel/cpu/common.c | 2 ++
arch/i386/kernel/cpu/intel.c | 20 ++++++++++++++------
arch/i386/kernel/traps.c | 35 +++++++++++++++++++++++++++++++++++
arch/x86_64/kernel/setup.c | 23 ++++++++++++++++++-----
arch/x86_64/kernel/traps.c | 33 +++++++++++++++++++++++++++++++++
include/asm-i386/msr-index.h | 3 +++
include/asm-i386/processor.h | 4 ++++
include/asm-x86_64/msr.h | 6 ++++++
include/asm-x86_64/processor.h | 3 +++
11 files changed, 125 insertions(+), 11 deletions(-)
Index: linux/Documentation/kernel-parameters.txt
===================================================================
--- linux.orig/Documentation/kernel-parameters.txt
+++ linux/Documentation/kernel-parameters.txt
@@ -1152,6 +1152,9 @@ and is between 256 and 4096 characters.
nolapic_timer [X86-32,APIC] Do not use the local APIC timer.
+ noler [X86-32/X86-64] Do not print last exception records
+ with kernel register dumps.
+
noltlbs [PPC] Do not use large page/tlb entries for kernel
lowmem mapping on PPC40x.
Index: linux/arch/i386/kernel/cpu/amd.c
===================================================================
--- linux.orig/arch/i386/kernel/cpu/amd.c
+++ linux/arch/i386/kernel/cpu/amd.c
@@ -238,9 +238,13 @@ static void __cpuinit init_amd(struct cp
case 0x10:
case 0x11:
set_bit(X86_FEATURE_K8, c->x86_capability);
+ if (ler_enabled)
+ __get_cpu_var(ler_msr) = MSR_IA32_LASTINTFROMIP;
break;
case 6:
set_bit(X86_FEATURE_K7, c->x86_capability);
+ if (ler_enabled)
+ __get_cpu_var(ler_msr) = MSR_IA32_LASTINTFROMIP;
break;
}
if (c->x86 >= 6)
Index: linux/arch/i386/kernel/cpu/common.c
===================================================================
--- linux.orig/arch/i386/kernel/cpu/common.c
+++ linux/arch/i386/kernel/cpu/common.c
@@ -503,6 +503,8 @@ static void __cpuinit identify_cpu(struc
/* Init Machine Check Exception if available. */
mcheck_init(c);
+
+ ler_enable();
}
void __init identify_boot_cpu(void)
Index: linux/arch/i386/kernel/cpu/intel.c
===================================================================
--- linux.orig/arch/i386/kernel/cpu/intel.c
+++ linux/arch/i386/kernel/cpu/intel.c
@@ -188,15 +188,23 @@ static void __cpuinit init_intel(struct
}
#endif
- if (c->x86 == 15) {
+ switch (c->x86) {
+ case 15:
set_bit(X86_FEATURE_P4, c->x86_capability);
set_bit(X86_FEATURE_SYNC_RDTSC, c->x86_capability);
- }
- if (c->x86 == 6)
+ if (c->x86_model >= 0x03)
+ set_bit(X86_FEATURE_CONSTANT_TSC, c->x86_capability);
+ if (ler_enabled)
+ __get_cpu_var(ler_msr) = MSR_P4_LER_FROM_LIP;
+ break;
+ case 6:
set_bit(X86_FEATURE_P3, c->x86_capability);
- if ((c->x86 == 0xf && c->x86_model >= 0x03) ||
- (c->x86 == 0x6 && c->x86_model >= 0x0e))
- set_bit(X86_FEATURE_CONSTANT_TSC, c->x86_capability);
+ if (c->x86_model >= 0x0e)
+ set_bit(X86_FEATURE_CONSTANT_TSC, c->x86_capability);
+ if (ler_enabled)
+ __get_cpu_var(ler_msr) = MSR_IA32_LASTINTFROMIP;
+ break;
+ }
if (cpu_has_ds) {
unsigned int l1;
Index: linux/arch/i386/kernel/traps.c
===================================================================
--- linux.orig/arch/i386/kernel/traps.c
+++ linux/arch/i386/kernel/traps.c
@@ -374,6 +374,20 @@ void show_registers(struct pt_regs *regs
unsigned int code_len = code_bytes;
unsigned char c;
+ if (oops_in_progress && __get_cpu_var(ler_msr)) {
+ u32 from, to, hi;
+
+ if (rdmsr_safe(__get_cpu_var(ler_msr), &from, &hi) == 0
+ && rdmsr_safe(__get_cpu_var(ler_msr) + 1, &to, &hi) == 0) {
+ printk("\n" KERN_EMERG
+ "last branch before last exception/interrupt\n");
+ printk(KERN_EMERG " from %08x", from);
+ print_symbol(" (%s)\n", from);
+ printk(KERN_EMERG " to %08x", to);
+ print_symbol(" (%s)", to);
+ } else
+ __get_cpu_var(ler_msr) = 0;
+ }
printk("\n" KERN_EMERG "Stack: ");
show_stack_log_lvl(NULL, regs, ®s->esp, KERN_EMERG);
@@ -413,6 +427,19 @@ int is_valid_bugaddr(unsigned long eip)
return ud2 == 0x0b0f;
}
+DEFINE_PER_CPU(u32, ler_msr);
+int ler_enabled = 1;
+
+void ler_enable(void) {
+ if (__get_cpu_var(ler_msr)) {
+ u32 lo, hi;
+
+ if (rdmsr_safe(MSR_IA32_DEBUGCTLMSR, &lo, &hi) < 0
+ || wrmsr_safe(MSR_IA32_DEBUGCTLMSR, lo | 1, hi) < 0)
+ __get_cpu_var(ler_msr) = 0;
+ }
+}
+
/*
* This is gone through when something in the kernel has done something bad and
* is about to be terminated.
@@ -891,6 +918,7 @@ fastcall void __kprobes do_debug(struct
struct task_struct *tsk = current;
get_debugreg(condition, 6);
+ ler_enable();
if (notify_die(DIE_DEBUG, "debug", regs, condition, error_code,
SIGTRAP) == NOTIFY_STOP)
@@ -1275,6 +1303,13 @@ static int __init kstack_setup(char *s)
}
__setup("kstack=", kstack_setup);
+static int __init ler_setup(char *s)
+{
+ ler_enabled = 0;
+ return 1;
+}
+__setup("noler", ler_setup);
+
static int __init code_bytes_setup(char *s)
{
code_bytes = simple_strtoul(s, NULL, 0);
Index: linux/arch/x86_64/kernel/setup.c
===================================================================
--- linux.orig/arch/x86_64/kernel/setup.c
+++ linux/arch/x86_64/kernel/setup.c
@@ -639,6 +639,9 @@ static void __cpuinit init_amd(struct cp
!rdmsr_safe(MSR_VM_CR, &flags, &dummy) &&
(flags & 0x18))
set_bit(X86_FEATURE_VIRT_DISABLED, &c->x86_capability);
+
+ if (ler_enabled && c->x86 <= 17)
+ __get_cpu_var(ler_msr) = MSR_IA32_LASTINTFROMIP;
}
static int enable_svm_lock(char *s)
@@ -774,13 +777,22 @@ static void __cpuinit init_intel(struct
c->x86_phys_bits = 36;
}
- if (c->x86 == 15)
+ switch (c->x86) {
+ case 15:
c->x86_cache_alignment = c->x86_clflush_size * 2;
- if ((c->x86 == 0xf && c->x86_model >= 0x03) ||
- (c->x86 == 0x6 && c->x86_model >= 0x0e))
- set_bit(X86_FEATURE_CONSTANT_TSC, &c->x86_capability);
- if (c->x86 == 6)
+ if (c->x86_model >= 0x03)
+ set_bit(X86_FEATURE_CONSTANT_TSC, &c->x86_capability);
+ if (ler_enabled)
+ __get_cpu_var(ler_msr) = MSR_P4_LER_FROM_LIP;
+ break;
+ case 6:
+ if (c->x86_model >= 0x0e)
+ set_bit(X86_FEATURE_CONSTANT_TSC, &c->x86_capability);
set_bit(X86_FEATURE_REP_GOOD, &c->x86_capability);
+ if (ler_enabled)
+ __get_cpu_var(ler_msr) = MSR_IA32_LASTINTFROMIP;
+ break;
+ }
if (c->x86 == 15)
set_bit(X86_FEATURE_SYNC_RDTSC, &c->x86_capability);
else
@@ -951,6 +963,7 @@ void __cpuinit identify_cpu(struct cpuin
#ifdef CONFIG_NUMA
numa_add_cpu(smp_processor_id());
#endif
+ ler_enable();
}
Index: linux/arch/x86_64/kernel/traps.c
===================================================================
--- linux.orig/arch/x86_64/kernel/traps.c
+++ linux/arch/x86_64/kernel/traps.c
@@ -492,6 +492,19 @@ void show_registers(struct pt_regs *regs
* time of the fault..
*/
if (in_kernel) {
+ if (oops_in_progress && __get_cpu_var(ler_msr)) {
+ u64 from, to;
+
+ if (checking_rdmsrl(__get_cpu_var(ler_msr), from) == 0
+ && checking_rdmsrl(__get_cpu_var(ler_msr) + 1, to) == 0) {
+ printk("last branch before last exception/interrupt\n");
+ printk(" from ");
+ printk_address(from);
+ printk(" to ");
+ printk_address(to);
+ } else
+ __get_cpu_var(ler_msr) = 0;
+ }
printk("Stack: ");
_show_stack(NULL, regs, (unsigned long*)rsp);
@@ -530,6 +543,19 @@ void out_of_line_bug(void)
EXPORT_SYMBOL(out_of_line_bug);
#endif
+DEFINE_PER_CPU(u32, ler_msr);
+int ler_enabled = 1;
+
+void ler_enable(void) {
+ if (__get_cpu_var(ler_msr)) {
+ u32 lo, hi;
+
+ if (rdmsr_safe(MSR_IA32_DEBUGCTLMSR, &lo, &hi) < 0
+ || wrmsr_safe(MSR_IA32_DEBUGCTLMSR, lo | 1, hi) < 0)
+ __get_cpu_var(ler_msr) = 0;
+ }
+}
+
static DEFINE_SPINLOCK(die_lock);
static int die_owner = -1;
static unsigned int die_nest_count;
@@ -920,6 +946,7 @@ asmlinkage void __kprobes do_debug(struc
siginfo_t info;
get_debugreg(condition, 6);
+ ler_enable();
if (notify_die(DIE_DEBUG, "debug", regs, condition, error_code,
SIGTRAP) == NOTIFY_STOP)
@@ -1188,6 +1215,12 @@ void __init trap_init(void)
cpu_init();
}
+static int __init ler_setup(char *s)
+{
+ ler_enabled = 0;
+ return 1;
+}
+__setup("noler", ler_setup);
static int __init oops_setup(char *s)
{
Index: linux/include/asm-i386/msr-index.h
===================================================================
--- linux.orig/include/asm-i386/msr-index.h
+++ linux/include/asm-i386/msr-index.h
@@ -63,6 +63,9 @@
#define MSR_IA32_LASTINTFROMIP 0x000001dd
#define MSR_IA32_LASTINTTOIP 0x000001de
+#define MSR_P4_LER_FROM_LIP 0x000001d7
+#define MSR_P4_LER_TO_LIP 0x000001d8
+
#define MSR_IA32_MC0_CTL 0x00000400
#define MSR_IA32_MC0_STATUS 0x00000401
#define MSR_IA32_MC0_ADDR 0x00000402
Index: linux/include/asm-i386/processor.h
===================================================================
--- linux.orig/include/asm-i386/processor.h
+++ linux/include/asm-i386/processor.h
@@ -643,6 +643,10 @@ static inline unsigned int cpuid_edx(uns
return edx;
}
+DECLARE_PER_CPU(u32, ler_msr);
+extern int ler_enabled;
+void ler_enable(void);
+
/* generic versions from gas */
#define GENERIC_NOP1 ".byte 0x90\n"
#define GENERIC_NOP2 ".byte 0x89,0xf6\n"
Index: linux/include/asm-x86_64/msr.h
===================================================================
--- linux.orig/include/asm-x86_64/msr.h
+++ linux/include/asm-x86_64/msr.h
@@ -63,6 +63,12 @@
:"c"(msr), "i"(-EIO), "0"(0)); \
ret__; })
+#define checking_rdmsrl(msr,val) ({ \
+ u32 lo__, hi__; \
+ int rc__ = rdmsr_safe(msr, &lo__, &hi__); \
+ val = lo__ | ((u64)hi__ << 32); \
+ rc__; })
+
#define rdtsc(low,high) \
__asm__ __volatile__("rdtsc" : "=a" (low), "=d" (high))
Index: linux/include/asm-x86_64/processor.h
===================================================================
--- linux.orig/include/asm-x86_64/processor.h
+++ linux/include/asm-x86_64/processor.h
@@ -334,6 +334,9 @@ struct extended_sigtable {
struct extended_signature sigs[0];
};
+DECLARE_PER_CPU(u32, ler_msr);
+extern int ler_enabled;
+void ler_enable(void);
#define ASM_NOP1 K8_NOP1
#define ASM_NOP2 K8_NOP2
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
[Index of Archives]
[Kernel Newbies]
[Netfilter]
[Bugtraq]
[Photo]
[Stuff]
[Gimp]
[Yosemite News]
[MIPS Linux]
[ARM Linux]
[Linux Security]
[Linux RAID]
[Video 4 Linux]
[Linux for the blind]
[Linux Resources]