[RFC PATCH] x86 NMI-safe INT3 and Page Fault

From: Mathieu Desnoyers
Date: Thu Apr 10 2008 - 11:38:20 EST


Implements an alternative iret with popf and far return so trap and exception
handlers can return to the NMI handler without issuing iret. iret would cause
NMIs to be reenabled prematurely.

It allows placing immediate values (and therefore optimized trace_marks) in NMI
code and accessing vmalloc'd memory, which allows executing module code or
accessing vmapped or vmalloc'd areas from NMI context. This is very useful to
tracers like LTTng.

This patch makes all faults, traps and exception safe to be called from NMI
context *except* single-stepping, which requires iret to restore the TF (trap
flag) and jump to the return address in a single instruction. Sorry, no kprobes
support in NMI handlers because of this limitation. We cannot single-step an
NMI handler, because iret must set the TF flag and return back to the
instruction to single-step in a single instruction. This cannot be emulated with
popf/lret, because lret would be single-stepped. It does not apply to immediate
values because they do not use single-stepping. This code detects if the TF
flag is set and uses the iret path for single-stepping, even if it reactivates
NMIs prematurely.

alpha and avr32 use the active count bit 31. This patch moves them to 28.

TODO : support paravirt ops.
TODO : test x86_64
TODO : test alpha and avr32 active count modification

tested on x86_32 (tests implemented in a separate patch) :
- instrumented the return path to export the EIP, CS and EFLAGS values when
taken so we know the return path code has been executed.
- trace_mark, using immediate values, with 10ms delay with the breakpoint
activated. Runs well through the return path.
- tested vmalloc faults in NMI handler by placing a non-optimized marker in the
NMI handler (so no breakpoint is executed) and connecting a probe which
touches every pages of a 20MB vmalloc'd buffer. It executes trough the return
path without problem.

"This way lies madness. Don't go there."
- Andi

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@xxxxxxxxxx>
CC: Andi Kleen <andi@xxxxxxxxxxxxxx>
CC: akpm@xxxxxxxx
CC: mingo@xxxxxxx
---
arch/x86/kernel/entry_32.S | 9 +++++++
arch/x86/kernel/entry_64.S | 6 +++++
include/asm-alpha/thread_info.h | 2 -
include/asm-avr32/thread_info.h | 2 -
include/asm-x86/irqflags.h | 48 ++++++++++++++++++++++++++++++++++++++++
include/linux/hardirq.h | 24 ++++++++++++++++++--
6 files changed, 87 insertions(+), 4 deletions(-)

Index: linux-2.6-lttng/include/linux/hardirq.h
===================================================================
--- linux-2.6-lttng.orig/include/linux/hardirq.h 2008-04-09 19:17:37.000000000 -0400
+++ linux-2.6-lttng/include/linux/hardirq.h 2008-04-09 21:24:03.000000000 -0400
@@ -22,10 +22,13 @@
* PREEMPT_MASK: 0x000000ff
* SOFTIRQ_MASK: 0x0000ff00
* HARDIRQ_MASK: 0x0fff0000
+ * HARDNMI_MASK: 0x40000000
*/
#define PREEMPT_BITS 8
#define SOFTIRQ_BITS 8

+#define HARDNMI_BITS 1
+
#ifndef HARDIRQ_BITS
#define HARDIRQ_BITS 12

@@ -45,16 +48,19 @@
#define PREEMPT_SHIFT 0
#define SOFTIRQ_SHIFT (PREEMPT_SHIFT + PREEMPT_BITS)
#define HARDIRQ_SHIFT (SOFTIRQ_SHIFT + SOFTIRQ_BITS)
+#define HARDNMI_SHIFT (30)

#define __IRQ_MASK(x) ((1UL << (x))-1)

#define PREEMPT_MASK (__IRQ_MASK(PREEMPT_BITS) << PREEMPT_SHIFT)
#define SOFTIRQ_MASK (__IRQ_MASK(SOFTIRQ_BITS) << SOFTIRQ_SHIFT)
#define HARDIRQ_MASK (__IRQ_MASK(HARDIRQ_BITS) << HARDIRQ_SHIFT)
+#define HARDNMI_MASK (__IRQ_MASK(HARDNMI_BITS) << HARDNMI_SHIFT)

#define PREEMPT_OFFSET (1UL << PREEMPT_SHIFT)
#define SOFTIRQ_OFFSET (1UL << SOFTIRQ_SHIFT)
#define HARDIRQ_OFFSET (1UL << HARDIRQ_SHIFT)
+#define HARDNMI_OFFSET (1UL << HARDNMI_SHIFT)

#if PREEMPT_ACTIVE < (1 << (HARDIRQ_SHIFT + HARDIRQ_BITS))
#error PREEMPT_ACTIVE is too low!
@@ -63,6 +69,7 @@
#define hardirq_count() (preempt_count() & HARDIRQ_MASK)
#define softirq_count() (preempt_count() & SOFTIRQ_MASK)
#define irq_count() (preempt_count() & (HARDIRQ_MASK | SOFTIRQ_MASK))
+#define hardnmi_count() (preempt_count() & HARDNMI_MASK)

/*
* Are we doing bottom half or hardware interrupt processing?
@@ -71,6 +78,7 @@
#define in_irq() (hardirq_count())
#define in_softirq() (softirq_count())
#define in_interrupt() (irq_count())
+#define in_nmi() (hardnmi_count())

/*
* Are we running in atomic context? WARNING: this macro cannot
@@ -159,7 +167,19 @@ extern void irq_enter(void);
*/
extern void irq_exit(void);

-#define nmi_enter() do { lockdep_off(); __irq_enter(); } while (0)
-#define nmi_exit() do { __irq_exit(); lockdep_on(); } while (0)
+#define nmi_enter() \
+ do { \
+ lockdep_off(); \
+ BUG_ON(hardnmi_count()); \
+ add_preempt_count(HARDNMI_OFFSET); \
+ __irq_enter(); \
+ } while (0)
+
+#define nmi_exit() \
+ do { \
+ __irq_exit(); \
+ sub_preempt_count(HARDNMI_OFFSET); \
+ lockdep_on(); \
+ } while (0)

#endif /* LINUX_HARDIRQ_H */
Index: linux-2.6-lttng/arch/x86/kernel/entry_32.S
===================================================================
--- linux-2.6-lttng.orig/arch/x86/kernel/entry_32.S 2008-04-09 19:21:08.000000000 -0400
+++ linux-2.6-lttng/arch/x86/kernel/entry_32.S 2008-04-10 11:03:33.000000000 -0400
@@ -265,6 +265,8 @@ END(ret_from_exception)
#ifdef CONFIG_PREEMPT
ENTRY(resume_kernel)
DISABLE_INTERRUPTS(CLBR_ANY)
+ testl $0x40000000,TI_preempt_count(%ebp) # nested over NMI ?
+ jnz return_to_nmi
cmpl $0,TI_preempt_count(%ebp) # non-zero preempt_count ?
jnz restore_nocheck
need_resched:
@@ -411,6 +413,13 @@ restore_nocheck_notrace:
CFI_ADJUST_CFA_OFFSET -4
irq_return:
INTERRUPT_RETURN
+return_to_nmi:
+ TRACE_IRQS_IRET
+ RESTORE_REGS
+ addl $4, %esp # skip orig_eax/error_code
+ CFI_ADJUST_CFA_OFFSET -4
+ INTERRUPT_RETURN_NMI_SAFE
+
.section .fixup,"ax"
iret_exc:
pushl $0 # no error code
Index: linux-2.6-lttng/arch/x86/kernel/entry_64.S
===================================================================
--- linux-2.6-lttng.orig/arch/x86/kernel/entry_64.S 2008-04-09 19:21:08.000000000 -0400
+++ linux-2.6-lttng/arch/x86/kernel/entry_64.S 2008-04-09 21:01:19.000000000 -0400
@@ -824,8 +824,14 @@ paranoid_swapgs\trace:
.endif
SWAPGS_UNSAFE_STACK
paranoid_restore\trace:
+ GET_THREAD_INFO(%rcx)
+ testl $0x40000000,threadinfo_preempt_count(%rcx) /* Nested over NMI ? */
+ jnz return_to_nmi\trace
RESTORE_ALL 8
jmp irq_return
+return_to_nmi\trace:
+ RESTORE_ALL 8
+ INTERRUPT_RETURN_NMI_SAFE
paranoid_userspace\trace:
GET_THREAD_INFO(%rcx)
movl threadinfo_flags(%rcx),%ebx
Index: linux-2.6-lttng/include/asm-x86/irqflags.h
===================================================================
--- linux-2.6-lttng.orig/include/asm-x86/irqflags.h 2008-04-09 19:17:37.000000000 -0400
+++ linux-2.6-lttng/include/asm-x86/irqflags.h 2008-04-10 10:53:24.000000000 -0400
@@ -138,12 +138,60 @@ static inline unsigned long __raw_local_

#ifdef CONFIG_X86_64
#define INTERRUPT_RETURN iretq
+
+/*
+ * Protected mode only, no V8086. Implies that protected mode must
+ * be entered before NMIs or MCEs are enabled. Only returns from a trap or
+ * exception to a NMI context (intra-privilege level return). Should be used
+ * upon trap or exception return when nested over a NMI context so no iret is
+ * issued.
+ *
+ * The stack, at that point, looks like :
+ *
+ * 0(esp) EIP
+ * 8(esp) CS
+ * 16(esp) EFLAGS
+ *
+ * Upon execution :
+ * Copy the stack eflags to top of stack
+ * Pop eflags into the eflags register
+ * Far return: pop EIP and CS into their register, and additionally pop EFLAGS.
+ */
+#define INTERRUPT_RETURN_NMI_SAFE pushl 16(%esp); \
+ popfl; \
+ .byte 0xCA; \
+ .word 8;
+
#define ENABLE_INTERRUPTS_SYSCALL_RET \
movq %gs:pda_oldrsp, %rsp; \
swapgs; \
sysretq;
#else
#define INTERRUPT_RETURN iret
+
+/*
+ * Protected mode only, no V8086. Implies that protected mode must
+ * be entered before NMIs or MCEs are enabled. Only returns from a trap or
+ * exception to a NMI context (intra-privilege level return). Should be used
+ * upon trap or exception return when nested over a NMI context so no iret is
+ * issued.
+ *
+ * The stack, at that point, looks like :
+ *
+ * 0(esp) EIP
+ * 4(esp) CS
+ * 8(esp) EFLAGS
+ *
+ * Upon execution :
+ * Copy the stack eflags to top of stack
+ * Pop eflags into the eflags register
+ * Far return: pop EIP and CS into their register, and additionally pop EFLAGS.
+ */
+#define INTERRUPT_RETURN_NMI_SAFE pushl 8(%esp); \
+ popfl; \
+ .byte 0xCA; \
+ .word 4;
+
#define ENABLE_INTERRUPTS_SYSCALL_RET sti; sysexit
#define GET_CR0_INTO_EAX movl %cr0, %eax
#endif
Index: linux-2.6-lttng/include/asm-alpha/thread_info.h
===================================================================
--- linux-2.6-lttng.orig/include/asm-alpha/thread_info.h 2008-04-09 20:02:09.000000000 -0400
+++ linux-2.6-lttng/include/asm-alpha/thread_info.h 2008-04-09 20:02:46.000000000 -0400
@@ -57,7 +57,7 @@ register struct thread_info *__current_t

#endif /* __ASSEMBLY__ */

-#define PREEMPT_ACTIVE 0x40000000
+#define PREEMPT_ACTIVE 0x10000000

/*
* Thread information flags:
Index: linux-2.6-lttng/include/asm-avr32/thread_info.h
===================================================================
--- linux-2.6-lttng.orig/include/asm-avr32/thread_info.h 2008-04-09 20:02:58.000000000 -0400
+++ linux-2.6-lttng/include/asm-avr32/thread_info.h 2008-04-09 20:03:07.000000000 -0400
@@ -70,7 +70,7 @@ static inline struct thread_info *curren

#endif /* !__ASSEMBLY__ */

-#define PREEMPT_ACTIVE 0x40000000
+#define PREEMPT_ACTIVE 0x10000000

/*
* Thread information flags

--
Mathieu Desnoyers
Computer Engineering Ph.D. Student, Ecole Polytechnique de Montreal
OpenPGP key fingerprint: 8CD5 52C3 8E3C 4140 715F BA06 3F25 A8FE 3BAE 9A68
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/