Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (470 commits)
  x86: Fix comments of register/stack access functions
  perf tools: Replace %m with %a in sscanf
  hw-breakpoints: Keep track of user disabled breakpoints
  tracing/syscalls: Make syscall events print callbacks static
  tracing: Add DEFINE_EVENT(), DEFINE_SINGLE_EVENT() support to docbook
  perf: Don't free perf_mmap_data until work has been done
  perf_event: Fix compile error
  perf tools: Fix _GNU_SOURCE macro related strndup() build error
  trace_syscalls: Remove unused syscall_name_to_nr()
  trace_syscalls: Simplify syscall profile
  trace_syscalls: Remove duplicate init_enter_##sname()
  trace_syscalls: Add syscall_nr field to struct syscall_metadata
  trace_syscalls: Remove enter_id exit_id
  trace_syscalls: Set event_enter_##sname->data to its metadata
  trace_syscalls: Remove unused event_syscall_enter and event_syscall_exit
  perf_event: Initialize data.period in perf_swevent_hrtimer()
  perf probe: Simplify event naming
  perf probe: Add --list option for listing current probe events
  perf probe: Add argv_split() from lib/argv_split.c
  perf probe: Move probe event utility functions to probe-event.c
  ...

Documentation/DocBook/tracepoint.tmpl

@@ -86,4 +86,9 @@
 !Iinclude/trace/events/irq.h
   </chapter>
 
+  <chapter id="signal">
+   <title>SIGNAL</title>
+!Iinclude/trace/events/signal.h
+  </chapter>
+
 </book>

Documentation/trace/kprobetrace.txt

@@ -0,0 +1,149 @@
+                        Kprobe-based Event Tracing
+                        ==========================
+
+                 Documentation is written by Masami Hiramatsu
+
+
+Overview
+--------
+These events are similar to tracepoint based events. Instead of Tracepoint,
+this is based on kprobes (kprobe and kretprobe). So it can probe wherever
+kprobes can probe (this means, all functions body except for __kprobes
+functions). Unlike the Tracepoint based event, this can be added and removed
+dynamically, on the fly.
+
+To enable this feature, build your kernel with CONFIG_KPROBE_TRACING=y.
+
+Similar to the events tracer, this doesn't need to be activated via
+current_tracer. Instead of that, add probe points via
+/sys/kernel/debug/tracing/kprobe_events, and enable it via
+/sys/kernel/debug/tracing/events/kprobes/<EVENT>/enabled.
+
+
+Synopsis of kprobe_events
+-------------------------
+  p[:[GRP/]EVENT] SYMBOL[+offs]|MEMADDR [FETCHARGS]	: Set a probe
+  r[:[GRP/]EVENT] SYMBOL[+0] [FETCHARGS]		: Set a return probe
+
+ GRP		: Group name. If omitted, use "kprobes" for it.
+ EVENT		: Event name. If omitted, the event name is generated
+		  based on SYMBOL+offs or MEMADDR.
+ SYMBOL[+offs]	: Symbol+offset where the probe is inserted.
+ MEMADDR	: Address where the probe is inserted.
+
+ FETCHARGS	: Arguments. Each probe can have up to 128 args.
+  %REG		: Fetch register REG
+  @ADDR		: Fetch memory at ADDR (ADDR should be in kernel)
+  @SYM[+|-offs]	: Fetch memory at SYM +|- offs (SYM should be a data symbol)
+  $stackN	: Fetch Nth entry of stack (N >= 0)
+  $stack	: Fetch stack address.
+  $argN		: Fetch function argument. (N >= 0)(*)
+  $retval	: Fetch return value.(**)
+  +|-offs(FETCHARG) : Fetch memory at FETCHARG +|- offs address.(***)
+  NAME=FETCHARG: Set NAME as the argument name of FETCHARG.
+
+  (*) aN may not correct on asmlinkaged functions and at the middle of
+      function body.
+  (**) only for return probe.
+  (***) this is useful for fetching a field of data structures.
+
+
+Per-Probe Event Filtering
+-------------------------
+ Per-probe event filtering feature allows you to set different filter on each
+probe and gives you what arguments will be shown in trace buffer. If an event
+name is specified right after 'p:' or 'r:' in kprobe_events, it adds an event
+under tracing/events/kprobes/<EVENT>, at the directory you can see 'id',
+'enabled', 'format' and 'filter'.
+
+enabled:
+  You can enable/disable the probe by writing 1 or 0 on it.
+
+format:
+  This shows the format of this probe event.
+
+filter:
+  You can write filtering rules of this event.
+
+id:
+  This shows the id of this probe event.
+
+
+Event Profiling
+---------------
+ You can check the total number of probe hits and probe miss-hits via
+/sys/kernel/debug/tracing/kprobe_profile.
+ The first column is event name, the second is the number of probe hits,
+the third is the number of probe miss-hits.
+
+
+Usage examples
+--------------
+To add a probe as a new event, write a new definition to kprobe_events
+as below.
+
+  echo p:myprobe do_sys_open dfd=$arg0 filename=$arg1 flags=$arg2 mode=$arg3 > /sys/kernel/debug/tracing/kprobe_events
+
+ This sets a kprobe on the top of do_sys_open() function with recording
+1st to 4th arguments as "myprobe" event. As this example shows, users can
+choose more familiar names for each arguments.
+
+  echo r:myretprobe do_sys_open $retval >> /sys/kernel/debug/tracing/kprobe_events
+
+ This sets a kretprobe on the return point of do_sys_open() function with
+recording return value as "myretprobe" event.
+ You can see the format of these events via
+/sys/kernel/debug/tracing/events/kprobes/<EVENT>/format.
+
+  cat /sys/kernel/debug/tracing/events/kprobes/myprobe/format
+name: myprobe
+ID: 75
+format:
+	field:unsigned short common_type;	offset:0;	size:2;
+	field:unsigned char common_flags;	offset:2;	size:1;
+	field:unsigned char common_preempt_count;	offset:3;	size:1;
+	field:int common_pid;	offset:4;	size:4;
+	field:int common_tgid;	offset:8;	size:4;
+
+	field: unsigned long ip;	offset:16;tsize:8;
+	field: int nargs;	offset:24;tsize:4;
+	field: unsigned long dfd;	offset:32;tsize:8;
+	field: unsigned long filename;	offset:40;tsize:8;
+	field: unsigned long flags;	offset:48;tsize:8;
+	field: unsigned long mode;	offset:56;tsize:8;
+
+print fmt: "(%lx) dfd=%lx filename=%lx flags=%lx mode=%lx", REC->ip, REC->dfd, REC->filename, REC->flags, REC->mode
+
+
+ You can see that the event has 4 arguments as in the expressions you specified.
+
+  echo > /sys/kernel/debug/tracing/kprobe_events
+
+ This clears all probe points.
+
+ Right after definition, each event is disabled by default. For tracing these
+events, you need to enable it.
+
+  echo 1 > /sys/kernel/debug/tracing/events/kprobes/myprobe/enable
+  echo 1 > /sys/kernel/debug/tracing/events/kprobes/myretprobe/enable
+
+ And you can see the traced information via /sys/kernel/debug/tracing/trace.
+
+  cat /sys/kernel/debug/tracing/trace
+# tracer: nop
+#
+#           TASK-PID    CPU#    TIMESTAMP  FUNCTION
+#              | |       |          |         |
+           <...>-1447  [001] 1038282.286875: myprobe: (do_sys_open+0x0/0xd6) dfd=3 filename=7fffd1ec4440 flags=8000 mode=0
+           <...>-1447  [001] 1038282.286878: myretprobe: (sys_openat+0xc/0xe <- do_sys_open) $retval=fffffffffffffffe
+           <...>-1447  [001] 1038282.286885: myprobe: (do_sys_open+0x0/0xd6) dfd=ffffff9c filename=40413c flags=8000 mode=1b6
+           <...>-1447  [001] 1038282.286915: myretprobe: (sys_open+0x1b/0x1d <- do_sys_open) $retval=3
+           <...>-1447  [001] 1038282.286969: myprobe: (do_sys_open+0x0/0xd6) dfd=ffffff9c filename=4041c6 flags=98800 mode=10
+           <...>-1447  [001] 1038282.286976: myretprobe: (sys_open+0x1b/0x1d <- do_sys_open) $retval=3
+
+
+ Each line shows when the kernel hits an event, and <- SYMBOL means kernel
+returns from SYMBOL(e.g. "sys_open+0x1b/0x1d <- do_sys_open" means kernel
+returns from do_sys_open to sys_open+0x1b).
+
+

arch/Kconfig

@@ -126,4 +126,11 @@ config HAVE_DMA_API_DEBUG
 config HAVE_DEFAULT_NO_SPIN_MUTEXES
 	bool
 
+config HAVE_HW_BREAKPOINT
+	bool
+	depends on HAVE_PERF_EVENTS
+	select ANON_INODES
+	select PERF_EVENTS
+
+
 source "kernel/gcov/Kconfig"

arch/powerpc/Kconfig.debug

@@ -46,7 +46,7 @@ config DEBUG_STACK_USAGE
 
 config HCALL_STATS
 	bool "Hypervisor call instrumentation"
-	depends on PPC_PSERIES && DEBUG_FS
+	depends on PPC_PSERIES && DEBUG_FS && TRACEPOINTS
 	help
 	  Adds code to keep track of the number of hypervisor calls made and
 	  the amount of time spent in hypervisor calls.  Wall time spent in

arch/powerpc/configs/pseries_defconfig

@@ -1683,7 +1683,7 @@ CONFIG_HAVE_ARCH_KGDB=y
 CONFIG_DEBUG_STACKOVERFLOW=y
 # CONFIG_DEBUG_STACK_USAGE is not set
 # CONFIG_DEBUG_PAGEALLOC is not set
-CONFIG_HCALL_STATS=y
+# CONFIG_HCALL_STATS is not set
 # CONFIG_CODE_PATCHING_SELFTEST is not set
 # CONFIG_FTR_FIXUP_SELFTEST is not set
 # CONFIG_MSI_BITMAP_SELFTEST is not set

arch/powerpc/include/asm/emulated_ops.h

@@ -19,6 +19,7 @@
 #define _ASM_POWERPC_EMULATED_OPS_H
 
 #include <asm/atomic.h>
+#include <linux/perf_event.h>
 
 
 #ifdef CONFIG_PPC_EMULATED_STATS
@@ -57,7 +58,7 @@ extern u32 ppc_warn_emulated;
 
 extern void ppc_warn_emulated_print(const char *type);
 
-#define PPC_WARN_EMULATED(type)						 \
+#define __PPC_WARN_EMULATED(type)					 \
 	do {								 \
 		atomic_inc(&ppc_emulated.type.val);			 \
 		if (ppc_warn_emulated)					 \
@@ -66,8 +67,22 @@ extern void ppc_warn_emulated_print(const char *type);
 
 #else /* !CONFIG_PPC_EMULATED_STATS */
 
-#define PPC_WARN_EMULATED(type)	do { } while (0)
+#define __PPC_WARN_EMULATED(type)	do { } while (0)
 
 #endif /* !CONFIG_PPC_EMULATED_STATS */
 
+#define PPC_WARN_EMULATED(type, regs)					\
+	do {								\
+		perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS,		\
+			1, 0, regs, 0);					\
+		__PPC_WARN_EMULATED(type);				\
+	} while (0)
+
+#define PPC_WARN_ALIGNMENT(type, regs)					\
+	do {								\
+		perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS,		\
+			1, 0, regs, regs->dar);				\
+		__PPC_WARN_EMULATED(type);				\
+	} while (0)
+
 #endif /* _ASM_POWERPC_EMULATED_OPS_H */

arch/powerpc/include/asm/hvcall.h

@@ -274,6 +274,8 @@ struct hcall_stats {
 	unsigned long	num_calls;	/* number of calls (on this CPU) */
 	unsigned long	tb_total;	/* total wall time (mftb) of calls. */
 	unsigned long	purr_total;	/* total cpu time (PURR) of calls. */
+	unsigned long	tb_start;
+	unsigned long	purr_start;
 };
 #define HCALL_STAT_ARRAY_SIZE	((MAX_HCALL_OPCODE >> 2) + 1)
 

arch/powerpc/include/asm/reg.h

@@ -489,6 +489,8 @@
 #define SPRN_MMCR1	798
 #define SPRN_MMCRA	0x312
 #define   MMCRA_SDSYNC	0x80000000UL /* SDAR synced with SIAR */
+#define   MMCRA_SDAR_DCACHE_MISS 0x40000000UL
+#define   MMCRA_SDAR_ERAT_MISS   0x20000000UL
 #define   MMCRA_SIHV	0x10000000UL /* state of MSR HV when SIAR set */
 #define   MMCRA_SIPR	0x08000000UL /* state of MSR PR when SIAR set */
 #define   MMCRA_SLOT	0x07000000UL /* SLOT bits (37-39) */

arch/powerpc/include/asm/trace.h

@@ -0,0 +1,133 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM powerpc
+
+#if !defined(_TRACE_POWERPC_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_POWERPC_H
+
+#include <linux/tracepoint.h>
+
+struct pt_regs;
+
+TRACE_EVENT(irq_entry,
+
+	TP_PROTO(struct pt_regs *regs),
+
+	TP_ARGS(regs),
+
+	TP_STRUCT__entry(
+		__field(struct pt_regs *, regs)
+	),
+
+	TP_fast_assign(
+		__entry->regs = regs;
+	),
+
+	TP_printk("pt_regs=%p", __entry->regs)
+);
+
+TRACE_EVENT(irq_exit,
+
+	TP_PROTO(struct pt_regs *regs),
+
+	TP_ARGS(regs),
+
+	TP_STRUCT__entry(
+		__field(struct pt_regs *, regs)
+	),
+
+	TP_fast_assign(
+		__entry->regs = regs;
+	),
+
+	TP_printk("pt_regs=%p", __entry->regs)
+);
+
+TRACE_EVENT(timer_interrupt_entry,
+
+	TP_PROTO(struct pt_regs *regs),
+
+	TP_ARGS(regs),
+
+	TP_STRUCT__entry(
+		__field(struct pt_regs *, regs)
+	),
+
+	TP_fast_assign(
+		__entry->regs = regs;
+	),
+
+	TP_printk("pt_regs=%p", __entry->regs)
+);
+
+TRACE_EVENT(timer_interrupt_exit,
+
+	TP_PROTO(struct pt_regs *regs),
+
+	TP_ARGS(regs),
+
+	TP_STRUCT__entry(
+		__field(struct pt_regs *, regs)
+	),
+
+	TP_fast_assign(
+		__entry->regs = regs;
+	),
+
+	TP_printk("pt_regs=%p", __entry->regs)
+);
+
+#ifdef CONFIG_PPC_PSERIES
+extern void hcall_tracepoint_regfunc(void);
+extern void hcall_tracepoint_unregfunc(void);
+
+TRACE_EVENT_FN(hcall_entry,
+
+	TP_PROTO(unsigned long opcode, unsigned long *args),
+
+	TP_ARGS(opcode, args),
+
+	TP_STRUCT__entry(
+		__field(unsigned long, opcode)
+	),
+
+	TP_fast_assign(
+		__entry->opcode = opcode;
+	),
+
+	TP_printk("opcode=%lu", __entry->opcode),
+
+	hcall_tracepoint_regfunc, hcall_tracepoint_unregfunc
+);
+
+TRACE_EVENT_FN(hcall_exit,
+
+	TP_PROTO(unsigned long opcode, unsigned long retval,
+		unsigned long *retbuf),
+
+	TP_ARGS(opcode, retval, retbuf),
+
+	TP_STRUCT__entry(
+		__field(unsigned long, opcode)
+		__field(unsigned long, retval)
+	),
+
+	TP_fast_assign(
+		__entry->opcode = opcode;
+		__entry->retval = retval;
+	),
+
+	TP_printk("opcode=%lu retval=%lu", __entry->opcode, __entry->retval),
+
+	hcall_tracepoint_regfunc, hcall_tracepoint_unregfunc
+);
+#endif
+
+#endif /* _TRACE_POWERPC_H */
+
+#undef TRACE_INCLUDE_PATH
+#undef TRACE_INCLUDE_FILE
+
+#define TRACE_INCLUDE_PATH asm
+#define TRACE_INCLUDE_FILE trace
+
+#include <trace/define_trace.h>

arch/powerpc/kernel/align.c

@@ -732,7 +732,7 @@ int fix_alignment(struct pt_regs *regs)
 
 #ifdef CONFIG_SPE
 	if ((instr >> 26) == 0x4) {
-		PPC_WARN_EMULATED(spe);
+		PPC_WARN_ALIGNMENT(spe, regs);
 		return emulate_spe(regs, reg, instr);
 	}
 #endif
@@ -786,7 +786,7 @@ int fix_alignment(struct pt_regs *regs)
 			flags |= SPLT;
 			nb = 8;
 		}
-		PPC_WARN_EMULATED(vsx);
+		PPC_WARN_ALIGNMENT(vsx, regs);
 		return emulate_vsx(addr, reg, areg, regs, flags, nb);
 	}
 #endif
@@ -794,7 +794,7 @@ int fix_alignment(struct pt_regs *regs)
 	 * the exception of DCBZ which is handled as a special case here
 	 */
 	if (instr == DCBZ) {
-		PPC_WARN_EMULATED(dcbz);
+		PPC_WARN_ALIGNMENT(dcbz, regs);
 		return emulate_dcbz(regs, addr);
 	}
 	if (unlikely(nb == 0))
@@ -804,7 +804,7 @@ int fix_alignment(struct pt_regs *regs)
 	 * function
 	 */
 	if (flags & M) {
-		PPC_WARN_EMULATED(multiple);
+		PPC_WARN_ALIGNMENT(multiple, regs);
 		return emulate_multiple(regs, addr, reg, nb,
 					flags, instr, swiz);
 	}
@@ -825,11 +825,11 @@ int fix_alignment(struct pt_regs *regs)
 
 	/* Special case for 16-byte FP loads and stores */
 	if (nb == 16) {
-		PPC_WARN_EMULATED(fp_pair);
+		PPC_WARN_ALIGNMENT(fp_pair, regs);
 		return emulate_fp_pair(addr, reg, flags);
 	}
 
-	PPC_WARN_EMULATED(unaligned);
+	PPC_WARN_ALIGNMENT(unaligned, regs);
 
 	/* If we are loading, get the data from user space, else
 	 * get it from register values

arch/powerpc/kernel/entry_64.S

@@ -551,7 +551,7 @@ restore:
 BEGIN_FW_FTR_SECTION
 	ld	r5,SOFTE(r1)
 FW_FTR_SECTION_ELSE
-	b	iseries_check_pending_irqs
+	b	.Liseries_check_pending_irqs
 ALT_FW_FTR_SECTION_END_IFCLR(FW_FEATURE_ISERIES)
 2:
 	TRACE_AND_RESTORE_IRQ(r5);
@@ -623,7 +623,7 @@ ALT_FW_FTR_SECTION_END_IFCLR(FW_FEATURE_ISERIES)
 
 #endif /* CONFIG_PPC_BOOK3E */
 
-iseries_check_pending_irqs:
+.Liseries_check_pending_irqs:
 #ifdef CONFIG_PPC_ISERIES
 	ld	r5,SOFTE(r1)
 	cmpdi	0,r5,0

arch/powerpc/kernel/exceptions-64s.S

@@ -185,12 +185,15 @@ END_FTR_SECTION_IFSET(CPU_FTR_REAL_LE)
 	 * prolog code of the PerformanceMonitor one. A little
 	 * trickery is thus necessary
 	 */
+performance_monitor_pSeries_1:
 	. = 0xf00
 	b	performance_monitor_pSeries
 
+altivec_unavailable_pSeries_1:
 	. = 0xf20
 	b	altivec_unavailable_pSeries
 
+vsx_unavailable_pSeries_1:
 	. = 0xf40
 	b	vsx_unavailable_pSeries
 

arch/powerpc/kernel/irq.c

@@ -70,6 +70,8 @@
 #include <asm/firmware.h>
 #include <asm/lv1call.h>
 #endif
+#define CREATE_TRACE_POINTS
+#include <asm/trace.h>
 
 int __irq_offset_value;
 static int ppc_spurious_interrupts;
@@ -325,6 +327,8 @@ void do_IRQ(struct pt_regs *regs)
 	struct pt_regs *old_regs = set_irq_regs(regs);
 	unsigned int irq;
 
+	trace_irq_entry(regs);
+
 	irq_enter();
 
 	check_stack_overflow();
@@ -348,6 +352,8 @@ void do_IRQ(struct pt_regs *regs)
 		timer_interrupt(regs);
 	}
 #endif
+
+	trace_irq_exit(regs);
 }
 
 void __init init_IRQ(void)

arch/powerpc/kernel/perf_event.c

@@ -1165,7 +1165,7 @@ static void record_and_restart(struct perf_event *event, unsigned long val,
 	 */
 	if (record) {
 		struct perf_sample_data data = {
-			.addr	= 0,
+			.addr	= ~0ULL,
 			.period	= event->hw.last_period,
 		};
 

arch/powerpc/kernel/power5+-pmu.c

@@ -72,10 +72,6 @@
 #define MMCR1_PMCSEL_SH(n)	(MMCR1_PMC1SEL_SH - (n) * 8)
 #define MMCR1_PMCSEL_MSK	0x7f
 
-/*
- * Bits in MMCRA
- */
-
 /*
  * Layout of constraint bits:
  * 6666555555555544444444443333333333222222222211111111110000000000

arch/powerpc/kernel/power5-pmu.c

@@ -72,10 +72,6 @@
 #define MMCR1_PMCSEL_SH(n)	(MMCR1_PMC1SEL_SH - (n) * 8)
 #define MMCR1_PMCSEL_MSK	0x7f
 
-/*
- * Bits in MMCRA
- */
-
 /*
  * Layout of constraint bits:
  * 6666555555555544444444443333333333222222222211111111110000000000
@@ -390,7 +386,7 @@ static int power5_compute_mmcr(u64 event[], int n_ev,
 			       unsigned int hwc[], unsigned long mmcr[])
 {
 	unsigned long mmcr1 = 0;
-	unsigned long mmcra = 0;
+	unsigned long mmcra = MMCRA_SDAR_DCACHE_MISS | MMCRA_SDAR_ERAT_MISS;
 	unsigned int pmc, unit, byte, psel;
 	unsigned int ttm, grp;
 	int i, isbus, bit, grsel;

arch/powerpc/kernel/power6-pmu.c

@@ -178,7 +178,7 @@ static int p6_compute_mmcr(u64 event[], int n_ev,
 			   unsigned int hwc[], unsigned long mmcr[])
 {
 	unsigned long mmcr1 = 0;
-	unsigned long mmcra = 0;
+	unsigned long mmcra = MMCRA_SDAR_DCACHE_MISS | MMCRA_SDAR_ERAT_MISS;
 	int i;
 	unsigned int pmc, ev, b, u, s, psel;
 	unsigned int ttmset = 0;

arch/powerpc/kernel/power7-pmu.c

@@ -50,10 +50,6 @@
 #define MMCR1_PMCSEL_SH(n)	(MMCR1_PMC1SEL_SH - (n) * 8)
 #define MMCR1_PMCSEL_MSK	0xff
 
-/*
- * Bits in MMCRA
- */
-
 /*
  * Layout of constraint bits:
  * 6666555555555544444444443333333333222222222211111111110000000000
@@ -230,7 +226,7 @@ static int power7_compute_mmcr(u64 event[], int n_ev,
 			       unsigned int hwc[], unsigned long mmcr[])
 {
 	unsigned long mmcr1 = 0;
-	unsigned long mmcra = 0;
+	unsigned long mmcra = MMCRA_SDAR_DCACHE_MISS | MMCRA_SDAR_ERAT_MISS;
 	unsigned int pmc, unit, combine, l2sel, psel;
 	unsigned int pmc_inuse = 0;
 	int i;

arch/powerpc/kernel/ppc970-pmu.c

@@ -83,10 +83,6 @@ static short mmcr1_adder_bits[8] = {
 	MMCR1_PMC8_ADDER_SEL_SH
 };
 
-/*
- * Bits in MMCRA
- */
-
 /*
  * Layout of constraint bits:
  * 6666555555555544444444443333333333222222222211111111110000000000

arch/powerpc/kernel/setup-common.c

@@ -660,6 +660,7 @@ late_initcall(check_cache_coherency);
 
 #ifdef CONFIG_DEBUG_FS
 struct dentry *powerpc_debugfs_root;
+EXPORT_SYMBOL(powerpc_debugfs_root);
 
 static int powerpc_debugfs_init(void)
 {

arch/powerpc/kernel/time.c

@@ -54,6 +54,7 @@
 #include <linux/irq.h>
 #include <linux/delay.h>
 #include <linux/perf_event.h>
+#include <asm/trace.h>
 
 #include <asm/io.h>
 #include <asm/processor.h>
@@ -571,6 +572,8 @@ void timer_interrupt(struct pt_regs * regs)
 	struct clock_event_device *evt = &decrementer->event;
 	u64 now;
 
+	trace_timer_interrupt_entry(regs);
+
 	/* Ensure a positive value is written to the decrementer, or else
 	 * some CPUs will continuue to take decrementer exceptions */
 	set_dec(DECREMENTER_MAX);
@@ -590,6 +593,7 @@ void timer_interrupt(struct pt_regs * regs)
 		now = decrementer->next_tb - now;
 		if (now <= DECREMENTER_MAX)
 			set_dec((int)now);
+		trace_timer_interrupt_exit(regs);
 		return;
 	}
 	old_regs = set_irq_regs(regs);
@@ -620,6 +624,8 @@ void timer_interrupt(struct pt_regs * regs)
 
 	irq_exit();
 	set_irq_regs(old_regs);
+
+	trace_timer_interrupt_exit(regs);
 }
 
 void wakeup_decrementer(void)

arch/powerpc/kernel/traps.c

@@ -759,7 +759,7 @@ static int emulate_instruction(struct pt_regs *regs)
 
 	/* Emulate the mfspr rD, PVR. */
 	if ((instword & PPC_INST_MFSPR_PVR_MASK) == PPC_INST_MFSPR_PVR) {
-		PPC_WARN_EMULATED(mfpvr);
+		PPC_WARN_EMULATED(mfpvr, regs);
 		rd = (instword >> 21) & 0x1f;
 		regs->gpr[rd] = mfspr(SPRN_PVR);
 		return 0;
@@ -767,7 +767,7 @@ static int emulate_instruction(struct pt_regs *regs)
 
 	/* Emulating the dcba insn is just a no-op.  */
 	if ((instword & PPC_INST_DCBA_MASK) == PPC_INST_DCBA) {
-		PPC_WARN_EMULATED(dcba);
+		PPC_WARN_EMULATED(dcba, regs);
 		return 0;
 	}
 
@@ -776,7 +776,7 @@ static int emulate_instruction(struct pt_regs *regs)
 		int shift = (instword >> 21) & 0x1c;
 		unsigned long msk = 0xf0000000UL >> shift;
 
-		PPC_WARN_EMULATED(mcrxr);
+		PPC_WARN_EMULATED(mcrxr, regs);
 		regs->ccr = (regs->ccr & ~msk) | ((regs->xer >> shift) & msk);
 		regs->xer &= ~0xf0000000UL;
 		return 0;
@@ -784,19 +784,19 @@ static int emulate_instruction(struct pt_regs *regs)
 
 	/* Emulate load/store string insn. */
 	if ((instword & PPC_INST_STRING_GEN_MASK) == PPC_INST_STRING) {
-		PPC_WARN_EMULATED(string);
+		PPC_WARN_EMULATED(string, regs);
 		return emulate_string_inst(regs, instword);
 	}
 
 	/* Emulate the popcntb (Population Count Bytes) instruction. */
 	if ((instword & PPC_INST_POPCNTB_MASK) == PPC_INST_POPCNTB) {
-		PPC_WARN_EMULATED(popcntb);
+		PPC_WARN_EMULATED(popcntb, regs);
 		return emulate_popcntb_inst(regs, instword);
 	}
 
 	/* Emulate isel (Integer Select) instruction */
 	if ((instword & PPC_INST_ISEL_MASK) == PPC_INST_ISEL) {
-		PPC_WARN_EMULATED(isel);
+		PPC_WARN_EMULATED(isel, regs);
 		return emulate_isel(regs, instword);
 	}
 
@@ -995,7 +995,7 @@ void SoftwareEmulation(struct pt_regs *regs)
 #ifdef CONFIG_MATH_EMULATION
 	errcode = do_mathemu(regs);
 	if (errcode >= 0)
-		PPC_WARN_EMULATED(math);
+		PPC_WARN_EMULATED(math, regs);
 
 	switch (errcode) {
 	case 0:
@@ -1018,7 +1018,7 @@ void SoftwareEmulation(struct pt_regs *regs)
 #elif defined(CONFIG_8XX_MINIMAL_FPEMU)
 	errcode = Soft_emulate_8xx(regs);
 	if (errcode >= 0)
-		PPC_WARN_EMULATED(8xx);
+		PPC_WARN_EMULATED(8xx, regs);
 
 	switch (errcode) {
 	case 0:
@@ -1129,7 +1129,7 @@ void altivec_assist_exception(struct pt_regs *regs)
 
 	flush_altivec_to_thread(current);
 
-	PPC_WARN_EMULATED(altivec);
+	PPC_WARN_EMULATED(altivec, regs);
 	err = emulate_altivec(regs);
 	if (err == 0) {
 		regs->nip += 4;		/* skip emulated instruction */

arch/powerpc/lib/copypage_64.S

@@ -26,11 +26,11 @@ BEGIN_FTR_SECTION
 	srd	r8,r5,r11
 
 	mtctr	r8
-setup:
+.Lsetup:
 	dcbt	r9,r4
 	dcbz	r9,r3
 	add	r9,r9,r12
-	bdnz	setup
+	bdnz	.Lsetup
 END_FTR_SECTION_IFSET(CPU_FTR_CP_USE_DCBTZ)
 	addi	r3,r3,-8
 	srdi    r8,r5,7		/* page is copied in 128 byte strides */

arch/powerpc/platforms/pseries/hvCall.S

@@ -14,68 +14,94 @@
 	
 #define STK_PARM(i)     (48 + ((i)-3)*8)
 
-#ifdef CONFIG_HCALL_STATS
+#ifdef CONFIG_TRACEPOINTS
+
+	.section	".toc","aw"
+
+	.globl hcall_tracepoint_refcount
+hcall_tracepoint_refcount:
+	.llong	0
+
+	.section	".text"
+
 /*
  * precall must preserve all registers.  use unused STK_PARM()
- * areas to save snapshots and opcode.
+ * areas to save snapshots and opcode. We branch around this
+ * in early init (eg when populating the MMU hashtable) by using an
+ * unconditional cpu feature.
  */
-#define HCALL_INST_PRECALL					\
-	std	r3,STK_PARM(r3)(r1);	/* save opcode */	\
-	mftb	r0;			/* get timebase and */	\
-	std     r0,STK_PARM(r5)(r1);	/* save for later */	\
+#define HCALL_INST_PRECALL(FIRST_REG)				\
 BEGIN_FTR_SECTION;						\
-	mfspr	r0,SPRN_PURR;		/* get PURR and */	\
-	std	r0,STK_PARM(r6)(r1);	/* save for later */	\
-END_FTR_SECTION_IFSET(CPU_FTR_PURR);
-	
+	b	1f;						\
+END_FTR_SECTION(0, 1);						\
+	ld      r12,hcall_tracepoint_refcount@toc(r2);		\
+	cmpdi	r12,0;						\
+	beq+	1f;						\
+	mflr	r0;						\
+	std	r3,STK_PARM(r3)(r1);				\
+	std	r4,STK_PARM(r4)(r1);				\
+	std	r5,STK_PARM(r5)(r1);				\
+	std	r6,STK_PARM(r6)(r1);				\
+	std	r7,STK_PARM(r7)(r1);				\
+	std	r8,STK_PARM(r8)(r1);				\
+	std	r9,STK_PARM(r9)(r1);				\
+	std	r10,STK_PARM(r10)(r1);				\
+	std	r0,16(r1);					\
+	addi	r4,r1,STK_PARM(FIRST_REG);			\
+	stdu	r1,-STACK_FRAME_OVERHEAD(r1);			\
+	bl	.__trace_hcall_entry;				\
+	addi	r1,r1,STACK_FRAME_OVERHEAD;			\
+	ld	r0,16(r1);					\
+	ld	r3,STK_PARM(r3)(r1);				\
+	ld	r4,STK_PARM(r4)(r1);				\
+	ld	r5,STK_PARM(r5)(r1);				\
+	ld	r6,STK_PARM(r6)(r1);				\
+	ld	r7,STK_PARM(r7)(r1);				\
+	ld	r8,STK_PARM(r8)(r1);				\
+	ld	r9,STK_PARM(r9)(r1);				\
+	ld	r10,STK_PARM(r10)(r1);				\
+	mtlr	r0;						\
+1:
+
 /*
  * postcall is performed immediately before function return which
  * allows liberal use of volatile registers.  We branch around this
  * in early init (eg when populating the MMU hashtable) by using an
  * unconditional cpu feature.
  */
-#define HCALL_INST_POSTCALL					\
+#define __HCALL_INST_POSTCALL					\
 BEGIN_FTR_SECTION;						\
 	b	1f;						\
 END_FTR_SECTION(0, 1);						\
-	ld	r4,STK_PARM(r3)(r1);	/* validate opcode */	\
-	cmpldi	cr7,r4,MAX_HCALL_OPCODE;			\
-	bgt-	cr7,1f;						\
-								\
-	/* get time and PURR snapshots after hcall */		\
-	mftb	r7;			/* timebase after */	\
-BEGIN_FTR_SECTION;						\
-	mfspr	r8,SPRN_PURR;		/* PURR after */	\
-	ld	r6,STK_PARM(r6)(r1);	/* PURR before */	\
-	subf	r6,r6,r8;		/* delta */		\
-END_FTR_SECTION_IFSET(CPU_FTR_PURR);				\
-	ld	r5,STK_PARM(r5)(r1);	/* timebase before */	\
-	subf	r5,r5,r7;		/* time delta */	\
-								\
-	/* calculate address of stat structure r4 = opcode */	\
-	srdi	r4,r4,2;		/* index into array */	\
-	mulli	r4,r4,HCALL_STAT_SIZE;				\
-	LOAD_REG_ADDR(r7, per_cpu__hcall_stats);		\
-	add	r4,r4,r7;					\
-	ld	r7,PACA_DATA_OFFSET(r13); /* per cpu offset */	\
-	add	r4,r4,r7;					\
-								\
-	/* update stats	*/					\
-	ld	r7,HCALL_STAT_CALLS(r4); /* count */		\
-	addi	r7,r7,1;					\
-	std	r7,HCALL_STAT_CALLS(r4);			\
-	ld      r7,HCALL_STAT_TB(r4);	/* timebase */		\
-	add	r7,r7,r5;					\
-	std	r7,HCALL_STAT_TB(r4);				\
-BEGIN_FTR_SECTION;						\
-	ld	r7,HCALL_STAT_PURR(r4);	/* PURR */		\
-	add	r7,r7,r6;					\
-	std	r7,HCALL_STAT_PURR(r4);				\
-END_FTR_SECTION_IFSET(CPU_FTR_PURR);				\
+	ld      r12,hcall_tracepoint_refcount@toc(r2);		\
+	cmpdi	r12,0;						\
+	beq+	1f;						\
+	mflr	r0;						\
+	ld	r6,STK_PARM(r3)(r1);				\
+	std	r3,STK_PARM(r3)(r1);				\
+	mr	r4,r3;						\
+	mr	r3,r6;						\
+	std	r0,16(r1);					\
+	stdu	r1,-STACK_FRAME_OVERHEAD(r1);			\
+	bl	.__trace_hcall_exit;				\
+	addi	r1,r1,STACK_FRAME_OVERHEAD;			\
+	ld	r0,16(r1);					\
+	ld	r3,STK_PARM(r3)(r1);				\
+	mtlr	r0;						\
 1:
+
+#define HCALL_INST_POSTCALL_NORETS				\
+	li	r5,0;						\
+	__HCALL_INST_POSTCALL
+
+#define HCALL_INST_POSTCALL(BUFREG)				\
+	mr	r5,BUFREG;					\
+	__HCALL_INST_POSTCALL
+
 #else
-#define HCALL_INST_PRECALL
-#define HCALL_INST_POSTCALL
+#define HCALL_INST_PRECALL(FIRST_ARG)
+#define HCALL_INST_POSTCALL_NORETS
+#define HCALL_INST_POSTCALL(BUFREG)
 #endif
 
 	.text
@@ -86,11 +112,11 @@ _GLOBAL(plpar_hcall_norets)
 	mfcr	r0
 	stw	r0,8(r1)
 
-	HCALL_INST_PRECALL
+	HCALL_INST_PRECALL(r4)
 
 	HVSC				/* invoke the hypervisor */
 
-	HCALL_INST_POSTCALL
+	HCALL_INST_POSTCALL_NORETS
 
 	lwz	r0,8(r1)
 	mtcrf	0xff,r0
@@ -102,7 +128,7 @@ _GLOBAL(plpar_hcall)
 	mfcr	r0
 	stw	r0,8(r1)
 
-	HCALL_INST_PRECALL
+	HCALL_INST_PRECALL(r5)
 
 	std     r4,STK_PARM(r4)(r1)     /* Save ret buffer */
 
@@ -121,7 +147,7 @@ _GLOBAL(plpar_hcall)
 	std	r6, 16(r12)
 	std	r7, 24(r12)
 
-	HCALL_INST_POSTCALL
+	HCALL_INST_POSTCALL(r12)
 
 	lwz	r0,8(r1)
 	mtcrf	0xff,r0
@@ -168,7 +194,7 @@ _GLOBAL(plpar_hcall9)
 	mfcr	r0
 	stw	r0,8(r1)
 
-	HCALL_INST_PRECALL
+	HCALL_INST_PRECALL(r5)
 
 	std     r4,STK_PARM(r4)(r1)     /* Save ret buffer */
 
@@ -196,7 +222,7 @@ _GLOBAL(plpar_hcall9)
 	std	r11,56(r12)
 	std	r0, 64(r12)
 
-	HCALL_INST_POSTCALL
+	HCALL_INST_POSTCALL(r12)
 
 	lwz	r0,8(r1)
 	mtcrf	0xff,r0

arch/powerpc/platforms/pseries/hvCall_inst.c

@@ -26,6 +26,7 @@
 #include <asm/hvcall.h>
 #include <asm/firmware.h>
 #include <asm/cputable.h>
+#include <asm/trace.h>
 
 DEFINE_PER_CPU(struct hcall_stats[HCALL_STAT_ARRAY_SIZE], hcall_stats);
 
@@ -100,6 +101,35 @@ static const struct file_operations hcall_inst_seq_fops = {
 #define	HCALL_ROOT_DIR		"hcall_inst"
 #define CPU_NAME_BUF_SIZE	32
 
+
+static void probe_hcall_entry(unsigned long opcode, unsigned long *args)
+{
+	struct hcall_stats *h;
+
+	if (opcode > MAX_HCALL_OPCODE)
+		return;
+
+	h = &get_cpu_var(hcall_stats)[opcode / 4];
+	h->tb_start = mftb();
+	h->purr_start = mfspr(SPRN_PURR);
+}
+
+static void probe_hcall_exit(unsigned long opcode, unsigned long retval,
+			     unsigned long *retbuf)
+{
+	struct hcall_stats *h;
+
+	if (opcode > MAX_HCALL_OPCODE)
+		return;
+
+	h = &__get_cpu_var(hcall_stats)[opcode / 4];
+	h->num_calls++;
+	h->tb_total = mftb() - h->tb_start;
+	h->purr_total = mfspr(SPRN_PURR) - h->purr_start;
+
+	put_cpu_var(hcall_stats);
+}
+
 static int __init hcall_inst_init(void)
 {
 	struct dentry *hcall_root;
@@ -110,6 +140,14 @@ static int __init hcall_inst_init(void)
 	if (!firmware_has_feature(FW_FEATURE_LPAR))
 		return 0;
 
+	if (register_trace_hcall_entry(probe_hcall_entry))
+		return -EINVAL;
+
+	if (register_trace_hcall_exit(probe_hcall_exit)) {
+		unregister_trace_hcall_entry(probe_hcall_entry);
+		return -EINVAL;
+	}
+
 	hcall_root = debugfs_create_dir(HCALL_ROOT_DIR, NULL);
 	if (!hcall_root)
 		return -ENOMEM;

arch/powerpc/platforms/pseries/lpar.c

@@ -39,6 +39,7 @@
 #include <asm/cputable.h>
 #include <asm/udbg.h>
 #include <asm/smp.h>
+#include <asm/trace.h>
 
 #include "plpar_wrappers.h"
 #include "pseries.h"
@@ -661,3 +662,35 @@ void arch_free_page(struct page *page, int order)
 EXPORT_SYMBOL(arch_free_page);
 
 #endif
+
+#ifdef CONFIG_TRACEPOINTS
+/*
+ * We optimise our hcall path by placing hcall_tracepoint_refcount
+ * directly in the TOC so we can check if the hcall tracepoints are
+ * enabled via a single load.
+ */
+
+/* NB: reg/unreg are called while guarded with the tracepoints_mutex */
+extern long hcall_tracepoint_refcount;
+
+void hcall_tracepoint_regfunc(void)
+{
+	hcall_tracepoint_refcount++;
+}
+
+void hcall_tracepoint_unregfunc(void)
+{
+	hcall_tracepoint_refcount--;
+}
+
+void __trace_hcall_entry(unsigned long opcode, unsigned long *args)
+{
+	trace_hcall_entry(opcode, args);
+}
+
+void __trace_hcall_exit(long opcode, unsigned long retval,
+			unsigned long *retbuf)
+{
+	trace_hcall_exit(opcode, retval, retbuf);
+}
+#endif

arch/x86/Kconfig

@@ -49,6 +49,7 @@ config X86
 	select HAVE_KERNEL_GZIP
 	select HAVE_KERNEL_BZIP2
 	select HAVE_KERNEL_LZMA
+	select HAVE_HW_BREAKPOINT
 	select HAVE_ARCH_KMEMCHECK
 
 config OUTPUT_FORMAT

arch/x86/Kconfig.debug

@@ -186,6 +186,15 @@ config X86_DS_SELFTEST
 config HAVE_MMIOTRACE_SUPPORT
 	def_bool y
 
+config X86_DECODER_SELFTEST
+     bool "x86 instruction decoder selftest"
+     depends on DEBUG_KERNEL
+	---help---
+	 Perform x86 instruction decoder selftests at build time.
+	 This option is useful for checking the sanity of x86 instruction
+	 decoder code.
+	 If unsure, say "N".
+
 #
 # IO delay types:
 #

arch/x86/Makefile

@@ -155,6 +155,9 @@ all: bzImage
 KBUILD_IMAGE := $(boot)/bzImage
 
 bzImage: vmlinux
+ifeq ($(CONFIG_X86_DECODER_SELFTEST),y)
+	$(Q)$(MAKE) $(build)=arch/x86/tools posttest
+endif
 	$(Q)$(MAKE) $(build)=$(boot) $(KBUILD_IMAGE)
 	$(Q)mkdir -p $(objtree)/arch/$(UTS_MACHINE)/boot
 	$(Q)ln -fsn ../../x86/boot/bzImage $(objtree)/arch/$(UTS_MACHINE)/boot/$@

arch/x86/include/asm/Kbuild

@@ -10,6 +10,7 @@ header-y += ptrace-abi.h
 header-y += sigcontext32.h
 header-y += ucontext.h
 header-y += processor-flags.h
+header-y += hw_breakpoint.h
 
 unifdef-y += e820.h
 unifdef-y += ist.h

arch/x86/include/asm/a.out-core.h

@@ -17,6 +17,7 @@
 
 #include <linux/user.h>
 #include <linux/elfcore.h>
+#include <asm/debugreg.h>
 
 /*
  * fill in the user structure for an a.out core dump
@@ -32,14 +33,7 @@ static inline void aout_dump_thread(struct pt_regs *regs, struct user *dump)
 			>> PAGE_SHIFT;
 	dump->u_dsize -= dump->u_tsize;
 	dump->u_ssize = 0;
-	dump->u_debugreg[0] = current->thread.debugreg0;
-	dump->u_debugreg[1] = current->thread.debugreg1;
-	dump->u_debugreg[2] = current->thread.debugreg2;
-	dump->u_debugreg[3] = current->thread.debugreg3;
-	dump->u_debugreg[4] = 0;
-	dump->u_debugreg[5] = 0;
-	dump->u_debugreg[6] = current->thread.debugreg6;
-	dump->u_debugreg[7] = current->thread.debugreg7;
+	aout_dump_debugregs(dump);
 
 	if (dump->start_stack < TASK_SIZE)
 		dump->u_ssize = ((unsigned long)(TASK_SIZE - dump->start_stack))

arch/x86/include/asm/debugreg.h

@@ -18,6 +18,7 @@
 #define DR_TRAP1	(0x2)		/* db1 */
 #define DR_TRAP2	(0x4)		/* db2 */
 #define DR_TRAP3	(0x8)		/* db3 */
+#define DR_TRAP_BITS	(DR_TRAP0|DR_TRAP1|DR_TRAP2|DR_TRAP3)
 
 #define DR_STEP		(0x4000)	/* single-step */
 #define DR_SWITCH	(0x8000)	/* task switch */
@@ -49,6 +50,8 @@
 
 #define DR_LOCAL_ENABLE_SHIFT 0    /* Extra shift to the local enable bit */
 #define DR_GLOBAL_ENABLE_SHIFT 1   /* Extra shift to the global enable bit */
+#define DR_LOCAL_ENABLE (0x1)      /* Local enable for reg 0 */
+#define DR_GLOBAL_ENABLE (0x2)     /* Global enable for reg 0 */
 #define DR_ENABLE_SIZE 2           /* 2 enable bits per register */
 
 #define DR_LOCAL_ENABLE_MASK (0x55)  /* Set  local bits for all 4 regs */
@@ -67,4 +70,34 @@
 #define DR_LOCAL_SLOWDOWN (0x100)   /* Local slow the pipeline */
 #define DR_GLOBAL_SLOWDOWN (0x200)  /* Global slow the pipeline */
 
+/*
+ * HW breakpoint additions
+ */
+#ifdef __KERNEL__
+
+DECLARE_PER_CPU(unsigned long, cpu_dr7);
+
+static inline void hw_breakpoint_disable(void)
+{
+	/* Zero the control register for HW Breakpoint */
+	set_debugreg(0UL, 7);
+
+	/* Zero-out the individual HW breakpoint address registers */
+	set_debugreg(0UL, 0);
+	set_debugreg(0UL, 1);
+	set_debugreg(0UL, 2);
+	set_debugreg(0UL, 3);
+}
+
+static inline int hw_breakpoint_active(void)
+{
+	return __get_cpu_var(cpu_dr7) & DR_GLOBAL_ENABLE_MASK;
+}
+
+extern void aout_dump_debugregs(struct user *dump);
+
+extern void hw_breakpoint_restore(void);
+
+#endif	/* __KERNEL__ */
+
 #endif /* _ASM_X86_DEBUGREG_H */

arch/x86/include/asm/hardirq.h

@@ -20,11 +20,11 @@ typedef struct {
 	unsigned int irq_call_count;
 	unsigned int irq_tlb_count;
 #endif
-#ifdef CONFIG_X86_MCE
+#ifdef CONFIG_X86_THERMAL_VECTOR
 	unsigned int irq_thermal_count;
-# ifdef CONFIG_X86_MCE_THRESHOLD
+#endif
+#ifdef CONFIG_X86_MCE_THRESHOLD
 	unsigned int irq_threshold_count;
-# endif
 #endif
 } ____cacheline_aligned irq_cpustat_t;
 

arch/x86/include/asm/hw_breakpoint.h

@@ -0,0 +1,73 @@
+#ifndef	_I386_HW_BREAKPOINT_H
+#define	_I386_HW_BREAKPOINT_H
+
+#ifdef	__KERNEL__
+#define	__ARCH_HW_BREAKPOINT_H
+
+/*
+ * The name should probably be something dealt in
+ * a higher level. While dealing with the user
+ * (display/resolving)
+ */
+struct arch_hw_breakpoint {
+	char		*name; /* Contains name of the symbol to set bkpt */
+	unsigned long	address;
+	u8		len;
+	u8		type;
+};
+
+#include <linux/kdebug.h>
+#include <linux/percpu.h>
+#include <linux/list.h>
+
+/* Available HW breakpoint length encodings */
+#define X86_BREAKPOINT_LEN_1		0x40
+#define X86_BREAKPOINT_LEN_2		0x44
+#define X86_BREAKPOINT_LEN_4		0x4c
+#define X86_BREAKPOINT_LEN_EXECUTE	0x40
+
+#ifdef CONFIG_X86_64
+#define X86_BREAKPOINT_LEN_8		0x48
+#endif
+
+/* Available HW breakpoint type encodings */
+
+/* trigger on instruction execute */
+#define X86_BREAKPOINT_EXECUTE	0x80
+/* trigger on memory write */
+#define X86_BREAKPOINT_WRITE	0x81
+/* trigger on memory read or write */
+#define X86_BREAKPOINT_RW	0x83
+
+/* Total number of available HW breakpoint registers */
+#define HBP_NUM 4
+
+struct perf_event;
+struct pmu;
+
+extern int arch_check_va_in_userspace(unsigned long va, u8 hbp_len);
+extern int arch_validate_hwbkpt_settings(struct perf_event *bp,
+					 struct task_struct *tsk);
+extern int hw_breakpoint_exceptions_notify(struct notifier_block *unused,
+					   unsigned long val, void *data);
+
+
+int arch_install_hw_breakpoint(struct perf_event *bp);
+void arch_uninstall_hw_breakpoint(struct perf_event *bp);
+void hw_breakpoint_pmu_read(struct perf_event *bp);
+void hw_breakpoint_pmu_unthrottle(struct perf_event *bp);
+
+extern void
+arch_fill_perf_breakpoint(struct perf_event *bp);
+
+unsigned long encode_dr7(int drnum, unsigned int len, unsigned int type);
+int decode_dr7(unsigned long dr7, int bpnum, unsigned *len, unsigned *type);
+
+extern int arch_bp_generic_fields(int x86_len, int x86_type,
+				  int *gen_len, int *gen_type);
+
+extern struct pmu perf_ops_bp;
+
+#endif	/* __KERNEL__ */
+#endif	/* _I386_HW_BREAKPOINT_H */
+

arch/x86/include/asm/inat.h

@@ -0,0 +1,220 @@
+#ifndef _ASM_X86_INAT_H
+#define _ASM_X86_INAT_H
+/*
+ * x86 instruction attributes
+ *
+ * Written by Masami Hiramatsu <mhiramat@redhat.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ */
+#include <asm/inat_types.h>
+
+/*
+ * Internal bits. Don't use bitmasks directly, because these bits are
+ * unstable. You should use checking functions.
+ */
+
+#define INAT_OPCODE_TABLE_SIZE 256
+#define INAT_GROUP_TABLE_SIZE 8
+
+/* Legacy last prefixes */
+#define INAT_PFX_OPNDSZ	1	/* 0x66 */ /* LPFX1 */
+#define INAT_PFX_REPE	2	/* 0xF3 */ /* LPFX2 */
+#define INAT_PFX_REPNE	3	/* 0xF2 */ /* LPFX3 */
+/* Other Legacy prefixes */
+#define INAT_PFX_LOCK	4	/* 0xF0 */
+#define INAT_PFX_CS	5	/* 0x2E */
+#define INAT_PFX_DS	6	/* 0x3E */
+#define INAT_PFX_ES	7	/* 0x26 */
+#define INAT_PFX_FS	8	/* 0x64 */
+#define INAT_PFX_GS	9	/* 0x65 */
+#define INAT_PFX_SS	10	/* 0x36 */
+#define INAT_PFX_ADDRSZ	11	/* 0x67 */
+/* x86-64 REX prefix */
+#define INAT_PFX_REX	12	/* 0x4X */
+/* AVX VEX prefixes */
+#define INAT_PFX_VEX2	13	/* 2-bytes VEX prefix */
+#define INAT_PFX_VEX3	14	/* 3-bytes VEX prefix */
+
+#define INAT_LSTPFX_MAX	3
+#define INAT_LGCPFX_MAX	11
+
+/* Immediate size */
+#define INAT_IMM_BYTE		1
+#define INAT_IMM_WORD		2
+#define INAT_IMM_DWORD		3
+#define INAT_IMM_QWORD		4
+#define INAT_IMM_PTR		5
+#define INAT_IMM_VWORD32	6
+#define INAT_IMM_VWORD		7
+
+/* Legacy prefix */
+#define INAT_PFX_OFFS	0
+#define INAT_PFX_BITS	4
+#define INAT_PFX_MAX    ((1 << INAT_PFX_BITS) - 1)
+#define INAT_PFX_MASK	(INAT_PFX_MAX << INAT_PFX_OFFS)
+/* Escape opcodes */
+#define INAT_ESC_OFFS	(INAT_PFX_OFFS + INAT_PFX_BITS)
+#define INAT_ESC_BITS	2
+#define INAT_ESC_MAX	((1 << INAT_ESC_BITS) - 1)
+#define INAT_ESC_MASK	(INAT_ESC_MAX << INAT_ESC_OFFS)
+/* Group opcodes (1-16) */
+#define INAT_GRP_OFFS	(INAT_ESC_OFFS + INAT_ESC_BITS)
+#define INAT_GRP_BITS	5
+#define INAT_GRP_MAX	((1 << INAT_GRP_BITS) - 1)
+#define INAT_GRP_MASK	(INAT_GRP_MAX << INAT_GRP_OFFS)
+/* Immediates */
+#define INAT_IMM_OFFS	(INAT_GRP_OFFS + INAT_GRP_BITS)
+#define INAT_IMM_BITS	3
+#define INAT_IMM_MASK	(((1 << INAT_IMM_BITS) - 1) << INAT_IMM_OFFS)
+/* Flags */
+#define INAT_FLAG_OFFS	(INAT_IMM_OFFS + INAT_IMM_BITS)
+#define INAT_MODRM	(1 << (INAT_FLAG_OFFS))
+#define INAT_FORCE64	(1 << (INAT_FLAG_OFFS + 1))
+#define INAT_SCNDIMM	(1 << (INAT_FLAG_OFFS + 2))
+#define INAT_MOFFSET	(1 << (INAT_FLAG_OFFS + 3))
+#define INAT_VARIANT	(1 << (INAT_FLAG_OFFS + 4))
+#define INAT_VEXOK	(1 << (INAT_FLAG_OFFS + 5))
+#define INAT_VEXONLY	(1 << (INAT_FLAG_OFFS + 6))
+/* Attribute making macros for attribute tables */
+#define INAT_MAKE_PREFIX(pfx)	(pfx << INAT_PFX_OFFS)
+#define INAT_MAKE_ESCAPE(esc)	(esc << INAT_ESC_OFFS)
+#define INAT_MAKE_GROUP(grp)	((grp << INAT_GRP_OFFS) | INAT_MODRM)
+#define INAT_MAKE_IMM(imm)	(imm << INAT_IMM_OFFS)
+
+/* Attribute search APIs */
+extern insn_attr_t inat_get_opcode_attribute(insn_byte_t opcode);
+extern insn_attr_t inat_get_escape_attribute(insn_byte_t opcode,
+					     insn_byte_t last_pfx,
+					     insn_attr_t esc_attr);
+extern insn_attr_t inat_get_group_attribute(insn_byte_t modrm,
+					    insn_byte_t last_pfx,
+					    insn_attr_t esc_attr);
+extern insn_attr_t inat_get_avx_attribute(insn_byte_t opcode,
+					  insn_byte_t vex_m,
+					  insn_byte_t vex_pp);
+
+/* Attribute checking functions */
+static inline int inat_is_legacy_prefix(insn_attr_t attr)
+{
+	attr &= INAT_PFX_MASK;
+	return attr && attr <= INAT_LGCPFX_MAX;
+}
+
+static inline int inat_is_address_size_prefix(insn_attr_t attr)
+{
+	return (attr & INAT_PFX_MASK) == INAT_PFX_ADDRSZ;
+}
+
+static inline int inat_is_operand_size_prefix(insn_attr_t attr)
+{
+	return (attr & INAT_PFX_MASK) == INAT_PFX_OPNDSZ;
+}
+
+static inline int inat_is_rex_prefix(insn_attr_t attr)
+{
+	return (attr & INAT_PFX_MASK) == INAT_PFX_REX;
+}
+
+static inline int inat_last_prefix_id(insn_attr_t attr)
+{
+	if ((attr & INAT_PFX_MASK) > INAT_LSTPFX_MAX)
+		return 0;
+	else
+		return attr & INAT_PFX_MASK;
+}
+
+static inline int inat_is_vex_prefix(insn_attr_t attr)
+{
+	attr &= INAT_PFX_MASK;
+	return attr == INAT_PFX_VEX2 || attr == INAT_PFX_VEX3;
+}
+
+static inline int inat_is_vex3_prefix(insn_attr_t attr)
+{
+	return (attr & INAT_PFX_MASK) == INAT_PFX_VEX3;
+}
+
+static inline int inat_is_escape(insn_attr_t attr)
+{
+	return attr & INAT_ESC_MASK;
+}
+
+static inline int inat_escape_id(insn_attr_t attr)
+{
+	return (attr & INAT_ESC_MASK) >> INAT_ESC_OFFS;
+}
+
+static inline int inat_is_group(insn_attr_t attr)
+{
+	return attr & INAT_GRP_MASK;
+}
+
+static inline int inat_group_id(insn_attr_t attr)
+{
+	return (attr & INAT_GRP_MASK) >> INAT_GRP_OFFS;
+}
+
+static inline int inat_group_common_attribute(insn_attr_t attr)
+{
+	return attr & ~INAT_GRP_MASK;
+}
+
+static inline int inat_has_immediate(insn_attr_t attr)
+{
+	return attr & INAT_IMM_MASK;
+}
+
+static inline int inat_immediate_size(insn_attr_t attr)
+{
+	return (attr & INAT_IMM_MASK) >> INAT_IMM_OFFS;
+}
+
+static inline int inat_has_modrm(insn_attr_t attr)
+{
+	return attr & INAT_MODRM;
+}
+
+static inline int inat_is_force64(insn_attr_t attr)
+{
+	return attr & INAT_FORCE64;
+}
+
+static inline int inat_has_second_immediate(insn_attr_t attr)
+{
+	return attr & INAT_SCNDIMM;
+}
+
+static inline int inat_has_moffset(insn_attr_t attr)
+{
+	return attr & INAT_MOFFSET;
+}
+
+static inline int inat_has_variant(insn_attr_t attr)
+{
+	return attr & INAT_VARIANT;
+}
+
+static inline int inat_accept_vex(insn_attr_t attr)
+{
+	return attr & INAT_VEXOK;
+}
+
+static inline int inat_must_vex(insn_attr_t attr)
+{
+	return attr & INAT_VEXONLY;
+}
+#endif

arch/x86/include/asm/inat_types.h

@@ -0,0 +1,29 @@
+#ifndef _ASM_X86_INAT_TYPES_H
+#define _ASM_X86_INAT_TYPES_H
+/*
+ * x86 instruction attributes
+ *
+ * Written by Masami Hiramatsu <mhiramat@redhat.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ */
+
+/* Instruction attributes */
+typedef unsigned int insn_attr_t;
+typedef unsigned char insn_byte_t;
+typedef signed int insn_value_t;
+
+#endif

arch/x86/include/asm/insn.h

@@ -0,0 +1,184 @@
+#ifndef _ASM_X86_INSN_H
+#define _ASM_X86_INSN_H
+/*
+ * x86 instruction analysis
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ * Copyright (C) IBM Corporation, 2009
+ */
+
+/* insn_attr_t is defined in inat.h */
+#include <asm/inat.h>
+
+struct insn_field {
+	union {
+		insn_value_t value;
+		insn_byte_t bytes[4];
+	};
+	/* !0 if we've run insn_get_xxx() for this field */
+	unsigned char got;
+	unsigned char nbytes;
+};
+
+struct insn {
+	struct insn_field prefixes;	/*
+					 * Prefixes
+					 * prefixes.bytes[3]: last prefix
+					 */
+	struct insn_field rex_prefix;	/* REX prefix */
+	struct insn_field vex_prefix;	/* VEX prefix */
+	struct insn_field opcode;	/*
+					 * opcode.bytes[0]: opcode1
+					 * opcode.bytes[1]: opcode2
+					 * opcode.bytes[2]: opcode3
+					 */
+	struct insn_field modrm;
+	struct insn_field sib;
+	struct insn_field displacement;
+	union {
+		struct insn_field immediate;
+		struct insn_field moffset1;	/* for 64bit MOV */
+		struct insn_field immediate1;	/* for 64bit imm or off16/32 */
+	};
+	union {
+		struct insn_field moffset2;	/* for 64bit MOV */
+		struct insn_field immediate2;	/* for 64bit imm or seg16 */
+	};
+
+	insn_attr_t attr;
+	unsigned char opnd_bytes;
+	unsigned char addr_bytes;
+	unsigned char length;
+	unsigned char x86_64;
+
+	const insn_byte_t *kaddr;	/* kernel address of insn to analyze */
+	const insn_byte_t *next_byte;
+};
+
+#define X86_MODRM_MOD(modrm) (((modrm) & 0xc0) >> 6)
+#define X86_MODRM_REG(modrm) (((modrm) & 0x38) >> 3)
+#define X86_MODRM_RM(modrm) ((modrm) & 0x07)
+
+#define X86_SIB_SCALE(sib) (((sib) & 0xc0) >> 6)
+#define X86_SIB_INDEX(sib) (((sib) & 0x38) >> 3)
+#define X86_SIB_BASE(sib) ((sib) & 0x07)
+
+#define X86_REX_W(rex) ((rex) & 8)
+#define X86_REX_R(rex) ((rex) & 4)
+#define X86_REX_X(rex) ((rex) & 2)
+#define X86_REX_B(rex) ((rex) & 1)
+
+/* VEX bit flags  */
+#define X86_VEX_W(vex)	((vex) & 0x80)	/* VEX3 Byte2 */
+#define X86_VEX_R(vex)	((vex) & 0x80)	/* VEX2/3 Byte1 */
+#define X86_VEX_X(vex)	((vex) & 0x40)	/* VEX3 Byte1 */
+#define X86_VEX_B(vex)	((vex) & 0x20)	/* VEX3 Byte1 */
+#define X86_VEX_L(vex)	((vex) & 0x04)	/* VEX3 Byte2, VEX2 Byte1 */
+/* VEX bit fields */
+#define X86_VEX3_M(vex)	((vex) & 0x1f)		/* VEX3 Byte1 */
+#define X86_VEX2_M	1			/* VEX2.M always 1 */
+#define X86_VEX_V(vex)	(((vex) & 0x78) >> 3)	/* VEX3 Byte2, VEX2 Byte1 */
+#define X86_VEX_P(vex)	((vex) & 0x03)		/* VEX3 Byte2, VEX2 Byte1 */
+#define X86_VEX_M_MAX	0x1f			/* VEX3.M Maximum value */
+
+/* The last prefix is needed for two-byte and three-byte opcodes */
+static inline insn_byte_t insn_last_prefix(struct insn *insn)
+{
+	return insn->prefixes.bytes[3];
+}
+
+extern void insn_init(struct insn *insn, const void *kaddr, int x86_64);
+extern void insn_get_prefixes(struct insn *insn);
+extern void insn_get_opcode(struct insn *insn);
+extern void insn_get_modrm(struct insn *insn);
+extern void insn_get_sib(struct insn *insn);
+extern void insn_get_displacement(struct insn *insn);
+extern void insn_get_immediate(struct insn *insn);
+extern void insn_get_length(struct insn *insn);
+
+/* Attribute will be determined after getting ModRM (for opcode groups) */
+static inline void insn_get_attribute(struct insn *insn)
+{
+	insn_get_modrm(insn);
+}
+
+/* Instruction uses RIP-relative addressing */
+extern int insn_rip_relative(struct insn *insn);
+
+/* Init insn for kernel text */
+static inline void kernel_insn_init(struct insn *insn, const void *kaddr)
+{
+#ifdef CONFIG_X86_64
+	insn_init(insn, kaddr, 1);
+#else /* CONFIG_X86_32 */
+	insn_init(insn, kaddr, 0);
+#endif
+}
+
+static inline int insn_is_avx(struct insn *insn)
+{
+	if (!insn->prefixes.got)
+		insn_get_prefixes(insn);
+	return (insn->vex_prefix.value != 0);
+}
+
+static inline insn_byte_t insn_vex_m_bits(struct insn *insn)
+{
+	if (insn->vex_prefix.nbytes == 2)	/* 2 bytes VEX */
+		return X86_VEX2_M;
+	else
+		return X86_VEX3_M(insn->vex_prefix.bytes[1]);
+}
+
+static inline insn_byte_t insn_vex_p_bits(struct insn *insn)
+{
+	if (insn->vex_prefix.nbytes == 2)	/* 2 bytes VEX */
+		return X86_VEX_P(insn->vex_prefix.bytes[1]);
+	else
+		return X86_VEX_P(insn->vex_prefix.bytes[2]);
+}
+
+/* Offset of each field from kaddr */
+static inline int insn_offset_rex_prefix(struct insn *insn)
+{
+	return insn->prefixes.nbytes;
+}
+static inline int insn_offset_vex_prefix(struct insn *insn)
+{
+	return insn_offset_rex_prefix(insn) + insn->rex_prefix.nbytes;
+}
+static inline int insn_offset_opcode(struct insn *insn)
+{
+	return insn_offset_vex_prefix(insn) + insn->vex_prefix.nbytes;
+}
+static inline int insn_offset_modrm(struct insn *insn)
+{
+	return insn_offset_opcode(insn) + insn->opcode.nbytes;
+}
+static inline int insn_offset_sib(struct insn *insn)
+{
+	return insn_offset_modrm(insn) + insn->modrm.nbytes;
+}
+static inline int insn_offset_displacement(struct insn *insn)
+{
+	return insn_offset_sib(insn) + insn->sib.nbytes;
+}
+static inline int insn_offset_immediate(struct insn *insn)
+{
+	return insn_offset_displacement(insn) + insn->displacement.nbytes;
+}
+
+#endif /* _ASM_X86_INSN_H */

arch/x86/include/asm/mce.h

@@ -108,6 +108,8 @@ struct mce_log {
 #define K8_MCE_THRESHOLD_BANK_5    (MCE_THRESHOLD_BASE + 5 * 9)
 #define K8_MCE_THRESHOLD_DRAM_ECC  (MCE_THRESHOLD_BANK_4 + 0)
 
+extern struct atomic_notifier_head x86_mce_decoder_chain;
+
 #ifdef __KERNEL__
 
 #include <linux/percpu.h>
@@ -118,9 +120,11 @@ extern int mce_disabled;
 extern int mce_p5_enabled;
 
 #ifdef CONFIG_X86_MCE
-void mcheck_init(struct cpuinfo_x86 *c);
+int mcheck_init(void);
+void mcheck_cpu_init(struct cpuinfo_x86 *c);
 #else
-static inline void mcheck_init(struct cpuinfo_x86 *c) {}
+static inline int mcheck_init(void) { return 0; }
+static inline void mcheck_cpu_init(struct cpuinfo_x86 *c) {}
 #endif
 
 #ifdef CONFIG_X86_ANCIENT_MCE
@@ -214,5 +218,11 @@ void intel_init_thermal(struct cpuinfo_x86 *c);
 
 void mce_log_therm_throt_event(__u64 status);
 
+#ifdef CONFIG_X86_THERMAL_VECTOR
+extern void mcheck_intel_therm_init(void);
+#else
+static inline void mcheck_intel_therm_init(void) { }
+#endif
+
 #endif /* __KERNEL__ */
 #endif /* _ASM_X86_MCE_H */

arch/x86/include/asm/perf_event.h

@@ -28,9 +28,20 @@
  */
 #define ARCH_PERFMON_EVENT_MASK				    0xffff
 
+/*
+ * filter mask to validate fixed counter events.
+ * the following filters disqualify for fixed counters:
+ *  - inv
+ *  - edge
+ *  - cnt-mask
+ *  The other filters are supported by fixed counters.
+ *  The any-thread option is supported starting with v3.
+ */
+#define ARCH_PERFMON_EVENT_FILTER_MASK			0xff840000
+
 #define ARCH_PERFMON_UNHALTED_CORE_CYCLES_SEL		      0x3c
 #define ARCH_PERFMON_UNHALTED_CORE_CYCLES_UMASK		(0x00 << 8)
-#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_INDEX 		 0
+#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_INDEX			 0
 #define ARCH_PERFMON_UNHALTED_CORE_CYCLES_PRESENT \
 		(1 << (ARCH_PERFMON_UNHALTED_CORE_CYCLES_INDEX))
 

arch/x86/include/asm/processor.h

@@ -30,6 +30,7 @@ struct mm_struct;
 #include <linux/math64.h>
 #include <linux/init.h>
 
+#define HBP_NUM 4
 /*
  * Default implementation of macro that returns current
  * instruction pointer ("program counter").
@@ -422,6 +423,8 @@ extern unsigned int xstate_size;
 extern void free_thread_xstate(struct task_struct *);
 extern struct kmem_cache *task_xstate_cachep;
 
+struct perf_event;
+
 struct thread_struct {
 	/* Cached TLS descriptors: */
 	struct desc_struct	tls_array[GDT_ENTRY_TLS_ENTRIES];
@@ -443,13 +446,10 @@ struct thread_struct {
 	unsigned long		fs;
 #endif
 	unsigned long		gs;
-	/* Hardware debugging registers: */
-	unsigned long		debugreg0;
-	unsigned long		debugreg1;
-	unsigned long		debugreg2;
-	unsigned long		debugreg3;
-	unsigned long		debugreg6;
-	unsigned long		debugreg7;
+	/* Save middle states of ptrace breakpoints */
+	struct perf_event	*ptrace_bps[HBP_NUM];
+	/* Debug status used for traps, single steps, etc... */
+	unsigned long           debugreg6;
 	/* Fault info: */
 	unsigned long		cr2;
 	unsigned long		trap_no;

arch/x86/include/asm/ptrace.h

@@ -7,6 +7,7 @@
 
 #ifdef __KERNEL__
 #include <asm/segment.h>
+#include <asm/page_types.h>
 #endif
 
 #ifndef __ASSEMBLY__
@@ -216,6 +217,67 @@ static inline unsigned long user_stack_pointer(struct pt_regs *regs)
 	return regs->sp;
 }
 
+/* Query offset/name of register from its name/offset */
+extern int regs_query_register_offset(const char *name);
+extern const char *regs_query_register_name(unsigned int offset);
+#define MAX_REG_OFFSET (offsetof(struct pt_regs, ss))
+
+/**
+ * regs_get_register() - get register value from its offset
+ * @regs:	pt_regs from which register value is gotten.
+ * @offset:	offset number of the register.
+ *
+ * regs_get_register returns the value of a register. The @offset is the
+ * offset of the register in struct pt_regs address which specified by @regs.
+ * If @offset is bigger than MAX_REG_OFFSET, this returns 0.
+ */
+static inline unsigned long regs_get_register(struct pt_regs *regs,
+					      unsigned int offset)
+{
+	if (unlikely(offset > MAX_REG_OFFSET))
+		return 0;
+	return *(unsigned long *)((unsigned long)regs + offset);
+}
+
+/**
+ * regs_within_kernel_stack() - check the address in the stack
+ * @regs:	pt_regs which contains kernel stack pointer.
+ * @addr:	address which is checked.
+ *
+ * regs_within_kernel_stack() checks @addr is within the kernel stack page(s).
+ * If @addr is within the kernel stack, it returns true. If not, returns false.
+ */
+static inline int regs_within_kernel_stack(struct pt_regs *regs,
+					   unsigned long addr)
+{
+	return ((addr & ~(THREAD_SIZE - 1))  ==
+		(kernel_stack_pointer(regs) & ~(THREAD_SIZE - 1)));
+}
+
+/**
+ * regs_get_kernel_stack_nth() - get Nth entry of the stack
+ * @regs:	pt_regs which contains kernel stack pointer.
+ * @n:		stack entry number.
+ *
+ * regs_get_kernel_stack_nth() returns @n th entry of the kernel stack which
+ * is specified by @regs. If the @n th entry is NOT in the kernel stack,
+ * this returns 0.
+ */
+static inline unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs,
+						      unsigned int n)
+{
+	unsigned long *addr = (unsigned long *)kernel_stack_pointer(regs);
+	addr += n;
+	if (regs_within_kernel_stack(regs, (unsigned long)addr))
+		return *addr;
+	else
+		return 0;
+}
+
+/* Get Nth argument at function call */
+extern unsigned long regs_get_argument_nth(struct pt_regs *regs,
+					   unsigned int n);
+
 /*
  * These are defined as per linux/ptrace.h, which see.
  */

arch/x86/kernel/Makefile

@@ -40,7 +40,7 @@ obj-$(CONFIG_X86_64)	+= sys_x86_64.o x8664_ksyms_64.o
 obj-$(CONFIG_X86_64)	+= syscall_64.o vsyscall_64.o
 obj-y			+= bootflag.o e820.o
 obj-y			+= pci-dma.o quirks.o i8237.o topology.o kdebugfs.o
-obj-y			+= alternative.o i8253.o pci-nommu.o
+obj-y			+= alternative.o i8253.o pci-nommu.o hw_breakpoint.o
 obj-y			+= tsc.o io_delay.o rtc.o
 
 obj-$(CONFIG_X86_TRAMPOLINE)	+= trampoline.o

arch/x86/kernel/cpu/Makefile

@@ -5,6 +5,7 @@
 # Don't trace early stages of a secondary CPU boot
 ifdef CONFIG_FUNCTION_TRACER
 CFLAGS_REMOVE_common.o = -pg
+CFLAGS_REMOVE_perf_event.o = -pg
 endif
 
 # Make sure load_percpu_segment has no stackprotector

arch/x86/kernel/cpu/common.c

@@ -837,10 +837,8 @@ static void __cpuinit identify_cpu(struct cpuinfo_x86 *c)
 			boot_cpu_data.x86_capability[i] &= c->x86_capability[i];
 	}
 
-#ifdef CONFIG_X86_MCE
 	/* Init Machine Check Exception if available. */
-	mcheck_init(c);
-#endif
+	mcheck_cpu_init(c);
 
 	select_idle_routine(c);
 

arch/x86/kernel/cpu/mcheck/mce.c

@@ -46,6 +46,9 @@
 
 #include "mce-internal.h"
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/mce.h>
+
 int mce_disabled __read_mostly;
 
 #define MISC_MCELOG_MINOR	227
@@ -85,18 +88,26 @@ static DECLARE_WAIT_QUEUE_HEAD(mce_wait);
 static DEFINE_PER_CPU(struct mce, mces_seen);
 static int			cpu_missing;
 
-static void default_decode_mce(struct mce *m)
+/*
+ * CPU/chipset specific EDAC code can register a notifier call here to print
+ * MCE errors in a human-readable form.
+ */
+ATOMIC_NOTIFIER_HEAD(x86_mce_decoder_chain);
+EXPORT_SYMBOL_GPL(x86_mce_decoder_chain);
+
+static int default_decode_mce(struct notifier_block *nb, unsigned long val,
+			       void *data)
 {
 	pr_emerg("No human readable MCE decoding support on this CPU type.\n");
 	pr_emerg("Run the message through 'mcelog --ascii' to decode.\n");
+
+	return NOTIFY_STOP;
 }
 
-/*
- * CPU/chipset specific EDAC code can register a callback here to print
- * MCE errors in a human-readable form:
- */
-void (*x86_mce_decode_callback)(struct mce *m) = default_decode_mce;
-EXPORT_SYMBOL(x86_mce_decode_callback);
+static struct notifier_block mce_dec_nb = {
+	.notifier_call = default_decode_mce,
+	.priority      = -1,
+};
 
 /* MCA banks polled by the period polling timer for corrected events */
 DEFINE_PER_CPU(mce_banks_t, mce_poll_banks) = {
@@ -141,6 +152,9 @@ void mce_log(struct mce *mce)
 {
 	unsigned next, entry;
 
+	/* Emit the trace record: */
+	trace_mce_record(mce);
+
 	mce->finished = 0;
 	wmb();
 	for (;;) {
@@ -204,9 +218,9 @@ static void print_mce(struct mce *m)
 
 	/*
 	 * Print out human-readable details about the MCE error,
-	 * (if the CPU has an implementation for that):
+	 * (if the CPU has an implementation for that)
 	 */
-	x86_mce_decode_callback(m);
+	atomic_notifier_call_chain(&x86_mce_decoder_chain, 0, m);
 }
 
 static void print_mce_head(void)
@@ -1122,7 +1136,7 @@ static int check_interval = 5 * 60; /* 5 minutes */
 static DEFINE_PER_CPU(int, mce_next_interval); /* in jiffies */
 static DEFINE_PER_CPU(struct timer_list, mce_timer);
 
-static void mcheck_timer(unsigned long data)
+static void mce_start_timer(unsigned long data)
 {
 	struct timer_list *t = &per_cpu(mce_timer, data);
 	int *n;
@@ -1187,7 +1201,7 @@ int mce_notify_irq(void)
 }
 EXPORT_SYMBOL_GPL(mce_notify_irq);
 
-static int mce_banks_init(void)
+static int __cpuinit __mcheck_cpu_mce_banks_init(void)
 {
 	int i;
 
@@ -1206,7 +1220,7 @@ static int mce_banks_init(void)
 /*
  * Initialize Machine Checks for a CPU.
  */
-static int __cpuinit mce_cap_init(void)
+static int __cpuinit __mcheck_cpu_cap_init(void)
 {
 	unsigned b;
 	u64 cap;
@@ -1228,7 +1242,7 @@ static int __cpuinit mce_cap_init(void)
 	WARN_ON(banks != 0 && b != banks);
 	banks = b;
 	if (!mce_banks) {
-		int err = mce_banks_init();
+		int err = __mcheck_cpu_mce_banks_init();
 
 		if (err)
 			return err;
@@ -1244,7 +1258,7 @@ static int __cpuinit mce_cap_init(void)
 	return 0;
 }
 
-static void mce_init(void)
+static void __mcheck_cpu_init_generic(void)
 {
 	mce_banks_t all_banks;
 	u64 cap;
@@ -1273,7 +1287,7 @@ static void mce_init(void)
 }
 
 /* Add per CPU specific workarounds here */
-static int __cpuinit mce_cpu_quirks(struct cpuinfo_x86 *c)
+static int __cpuinit __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c)
 {
 	if (c->x86_vendor == X86_VENDOR_UNKNOWN) {
 		pr_info("MCE: unknown CPU type - not enabling MCE support.\n");
@@ -1341,7 +1355,7 @@ static int __cpuinit mce_cpu_quirks(struct cpuinfo_x86 *c)
 	return 0;
 }
 
-static void __cpuinit mce_ancient_init(struct cpuinfo_x86 *c)
+static void __cpuinit __mcheck_cpu_ancient_init(struct cpuinfo_x86 *c)
 {
 	if (c->x86 != 5)
 		return;
@@ -1355,7 +1369,7 @@ static void __cpuinit mce_ancient_init(struct cpuinfo_x86 *c)
 	}
 }
 
-static void mce_cpu_features(struct cpuinfo_x86 *c)
+static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c)
 {
 	switch (c->x86_vendor) {
 	case X86_VENDOR_INTEL:
@@ -1369,7 +1383,7 @@ static void mce_cpu_features(struct cpuinfo_x86 *c)
 	}
 }
 
-static void mce_init_timer(void)
+static void __mcheck_cpu_init_timer(void)
 {
 	struct timer_list *t = &__get_cpu_var(mce_timer);
 	int *n = &__get_cpu_var(mce_next_interval);
@@ -1380,7 +1394,7 @@ static void mce_init_timer(void)
 	*n = check_interval * HZ;
 	if (!*n)
 		return;
-	setup_timer(t, mcheck_timer, smp_processor_id());
+	setup_timer(t, mce_start_timer, smp_processor_id());
 	t->expires = round_jiffies(jiffies + *n);
 	add_timer_on(t, smp_processor_id());
 }
@@ -1400,27 +1414,28 @@ void (*machine_check_vector)(struct pt_regs *, long error_code) =
  * Called for each booted CPU to set up machine checks.
  * Must be called with preempt off:
  */
-void __cpuinit mcheck_init(struct cpuinfo_x86 *c)
+void __cpuinit mcheck_cpu_init(struct cpuinfo_x86 *c)
 {
 	if (mce_disabled)
 		return;
 
-	mce_ancient_init(c);
+	__mcheck_cpu_ancient_init(c);
 
 	if (!mce_available(c))
 		return;
 
-	if (mce_cap_init() < 0 || mce_cpu_quirks(c) < 0) {
+	if (__mcheck_cpu_cap_init() < 0 || __mcheck_cpu_apply_quirks(c) < 0) {
 		mce_disabled = 1;
 		return;
 	}
 
 	machine_check_vector = do_machine_check;
 
-	mce_init();
-	mce_cpu_features(c);
-	mce_init_timer();
+	__mcheck_cpu_init_generic();
+	__mcheck_cpu_init_vendor(c);
+	__mcheck_cpu_init_timer();
 	INIT_WORK(&__get_cpu_var(mce_work), mce_process_work);
+
 }
 
 /*
@@ -1640,6 +1655,15 @@ static int __init mcheck_enable(char *str)
 }
 __setup("mce", mcheck_enable);
 
+int __init mcheck_init(void)
+{
+	atomic_notifier_chain_register(&x86_mce_decoder_chain, &mce_dec_nb);
+
+	mcheck_intel_therm_init();
+
+	return 0;
+}
+
 /*
  * Sysfs support
  */
@@ -1648,7 +1672,7 @@ __setup("mce", mcheck_enable);
  * Disable machine checks on suspend and shutdown. We can't really handle
  * them later.
  */
-static int mce_disable(void)
+static int mce_disable_error_reporting(void)
 {
 	int i;
 
@@ -1663,12 +1687,12 @@ static int mce_disable(void)
 
 static int mce_suspend(struct sys_device *dev, pm_message_t state)
 {
-	return mce_disable();
+	return mce_disable_error_reporting();
 }
 
 static int mce_shutdown(struct sys_device *dev)
 {
-	return mce_disable();
+	return mce_disable_error_reporting();
 }
 
 /*
@@ -1678,8 +1702,8 @@ static int mce_shutdown(struct sys_device *dev)
  */
 static int mce_resume(struct sys_device *dev)
 {
-	mce_init();
-	mce_cpu_features(&current_cpu_data);
+	__mcheck_cpu_init_generic();
+	__mcheck_cpu_init_vendor(&current_cpu_data);
 
 	return 0;
 }
@@ -1689,8 +1713,8 @@ static void mce_cpu_restart(void *data)
 	del_timer_sync(&__get_cpu_var(mce_timer));
 	if (!mce_available(&current_cpu_data))
 		return;
-	mce_init();
-	mce_init_timer();
+	__mcheck_cpu_init_generic();
+	__mcheck_cpu_init_timer();
 }
 
 /* Reinit MCEs after user configuration changes */
@@ -1716,7 +1740,7 @@ static void mce_enable_ce(void *all)
 	cmci_reenable();
 	cmci_recheck();
 	if (all)
-		mce_init_timer();
+		__mcheck_cpu_init_timer();
 }
 
 static struct sysdev_class mce_sysclass = {
@@ -1929,13 +1953,14 @@ static __cpuinit void mce_remove_device(unsigned int cpu)
 }
 
 /* Make sure there are no machine checks on offlined CPUs. */
-static void mce_disable_cpu(void *h)
+static void __cpuinit mce_disable_cpu(void *h)
 {
 	unsigned long action = *(unsigned long *)h;
 	int i;
 
 	if (!mce_available(&current_cpu_data))
 		return;
+
 	if (!(action & CPU_TASKS_FROZEN))
 		cmci_clear();
 	for (i = 0; i < banks; i++) {
@@ -1946,7 +1971,7 @@ static void mce_disable_cpu(void *h)
 	}
 }
 
-static void mce_reenable_cpu(void *h)
+static void __cpuinit mce_reenable_cpu(void *h)
 {
 	unsigned long action = *(unsigned long *)h;
 	int i;
@@ -2025,7 +2050,7 @@ static __init void mce_init_banks(void)
 	}
 }
 
-static __init int mce_init_device(void)
+static __init int mcheck_init_device(void)
 {
 	int err;
 	int i = 0;
@@ -2053,7 +2078,7 @@ static __init int mce_init_device(void)
 	return err;
 }
 
-device_initcall(mce_init_device);
+device_initcall(mcheck_init_device);
 
 /*
  * Old style boot options parsing. Only for compatibility.
@@ -2101,7 +2126,7 @@ static int fake_panic_set(void *data, u64 val)
 DEFINE_SIMPLE_ATTRIBUTE(fake_panic_fops, fake_panic_get,
 			fake_panic_set, "%llu\n");
 
-static int __init mce_debugfs_init(void)
+static int __init mcheck_debugfs_init(void)
 {
 	struct dentry *dmce, *ffake_panic;
 
@@ -2115,5 +2140,5 @@ static int __init mce_debugfs_init(void)
 
 	return 0;
 }
-late_initcall(mce_debugfs_init);
+late_initcall(mcheck_debugfs_init);
 #endif

arch/x86/kernel/cpu/mcheck/therm_throt.c

@@ -49,6 +49,8 @@ static DEFINE_PER_CPU(struct thermal_state, thermal_state);
 
 static atomic_t therm_throt_en	= ATOMIC_INIT(0);
 
+static u32 lvtthmr_init __read_mostly;
+
 #ifdef CONFIG_SYSFS
 #define define_therm_throt_sysdev_one_ro(_name)				\
 	static SYSDEV_ATTR(_name, 0444, therm_throt_sysdev_show_##_name, NULL)
@@ -254,6 +256,18 @@ asmlinkage void smp_thermal_interrupt(struct pt_regs *regs)
 	ack_APIC_irq();
 }
 
+void __init mcheck_intel_therm_init(void)
+{
+	/*
+	 * This function is only called on boot CPU. Save the init thermal
+	 * LVT value on BSP and use that value to restore APs' thermal LVT
+	 * entry BIOS programmed later
+	 */
+	if (cpu_has(&boot_cpu_data, X86_FEATURE_ACPI) &&
+		cpu_has(&boot_cpu_data, X86_FEATURE_ACC))
+		lvtthmr_init = apic_read(APIC_LVTTHMR);
+}
+
 void intel_init_thermal(struct cpuinfo_x86 *c)
 {
 	unsigned int cpu = smp_processor_id();
@@ -270,7 +284,20 @@ void intel_init_thermal(struct cpuinfo_x86 *c)
 	 * since it might be delivered via SMI already:
 	 */
 	rdmsr(MSR_IA32_MISC_ENABLE, l, h);
-	h = apic_read(APIC_LVTTHMR);
+
+	/*
+	 * The initial value of thermal LVT entries on all APs always reads
+	 * 0x10000 because APs are woken up by BSP issuing INIT-SIPI-SIPI
+	 * sequence to them and LVT registers are reset to 0s except for
+	 * the mask bits which are set to 1s when APs receive INIT IPI.
+	 * Always restore the value that BIOS has programmed on AP based on
+	 * BSP's info we saved since BIOS is always setting the same value
+	 * for all threads/cores
+	 */
+	apic_write(APIC_LVTTHMR, lvtthmr_init);
+
+	h = lvtthmr_init;
+
 	if ((l & MSR_IA32_MISC_ENABLE_TM1) && (h & APIC_DM_SMI)) {
 		printk(KERN_DEBUG
 		       "CPU%d: Thermal monitoring handled by SMI\n", cpu);

arch/x86/kernel/cpu/perf_event.c

@@ -77,6 +77,18 @@ struct cpu_hw_events {
 	struct debug_store	*ds;
 };
 
+struct event_constraint {
+	unsigned long	idxmsk[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
+	int		code;
+};
+
+#define EVENT_CONSTRAINT(c, m) { .code = (c), .idxmsk[0] = (m) }
+#define EVENT_CONSTRAINT_END  { .code = 0, .idxmsk[0] = 0 }
+
+#define for_each_event_constraint(e, c) \
+	for ((e) = (c); (e)->idxmsk[0]; (e)++)
+
+
 /*
  * struct x86_pmu - generic x86 pmu
  */
@@ -102,6 +114,8 @@ struct x86_pmu {
 	u64		intel_ctrl;
 	void		(*enable_bts)(u64 config);
 	void		(*disable_bts)(void);
+	int		(*get_event_idx)(struct cpu_hw_events *cpuc,
+					 struct hw_perf_event *hwc);
 };
 
 static struct x86_pmu x86_pmu __read_mostly;
@@ -110,6 +124,8 @@ static DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events) = {
 	.enabled = 1,
 };
 
+static const struct event_constraint *event_constraints;
+
 /*
  * Not sure about some of these
  */
@@ -155,6 +171,16 @@ static u64 p6_pmu_raw_event(u64 hw_event)
 	return hw_event & P6_EVNTSEL_MASK;
 }
 
+static const struct event_constraint intel_p6_event_constraints[] =
+{
+	EVENT_CONSTRAINT(0xc1, 0x1),	/* FLOPS */
+	EVENT_CONSTRAINT(0x10, 0x1),	/* FP_COMP_OPS_EXE */
+	EVENT_CONSTRAINT(0x11, 0x1),	/* FP_ASSIST */
+	EVENT_CONSTRAINT(0x12, 0x2),	/* MUL */
+	EVENT_CONSTRAINT(0x13, 0x2),	/* DIV */
+	EVENT_CONSTRAINT(0x14, 0x1),	/* CYCLES_DIV_BUSY */
+	EVENT_CONSTRAINT_END
+};
 
 /*
  * Intel PerfMon v3. Used on Core2 and later.
@@ -170,6 +196,35 @@ static const u64 intel_perfmon_event_map[] =
   [PERF_COUNT_HW_BUS_CYCLES]		= 0x013c,
 };
 
+static const struct event_constraint intel_core_event_constraints[] =
+{
+	EVENT_CONSTRAINT(0x10, 0x1),	/* FP_COMP_OPS_EXE */
+	EVENT_CONSTRAINT(0x11, 0x2),	/* FP_ASSIST */
+	EVENT_CONSTRAINT(0x12, 0x2),	/* MUL */
+	EVENT_CONSTRAINT(0x13, 0x2),	/* DIV */
+	EVENT_CONSTRAINT(0x14, 0x1),	/* CYCLES_DIV_BUSY */
+	EVENT_CONSTRAINT(0x18, 0x1),	/* IDLE_DURING_DIV */
+	EVENT_CONSTRAINT(0x19, 0x2),	/* DELAYED_BYPASS */
+	EVENT_CONSTRAINT(0xa1, 0x1),	/* RS_UOPS_DISPATCH_CYCLES */
+	EVENT_CONSTRAINT(0xcb, 0x1),	/* MEM_LOAD_RETIRED */
+	EVENT_CONSTRAINT_END
+};
+
+static const struct event_constraint intel_nehalem_event_constraints[] =
+{
+	EVENT_CONSTRAINT(0x40, 0x3),	/* L1D_CACHE_LD */
+	EVENT_CONSTRAINT(0x41, 0x3),	/* L1D_CACHE_ST */
+	EVENT_CONSTRAINT(0x42, 0x3),	/* L1D_CACHE_LOCK */
+	EVENT_CONSTRAINT(0x43, 0x3),	/* L1D_ALL_REF */
+	EVENT_CONSTRAINT(0x4e, 0x3),	/* L1D_PREFETCH */
+	EVENT_CONSTRAINT(0x4c, 0x3),	/* LOAD_HIT_PRE */
+	EVENT_CONSTRAINT(0x51, 0x3),	/* L1D */
+	EVENT_CONSTRAINT(0x52, 0x3),	/* L1D_CACHE_PREFETCH_LOCK_FB_HIT */
+	EVENT_CONSTRAINT(0x53, 0x3),	/* L1D_CACHE_LOCK_FB_HIT */
+	EVENT_CONSTRAINT(0xc5, 0x3),	/* CACHE_LOCK_CYCLES */
+	EVENT_CONSTRAINT_END
+};
+
 static u64 intel_pmu_event_map(int hw_event)
 {
 	return intel_perfmon_event_map[hw_event];
@@ -190,7 +245,7 @@ static u64 __read_mostly hw_cache_event_ids
 				[PERF_COUNT_HW_CACHE_OP_MAX]
 				[PERF_COUNT_HW_CACHE_RESULT_MAX];
 
-static const u64 nehalem_hw_cache_event_ids
+static __initconst u64 nehalem_hw_cache_event_ids
 				[PERF_COUNT_HW_CACHE_MAX]
 				[PERF_COUNT_HW_CACHE_OP_MAX]
 				[PERF_COUNT_HW_CACHE_RESULT_MAX] =
@@ -281,7 +336,7 @@ static const u64 nehalem_hw_cache_event_ids
  },
 };
 
-static const u64 core2_hw_cache_event_ids
+static __initconst u64 core2_hw_cache_event_ids
 				[PERF_COUNT_HW_CACHE_MAX]
 				[PERF_COUNT_HW_CACHE_OP_MAX]
 				[PERF_COUNT_HW_CACHE_RESULT_MAX] =
@@ -372,7 +427,7 @@ static const u64 core2_hw_cache_event_ids
  },
 };
 
-static const u64 atom_hw_cache_event_ids
+static __initconst u64 atom_hw_cache_event_ids
 				[PERF_COUNT_HW_CACHE_MAX]
 				[PERF_COUNT_HW_CACHE_OP_MAX]
 				[PERF_COUNT_HW_CACHE_RESULT_MAX] =
@@ -469,7 +524,7 @@ static u64 intel_pmu_raw_event(u64 hw_event)
 #define CORE_EVNTSEL_UNIT_MASK		0x0000FF00ULL
 #define CORE_EVNTSEL_EDGE_MASK		0x00040000ULL
 #define CORE_EVNTSEL_INV_MASK		0x00800000ULL
-#define CORE_EVNTSEL_REG_MASK	0xFF000000ULL
+#define CORE_EVNTSEL_REG_MASK		0xFF000000ULL
 
 #define CORE_EVNTSEL_MASK		\
 	(CORE_EVNTSEL_EVENT_MASK |	\
@@ -481,7 +536,7 @@ static u64 intel_pmu_raw_event(u64 hw_event)
 	return hw_event & CORE_EVNTSEL_MASK;
 }
 
-static const u64 amd_hw_cache_event_ids
+static __initconst u64 amd_hw_cache_event_ids
 				[PERF_COUNT_HW_CACHE_MAX]
 				[PERF_COUNT_HW_CACHE_OP_MAX]
 				[PERF_COUNT_HW_CACHE_RESULT_MAX] =
@@ -932,6 +987,8 @@ static int __hw_perf_event_init(struct perf_event *event)
 	 */
 	hwc->config = ARCH_PERFMON_EVENTSEL_INT;
 
+	hwc->idx = -1;
+
 	/*
 	 * Count user and OS events unless requested not to.
 	 */
@@ -1334,8 +1391,7 @@ static void amd_pmu_enable_event(struct hw_perf_event *hwc, int idx)
 		x86_pmu_enable_event(hwc, idx);
 }
 
-static int
-fixed_mode_idx(struct perf_event *event, struct hw_perf_event *hwc)
+static int fixed_mode_idx(struct hw_perf_event *hwc)
 {
 	unsigned int hw_event;
 
@@ -1349,6 +1405,12 @@ fixed_mode_idx(struct perf_event *event, struct hw_perf_event *hwc)
 	if (!x86_pmu.num_events_fixed)
 		return -1;
 
+	/*
+	 * fixed counters do not take all possible filters
+	 */
+	if (hwc->config & ARCH_PERFMON_EVENT_FILTER_MASK)
+		return -1;
+
 	if (unlikely(hw_event == x86_pmu.event_map(PERF_COUNT_HW_INSTRUCTIONS)))
 		return X86_PMC_IDX_FIXED_INSTRUCTIONS;
 	if (unlikely(hw_event == x86_pmu.event_map(PERF_COUNT_HW_CPU_CYCLES)))
@@ -1360,22 +1422,57 @@ fixed_mode_idx(struct perf_event *event, struct hw_perf_event *hwc)
 }
 
 /*
- * Find a PMC slot for the freshly enabled / scheduled in event:
+ * generic counter allocator: get next free counter
  */
-static int x86_pmu_enable(struct perf_event *event)
+static int
+gen_get_event_idx(struct cpu_hw_events *cpuc, struct hw_perf_event *hwc)
+{
+	int idx;
+
+	idx = find_first_zero_bit(cpuc->used_mask, x86_pmu.num_events);
+	return idx == x86_pmu.num_events ? -1 : idx;
+}
+
+/*
+ * intel-specific counter allocator: check event constraints
+ */
+static int
+intel_get_event_idx(struct cpu_hw_events *cpuc, struct hw_perf_event *hwc)
+{
+	const struct event_constraint *event_constraint;
+	int i, code;
+
+	if (!event_constraints)
+		goto skip;
+
+	code = hwc->config & CORE_EVNTSEL_EVENT_MASK;
+
+	for_each_event_constraint(event_constraint, event_constraints) {
+		if (code == event_constraint->code) {
+			for_each_bit(i, event_constraint->idxmsk, X86_PMC_IDX_MAX) {
+				if (!test_and_set_bit(i, cpuc->used_mask))
+					return i;
+			}
+			return -1;
+		}
+	}
+skip:
+	return gen_get_event_idx(cpuc, hwc);
+}
+
+static int
+x86_schedule_event(struct cpu_hw_events *cpuc, struct hw_perf_event *hwc)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
-	struct hw_perf_event *hwc = &event->hw;
 	int idx;
 
-	idx = fixed_mode_idx(event, hwc);
+	idx = fixed_mode_idx(hwc);
 	if (idx == X86_PMC_IDX_FIXED_BTS) {
 		/* BTS is already occupied. */
 		if (test_and_set_bit(idx, cpuc->used_mask))
 			return -EAGAIN;
 
 		hwc->config_base	= 0;
-		hwc->event_base	= 0;
+		hwc->event_base		= 0;
 		hwc->idx		= idx;
 	} else if (idx >= 0) {
 		/*
@@ -1396,20 +1493,35 @@ static int x86_pmu_enable(struct perf_event *event)
 	} else {
 		idx = hwc->idx;
 		/* Try to get the previous generic event again */
-		if (test_and_set_bit(idx, cpuc->used_mask)) {
+		if (idx == -1 || test_and_set_bit(idx, cpuc->used_mask)) {
 try_generic:
-			idx = find_first_zero_bit(cpuc->used_mask,
-						  x86_pmu.num_events);
-			if (idx == x86_pmu.num_events)
+			idx = x86_pmu.get_event_idx(cpuc, hwc);
+			if (idx == -1)
 				return -EAGAIN;
 
 			set_bit(idx, cpuc->used_mask);
 			hwc->idx = idx;
 		}
-		hwc->config_base  = x86_pmu.eventsel;
-		hwc->event_base = x86_pmu.perfctr;
+		hwc->config_base = x86_pmu.eventsel;
+		hwc->event_base  = x86_pmu.perfctr;
 	}
 
+	return idx;
+}
+
+/*
+ * Find a PMC slot for the freshly enabled / scheduled in event:
+ */
+static int x86_pmu_enable(struct perf_event *event)
+{
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct hw_perf_event *hwc = &event->hw;
+	int idx;
+
+	idx = x86_schedule_event(cpuc, hwc);
+	if (idx < 0)
+		return idx;
+
 	perf_events_lapic_init();
 
 	x86_pmu.disable(hwc, idx);
@@ -1852,7 +1964,7 @@ static __read_mostly struct notifier_block perf_event_nmi_notifier = {
 	.priority		= 1
 };
 
-static struct x86_pmu p6_pmu = {
+static __initconst struct x86_pmu p6_pmu = {
 	.name			= "p6",
 	.handle_irq		= p6_pmu_handle_irq,
 	.disable_all		= p6_pmu_disable_all,
@@ -1877,9 +1989,10 @@ static struct x86_pmu p6_pmu = {
 	 */
 	.event_bits		= 32,
 	.event_mask		= (1ULL << 32) - 1,
+	.get_event_idx		= intel_get_event_idx,
 };
 
-static struct x86_pmu intel_pmu = {
+static __initconst struct x86_pmu intel_pmu = {
 	.name			= "Intel",
 	.handle_irq		= intel_pmu_handle_irq,
 	.disable_all		= intel_pmu_disable_all,
@@ -1900,9 +2013,10 @@ static struct x86_pmu intel_pmu = {
 	.max_period		= (1ULL << 31) - 1,
 	.enable_bts		= intel_pmu_enable_bts,
 	.disable_bts		= intel_pmu_disable_bts,
+	.get_event_idx		= intel_get_event_idx,
 };
 
-static struct x86_pmu amd_pmu = {
+static __initconst struct x86_pmu amd_pmu = {
 	.name			= "AMD",
 	.handle_irq		= amd_pmu_handle_irq,
 	.disable_all		= amd_pmu_disable_all,
@@ -1920,9 +2034,10 @@ static struct x86_pmu amd_pmu = {
 	.apic			= 1,
 	/* use highest bit to detect overflow */
 	.max_period		= (1ULL << 47) - 1,
+	.get_event_idx		= gen_get_event_idx,
 };
 
-static int p6_pmu_init(void)
+static __init int p6_pmu_init(void)
 {
 	switch (boot_cpu_data.x86_model) {
 	case 1:
@@ -1932,10 +2047,12 @@ static int p6_pmu_init(void)
 	case 7:
 	case 8:
 	case 11: /* Pentium III */
+		event_constraints = intel_p6_event_constraints;
 		break;
 	case 9:
 	case 13:
 		/* Pentium M */
+		event_constraints = intel_p6_event_constraints;
 		break;
 	default:
 		pr_cont("unsupported p6 CPU model %d ",
@@ -1954,7 +2071,7 @@ static int p6_pmu_init(void)
 	return 0;
 }
 
-static int intel_pmu_init(void)
+static __init int intel_pmu_init(void)
 {
 	union cpuid10_edx edx;
 	union cpuid10_eax eax;
@@ -2007,12 +2124,14 @@ static int intel_pmu_init(void)
 		       sizeof(hw_cache_event_ids));
 
 		pr_cont("Core2 events, ");
+		event_constraints = intel_core_event_constraints;
 		break;
 	default:
 	case 26:
 		memcpy(hw_cache_event_ids, nehalem_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
 
+		event_constraints = intel_nehalem_event_constraints;
 		pr_cont("Nehalem/Corei7 events, ");
 		break;
 	case 28:
@@ -2025,7 +2144,7 @@ static int intel_pmu_init(void)
 	return 0;
 }
 
-static int amd_pmu_init(void)
+static __init int amd_pmu_init(void)
 {
 	/* Performance-monitoring supported from K7 and later: */
 	if (boot_cpu_data.x86 < 6)
@@ -2105,11 +2224,47 @@ static const struct pmu pmu = {
 	.unthrottle	= x86_pmu_unthrottle,
 };
 
+static int
+validate_event(struct cpu_hw_events *cpuc, struct perf_event *event)
+{
+	struct hw_perf_event fake_event = event->hw;
+
+	if (event->pmu && event->pmu != &pmu)
+		return 0;
+
+	return x86_schedule_event(cpuc, &fake_event) >= 0;
+}
+
+static int validate_group(struct perf_event *event)
+{
+	struct perf_event *sibling, *leader = event->group_leader;
+	struct cpu_hw_events fake_pmu;
+
+	memset(&fake_pmu, 0, sizeof(fake_pmu));
+
+	if (!validate_event(&fake_pmu, leader))
+		return -ENOSPC;
+
+	list_for_each_entry(sibling, &leader->sibling_list, group_entry) {
+		if (!validate_event(&fake_pmu, sibling))
+			return -ENOSPC;
+	}
+
+	if (!validate_event(&fake_pmu, event))
+		return -ENOSPC;
+
+	return 0;
+}
+
 const struct pmu *hw_perf_event_init(struct perf_event *event)
 {
 	int err;
 
 	err = __hw_perf_event_init(event);
+	if (!err) {
+		if (event->group_leader != event)
+			err = validate_group(event);
+	}
 	if (err) {
 		if (event->destroy)
 			event->destroy(event);

arch/x86/kernel/entry_32.S

@@ -333,6 +333,10 @@ ENTRY(ret_from_fork)
 	CFI_ENDPROC
 END(ret_from_fork)
 
+/*
+ * Interrupt exit functions should be protected against kprobes
+ */
+	.pushsection .kprobes.text, "ax"
 /*
  * Return to user mode is not as complex as all this looks,
  * but we want the default path for a system call return to
@@ -383,6 +387,10 @@ need_resched:
 END(resume_kernel)
 #endif
 	CFI_ENDPROC
+/*
+ * End of kprobes section
+ */
+	.popsection
 
 /* SYSENTER_RETURN points to after the "sysenter" instruction in
    the vsyscall page.  See vsyscall-sysentry.S, which defines the symbol.  */
@@ -513,6 +521,10 @@ sysexit_audit:
 	PTGS_TO_GS_EX
 ENDPROC(ia32_sysenter_target)
 
+/*
+ * syscall stub including irq exit should be protected against kprobes
+ */
+	.pushsection .kprobes.text, "ax"
 	# system call handler stub
 ENTRY(system_call)
 	RING0_INT_FRAME			# can't unwind into user space anyway
@@ -705,6 +717,10 @@ syscall_badsys:
 	jmp resume_userspace
 END(syscall_badsys)
 	CFI_ENDPROC
+/*
+ * End of kprobes section
+ */
+	.popsection
 
 /*
  * System calls that need a pt_regs pointer.
@@ -814,6 +830,10 @@ common_interrupt:
 ENDPROC(common_interrupt)
 	CFI_ENDPROC
 
+/*
+ *  Irq entries should be protected against kprobes
+ */
+	.pushsection .kprobes.text, "ax"
 #define BUILD_INTERRUPT3(name, nr, fn)	\
 ENTRY(name)				\
 	RING0_INT_FRAME;		\
@@ -980,6 +1000,10 @@ ENTRY(spurious_interrupt_bug)
 	jmp error_code
 	CFI_ENDPROC
 END(spurious_interrupt_bug)
+/*
+ * End of kprobes section
+ */
+	.popsection
 
 ENTRY(kernel_thread_helper)
 	pushl $0		# fake return address for unwinder

arch/x86/kernel/entry_64.S

@@ -803,6 +803,10 @@ END(interrupt)
 	call \func
 	.endm
 
+/*
+ * Interrupt entry/exit should be protected against kprobes
+ */
+	.pushsection .kprobes.text, "ax"
 	/*
 	 * The interrupt stubs push (~vector+0x80) onto the stack and
 	 * then jump to common_interrupt.
@@ -941,6 +945,10 @@ ENTRY(retint_kernel)
 
 	CFI_ENDPROC
 END(common_interrupt)
+/*
+ * End of kprobes section
+ */
+       .popsection
 
 /*
  * APIC interrupts.

arch/x86/kernel/hw_breakpoint.c

@@ -0,0 +1,555 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ * Copyright (C) 2007 Alan Stern
+ * Copyright (C) 2009 IBM Corporation
+ * Copyright (C) 2009 Frederic Weisbecker <fweisbec@gmail.com>
+ *
+ * Authors: Alan Stern <stern@rowland.harvard.edu>
+ *          K.Prasad <prasad@linux.vnet.ibm.com>
+ *          Frederic Weisbecker <fweisbec@gmail.com>
+ */
+
+/*
+ * HW_breakpoint: a unified kernel/user-space hardware breakpoint facility,
+ * using the CPU's debug registers.
+ */
+
+#include <linux/perf_event.h>
+#include <linux/hw_breakpoint.h>
+#include <linux/irqflags.h>
+#include <linux/notifier.h>
+#include <linux/kallsyms.h>
+#include <linux/kprobes.h>
+#include <linux/percpu.h>
+#include <linux/kdebug.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/sched.h>
+#include <linux/init.h>
+#include <linux/smp.h>
+
+#include <asm/hw_breakpoint.h>
+#include <asm/processor.h>
+#include <asm/debugreg.h>
+
+/* Per cpu debug control register value */
+DEFINE_PER_CPU(unsigned long, cpu_dr7);
+EXPORT_PER_CPU_SYMBOL(cpu_dr7);
+
+/* Per cpu debug address registers values */
+static DEFINE_PER_CPU(unsigned long, cpu_debugreg[HBP_NUM]);
+
+/*
+ * Stores the breakpoints currently in use on each breakpoint address
+ * register for each cpus
+ */
+static DEFINE_PER_CPU(struct perf_event *, bp_per_reg[HBP_NUM]);
+
+
+static inline unsigned long
+__encode_dr7(int drnum, unsigned int len, unsigned int type)
+{
+	unsigned long bp_info;
+
+	bp_info = (len | type) & 0xf;
+	bp_info <<= (DR_CONTROL_SHIFT + drnum * DR_CONTROL_SIZE);
+	bp_info |= (DR_GLOBAL_ENABLE << (drnum * DR_ENABLE_SIZE));
+
+	return bp_info;
+}
+
+/*
+ * Encode the length, type, Exact, and Enable bits for a particular breakpoint
+ * as stored in debug register 7.
+ */
+unsigned long encode_dr7(int drnum, unsigned int len, unsigned int type)
+{
+	return __encode_dr7(drnum, len, type) | DR_GLOBAL_SLOWDOWN;
+}
+
+/*
+ * Decode the length and type bits for a particular breakpoint as
+ * stored in debug register 7.  Return the "enabled" status.
+ */
+int decode_dr7(unsigned long dr7, int bpnum, unsigned *len, unsigned *type)
+{
+	int bp_info = dr7 >> (DR_CONTROL_SHIFT + bpnum * DR_CONTROL_SIZE);
+
+	*len = (bp_info & 0xc) | 0x40;
+	*type = (bp_info & 0x3) | 0x80;
+
+	return (dr7 >> (bpnum * DR_ENABLE_SIZE)) & 0x3;
+}
+
+/*
+ * Install a perf counter breakpoint.
+ *
+ * We seek a free debug address register and use it for this
+ * breakpoint. Eventually we enable it in the debug control register.
+ *
+ * Atomic: we hold the counter->ctx->lock and we only handle variables
+ * and registers local to this cpu.
+ */
+int arch_install_hw_breakpoint(struct perf_event *bp)
+{
+	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
+	unsigned long *dr7;
+	int i;
+
+	for (i = 0; i < HBP_NUM; i++) {
+		struct perf_event **slot = &__get_cpu_var(bp_per_reg[i]);
+
+		if (!*slot) {
+			*slot = bp;
+			break;
+		}
+	}
+
+	if (WARN_ONCE(i == HBP_NUM, "Can't find any breakpoint slot"))
+		return -EBUSY;
+
+	set_debugreg(info->address, i);
+	__get_cpu_var(cpu_debugreg[i]) = info->address;
+
+	dr7 = &__get_cpu_var(cpu_dr7);
+	*dr7 |= encode_dr7(i, info->len, info->type);
+
+	set_debugreg(*dr7, 7);
+
+	return 0;
+}
+
+/*
+ * Uninstall the breakpoint contained in the given counter.
+ *
+ * First we search the debug address register it uses and then we disable
+ * it.
+ *
+ * Atomic: we hold the counter->ctx->lock and we only handle variables
+ * and registers local to this cpu.
+ */
+void arch_uninstall_hw_breakpoint(struct perf_event *bp)
+{
+	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
+	unsigned long *dr7;
+	int i;
+
+	for (i = 0; i < HBP_NUM; i++) {
+		struct perf_event **slot = &__get_cpu_var(bp_per_reg[i]);
+
+		if (*slot == bp) {
+			*slot = NULL;
+			break;
+		}
+	}
+
+	if (WARN_ONCE(i == HBP_NUM, "Can't find any breakpoint slot"))
+		return;
+
+	dr7 = &__get_cpu_var(cpu_dr7);
+	*dr7 &= ~__encode_dr7(i, info->len, info->type);
+
+	set_debugreg(*dr7, 7);
+}
+
+static int get_hbp_len(u8 hbp_len)
+{
+	unsigned int len_in_bytes = 0;
+
+	switch (hbp_len) {
+	case X86_BREAKPOINT_LEN_1:
+		len_in_bytes = 1;
+		break;
+	case X86_BREAKPOINT_LEN_2:
+		len_in_bytes = 2;
+		break;
+	case X86_BREAKPOINT_LEN_4:
+		len_in_bytes = 4;
+		break;
+#ifdef CONFIG_X86_64
+	case X86_BREAKPOINT_LEN_8:
+		len_in_bytes = 8;
+		break;
+#endif
+	}
+	return len_in_bytes;
+}
+
+/*
+ * Check for virtual address in user space.
+ */
+int arch_check_va_in_userspace(unsigned long va, u8 hbp_len)
+{
+	unsigned int len;
+
+	len = get_hbp_len(hbp_len);
+
+	return (va <= TASK_SIZE - len);
+}
+
+/*
+ * Check for virtual address in kernel space.
+ */
+static int arch_check_va_in_kernelspace(unsigned long va, u8 hbp_len)
+{
+	unsigned int len;
+
+	len = get_hbp_len(hbp_len);
+
+	return (va >= TASK_SIZE) && ((va + len - 1) >= TASK_SIZE);
+}
+
+/*
+ * Store a breakpoint's encoded address, length, and type.
+ */
+static int arch_store_info(struct perf_event *bp)
+{
+	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
+	/*
+	 * For kernel-addresses, either the address or symbol name can be
+	 * specified.
+	 */
+	if (info->name)
+		info->address = (unsigned long)
+				kallsyms_lookup_name(info->name);
+	if (info->address)
+		return 0;
+
+	return -EINVAL;
+}
+
+int arch_bp_generic_fields(int x86_len, int x86_type,
+			   int *gen_len, int *gen_type)
+{
+	/* Len */
+	switch (x86_len) {
+	case X86_BREAKPOINT_LEN_1:
+		*gen_len = HW_BREAKPOINT_LEN_1;
+		break;
+	case X86_BREAKPOINT_LEN_2:
+		*gen_len = HW_BREAKPOINT_LEN_2;
+		break;
+	case X86_BREAKPOINT_LEN_4:
+		*gen_len = HW_BREAKPOINT_LEN_4;
+		break;
+#ifdef CONFIG_X86_64
+	case X86_BREAKPOINT_LEN_8:
+		*gen_len = HW_BREAKPOINT_LEN_8;
+		break;
+#endif
+	default:
+		return -EINVAL;
+	}
+
+	/* Type */
+	switch (x86_type) {
+	case X86_BREAKPOINT_EXECUTE:
+		*gen_type = HW_BREAKPOINT_X;
+		break;
+	case X86_BREAKPOINT_WRITE:
+		*gen_type = HW_BREAKPOINT_W;
+		break;
+	case X86_BREAKPOINT_RW:
+		*gen_type = HW_BREAKPOINT_W | HW_BREAKPOINT_R;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+
+static int arch_build_bp_info(struct perf_event *bp)
+{
+	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
+
+	info->address = bp->attr.bp_addr;
+
+	/* Len */
+	switch (bp->attr.bp_len) {
+	case HW_BREAKPOINT_LEN_1:
+		info->len = X86_BREAKPOINT_LEN_1;
+		break;
+	case HW_BREAKPOINT_LEN_2:
+		info->len = X86_BREAKPOINT_LEN_2;
+		break;
+	case HW_BREAKPOINT_LEN_4:
+		info->len = X86_BREAKPOINT_LEN_4;
+		break;
+#ifdef CONFIG_X86_64
+	case HW_BREAKPOINT_LEN_8:
+		info->len = X86_BREAKPOINT_LEN_8;
+		break;
+#endif
+	default:
+		return -EINVAL;
+	}
+
+	/* Type */
+	switch (bp->attr.bp_type) {
+	case HW_BREAKPOINT_W:
+		info->type = X86_BREAKPOINT_WRITE;
+		break;
+	case HW_BREAKPOINT_W | HW_BREAKPOINT_R:
+		info->type = X86_BREAKPOINT_RW;
+		break;
+	case HW_BREAKPOINT_X:
+		info->type = X86_BREAKPOINT_EXECUTE;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+/*
+ * Validate the arch-specific HW Breakpoint register settings
+ */
+int arch_validate_hwbkpt_settings(struct perf_event *bp,
+				  struct task_struct *tsk)
+{
+	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
+	unsigned int align;
+	int ret;
+
+
+	ret = arch_build_bp_info(bp);
+	if (ret)
+		return ret;
+
+	ret = -EINVAL;
+
+	if (info->type == X86_BREAKPOINT_EXECUTE)
+		/*
+		 * Ptrace-refactoring code
+		 * For now, we'll allow instruction breakpoint only for user-space
+		 * addresses
+		 */
+		if ((!arch_check_va_in_userspace(info->address, info->len)) &&
+			info->len != X86_BREAKPOINT_EXECUTE)
+			return ret;
+
+	switch (info->len) {
+	case X86_BREAKPOINT_LEN_1:
+		align = 0;
+		break;
+	case X86_BREAKPOINT_LEN_2:
+		align = 1;
+		break;
+	case X86_BREAKPOINT_LEN_4:
+		align = 3;
+		break;
+#ifdef CONFIG_X86_64
+	case X86_BREAKPOINT_LEN_8:
+		align = 7;
+		break;
+#endif
+	default:
+		return ret;
+	}
+
+	if (bp->callback)
+		ret = arch_store_info(bp);
+
+	if (ret < 0)
+		return ret;
+	/*
+	 * Check that the low-order bits of the address are appropriate
+	 * for the alignment implied by len.
+	 */
+	if (info->address & align)
+		return -EINVAL;
+
+	/* Check that the virtual address is in the proper range */
+	if (tsk) {
+		if (!arch_check_va_in_userspace(info->address, info->len))
+			return -EFAULT;
+	} else {
+		if (!arch_check_va_in_kernelspace(info->address, info->len))
+			return -EFAULT;
+	}
+
+	return 0;
+}
+
+/*
+ * Dump the debug register contents to the user.
+ * We can't dump our per cpu values because it
+ * may contain cpu wide breakpoint, something that
+ * doesn't belong to the current task.
+ *
+ * TODO: include non-ptrace user breakpoints (perf)
+ */
+void aout_dump_debugregs(struct user *dump)
+{
+	int i;
+	int dr7 = 0;
+	struct perf_event *bp;
+	struct arch_hw_breakpoint *info;
+	struct thread_struct *thread = &current->thread;
+
+	for (i = 0; i < HBP_NUM; i++) {
+		bp = thread->ptrace_bps[i];
+
+		if (bp && !bp->attr.disabled) {
+			dump->u_debugreg[i] = bp->attr.bp_addr;
+			info = counter_arch_bp(bp);
+			dr7 |= encode_dr7(i, info->len, info->type);
+		} else {
+			dump->u_debugreg[i] = 0;
+		}
+	}
+
+	dump->u_debugreg[4] = 0;
+	dump->u_debugreg[5] = 0;
+	dump->u_debugreg[6] = current->thread.debugreg6;
+
+	dump->u_debugreg[7] = dr7;
+}
+EXPORT_SYMBOL_GPL(aout_dump_debugregs);
+
+/*
+ * Release the user breakpoints used by ptrace
+ */
+void flush_ptrace_hw_breakpoint(struct task_struct *tsk)
+{
+	int i;
+	struct thread_struct *t = &tsk->thread;
+
+	for (i = 0; i < HBP_NUM; i++) {
+		unregister_hw_breakpoint(t->ptrace_bps[i]);
+		t->ptrace_bps[i] = NULL;
+	}
+}
+
+void hw_breakpoint_restore(void)
+{
+	set_debugreg(__get_cpu_var(cpu_debugreg[0]), 0);
+	set_debugreg(__get_cpu_var(cpu_debugreg[1]), 1);
+	set_debugreg(__get_cpu_var(cpu_debugreg[2]), 2);
+	set_debugreg(__get_cpu_var(cpu_debugreg[3]), 3);
+	set_debugreg(current->thread.debugreg6, 6);
+	set_debugreg(__get_cpu_var(cpu_dr7), 7);
+}
+EXPORT_SYMBOL_GPL(hw_breakpoint_restore);
+
+/*
+ * Handle debug exception notifications.
+ *
+ * Return value is either NOTIFY_STOP or NOTIFY_DONE as explained below.
+ *
+ * NOTIFY_DONE returned if one of the following conditions is true.
+ * i) When the causative address is from user-space and the exception
+ * is a valid one, i.e. not triggered as a result of lazy debug register
+ * switching
+ * ii) When there are more bits than trap<n> set in DR6 register (such
+ * as BD, BS or BT) indicating that more than one debug condition is
+ * met and requires some more action in do_debug().
+ *
+ * NOTIFY_STOP returned for all other cases
+ *
+ */
+static int __kprobes hw_breakpoint_handler(struct die_args *args)
+{
+	int i, cpu, rc = NOTIFY_STOP;
+	struct perf_event *bp;
+	unsigned long dr7, dr6;
+	unsigned long *dr6_p;
+
+	/* The DR6 value is pointed by args->err */
+	dr6_p = (unsigned long *)ERR_PTR(args->err);
+	dr6 = *dr6_p;
+
+	/* Do an early return if no trap bits are set in DR6 */
+	if ((dr6 & DR_TRAP_BITS) == 0)
+		return NOTIFY_DONE;
+
+	get_debugreg(dr7, 7);
+	/* Disable breakpoints during exception handling */
+	set_debugreg(0UL, 7);
+	/*
+	 * Assert that local interrupts are disabled
+	 * Reset the DRn bits in the virtualized register value.
+	 * The ptrace trigger routine will add in whatever is needed.
+	 */
+	current->thread.debugreg6 &= ~DR_TRAP_BITS;
+	cpu = get_cpu();
+
+	/* Handle all the breakpoints that were triggered */
+	for (i = 0; i < HBP_NUM; ++i) {
+		if (likely(!(dr6 & (DR_TRAP0 << i))))
+			continue;
+
+		/*
+		 * The counter may be concurrently released but that can only
+		 * occur from a call_rcu() path. We can then safely fetch
+		 * the breakpoint, use its callback, touch its counter
+		 * while we are in an rcu_read_lock() path.
+		 */
+		rcu_read_lock();
+
+		bp = per_cpu(bp_per_reg[i], cpu);
+		if (bp)
+			rc = NOTIFY_DONE;
+		/*
+		 * Reset the 'i'th TRAP bit in dr6 to denote completion of
+		 * exception handling
+		 */
+		(*dr6_p) &= ~(DR_TRAP0 << i);
+		/*
+		 * bp can be NULL due to lazy debug register switching
+		 * or due to concurrent perf counter removing.
+		 */
+		if (!bp) {
+			rcu_read_unlock();
+			break;
+		}
+
+		(bp->callback)(bp, args->regs);
+
+		rcu_read_unlock();
+	}
+	if (dr6 & (~DR_TRAP_BITS))
+		rc = NOTIFY_DONE;
+
+	set_debugreg(dr7, 7);
+	put_cpu();
+
+	return rc;
+}
+
+/*
+ * Handle debug exception notifications.
+ */
+int __kprobes hw_breakpoint_exceptions_notify(
+		struct notifier_block *unused, unsigned long val, void *data)
+{
+	if (val != DIE_DEBUG)
+		return NOTIFY_DONE;
+
+	return hw_breakpoint_handler(data);
+}
+
+void hw_breakpoint_pmu_read(struct perf_event *bp)
+{
+	/* TODO */
+}
+
+void hw_breakpoint_pmu_unthrottle(struct perf_event *bp)
+{
+	/* TODO */
+}

arch/x86/kernel/irq.c

@@ -92,17 +92,17 @@ static int show_other_interrupts(struct seq_file *p, int prec)
 		seq_printf(p, "%10u ", irq_stats(j)->irq_tlb_count);
 	seq_printf(p, "  TLB shootdowns\n");
 #endif
-#ifdef CONFIG_X86_MCE
+#ifdef CONFIG_X86_THERMAL_VECTOR
 	seq_printf(p, "%*s: ", prec, "TRM");
 	for_each_online_cpu(j)
 		seq_printf(p, "%10u ", irq_stats(j)->irq_thermal_count);
 	seq_printf(p, "  Thermal event interrupts\n");
-# ifdef CONFIG_X86_MCE_THRESHOLD
+#endif
+#ifdef CONFIG_X86_MCE_THRESHOLD
 	seq_printf(p, "%*s: ", prec, "THR");
 	for_each_online_cpu(j)
 		seq_printf(p, "%10u ", irq_stats(j)->irq_threshold_count);
 	seq_printf(p, "  Threshold APIC interrupts\n");
-# endif
 #endif
 #ifdef CONFIG_X86_MCE
 	seq_printf(p, "%*s: ", prec, "MCE");
@@ -194,11 +194,11 @@ u64 arch_irq_stat_cpu(unsigned int cpu)
 	sum += irq_stats(cpu)->irq_call_count;
 	sum += irq_stats(cpu)->irq_tlb_count;
 #endif
-#ifdef CONFIG_X86_MCE
+#ifdef CONFIG_X86_THERMAL_VECTOR
 	sum += irq_stats(cpu)->irq_thermal_count;
-# ifdef CONFIG_X86_MCE_THRESHOLD
+#endif
+#ifdef CONFIG_X86_MCE_THRESHOLD
 	sum += irq_stats(cpu)->irq_threshold_count;
-# endif
 #endif
 #ifdef CONFIG_X86_MCE
 	sum += per_cpu(mce_exception_count, cpu);

arch/x86/kernel/kgdb.c

@@ -43,6 +43,7 @@
 #include <linux/smp.h>
 #include <linux/nmi.h>
 
+#include <asm/debugreg.h>
 #include <asm/apicdef.h>
 #include <asm/system.h>
 
@@ -434,6 +435,11 @@ single_step_cont(struct pt_regs *regs, struct die_args *args)
 			"resuming...\n");
 	kgdb_arch_handle_exception(args->trapnr, args->signr,
 				   args->err, "c", "", regs);
+	/*
+	 * Reset the BS bit in dr6 (pointed by args->err) to
+	 * denote completion of processing
+	 */
+	(*(unsigned long *)ERR_PTR(args->err)) &= ~DR_STEP;
 
 	return NOTIFY_STOP;
 }

arch/x86/kernel/kprobes.c

@@ -48,12 +48,15 @@
 #include <linux/preempt.h>
 #include <linux/module.h>
 #include <linux/kdebug.h>
+#include <linux/kallsyms.h>
 
 #include <asm/cacheflush.h>
 #include <asm/desc.h>
 #include <asm/pgtable.h>
 #include <asm/uaccess.h>
 #include <asm/alternative.h>
+#include <asm/insn.h>
+#include <asm/debugreg.h>
 
 void jprobe_return_end(void);
 
@@ -106,50 +109,6 @@ static const u32 twobyte_is_boostable[256 / 32] = {
 	/*      -----------------------------------------------         */
 	/*      0  1  2  3  4  5  6  7  8  9  a  b  c  d  e  f          */
 };
-static const u32 onebyte_has_modrm[256 / 32] = {
-	/*      0  1  2  3  4  5  6  7  8  9  a  b  c  d  e  f          */
-	/*      -----------------------------------------------         */
-	W(0x00, 1, 1, 1, 1, 0, 0, 0, 0, 1, 1, 1, 1, 0, 0, 0, 0) | /* 00 */
-	W(0x10, 1, 1, 1, 1, 0, 0, 0, 0, 1, 1, 1, 1, 0, 0, 0, 0) , /* 10 */
-	W(0x20, 1, 1, 1, 1, 0, 0, 0, 0, 1, 1, 1, 1, 0, 0, 0, 0) | /* 20 */
-	W(0x30, 1, 1, 1, 1, 0, 0, 0, 0, 1, 1, 1, 1, 0, 0, 0, 0) , /* 30 */
-	W(0x40, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) | /* 40 */
-	W(0x50, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) , /* 50 */
-	W(0x60, 0, 0, 1, 1, 0, 0, 0, 0, 0, 1, 0, 1, 0, 0, 0, 0) | /* 60 */
-	W(0x70, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) , /* 70 */
-	W(0x80, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) | /* 80 */
-	W(0x90, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) , /* 90 */
-	W(0xa0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) | /* a0 */
-	W(0xb0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) , /* b0 */
-	W(0xc0, 1, 1, 0, 0, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0) | /* c0 */
-	W(0xd0, 1, 1, 1, 1, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1) , /* d0 */
-	W(0xe0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) | /* e0 */
-	W(0xf0, 0, 0, 0, 0, 0, 0, 1, 1, 0, 0, 0, 0, 0, 0, 1, 1)   /* f0 */
-	/*      -----------------------------------------------         */
-	/*      0  1  2  3  4  5  6  7  8  9  a  b  c  d  e  f          */
-};
-static const u32 twobyte_has_modrm[256 / 32] = {
-	/*      0  1  2  3  4  5  6  7  8  9  a  b  c  d  e  f          */
-	/*      -----------------------------------------------         */
-	W(0x00, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 1) | /* 0f */
-	W(0x10, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0) , /* 1f */
-	W(0x20, 1, 1, 1, 1, 1, 0, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1) | /* 2f */
-	W(0x30, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) , /* 3f */
-	W(0x40, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) | /* 4f */
-	W(0x50, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* 5f */
-	W(0x60, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) | /* 6f */
-	W(0x70, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 1, 1, 1, 1) , /* 7f */
-	W(0x80, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) | /* 8f */
-	W(0x90, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* 9f */
-	W(0xa0, 0, 0, 0, 1, 1, 1, 1, 1, 0, 0, 0, 1, 1, 1, 1, 1) | /* af */
-	W(0xb0, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1, 1, 1) , /* bf */
-	W(0xc0, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0) | /* cf */
-	W(0xd0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* df */
-	W(0xe0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) | /* ef */
-	W(0xf0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0)   /* ff */
-	/*      -----------------------------------------------         */
-	/*      0  1  2  3  4  5  6  7  8  9  a  b  c  d  e  f          */
-};
 #undef W
 
 struct kretprobe_blackpoint kretprobe_blacklist[] = {
@@ -244,6 +203,75 @@ retry:
 	}
 }
 
+/* Recover the probed instruction at addr for further analysis. */
+static int recover_probed_instruction(kprobe_opcode_t *buf, unsigned long addr)
+{
+	struct kprobe *kp;
+	kp = get_kprobe((void *)addr);
+	if (!kp)
+		return -EINVAL;
+
+	/*
+	 *  Basically, kp->ainsn.insn has an original instruction.
+	 *  However, RIP-relative instruction can not do single-stepping
+	 *  at different place, fix_riprel() tweaks the displacement of
+	 *  that instruction. In that case, we can't recover the instruction
+	 *  from the kp->ainsn.insn.
+	 *
+	 *  On the other hand, kp->opcode has a copy of the first byte of
+	 *  the probed instruction, which is overwritten by int3. And
+	 *  the instruction at kp->addr is not modified by kprobes except
+	 *  for the first byte, we can recover the original instruction
+	 *  from it and kp->opcode.
+	 */
+	memcpy(buf, kp->addr, MAX_INSN_SIZE * sizeof(kprobe_opcode_t));
+	buf[0] = kp->opcode;
+	return 0;
+}
+
+/* Dummy buffers for kallsyms_lookup */
+static char __dummy_buf[KSYM_NAME_LEN];
+
+/* Check if paddr is at an instruction boundary */
+static int __kprobes can_probe(unsigned long paddr)
+{
+	int ret;
+	unsigned long addr, offset = 0;
+	struct insn insn;
+	kprobe_opcode_t buf[MAX_INSN_SIZE];
+
+	if (!kallsyms_lookup(paddr, NULL, &offset, NULL, __dummy_buf))
+		return 0;
+
+	/* Decode instructions */
+	addr = paddr - offset;
+	while (addr < paddr) {
+		kernel_insn_init(&insn, (void *)addr);
+		insn_get_opcode(&insn);
+
+		/*
+		 * Check if the instruction has been modified by another
+		 * kprobe, in which case we replace the breakpoint by the
+		 * original instruction in our buffer.
+		 */
+		if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION) {
+			ret = recover_probed_instruction(buf, addr);
+			if (ret)
+				/*
+				 * Another debugging subsystem might insert
+				 * this breakpoint. In that case, we can't
+				 * recover it.
+				 */
+				return 0;
+			kernel_insn_init(&insn, buf);
+		}
+		insn_get_length(&insn);
+		addr += insn.length;
+	}
+
+	return (addr == paddr);
+}
+
 /*
  * Returns non-zero if opcode modifies the interrupt flag.
  */
@@ -277,68 +305,30 @@ static int __kprobes is_IF_modifier(kprobe_opcode_t *insn)
 static void __kprobes fix_riprel(struct kprobe *p)
 {
 #ifdef CONFIG_X86_64
-	u8 *insn = p->ainsn.insn;
-	s64 disp;
-	int need_modrm;
-
-	/* Skip legacy instruction prefixes.  */
-	while (1) {
-		switch (*insn) {
-		case 0x66:
-		case 0x67:
-		case 0x2e:
-		case 0x3e:
-		case 0x26:
-		case 0x64:
-		case 0x65:
-		case 0x36:
-		case 0xf0:
-		case 0xf3:
-		case 0xf2:
-			++insn;
-			continue;
-		}
-		break;
-	}
+	struct insn insn;
+	kernel_insn_init(&insn, p->ainsn.insn);
 
-	/* Skip REX instruction prefix.  */
-	if (is_REX_prefix(insn))
-		++insn;
-
-	if (*insn == 0x0f) {
-		/* Two-byte opcode.  */
-		++insn;
-		need_modrm = test_bit(*insn,
-				      (unsigned long *)twobyte_has_modrm);
-	} else
-		/* One-byte opcode.  */
-		need_modrm = test_bit(*insn,
-				      (unsigned long *)onebyte_has_modrm);
-
-	if (need_modrm) {
-		u8 modrm = *++insn;
-		if ((modrm & 0xc7) == 0x05) {
-			/* %rip+disp32 addressing mode */
-			/* Displacement follows ModRM byte.  */
-			++insn;
-			/*
-			 * The copied instruction uses the %rip-relative
-			 * addressing mode.  Adjust the displacement for the
-			 * difference between the original location of this
-			 * instruction and the location of the copy that will
-			 * actually be run.  The tricky bit here is making sure
-			 * that the sign extension happens correctly in this
-			 * calculation, since we need a signed 32-bit result to
-			 * be sign-extended to 64 bits when it's added to the
-			 * %rip value and yield the same 64-bit result that the
-			 * sign-extension of the original signed 32-bit
-			 * displacement would have given.
-			 */
-			disp = (u8 *) p->addr + *((s32 *) insn) -
-			       (u8 *) p->ainsn.insn;
-			BUG_ON((s64) (s32) disp != disp); /* Sanity check.  */
-			*(s32 *)insn = (s32) disp;
-		}
+	if (insn_rip_relative(&insn)) {
+		s64 newdisp;
+		u8 *disp;
+		insn_get_displacement(&insn);
+		/*
+		 * The copied instruction uses the %rip-relative addressing
+		 * mode.  Adjust the displacement for the difference between
+		 * the original location of this instruction and the location
+		 * of the copy that will actually be run.  The tricky bit here
+		 * is making sure that the sign extension happens correctly in
+		 * this calculation, since we need a signed 32-bit result to
+		 * be sign-extended to 64 bits when it's added to the %rip
+		 * value and yield the same 64-bit result that the sign-
+		 * extension of the original signed 32-bit displacement would
+		 * have given.
+		 */
+		newdisp = (u8 *) p->addr + (s64) insn.displacement.value -
+			  (u8 *) p->ainsn.insn;
+		BUG_ON((s64) (s32) newdisp != newdisp); /* Sanity check.  */
+		disp = (u8 *) p->ainsn.insn + insn_offset_displacement(&insn);
+		*(s32 *) disp = (s32) newdisp;
 	}
 #endif
 }
@@ -359,6 +349,8 @@ static void __kprobes arch_copy_kprobe(struct kprobe *p)
 
 int __kprobes arch_prepare_kprobe(struct kprobe *p)
 {
+	if (!can_probe((unsigned long)p->addr))
+		return -EILSEQ;
 	/* insn: must be on special executable page on x86. */
 	p->ainsn.insn = get_insn_slot();
 	if (!p->ainsn.insn)
@@ -472,17 +464,6 @@ static int __kprobes reenter_kprobe(struct kprobe *p, struct pt_regs *regs,
 {
 	switch (kcb->kprobe_status) {
 	case KPROBE_HIT_SSDONE:
-#ifdef CONFIG_X86_64
-		/* TODO: Provide re-entrancy from post_kprobes_handler() and
-		 * avoid exception stack corruption while single-stepping on
-		 * the instruction of the new probe.
-		 */
-		arch_disarm_kprobe(p);
-		regs->ip = (unsigned long)p->addr;
-		reset_current_kprobe();
-		preempt_enable_no_resched();
-		break;
-#endif
 	case KPROBE_HIT_ACTIVE:
 		save_previous_kprobe(kcb);
 		set_current_kprobe(p, regs, kcb);
@@ -491,18 +472,16 @@ static int __kprobes reenter_kprobe(struct kprobe *p, struct pt_regs *regs,
 		kcb->kprobe_status = KPROBE_REENTER;
 		break;
 	case KPROBE_HIT_SS:
-		if (p == kprobe_running()) {
-			regs->flags &= ~X86_EFLAGS_TF;
-			regs->flags |= kcb->kprobe_saved_flags;
-			return 0;
-		} else {
-			/* A probe has been hit in the codepath leading up
-			 * to, or just after, single-stepping of a probed
-			 * instruction. This entire codepath should strictly
-			 * reside in .kprobes.text section. Raise a warning
-			 * to highlight this peculiar case.
-			 */
-		}
+		/* A probe has been hit in the codepath leading up to, or just
+		 * after, single-stepping of a probed instruction. This entire
+		 * codepath should strictly reside in .kprobes.text section.
+		 * Raise a BUG or we'll continue in an endless reentering loop
+		 * and eventually a stack overflow.
+		 */
+		printk(KERN_WARNING "Unrecoverable kprobe detected at %p.\n",
+		       p->addr);
+		dump_kprobe(p);
+		BUG();
 	default:
 		/* impossible cases */
 		WARN_ON(1);
@@ -967,8 +946,14 @@ int __kprobes kprobe_exceptions_notify(struct notifier_block *self,
 			ret = NOTIFY_STOP;
 		break;
 	case DIE_DEBUG:
-		if (post_kprobe_handler(args->regs))
+		if (post_kprobe_handler(args->regs)) {
+			/*
+			 * Reset the BS bit in dr6 (pointed by args->err) to
+			 * denote completion of processing
+			 */
+			(*(unsigned long *)ERR_PTR(args->err)) &= ~DR_STEP;
 			ret = NOTIFY_STOP;
+		}
 		break;
 	case DIE_GPF:
 		/*

arch/x86/kernel/machine_kexec_32.c

@@ -25,6 +25,7 @@
 #include <asm/desc.h>
 #include <asm/system.h>
 #include <asm/cacheflush.h>
+#include <asm/debugreg.h>
 
 static void set_idt(void *newidt, __u16 limit)
 {
@@ -202,6 +203,7 @@ void machine_kexec(struct kimage *image)
 
 	/* Interrupts aren't acceptable while we reboot */
 	local_irq_disable();
+	hw_breakpoint_disable();
 
 	if (image->preserve_context) {
 #ifdef CONFIG_X86_IO_APIC

arch/x86/kernel/machine_kexec_64.c

@@ -18,6 +18,7 @@
 #include <asm/pgtable.h>
 #include <asm/tlbflush.h>
 #include <asm/mmu_context.h>
+#include <asm/debugreg.h>
 
 static int init_one_level2_page(struct kimage *image, pgd_t *pgd,
 				unsigned long addr)
@@ -282,6 +283,7 @@ void machine_kexec(struct kimage *image)
 
 	/* Interrupts aren't acceptable while we reboot */
 	local_irq_disable();
+	hw_breakpoint_disable();
 
 	if (image->preserve_context) {
 #ifdef CONFIG_X86_IO_APIC

arch/x86/kernel/process.c

@@ -10,6 +10,7 @@
 #include <linux/clockchips.h>
 #include <linux/random.h>
 #include <trace/events/power.h>
+#include <linux/hw_breakpoint.h>
 #include <asm/system.h>
 #include <asm/apic.h>
 #include <asm/syscalls.h>
@@ -17,6 +18,7 @@
 #include <asm/uaccess.h>
 #include <asm/i387.h>
 #include <asm/ds.h>
+#include <asm/debugreg.h>
 
 unsigned long idle_halt;
 EXPORT_SYMBOL(idle_halt);
@@ -103,14 +105,7 @@ void flush_thread(void)
 	}
 #endif
 
-	clear_tsk_thread_flag(tsk, TIF_DEBUG);
-
-	tsk->thread.debugreg0 = 0;
-	tsk->thread.debugreg1 = 0;
-	tsk->thread.debugreg2 = 0;
-	tsk->thread.debugreg3 = 0;
-	tsk->thread.debugreg6 = 0;
-	tsk->thread.debugreg7 = 0;
+	flush_ptrace_hw_breakpoint(tsk);
 	memset(tsk->thread.tls_array, 0, sizeof(tsk->thread.tls_array));
 	/*
 	 * Forget coprocessor state..
@@ -192,16 +187,6 @@ void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p,
 	else if (next->debugctlmsr != prev->debugctlmsr)
 		update_debugctlmsr(next->debugctlmsr);
 
-	if (test_tsk_thread_flag(next_p, TIF_DEBUG)) {
-		set_debugreg(next->debugreg0, 0);
-		set_debugreg(next->debugreg1, 1);
-		set_debugreg(next->debugreg2, 2);
-		set_debugreg(next->debugreg3, 3);
-		/* no 4 and 5 */
-		set_debugreg(next->debugreg6, 6);
-		set_debugreg(next->debugreg7, 7);
-	}
-
 	if (test_tsk_thread_flag(prev_p, TIF_NOTSC) ^
 	    test_tsk_thread_flag(next_p, TIF_NOTSC)) {
 		/* prev and next are different */

arch/x86/kernel/process_32.c

@@ -58,6 +58,7 @@
 #include <asm/idle.h>
 #include <asm/syscalls.h>
 #include <asm/ds.h>
+#include <asm/debugreg.h>
 
 asmlinkage void ret_from_fork(void) __asm__("ret_from_fork");
 
@@ -259,7 +260,12 @@ int copy_thread(unsigned long clone_flags, unsigned long sp,
 
 	task_user_gs(p) = get_user_gs(regs);
 
+	p->thread.io_bitmap_ptr = NULL;
 	tsk = current;
+	err = -ENOMEM;
+
+	memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps));
+
 	if (unlikely(test_tsk_thread_flag(tsk, TIF_IO_BITMAP))) {
 		p->thread.io_bitmap_ptr = kmemdup(tsk->thread.io_bitmap_ptr,
 						IO_BITMAP_BYTES, GFP_KERNEL);

arch/x86/kernel/process_64.c

@@ -52,6 +52,7 @@
 #include <asm/idle.h>
 #include <asm/syscalls.h>
 #include <asm/ds.h>
+#include <asm/debugreg.h>
 
 asmlinkage extern void ret_from_fork(void);
 
@@ -297,12 +298,16 @@ int copy_thread(unsigned long clone_flags, unsigned long sp,
 
 	p->thread.fs = me->thread.fs;
 	p->thread.gs = me->thread.gs;
+	p->thread.io_bitmap_ptr = NULL;
 
 	savesegment(gs, p->thread.gsindex);
 	savesegment(fs, p->thread.fsindex);
 	savesegment(es, p->thread.es);
 	savesegment(ds, p->thread.ds);
 
+	err = -ENOMEM;
+	memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps));
+
 	if (unlikely(test_tsk_thread_flag(me, TIF_IO_BITMAP))) {
 		p->thread.io_bitmap_ptr = kmalloc(IO_BITMAP_BYTES, GFP_KERNEL);
 		if (!p->thread.io_bitmap_ptr) {
@@ -341,6 +346,7 @@ out:
 		kfree(p->thread.io_bitmap_ptr);
 		p->thread.io_bitmap_max = 0;
 	}
+
 	return err;
 }
 
@@ -495,6 +501,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	 */
 	if (preload_fpu)
 		__math_state_restore();
+
 	return prev_p;
 }
 

arch/x86/kernel/ptrace.c

@@ -22,6 +22,8 @@
 #include <linux/seccomp.h>
 #include <linux/signal.h>
 #include <linux/workqueue.h>
+#include <linux/perf_event.h>
+#include <linux/hw_breakpoint.h>
 
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
@@ -34,6 +36,7 @@
 #include <asm/prctl.h>
 #include <asm/proto.h>
 #include <asm/ds.h>
+#include <asm/hw_breakpoint.h>
 
 #include "tls.h"
 
@@ -49,6 +52,118 @@ enum x86_regset {
 	REGSET_IOPERM32,
 };
 
+struct pt_regs_offset {
+	const char *name;
+	int offset;
+};
+
+#define REG_OFFSET_NAME(r) {.name = #r, .offset = offsetof(struct pt_regs, r)}
+#define REG_OFFSET_END {.name = NULL, .offset = 0}
+
+static const struct pt_regs_offset regoffset_table[] = {
+#ifdef CONFIG_X86_64
+	REG_OFFSET_NAME(r15),
+	REG_OFFSET_NAME(r14),
+	REG_OFFSET_NAME(r13),
+	REG_OFFSET_NAME(r12),
+	REG_OFFSET_NAME(r11),
+	REG_OFFSET_NAME(r10),
+	REG_OFFSET_NAME(r9),
+	REG_OFFSET_NAME(r8),
+#endif
+	REG_OFFSET_NAME(bx),
+	REG_OFFSET_NAME(cx),
+	REG_OFFSET_NAME(dx),
+	REG_OFFSET_NAME(si),
+	REG_OFFSET_NAME(di),
+	REG_OFFSET_NAME(bp),
+	REG_OFFSET_NAME(ax),
+#ifdef CONFIG_X86_32
+	REG_OFFSET_NAME(ds),
+	REG_OFFSET_NAME(es),
+	REG_OFFSET_NAME(fs),
+	REG_OFFSET_NAME(gs),
+#endif
+	REG_OFFSET_NAME(orig_ax),
+	REG_OFFSET_NAME(ip),
+	REG_OFFSET_NAME(cs),
+	REG_OFFSET_NAME(flags),
+	REG_OFFSET_NAME(sp),
+	REG_OFFSET_NAME(ss),
+	REG_OFFSET_END,
+};
+
+/**
+ * regs_query_register_offset() - query register offset from its name
+ * @name:	the name of a register
+ *
+ * regs_query_register_offset() returns the offset of a register in struct
+ * pt_regs from its name. If the name is invalid, this returns -EINVAL;
+ */
+int regs_query_register_offset(const char *name)
+{
+	const struct pt_regs_offset *roff;
+	for (roff = regoffset_table; roff->name != NULL; roff++)
+		if (!strcmp(roff->name, name))
+			return roff->offset;
+	return -EINVAL;
+}
+
+/**
+ * regs_query_register_name() - query register name from its offset
+ * @offset:	the offset of a register in struct pt_regs.
+ *
+ * regs_query_register_name() returns the name of a register from its
+ * offset in struct pt_regs. If the @offset is invalid, this returns NULL;
+ */
+const char *regs_query_register_name(unsigned int offset)
+{
+	const struct pt_regs_offset *roff;
+	for (roff = regoffset_table; roff->name != NULL; roff++)
+		if (roff->offset == offset)
+			return roff->name;
+	return NULL;
+}
+
+static const int arg_offs_table[] = {
+#ifdef CONFIG_X86_32
+	[0] = offsetof(struct pt_regs, ax),
+	[1] = offsetof(struct pt_regs, dx),
+	[2] = offsetof(struct pt_regs, cx)
+#else /* CONFIG_X86_64 */
+	[0] = offsetof(struct pt_regs, di),
+	[1] = offsetof(struct pt_regs, si),
+	[2] = offsetof(struct pt_regs, dx),
+	[3] = offsetof(struct pt_regs, cx),
+	[4] = offsetof(struct pt_regs, r8),
+	[5] = offsetof(struct pt_regs, r9)
+#endif
+};
+
+/**
+ * regs_get_argument_nth() - get Nth argument at function call
+ * @regs:	pt_regs which contains registers at function entry.
+ * @n:		argument number.
+ *
+ * regs_get_argument_nth() returns @n th argument of a function call.
+ * Since usually the kernel stack will be changed right after function entry,
+ * you must use this at function entry. If the @n th entry is NOT in the
+ * kernel stack or pt_regs, this returns 0.
+ */
+unsigned long regs_get_argument_nth(struct pt_regs *regs, unsigned int n)
+{
+	if (n < ARRAY_SIZE(arg_offs_table))
+		return *(unsigned long *)((char *)regs + arg_offs_table[n]);
+	else {
+		/*
+		 * The typical case: arg n is on the stack.
+		 * (Note: stack[0] = return address, so skip it)
+		 */
+		n -= ARRAY_SIZE(arg_offs_table);
+		return regs_get_kernel_stack_nth(regs, 1 + n);
+	}
+}
+
 /*
  * does not yet catch signals sent when the child dies.
  * in exit.c or in signal.c.
@@ -137,11 +252,6 @@ static int set_segment_reg(struct task_struct *task,
 	return 0;
 }
 
-static unsigned long debugreg_addr_limit(struct task_struct *task)
-{
-	return TASK_SIZE - 3;
-}
-
 #else  /* CONFIG_X86_64 */
 
 #define FLAG_MASK		(FLAG_MASK_32 | X86_EFLAGS_NT)
@@ -266,15 +376,6 @@ static int set_segment_reg(struct task_struct *task,
 	return 0;
 }
 
-static unsigned long debugreg_addr_limit(struct task_struct *task)
-{
-#ifdef CONFIG_IA32_EMULATION
-	if (test_tsk_thread_flag(task, TIF_IA32))
-		return IA32_PAGE_OFFSET - 3;
-#endif
-	return TASK_SIZE_MAX - 7;
-}
-
 #endif	/* CONFIG_X86_32 */
 
 static unsigned long get_flags(struct task_struct *task)
@@ -454,98 +555,238 @@ static int genregs_set(struct task_struct *target,
 	return ret;
 }
 
+static void ptrace_triggered(struct perf_event *bp, void *data)
+{
+	int i;
+	struct thread_struct *thread = &(current->thread);
+
+	/*
+	 * Store in the virtual DR6 register the fact that the breakpoint
+	 * was hit so the thread's debugger will see it.
+	 */
+	for (i = 0; i < HBP_NUM; i++) {
+		if (thread->ptrace_bps[i] == bp)
+			break;
+	}
+
+	thread->debugreg6 |= (DR_TRAP0 << i);
+}
+
 /*
- * This function is trivial and will be inlined by the compiler.
- * Having it separates the implementation details of debug
- * registers from the interface details of ptrace.
+ * Walk through every ptrace breakpoints for this thread and
+ * build the dr7 value on top of their attributes.
+ *
  */
-static unsigned long ptrace_get_debugreg(struct task_struct *child, int n)
+static unsigned long ptrace_get_dr7(struct perf_event *bp[])
 {
-	switch (n) {
-	case 0:		return child->thread.debugreg0;
-	case 1:		return child->thread.debugreg1;
-	case 2:		return child->thread.debugreg2;
-	case 3:		return child->thread.debugreg3;
-	case 6:		return child->thread.debugreg6;
-	case 7:		return child->thread.debugreg7;
+	int i;
+	int dr7 = 0;
+	struct arch_hw_breakpoint *info;
+
+	for (i = 0; i < HBP_NUM; i++) {
+		if (bp[i] && !bp[i]->attr.disabled) {
+			info = counter_arch_bp(bp[i]);
+			dr7 |= encode_dr7(i, info->len, info->type);
+		}
 	}
-	return 0;
+
+	return dr7;
 }
 
-static int ptrace_set_debugreg(struct task_struct *child,
-			       int n, unsigned long data)
+static struct perf_event *
+ptrace_modify_breakpoint(struct perf_event *bp, int len, int type,
+			 struct task_struct *tsk, int disabled)
 {
-	int i;
+	int err;
+	int gen_len, gen_type;
+	DEFINE_BREAKPOINT_ATTR(attr);
 
-	if (unlikely(n == 4 || n == 5))
-		return -EIO;
+	/*
+	 * We shoud have at least an inactive breakpoint at this
+	 * slot. It means the user is writing dr7 without having
+	 * written the address register first
+	 */
+	if (!bp)
+		return ERR_PTR(-EINVAL);
 
-	if (n < 4 && unlikely(data >= debugreg_addr_limit(child)))
-		return -EIO;
+	err = arch_bp_generic_fields(len, type, &gen_len, &gen_type);
+	if (err)
+		return ERR_PTR(err);
 
-	switch (n) {
-	case 0:		child->thread.debugreg0 = data; break;
-	case 1:		child->thread.debugreg1 = data; break;
-	case 2:		child->thread.debugreg2 = data; break;
-	case 3:		child->thread.debugreg3 = data; break;
+	attr = bp->attr;
+	attr.bp_len = gen_len;
+	attr.bp_type = gen_type;
+	attr.disabled = disabled;
 
-	case 6:
-		if ((data & ~0xffffffffUL) != 0)
-			return -EIO;
-		child->thread.debugreg6 = data;
-		break;
+	return modify_user_hw_breakpoint(bp, &attr, bp->callback, tsk);
+}
+
+/*
+ * Handle ptrace writes to debug register 7.
+ */
+static int ptrace_write_dr7(struct task_struct *tsk, unsigned long data)
+{
+	struct thread_struct *thread = &(tsk->thread);
+	unsigned long old_dr7;
+	int i, orig_ret = 0, rc = 0;
+	int enabled, second_pass = 0;
+	unsigned len, type;
+	struct perf_event *bp;
+
+	data &= ~DR_CONTROL_RESERVED;
+	old_dr7 = ptrace_get_dr7(thread->ptrace_bps);
+restore:
+	/*
+	 * Loop through all the hardware breakpoints, making the
+	 * appropriate changes to each.
+	 */
+	for (i = 0; i < HBP_NUM; i++) {
+		enabled = decode_dr7(data, i, &len, &type);
+		bp = thread->ptrace_bps[i];
+
+		if (!enabled) {
+			if (bp) {
+				/*
+				 * Don't unregister the breakpoints right-away,
+				 * unless all register_user_hw_breakpoint()
+				 * requests have succeeded. This prevents
+				 * any window of opportunity for debug
+				 * register grabbing by other users.
+				 */
+				if (!second_pass)
+					continue;
+
+				thread->ptrace_bps[i] = NULL;
+				bp = ptrace_modify_breakpoint(bp, len, type,
+							      tsk, 1);
+				if (IS_ERR(bp)) {
+					rc = PTR_ERR(bp);
+					thread->ptrace_bps[i] = NULL;
+					break;
+				}
+				thread->ptrace_bps[i] = bp;
+			}
+			continue;
+		}
+
+		bp = ptrace_modify_breakpoint(bp, len, type, tsk, 0);
+
+		/* Incorrect bp, or we have a bug in bp API */
+		if (IS_ERR(bp)) {
+			rc = PTR_ERR(bp);
+			thread->ptrace_bps[i] = NULL;
+			break;
+		}
+		thread->ptrace_bps[i] = bp;
+	}
+	/*
+	 * Make a second pass to free the remaining unused breakpoints
+	 * or to restore the original breakpoints if an error occurred.
+	 */
+	if (!second_pass) {
+		second_pass = 1;
+		if (rc < 0) {
+			orig_ret = rc;
+			data = old_dr7;
+		}
+		goto restore;
+	}
+	return ((orig_ret < 0) ? orig_ret : rc);
+}
+
+/*
+ * Handle PTRACE_PEEKUSR calls for the debug register area.
+ */
+static unsigned long ptrace_get_debugreg(struct task_struct *tsk, int n)
+{
+	struct thread_struct *thread = &(tsk->thread);
+	unsigned long val = 0;
 
-	case 7:
+	if (n < HBP_NUM) {
+		struct perf_event *bp;
+		bp = thread->ptrace_bps[n];
+		if (!bp)
+			return 0;
+		val = bp->hw.info.address;
+	} else if (n == 6) {
+		val = thread->debugreg6;
+	 } else if (n == 7) {
+		val = ptrace_get_dr7(thread->ptrace_bps);
+	}
+	return val;
+}
+
+static int ptrace_set_breakpoint_addr(struct task_struct *tsk, int nr,
+				      unsigned long addr)
+{
+	struct perf_event *bp;
+	struct thread_struct *t = &tsk->thread;
+	DEFINE_BREAKPOINT_ATTR(attr);
+
+	if (!t->ptrace_bps[nr]) {
 		/*
-		 * Sanity-check data. Take one half-byte at once with
-		 * check = (val >> (16 + 4*i)) & 0xf. It contains the
-		 * R/Wi and LENi bits; bits 0 and 1 are R/Wi, and bits
-		 * 2 and 3 are LENi. Given a list of invalid values,
-		 * we do mask |= 1 << invalid_value, so that
-		 * (mask >> check) & 1 is a correct test for invalid
-		 * values.
-		 *
-		 * R/Wi contains the type of the breakpoint /
-		 * watchpoint, LENi contains the length of the watched
-		 * data in the watchpoint case.
-		 *
-		 * The invalid values are:
-		 * - LENi == 0x10 (undefined), so mask |= 0x0f00.	[32-bit]
-		 * - R/Wi == 0x10 (break on I/O reads or writes), so
-		 *   mask |= 0x4444.
-		 * - R/Wi == 0x00 && LENi != 0x00, so we have mask |=
-		 *   0x1110.
-		 *
-		 * Finally, mask = 0x0f00 | 0x4444 | 0x1110 == 0x5f54.
-		 *
-		 * See the Intel Manual "System Programming Guide",
-		 * 15.2.4
-		 *
-		 * Note that LENi == 0x10 is defined on x86_64 in long
-		 * mode (i.e. even for 32-bit userspace software, but
-		 * 64-bit kernel), so the x86_64 mask value is 0x5454.
-		 * See the AMD manual no. 24593 (AMD64 System Programming)
+		 * Put stub len and type to register (reserve) an inactive but
+		 * correct bp
 		 */
-#ifdef CONFIG_X86_32
-#define	DR7_MASK	0x5f54
-#else
-#define	DR7_MASK	0x5554
-#endif
-		data &= ~DR_CONTROL_RESERVED;
-		for (i = 0; i < 4; i++)
-			if ((DR7_MASK >> ((data >> (16 + 4*i)) & 0xf)) & 1)
-				return -EIO;
-		child->thread.debugreg7 = data;
-		if (data)
-			set_tsk_thread_flag(child, TIF_DEBUG);
-		else
-			clear_tsk_thread_flag(child, TIF_DEBUG);
-		break;
+		attr.bp_addr = addr;
+		attr.bp_len = HW_BREAKPOINT_LEN_1;
+		attr.bp_type = HW_BREAKPOINT_W;
+		attr.disabled = 1;
+
+		bp = register_user_hw_breakpoint(&attr, ptrace_triggered, tsk);
+	} else {
+		bp = t->ptrace_bps[nr];
+		t->ptrace_bps[nr] = NULL;
+
+		attr = bp->attr;
+		attr.bp_addr = addr;
+		bp = modify_user_hw_breakpoint(bp, &attr, bp->callback, tsk);
 	}
+	/*
+	 * CHECKME: the previous code returned -EIO if the addr wasn't a
+	 * valid task virtual addr. The new one will return -EINVAL in this
+	 * case.
+	 * -EINVAL may be what we want for in-kernel breakpoints users, but
+	 * -EIO looks better for ptrace, since we refuse a register writing
+	 * for the user. And anyway this is the previous behaviour.
+	 */
+	if (IS_ERR(bp))
+		return PTR_ERR(bp);
+
+	t->ptrace_bps[nr] = bp;
 
 	return 0;
 }
 
+/*
+ * Handle PTRACE_POKEUSR calls for the debug register area.
+ */
+int ptrace_set_debugreg(struct task_struct *tsk, int n, unsigned long val)
+{
+	struct thread_struct *thread = &(tsk->thread);
+	int rc = 0;
+
+	/* There are no DR4 or DR5 registers */
+	if (n == 4 || n == 5)
+		return -EIO;
+
+	if (n == 6) {
+		thread->debugreg6 = val;
+		goto ret_path;
+	}
+	if (n < HBP_NUM) {
+		rc = ptrace_set_breakpoint_addr(tsk, n, val);
+		if (rc)
+			return rc;
+	}
+	/* All that's left is DR7 */
+	if (n == 7)
+		rc = ptrace_write_dr7(tsk, val);
+
+ret_path:
+	return rc;
+}
+
 /*
  * These access the current or another (stopped) task's io permission
  * bitmap for debugging or core dump.

arch/x86/kernel/setup.c

@@ -109,6 +109,7 @@
 #ifdef CONFIG_X86_64
 #include <asm/numa_64.h>
 #endif
+#include <asm/mce.h>
 
 /*
  * end_pfn only includes RAM, while max_pfn_mapped includes all e820 entries.
@@ -1031,6 +1032,8 @@ void __init setup_arch(char **cmdline_p)
 #endif
 #endif
 	x86_init.oem.banner();
+
+	mcheck_init();
 }
 
 #ifdef CONFIG_X86_32

arch/x86/kernel/signal.c

@@ -799,15 +799,6 @@ static void do_signal(struct pt_regs *regs)
 
 	signr = get_signal_to_deliver(&info, &ka, regs, NULL);
 	if (signr > 0) {
-		/*
-		 * Re-enable any watchpoints before delivering the
-		 * signal to user space. The processor register will
-		 * have been cleared if the watchpoint triggered
-		 * inside the kernel.
-		 */
-		if (current->thread.debugreg7)
-			set_debugreg(current->thread.debugreg7, 7);
-
 		/* Whee! Actually deliver the signal.  */
 		if (handle_signal(signr, &info, &ka, oldset, regs) == 0) {
 			/*

arch/x86/kernel/traps.c

@@ -529,77 +529,56 @@ asmlinkage __kprobes struct pt_regs *sync_regs(struct pt_regs *eregs)
 dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code)
 {
 	struct task_struct *tsk = current;
-	unsigned long condition;
+	unsigned long dr6;
 	int si_code;
 
-	get_debugreg(condition, 6);
+	get_debugreg(dr6, 6);
 
 	/* Catch kmemcheck conditions first of all! */
-	if (condition & DR_STEP && kmemcheck_trap(regs))
+	if ((dr6 & DR_STEP) && kmemcheck_trap(regs))
 		return;
 
+	/* DR6 may or may not be cleared by the CPU */
+	set_debugreg(0, 6);
 	/*
 	 * The processor cleared BTF, so don't mark that we need it set.
 	 */
 	clear_tsk_thread_flag(tsk, TIF_DEBUGCTLMSR);
 	tsk->thread.debugctlmsr = 0;
 
-	if (notify_die(DIE_DEBUG, "debug", regs, condition, error_code,
-						SIGTRAP) == NOTIFY_STOP)
+	/* Store the virtualized DR6 value */
+	tsk->thread.debugreg6 = dr6;
+
+	if (notify_die(DIE_DEBUG, "debug", regs, PTR_ERR(&dr6), error_code,
+							SIGTRAP) == NOTIFY_STOP)
 		return;
 
 	/* It's safe to allow irq's after DR6 has been saved */
 	preempt_conditional_sti(regs);
 
-	/* Mask out spurious debug traps due to lazy DR7 setting */
-	if (condition & (DR_TRAP0|DR_TRAP1|DR_TRAP2|DR_TRAP3)) {
-		if (!tsk->thread.debugreg7)
-			goto clear_dr7;
+	if (regs->flags & X86_VM_MASK) {
+		handle_vm86_trap((struct kernel_vm86_regs *) regs,
+				error_code, 1);
+		return;
 	}
 
-#ifdef CONFIG_X86_32
-	if (regs->flags & X86_VM_MASK)
-		goto debug_vm86;
-#endif
-
-	/* Save debug status register where ptrace can see it */
-	tsk->thread.debugreg6 = condition;
-
 	/*
-	 * Single-stepping through TF: make sure we ignore any events in
-	 * kernel space (but re-enable TF when returning to user mode).
+	 * Single-stepping through system calls: ignore any exceptions in
+	 * kernel space, but re-enable TF when returning to user mode.
+	 *
+	 * We already checked v86 mode above, so we can check for kernel mode
+	 * by just checking the CPL of CS.
 	 */
-	if (condition & DR_STEP) {
-		if (!user_mode(regs))
-			goto clear_TF_reenable;
+	if ((dr6 & DR_STEP) && !user_mode(regs)) {
+		tsk->thread.debugreg6 &= ~DR_STEP;
+		set_tsk_thread_flag(tsk, TIF_SINGLESTEP);
+		regs->flags &= ~X86_EFLAGS_TF;
 	}
-
-	si_code = get_si_code(condition);
-	/* Ok, finally something we can handle */
-	send_sigtrap(tsk, regs, error_code, si_code);
-
-	/*
-	 * Disable additional traps. They'll be re-enabled when
-	 * the signal is delivered.
-	 */
-clear_dr7:
-	set_debugreg(0, 7);
+	si_code = get_si_code(tsk->thread.debugreg6);
+	if (tsk->thread.debugreg6 & (DR_STEP | DR_TRAP_BITS))
+		send_sigtrap(tsk, regs, error_code, si_code);
 	preempt_conditional_cli(regs);
-	return;
 
-#ifdef CONFIG_X86_32
-debug_vm86:
-	/* reenable preemption: handle_vm86_trap() might sleep */
-	dec_preempt_count();
-	handle_vm86_trap((struct kernel_vm86_regs *) regs, error_code, 1);
-	conditional_cli(regs);
-	return;
-#endif
-
-clear_TF_reenable:
-	set_tsk_thread_flag(tsk, TIF_SINGLESTEP);
-	regs->flags &= ~X86_EFLAGS_TF;
-	preempt_conditional_cli(regs);
 	return;
 }
 

arch/x86/kvm/x86.c

@@ -42,6 +42,7 @@
 #define CREATE_TRACE_POINTS
 #include "trace.h"
 
+#include <asm/debugreg.h>
 #include <asm/uaccess.h>
 #include <asm/msr.h>
 #include <asm/desc.h>
@@ -3643,14 +3644,15 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	trace_kvm_entry(vcpu->vcpu_id);
 	kvm_x86_ops->run(vcpu, kvm_run);
 
-	if (unlikely(vcpu->arch.switch_db_regs || test_thread_flag(TIF_DEBUG))) {
-		set_debugreg(current->thread.debugreg0, 0);
-		set_debugreg(current->thread.debugreg1, 1);
-		set_debugreg(current->thread.debugreg2, 2);
-		set_debugreg(current->thread.debugreg3, 3);
-		set_debugreg(current->thread.debugreg6, 6);
-		set_debugreg(current->thread.debugreg7, 7);
-	}
+	/*
+	 * If the guest has used debug registers, at least dr7
+	 * will be disabled while returning to the host.
+	 * If we don't have active breakpoints in the host, we don't
+	 * care about the messed up debug address registers. But if
+	 * we have some of them active, restore the old state.
+	 */
+	if (hw_breakpoint_active())
+		hw_breakpoint_restore();
 
 	set_bit(KVM_REQ_KICK, &vcpu->requests);
 	local_irq_enable();

arch/x86/lib/.gitignore

@@ -0,0 +1 @@
+inat-tables.c

arch/x86/lib/Makefile

@@ -2,12 +2,25 @@
 # Makefile for x86 specific library files.
 #
 
+inat_tables_script = $(srctree)/arch/x86/tools/gen-insn-attr-x86.awk
+inat_tables_maps = $(srctree)/arch/x86/lib/x86-opcode-map.txt
+quiet_cmd_inat_tables = GEN     $@
+      cmd_inat_tables = $(AWK) -f $(inat_tables_script) $(inat_tables_maps) > $@
+
+$(obj)/inat-tables.c: $(inat_tables_script) $(inat_tables_maps)
+	$(call cmd,inat_tables)
+
+$(obj)/inat.o: $(obj)/inat-tables.c
+
+clean-files := inat-tables.c
+
 obj-$(CONFIG_SMP) := msr.o
 
 lib-y := delay.o
 lib-y += thunk_$(BITS).o
 lib-y += usercopy_$(BITS).o getuser.o putuser.o
 lib-y += memcpy_$(BITS).o
+lib-y += insn.o inat.o
 
 obj-y += msr-reg.o msr-reg-export.o
 

arch/x86/lib/inat.c

@@ -0,0 +1,90 @@
+/*
+ * x86 instruction attribute tables
+ *
+ * Written by Masami Hiramatsu <mhiramat@redhat.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ */
+#include <asm/insn.h>
+
+/* Attribute tables are generated from opcode map */
+#include "inat-tables.c"
+
+/* Attribute search APIs */
+insn_attr_t inat_get_opcode_attribute(insn_byte_t opcode)
+{
+	return inat_primary_table[opcode];
+}
+
+insn_attr_t inat_get_escape_attribute(insn_byte_t opcode, insn_byte_t last_pfx,
+				      insn_attr_t esc_attr)
+{
+	const insn_attr_t *table;
+	insn_attr_t lpfx_attr;
+	int n, m = 0;
+
+	n = inat_escape_id(esc_attr);
+	if (last_pfx) {
+		lpfx_attr = inat_get_opcode_attribute(last_pfx);
+		m = inat_last_prefix_id(lpfx_attr);
+	}
+	table = inat_escape_tables[n][0];
+	if (!table)
+		return 0;
+	if (inat_has_variant(table[opcode]) && m) {
+		table = inat_escape_tables[n][m];
+		if (!table)
+			return 0;
+	}
+	return table[opcode];
+}
+
+insn_attr_t inat_get_group_attribute(insn_byte_t modrm, insn_byte_t last_pfx,
+				     insn_attr_t grp_attr)
+{
+	const insn_attr_t *table;
+	insn_attr_t lpfx_attr;
+	int n, m = 0;
+
+	n = inat_group_id(grp_attr);
+	if (last_pfx) {
+		lpfx_attr = inat_get_opcode_attribute(last_pfx);
+		m = inat_last_prefix_id(lpfx_attr);
+	}
+	table = inat_group_tables[n][0];
+	if (!table)
+		return inat_group_common_attribute(grp_attr);
+	if (inat_has_variant(table[X86_MODRM_REG(modrm)]) && m) {
+		table = inat_group_tables[n][m];
+		if (!table)
+			return inat_group_common_attribute(grp_attr);
+	}
+	return table[X86_MODRM_REG(modrm)] |
+	       inat_group_common_attribute(grp_attr);
+}
+
+insn_attr_t inat_get_avx_attribute(insn_byte_t opcode, insn_byte_t vex_m,
+				   insn_byte_t vex_p)
+{
+	const insn_attr_t *table;
+	if (vex_m > X86_VEX_M_MAX || vex_p > INAT_LSTPFX_MAX)
+		return 0;
+	table = inat_avx_tables[vex_m][vex_p];
+	if (!table)
+		return 0;
+	return table[opcode];
+}
+

arch/x86/lib/insn.c

@@ -0,0 +1,516 @@
+/*
+ * x86 instruction analysis
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ * Copyright (C) IBM Corporation, 2002, 2004, 2009
+ */
+
+#include <linux/string.h>
+#include <asm/inat.h>
+#include <asm/insn.h>
+
+#define get_next(t, insn)	\
+	({t r; r = *(t*)insn->next_byte; insn->next_byte += sizeof(t); r; })
+
+#define peek_next(t, insn)	\
+	({t r; r = *(t*)insn->next_byte; r; })
+
+#define peek_nbyte_next(t, insn, n)	\
+	({t r; r = *(t*)((insn)->next_byte + n); r; })
+
+/**
+ * insn_init() - initialize struct insn
+ * @insn:	&struct insn to be initialized
+ * @kaddr:	address (in kernel memory) of instruction (or copy thereof)
+ * @x86_64:	!0 for 64-bit kernel or 64-bit app
+ */
+void insn_init(struct insn *insn, const void *kaddr, int x86_64)
+{
+	memset(insn, 0, sizeof(*insn));
+	insn->kaddr = kaddr;
+	insn->next_byte = kaddr;
+	insn->x86_64 = x86_64 ? 1 : 0;
+	insn->opnd_bytes = 4;
+	if (x86_64)
+		insn->addr_bytes = 8;
+	else
+		insn->addr_bytes = 4;
+}
+
+/**
+ * insn_get_prefixes - scan x86 instruction prefix bytes
+ * @insn:	&struct insn containing instruction
+ *
+ * Populates the @insn->prefixes bitmap, and updates @insn->next_byte
+ * to point to the (first) opcode.  No effect if @insn->prefixes.got
+ * is already set.
+ */
+void insn_get_prefixes(struct insn *insn)
+{
+	struct insn_field *prefixes = &insn->prefixes;
+	insn_attr_t attr;
+	insn_byte_t b, lb;
+	int i, nb;
+
+	if (prefixes->got)
+		return;
+
+	nb = 0;
+	lb = 0;
+	b = peek_next(insn_byte_t, insn);
+	attr = inat_get_opcode_attribute(b);
+	while (inat_is_legacy_prefix(attr)) {
+		/* Skip if same prefix */
+		for (i = 0; i < nb; i++)
+			if (prefixes->bytes[i] == b)
+				goto found;
+		if (nb == 4)
+			/* Invalid instruction */
+			break;
+		prefixes->bytes[nb++] = b;
+		if (inat_is_address_size_prefix(attr)) {
+			/* address size switches 2/4 or 4/8 */
+			if (insn->x86_64)
+				insn->addr_bytes ^= 12;
+			else
+				insn->addr_bytes ^= 6;
+		} else if (inat_is_operand_size_prefix(attr)) {
+			/* oprand size switches 2/4 */
+			insn->opnd_bytes ^= 6;
+		}
+found:
+		prefixes->nbytes++;
+		insn->next_byte++;
+		lb = b;
+		b = peek_next(insn_byte_t, insn);
+		attr = inat_get_opcode_attribute(b);
+	}
+	/* Set the last prefix */
+	if (lb && lb != insn->prefixes.bytes[3]) {
+		if (unlikely(insn->prefixes.bytes[3])) {
+			/* Swap the last prefix */
+			b = insn->prefixes.bytes[3];
+			for (i = 0; i < nb; i++)
+				if (prefixes->bytes[i] == lb)
+					prefixes->bytes[i] = b;
+		}
+		insn->prefixes.bytes[3] = lb;
+	}
+
+	/* Decode REX prefix */
+	if (insn->x86_64) {
+		b = peek_next(insn_byte_t, insn);
+		attr = inat_get_opcode_attribute(b);
+		if (inat_is_rex_prefix(attr)) {
+			insn->rex_prefix.value = b;
+			insn->rex_prefix.nbytes = 1;
+			insn->next_byte++;
+			if (X86_REX_W(b))
+				/* REX.W overrides opnd_size */
+				insn->opnd_bytes = 8;
+		}
+	}
+	insn->rex_prefix.got = 1;
+
+	/* Decode VEX prefix */
+	b = peek_next(insn_byte_t, insn);
+	attr = inat_get_opcode_attribute(b);
+	if (inat_is_vex_prefix(attr)) {
+		insn_byte_t b2 = peek_nbyte_next(insn_byte_t, insn, 1);
+		if (!insn->x86_64) {
+			/*
+			 * In 32-bits mode, if the [7:6] bits (mod bits of
+			 * ModRM) on the second byte are not 11b, it is
+			 * LDS or LES.
+			 */
+			if (X86_MODRM_MOD(b2) != 3)
+				goto vex_end;
+		}
+		insn->vex_prefix.bytes[0] = b;
+		insn->vex_prefix.bytes[1] = b2;
+		if (inat_is_vex3_prefix(attr)) {
+			b2 = peek_nbyte_next(insn_byte_t, insn, 2);
+			insn->vex_prefix.bytes[2] = b2;
+			insn->vex_prefix.nbytes = 3;
+			insn->next_byte += 3;
+			if (insn->x86_64 && X86_VEX_W(b2))
+				/* VEX.W overrides opnd_size */
+				insn->opnd_bytes = 8;
+		} else {
+			insn->vex_prefix.nbytes = 2;
+			insn->next_byte += 2;
+		}
+	}
+vex_end:
+	insn->vex_prefix.got = 1;
+
+	prefixes->got = 1;
+	return;
+}
+
+/**
+ * insn_get_opcode - collect opcode(s)
+ * @insn:	&struct insn containing instruction
+ *
+ * Populates @insn->opcode, updates @insn->next_byte to point past the
+ * opcode byte(s), and set @insn->attr (except for groups).
+ * If necessary, first collects any preceding (prefix) bytes.
+ * Sets @insn->opcode.value = opcode1.  No effect if @insn->opcode.got
+ * is already 1.
+ */
+void insn_get_opcode(struct insn *insn)
+{
+	struct insn_field *opcode = &insn->opcode;
+	insn_byte_t op, pfx;
+	if (opcode->got)
+		return;
+	if (!insn->prefixes.got)
+		insn_get_prefixes(insn);
+
+	/* Get first opcode */
+	op = get_next(insn_byte_t, insn);
+	opcode->bytes[0] = op;
+	opcode->nbytes = 1;
+
+	/* Check if there is VEX prefix or not */
+	if (insn_is_avx(insn)) {
+		insn_byte_t m, p;
+		m = insn_vex_m_bits(insn);
+		p = insn_vex_p_bits(insn);
+		insn->attr = inat_get_avx_attribute(op, m, p);
+		if (!inat_accept_vex(insn->attr))
+			insn->attr = 0;	/* This instruction is bad */
+		goto end;	/* VEX has only 1 byte for opcode */
+	}
+
+	insn->attr = inat_get_opcode_attribute(op);
+	while (inat_is_escape(insn->attr)) {
+		/* Get escaped opcode */
+		op = get_next(insn_byte_t, insn);
+		opcode->bytes[opcode->nbytes++] = op;
+		pfx = insn_last_prefix(insn);
+		insn->attr = inat_get_escape_attribute(op, pfx, insn->attr);
+	}
+	if (inat_must_vex(insn->attr))
+		insn->attr = 0;	/* This instruction is bad */
+end:
+	opcode->got = 1;
+}
+
+/**
+ * insn_get_modrm - collect ModRM byte, if any
+ * @insn:	&struct insn containing instruction
+ *
+ * Populates @insn->modrm and updates @insn->next_byte to point past the
+ * ModRM byte, if any.  If necessary, first collects the preceding bytes
+ * (prefixes and opcode(s)).  No effect if @insn->modrm.got is already 1.
+ */
+void insn_get_modrm(struct insn *insn)
+{
+	struct insn_field *modrm = &insn->modrm;
+	insn_byte_t pfx, mod;
+	if (modrm->got)
+		return;
+	if (!insn->opcode.got)
+		insn_get_opcode(insn);
+
+	if (inat_has_modrm(insn->attr)) {
+		mod = get_next(insn_byte_t, insn);
+		modrm->value = mod;
+		modrm->nbytes = 1;
+		if (inat_is_group(insn->attr)) {
+			pfx = insn_last_prefix(insn);
+			insn->attr = inat_get_group_attribute(mod, pfx,
+							      insn->attr);
+		}
+	}
+
+	if (insn->x86_64 && inat_is_force64(insn->attr))
+		insn->opnd_bytes = 8;
+	modrm->got = 1;
+}
+
+
+/**
+ * insn_rip_relative() - Does instruction use RIP-relative addressing mode?
+ * @insn:	&struct insn containing instruction
+ *
+ * If necessary, first collects the instruction up to and including the
+ * ModRM byte.  No effect if @insn->x86_64 is 0.
+ */
+int insn_rip_relative(struct insn *insn)
+{
+	struct insn_field *modrm = &insn->modrm;
+
+	if (!insn->x86_64)
+		return 0;
+	if (!modrm->got)
+		insn_get_modrm(insn);
+	/*
+	 * For rip-relative instructions, the mod field (top 2 bits)
+	 * is zero and the r/m field (bottom 3 bits) is 0x5.
+	 */
+	return (modrm->nbytes && (modrm->value & 0xc7) == 0x5);
+}
+
+/**
+ * insn_get_sib() - Get the SIB byte of instruction
+ * @insn:	&struct insn containing instruction
+ *
+ * If necessary, first collects the instruction up to and including the
+ * ModRM byte.
+ */
+void insn_get_sib(struct insn *insn)
+{
+	insn_byte_t modrm;
+
+	if (insn->sib.got)
+		return;
+	if (!insn->modrm.got)
+		insn_get_modrm(insn);
+	if (insn->modrm.nbytes) {
+		modrm = (insn_byte_t)insn->modrm.value;
+		if (insn->addr_bytes != 2 &&
+		    X86_MODRM_MOD(modrm) != 3 && X86_MODRM_RM(modrm) == 4) {
+			insn->sib.value = get_next(insn_byte_t, insn);
+			insn->sib.nbytes = 1;
+		}
+	}
+	insn->sib.got = 1;
+}
+
+
+/**
+ * insn_get_displacement() - Get the displacement of instruction
+ * @insn:	&struct insn containing instruction
+ *
+ * If necessary, first collects the instruction up to and including the
+ * SIB byte.
+ * Displacement value is sign-expanded.
+ */
+void insn_get_displacement(struct insn *insn)
+{
+	insn_byte_t mod, rm, base;
+
+	if (insn->displacement.got)
+		return;
+	if (!insn->sib.got)
+		insn_get_sib(insn);
+	if (insn->modrm.nbytes) {
+		/*
+		 * Interpreting the modrm byte:
+		 * mod = 00 - no displacement fields (exceptions below)
+		 * mod = 01 - 1-byte displacement field
+		 * mod = 10 - displacement field is 4 bytes, or 2 bytes if
+		 * 	address size = 2 (0x67 prefix in 32-bit mode)
+		 * mod = 11 - no memory operand
+		 *
+		 * If address size = 2...
+		 * mod = 00, r/m = 110 - displacement field is 2 bytes
+		 *
+		 * If address size != 2...
+		 * mod != 11, r/m = 100 - SIB byte exists
+		 * mod = 00, SIB base = 101 - displacement field is 4 bytes
+		 * mod = 00, r/m = 101 - rip-relative addressing, displacement
+		 * 	field is 4 bytes
+		 */
+		mod = X86_MODRM_MOD(insn->modrm.value);
+		rm = X86_MODRM_RM(insn->modrm.value);
+		base = X86_SIB_BASE(insn->sib.value);
+		if (mod == 3)
+			goto out;
+		if (mod == 1) {
+			insn->displacement.value = get_next(char, insn);
+			insn->displacement.nbytes = 1;
+		} else if (insn->addr_bytes == 2) {
+			if ((mod == 0 && rm == 6) || mod == 2) {
+				insn->displacement.value =
+					 get_next(short, insn);
+				insn->displacement.nbytes = 2;
+			}
+		} else {
+			if ((mod == 0 && rm == 5) || mod == 2 ||
+			    (mod == 0 && base == 5)) {
+				insn->displacement.value = get_next(int, insn);
+				insn->displacement.nbytes = 4;
+			}
+		}
+	}
+out:
+	insn->displacement.got = 1;
+}
+
+/* Decode moffset16/32/64 */
+static void __get_moffset(struct insn *insn)
+{
+	switch (insn->addr_bytes) {
+	case 2:
+		insn->moffset1.value = get_next(short, insn);
+		insn->moffset1.nbytes = 2;
+		break;
+	case 4:
+		insn->moffset1.value = get_next(int, insn);
+		insn->moffset1.nbytes = 4;
+		break;
+	case 8:
+		insn->moffset1.value = get_next(int, insn);
+		insn->moffset1.nbytes = 4;
+		insn->moffset2.value = get_next(int, insn);
+		insn->moffset2.nbytes = 4;
+		break;
+	}
+	insn->moffset1.got = insn->moffset2.got = 1;
+}
+
+/* Decode imm v32(Iz) */
+static void __get_immv32(struct insn *insn)
+{
+	switch (insn->opnd_bytes) {
+	case 2:
+		insn->immediate.value = get_next(short, insn);
+		insn->immediate.nbytes = 2;
+		break;
+	case 4:
+	case 8:
+		insn->immediate.value = get_next(int, insn);
+		insn->immediate.nbytes = 4;
+		break;
+	}
+}
+
+/* Decode imm v64(Iv/Ov) */
+static void __get_immv(struct insn *insn)
+{
+	switch (insn->opnd_bytes) {
+	case 2:
+		insn->immediate1.value = get_next(short, insn);
+		insn->immediate1.nbytes = 2;
+		break;
+	case 4:
+		insn->immediate1.value = get_next(int, insn);
+		insn->immediate1.nbytes = 4;
+		break;
+	case 8:
+		insn->immediate1.value = get_next(int, insn);
+		insn->immediate1.nbytes = 4;
+		insn->immediate2.value = get_next(int, insn);
+		insn->immediate2.nbytes = 4;
+		break;
+	}
+	insn->immediate1.got = insn->immediate2.got = 1;
+}
+
+/* Decode ptr16:16/32(Ap) */
+static void __get_immptr(struct insn *insn)
+{
+	switch (insn->opnd_bytes) {
+	case 2:
+		insn->immediate1.value = get_next(short, insn);
+		insn->immediate1.nbytes = 2;
+		break;
+	case 4:
+		insn->immediate1.value = get_next(int, insn);
+		insn->immediate1.nbytes = 4;
+		break;
+	case 8:
+		/* ptr16:64 is not exist (no segment) */
+		return;
+	}
+	insn->immediate2.value = get_next(unsigned short, insn);
+	insn->immediate2.nbytes = 2;
+	insn->immediate1.got = insn->immediate2.got = 1;
+}
+
+/**
+ * insn_get_immediate() - Get the immediates of instruction
+ * @insn:	&struct insn containing instruction
+ *
+ * If necessary, first collects the instruction up to and including the
+ * displacement bytes.
+ * Basically, most of immediates are sign-expanded. Unsigned-value can be
+ * get by bit masking with ((1 << (nbytes * 8)) - 1)
+ */
+void insn_get_immediate(struct insn *insn)
+{
+	if (insn->immediate.got)
+		return;
+	if (!insn->displacement.got)
+		insn_get_displacement(insn);
+
+	if (inat_has_moffset(insn->attr)) {
+		__get_moffset(insn);
+		goto done;
+	}
+
+	if (!inat_has_immediate(insn->attr))
+		/* no immediates */
+		goto done;
+
+	switch (inat_immediate_size(insn->attr)) {
+	case INAT_IMM_BYTE:
+		insn->immediate.value = get_next(char, insn);
+		insn->immediate.nbytes = 1;
+		break;
+	case INAT_IMM_WORD:
+		insn->immediate.value = get_next(short, insn);
+		insn->immediate.nbytes = 2;
+		break;
+	case INAT_IMM_DWORD:
+		insn->immediate.value = get_next(int, insn);
+		insn->immediate.nbytes = 4;
+		break;
+	case INAT_IMM_QWORD:
+		insn->immediate1.value = get_next(int, insn);
+		insn->immediate1.nbytes = 4;
+		insn->immediate2.value = get_next(int, insn);
+		insn->immediate2.nbytes = 4;
+		break;
+	case INAT_IMM_PTR:
+		__get_immptr(insn);
+		break;
+	case INAT_IMM_VWORD32:
+		__get_immv32(insn);
+		break;
+	case INAT_IMM_VWORD:
+		__get_immv(insn);
+		break;
+	default:
+		break;
+	}
+	if (inat_has_second_immediate(insn->attr)) {
+		insn->immediate2.value = get_next(char, insn);
+		insn->immediate2.nbytes = 1;
+	}
+done:
+	insn->immediate.got = 1;
+}
+
+/**
+ * insn_get_length() - Get the length of instruction
+ * @insn:	&struct insn containing instruction
+ *
+ * If necessary, first collects the instruction up to and including the
+ * immediates bytes.
+ */
+void insn_get_length(struct insn *insn)
+{
+	if (insn->length)
+		return;
+	if (!insn->immediate.got)
+		insn_get_immediate(insn);
+	insn->length = (unsigned char)((unsigned long)insn->next_byte
+				     - (unsigned long)insn->kaddr);
+}

arch/x86/lib/x86-opcode-map.txt

@@ -0,0 +1,893 @@
+# x86 Opcode Maps
+#
+#<Opcode maps>
+# Table: table-name
+# Referrer: escaped-name
+# AVXcode: avx-code
+# opcode: mnemonic|GrpXXX [operand1[,operand2...]] [(extra1)[,(extra2)...] [| 2nd-mnemonic ...]
+# (or)
+# opcode: escape # escaped-name
+# EndTable
+#
+#<group maps>
+# GrpTable: GrpXXX
+# reg:  mnemonic [operand1[,operand2...]] [(extra1)[,(extra2)...] [| 2nd-mnemonic ...]
+# EndTable
+#
+# AVX Superscripts
+#  (VEX): this opcode can accept VEX prefix.
+#  (oVEX): this opcode requires VEX prefix.
+#  (o128): this opcode only supports 128bit VEX.
+#  (o256): this opcode only supports 256bit VEX.
+#
+
+Table: one byte opcode
+Referrer:
+AVXcode:
+# 0x00 - 0x0f
+00: ADD Eb,Gb
+01: ADD Ev,Gv
+02: ADD Gb,Eb
+03: ADD Gv,Ev
+04: ADD AL,Ib
+05: ADD rAX,Iz
+06: PUSH ES (i64)
+07: POP ES (i64)
+08: OR Eb,Gb
+09: OR Ev,Gv
+0a: OR Gb,Eb
+0b: OR Gv,Ev
+0c: OR AL,Ib
+0d: OR rAX,Iz
+0e: PUSH CS (i64)
+0f: escape # 2-byte escape
+# 0x10 - 0x1f
+10: ADC Eb,Gb
+11: ADC Ev,Gv
+12: ADC Gb,Eb
+13: ADC Gv,Ev
+14: ADC AL,Ib
+15: ADC rAX,Iz
+16: PUSH SS (i64)
+17: POP SS (i64)
+18: SBB Eb,Gb
+19: SBB Ev,Gv
+1a: SBB Gb,Eb
+1b: SBB Gv,Ev
+1c: SBB AL,Ib
+1d: SBB rAX,Iz
+1e: PUSH DS (i64)
+1f: POP DS (i64)
+# 0x20 - 0x2f
+20: AND Eb,Gb
+21: AND Ev,Gv
+22: AND Gb,Eb
+23: AND Gv,Ev
+24: AND AL,Ib
+25: AND rAx,Iz
+26: SEG=ES (Prefix)
+27: DAA (i64)
+28: SUB Eb,Gb
+29: SUB Ev,Gv
+2a: SUB Gb,Eb
+2b: SUB Gv,Ev
+2c: SUB AL,Ib
+2d: SUB rAX,Iz
+2e: SEG=CS (Prefix)
+2f: DAS (i64)
+# 0x30 - 0x3f
+30: XOR Eb,Gb
+31: XOR Ev,Gv
+32: XOR Gb,Eb
+33: XOR Gv,Ev
+34: XOR AL,Ib
+35: XOR rAX,Iz
+36: SEG=SS (Prefix)
+37: AAA (i64)
+38: CMP Eb,Gb
+39: CMP Ev,Gv
+3a: CMP Gb,Eb
+3b: CMP Gv,Ev
+3c: CMP AL,Ib
+3d: CMP rAX,Iz
+3e: SEG=DS (Prefix)
+3f: AAS (i64)
+# 0x40 - 0x4f
+40: INC eAX (i64) | REX (o64)
+41: INC eCX (i64) | REX.B (o64)
+42: INC eDX (i64) | REX.X (o64)
+43: INC eBX (i64) | REX.XB (o64)
+44: INC eSP (i64) | REX.R (o64)
+45: INC eBP (i64) | REX.RB (o64)
+46: INC eSI (i64) | REX.RX (o64)
+47: INC eDI (i64) | REX.RXB (o64)
+48: DEC eAX (i64) | REX.W (o64)
+49: DEC eCX (i64) | REX.WB (o64)
+4a: DEC eDX (i64) | REX.WX (o64)
+4b: DEC eBX (i64) | REX.WXB (o64)
+4c: DEC eSP (i64) | REX.WR (o64)
+4d: DEC eBP (i64) | REX.WRB (o64)
+4e: DEC eSI (i64) | REX.WRX (o64)
+4f: DEC eDI (i64) | REX.WRXB (o64)
+# 0x50 - 0x5f
+50: PUSH rAX/r8 (d64)
+51: PUSH rCX/r9 (d64)
+52: PUSH rDX/r10 (d64)
+53: PUSH rBX/r11 (d64)
+54: PUSH rSP/r12 (d64)
+55: PUSH rBP/r13 (d64)
+56: PUSH rSI/r14 (d64)
+57: PUSH rDI/r15 (d64)
+58: POP rAX/r8 (d64)
+59: POP rCX/r9 (d64)
+5a: POP rDX/r10 (d64)
+5b: POP rBX/r11 (d64)
+5c: POP rSP/r12 (d64)
+5d: POP rBP/r13 (d64)
+5e: POP rSI/r14 (d64)
+5f: POP rDI/r15 (d64)
+# 0x60 - 0x6f
+60: PUSHA/PUSHAD (i64)
+61: POPA/POPAD (i64)
+62: BOUND Gv,Ma (i64)
+63: ARPL Ew,Gw (i64) | MOVSXD Gv,Ev (o64)
+64: SEG=FS (Prefix)
+65: SEG=GS (Prefix)
+66: Operand-Size (Prefix)
+67: Address-Size (Prefix)
+68: PUSH Iz (d64)
+69: IMUL Gv,Ev,Iz
+6a: PUSH Ib (d64)
+6b: IMUL Gv,Ev,Ib
+6c: INS/INSB Yb,DX
+6d: INS/INSW/INSD Yz,DX
+6e: OUTS/OUTSB DX,Xb
+6f: OUTS/OUTSW/OUTSD DX,Xz
+# 0x70 - 0x7f
+70: JO Jb
+71: JNO Jb
+72: JB/JNAE/JC Jb
+73: JNB/JAE/JNC Jb
+74: JZ/JE Jb
+75: JNZ/JNE Jb
+76: JBE/JNA Jb
+77: JNBE/JA Jb
+78: JS Jb
+79: JNS Jb
+7a: JP/JPE Jb
+7b: JNP/JPO Jb
+7c: JL/JNGE Jb
+7d: JNL/JGE Jb
+7e: JLE/JNG Jb
+7f: JNLE/JG Jb
+# 0x80 - 0x8f
+80: Grp1 Eb,Ib (1A)
+81: Grp1 Ev,Iz (1A)
+82: Grp1 Eb,Ib (1A),(i64)
+83: Grp1 Ev,Ib (1A)
+84: TEST Eb,Gb
+85: TEST Ev,Gv
+86: XCHG Eb,Gb
+87: XCHG Ev,Gv
+88: MOV Eb,Gb
+89: MOV Ev,Gv
+8a: MOV Gb,Eb
+8b: MOV Gv,Ev
+8c: MOV Ev,Sw
+8d: LEA Gv,M
+8e: MOV Sw,Ew
+8f: Grp1A (1A) | POP Ev (d64)
+# 0x90 - 0x9f
+90: NOP | PAUSE (F3) | XCHG r8,rAX
+91: XCHG rCX/r9,rAX
+92: XCHG rDX/r10,rAX
+93: XCHG rBX/r11,rAX
+94: XCHG rSP/r12,rAX
+95: XCHG rBP/r13,rAX
+96: XCHG rSI/r14,rAX
+97: XCHG rDI/r15,rAX
+98: CBW/CWDE/CDQE
+99: CWD/CDQ/CQO
+9a: CALLF Ap (i64)
+9b: FWAIT/WAIT
+9c: PUSHF/D/Q Fv (d64)
+9d: POPF/D/Q Fv (d64)
+9e: SAHF
+9f: LAHF
+# 0xa0 - 0xaf
+a0: MOV AL,Ob
+a1: MOV rAX,Ov
+a2: MOV Ob,AL
+a3: MOV Ov,rAX
+a4: MOVS/B Xb,Yb
+a5: MOVS/W/D/Q Xv,Yv
+a6: CMPS/B Xb,Yb
+a7: CMPS/W/D Xv,Yv
+a8: TEST AL,Ib
+a9: TEST rAX,Iz
+aa: STOS/B Yb,AL
+ab: STOS/W/D/Q Yv,rAX
+ac: LODS/B AL,Xb
+ad: LODS/W/D/Q rAX,Xv
+ae: SCAS/B AL,Yb
+af: SCAS/W/D/Q rAX,Xv
+# 0xb0 - 0xbf
+b0: MOV AL/R8L,Ib
+b1: MOV CL/R9L,Ib
+b2: MOV DL/R10L,Ib
+b3: MOV BL/R11L,Ib
+b4: MOV AH/R12L,Ib
+b5: MOV CH/R13L,Ib
+b6: MOV DH/R14L,Ib
+b7: MOV BH/R15L,Ib
+b8: MOV rAX/r8,Iv
+b9: MOV rCX/r9,Iv
+ba: MOV rDX/r10,Iv
+bb: MOV rBX/r11,Iv
+bc: MOV rSP/r12,Iv
+bd: MOV rBP/r13,Iv
+be: MOV rSI/r14,Iv
+bf: MOV rDI/r15,Iv
+# 0xc0 - 0xcf
+c0: Grp2 Eb,Ib (1A)
+c1: Grp2 Ev,Ib (1A)
+c2: RETN Iw (f64)
+c3: RETN
+c4: LES Gz,Mp (i64) | 3bytes-VEX (Prefix)
+c5: LDS Gz,Mp (i64) | 2bytes-VEX (Prefix)
+c6: Grp11 Eb,Ib (1A)
+c7: Grp11 Ev,Iz (1A)
+c8: ENTER Iw,Ib
+c9: LEAVE (d64)
+ca: RETF Iw
+cb: RETF
+cc: INT3
+cd: INT Ib
+ce: INTO (i64)
+cf: IRET/D/Q
+# 0xd0 - 0xdf
+d0: Grp2 Eb,1 (1A)
+d1: Grp2 Ev,1 (1A)
+d2: Grp2 Eb,CL (1A)
+d3: Grp2 Ev,CL (1A)
+d4: AAM Ib (i64)
+d5: AAD Ib (i64)
+d6:
+d7: XLAT/XLATB
+d8: ESC
+d9: ESC
+da: ESC
+db: ESC
+dc: ESC
+dd: ESC
+de: ESC
+df: ESC
+# 0xe0 - 0xef
+e0: LOOPNE/LOOPNZ Jb (f64)
+e1: LOOPE/LOOPZ Jb (f64)
+e2: LOOP Jb (f64)
+e3: JrCXZ Jb (f64)
+e4: IN AL,Ib
+e5: IN eAX,Ib
+e6: OUT Ib,AL
+e7: OUT Ib,eAX
+e8: CALL Jz (f64)
+e9: JMP-near Jz (f64)
+ea: JMP-far Ap (i64)
+eb: JMP-short Jb (f64)
+ec: IN AL,DX
+ed: IN eAX,DX
+ee: OUT DX,AL
+ef: OUT DX,eAX
+# 0xf0 - 0xff
+f0: LOCK (Prefix)
+f1:
+f2: REPNE (Prefix)
+f3: REP/REPE (Prefix)
+f4: HLT
+f5: CMC
+f6: Grp3_1 Eb (1A)
+f7: Grp3_2 Ev (1A)
+f8: CLC
+f9: STC
+fa: CLI
+fb: STI
+fc: CLD
+fd: STD
+fe: Grp4 (1A)
+ff: Grp5 (1A)
+EndTable
+
+Table: 2-byte opcode (0x0f)
+Referrer: 2-byte escape
+AVXcode: 1
+# 0x0f 0x00-0x0f
+00: Grp6 (1A)
+01: Grp7 (1A)
+02: LAR Gv,Ew
+03: LSL Gv,Ew
+04:
+05: SYSCALL (o64)
+06: CLTS
+07: SYSRET (o64)
+08: INVD
+09: WBINVD
+0a:
+0b: UD2 (1B)
+0c:
+0d: NOP Ev | GrpP
+0e: FEMMS
+# 3DNow! uses the last imm byte as opcode extension.
+0f: 3DNow! Pq,Qq,Ib
+# 0x0f 0x10-0x1f
+10: movups Vps,Wps (VEX) | movss Vss,Wss (F3),(VEX),(o128) | movupd Vpd,Wpd (66),(VEX) | movsd Vsd,Wsd (F2),(VEX),(o128)
+11: movups Wps,Vps (VEX) | movss Wss,Vss (F3),(VEX),(o128) | movupd Wpd,Vpd (66),(VEX) | movsd Wsd,Vsd (F2),(VEX),(o128)
+12: movlps Vq,Mq (VEX),(o128) | movlpd Vq,Mq (66),(VEX),(o128) | movhlps Vq,Uq (VEX),(o128) | movddup Vq,Wq (F2),(VEX) | movsldup Vq,Wq (F3),(VEX)
+13: mpvlps Mq,Vq (VEX),(o128) | movlpd Mq,Vq (66),(VEX),(o128)
+14: unpcklps Vps,Wq (VEX) | unpcklpd Vpd,Wq (66),(VEX)
+15: unpckhps Vps,Wq (VEX) | unpckhpd Vpd,Wq (66),(VEX)
+16: movhps Vq,Mq (VEX),(o128) | movhpd Vq,Mq (66),(VEX),(o128) | movlsps Vq,Uq (VEX),(o128) | movshdup Vq,Wq (F3),(VEX)
+17: movhps Mq,Vq (VEX),(o128) | movhpd Mq,Vq (66),(VEX),(o128)
+18: Grp16 (1A)
+19:
+1a:
+1b:
+1c:
+1d:
+1e:
+1f: NOP Ev
+# 0x0f 0x20-0x2f
+20: MOV Rd,Cd
+21: MOV Rd,Dd
+22: MOV Cd,Rd
+23: MOV Dd,Rd
+24:
+25:
+26:
+27:
+28: movaps Vps,Wps (VEX) | movapd Vpd,Wpd (66),(VEX)
+29: movaps Wps,Vps (VEX) | movapd Wpd,Vpd (66),(VEX)
+2a: cvtpi2ps Vps,Qpi | cvtsi2ss Vss,Ed/q (F3),(VEX),(o128) | cvtpi2pd Vpd,Qpi (66) | cvtsi2sd Vsd,Ed/q (F2),(VEX),(o128)
+2b: movntps Mps,Vps (VEX) | movntpd Mpd,Vpd (66),(VEX)
+2c: cvttps2pi Ppi,Wps | cvttss2si  Gd/q,Wss (F3),(VEX),(o128) | cvttpd2pi Ppi,Wpd (66) | cvttsd2si Gd/q,Wsd (F2),(VEX),(o128)
+2d: cvtps2pi Ppi,Wps | cvtss2si Gd/q,Wss (F3),(VEX),(o128) | cvtpd2pi Qpi,Wpd (66) | cvtsd2si Gd/q,Wsd (F2),(VEX),(o128)
+2e: ucomiss Vss,Wss (VEX),(o128) | ucomisd  Vsd,Wsd (66),(VEX),(o128)
+2f: comiss Vss,Wss (VEX),(o128) | comisd  Vsd,Wsd (66),(VEX),(o128)
+# 0x0f 0x30-0x3f
+30: WRMSR
+31: RDTSC
+32: RDMSR
+33: RDPMC
+34: SYSENTER
+35: SYSEXIT
+36:
+37: GETSEC
+38: escape # 3-byte escape 1
+39:
+3a: escape # 3-byte escape 2
+3b:
+3c:
+3d:
+3e:
+3f:
+# 0x0f 0x40-0x4f
+40: CMOVO Gv,Ev
+41: CMOVNO Gv,Ev
+42: CMOVB/C/NAE Gv,Ev
+43: CMOVAE/NB/NC Gv,Ev
+44: CMOVE/Z Gv,Ev
+45: CMOVNE/NZ Gv,Ev
+46: CMOVBE/NA Gv,Ev
+47: CMOVA/NBE Gv,Ev
+48: CMOVS Gv,Ev
+49: CMOVNS Gv,Ev
+4a: CMOVP/PE Gv,Ev
+4b: CMOVNP/PO Gv,Ev
+4c: CMOVL/NGE Gv,Ev
+4d: CMOVNL/GE Gv,Ev
+4e: CMOVLE/NG Gv,Ev
+4f: CMOVNLE/G Gv,Ev
+# 0x0f 0x50-0x5f
+50: movmskps Gd/q,Ups (VEX) | movmskpd Gd/q,Upd (66),(VEX)
+51: sqrtps Vps,Wps (VEX) | sqrtss Vss,Wss (F3),(VEX),(o128) | sqrtpd Vpd,Wpd (66),(VEX) | sqrtsd Vsd,Wsd (F2),(VEX),(o128)
+52: rsqrtps Vps,Wps (VEX) | rsqrtss Vss,Wss (F3),(VEX),(o128)
+53: rcpps Vps,Wps (VEX) | rcpss Vss,Wss (F3),(VEX),(o128)
+54: andps Vps,Wps (VEX) | andpd Vpd,Wpd (66),(VEX)
+55: andnps Vps,Wps (VEX) | andnpd Vpd,Wpd (66),(VEX)
+56: orps Vps,Wps (VEX) | orpd Vpd,Wpd (66),(VEX)
+57: xorps Vps,Wps (VEX) | xorpd Vpd,Wpd (66),(VEX)
+58: addps Vps,Wps (VEX) | addss Vss,Wss (F3),(VEX),(o128) | addpd Vpd,Wpd (66),(VEX) | addsd Vsd,Wsd (F2),(VEX),(o128)
+59: mulps Vps,Wps (VEX) | mulss Vss,Wss (F3),(VEX),(o128) | mulpd Vpd,Wpd (66),(VEX) | mulsd Vsd,Wsd (F2),(VEX),(o128)
+5a: cvtps2pd Vpd,Wps (VEX) | cvtss2sd Vsd,Wss (F3),(VEX),(o128) | cvtpd2ps Vps,Wpd (66),(VEX) | cvtsd2ss Vsd,Wsd (F2),(VEX),(o128)
+5b: cvtdq2ps Vps,Wdq (VEX) | cvtps2dq Vdq,Wps (66),(VEX) | cvttps2dq Vdq,Wps (F3),(VEX)
+5c: subps Vps,Wps (VEX) | subss Vss,Wss (F3),(VEX),(o128) | subpd Vpd,Wpd (66),(VEX) | subsd Vsd,Wsd (F2),(VEX),(o128)
+5d: minps Vps,Wps (VEX) | minss Vss,Wss (F3),(VEX),(o128) | minpd Vpd,Wpd (66),(VEX) | minsd Vsd,Wsd (F2),(VEX),(o128)
+5e: divps Vps,Wps (VEX) | divss Vss,Wss (F3),(VEX),(o128) | divpd Vpd,Wpd (66),(VEX) | divsd Vsd,Wsd (F2),(VEX),(o128)
+5f: maxps Vps,Wps (VEX) | maxss Vss,Wss (F3),(VEX),(o128) | maxpd Vpd,Wpd (66),(VEX) | maxsd Vsd,Wsd (F2),(VEX),(o128)
+# 0x0f 0x60-0x6f
+60: punpcklbw Pq,Qd | punpcklbw Vdq,Wdq (66),(VEX),(o128)
+61: punpcklwd Pq,Qd | punpcklwd Vdq,Wdq (66),(VEX),(o128)
+62: punpckldq Pq,Qd | punpckldq Vdq,Wdq (66),(VEX),(o128)
+63: packsswb Pq,Qq | packsswb Vdq,Wdq (66),(VEX),(o128)
+64: pcmpgtb Pq,Qq | pcmpgtb Vdq,Wdq (66),(VEX),(o128)
+65: pcmpgtw Pq,Qq | pcmpgtw Vdq,Wdq (66),(VEX),(o128)
+66: pcmpgtd Pq,Qq | pcmpgtd Vdq,Wdq (66),(VEX),(o128)
+67: packuswb Pq,Qq | packuswb Vdq,Wdq (66),(VEX),(o128)
+68: punpckhbw Pq,Qd | punpckhbw Vdq,Wdq (66),(VEX),(o128)
+69: punpckhwd Pq,Qd | punpckhwd Vdq,Wdq (66),(VEX),(o128)
+6a: punpckhdq Pq,Qd | punpckhdq Vdq,Wdq (66),(VEX),(o128)
+6b: packssdw Pq,Qd | packssdw Vdq,Wdq (66),(VEX),(o128)
+6c: punpcklqdq Vdq,Wdq (66),(VEX),(o128)
+6d: punpckhqdq Vdq,Wdq (66),(VEX),(o128)
+6e: movd/q/ Pd,Ed/q | movd/q Vdq,Ed/q (66),(VEX),(o128)
+6f: movq Pq,Qq | movdqa Vdq,Wdq (66),(VEX) | movdqu Vdq,Wdq (F3),(VEX)
+# 0x0f 0x70-0x7f
+70: pshufw Pq,Qq,Ib | pshufd Vdq,Wdq,Ib (66),(VEX),(o128) | pshufhw Vdq,Wdq,Ib (F3),(VEX),(o128) | pshuflw VdqWdq,Ib (F2),(VEX),(o128)
+71: Grp12 (1A)
+72: Grp13 (1A)
+73: Grp14 (1A)
+74: pcmpeqb Pq,Qq | pcmpeqb Vdq,Wdq (66),(VEX),(o128)
+75: pcmpeqw Pq,Qq | pcmpeqw Vdq,Wdq (66),(VEX),(o128)
+76: pcmpeqd Pq,Qq | pcmpeqd Vdq,Wdq (66),(VEX),(o128)
+77: emms/vzeroupper/vzeroall (VEX)
+78: VMREAD Ed/q,Gd/q
+79: VMWRITE Gd/q,Ed/q
+7a:
+7b:
+7c: haddps Vps,Wps (F2),(VEX) | haddpd Vpd,Wpd (66),(VEX)
+7d: hsubps Vps,Wps (F2),(VEX) | hsubpd Vpd,Wpd (66),(VEX)
+7e: movd/q Ed/q,Pd | movd/q Ed/q,Vdq (66),(VEX),(o128) | movq Vq,Wq (F3),(VEX),(o128)
+7f: movq Qq,Pq | movdqa Wdq,Vdq (66),(VEX) | movdqu Wdq,Vdq (F3),(VEX)
+# 0x0f 0x80-0x8f
+80: JO Jz (f64)
+81: JNO Jz (f64)
+82: JB/JNAE/JC Jz (f64)
+83: JNB/JAE/JNC Jz (f64)
+84: JZ/JE Jz (f64)
+85: JNZ/JNE Jz (f64)
+86: JBE/JNA Jz (f64)
+87: JNBE/JA Jz (f64)
+88: JS Jz (f64)
+89: JNS Jz (f64)
+8a: JP/JPE Jz (f64)
+8b: JNP/JPO Jz (f64)
+8c: JL/JNGE Jz (f64)
+8d: JNL/JGE Jz (f64)
+8e: JLE/JNG Jz (f64)
+8f: JNLE/JG Jz (f64)
+# 0x0f 0x90-0x9f
+90: SETO Eb
+91: SETNO Eb
+92: SETB/C/NAE Eb
+93: SETAE/NB/NC Eb
+94: SETE/Z Eb
+95: SETNE/NZ Eb
+96: SETBE/NA Eb
+97: SETA/NBE Eb
+98: SETS Eb
+99: SETNS Eb
+9a: SETP/PE Eb
+9b: SETNP/PO Eb
+9c: SETL/NGE Eb
+9d: SETNL/GE Eb
+9e: SETLE/NG Eb
+9f: SETNLE/G Eb
+# 0x0f 0xa0-0xaf
+a0: PUSH FS (d64)
+a1: POP FS (d64)
+a2: CPUID
+a3: BT Ev,Gv
+a4: SHLD Ev,Gv,Ib
+a5: SHLD Ev,Gv,CL
+a6: GrpPDLK
+a7: GrpRNG
+a8: PUSH GS (d64)
+a9: POP GS (d64)
+aa: RSM
+ab: BTS Ev,Gv
+ac: SHRD Ev,Gv,Ib
+ad: SHRD Ev,Gv,CL
+ae: Grp15 (1A),(1C)
+af: IMUL Gv,Ev
+# 0x0f 0xb0-0xbf
+b0: CMPXCHG Eb,Gb
+b1: CMPXCHG Ev,Gv
+b2: LSS Gv,Mp
+b3: BTR Ev,Gv
+b4: LFS Gv,Mp
+b5: LGS Gv,Mp
+b6: MOVZX Gv,Eb
+b7: MOVZX Gv,Ew
+b8: JMPE | POPCNT Gv,Ev (F3)
+b9: Grp10 (1A)
+ba: Grp8 Ev,Ib (1A)
+bb: BTC Ev,Gv
+bc: BSF Gv,Ev
+bd: BSR Gv,Ev
+be: MOVSX Gv,Eb
+bf: MOVSX Gv,Ew
+# 0x0f 0xc0-0xcf
+c0: XADD Eb,Gb
+c1: XADD Ev,Gv
+c2: cmpps Vps,Wps,Ib (VEX) | cmpss Vss,Wss,Ib (F3),(VEX),(o128) | cmppd Vpd,Wpd,Ib (66),(VEX) | cmpsd Vsd,Wsd,Ib (F2),(VEX)
+c3: movnti Md/q,Gd/q
+c4: pinsrw Pq,Rd/q/Mw,Ib | pinsrw Vdq,Rd/q/Mw,Ib (66),(VEX),(o128)
+c5: pextrw Gd,Nq,Ib | pextrw Gd,Udq,Ib (66),(VEX),(o128)
+c6: shufps Vps,Wps,Ib (VEX) | shufpd Vpd,Wpd,Ib (66),(VEX)
+c7: Grp9 (1A)
+c8: BSWAP RAX/EAX/R8/R8D
+c9: BSWAP RCX/ECX/R9/R9D
+ca: BSWAP RDX/EDX/R10/R10D
+cb: BSWAP RBX/EBX/R11/R11D
+cc: BSWAP RSP/ESP/R12/R12D
+cd: BSWAP RBP/EBP/R13/R13D
+ce: BSWAP RSI/ESI/R14/R14D
+cf: BSWAP RDI/EDI/R15/R15D
+# 0x0f 0xd0-0xdf
+d0: addsubps Vps,Wps (F2),(VEX) | addsubpd Vpd,Wpd (66),(VEX)
+d1: psrlw Pq,Qq | psrlw Vdq,Wdq (66),(VEX),(o128)
+d2: psrld Pq,Qq | psrld Vdq,Wdq (66),(VEX),(o128)
+d3: psrlq Pq,Qq | psrlq Vdq,Wdq (66),(VEX),(o128)
+d4: paddq Pq,Qq | paddq Vdq,Wdq (66),(VEX),(o128)
+d5: pmullw Pq,Qq | pmullw Vdq,Wdq (66),(VEX),(o128)
+d6: movq Wq,Vq (66),(VEX),(o128) | movq2dq Vdq,Nq (F3) | movdq2q Pq,Uq (F2)
+d7: pmovmskb Gd,Nq | pmovmskb Gd,Udq (66),(VEX),(o128)
+d8: psubusb Pq,Qq | psubusb Vdq,Wdq (66),(VEX),(o128)
+d9: psubusw Pq,Qq | psubusw Vdq,Wdq (66),(VEX),(o128)
+da: pminub Pq,Qq | pminub Vdq,Wdq (66),(VEX),(o128)
+db: pand Pq,Qq | pand Vdq,Wdq (66),(VEX),(o128)
+dc: paddusb Pq,Qq | paddusb Vdq,Wdq (66),(VEX),(o128)
+dd: paddusw Pq,Qq | paddusw Vdq,Wdq (66),(VEX),(o128)
+de: pmaxub Pq,Qq | pmaxub Vdq,Wdq (66),(VEX),(o128)
+df: pandn Pq,Qq | pandn Vdq,Wdq (66),(VEX),(o128)
+# 0x0f 0xe0-0xef
+e0: pavgb Pq,Qq | pavgb Vdq,Wdq (66),(VEX),(o128)
+e1: psraw Pq,Qq | psraw Vdq,Wdq (66),(VEX),(o128)
+e2: psrad Pq,Qq | psrad Vdq,Wdq (66),(VEX),(o128)
+e3: pavgw Pq,Qq | pavgw Vdq,Wdq (66),(VEX),(o128)
+e4: pmulhuw Pq,Qq | pmulhuw Vdq,Wdq (66),(VEX),(o128)
+e5: pmulhw Pq,Qq | pmulhw Vdq,Wdq (66),(VEX),(o128)
+e6: cvtpd2dq Vdq,Wpd (F2),(VEX) | cvttpd2dq Vdq,Wpd (66),(VEX) | cvtdq2pd Vpd,Wdq (F3),(VEX)
+e7: movntq Mq,Pq | movntdq Mdq,Vdq (66),(VEX)
+e8: psubsb Pq,Qq | psubsb Vdq,Wdq (66),(VEX),(o128)
+e9: psubsw Pq,Qq | psubsw Vdq,Wdq (66),(VEX),(o128)
+ea: pminsw Pq,Qq | pminsw Vdq,Wdq (66),(VEX),(o128)
+eb: por Pq,Qq | por Vdq,Wdq (66),(VEX),(o128)
+ec: paddsb Pq,Qq | paddsb Vdq,Wdq (66),(VEX),(o128)
+ed: paddsw Pq,Qq | paddsw Vdq,Wdq (66),(VEX),(o128)
+ee: pmaxsw Pq,Qq | pmaxsw Vdq,Wdq (66),(VEX),(o128)
+ef: pxor Pq,Qq | pxor Vdq,Wdq (66),(VEX),(o128)
+# 0x0f 0xf0-0xff
+f0: lddqu Vdq,Mdq (F2),(VEX)
+f1: psllw Pq,Qq | psllw Vdq,Wdq (66),(VEX),(o128)
+f2: pslld Pq,Qq | pslld Vdq,Wdq (66),(VEX),(o128)
+f3: psllq Pq,Qq | psllq Vdq,Wdq (66),(VEX),(o128)
+f4: pmuludq Pq,Qq | pmuludq Vdq,Wdq (66),(VEX),(o128)
+f5: pmaddwd Pq,Qq | pmaddwd Vdq,Wdq (66),(VEX),(o128)
+f6: psadbw Pq,Qq | psadbw Vdq,Wdq (66),(VEX),(o128)
+f7: maskmovq Pq,Nq | maskmovdqu Vdq,Udq (66),(VEX),(o128)
+f8: psubb Pq,Qq | psubb Vdq,Wdq (66),(VEX),(o128)
+f9: psubw Pq,Qq | psubw Vdq,Wdq (66),(VEX),(o128)
+fa: psubd Pq,Qq | psubd Vdq,Wdq (66),(VEX),(o128)
+fb: psubq Pq,Qq | psubq Vdq,Wdq (66),(VEX),(o128)
+fc: paddb Pq,Qq | paddb Vdq,Wdq (66),(VEX),(o128)
+fd: paddw Pq,Qq | paddw Vdq,Wdq (66),(VEX),(o128)
+fe: paddd Pq,Qq | paddd Vdq,Wdq (66),(VEX),(o128)
+ff:
+EndTable
+
+Table: 3-byte opcode 1 (0x0f 0x38)
+Referrer: 3-byte escape 1
+AVXcode: 2
+# 0x0f 0x38 0x00-0x0f
+00: pshufb Pq,Qq | pshufb Vdq,Wdq (66),(VEX),(o128)
+01: phaddw Pq,Qq | phaddw Vdq,Wdq (66),(VEX),(o128)
+02: phaddd Pq,Qq | phaddd Vdq,Wdq (66),(VEX),(o128)
+03: phaddsw Pq,Qq | phaddsw Vdq,Wdq (66),(VEX),(o128)
+04: pmaddubsw Pq,Qq | pmaddubsw Vdq,Wdq (66),(VEX),(o128)
+05: phsubw Pq,Qq | phsubw Vdq,Wdq (66),(VEX),(o128)
+06: phsubd Pq,Qq | phsubd Vdq,Wdq (66),(VEX),(o128)
+07: phsubsw Pq,Qq | phsubsw Vdq,Wdq (66),(VEX),(o128)
+08: psignb Pq,Qq | psignb Vdq,Wdq (66),(VEX),(o128)
+09: psignw Pq,Qq | psignw Vdq,Wdq (66),(VEX),(o128)
+0a: psignd Pq,Qq | psignd Vdq,Wdq (66),(VEX),(o128)
+0b: pmulhrsw Pq,Qq | pmulhrsw Vdq,Wdq (66),(VEX),(o128)
+0c: Vpermilps /r (66),(oVEX)
+0d: Vpermilpd /r (66),(oVEX)
+0e: vtestps /r (66),(oVEX)
+0f: vtestpd /r (66),(oVEX)
+# 0x0f 0x38 0x10-0x1f
+10: pblendvb Vdq,Wdq (66)
+11:
+12:
+13:
+14: blendvps Vdq,Wdq (66)
+15: blendvpd Vdq,Wdq (66)
+16:
+17: ptest Vdq,Wdq (66),(VEX)
+18: vbroadcastss /r (66),(oVEX)
+19: vbroadcastsd /r (66),(oVEX),(o256)
+1a: vbroadcastf128 /r (66),(oVEX),(o256)
+1b:
+1c: pabsb Pq,Qq | pabsb Vdq,Wdq (66),(VEX),(o128)
+1d: pabsw Pq,Qq | pabsw Vdq,Wdq (66),(VEX),(o128)
+1e: pabsd Pq,Qq | pabsd Vdq,Wdq (66),(VEX),(o128)
+1f:
+# 0x0f 0x38 0x20-0x2f
+20: pmovsxbw Vdq,Udq/Mq (66),(VEX),(o128)
+21: pmovsxbd Vdq,Udq/Md (66),(VEX),(o128)
+22: pmovsxbq Vdq,Udq/Mw (66),(VEX),(o128)
+23: pmovsxwd Vdq,Udq/Mq (66),(VEX),(o128)
+24: pmovsxwq Vdq,Udq/Md (66),(VEX),(o128)
+25: pmovsxdq Vdq,Udq/Mq (66),(VEX),(o128)
+26:
+27:
+28: pmuldq Vdq,Wdq (66),(VEX),(o128)
+29: pcmpeqq Vdq,Wdq (66),(VEX),(o128)
+2a: movntdqa Vdq,Mdq (66),(VEX),(o128)
+2b: packusdw Vdq,Wdq (66),(VEX),(o128)
+2c: vmaskmovps(ld) /r (66),(oVEX)
+2d: vmaskmovpd(ld) /r (66),(oVEX)
+2e: vmaskmovps(st) /r (66),(oVEX)
+2f: vmaskmovpd(st) /r (66),(oVEX)
+# 0x0f 0x38 0x30-0x3f
+30: pmovzxbw Vdq,Udq/Mq (66),(VEX),(o128)
+31: pmovzxbd Vdq,Udq/Md (66),(VEX),(o128)
+32: pmovzxbq Vdq,Udq/Mw (66),(VEX),(o128)
+33: pmovzxwd Vdq,Udq/Mq (66),(VEX),(o128)
+34: pmovzxwq Vdq,Udq/Md (66),(VEX),(o128)
+35: pmovzxdq Vdq,Udq/Mq (66),(VEX),(o128)
+36:
+37: pcmpgtq Vdq,Wdq (66),(VEX),(o128)
+38: pminsb Vdq,Wdq (66),(VEX),(o128)
+39: pminsd Vdq,Wdq (66),(VEX),(o128)
+3a: pminuw Vdq,Wdq (66),(VEX),(o128)
+3b: pminud Vdq,Wdq (66),(VEX),(o128)
+3c: pmaxsb Vdq,Wdq (66),(VEX),(o128)
+3d: pmaxsd Vdq,Wdq (66),(VEX),(o128)
+3e: pmaxuw Vdq,Wdq (66),(VEX),(o128)
+3f: pmaxud Vdq,Wdq (66),(VEX),(o128)
+# 0x0f 0x38 0x40-0x8f
+40: pmulld Vdq,Wdq (66),(VEX),(o128)
+41: phminposuw Vdq,Wdq (66),(VEX),(o128)
+80: INVEPT Gd/q,Mdq (66)
+81: INVPID Gd/q,Mdq (66)
+# 0x0f 0x38 0x90-0xbf (FMA)
+96: vfmaddsub132pd/ps /r (66),(VEX)
+97: vfmsubadd132pd/ps /r (66),(VEX)
+98: vfmadd132pd/ps /r (66),(VEX)
+99: vfmadd132sd/ss /r (66),(VEX),(o128)
+9a: vfmsub132pd/ps /r (66),(VEX)
+9b: vfmsub132sd/ss /r (66),(VEX),(o128)
+9c: vfnmadd132pd/ps /r (66),(VEX)
+9d: vfnmadd132sd/ss /r (66),(VEX),(o128)
+9e: vfnmsub132pd/ps /r (66),(VEX)
+9f: vfnmsub132sd/ss /r (66),(VEX),(o128)
+a6: vfmaddsub213pd/ps /r (66),(VEX)
+a7: vfmsubadd213pd/ps /r (66),(VEX)
+a8: vfmadd213pd/ps /r (66),(VEX)
+a9: vfmadd213sd/ss /r (66),(VEX),(o128)
+aa: vfmsub213pd/ps /r (66),(VEX)
+ab: vfmsub213sd/ss /r (66),(VEX),(o128)
+ac: vfnmadd213pd/ps /r (66),(VEX)
+ad: vfnmadd213sd/ss /r (66),(VEX),(o128)
+ae: vfnmsub213pd/ps /r (66),(VEX)
+af: vfnmsub213sd/ss /r (66),(VEX),(o128)
+b6: vfmaddsub231pd/ps /r (66),(VEX)
+b7: vfmsubadd231pd/ps /r (66),(VEX)
+b8: vfmadd231pd/ps /r (66),(VEX)
+b9: vfmadd231sd/ss /r (66),(VEX),(o128)
+ba: vfmsub231pd/ps /r (66),(VEX)
+bb: vfmsub231sd/ss /r (66),(VEX),(o128)
+bc: vfnmadd231pd/ps /r (66),(VEX)
+bd: vfnmadd231sd/ss /r (66),(VEX),(o128)
+be: vfnmsub231pd/ps /r (66),(VEX)
+bf: vfnmsub231sd/ss /r (66),(VEX),(o128)
+# 0x0f 0x38 0xc0-0xff
+db: aesimc Vdq,Wdq (66),(VEX),(o128)
+dc: aesenc Vdq,Wdq (66),(VEX),(o128)
+dd: aesenclast Vdq,Wdq (66),(VEX),(o128)
+de: aesdec Vdq,Wdq (66),(VEX),(o128)
+df: aesdeclast Vdq,Wdq (66),(VEX),(o128)
+f0: MOVBE Gv,Mv | CRC32 Gd,Eb (F2)
+f1: MOVBE Mv,Gv | CRC32 Gd,Ev (F2)
+EndTable
+
+Table: 3-byte opcode 2 (0x0f 0x3a)
+Referrer: 3-byte escape 2
+AVXcode: 3
+# 0x0f 0x3a 0x00-0xff
+04: vpermilps /r,Ib (66),(oVEX)
+05: vpermilpd /r,Ib (66),(oVEX)
+06: vperm2f128 /r,Ib (66),(oVEX),(o256)
+08: roundps Vdq,Wdq,Ib (66),(VEX)
+09: roundpd Vdq,Wdq,Ib (66),(VEX)
+0a: roundss Vss,Wss,Ib (66),(VEX),(o128)
+0b: roundsd Vsd,Wsd,Ib (66),(VEX),(o128)
+0c: blendps Vdq,Wdq,Ib (66),(VEX)
+0d: blendpd Vdq,Wdq,Ib (66),(VEX)
+0e: pblendw Vdq,Wdq,Ib (66),(VEX),(o128)
+0f: palignr Pq,Qq,Ib | palignr Vdq,Wdq,Ib (66),(VEX),(o128)
+14: pextrb Rd/Mb,Vdq,Ib (66),(VEX),(o128)
+15: pextrw Rd/Mw,Vdq,Ib (66),(VEX),(o128)
+16: pextrd/pextrq Ed/q,Vdq,Ib (66),(VEX),(o128)
+17: extractps Ed,Vdq,Ib (66),(VEX),(o128)
+18: vinsertf128 /r,Ib (66),(oVEX),(o256)
+19: vextractf128 /r,Ib (66),(oVEX),(o256)
+20: pinsrb Vdq,Rd/q/Mb,Ib (66),(VEX),(o128)
+21: insertps Vdq,Udq/Md,Ib (66),(VEX),(o128)
+22: pinsrd/pinsrq Vdq,Ed/q,Ib (66),(VEX),(o128)
+40: dpps Vdq,Wdq,Ib (66),(VEX)
+41: dppd Vdq,Wdq,Ib (66),(VEX),(o128)
+42: mpsadbw Vdq,Wdq,Ib (66),(VEX),(o128)
+44: pclmulq Vdq,Wdq,Ib (66),(VEX),(o128)
+4a: vblendvps /r,Ib (66),(oVEX)
+4b: vblendvpd /r,Ib (66),(oVEX)
+4c: vpblendvb /r,Ib (66),(oVEX),(o128)
+60: pcmpestrm Vdq,Wdq,Ib (66),(VEX),(o128)
+61: pcmpestri Vdq,Wdq,Ib (66),(VEX),(o128)
+62: pcmpistrm Vdq,Wdq,Ib (66),(VEX),(o128)
+63: pcmpistri Vdq,Wdq,Ib (66),(VEX),(o128)
+df: aeskeygenassist Vdq,Wdq,Ib (66),(VEX),(o128)
+EndTable
+
+GrpTable: Grp1
+0: ADD
+1: OR
+2: ADC
+3: SBB
+4: AND
+5: SUB
+6: XOR
+7: CMP
+EndTable
+
+GrpTable: Grp1A
+0: POP
+EndTable
+
+GrpTable: Grp2
+0: ROL
+1: ROR
+2: RCL
+3: RCR
+4: SHL/SAL
+5: SHR
+6:
+7: SAR
+EndTable
+
+GrpTable: Grp3_1
+0: TEST Eb,Ib
+1:
+2: NOT Eb
+3: NEG Eb
+4: MUL AL,Eb
+5: IMUL AL,Eb
+6: DIV AL,Eb
+7: IDIV AL,Eb
+EndTable
+
+GrpTable: Grp3_2
+0: TEST Ev,Iz
+1:
+2: NOT Ev
+3: NEG Ev
+4: MUL rAX,Ev
+5: IMUL rAX,Ev
+6: DIV rAX,Ev
+7: IDIV rAX,Ev
+EndTable
+
+GrpTable: Grp4
+0: INC Eb
+1: DEC Eb
+EndTable
+
+GrpTable: Grp5
+0: INC Ev
+1: DEC Ev
+2: CALLN Ev (f64)
+3: CALLF Ep
+4: JMPN Ev (f64)
+5: JMPF Ep
+6: PUSH Ev (d64)
+7:
+EndTable
+
+GrpTable: Grp6
+0: SLDT Rv/Mw
+1: STR Rv/Mw
+2: LLDT Ew
+3: LTR Ew
+4: VERR Ew
+5: VERW Ew
+EndTable
+
+GrpTable: Grp7
+0: SGDT Ms | VMCALL (001),(11B) | VMLAUNCH (010),(11B) | VMRESUME (011),(11B) | VMXOFF (100),(11B)
+1: SIDT Ms | MONITOR (000),(11B) | MWAIT (001)
+2: LGDT Ms | XGETBV (000),(11B) | XSETBV (001),(11B)
+3: LIDT Ms
+4: SMSW Mw/Rv
+5:
+6: LMSW Ew
+7: INVLPG Mb | SWAPGS (o64),(000),(11B) | RDTSCP (001),(11B)
+EndTable
+
+GrpTable: Grp8
+4: BT
+5: BTS
+6: BTR
+7: BTC
+EndTable
+
+GrpTable: Grp9
+1: CMPXCHG8B/16B Mq/Mdq
+6: VMPTRLD Mq | VMCLEAR Mq (66) | VMXON Mq (F3)
+7: VMPTRST Mq
+EndTable
+
+GrpTable: Grp10
+EndTable
+
+GrpTable: Grp11
+0: MOV
+EndTable
+
+GrpTable: Grp12
+2: psrlw Nq,Ib (11B) | psrlw Udq,Ib (66),(11B),(VEX),(o128)
+4: psraw Nq,Ib (11B) | psraw Udq,Ib (66),(11B),(VEX),(o128)
+6: psllw Nq,Ib (11B) | psllw Udq,Ib (66),(11B),(VEX),(o128)
+EndTable
+
+GrpTable: Grp13
+2: psrld Nq,Ib (11B) | psrld Udq,Ib (66),(11B),(VEX),(o128)
+4: psrad Nq,Ib (11B) | psrad Udq,Ib (66),(11B),(VEX),(o128)
+6: pslld Nq,Ib (11B) | pslld Udq,Ib (66),(11B),(VEX),(o128)
+EndTable
+
+GrpTable: Grp14
+2: psrlq Nq,Ib (11B) | psrlq Udq,Ib (66),(11B),(VEX),(o128)
+3: psrldq Udq,Ib (66),(11B),(VEX),(o128)
+6: psllq Nq,Ib (11B) | psllq Udq,Ib (66),(11B),(VEX),(o128)
+7: pslldq Udq,Ib (66),(11B),(VEX),(o128)
+EndTable
+
+GrpTable: Grp15
+0: fxsave
+1: fxstor
+2: ldmxcsr (VEX)
+3: stmxcsr (VEX)
+4: XSAVE
+5: XRSTOR | lfence (11B)
+6: mfence (11B)
+7: clflush | sfence (11B)
+EndTable
+
+GrpTable: Grp16
+0: prefetch NTA
+1: prefetch T0
+2: prefetch T1
+3: prefetch T2
+EndTable
+
+# AMD's Prefetch Group
+GrpTable: GrpP
+0: PREFETCH
+1: PREFETCHW
+EndTable
+
+GrpTable: GrpPDLK
+0: MONTMUL
+1: XSHA1
+2: XSHA2
+EndTable
+
+GrpTable: GrpRNG
+0: xstore-rng
+1: xcrypt-ecb
+2: xcrypt-cbc
+4: xcrypt-cfb
+5: xcrypt-ofb
+EndTable

arch/x86/mm/fault.c

@@ -38,7 +38,8 @@ enum x86_pf_error_code {
  * Returns 0 if mmiotrace is disabled, or if the fault is not
  * handled by mmiotrace:
  */
-static inline int kmmio_fault(struct pt_regs *regs, unsigned long addr)
+static inline int __kprobes
+kmmio_fault(struct pt_regs *regs, unsigned long addr)
 {
 	if (unlikely(is_kmmio_active()))
 		if (kmmio_handler(regs, addr) == 1)
@@ -46,7 +47,7 @@ static inline int kmmio_fault(struct pt_regs *regs, unsigned long addr)
 	return 0;
 }
 
-static inline int notify_page_fault(struct pt_regs *regs)
+static inline int __kprobes notify_page_fault(struct pt_regs *regs)
 {
 	int ret = 0;
 
@@ -240,7 +241,7 @@ void vmalloc_sync_all(void)
  *
  *   Handle a fault on the vmalloc or module mapping area
  */
-static noinline int vmalloc_fault(unsigned long address)
+static noinline __kprobes int vmalloc_fault(unsigned long address)
 {
 	unsigned long pgd_paddr;
 	pmd_t *pmd_k;
@@ -357,7 +358,7 @@ void vmalloc_sync_all(void)
  *
  * This assumes no large pages in there.
  */
-static noinline int vmalloc_fault(unsigned long address)
+static noinline __kprobes int vmalloc_fault(unsigned long address)
 {
 	pgd_t *pgd, *pgd_ref;
 	pud_t *pud, *pud_ref;
@@ -860,7 +861,7 @@ static int spurious_fault_check(unsigned long error_code, pte_t *pte)
  * There are no security implications to leaving a stale TLB when
  * increasing the permissions on a page.
  */
-static noinline int
+static noinline __kprobes int
 spurious_fault(unsigned long error_code, unsigned long address)
 {
 	pgd_t *pgd;

arch/x86/mm/kmmio.c

@@ -540,8 +540,14 @@ kmmio_die_notifier(struct notifier_block *nb, unsigned long val, void *args)
 	struct die_args *arg = args;
 
 	if (val == DIE_DEBUG && (arg->err & DR_STEP))
-		if (post_kmmio_handler(arg->err, arg->regs) == 1)
+		if (post_kmmio_handler(arg->err, arg->regs) == 1) {
+			/*
+			 * Reset the BS bit in dr6 (pointed by args->err) to
+			 * denote completion of processing
+			 */
+			(*(unsigned long *)ERR_PTR(arg->err)) &= ~DR_STEP;
 			return NOTIFY_STOP;
+		}
 
 	return NOTIFY_DONE;
 }

arch/x86/power/cpu.c

@@ -18,6 +18,7 @@
 #include <asm/mce.h>
 #include <asm/xcr.h>
 #include <asm/suspend.h>
+#include <asm/debugreg.h>
 
 #ifdef CONFIG_X86_32
 static struct saved_context saved_context;
@@ -142,31 +143,6 @@ static void fix_processor_context(void)
 #endif
 	load_TR_desc();				/* This does ltr */
 	load_LDT(&current->active_mm->context);	/* This does lldt */
-
-	/*
-	 * Now maybe reload the debug registers
-	 */
-	if (current->thread.debugreg7) {
-#ifdef CONFIG_X86_32
-		set_debugreg(current->thread.debugreg0, 0);
-		set_debugreg(current->thread.debugreg1, 1);
-		set_debugreg(current->thread.debugreg2, 2);
-		set_debugreg(current->thread.debugreg3, 3);
-		/* no 4 and 5 */
-		set_debugreg(current->thread.debugreg6, 6);
-		set_debugreg(current->thread.debugreg7, 7);
-#else
-		/* CONFIG_X86_64 */
-		loaddebug(&current->thread, 0);
-		loaddebug(&current->thread, 1);
-		loaddebug(&current->thread, 2);
-		loaddebug(&current->thread, 3);
-		/* no 4 and 5 */
-		loaddebug(&current->thread, 6);
-		loaddebug(&current->thread, 7);
-#endif
-	}
-
 }
 
 /**

arch/x86/tools/Makefile

@@ -0,0 +1,31 @@
+PHONY += posttest
+
+ifeq ($(KBUILD_VERBOSE),1)
+  posttest_verbose = -v
+else
+  posttest_verbose =
+endif
+
+ifeq ($(CONFIG_64BIT),y)
+  posttest_64bit = -y
+else
+  posttest_64bit = -n
+endif
+
+distill_awk = $(srctree)/arch/x86/tools/distill.awk
+chkobjdump = $(srctree)/arch/x86/tools/chkobjdump.awk
+
+quiet_cmd_posttest = TEST    $@
+      cmd_posttest = ($(OBJDUMP) -v | $(AWK) -f $(chkobjdump)) || $(OBJDUMP) -d -j .text $(objtree)/vmlinux | $(AWK) -f $(distill_awk) | $(obj)/test_get_len $(posttest_64bit) $(posttest_verbose)
+
+posttest: $(obj)/test_get_len vmlinux
+	$(call cmd,posttest)
+
+hostprogs-y	:= test_get_len
+
+# -I needed for generated C source and C source which in the kernel tree.
+HOSTCFLAGS_test_get_len.o := -Wall -I$(objtree)/arch/x86/lib/ -I$(srctree)/arch/x86/include/ -I$(srctree)/arch/x86/lib/ -I$(srctree)/include/
+
+# Dependencies are also needed.
+$(obj)/test_get_len.o: $(srctree)/arch/x86/lib/insn.c $(srctree)/arch/x86/lib/inat.c $(srctree)/arch/x86/include/asm/inat_types.h $(srctree)/arch/x86/include/asm/inat.h $(srctree)/arch/x86/include/asm/insn.h $(objtree)/arch/x86/lib/inat-tables.c
+

arch/x86/tools/chkobjdump.awk

@@ -0,0 +1,23 @@
+# GNU objdump version checker
+#
+# Usage:
+# objdump -v | awk -f chkobjdump.awk
+BEGIN {
+	# objdump version 2.19 or later is OK for the test.
+	od_ver = 2;
+	od_sver = 19;
+}
+
+/^GNU/ {
+	split($4, ver, ".");
+	if (ver[1] > od_ver ||
+	    (ver[1] == od_ver && ver[2] >= od_sver)) {
+		exit 1;
+	} else {
+		printf("Warning: objdump version %s is older than %d.%d\n",
+		       $4, od_ver, od_sver);
+		print("Warning: Skipping posttest.");
+		# Logic is inverted, because we just skip test without error.
+		exit 0;
+	}
+}

arch/x86/tools/distill.awk

@@ -0,0 +1,47 @@
+#!/bin/awk -f
+# Usage: objdump -d a.out | awk -f distill.awk | ./test_get_len
+# Distills the disassembly as follows:
+# - Removes all lines except the disassembled instructions.
+# - For instructions that exceed 1 line (7 bytes), crams all the hex bytes
+# into a single line.
+# - Remove bad(or prefix only) instructions
+
+BEGIN {
+	prev_addr = ""
+	prev_hex = ""
+	prev_mnemonic = ""
+	bad_expr = "(\\(bad\\)|^rex|^.byte|^rep(z|nz)$|^lock$|^es$|^cs$|^ss$|^ds$|^fs$|^gs$|^data(16|32)$|^addr(16|32|64))"
+	fwait_expr = "^9b "
+	fwait_str="9b\tfwait"
+}
+
+/^ *[0-9a-f]+ <[^>]*>:/ {
+	# Symbol entry
+	printf("%s%s\n", $2, $1)
+}
+
+/^ *[0-9a-f]+:/ {
+	if (split($0, field, "\t") < 3) {
+		# This is a continuation of the same insn.
+		prev_hex = prev_hex field[2]
+	} else {
+		# Skip bad instructions
+		if (match(prev_mnemonic, bad_expr))
+			prev_addr = ""
+		# Split fwait from other f* instructions
+		if (match(prev_hex, fwait_expr) && prev_mnemonic != "fwait") {
+			printf "%s\t%s\n", prev_addr, fwait_str
+			sub(fwait_expr, "", prev_hex)
+		}
+		if (prev_addr != "")
+			printf "%s\t%s\t%s\n", prev_addr, prev_hex, prev_mnemonic
+		prev_addr = field[1]
+		prev_hex = field[2]
+		prev_mnemonic = field[3]
+	}
+}
+
+END {
+	if (prev_addr != "")
+		printf "%s\t%s\t%s\n", prev_addr, prev_hex, prev_mnemonic
+}

arch/x86/tools/gen-insn-attr-x86.awk

@@ -0,0 +1,380 @@
+#!/bin/awk -f
+# gen-insn-attr-x86.awk: Instruction attribute table generator
+# Written by Masami Hiramatsu <mhiramat@redhat.com>
+#
+# Usage: awk -f gen-insn-attr-x86.awk x86-opcode-map.txt > inat-tables.c
+
+# Awk implementation sanity check
+function check_awk_implement() {
+	if (!match("abc", "[[:lower:]]+"))
+		return "Your awk doesn't support charactor-class."
+	if (sprintf("%x", 0) != "0")
+		return "Your awk has a printf-format problem."
+	return ""
+}
+
+# Clear working vars
+function clear_vars() {
+	delete table
+	delete lptable2
+	delete lptable1
+	delete lptable3
+	eid = -1 # escape id
+	gid = -1 # group id
+	aid = -1 # AVX id
+	tname = ""
+}
+
+BEGIN {
+	# Implementation error checking
+	awkchecked = check_awk_implement()
+	if (awkchecked != "") {
+		print "Error: " awkchecked > "/dev/stderr"
+		print "Please try to use gawk." > "/dev/stderr"
+		exit 1
+	}
+
+	# Setup generating tables
+	print "/* x86 opcode map generated from x86-opcode-map.txt */"
+	print "/* Do not change this code. */\n"
+	ggid = 1
+	geid = 1
+	gaid = 0
+	delete etable
+	delete gtable
+	delete atable
+
+	opnd_expr = "^[[:alpha:]/]"
+	ext_expr = "^\\("
+	sep_expr = "^\\|$"
+	group_expr = "^Grp[[:alnum:]]+"
+
+	imm_expr = "^[IJAO][[:lower:]]"
+	imm_flag["Ib"] = "INAT_MAKE_IMM(INAT_IMM_BYTE)"
+	imm_flag["Jb"] = "INAT_MAKE_IMM(INAT_IMM_BYTE)"
+	imm_flag["Iw"] = "INAT_MAKE_IMM(INAT_IMM_WORD)"
+	imm_flag["Id"] = "INAT_MAKE_IMM(INAT_IMM_DWORD)"
+	imm_flag["Iq"] = "INAT_MAKE_IMM(INAT_IMM_QWORD)"
+	imm_flag["Ap"] = "INAT_MAKE_IMM(INAT_IMM_PTR)"
+	imm_flag["Iz"] = "INAT_MAKE_IMM(INAT_IMM_VWORD32)"
+	imm_flag["Jz"] = "INAT_MAKE_IMM(INAT_IMM_VWORD32)"
+	imm_flag["Iv"] = "INAT_MAKE_IMM(INAT_IMM_VWORD)"
+	imm_flag["Ob"] = "INAT_MOFFSET"
+	imm_flag["Ov"] = "INAT_MOFFSET"
+
+	modrm_expr = "^([CDEGMNPQRSUVW/][[:lower:]]+|NTA|T[012])"
+	force64_expr = "\\([df]64\\)"
+	rex_expr = "^REX(\\.[XRWB]+)*"
+	fpu_expr = "^ESC" # TODO
+
+	lprefix1_expr = "\\(66\\)"
+	lprefix2_expr = "\\(F3\\)"
+	lprefix3_expr = "\\(F2\\)"
+	max_lprefix = 4
+
+	vexok_expr = "\\(VEX\\)"
+	vexonly_expr = "\\(oVEX\\)"
+
+	prefix_expr = "\\(Prefix\\)"
+	prefix_num["Operand-Size"] = "INAT_PFX_OPNDSZ"
+	prefix_num["REPNE"] = "INAT_PFX_REPNE"
+	prefix_num["REP/REPE"] = "INAT_PFX_REPE"
+	prefix_num["LOCK"] = "INAT_PFX_LOCK"
+	prefix_num["SEG=CS"] = "INAT_PFX_CS"
+	prefix_num["SEG=DS"] = "INAT_PFX_DS"
+	prefix_num["SEG=ES"] = "INAT_PFX_ES"
+	prefix_num["SEG=FS"] = "INAT_PFX_FS"
+	prefix_num["SEG=GS"] = "INAT_PFX_GS"
+	prefix_num["SEG=SS"] = "INAT_PFX_SS"
+	prefix_num["Address-Size"] = "INAT_PFX_ADDRSZ"
+	prefix_num["2bytes-VEX"] = "INAT_PFX_VEX2"
+	prefix_num["3bytes-VEX"] = "INAT_PFX_VEX3"
+
+	clear_vars()
+}
+
+function semantic_error(msg) {
+	print "Semantic error at " NR ": " msg > "/dev/stderr"
+	exit 1
+}
+
+function debug(msg) {
+	print "DEBUG: " msg
+}
+
+function array_size(arr,   i,c) {
+	c = 0
+	for (i in arr)
+		c++
+	return c
+}
+
+/^Table:/ {
+	print "/* " $0 " */"
+	if (tname != "")
+		semantic_error("Hit Table: before EndTable:.");
+}
+
+/^Referrer:/ {
+	if (NF != 1) {
+		# escape opcode table
+		ref = ""
+		for (i = 2; i <= NF; i++)
+			ref = ref $i
+		eid = escape[ref]
+		tname = sprintf("inat_escape_table_%d", eid)
+	}
+}
+
+/^AVXcode:/ {
+	if (NF != 1) {
+		# AVX/escape opcode table
+		aid = $2
+		if (gaid <= aid)
+			gaid = aid + 1
+		if (tname == "")	# AVX only opcode table
+			tname = sprintf("inat_avx_table_%d", $2)
+	}
+	if (aid == -1 && eid == -1)	# primary opcode table
+		tname = "inat_primary_table"
+}
+
+/^GrpTable:/ {
+	print "/* " $0 " */"
+	if (!($2 in group))
+		semantic_error("No group: " $2 )
+	gid = group[$2]
+	tname = "inat_group_table_" gid
+}
+
+function print_table(tbl,name,fmt,n)
+{
+	print "const insn_attr_t " name " = {"
+	for (i = 0; i < n; i++) {
+		id = sprintf(fmt, i)
+		if (tbl[id])
+			print "	[" id "] = " tbl[id] ","
+	}
+	print "};"
+}
+
+/^EndTable/ {
+	if (gid != -1) {
+		# print group tables
+		if (array_size(table) != 0) {
+			print_table(table, tname "[INAT_GROUP_TABLE_SIZE]",
+				    "0x%x", 8)
+			gtable[gid,0] = tname
+		}
+		if (array_size(lptable1) != 0) {
+			print_table(lptable1, tname "_1[INAT_GROUP_TABLE_SIZE]",
+				    "0x%x", 8)
+			gtable[gid,1] = tname "_1"
+		}
+		if (array_size(lptable2) != 0) {
+			print_table(lptable2, tname "_2[INAT_GROUP_TABLE_SIZE]",
+				    "0x%x", 8)
+			gtable[gid,2] = tname "_2"
+		}
+		if (array_size(lptable3) != 0) {
+			print_table(lptable3, tname "_3[INAT_GROUP_TABLE_SIZE]",
+				    "0x%x", 8)
+			gtable[gid,3] = tname "_3"
+		}
+	} else {
+		# print primary/escaped tables
+		if (array_size(table) != 0) {
+			print_table(table, tname "[INAT_OPCODE_TABLE_SIZE]",
+				    "0x%02x", 256)
+			etable[eid,0] = tname
+			if (aid >= 0)
+				atable[aid,0] = tname
+		}
+		if (array_size(lptable1) != 0) {
+			print_table(lptable1,tname "_1[INAT_OPCODE_TABLE_SIZE]",
+				    "0x%02x", 256)
+			etable[eid,1] = tname "_1"
+			if (aid >= 0)
+				atable[aid,1] = tname "_1"
+		}
+		if (array_size(lptable2) != 0) {
+			print_table(lptable2,tname "_2[INAT_OPCODE_TABLE_SIZE]",
+				    "0x%02x", 256)
+			etable[eid,2] = tname "_2"
+			if (aid >= 0)
+				atable[aid,2] = tname "_2"
+		}
+		if (array_size(lptable3) != 0) {
+			print_table(lptable3,tname "_3[INAT_OPCODE_TABLE_SIZE]",
+				    "0x%02x", 256)
+			etable[eid,3] = tname "_3"
+			if (aid >= 0)
+				atable[aid,3] = tname "_3"
+		}
+	}
+	print ""
+	clear_vars()
+}
+
+function add_flags(old,new) {
+	if (old && new)
+		return old " | " new
+	else if (old)
+		return old
+	else
+		return new
+}
+
+# convert operands to flags.
+function convert_operands(opnd,       i,imm,mod)
+{
+	imm = null
+	mod = null
+	for (i in opnd) {
+		i  = opnd[i]
+		if (match(i, imm_expr) == 1) {
+			if (!imm_flag[i])
+				semantic_error("Unknown imm opnd: " i)
+			if (imm) {
+				if (i != "Ib")
+					semantic_error("Second IMM error")
+				imm = add_flags(imm, "INAT_SCNDIMM")
+			} else
+				imm = imm_flag[i]
+		} else if (match(i, modrm_expr))
+			mod = "INAT_MODRM"
+	}
+	return add_flags(imm, mod)
+}
+
+/^[0-9a-f]+\:/ {
+	if (NR == 1)
+		next
+	# get index
+	idx = "0x" substr($1, 1, index($1,":") - 1)
+	if (idx in table)
+		semantic_error("Redefine " idx " in " tname)
+
+	# check if escaped opcode
+	if ("escape" == $2) {
+		if ($3 != "#")
+			semantic_error("No escaped name")
+		ref = ""
+		for (i = 4; i <= NF; i++)
+			ref = ref $i
+		if (ref in escape)
+			semantic_error("Redefine escape (" ref ")")
+		escape[ref] = geid
+		geid++
+		table[idx] = "INAT_MAKE_ESCAPE(" escape[ref] ")"
+		next
+	}
+
+	variant = null
+	# converts
+	i = 2
+	while (i <= NF) {
+		opcode = $(i++)
+		delete opnds
+		ext = null
+		flags = null
+		opnd = null
+		# parse one opcode
+		if (match($i, opnd_expr)) {
+			opnd = $i
+			split($(i++), opnds, ",")
+			flags = convert_operands(opnds)
+		}
+		if (match($i, ext_expr))
+			ext = $(i++)
+		if (match($i, sep_expr))
+			i++
+		else if (i < NF)
+			semantic_error($i " is not a separator")
+
+		# check if group opcode
+		if (match(opcode, group_expr)) {
+			if (!(opcode in group)) {
+				group[opcode] = ggid
+				ggid++
+			}
+			flags = add_flags(flags, "INAT_MAKE_GROUP(" group[opcode] ")")
+		}
+		# check force(or default) 64bit
+		if (match(ext, force64_expr))
+			flags = add_flags(flags, "INAT_FORCE64")
+
+		# check REX prefix
+		if (match(opcode, rex_expr))
+			flags = add_flags(flags, "INAT_MAKE_PREFIX(INAT_PFX_REX)")
+
+		# check coprocessor escape : TODO
+		if (match(opcode, fpu_expr))
+			flags = add_flags(flags, "INAT_MODRM")
+
+		# check VEX only code
+		if (match(ext, vexonly_expr))
+			flags = add_flags(flags, "INAT_VEXOK | INAT_VEXONLY")
+
+		# check VEX only code
+		if (match(ext, vexok_expr))
+			flags = add_flags(flags, "INAT_VEXOK")
+
+		# check prefixes
+		if (match(ext, prefix_expr)) {
+			if (!prefix_num[opcode])
+				semantic_error("Unknown prefix: " opcode)
+			flags = add_flags(flags, "INAT_MAKE_PREFIX(" prefix_num[opcode] ")")
+		}
+		if (length(flags) == 0)
+			continue
+		# check if last prefix
+		if (match(ext, lprefix1_expr)) {
+			lptable1[idx] = add_flags(lptable1[idx],flags)
+			variant = "INAT_VARIANT"
+		} else if (match(ext, lprefix2_expr)) {
+			lptable2[idx] = add_flags(lptable2[idx],flags)
+			variant = "INAT_VARIANT"
+		} else if (match(ext, lprefix3_expr)) {
+			lptable3[idx] = add_flags(lptable3[idx],flags)
+			variant = "INAT_VARIANT"
+		} else {
+			table[idx] = add_flags(table[idx],flags)
+		}
+	}
+	if (variant)
+		table[idx] = add_flags(table[idx],variant)
+}
+
+END {
+	if (awkchecked != "")
+		exit 1
+	# print escape opcode map's array
+	print "/* Escape opcode map array */"
+	print "const insn_attr_t const *inat_escape_tables[INAT_ESC_MAX + 1]" \
+	      "[INAT_LSTPFX_MAX + 1] = {"
+	for (i = 0; i < geid; i++)
+		for (j = 0; j < max_lprefix; j++)
+			if (etable[i,j])
+				print "	["i"]["j"] = "etable[i,j]","
+	print "};\n"
+	# print group opcode map's array
+	print "/* Group opcode map array */"
+	print "const insn_attr_t const *inat_group_tables[INAT_GRP_MAX + 1]"\
+	      "[INAT_LSTPFX_MAX + 1] = {"
+	for (i = 0; i < ggid; i++)
+		for (j = 0; j < max_lprefix; j++)
+			if (gtable[i,j])
+				print "	["i"]["j"] = "gtable[i,j]","
+	print "};\n"
+	# print AVX opcode map's array
+	print "/* AVX opcode map array */"
+	print "const insn_attr_t const *inat_avx_tables[X86_VEX_M_MAX + 1]"\
+	      "[INAT_LSTPFX_MAX + 1] = {"
+	for (i = 0; i < gaid; i++)
+		for (j = 0; j < max_lprefix; j++)
+			if (atable[i,j])
+				print "	["i"]["j"] = "atable[i,j]","
+	print "};"
+}
+

arch/x86/tools/test_get_len.c

@@ -0,0 +1,173 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ * Copyright (C) IBM Corporation, 2009
+ */
+
+#include <stdlib.h>
+#include <stdio.h>
+#include <string.h>
+#include <assert.h>
+#include <unistd.h>
+
+#define unlikely(cond) (cond)
+
+#include <asm/insn.h>
+#include <inat.c>
+#include <insn.c>
+
+/*
+ * Test of instruction analysis in general and insn_get_length() in
+ * particular.  See if insn_get_length() and the disassembler agree
+ * on the length of each instruction in an elf disassembly.
+ *
+ * Usage: objdump -d a.out | awk -f distill.awk | ./test_get_len
+ */
+
+const char *prog;
+static int verbose;
+static int x86_64;
+
+static void usage(void)
+{
+	fprintf(stderr, "Usage: objdump -d a.out | awk -f distill.awk |"
+		" %s [-y|-n] [-v] \n", prog);
+	fprintf(stderr, "\t-y	64bit mode\n");
+	fprintf(stderr, "\t-n	32bit mode\n");
+	fprintf(stderr, "\t-v	verbose mode\n");
+	exit(1);
+}
+
+static void malformed_line(const char *line, int line_nr)
+{
+	fprintf(stderr, "%s: malformed line %d:\n%s", prog, line_nr, line);
+	exit(3);
+}
+
+static void dump_field(FILE *fp, const char *name, const char *indent,
+		       struct insn_field *field)
+{
+	fprintf(fp, "%s.%s = {\n", indent, name);
+	fprintf(fp, "%s\t.value = %d, bytes[] = {%x, %x, %x, %x},\n",
+		indent, field->value, field->bytes[0], field->bytes[1],
+		field->bytes[2], field->bytes[3]);
+	fprintf(fp, "%s\t.got = %d, .nbytes = %d},\n", indent,
+		field->got, field->nbytes);
+}
+
+static void dump_insn(FILE *fp, struct insn *insn)
+{
+	fprintf(fp, "Instruction = { \n");
+	dump_field(fp, "prefixes", "\t",	&insn->prefixes);
+	dump_field(fp, "rex_prefix", "\t",	&insn->rex_prefix);
+	dump_field(fp, "vex_prefix", "\t",	&insn->vex_prefix);
+	dump_field(fp, "opcode", "\t",		&insn->opcode);
+	dump_field(fp, "modrm", "\t",		&insn->modrm);
+	dump_field(fp, "sib", "\t",		&insn->sib);
+	dump_field(fp, "displacement", "\t",	&insn->displacement);
+	dump_field(fp, "immediate1", "\t",	&insn->immediate1);
+	dump_field(fp, "immediate2", "\t",	&insn->immediate2);
+	fprintf(fp, "\t.attr = %x, .opnd_bytes = %d, .addr_bytes = %d,\n",
+		insn->attr, insn->opnd_bytes, insn->addr_bytes);
+	fprintf(fp, "\t.length = %d, .x86_64 = %d, .kaddr = %p}\n",
+		insn->length, insn->x86_64, insn->kaddr);
+}
+
+static void parse_args(int argc, char **argv)
+{
+	int c;
+	prog = argv[0];
+	while ((c = getopt(argc, argv, "ynv")) != -1) {
+		switch (c) {
+		case 'y':
+			x86_64 = 1;
+			break;
+		case 'n':
+			x86_64 = 0;
+			break;
+		case 'v':
+			verbose = 1;
+			break;
+		default:
+			usage();
+		}
+	}
+}
+
+#define BUFSIZE 256
+
+int main(int argc, char **argv)
+{
+	char line[BUFSIZE], sym[BUFSIZE] = "<unknown>";
+	unsigned char insn_buf[16];
+	struct insn insn;
+	int insns = 0, c;
+	int warnings = 0;
+
+	parse_args(argc, argv);
+
+	while (fgets(line, BUFSIZE, stdin)) {
+		char copy[BUFSIZE], *s, *tab1, *tab2;
+		int nb = 0;
+		unsigned int b;
+
+		if (line[0] == '<') {
+			/* Symbol line */
+			strcpy(sym, line);
+			continue;
+		}
+
+		insns++;
+		memset(insn_buf, 0, 16);
+		strcpy(copy, line);
+		tab1 = strchr(copy, '\t');
+		if (!tab1)
+			malformed_line(line, insns);
+		s = tab1 + 1;
+		s += strspn(s, " ");
+		tab2 = strchr(s, '\t');
+		if (!tab2)
+			malformed_line(line, insns);
+		*tab2 = '\0';	/* Characters beyond tab2 aren't examined */
+		while (s < tab2) {
+			if (sscanf(s, "%x", &b) == 1) {
+				insn_buf[nb++] = (unsigned char) b;
+				s += 3;
+			} else
+				break;
+		}
+		/* Decode an instruction */
+		insn_init(&insn, insn_buf, x86_64);
+		insn_get_length(&insn);
+		if (insn.length != nb) {
+			warnings++;
+			fprintf(stderr, "Warning: %s found difference at %s\n",
+				prog, sym);
+			fprintf(stderr, "Warning: %s", line);
+			fprintf(stderr, "Warning: objdump says %d bytes, but "
+				"insn_get_length() says %d\n", nb,
+				insn.length);
+			if (verbose)
+				dump_insn(stderr, &insn);
+		}
+	}
+	if (warnings)
+		fprintf(stderr, "Warning: decoded and checked %d"
+			" instructions with %d warnings\n", insns, warnings);
+	else
+		fprintf(stderr, "Succeed: decoded and checked %d"
+			" instructions\n", insns);
+	return 0;
+}

drivers/edac/edac_mce_amd.c

@@ -3,7 +3,6 @@
 
 static bool report_gart_errors;
 static void (*nb_bus_decoder)(int node_id, struct err_regs *regs);
-static void (*orig_mce_callback)(struct mce *m);
 
 void amd_report_gart_errors(bool v)
 {
@@ -363,8 +362,10 @@ static inline void amd_decode_err_code(unsigned int ec)
 		pr_warning("Huh? Unknown MCE error 0x%x\n", ec);
 }
 
-static void amd_decode_mce(struct mce *m)
+static int amd_decode_mce(struct notifier_block *nb, unsigned long val,
+			   void *data)
 {
+	struct mce *m = (struct mce *)data;
 	struct err_regs regs;
 	int node, ecc;
 
@@ -420,20 +421,22 @@ static void amd_decode_mce(struct mce *m)
 	}
 
 	amd_decode_err_code(m->status & 0xffff);
+
+	return NOTIFY_STOP;
 }
 
+static struct notifier_block amd_mce_dec_nb = {
+	.notifier_call	= amd_decode_mce,
+};
+
 static int __init mce_amd_init(void)
 {
 	/*
 	 * We can decode MCEs for Opteron and later CPUs:
 	 */
 	if ((boot_cpu_data.x86_vendor == X86_VENDOR_AMD) &&
-	    (boot_cpu_data.x86 >= 0xf)) {
-		/* safe the default decode mce callback */
-		orig_mce_callback = x86_mce_decode_callback;
-
-		x86_mce_decode_callback = amd_decode_mce;
-	}
+	    (boot_cpu_data.x86 >= 0xf))
+		atomic_notifier_chain_register(&x86_mce_decoder_chain, &amd_mce_dec_nb);
 
 	return 0;
 }
@@ -442,7 +445,7 @@ early_initcall(mce_amd_init);
 #ifdef MODULE
 static void __exit mce_amd_exit(void)
 {
-	x86_mce_decode_callback = orig_mce_callback;
+	atomic_notifier_chain_unregister(&x86_mce_decoder_chain, &amd_mce_dec_nb);
 }
 
 MODULE_DESCRIPTION("AMD MCE decoder");

include/linux/ftrace_event.h

@@ -117,12 +117,12 @@ struct ftrace_event_call {
 	struct dentry		*dir;
 	struct trace_event	*event;
 	int			enabled;
-	int			(*regfunc)(void *);
-	void			(*unregfunc)(void *);
+	int			(*regfunc)(struct ftrace_event_call *);
+	void			(*unregfunc)(struct ftrace_event_call *);
 	int			id;
-	int			(*raw_init)(void);
-	int			(*show_format)(struct ftrace_event_call *call,
-					       struct trace_seq *s);
+	int			(*raw_init)(struct ftrace_event_call *);
+	int			(*show_format)(struct ftrace_event_call *,
+					       struct trace_seq *);
 	int			(*define_fields)(struct ftrace_event_call *);
 	struct list_head	fields;
 	int			filter_active;
@@ -131,20 +131,20 @@ struct ftrace_event_call {
 	void			*data;
 
 	atomic_t		profile_count;
-	int			(*profile_enable)(void);
-	void			(*profile_disable)(void);
+	int			(*profile_enable)(struct ftrace_event_call *);
+	void			(*profile_disable)(struct ftrace_event_call *);
 };
 
 #define FTRACE_MAX_PROFILE_SIZE	2048
 
-extern char			*trace_profile_buf;
-extern char			*trace_profile_buf_nmi;
+extern char *perf_trace_buf;
+extern char *perf_trace_buf_nmi;
 
 #define MAX_FILTER_PRED		32
 #define MAX_FILTER_STR_VAL	256	/* Should handle KSYM_SYMBOL_LEN */
 
 extern void destroy_preds(struct ftrace_event_call *call);
-extern int filter_match_preds(struct ftrace_event_call *call, void *rec);
+extern int filter_match_preds(struct event_filter *filter, void *rec);
 extern int filter_current_check_discard(struct ring_buffer *buffer,
 					struct ftrace_event_call *call,
 					void *rec,
@@ -157,11 +157,12 @@ enum {
 	FILTER_PTR_STRING,
 };
 
-extern int trace_define_field(struct ftrace_event_call *call,
-			      const char *type, const char *name,
-			      int offset, int size, int is_signed,
-			      int filter_type);
 extern int trace_define_common_fields(struct ftrace_event_call *call);
+extern int trace_define_field(struct ftrace_event_call *call, const char *type,
+			      const char *name, int offset, int size,
+			      int is_signed, int filter_type);
+extern int trace_add_event_call(struct ftrace_event_call *call);
+extern void trace_remove_event_call(struct ftrace_event_call *call);
 
 #define is_signed_type(type)	(((type)(-1)) < 0)
 
@@ -186,4 +187,13 @@ do {									\
 		__trace_printk(ip, fmt, ##args);			\
 } while (0)
 
+#ifdef CONFIG_EVENT_PROFILE
+struct perf_event;
+extern int ftrace_profile_enable(int event_id);
+extern void ftrace_profile_disable(int event_id);
+extern int ftrace_profile_set_filter(struct perf_event *event, int event_id,
+				     char *filter_str);
+extern void ftrace_profile_free_filter(struct perf_event *event);
+#endif
+
 #endif /* _LINUX_FTRACE_EVENT_H */

include/linux/hw_breakpoint.h

@@ -0,0 +1,131 @@
+#ifndef _LINUX_HW_BREAKPOINT_H
+#define _LINUX_HW_BREAKPOINT_H
+
+enum {
+	HW_BREAKPOINT_LEN_1 = 1,
+	HW_BREAKPOINT_LEN_2 = 2,
+	HW_BREAKPOINT_LEN_4 = 4,
+	HW_BREAKPOINT_LEN_8 = 8,
+};
+
+enum {
+	HW_BREAKPOINT_R = 1,
+	HW_BREAKPOINT_W = 2,
+	HW_BREAKPOINT_X = 4,
+};
+
+#ifdef __KERNEL__
+
+#include <linux/perf_event.h>
+
+#ifdef CONFIG_HAVE_HW_BREAKPOINT
+
+/* As it's for in-kernel or ptrace use, we want it to be pinned */
+#define DEFINE_BREAKPOINT_ATTR(name)	\
+struct perf_event_attr name = {		\
+	.type = PERF_TYPE_BREAKPOINT,	\
+	.size = sizeof(name),		\
+	.pinned = 1,			\
+};
+
+static inline void hw_breakpoint_init(struct perf_event_attr *attr)
+{
+	attr->type = PERF_TYPE_BREAKPOINT;
+	attr->size = sizeof(*attr);
+	attr->pinned = 1;
+}
+
+static inline unsigned long hw_breakpoint_addr(struct perf_event *bp)
+{
+	return bp->attr.bp_addr;
+}
+
+static inline int hw_breakpoint_type(struct perf_event *bp)
+{
+	return bp->attr.bp_type;
+}
+
+static inline int hw_breakpoint_len(struct perf_event *bp)
+{
+	return bp->attr.bp_len;
+}
+
+extern struct perf_event *
+register_user_hw_breakpoint(struct perf_event_attr *attr,
+			    perf_callback_t triggered,
+			    struct task_struct *tsk);
+
+/* FIXME: only change from the attr, and don't unregister */
+extern struct perf_event *
+modify_user_hw_breakpoint(struct perf_event *bp,
+			  struct perf_event_attr *attr,
+			  perf_callback_t triggered,
+			  struct task_struct *tsk);
+
+/*
+ * Kernel breakpoints are not associated with any particular thread.
+ */
+extern struct perf_event *
+register_wide_hw_breakpoint_cpu(struct perf_event_attr *attr,
+				perf_callback_t triggered,
+				int cpu);
+
+extern struct perf_event **
+register_wide_hw_breakpoint(struct perf_event_attr *attr,
+			    perf_callback_t triggered);
+
+extern int register_perf_hw_breakpoint(struct perf_event *bp);
+extern int __register_perf_hw_breakpoint(struct perf_event *bp);
+extern void unregister_hw_breakpoint(struct perf_event *bp);
+extern void unregister_wide_hw_breakpoint(struct perf_event **cpu_events);
+
+extern int reserve_bp_slot(struct perf_event *bp);
+extern void release_bp_slot(struct perf_event *bp);
+
+extern void flush_ptrace_hw_breakpoint(struct task_struct *tsk);
+
+static inline struct arch_hw_breakpoint *counter_arch_bp(struct perf_event *bp)
+{
+	return &bp->hw.info;
+}
+
+#else /* !CONFIG_HAVE_HW_BREAKPOINT */
+
+static inline struct perf_event *
+register_user_hw_breakpoint(struct perf_event_attr *attr,
+			    perf_callback_t triggered,
+			    struct task_struct *tsk)	{ return NULL; }
+static inline struct perf_event *
+modify_user_hw_breakpoint(struct perf_event *bp,
+			  struct perf_event_attr *attr,
+			  perf_callback_t triggered,
+			  struct task_struct *tsk)	{ return NULL; }
+static inline struct perf_event *
+register_wide_hw_breakpoint_cpu(struct perf_event_attr *attr,
+				perf_callback_t triggered,
+				int cpu)		{ return NULL; }
+static inline struct perf_event **
+register_wide_hw_breakpoint(struct perf_event_attr *attr,
+			    perf_callback_t triggered)	{ return NULL; }
+static inline int
+register_perf_hw_breakpoint(struct perf_event *bp)	{ return -ENOSYS; }
+static inline int
+__register_perf_hw_breakpoint(struct perf_event *bp) 	{ return -ENOSYS; }
+static inline void unregister_hw_breakpoint(struct perf_event *bp)	{ }
+static inline void
+unregister_wide_hw_breakpoint(struct perf_event **cpu_events)		{ }
+static inline int
+reserve_bp_slot(struct perf_event *bp)			{return -ENOSYS; }
+static inline void release_bp_slot(struct perf_event *bp) 		{ }
+
+static inline void flush_ptrace_hw_breakpoint(struct task_struct *tsk)	{ }
+
+static inline struct arch_hw_breakpoint *counter_arch_bp(struct perf_event *bp)
+{
+	return NULL;
+}
+
+#endif /* CONFIG_HAVE_HW_BREAKPOINT */
+#endif /* __KERNEL__ */
+
+#endif /* _LINUX_HW_BREAKPOINT_H */

include/linux/kprobes.h

@@ -296,6 +296,8 @@ void recycle_rp_inst(struct kretprobe_instance *ri, struct hlist_head *head);
 int disable_kprobe(struct kprobe *kp);
 int enable_kprobe(struct kprobe *kp);
 
+void dump_kprobe(struct kprobe *kp);
+
 #else /* !CONFIG_KPROBES: */
 
 static inline int kprobes_built_in(void)

include/linux/perf_counter.h

@@ -106,6 +106,8 @@ enum perf_sw_ids {
 	PERF_COUNT_SW_CPU_MIGRATIONS		= 4,
 	PERF_COUNT_SW_PAGE_FAULTS_MIN		= 5,
 	PERF_COUNT_SW_PAGE_FAULTS_MAJ		= 6,
+	PERF_COUNT_SW_ALIGNMENT_FAULTS		= 7,
+	PERF_COUNT_SW_EMULATION_FAULTS		= 8,
 
 	PERF_COUNT_SW_MAX,			/* non-ABI */
 };
@@ -225,6 +227,7 @@ struct perf_counter_attr {
 #define PERF_COUNTER_IOC_RESET		_IO ('$', 3)
 #define PERF_COUNTER_IOC_PERIOD		_IOW('$', 4, u64)
 #define PERF_COUNTER_IOC_SET_OUTPUT	_IO ('$', 5)
+#define PERF_COUNTER_IOC_SET_FILTER	_IOW('$', 6, char *)
 
 enum perf_counter_ioc_flags {
 	PERF_IOC_FLAG_GROUP		= 1U << 0,

include/linux/perf_event.h

@@ -18,6 +18,10 @@
 #include <linux/ioctl.h>
 #include <asm/byteorder.h>
 
+#ifdef CONFIG_HAVE_HW_BREAKPOINT
+#include <asm/hw_breakpoint.h>
+#endif
+
 /*
  * User-space ABI bits:
  */
@@ -31,6 +35,7 @@ enum perf_type_id {
 	PERF_TYPE_TRACEPOINT			= 2,
 	PERF_TYPE_HW_CACHE			= 3,
 	PERF_TYPE_RAW				= 4,
+	PERF_TYPE_BREAKPOINT			= 5,
 
 	PERF_TYPE_MAX,				/* non-ABI */
 };
@@ -102,6 +107,8 @@ enum perf_sw_ids {
 	PERF_COUNT_SW_CPU_MIGRATIONS		= 4,
 	PERF_COUNT_SW_PAGE_FAULTS_MIN		= 5,
 	PERF_COUNT_SW_PAGE_FAULTS_MAJ		= 6,
+	PERF_COUNT_SW_ALIGNMENT_FAULTS		= 7,
+	PERF_COUNT_SW_EMULATION_FAULTS		= 8,
 
 	PERF_COUNT_SW_MAX,			/* non-ABI */
 };
@@ -207,6 +214,15 @@ struct perf_event_attr {
 		__u32		wakeup_events;	  /* wakeup every n events */
 		__u32		wakeup_watermark; /* bytes before wakeup   */
 	};
+
+	union {
+		struct { /* Hardware breakpoint info */
+			__u64		bp_addr;
+			__u32		bp_type;
+			__u32		bp_len;
+		};
+	};
+
 	__u32			__reserved_2;
 
 	__u64			__reserved_3;
@@ -219,8 +235,9 @@ struct perf_event_attr {
 #define PERF_EVENT_IOC_DISABLE		_IO ('$', 1)
 #define PERF_EVENT_IOC_REFRESH		_IO ('$', 2)
 #define PERF_EVENT_IOC_RESET		_IO ('$', 3)
-#define PERF_EVENT_IOC_PERIOD		_IOW('$', 4, u64)
+#define PERF_EVENT_IOC_PERIOD		_IOW('$', 4, __u64)
 #define PERF_EVENT_IOC_SET_OUTPUT	_IO ('$', 5)
+#define PERF_EVENT_IOC_SET_FILTER	_IOW('$', 6, char *)
 
 enum perf_event_ioc_flags {
 	PERF_IOC_FLAG_GROUP		= 1U << 0,
@@ -475,6 +492,11 @@ struct hw_perf_event {
 			s64		remaining;
 			struct hrtimer	hrtimer;
 		};
+#ifdef CONFIG_HAVE_HW_BREAKPOINT
+		union { /* breakpoint */
+			struct arch_hw_breakpoint	info;
+		};
+#endif
 	};
 	atomic64_t			prev_count;
 	u64				sample_period;
@@ -543,6 +565,10 @@ struct perf_pending_entry {
 	void (*func)(struct perf_pending_entry *);
 };
 
+typedef void (*perf_callback_t)(struct perf_event *, void *);
+
+struct perf_sample_data;
+
 /**
  * struct perf_event - performance event kernel representation:
  */
@@ -585,7 +611,7 @@ struct perf_event {
 	u64				tstamp_running;
 	u64				tstamp_stopped;
 
-	struct perf_event_attr	attr;
+	struct perf_event_attr		attr;
 	struct hw_perf_event		hw;
 
 	struct perf_event_context	*ctx;
@@ -633,7 +659,20 @@ struct perf_event {
 
 	struct pid_namespace		*ns;
 	u64				id;
+
+	void (*overflow_handler)(struct perf_event *event,
+			int nmi, struct perf_sample_data *data,
+			struct pt_regs *regs);
+
+#ifdef CONFIG_EVENT_PROFILE
+	struct event_filter		*filter;
 #endif
+
+	perf_callback_t			callback;
+
+	perf_callback_t			event_callback;
+
+#endif /* CONFIG_PERF_EVENTS */
 };
 
 /**
@@ -706,7 +745,6 @@ struct perf_output_handle {
 	int				nmi;
 	int				sample;
 	int				locked;
-	unsigned long			flags;
 };
 
 #ifdef CONFIG_PERF_EVENTS
@@ -738,6 +776,14 @@ extern int hw_perf_group_sched_in(struct perf_event *group_leader,
 	       struct perf_cpu_context *cpuctx,
 	       struct perf_event_context *ctx, int cpu);
 extern void perf_event_update_userpage(struct perf_event *event);
+extern int perf_event_release_kernel(struct perf_event *event);
+extern struct perf_event *
+perf_event_create_kernel_counter(struct perf_event_attr *attr,
+				int cpu,
+				pid_t pid,
+				perf_callback_t callback);
+extern u64 perf_event_read_value(struct perf_event *event,
+				 u64 *enabled, u64 *running);
 
 struct perf_sample_data {
 	u64				type;
@@ -814,6 +860,7 @@ extern int sysctl_perf_event_sample_rate;
 extern void perf_event_init(void);
 extern void perf_tp_event(int event_id, u64 addr, u64 count,
 				 void *record, int entry_size);
+extern void perf_bp_event(struct perf_event *event, void *data);
 
 #ifndef perf_misc_flags
 #define perf_misc_flags(regs)	(user_mode(regs) ? PERF_RECORD_MISC_USER : \
@@ -827,6 +874,8 @@ extern int perf_output_begin(struct perf_output_handle *handle,
 extern void perf_output_end(struct perf_output_handle *handle);
 extern void perf_output_copy(struct perf_output_handle *handle,
 			     const void *buf, unsigned int len);
+extern int perf_swevent_get_recursion_context(void);
+extern void perf_swevent_put_recursion_context(int rctx);
 #else
 static inline void
 perf_event_task_sched_in(struct task_struct *task, int cpu)		{ }
@@ -848,11 +897,15 @@ static inline int perf_event_task_enable(void)				{ return -EINVAL; }
 static inline void
 perf_sw_event(u32 event_id, u64 nr, int nmi,
 		     struct pt_regs *regs, u64 addr)			{ }
+static inline void
+perf_bp_event(struct perf_event *event, void *data)		{ }
 
 static inline void perf_event_mmap(struct vm_area_struct *vma)		{ }
 static inline void perf_event_comm(struct task_struct *tsk)		{ }
 static inline void perf_event_fork(struct task_struct *tsk)		{ }
 static inline void perf_event_init(void)				{ }
+static inline int  perf_swevent_get_recursion_context(void)  { return -1; }
+static inline void perf_swevent_put_recursion_context(int rctx)		{ }
 
 #endif
 

include/linux/syscalls.h

@@ -99,37 +99,16 @@ struct perf_event_attr;
 #define __SC_TEST6(t6, a6, ...)	__SC_TEST(t6); __SC_TEST5(__VA_ARGS__)
 
 #ifdef CONFIG_EVENT_PROFILE
-#define TRACE_SYS_ENTER_PROFILE(sname)					       \
-static int prof_sysenter_enable_##sname(void)				       \
-{									       \
-	return reg_prof_syscall_enter("sys"#sname);			       \
-}									       \
-									       \
-static void prof_sysenter_disable_##sname(void)				       \
-{									       \
-	unreg_prof_syscall_enter("sys"#sname);				       \
-}
-
-#define TRACE_SYS_EXIT_PROFILE(sname)					       \
-static int prof_sysexit_enable_##sname(void)				       \
-{									       \
-	return reg_prof_syscall_exit("sys"#sname);			       \
-}									       \
-									       \
-static void prof_sysexit_disable_##sname(void)				       \
-{                                                                              \
-	unreg_prof_syscall_exit("sys"#sname);				       \
-}
 
 #define TRACE_SYS_ENTER_PROFILE_INIT(sname)				       \
 	.profile_count = ATOMIC_INIT(-1),				       \
-	.profile_enable = prof_sysenter_enable_##sname,			       \
-	.profile_disable = prof_sysenter_disable_##sname,
+	.profile_enable = prof_sysenter_enable,				       \
+	.profile_disable = prof_sysenter_disable,
 
 #define TRACE_SYS_EXIT_PROFILE_INIT(sname)				       \
 	.profile_count = ATOMIC_INIT(-1),				       \
-	.profile_enable = prof_sysexit_enable_##sname,			       \
-	.profile_disable = prof_sysexit_disable_##sname,
+	.profile_enable = prof_sysexit_enable,				       \
+	.profile_disable = prof_sysexit_disable,
 #else
 #define TRACE_SYS_ENTER_PROFILE(sname)
 #define TRACE_SYS_ENTER_PROFILE_INIT(sname)
@@ -153,74 +132,46 @@ static void prof_sysexit_disable_##sname(void)				       \
 #define __SC_STR_TDECL6(t, a, ...)	#t, __SC_STR_TDECL5(__VA_ARGS__)
 
 #define SYSCALL_TRACE_ENTER_EVENT(sname)				\
+	static const struct syscall_metadata __syscall_meta_##sname;	\
 	static struct ftrace_event_call event_enter_##sname;		\
-	struct trace_event enter_syscall_print_##sname = {		\
+	static struct trace_event enter_syscall_print_##sname = {	\
 		.trace                  = print_syscall_enter,		\
 	};								\
-	static int init_enter_##sname(void)				\
-	{								\
-		int num, id;						\
-		num = syscall_name_to_nr("sys"#sname);			\
-		if (num < 0)						\
-			return -ENOSYS;					\
-		id = register_ftrace_event(&enter_syscall_print_##sname);\
-		if (!id)						\
-			return -ENODEV;					\
-		event_enter_##sname.id = id;				\
-		set_syscall_enter_id(num, id);				\
-		INIT_LIST_HEAD(&event_enter_##sname.fields);		\
-		return 0;						\
-	}								\
-	TRACE_SYS_ENTER_PROFILE(sname);					\
 	static struct ftrace_event_call __used				\
 	  __attribute__((__aligned__(4)))				\
 	  __attribute__((section("_ftrace_events")))			\
 	  event_enter_##sname = {					\
 		.name                   = "sys_enter"#sname,		\
 		.system                 = "syscalls",			\
-		.event                  = &event_syscall_enter,		\
-		.raw_init		= init_enter_##sname,		\
+		.event                  = &enter_syscall_print_##sname,	\
+		.raw_init		= init_syscall_trace,		\
 		.show_format		= syscall_enter_format,		\
 		.define_fields		= syscall_enter_define_fields,	\
 		.regfunc		= reg_event_syscall_enter,	\
 		.unregfunc		= unreg_event_syscall_enter,	\
-		.data			= "sys"#sname,			\
+		.data			= (void *)&__syscall_meta_##sname,\
 		TRACE_SYS_ENTER_PROFILE_INIT(sname)			\
 	}
 
 #define SYSCALL_TRACE_EXIT_EVENT(sname)					\
+	static const struct syscall_metadata __syscall_meta_##sname;	\
 	static struct ftrace_event_call event_exit_##sname;		\
-	struct trace_event exit_syscall_print_##sname = {		\
+	static struct trace_event exit_syscall_print_##sname = {	\
 		.trace                  = print_syscall_exit,		\
 	};								\
-	static int init_exit_##sname(void)				\
-	{								\
-		int num, id;						\
-		num = syscall_name_to_nr("sys"#sname);			\
-		if (num < 0)						\
-			return -ENOSYS;					\
-		id = register_ftrace_event(&exit_syscall_print_##sname);\
-		if (!id)						\
-			return -ENODEV;					\
-		event_exit_##sname.id = id;				\
-		set_syscall_exit_id(num, id);				\
-		INIT_LIST_HEAD(&event_exit_##sname.fields);		\
-		return 0;						\
-	}								\
-	TRACE_SYS_EXIT_PROFILE(sname);					\
 	static struct ftrace_event_call __used				\
 	  __attribute__((__aligned__(4)))				\
 	  __attribute__((section("_ftrace_events")))			\
 	  event_exit_##sname = {					\
 		.name                   = "sys_exit"#sname,		\
 		.system                 = "syscalls",			\
-		.event                  = &event_syscall_exit,		\
-		.raw_init		= init_exit_##sname,		\
+		.event                  = &exit_syscall_print_##sname,	\
+		.raw_init		= init_syscall_trace,		\
 		.show_format		= syscall_exit_format,		\
 		.define_fields		= syscall_exit_define_fields,	\
 		.regfunc		= reg_event_syscall_exit,	\
 		.unregfunc		= unreg_event_syscall_exit,	\
-		.data			= "sys"#sname,			\
+		.data			= (void *)&__syscall_meta_##sname,\
 		TRACE_SYS_EXIT_PROFILE_INIT(sname)			\
 	}
 

include/linux/tracepoint.h

@@ -280,6 +280,12 @@ static inline void tracepoint_synchronize_unregister(void)
  * TRACE_EVENT_FN to perform any (un)registration work.
  */
 
+#define DECLARE_EVENT_CLASS(name, proto, args, tstruct, assign, print)
+#define DEFINE_EVENT(template, name, proto, args)		\
+	DECLARE_TRACE(name, PARAMS(proto), PARAMS(args))
+#define DEFINE_EVENT_PRINT(template, name, proto, args, print)	\
+	DECLARE_TRACE(name, PARAMS(proto), PARAMS(args))
+
 #define TRACE_EVENT(name, proto, args, struct, assign, print)	\
 	DECLARE_TRACE(name, PARAMS(proto), PARAMS(args))
 #define TRACE_EVENT_FN(name, proto, args, struct,		\

include/trace/define_trace.h

@@ -31,6 +31,14 @@
 		assign, print, reg, unreg)			\
 	DEFINE_TRACE_FN(name, reg, unreg)
 
+#undef DEFINE_EVENT
+#define DEFINE_EVENT(template, name, proto, args) \
+	DEFINE_TRACE(name)
+
+#undef DEFINE_EVENT_PRINT
+#define DEFINE_EVENT_PRINT(template, name, proto, args, print)	\
+	DEFINE_TRACE(name)
+
 #undef DECLARE_TRACE
 #define DECLARE_TRACE(name, proto, args)	\
 	DEFINE_TRACE(name)
@@ -63,6 +71,9 @@
 
 #undef TRACE_EVENT
 #undef TRACE_EVENT_FN
+#undef DECLARE_EVENT_CLASS
+#undef DEFINE_EVENT
+#undef DEFINE_EVENT_PRINT
 #undef TRACE_HEADER_MULTI_READ
 
 /* Only undef what we defined in this file */

include/trace/events/bkl.h

@@ -13,7 +13,7 @@ TRACE_EVENT(lock_kernel,
 	TP_ARGS(func, file, line),
 
 	TP_STRUCT__entry(
-		__field(	int,		lock_depth		)
+		__field(	int,		depth			)
 		__field_ext(	const char *,	func, FILTER_PTR_STRING	)
 		__field_ext(	const char *,	file, FILTER_PTR_STRING	)
 		__field(	int,		line			)
@@ -21,13 +21,13 @@ TRACE_EVENT(lock_kernel,
 
 	TP_fast_assign(
 		/* We want to record the lock_depth after lock is acquired */
-		__entry->lock_depth = current->lock_depth + 1;
+		__entry->depth = current->lock_depth + 1;
 		__entry->func = func;
 		__entry->file = file;
 		__entry->line = line;
 	),
 
-	TP_printk("depth: %d, %s:%d %s()", __entry->lock_depth,
+	TP_printk("depth=%d file:line=%s:%d func=%s()", __entry->depth,
 		  __entry->file, __entry->line, __entry->func)
 );
 
@@ -38,20 +38,20 @@ TRACE_EVENT(unlock_kernel,
 	TP_ARGS(func, file, line),
 
 	TP_STRUCT__entry(
-		__field(int,		lock_depth)
-		__field(const char *,	func)
-		__field(const char *,	file)
-		__field(int,		line)
+		__field(int,		depth		)
+		__field(const char *,	func		)
+		__field(const char *,	file		)
+		__field(int,		line		)
 	),
 
 	TP_fast_assign(
-		__entry->lock_depth = current->lock_depth;
+		__entry->depth = current->lock_depth;
 		__entry->func = func;
 		__entry->file = file;
 		__entry->line = line;
 	),
 
-	TP_printk("depth: %d, %s:%d %s()", __entry->lock_depth,
+	TP_printk("depth=%d file:line=%s:%d func=%s()", __entry->depth,
 		  __entry->file, __entry->line, __entry->func)
 );
 

include/trace/events/block.h

@@ -8,7 +8,7 @@
 #include <linux/blkdev.h>
 #include <linux/tracepoint.h>
 
-TRACE_EVENT(block_rq_abort,
+DECLARE_EVENT_CLASS(block_rq_with_error,
 
 	TP_PROTO(struct request_queue *q, struct request *rq),
 
@@ -40,41 +40,28 @@ TRACE_EVENT(block_rq_abort,
 		  __entry->nr_sector, __entry->errors)
 );
 
-TRACE_EVENT(block_rq_insert,
+DEFINE_EVENT(block_rq_with_error, block_rq_abort,
 
 	TP_PROTO(struct request_queue *q, struct request *rq),
 
-	TP_ARGS(q, rq),
+	TP_ARGS(q, rq)
+);
 
-	TP_STRUCT__entry(
-		__field(  dev_t,	dev			)
-		__field(  sector_t,	sector			)
-		__field(  unsigned int,	nr_sector		)
-		__field(  unsigned int,	bytes			)
-		__array(  char,		rwbs,	6		)
-		__array(  char,         comm,   TASK_COMM_LEN   )
-		__dynamic_array( char,	cmd,	blk_cmd_buf_len(rq)	)
-	),
+DEFINE_EVENT(block_rq_with_error, block_rq_requeue,
 
-	TP_fast_assign(
-		__entry->dev	   = rq->rq_disk ? disk_devt(rq->rq_disk) : 0;
-		__entry->sector    = blk_pc_request(rq) ? 0 : blk_rq_pos(rq);
-		__entry->nr_sector = blk_pc_request(rq) ? 0 : blk_rq_sectors(rq);
-		__entry->bytes     = blk_pc_request(rq) ? blk_rq_bytes(rq) : 0;
+	TP_PROTO(struct request_queue *q, struct request *rq),
 
-		blk_fill_rwbs_rq(__entry->rwbs, rq);
-		blk_dump_cmd(__get_str(cmd), rq);
-		memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
-	),
+	TP_ARGS(q, rq)
+);
 
-	TP_printk("%d,%d %s %u (%s) %llu + %u [%s]",
-		  MAJOR(__entry->dev), MINOR(__entry->dev),
-		  __entry->rwbs, __entry->bytes, __get_str(cmd),
-		  (unsigned long long)__entry->sector,
-		  __entry->nr_sector, __entry->comm)
+DEFINE_EVENT(block_rq_with_error, block_rq_complete,
+
+	TP_PROTO(struct request_queue *q, struct request *rq),
+
+	TP_ARGS(q, rq)
 );
 
-TRACE_EVENT(block_rq_issue,
+DECLARE_EVENT_CLASS(block_rq,
 
 	TP_PROTO(struct request_queue *q, struct request *rq),
 
@@ -86,7 +73,7 @@ TRACE_EVENT(block_rq_issue,
 		__field(  unsigned int,	nr_sector		)
 		__field(  unsigned int,	bytes			)
 		__array(  char,		rwbs,	6		)
-		__array(  char,		comm,   TASK_COMM_LEN   )
+		__array(  char,         comm,   TASK_COMM_LEN   )
 		__dynamic_array( char,	cmd,	blk_cmd_buf_len(rq)	)
 	),
 
@@ -108,68 +95,18 @@ TRACE_EVENT(block_rq_issue,
 		  __entry->nr_sector, __entry->comm)
 );
 
-TRACE_EVENT(block_rq_requeue,
+DEFINE_EVENT(block_rq, block_rq_insert,
 
 	TP_PROTO(struct request_queue *q, struct request *rq),
 
-	TP_ARGS(q, rq),
-
-	TP_STRUCT__entry(
-		__field(  dev_t,	dev			)
-		__field(  sector_t,	sector			)
-		__field(  unsigned int,	nr_sector		)
-		__field(  int,		errors			)
-		__array(  char,		rwbs,	6		)
-		__dynamic_array( char,	cmd,	blk_cmd_buf_len(rq)	)
-	),
-
-	TP_fast_assign(
-		__entry->dev	   = rq->rq_disk ? disk_devt(rq->rq_disk) : 0;
-		__entry->sector    = blk_pc_request(rq) ? 0 : blk_rq_pos(rq);
-		__entry->nr_sector = blk_pc_request(rq) ? 0 : blk_rq_sectors(rq);
-		__entry->errors	   = rq->errors;
-
-		blk_fill_rwbs_rq(__entry->rwbs, rq);
-		blk_dump_cmd(__get_str(cmd), rq);
-	),
-
-	TP_printk("%d,%d %s (%s) %llu + %u [%d]",
-		  MAJOR(__entry->dev), MINOR(__entry->dev),
-		  __entry->rwbs, __get_str(cmd),
-		  (unsigned long long)__entry->sector,
-		  __entry->nr_sector, __entry->errors)
+	TP_ARGS(q, rq)
 );
 
-TRACE_EVENT(block_rq_complete,
+DEFINE_EVENT(block_rq, block_rq_issue,
 
 	TP_PROTO(struct request_queue *q, struct request *rq),
 
-	TP_ARGS(q, rq),
-
-	TP_STRUCT__entry(
-		__field(  dev_t,	dev			)
-		__field(  sector_t,	sector			)
-		__field(  unsigned int,	nr_sector		)
-		__field(  int,		errors			)
-		__array(  char,		rwbs,	6		)
-		__dynamic_array( char,	cmd,	blk_cmd_buf_len(rq)	)
-	),
-
-	TP_fast_assign(
-		__entry->dev	   = rq->rq_disk ? disk_devt(rq->rq_disk) : 0;
-		__entry->sector    = blk_pc_request(rq) ? 0 : blk_rq_pos(rq);
-		__entry->nr_sector = blk_pc_request(rq) ? 0 : blk_rq_sectors(rq);
-		__entry->errors    = rq->errors;
-
-		blk_fill_rwbs_rq(__entry->rwbs, rq);
-		blk_dump_cmd(__get_str(cmd), rq);
-	),
-
-	TP_printk("%d,%d %s (%s) %llu + %u [%d]",
-		  MAJOR(__entry->dev), MINOR(__entry->dev),
-		  __entry->rwbs, __get_str(cmd),
-		  (unsigned long long)__entry->sector,
-		  __entry->nr_sector, __entry->errors)
+	TP_ARGS(q, rq)
 );
 
 TRACE_EVENT(block_bio_bounce,
@@ -228,7 +165,7 @@ TRACE_EVENT(block_bio_complete,
 		  __entry->nr_sector, __entry->error)
 );
 
-TRACE_EVENT(block_bio_backmerge,
+DECLARE_EVENT_CLASS(block_bio,
 
 	TP_PROTO(struct request_queue *q, struct bio *bio),
 
@@ -256,63 +193,28 @@ TRACE_EVENT(block_bio_backmerge,
 		  __entry->nr_sector, __entry->comm)
 );
 
-TRACE_EVENT(block_bio_frontmerge,
+DEFINE_EVENT(block_bio, block_bio_backmerge,
 
 	TP_PROTO(struct request_queue *q, struct bio *bio),
 
-	TP_ARGS(q, bio),
-
-	TP_STRUCT__entry(
-		__field( dev_t,		dev			)
-		__field( sector_t,	sector			)
-		__field( unsigned,	nr_sector		)
-		__array( char,		rwbs,	6		)
-		__array( char,		comm,	TASK_COMM_LEN	)
-	),
-
-	TP_fast_assign(
-		__entry->dev		= bio->bi_bdev->bd_dev;
-		__entry->sector		= bio->bi_sector;
-		__entry->nr_sector	= bio->bi_size >> 9;
-		blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_size);
-		memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
-	),
-
-	TP_printk("%d,%d %s %llu + %u [%s]",
-		  MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rwbs,
-		  (unsigned long long)__entry->sector,
-		  __entry->nr_sector, __entry->comm)
+	TP_ARGS(q, bio)
 );
 
-TRACE_EVENT(block_bio_queue,
+DEFINE_EVENT(block_bio, block_bio_frontmerge,
 
 	TP_PROTO(struct request_queue *q, struct bio *bio),
 
-	TP_ARGS(q, bio),
+	TP_ARGS(q, bio)
+);
 
-	TP_STRUCT__entry(
-		__field( dev_t,		dev			)
-		__field( sector_t,	sector			)
-		__field( unsigned int,	nr_sector		)
-		__array( char,		rwbs,	6		)
-		__array( char,		comm,	TASK_COMM_LEN	)
-	),
+DEFINE_EVENT(block_bio, block_bio_queue,
 
-	TP_fast_assign(
-		__entry->dev		= bio->bi_bdev->bd_dev;
-		__entry->sector		= bio->bi_sector;
-		__entry->nr_sector	= bio->bi_size >> 9;
-		blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_size);
-		memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
-	),
+	TP_PROTO(struct request_queue *q, struct bio *bio),
 
-	TP_printk("%d,%d %s %llu + %u [%s]",
-		  MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rwbs,
-		  (unsigned long long)__entry->sector,
-		  __entry->nr_sector, __entry->comm)
+	TP_ARGS(q, bio)
 );
 
-TRACE_EVENT(block_getrq,
+DECLARE_EVENT_CLASS(block_get_rq,
 
 	TP_PROTO(struct request_queue *q, struct bio *bio, int rw),
 
@@ -341,33 +243,18 @@ TRACE_EVENT(block_getrq,
 		  __entry->nr_sector, __entry->comm)
 );
 
-TRACE_EVENT(block_sleeprq,
+DEFINE_EVENT(block_get_rq, block_getrq,
 
 	TP_PROTO(struct request_queue *q, struct bio *bio, int rw),
 
-	TP_ARGS(q, bio, rw),
+	TP_ARGS(q, bio, rw)
+);
 
-	TP_STRUCT__entry(
-		__field( dev_t,		dev			)
-		__field( sector_t,	sector			)
-		__field( unsigned int,	nr_sector		)
-		__array( char,		rwbs,	6		)
-		__array( char,		comm,	TASK_COMM_LEN	)
-	),
+DEFINE_EVENT(block_get_rq, block_sleeprq,
 
-	TP_fast_assign(
-		__entry->dev		= bio ? bio->bi_bdev->bd_dev : 0;
-		__entry->sector		= bio ? bio->bi_sector : 0;
-		__entry->nr_sector	= bio ? bio->bi_size >> 9 : 0;
-		blk_fill_rwbs(__entry->rwbs,
-			    bio ? bio->bi_rw : 0, __entry->nr_sector);
-		memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
-	),
+	TP_PROTO(struct request_queue *q, struct bio *bio, int rw),
 
-	TP_printk("%d,%d %s %llu + %u [%s]",
-		  MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rwbs,
-		  (unsigned long long)__entry->sector,
-		  __entry->nr_sector, __entry->comm)
+	TP_ARGS(q, bio, rw)
 );
 
 TRACE_EVENT(block_plug,
@@ -387,7 +274,7 @@ TRACE_EVENT(block_plug,
 	TP_printk("[%s]", __entry->comm)
 );
 
-TRACE_EVENT(block_unplug_timer,
+DECLARE_EVENT_CLASS(block_unplug,
 
 	TP_PROTO(struct request_queue *q),
 
@@ -406,23 +293,18 @@ TRACE_EVENT(block_unplug_timer,
 	TP_printk("[%s] %d", __entry->comm, __entry->nr_rq)
 );
 
-TRACE_EVENT(block_unplug_io,
+DEFINE_EVENT(block_unplug, block_unplug_timer,
 
 	TP_PROTO(struct request_queue *q),
 
-	TP_ARGS(q),
+	TP_ARGS(q)
+);
 
-	TP_STRUCT__entry(
-		__field( int,		nr_rq			)
-		__array( char,		comm,	TASK_COMM_LEN	)
-	),
+DEFINE_EVENT(block_unplug, block_unplug_io,
 
-	TP_fast_assign(
-		__entry->nr_rq	= q->rq.count[READ] + q->rq.count[WRITE];
-		memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
-	),
+	TP_PROTO(struct request_queue *q),
 
-	TP_printk("[%s] %d", __entry->comm, __entry->nr_rq)
+	TP_ARGS(q)
 );
 
 TRACE_EVENT(block_split,

include/trace/events/ext4.h

@@ -90,7 +90,7 @@ TRACE_EVENT(ext4_allocate_inode,
 		  (unsigned long) __entry->dir, __entry->mode)
 );
 
-TRACE_EVENT(ext4_write_begin,
+DECLARE_EVENT_CLASS(ext4__write_begin,
 
 	TP_PROTO(struct inode *inode, loff_t pos, unsigned int len,
 		 unsigned int flags),
@@ -118,7 +118,23 @@ TRACE_EVENT(ext4_write_begin,
 		  __entry->pos, __entry->len, __entry->flags)
 );
 
-TRACE_EVENT(ext4_ordered_write_end,
+DEFINE_EVENT(ext4__write_begin, ext4_write_begin,
+
+	TP_PROTO(struct inode *inode, loff_t pos, unsigned int len,
+		 unsigned int flags),
+
+	TP_ARGS(inode, pos, len, flags)
+);
+
+DEFINE_EVENT(ext4__write_begin, ext4_da_write_begin,
+
+	TP_PROTO(struct inode *inode, loff_t pos, unsigned int len,
+		 unsigned int flags),
+
+	TP_ARGS(inode, pos, len, flags)
+);
+
+DECLARE_EVENT_CLASS(ext4__write_end,
 	TP_PROTO(struct inode *inode, loff_t pos, unsigned int len,
 			unsigned int copied),
 
@@ -145,57 +161,36 @@ TRACE_EVENT(ext4_ordered_write_end,
 		  __entry->pos, __entry->len, __entry->copied)
 );
 
-TRACE_EVENT(ext4_writeback_write_end,
+DEFINE_EVENT(ext4__write_end, ext4_ordered_write_end,
+
 	TP_PROTO(struct inode *inode, loff_t pos, unsigned int len,
 		 unsigned int copied),
 
-	TP_ARGS(inode, pos, len, copied),
+	TP_ARGS(inode, pos, len, copied)
+);
 
-	TP_STRUCT__entry(
-		__field(	dev_t,	dev			)
-		__field(	ino_t,	ino			)
-		__field(	loff_t,	pos			)
-		__field(	unsigned int, len		)
-		__field(	unsigned int, copied		)
-	),
+DEFINE_EVENT(ext4__write_end, ext4_writeback_write_end,
 
-	TP_fast_assign(
-		__entry->dev	= inode->i_sb->s_dev;
-		__entry->ino	= inode->i_ino;
-		__entry->pos	= pos;
-		__entry->len	= len;
-		__entry->copied	= copied;
-	),
+	TP_PROTO(struct inode *inode, loff_t pos, unsigned int len,
+		 unsigned int copied),
 
-	TP_printk("dev %s ino %lu pos %llu len %u copied %u",
-		  jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino,
-		  __entry->pos, __entry->len, __entry->copied)
+	TP_ARGS(inode, pos, len, copied)
 );
 
-TRACE_EVENT(ext4_journalled_write_end,
+DEFINE_EVENT(ext4__write_end, ext4_journalled_write_end,
+
 	TP_PROTO(struct inode *inode, loff_t pos, unsigned int len,
 		 unsigned int copied),
-	TP_ARGS(inode, pos, len, copied),
 
-	TP_STRUCT__entry(
-		__field(	dev_t,	dev			)
-		__field(	ino_t,	ino			)
-		__field(	loff_t,	pos			)
-		__field(	unsigned int, len		)
-		__field(	unsigned int, copied		)
-	),
+	TP_ARGS(inode, pos, len, copied)
+);
 
-	TP_fast_assign(
-		__entry->dev	= inode->i_sb->s_dev;
-		__entry->ino	= inode->i_ino;
-		__entry->pos	= pos;
-		__entry->len	= len;
-		__entry->copied	= copied;
-	),
+DEFINE_EVENT(ext4__write_end, ext4_da_write_end,
 
-	TP_printk("dev %s ino %lu pos %llu len %u copied %u",
-		  jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino,
-		  __entry->pos, __entry->len, __entry->copied)
+	TP_PROTO(struct inode *inode, loff_t pos, unsigned int len,
+		 unsigned int copied),
+
+	TP_ARGS(inode, pos, len, copied)
 );
 
 TRACE_EVENT(ext4_writepage,
@@ -337,60 +332,6 @@ TRACE_EVENT(ext4_da_writepages_result,
 		  (unsigned long) __entry->writeback_index)
 );
 
-TRACE_EVENT(ext4_da_write_begin,
-	TP_PROTO(struct inode *inode, loff_t pos, unsigned int len,
-			unsigned int flags),
-
-	TP_ARGS(inode, pos, len, flags),
-
-	TP_STRUCT__entry(
-		__field(	dev_t,	dev			)
-		__field(	ino_t,	ino			)
-		__field(	loff_t,	pos			)
-		__field(	unsigned int, len		)
-		__field(	unsigned int, flags		)
-	),
-
-	TP_fast_assign(
-		__entry->dev	= inode->i_sb->s_dev;
-		__entry->ino	= inode->i_ino;
-		__entry->pos	= pos;
-		__entry->len	= len;
-		__entry->flags	= flags;
-	),
-
-	TP_printk("dev %s ino %lu pos %llu len %u flags %u",
-		  jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino,
-		  __entry->pos, __entry->len, __entry->flags)
-);
-
-TRACE_EVENT(ext4_da_write_end,
-	TP_PROTO(struct inode *inode, loff_t pos, unsigned int len,
-			unsigned int copied),
-
-	TP_ARGS(inode, pos, len, copied),
-
-	TP_STRUCT__entry(
-		__field(	dev_t,	dev			)
-		__field(	ino_t,	ino			)
-		__field(	loff_t,	pos			)
-		__field(	unsigned int, len		)
-		__field(	unsigned int, copied		)
-	),
-
-	TP_fast_assign(
-		__entry->dev	= inode->i_sb->s_dev;
-		__entry->ino	= inode->i_ino;
-		__entry->pos	= pos;
-		__entry->len	= len;
-		__entry->copied	= copied;
-	),
-
-	TP_printk("dev %s ino %lu pos %llu len %u copied %u",
-		  jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino,
-		  __entry->pos, __entry->len, __entry->copied)
-);
-
 TRACE_EVENT(ext4_discard_blocks,
 	TP_PROTO(struct super_block *sb, unsigned long long blk,
 			unsigned long long count),

include/trace/events/irq.h

@@ -48,7 +48,7 @@ TRACE_EVENT(irq_handler_entry,
 		__assign_str(name, action->name);
 	),
 
-	TP_printk("irq=%d handler=%s", __entry->irq, __get_str(name))
+	TP_printk("irq=%d name=%s", __entry->irq, __get_str(name))
 );
 
 /**
@@ -78,22 +78,11 @@ TRACE_EVENT(irq_handler_exit,
 		__entry->ret	= ret;
 	),
 
-	TP_printk("irq=%d return=%s",
+	TP_printk("irq=%d ret=%s",
 		  __entry->irq, __entry->ret ? "handled" : "unhandled")
 );
 
-/**
- * softirq_entry - called immediately before the softirq handler
- * @h: pointer to struct softirq_action
- * @vec: pointer to first struct softirq_action in softirq_vec array
- *
- * The @h parameter, contains a pointer to the struct softirq_action
- * which has a pointer to the action handler that is called. By subtracting
- * the @vec pointer from the @h pointer, we can determine the softirq
- * number. Also, when used in combination with the softirq_exit tracepoint
- * we can determine the softirq latency.
- */
-TRACE_EVENT(softirq_entry,
+DECLARE_EVENT_CLASS(softirq,
 
 	TP_PROTO(struct softirq_action *h, struct softirq_action *vec),
 
@@ -107,10 +96,28 @@ TRACE_EVENT(softirq_entry,
 		__entry->vec = (int)(h - vec);
 	),
 
-	TP_printk("softirq=%d action=%s", __entry->vec,
+	TP_printk("vec=%d [action=%s]", __entry->vec,
 		  show_softirq_name(__entry->vec))
 );
 
+/**
+ * softirq_entry - called immediately before the softirq handler
+ * @h: pointer to struct softirq_action
+ * @vec: pointer to first struct softirq_action in softirq_vec array
+ *
+ * The @h parameter, contains a pointer to the struct softirq_action
+ * which has a pointer to the action handler that is called. By subtracting
+ * the @vec pointer from the @h pointer, we can determine the softirq
+ * number. Also, when used in combination with the softirq_exit tracepoint
+ * we can determine the softirq latency.
+ */
+DEFINE_EVENT(softirq, softirq_entry,
+
+	TP_PROTO(struct softirq_action *h, struct softirq_action *vec),
+
+	TP_ARGS(h, vec)
+);
+
 /**
  * softirq_exit - called immediately after the softirq handler returns
  * @h: pointer to struct softirq_action
@@ -122,22 +129,11 @@ TRACE_EVENT(softirq_entry,
  * combination with the softirq_entry tracepoint we can determine the softirq
  * latency.
  */
-TRACE_EVENT(softirq_exit,
+DEFINE_EVENT(softirq, softirq_exit,
 
 	TP_PROTO(struct softirq_action *h, struct softirq_action *vec),
 
-	TP_ARGS(h, vec),
-
-	TP_STRUCT__entry(
-		__field(	int,	vec			)
-	),
-
-	TP_fast_assign(
-		__entry->vec = (int)(h - vec);
-	),
-
-	TP_printk("softirq=%d action=%s", __entry->vec,
-		  show_softirq_name(__entry->vec))
+	TP_ARGS(h, vec)
 );
 
 #endif /*  _TRACE_IRQ_H */

include/trace/events/jbd2.h

@@ -30,7 +30,7 @@ TRACE_EVENT(jbd2_checkpoint,
 		  jbd2_dev_to_name(__entry->dev), __entry->result)
 );
 
-TRACE_EVENT(jbd2_start_commit,
+DECLARE_EVENT_CLASS(jbd2_commit,
 
 	TP_PROTO(journal_t *journal, transaction_t *commit_transaction),
 
@@ -53,73 +53,32 @@ TRACE_EVENT(jbd2_start_commit,
 		  __entry->sync_commit)
 );
 
-TRACE_EVENT(jbd2_commit_locking,
+DEFINE_EVENT(jbd2_commit, jbd2_start_commit,
 
 	TP_PROTO(journal_t *journal, transaction_t *commit_transaction),
 
-	TP_ARGS(journal, commit_transaction),
-
-	TP_STRUCT__entry(
-		__field(	dev_t,	dev			)
-		__field(	char,	sync_commit		  )
-		__field(	int,	transaction		  )
-	),
-
-	TP_fast_assign(
-		__entry->dev		= journal->j_fs_dev->bd_dev;
-		__entry->sync_commit = commit_transaction->t_synchronous_commit;
-		__entry->transaction	= commit_transaction->t_tid;
-	),
-
-	TP_printk("dev %s transaction %d sync %d",
-		  jbd2_dev_to_name(__entry->dev), __entry->transaction,
-		  __entry->sync_commit)
+	TP_ARGS(journal, commit_transaction)
 );
 
-TRACE_EVENT(jbd2_commit_flushing,
+DEFINE_EVENT(jbd2_commit, jbd2_commit_locking,
 
 	TP_PROTO(journal_t *journal, transaction_t *commit_transaction),
 
-	TP_ARGS(journal, commit_transaction),
-
-	TP_STRUCT__entry(
-		__field(	dev_t,	dev			)
-		__field(	char,	sync_commit		  )
-		__field(	int,	transaction		  )
-	),
-
-	TP_fast_assign(
-		__entry->dev		= journal->j_fs_dev->bd_dev;
-		__entry->sync_commit = commit_transaction->t_synchronous_commit;
-		__entry->transaction	= commit_transaction->t_tid;
-	),
-
-	TP_printk("dev %s transaction %d sync %d",
-		  jbd2_dev_to_name(__entry->dev), __entry->transaction,
-		  __entry->sync_commit)
+	TP_ARGS(journal, commit_transaction)
 );
 
-TRACE_EVENT(jbd2_commit_logging,
+DEFINE_EVENT(jbd2_commit, jbd2_commit_flushing,
 
 	TP_PROTO(journal_t *journal, transaction_t *commit_transaction),
 
-	TP_ARGS(journal, commit_transaction),
+	TP_ARGS(journal, commit_transaction)
+);
 
-	TP_STRUCT__entry(
-		__field(	dev_t,	dev			)
-		__field(	char,	sync_commit		  )
-		__field(	int,	transaction		  )
-	),
+DEFINE_EVENT(jbd2_commit, jbd2_commit_logging,
 
-	TP_fast_assign(
-		__entry->dev		= journal->j_fs_dev->bd_dev;
-		__entry->sync_commit = commit_transaction->t_synchronous_commit;
-		__entry->transaction	= commit_transaction->t_tid;
-	),
+	TP_PROTO(journal_t *journal, transaction_t *commit_transaction),
 
-	TP_printk("dev %s transaction %d sync %d",
-		  jbd2_dev_to_name(__entry->dev), __entry->transaction,
-		  __entry->sync_commit)
+	TP_ARGS(journal, commit_transaction)
 );
 
 TRACE_EVENT(jbd2_end_commit,

include/trace/events/kmem.h

@@ -44,7 +44,7 @@
 	{(unsigned long)__GFP_MOVABLE,		"GFP_MOVABLE"}		\
 	) : "GFP_NOWAIT"
 
-TRACE_EVENT(kmalloc,
+DECLARE_EVENT_CLASS(kmem_alloc,
 
 	TP_PROTO(unsigned long call_site,
 		 const void *ptr,
@@ -78,41 +78,23 @@ TRACE_EVENT(kmalloc,
 		show_gfp_flags(__entry->gfp_flags))
 );
 
-TRACE_EVENT(kmem_cache_alloc,
+DEFINE_EVENT(kmem_alloc, kmalloc,
 
-	TP_PROTO(unsigned long call_site,
-		 const void *ptr,
-		 size_t bytes_req,
-		 size_t bytes_alloc,
-		 gfp_t gfp_flags),
+	TP_PROTO(unsigned long call_site, const void *ptr,
+		 size_t bytes_req, size_t bytes_alloc, gfp_t gfp_flags),
 
-	TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags),
+	TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags)
+);
 
-	TP_STRUCT__entry(
-		__field(	unsigned long,	call_site	)
-		__field(	const void *,	ptr		)
-		__field(	size_t,		bytes_req	)
-		__field(	size_t,		bytes_alloc	)
-		__field(	gfp_t,		gfp_flags	)
-	),
+DEFINE_EVENT(kmem_alloc, kmem_cache_alloc,
 
-	TP_fast_assign(
-		__entry->call_site	= call_site;
-		__entry->ptr		= ptr;
-		__entry->bytes_req	= bytes_req;
-		__entry->bytes_alloc	= bytes_alloc;
-		__entry->gfp_flags	= gfp_flags;
-	),
+	TP_PROTO(unsigned long call_site, const void *ptr,
+		 size_t bytes_req, size_t bytes_alloc, gfp_t gfp_flags),
 
-	TP_printk("call_site=%lx ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%s",
-		__entry->call_site,
-		__entry->ptr,
-		__entry->bytes_req,
-		__entry->bytes_alloc,
-		show_gfp_flags(__entry->gfp_flags))
+	TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags)
 );
 
-TRACE_EVENT(kmalloc_node,
+DECLARE_EVENT_CLASS(kmem_alloc_node,
 
 	TP_PROTO(unsigned long call_site,
 		 const void *ptr,
@@ -150,45 +132,25 @@ TRACE_EVENT(kmalloc_node,
 		__entry->node)
 );
 
-TRACE_EVENT(kmem_cache_alloc_node,
+DEFINE_EVENT(kmem_alloc_node, kmalloc_node,
 
-	TP_PROTO(unsigned long call_site,
-		 const void *ptr,
-		 size_t bytes_req,
-		 size_t bytes_alloc,
-		 gfp_t gfp_flags,
-		 int node),
+	TP_PROTO(unsigned long call_site, const void *ptr,
+		 size_t bytes_req, size_t bytes_alloc,
+		 gfp_t gfp_flags, int node),
 
-	TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags, node),
+	TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags, node)
+);
 
-	TP_STRUCT__entry(
-		__field(	unsigned long,	call_site	)
-		__field(	const void *,	ptr		)
-		__field(	size_t,		bytes_req	)
-		__field(	size_t,		bytes_alloc	)
-		__field(	gfp_t,		gfp_flags	)
-		__field(	int,		node		)
-	),
+DEFINE_EVENT(kmem_alloc_node, kmem_cache_alloc_node,
 
-	TP_fast_assign(
-		__entry->call_site	= call_site;
-		__entry->ptr		= ptr;
-		__entry->bytes_req	= bytes_req;
-		__entry->bytes_alloc	= bytes_alloc;
-		__entry->gfp_flags	= gfp_flags;
-		__entry->node		= node;
-	),
+	TP_PROTO(unsigned long call_site, const void *ptr,
+		 size_t bytes_req, size_t bytes_alloc,
+		 gfp_t gfp_flags, int node),
 
-	TP_printk("call_site=%lx ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%s node=%d",
-		__entry->call_site,
-		__entry->ptr,
-		__entry->bytes_req,
-		__entry->bytes_alloc,
-		show_gfp_flags(__entry->gfp_flags),
-		__entry->node)
+	TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags, node)
 );
 
-TRACE_EVENT(kfree,
+DECLARE_EVENT_CLASS(kmem_free,
 
 	TP_PROTO(unsigned long call_site, const void *ptr),
 
@@ -207,23 +169,18 @@ TRACE_EVENT(kfree,
 	TP_printk("call_site=%lx ptr=%p", __entry->call_site, __entry->ptr)
 );
 
-TRACE_EVENT(kmem_cache_free,
+DEFINE_EVENT(kmem_free, kfree,
 
 	TP_PROTO(unsigned long call_site, const void *ptr),
 
-	TP_ARGS(call_site, ptr),
+	TP_ARGS(call_site, ptr)
+);
 
-	TP_STRUCT__entry(
-		__field(	unsigned long,	call_site	)
-		__field(	const void *,	ptr		)
-	),
+DEFINE_EVENT(kmem_free, kmem_cache_free,
 
-	TP_fast_assign(
-		__entry->call_site	= call_site;
-		__entry->ptr		= ptr;
-	),
+	TP_PROTO(unsigned long call_site, const void *ptr),
 
-	TP_printk("call_site=%lx ptr=%p", __entry->call_site, __entry->ptr)
+	TP_ARGS(call_site, ptr)
 );
 
 TRACE_EVENT(mm_page_free_direct,
@@ -299,7 +256,7 @@ TRACE_EVENT(mm_page_alloc,
 		show_gfp_flags(__entry->gfp_flags))
 );
 
-TRACE_EVENT(mm_page_alloc_zone_locked,
+DECLARE_EVENT_CLASS(mm_page,
 
 	TP_PROTO(struct page *page, unsigned int order, int migratetype),
 
@@ -325,29 +282,22 @@ TRACE_EVENT(mm_page_alloc_zone_locked,
 		__entry->order == 0)
 );
 
-TRACE_EVENT(mm_page_pcpu_drain,
+DEFINE_EVENT(mm_page, mm_page_alloc_zone_locked,
 
-	TP_PROTO(struct page *page, int order, int migratetype),
+	TP_PROTO(struct page *page, unsigned int order, int migratetype),
 
-	TP_ARGS(page, order, migratetype),
+	TP_ARGS(page, order, migratetype)
+);
 
-	TP_STRUCT__entry(
-		__field(	struct page *,	page		)
-		__field(	int,		order		)
-		__field(	int,		migratetype	)
-	),
+DEFINE_EVENT_PRINT(mm_page, mm_page_pcpu_drain,
 
-	TP_fast_assign(
-		__entry->page		= page;
-		__entry->order		= order;
-		__entry->migratetype	= migratetype;
-	),
+	TP_PROTO(struct page *page, unsigned int order, int migratetype),
+
+	TP_ARGS(page, order, migratetype),
 
 	TP_printk("page=%p pfn=%lu order=%d migratetype=%d",
-		__entry->page,
-		page_to_pfn(__entry->page),
-		__entry->order,
-		__entry->migratetype)
+		__entry->page, page_to_pfn(__entry->page),
+		__entry->order, __entry->migratetype)
 );
 
 TRACE_EVENT(mm_page_alloc_extfrag,

include/trace/events/lockdep.h → include/trace/events/lock.h

@@ -1,8 +1,8 @@
 #undef TRACE_SYSTEM
-#define TRACE_SYSTEM lockdep
+#define TRACE_SYSTEM lock
 
-#if !defined(_TRACE_LOCKDEP_H) || defined(TRACE_HEADER_MULTI_READ)
-#define _TRACE_LOCKDEP_H
+#if !defined(_TRACE_LOCK_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_LOCK_H
 
 #include <linux/lockdep.h>
 #include <linux/tracepoint.h>
@@ -90,7 +90,7 @@ TRACE_EVENT(lock_acquired,
 #endif
 #endif
 
-#endif /* _TRACE_LOCKDEP_H */
+#endif /* _TRACE_LOCK_H */
 
 /* This part must be outside protection */
 #include <trace/define_trace.h>

include/trace/events/mce.h

@@ -0,0 +1,69 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM mce
+
+#if !defined(_TRACE_MCE_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_MCE_H
+
+#include <linux/ktime.h>
+#include <linux/tracepoint.h>
+#include <asm/mce.h>
+
+TRACE_EVENT(mce_record,
+
+	TP_PROTO(struct mce *m),
+
+	TP_ARGS(m),
+
+	TP_STRUCT__entry(
+		__field(	u64,		mcgcap		)
+		__field(	u64,		mcgstatus	)
+		__field(	u8,		bank		)
+		__field(	u64,		status		)
+		__field(	u64,		addr		)
+		__field(	u64,		misc		)
+		__field(	u64,		ip		)
+		__field(	u8,		cs		)
+		__field(	u64,		tsc		)
+		__field(	u64,		walltime	)
+		__field(	u32,		cpu		)
+		__field(	u32,		cpuid		)
+		__field(	u32,		apicid		)
+		__field(	u32,		socketid	)
+		__field(	u8,		cpuvendor	)
+	),
+
+	TP_fast_assign(
+		__entry->mcgcap		= m->mcgcap;
+		__entry->mcgstatus	= m->mcgstatus;
+		__entry->bank		= m->bank;
+		__entry->status		= m->status;
+		__entry->addr		= m->addr;
+		__entry->misc		= m->misc;
+		__entry->ip		= m->ip;
+		__entry->cs		= m->cs;
+		__entry->tsc		= m->tsc;
+		__entry->walltime	= m->time;
+		__entry->cpu		= m->extcpu;
+		__entry->cpuid		= m->cpuid;
+		__entry->apicid		= m->apicid;
+		__entry->socketid	= m->socketid;
+		__entry->cpuvendor	= m->cpuvendor;
+	),
+
+	TP_printk("CPU: %d, MCGc/s: %llx/%llx, MC%d: %016Lx, ADDR/MISC: %016Lx/%016Lx, RIP: %02x:<%016Lx>, TSC: %llx, PROCESSOR: %u:%x, TIME: %llu, SOCKET: %u, APIC: %x",
+		__entry->cpu,
+		__entry->mcgcap, __entry->mcgstatus,
+		__entry->bank, __entry->status,
+		__entry->addr, __entry->misc,
+		__entry->cs, __entry->ip,
+		__entry->tsc,
+		__entry->cpuvendor, __entry->cpuid,
+		__entry->walltime,
+		__entry->socketid,
+		__entry->apicid)
+);
+
+#endif /* _TRACE_MCE_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>

include/trace/events/module.h

@@ -51,7 +51,7 @@ TRACE_EVENT(module_free,
 	TP_printk("%s", __get_str(name))
 );
 
-TRACE_EVENT(module_get,
+DECLARE_EVENT_CLASS(module_refcnt,
 
 	TP_PROTO(struct module *mod, unsigned long ip, int refcnt),
 
@@ -73,26 +73,18 @@ TRACE_EVENT(module_get,
 		  __get_str(name), (void *)__entry->ip, __entry->refcnt)
 );
 
-TRACE_EVENT(module_put,
+DEFINE_EVENT(module_refcnt, module_get,
 
 	TP_PROTO(struct module *mod, unsigned long ip, int refcnt),
 
-	TP_ARGS(mod, ip, refcnt),
+	TP_ARGS(mod, ip, refcnt)
+);
 
-	TP_STRUCT__entry(
-		__field(	unsigned long,	ip		)
-		__field(	int,		refcnt		)
-		__string(	name,		mod->name	)
-	),
+DEFINE_EVENT(module_refcnt, module_put,
 
-	TP_fast_assign(
-		__entry->ip	= ip;
-		__entry->refcnt	= refcnt;
-		__assign_str(name, mod->name);
-	),
+	TP_PROTO(struct module *mod, unsigned long ip, int refcnt),
 
-	TP_printk("%s call_site=%pf refcnt=%d",
-		  __get_str(name), (void *)__entry->ip, __entry->refcnt)
+	TP_ARGS(mod, ip, refcnt)
 );
 
 TRACE_EVENT(module_request,

include/trace/events/power.h

@@ -16,9 +16,7 @@ enum {
 };
 #endif
 
-
-
-TRACE_EVENT(power_start,
+DECLARE_EVENT_CLASS(power,
 
 	TP_PROTO(unsigned int type, unsigned int state),
 
@@ -37,42 +35,36 @@ TRACE_EVENT(power_start,
 	TP_printk("type=%lu state=%lu", (unsigned long)__entry->type, (unsigned long)__entry->state)
 );
 
-TRACE_EVENT(power_end,
-
-	TP_PROTO(int dummy),
+DEFINE_EVENT(power, power_start,
 
-	TP_ARGS(dummy),
+	TP_PROTO(unsigned int type, unsigned int state),
 
-	TP_STRUCT__entry(
-		__field(	u64,		dummy		)
-	),
+	TP_ARGS(type, state)
+);
 
-	TP_fast_assign(
-		__entry->dummy = 0xffff;
-	),
+DEFINE_EVENT(power, power_frequency,
 
-	TP_printk("dummy=%lu", (unsigned long)__entry->dummy)
+	TP_PROTO(unsigned int type, unsigned int state),
 
+	TP_ARGS(type, state)
 );
 
+TRACE_EVENT(power_end,
 
-TRACE_EVENT(power_frequency,
-
-	TP_PROTO(unsigned int type, unsigned int state),
+	TP_PROTO(int dummy),
 
-	TP_ARGS(type, state),
+	TP_ARGS(dummy),
 
 	TP_STRUCT__entry(
-		__field(	u64,		type		)
-		__field(	u64,		state		)
+		__field(	u64,		dummy		)
 	),
 
 	TP_fast_assign(
-		__entry->type = type;
-		__entry->state = state;
+		__entry->dummy = 0xffff;
 	),
 
-	TP_printk("type=%lu state=%lu", (unsigned long)__entry->type, (unsigned long) __entry->state)
+	TP_printk("dummy=%lu", (unsigned long)__entry->dummy)
+
 );
 
 #endif /* _TRACE_POWER_H */

include/trace/events/sched.h

@@ -26,7 +26,7 @@ TRACE_EVENT(sched_kthread_stop,
 		__entry->pid	= t->pid;
 	),
 
-	TP_printk("task %s:%d", __entry->comm, __entry->pid)
+	TP_printk("comm=%s pid=%d", __entry->comm, __entry->pid)
 );
 
 /*
@@ -46,7 +46,7 @@ TRACE_EVENT(sched_kthread_stop_ret,
 		__entry->ret	= ret;
 	),
 
-	TP_printk("ret %d", __entry->ret)
+	TP_printk("ret=%d", __entry->ret)
 );
 
 /*
@@ -73,7 +73,7 @@ TRACE_EVENT(sched_wait_task,
 		__entry->prio	= p->prio;
 	),
 
-	TP_printk("task %s:%d [%d]",
+	TP_printk("comm=%s pid=%d prio=%d",
 		  __entry->comm, __entry->pid, __entry->prio)
 );
 
@@ -83,7 +83,7 @@ TRACE_EVENT(sched_wait_task,
  * (NOTE: the 'rq' argument is not used by generic trace events,
  *        but used by the latency tracer plugin. )
  */
-TRACE_EVENT(sched_wakeup,
+DECLARE_EVENT_CLASS(sched_wakeup_template,
 
 	TP_PROTO(struct rq *rq, struct task_struct *p, int success),
 
@@ -94,7 +94,7 @@ TRACE_EVENT(sched_wakeup,
 		__field(	pid_t,	pid			)
 		__field(	int,	prio			)
 		__field(	int,	success			)
-		__field(	int,	cpu			)
+		__field(	int,	target_cpu		)
 	),
 
 	TP_fast_assign(
@@ -102,46 +102,27 @@ TRACE_EVENT(sched_wakeup,
 		__entry->pid		= p->pid;
 		__entry->prio		= p->prio;
 		__entry->success	= success;
-		__entry->cpu		= task_cpu(p);
+		__entry->target_cpu	= task_cpu(p);
 	),
 
-	TP_printk("task %s:%d [%d] success=%d [%03d]",
+	TP_printk("comm=%s pid=%d prio=%d success=%d target_cpu=%03d",
 		  __entry->comm, __entry->pid, __entry->prio,
-		  __entry->success, __entry->cpu)
+		  __entry->success, __entry->target_cpu)
 );
 
+DEFINE_EVENT(sched_wakeup_template, sched_wakeup,
+	     TP_PROTO(struct rq *rq, struct task_struct *p, int success),
+	     TP_ARGS(rq, p, success));
+
 /*
  * Tracepoint for waking up a new task:
  *
  * (NOTE: the 'rq' argument is not used by generic trace events,
  *        but used by the latency tracer plugin. )
  */
-TRACE_EVENT(sched_wakeup_new,
-
-	TP_PROTO(struct rq *rq, struct task_struct *p, int success),
-
-	TP_ARGS(rq, p, success),
-
-	TP_STRUCT__entry(
-		__array(	char,	comm,	TASK_COMM_LEN	)
-		__field(	pid_t,	pid			)
-		__field(	int,	prio			)
-		__field(	int,	success			)
-		__field(	int,	cpu			)
-	),
-
-	TP_fast_assign(
-		memcpy(__entry->comm, p->comm, TASK_COMM_LEN);
-		__entry->pid		= p->pid;
-		__entry->prio		= p->prio;
-		__entry->success	= success;
-		__entry->cpu		= task_cpu(p);
-	),
-
-	TP_printk("task %s:%d [%d] success=%d [%03d]",
-		  __entry->comm, __entry->pid, __entry->prio,
-		  __entry->success, __entry->cpu)
-);
+DEFINE_EVENT(sched_wakeup_template, sched_wakeup_new,
+	     TP_PROTO(struct rq *rq, struct task_struct *p, int success),
+	     TP_ARGS(rq, p, success));
 
 /*
  * Tracepoint for task switches, performed by the scheduler:
@@ -176,7 +157,7 @@ TRACE_EVENT(sched_switch,
 		__entry->next_prio	= next->prio;
 	),
 
-	TP_printk("task %s:%d [%d] (%s) ==> %s:%d [%d]",
+	TP_printk("prev_comm=%s prev_pid=%d prev_prio=%d prev_state=%s ==> next_comm=%s next_pid=%d next_prio=%d",
 		__entry->prev_comm, __entry->prev_pid, __entry->prev_prio,
 		__entry->prev_state ?
 		  __print_flags(__entry->prev_state, "|",
@@ -211,15 +192,12 @@ TRACE_EVENT(sched_migrate_task,
 		__entry->dest_cpu	= dest_cpu;
 	),
 
-	TP_printk("task %s:%d [%d] from: %d  to: %d",
+	TP_printk("comm=%s pid=%d prio=%d orig_cpu=%d dest_cpu=%d",
 		  __entry->comm, __entry->pid, __entry->prio,
 		  __entry->orig_cpu, __entry->dest_cpu)
 );
 
-/*
- * Tracepoint for freeing a task:
- */
-TRACE_EVENT(sched_process_free,
+DECLARE_EVENT_CLASS(sched_process_template,
 
 	TP_PROTO(struct task_struct *p),
 
@@ -237,34 +215,24 @@ TRACE_EVENT(sched_process_free,
 		__entry->prio		= p->prio;
 	),
 
-	TP_printk("task %s:%d [%d]",
+	TP_printk("comm=%s pid=%d prio=%d",
 		  __entry->comm, __entry->pid, __entry->prio)
 );
 
 /*
- * Tracepoint for a task exiting:
+ * Tracepoint for freeing a task:
  */
-TRACE_EVENT(sched_process_exit,
+DEFINE_EVENT(sched_process_template, sched_process_free,
+	     TP_PROTO(struct task_struct *p),
+	     TP_ARGS(p));
+	     
 
-	TP_PROTO(struct task_struct *p),
-
-	TP_ARGS(p),
-
-	TP_STRUCT__entry(
-		__array(	char,	comm,	TASK_COMM_LEN	)
-		__field(	pid_t,	pid			)
-		__field(	int,	prio			)
-	),
-
-	TP_fast_assign(
-		memcpy(__entry->comm, p->comm, TASK_COMM_LEN);
-		__entry->pid		= p->pid;
-		__entry->prio		= p->prio;
-	),
-
-	TP_printk("task %s:%d [%d]",
-		  __entry->comm, __entry->pid, __entry->prio)
-);
+/*
+ * Tracepoint for a task exiting:
+ */
+DEFINE_EVENT(sched_process_template, sched_process_exit,
+	     TP_PROTO(struct task_struct *p),
+	     TP_ARGS(p));
 
 /*
  * Tracepoint for a waiting task:
@@ -287,7 +255,7 @@ TRACE_EVENT(sched_process_wait,
 		__entry->prio		= current->prio;
 	),
 
-	TP_printk("task %s:%d [%d]",
+	TP_printk("comm=%s pid=%d prio=%d",
 		  __entry->comm, __entry->pid, __entry->prio)
 );
 
@@ -314,46 +282,16 @@ TRACE_EVENT(sched_process_fork,
 		__entry->child_pid	= child->pid;
 	),
 
-	TP_printk("parent %s:%d  child %s:%d",
+	TP_printk("comm=%s pid=%d child_comm=%s child_pid=%d",
 		__entry->parent_comm, __entry->parent_pid,
 		__entry->child_comm, __entry->child_pid)
 );
 
-/*
- * Tracepoint for sending a signal:
- */
-TRACE_EVENT(sched_signal_send,
-
-	TP_PROTO(int sig, struct task_struct *p),
-
-	TP_ARGS(sig, p),
-
-	TP_STRUCT__entry(
-		__field(	int,	sig			)
-		__array(	char,	comm,	TASK_COMM_LEN	)
-		__field(	pid_t,	pid			)
-	),
-
-	TP_fast_assign(
-		memcpy(__entry->comm, p->comm, TASK_COMM_LEN);
-		__entry->pid	= p->pid;
-		__entry->sig	= sig;
-	),
-
-	TP_printk("sig: %d  task %s:%d",
-		  __entry->sig, __entry->comm, __entry->pid)
-);
-
 /*
  * XXX the below sched_stat tracepoints only apply to SCHED_OTHER/BATCH/IDLE
  *     adding sched_stat support to SCHED_FIFO/RR would be welcome.
  */
-
-/*
- * Tracepoint for accounting wait time (time the task is runnable
- * but not actually running due to scheduler contention).
- */
-TRACE_EVENT(sched_stat_wait,
+DECLARE_EVENT_CLASS(sched_stat_template,
 
 	TP_PROTO(struct task_struct *tsk, u64 delay),
 
@@ -374,11 +312,36 @@ TRACE_EVENT(sched_stat_wait,
 		__perf_count(delay);
 	),
 
-	TP_printk("task: %s:%d wait: %Lu [ns]",
+	TP_printk("comm=%s pid=%d delay=%Lu [ns]",
 			__entry->comm, __entry->pid,
 			(unsigned long long)__entry->delay)
 );
 
+
+/*
+ * Tracepoint for accounting wait time (time the task is runnable
+ * but not actually running due to scheduler contention).
+ */
+DEFINE_EVENT(sched_stat_template, sched_stat_wait,
+	     TP_PROTO(struct task_struct *tsk, u64 delay),
+	     TP_ARGS(tsk, delay));
+
+/*
+ * Tracepoint for accounting sleep time (time the task is not runnable,
+ * including iowait, see below).
+ */
+DEFINE_EVENT(sched_stat_template, sched_stat_sleep,
+	     TP_PROTO(struct task_struct *tsk, u64 delay),
+	     TP_ARGS(tsk, delay));
+
+/*
+ * Tracepoint for accounting iowait time (time the task is not runnable
+ * due to waiting on IO to complete).
+ */
+DEFINE_EVENT(sched_stat_template, sched_stat_iowait,
+	     TP_PROTO(struct task_struct *tsk, u64 delay),
+	     TP_ARGS(tsk, delay));
+
 /*
  * Tracepoint for accounting runtime (time the task is executing
  * on a CPU).
@@ -406,72 +369,12 @@ TRACE_EVENT(sched_stat_runtime,
 		__perf_count(runtime);
 	),
 
-	TP_printk("task: %s:%d runtime: %Lu [ns], vruntime: %Lu [ns]",
+	TP_printk("comm=%s pid=%d runtime=%Lu [ns] vruntime=%Lu [ns]",
 			__entry->comm, __entry->pid,
 			(unsigned long long)__entry->runtime,
 			(unsigned long long)__entry->vruntime)
 );
 
-/*
- * Tracepoint for accounting sleep time (time the task is not runnable,
- * including iowait, see below).
- */
-TRACE_EVENT(sched_stat_sleep,
-
-	TP_PROTO(struct task_struct *tsk, u64 delay),
-
-	TP_ARGS(tsk, delay),
-
-	TP_STRUCT__entry(
-		__array( char,	comm,	TASK_COMM_LEN	)
-		__field( pid_t,	pid			)
-		__field( u64,	delay			)
-	),
-
-	TP_fast_assign(
-		memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
-		__entry->pid	= tsk->pid;
-		__entry->delay	= delay;
-	)
-	TP_perf_assign(
-		__perf_count(delay);
-	),
-
-	TP_printk("task: %s:%d sleep: %Lu [ns]",
-			__entry->comm, __entry->pid,
-			(unsigned long long)__entry->delay)
-);
-
-/*
- * Tracepoint for accounting iowait time (time the task is not runnable
- * due to waiting on IO to complete).
- */
-TRACE_EVENT(sched_stat_iowait,
-
-	TP_PROTO(struct task_struct *tsk, u64 delay),
-
-	TP_ARGS(tsk, delay),
-
-	TP_STRUCT__entry(
-		__array( char,	comm,	TASK_COMM_LEN	)
-		__field( pid_t,	pid			)
-		__field( u64,	delay			)
-	),
-
-	TP_fast_assign(
-		memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
-		__entry->pid	= tsk->pid;
-		__entry->delay	= delay;
-	)
-	TP_perf_assign(
-		__perf_count(delay);
-	),
-
-	TP_printk("task: %s:%d iowait: %Lu [ns]",
-			__entry->comm, __entry->pid,
-			(unsigned long long)__entry->delay)
-);
-
 #endif /* _TRACE_SCHED_H */
 
 /* This part must be outside protection */

include/trace/events/signal.h

@@ -0,0 +1,173 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM signal
+
+#if !defined(_TRACE_SIGNAL_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_SIGNAL_H
+
+#include <linux/signal.h>
+#include <linux/sched.h>
+#include <linux/tracepoint.h>
+
+#define TP_STORE_SIGINFO(__entry, info)				\
+	do {							\
+		if (info == SEND_SIG_NOINFO) {			\
+			__entry->errno	= 0;			\
+			__entry->code	= SI_USER;		\
+		} else if (info == SEND_SIG_PRIV) {		\
+			__entry->errno	= 0;			\
+			__entry->code	= SI_KERNEL;		\
+		} else {					\
+			__entry->errno	= info->si_errno;	\
+			__entry->code	= info->si_code;	\
+		}						\
+	} while (0)
+
+/**
+ * signal_generate - called when a signal is generated
+ * @sig: signal number
+ * @info: pointer to struct siginfo
+ * @task: pointer to struct task_struct
+ *
+ * Current process sends a 'sig' signal to 'task' process with
+ * 'info' siginfo. If 'info' is SEND_SIG_NOINFO or SEND_SIG_PRIV,
+ * 'info' is not a pointer and you can't access its field. Instead,
+ * SEND_SIG_NOINFO means that si_code is SI_USER, and SEND_SIG_PRIV
+ * means that si_code is SI_KERNEL.
+ */
+TRACE_EVENT(signal_generate,
+
+	TP_PROTO(int sig, struct siginfo *info, struct task_struct *task),
+
+	TP_ARGS(sig, info, task),
+
+	TP_STRUCT__entry(
+		__field(	int,	sig			)
+		__field(	int,	errno			)
+		__field(	int,	code			)
+		__array(	char,	comm,	TASK_COMM_LEN	)
+		__field(	pid_t,	pid			)
+	),
+
+	TP_fast_assign(
+		__entry->sig	= sig;
+		TP_STORE_SIGINFO(__entry, info);
+		memcpy(__entry->comm, task->comm, TASK_COMM_LEN);
+		__entry->pid	= task->pid;
+	),
+
+	TP_printk("sig=%d errno=%d code=%d comm=%s pid=%d",
+		  __entry->sig, __entry->errno, __entry->code,
+		  __entry->comm, __entry->pid)
+);
+
+/**
+ * signal_deliver - called when a signal is delivered
+ * @sig: signal number
+ * @info: pointer to struct siginfo
+ * @ka: pointer to struct k_sigaction
+ *
+ * A 'sig' signal is delivered to current process with 'info' siginfo,
+ * and it will be handled by 'ka'. ka->sa.sa_handler can be SIG_IGN or
+ * SIG_DFL.
+ * Note that some signals reported by signal_generate tracepoint can be
+ * lost, ignored or modified (by debugger) before hitting this tracepoint.
+ * This means, this can show which signals are actually delivered, but
+ * matching generated signals and delivered signals may not be correct.
+ */
+TRACE_EVENT(signal_deliver,
+
+	TP_PROTO(int sig, struct siginfo *info, struct k_sigaction *ka),
+
+	TP_ARGS(sig, info, ka),
+
+	TP_STRUCT__entry(
+		__field(	int,		sig		)
+		__field(	int,		errno		)
+		__field(	int,		code		)
+		__field(	unsigned long,	sa_handler	)
+		__field(	unsigned long,	sa_flags	)
+	),
+
+	TP_fast_assign(
+		__entry->sig	= sig;
+		TP_STORE_SIGINFO(__entry, info);
+		__entry->sa_handler	= (unsigned long)ka->sa.sa_handler;
+		__entry->sa_flags	= ka->sa.sa_flags;
+	),
+
+	TP_printk("sig=%d errno=%d code=%d sa_handler=%lx sa_flags=%lx",
+		  __entry->sig, __entry->errno, __entry->code,
+		  __entry->sa_handler, __entry->sa_flags)
+);
+
+/**
+ * signal_overflow_fail - called when signal queue is overflow
+ * @sig: signal number
+ * @group: signal to process group or not (bool)
+ * @info: pointer to struct siginfo
+ *
+ * Kernel fails to generate 'sig' signal with 'info' siginfo, because
+ * siginfo queue is overflow, and the signal is dropped.
+ * 'group' is not 0 if the signal will be sent to a process group.
+ * 'sig' is always one of RT signals.
+ */
+TRACE_EVENT(signal_overflow_fail,
+
+	TP_PROTO(int sig, int group, struct siginfo *info),
+
+	TP_ARGS(sig, group, info),
+
+	TP_STRUCT__entry(
+		__field(	int,	sig	)
+		__field(	int,	group	)
+		__field(	int,	errno	)
+		__field(	int,	code	)
+	),
+
+	TP_fast_assign(
+		__entry->sig	= sig;
+		__entry->group	= group;
+		TP_STORE_SIGINFO(__entry, info);
+	),
+
+	TP_printk("sig=%d group=%d errno=%d code=%d",
+		  __entry->sig, __entry->group, __entry->errno, __entry->code)
+);
+
+/**
+ * signal_lose_info - called when siginfo is lost
+ * @sig: signal number
+ * @group: signal to process group or not (bool)
+ * @info: pointer to struct siginfo
+ *
+ * Kernel generates 'sig' signal but loses 'info' siginfo, because siginfo
+ * queue is overflow.
+ * 'group' is not 0 if the signal will be sent to a process group.
+ * 'sig' is always one of non-RT signals.
+ */
+TRACE_EVENT(signal_lose_info,
+
+	TP_PROTO(int sig, int group, struct siginfo *info),
+
+	TP_ARGS(sig, group, info),
+
+	TP_STRUCT__entry(
+		__field(	int,	sig	)
+		__field(	int,	group	)
+		__field(	int,	errno	)
+		__field(	int,	code	)
+	),
+
+	TP_fast_assign(
+		__entry->sig	= sig;
+		__entry->group	= group;
+		TP_STORE_SIGINFO(__entry, info);
+	),
+
+	TP_printk("sig=%d group=%d errno=%d code=%d",
+		  __entry->sig, __entry->group, __entry->errno, __entry->code)
+);
+#endif /* _TRACE_SIGNAL_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>

include/trace/events/timer.h

@@ -26,7 +26,7 @@ TRACE_EVENT(timer_init,
 		__entry->timer	= timer;
 	),
 
-	TP_printk("timer %p", __entry->timer)
+	TP_printk("timer=%p", __entry->timer)
 );
 
 /**
@@ -54,7 +54,7 @@ TRACE_EVENT(timer_start,
 		__entry->now		= jiffies;
 	),
 
-	TP_printk("timer %p: func %pf, expires %lu, timeout %ld",
+	TP_printk("timer=%p function=%pf expires=%lu [timeout=%ld]",
 		  __entry->timer, __entry->function, __entry->expires,
 		  (long)__entry->expires - __entry->now)
 );
@@ -81,7 +81,7 @@ TRACE_EVENT(timer_expire_entry,
 		__entry->now		= jiffies;
 	),
 
-	TP_printk("timer %p: now %lu", __entry->timer, __entry->now)
+	TP_printk("timer=%p now=%lu", __entry->timer, __entry->now)
 );
 
 /**
@@ -108,7 +108,7 @@ TRACE_EVENT(timer_expire_exit,
 		__entry->timer	= timer;
 	),
 
-	TP_printk("timer %p", __entry->timer)
+	TP_printk("timer=%p", __entry->timer)
 );
 
 /**
@@ -129,7 +129,7 @@ TRACE_EVENT(timer_cancel,
 		__entry->timer	= timer;
 	),
 
-	TP_printk("timer %p", __entry->timer)
+	TP_printk("timer=%p", __entry->timer)
 );
 
 /**
@@ -140,24 +140,24 @@ TRACE_EVENT(timer_cancel,
  */
 TRACE_EVENT(hrtimer_init,
 
-	TP_PROTO(struct hrtimer *timer, clockid_t clockid,
+	TP_PROTO(struct hrtimer *hrtimer, clockid_t clockid,
 		 enum hrtimer_mode mode),
 
-	TP_ARGS(timer, clockid, mode),
+	TP_ARGS(hrtimer, clockid, mode),
 
 	TP_STRUCT__entry(
-		__field( void *,		timer		)
+		__field( void *,		hrtimer		)
 		__field( clockid_t,		clockid		)
 		__field( enum hrtimer_mode,	mode		)
 	),
 
 	TP_fast_assign(
-		__entry->timer		= timer;
+		__entry->hrtimer	= hrtimer;
 		__entry->clockid	= clockid;
 		__entry->mode		= mode;
 	),
 
-	TP_printk("hrtimer %p, clockid %s, mode %s", __entry->timer,
+	TP_printk("hrtimer=%p clockid=%s mode=%s", __entry->hrtimer,
 		  __entry->clockid == CLOCK_REALTIME ?
 			"CLOCK_REALTIME" : "CLOCK_MONOTONIC",
 		  __entry->mode == HRTIMER_MODE_ABS ?
@@ -170,26 +170,26 @@ TRACE_EVENT(hrtimer_init,
  */
 TRACE_EVENT(hrtimer_start,
 
-	TP_PROTO(struct hrtimer *timer),
+	TP_PROTO(struct hrtimer *hrtimer),
 
-	TP_ARGS(timer),
+	TP_ARGS(hrtimer),
 
 	TP_STRUCT__entry(
-		__field( void *,	timer		)
+		__field( void *,	hrtimer		)
 		__field( void *,	function	)
 		__field( s64,		expires		)
 		__field( s64,		softexpires	)
 	),
 
 	TP_fast_assign(
-		__entry->timer		= timer;
-		__entry->function	= timer->function;
-		__entry->expires	= hrtimer_get_expires(timer).tv64;
-		__entry->softexpires	= hrtimer_get_softexpires(timer).tv64;
+		__entry->hrtimer	= hrtimer;
+		__entry->function	= hrtimer->function;
+		__entry->expires	= hrtimer_get_expires(hrtimer).tv64;
+		__entry->softexpires	= hrtimer_get_softexpires(hrtimer).tv64;
 	),
 
-	TP_printk("hrtimer %p, func %pf, expires %llu, softexpires %llu",
-		  __entry->timer, __entry->function,
+	TP_printk("hrtimer=%p function=%pf expires=%llu softexpires=%llu",
+		  __entry->hrtimer, __entry->function,
 		  (unsigned long long)ktime_to_ns((ktime_t) {
 				  .tv64 = __entry->expires }),
 		  (unsigned long long)ktime_to_ns((ktime_t) {
@@ -206,23 +206,22 @@ TRACE_EVENT(hrtimer_start,
  */
 TRACE_EVENT(hrtimer_expire_entry,
 
-	TP_PROTO(struct hrtimer *timer, ktime_t *now),
+	TP_PROTO(struct hrtimer *hrtimer, ktime_t *now),
 
-	TP_ARGS(timer, now),
+	TP_ARGS(hrtimer, now),
 
 	TP_STRUCT__entry(
-		__field( void *,	timer	)
+		__field( void *,	hrtimer	)
 		__field( s64,		now	)
 	),
 
 	TP_fast_assign(
-		__entry->timer	= timer;
-		__entry->now	= now->tv64;
+		__entry->hrtimer	= hrtimer;
+		__entry->now		= now->tv64;
 	),
 
-	TP_printk("hrtimer %p, now %llu", __entry->timer,
-		  (unsigned long long)ktime_to_ns((ktime_t) {
-				  .tv64 = __entry->now }))
+	TP_printk("hrtimer=%p now=%llu", __entry->hrtimer,
+		  (unsigned long long)ktime_to_ns((ktime_t) { .tv64 = __entry->now }))
  );
 
 /**
@@ -234,40 +233,40 @@ TRACE_EVENT(hrtimer_expire_entry,
  */
 TRACE_EVENT(hrtimer_expire_exit,
 
-	TP_PROTO(struct hrtimer *timer),
+	TP_PROTO(struct hrtimer *hrtimer),
 
-	TP_ARGS(timer),
+	TP_ARGS(hrtimer),
 
 	TP_STRUCT__entry(
-		__field( void *,	timer	)
+		__field( void *,	hrtimer	)
 	),
 
 	TP_fast_assign(
-		__entry->timer	= timer;
+		__entry->hrtimer	= hrtimer;
 	),
 
-	TP_printk("hrtimer %p", __entry->timer)
+	TP_printk("hrtimer=%p", __entry->hrtimer)
 );
 
 /**
  * hrtimer_cancel - called when the hrtimer is canceled
- * @timer:	pointer to struct hrtimer
+ * @hrtimer:	pointer to struct hrtimer
  */
 TRACE_EVENT(hrtimer_cancel,
 
-	TP_PROTO(struct hrtimer *timer),
+	TP_PROTO(struct hrtimer *hrtimer),
 
-	TP_ARGS(timer),
+	TP_ARGS(hrtimer),
 
 	TP_STRUCT__entry(
-		__field( void *,	timer	)
+		__field( void *,	hrtimer	)
 	),
 
 	TP_fast_assign(
-		__entry->timer	= timer;
+		__entry->hrtimer	= hrtimer;
 	),
 
-	TP_printk("hrtimer %p", __entry->timer)
+	TP_printk("hrtimer=%p", __entry->hrtimer)
 );
 
 /**
@@ -302,7 +301,7 @@ TRACE_EVENT(itimer_state,
 		__entry->interval_usec	= value->it_interval.tv_usec;
 	),
 
-	TP_printk("which %d, expires %lu, it_value %lu.%lu, it_interval %lu.%lu",
+	TP_printk("which=%d expires=%lu it_value=%lu.%lu it_interval=%lu.%lu",
 		  __entry->which, __entry->expires,
 		  __entry->value_sec, __entry->value_usec,
 		  __entry->interval_sec, __entry->interval_usec)
@@ -332,7 +331,7 @@ TRACE_EVENT(itimer_expire,
 		__entry->pid	= pid_nr(pid);
 	),
 
-	    TP_printk("which %d, pid %d, now %lu", __entry->which,
+	    TP_printk("which=%d pid=%d now=%lu", __entry->which,
 		      (int) __entry->pid, __entry->now)
 );
 

include/trace/events/workqueue.h

@@ -8,7 +8,7 @@
 #include <linux/sched.h>
 #include <linux/tracepoint.h>
 
-TRACE_EVENT(workqueue_insertion,
+DECLARE_EVENT_CLASS(workqueue,
 
 	TP_PROTO(struct task_struct *wq_thread, struct work_struct *work),
 
@@ -30,26 +30,18 @@ TRACE_EVENT(workqueue_insertion,
 		__entry->thread_pid, __entry->func)
 );
 
-TRACE_EVENT(workqueue_execution,
+DEFINE_EVENT(workqueue, workqueue_insertion,
 
 	TP_PROTO(struct task_struct *wq_thread, struct work_struct *work),
 
-	TP_ARGS(wq_thread, work),
+	TP_ARGS(wq_thread, work)
+);
 
-	TP_STRUCT__entry(
-		__array(char,		thread_comm,	TASK_COMM_LEN)
-		__field(pid_t,		thread_pid)
-		__field(work_func_t,	func)
-	),
+DEFINE_EVENT(workqueue, workqueue_execution,
 
-	TP_fast_assign(
-		memcpy(__entry->thread_comm, wq_thread->comm, TASK_COMM_LEN);
-		__entry->thread_pid	= wq_thread->pid;
-		__entry->func		= work->func;
-	),
+	TP_PROTO(struct task_struct *wq_thread, struct work_struct *work),
 
-	TP_printk("thread=%s:%d func=%pf", __entry->thread_comm,
-		__entry->thread_pid, __entry->func)
+	TP_ARGS(wq_thread, work)
 );
 
 /* Trace the creation of one workqueue thread on a cpu */

include/trace/ftrace.h

@@ -18,6 +18,26 @@
 
 #include <linux/ftrace_event.h>
 
+/*
+ * DECLARE_EVENT_CLASS can be used to add a generic function
+ * handlers for events. That is, if all events have the same
+ * parameters and just have distinct trace points.
+ * Each tracepoint can be defined with DEFINE_EVENT and that
+ * will map the DECLARE_EVENT_CLASS to the tracepoint.
+ *
+ * TRACE_EVENT is a one to one mapping between tracepoint and template.
+ */
+#undef TRACE_EVENT
+#define TRACE_EVENT(name, proto, args, tstruct, assign, print) \
+	DECLARE_EVENT_CLASS(name,			       \
+			     PARAMS(proto),		       \
+			     PARAMS(args),		       \
+			     PARAMS(tstruct),		       \
+			     PARAMS(assign),		       \
+			     PARAMS(print));		       \
+	DEFINE_EVENT(name, name, PARAMS(proto), PARAMS(args));
+
+
 #undef __field
 #define __field(type, item)		type	item;
 
@@ -36,15 +56,21 @@
 #undef TP_STRUCT__entry
 #define TP_STRUCT__entry(args...) args
 
-#undef TRACE_EVENT
-#define TRACE_EVENT(name, proto, args, tstruct, assign, print)	\
-	struct ftrace_raw_##name {				\
-		struct trace_entry	ent;			\
-		tstruct						\
-		char			__data[0];		\
-	};							\
+#undef DECLARE_EVENT_CLASS
+#define DECLARE_EVENT_CLASS(name, proto, args, tstruct, assign, print)	\
+	struct ftrace_raw_##name {					\
+		struct trace_entry	ent;				\
+		tstruct							\
+		char			__data[0];			\
+	};
+#undef DEFINE_EVENT
+#define DEFINE_EVENT(template, name, proto, args)	\
 	static struct ftrace_event_call event_##name
 
+#undef DEFINE_EVENT_PRINT
+#define DEFINE_EVENT_PRINT(template, name, proto, args, print)	\
+	DEFINE_EVENT(template, name, PARAMS(proto), PARAMS(args))
+
 #undef __cpparg
 #define __cpparg(arg...) arg
 
@@ -89,12 +115,19 @@
 #undef __string
 #define __string(item, src) __dynamic_array(char, item, -1)
 
-#undef TRACE_EVENT
-#define TRACE_EVENT(call, proto, args, tstruct, assign, print)		\
+#undef DECLARE_EVENT_CLASS
+#define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print)	\
 	struct ftrace_data_offsets_##call {				\
 		tstruct;						\
 	};
 
+#undef DEFINE_EVENT
+#define DEFINE_EVENT(template, name, proto, args)
+
+#undef DEFINE_EVENT_PRINT
+#define DEFINE_EVENT_PRINT(template, name, proto, args, print)	\
+	DEFINE_EVENT(template, name, PARAMS(proto), PARAMS(args))
+
 #include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
 
 /*
@@ -120,9 +153,10 @@
 #undef __field
 #define __field(type, item)					\
 	ret = trace_seq_printf(s, "\tfield:" #type " " #item ";\t"	\
-			       "offset:%u;\tsize:%u;\n",		\
+			       "offset:%u;\tsize:%u;\tsigned:%u;\n",	\
 			       (unsigned int)offsetof(typeof(field), item), \
-			       (unsigned int)sizeof(field.item));	\
+			       (unsigned int)sizeof(field.item),	\
+			       (unsigned int)is_signed_type(type));	\
 	if (!ret)							\
 		return 0;
 
@@ -132,19 +166,21 @@
 #undef __array
 #define __array(type, item, len)						\
 	ret = trace_seq_printf(s, "\tfield:" #type " " #item "[" #len "];\t"	\
-			       "offset:%u;\tsize:%u;\n",		\
+			       "offset:%u;\tsize:%u;\tsigned:%u;\n",	\
 			       (unsigned int)offsetof(typeof(field), item), \
-			       (unsigned int)sizeof(field.item));	\
+			       (unsigned int)sizeof(field.item),	\
+			       (unsigned int)is_signed_type(type));	\
 	if (!ret)							\
 		return 0;
 
 #undef __dynamic_array
 #define __dynamic_array(type, item, len)				       \
 	ret = trace_seq_printf(s, "\tfield:__data_loc " #type "[] " #item ";\t"\
-			       "offset:%u;\tsize:%u;\n",		       \
+			       "offset:%u;\tsize:%u;\tsigned:%u;\n",	       \
 			       (unsigned int)offsetof(typeof(field),	       \
 					__data_loc_##item),		       \
-			       (unsigned int)sizeof(field.__data_loc_##item)); \
+			       (unsigned int)sizeof(field.__data_loc_##item), \
+			       (unsigned int)is_signed_type(type));	\
 	if (!ret)							       \
 		return 0;
 
@@ -167,17 +203,50 @@
 #undef TP_perf_assign
 #define TP_perf_assign(args...)
 
-#undef TRACE_EVENT
-#define TRACE_EVENT(call, proto, args, tstruct, func, print)		\
+#undef DECLARE_EVENT_CLASS
+#define DECLARE_EVENT_CLASS(call, proto, args, tstruct, func, print)	\
 static int								\
-ftrace_format_##call(struct ftrace_event_call *unused,			\
-		      struct trace_seq *s)				\
+ftrace_format_setup_##call(struct ftrace_event_call *unused,		\
+			   struct trace_seq *s)				\
 {									\
 	struct ftrace_raw_##call field __attribute__((unused));		\
 	int ret = 0;							\
 									\
 	tstruct;							\
 									\
+	return ret;							\
+}									\
+									\
+static int								\
+ftrace_format_##call(struct ftrace_event_call *unused,			\
+		     struct trace_seq *s)				\
+{									\
+	int ret = 0;							\
+									\
+	ret = ftrace_format_setup_##call(unused, s);			\
+	if (!ret)							\
+		return ret;						\
+									\
+	ret = trace_seq_printf(s, "\nprint fmt: " print);		\
+									\
+	return ret;							\
+}
+
+#undef DEFINE_EVENT
+#define DEFINE_EVENT(template, name, proto, args)
+
+#undef DEFINE_EVENT_PRINT
+#define DEFINE_EVENT_PRINT(template, name, proto, args, print)		\
+static int								\
+ftrace_format_##name(struct ftrace_event_call *unused,			\
+		      struct trace_seq *s)				\
+{									\
+	int ret = 0;							\
+									\
+	ret = ftrace_format_setup_##template(unused, s);		\
+	if (!ret)							\
+		return ret;						\
+									\
 	trace_seq_printf(s, "\nprint fmt: " print);			\
 									\
 	return ret;							\
@@ -252,15 +321,57 @@ ftrace_format_##call(struct ftrace_event_call *unused,			\
 		ftrace_print_symbols_seq(p, value, symbols);		\
 	})
 
-#undef TRACE_EVENT
-#define TRACE_EVENT(call, proto, args, tstruct, assign, print)		\
+#undef DECLARE_EVENT_CLASS
+#define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print)	\
 static enum print_line_t						\
-ftrace_raw_output_##call(struct trace_iterator *iter, int flags)	\
+ftrace_raw_output_id_##call(int event_id, const char *name,		\
+			    struct trace_iterator *iter, int flags)	\
 {									\
 	struct trace_seq *s = &iter->seq;				\
 	struct ftrace_raw_##call *field;				\
 	struct trace_entry *entry;					\
 	struct trace_seq *p;						\
+	int ret;							\
+									\
+	entry = iter->ent;						\
+									\
+	if (entry->type != event_id) {					\
+		WARN_ON_ONCE(1);					\
+		return TRACE_TYPE_UNHANDLED;				\
+	}								\
+									\
+	field = (typeof(field))entry;					\
+									\
+	p = &get_cpu_var(ftrace_event_seq);				\
+	trace_seq_init(p);						\
+	ret = trace_seq_printf(s, "%s: ", name);			\
+	if (ret)							\
+		ret = trace_seq_printf(s, print);			\
+	put_cpu();							\
+	if (!ret)							\
+		return TRACE_TYPE_PARTIAL_LINE;				\
+									\
+	return TRACE_TYPE_HANDLED;					\
+}
+
+#undef DEFINE_EVENT
+#define DEFINE_EVENT(template, name, proto, args)			\
+static enum print_line_t						\
+ftrace_raw_output_##name(struct trace_iterator *iter, int flags)	\
+{									\
+	return ftrace_raw_output_id_##template(event_##name.id,		\
+					       #name, iter, flags);	\
+}
+
+#undef DEFINE_EVENT_PRINT
+#define DEFINE_EVENT_PRINT(template, call, proto, args, print)		\
+static enum print_line_t						\
+ftrace_raw_output_##call(struct trace_iterator *iter, int flags)	\
+{									\
+	struct trace_seq *s = &iter->seq;				\
+	struct ftrace_raw_##template *field;				\
+	struct trace_entry *entry;					\
+	struct trace_seq *p;						\
 	int ret;							\
 									\
 	entry = iter->ent;						\
@@ -274,14 +385,16 @@ ftrace_raw_output_##call(struct trace_iterator *iter, int flags)	\
 									\
 	p = &get_cpu_var(ftrace_event_seq);				\
 	trace_seq_init(p);						\
-	ret = trace_seq_printf(s, #call ": " print);			\
+	ret = trace_seq_printf(s, "%s: ", #call);			\
+	if (ret)							\
+		ret = trace_seq_printf(s, print);			\
 	put_cpu();							\
 	if (!ret)							\
 		return TRACE_TYPE_PARTIAL_LINE;				\
 									\
 	return TRACE_TYPE_HANDLED;					\
 }
-	
+
 #include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
 
 #undef __field_ext
@@ -315,8 +428,8 @@ ftrace_raw_output_##call(struct trace_iterator *iter, int flags)	\
 #undef __string
 #define __string(item, src) __dynamic_array(char, item, -1)
 
-#undef TRACE_EVENT
-#define TRACE_EVENT(call, proto, args, tstruct, func, print)		\
+#undef DECLARE_EVENT_CLASS
+#define DECLARE_EVENT_CLASS(call, proto, args, tstruct, func, print)	\
 static int								\
 ftrace_define_fields_##call(struct ftrace_event_call *event_call)	\
 {									\
@@ -332,6 +445,13 @@ ftrace_define_fields_##call(struct ftrace_event_call *event_call)	\
 	return ret;							\
 }
 
+#undef DEFINE_EVENT
+#define DEFINE_EVENT(template, name, proto, args)
+
+#undef DEFINE_EVENT_PRINT
+#define DEFINE_EVENT_PRINT(template, name, proto, args, print)	\
+	DEFINE_EVENT(template, name, PARAMS(proto), PARAMS(args))
+
 #include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
 
 /*
@@ -358,10 +478,10 @@ ftrace_define_fields_##call(struct ftrace_event_call *event_call)	\
 	__data_size += (len) * sizeof(type);
 
 #undef __string
-#define __string(item, src) __dynamic_array(char, item, strlen(src) + 1)       \
+#define __string(item, src) __dynamic_array(char, item, strlen(src) + 1)
 
-#undef TRACE_EVENT
-#define TRACE_EVENT(call, proto, args, tstruct, assign, print)		\
+#undef DECLARE_EVENT_CLASS
+#define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print)	\
 static inline int ftrace_get_offsets_##call(				\
 	struct ftrace_data_offsets_##call *__data_offsets, proto)       \
 {									\
@@ -373,6 +493,13 @@ static inline int ftrace_get_offsets_##call(				\
 	return __data_size;						\
 }
 
+#undef DEFINE_EVENT
+#define DEFINE_EVENT(template, name, proto, args)
+
+#undef DEFINE_EVENT_PRINT
+#define DEFINE_EVENT_PRINT(template, name, proto, args, print)	\
+	DEFINE_EVENT(template, name, PARAMS(proto), PARAMS(args))
+
 #include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
 
 #ifdef CONFIG_EVENT_PROFILE
@@ -394,21 +521,28 @@ static inline int ftrace_get_offsets_##call(				\
  *
  */
 
-#undef TRACE_EVENT
-#define TRACE_EVENT(call, proto, args, tstruct, assign, print)		\
+#undef DECLARE_EVENT_CLASS
+#define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print)
+
+#undef DEFINE_EVENT
+#define DEFINE_EVENT(template, name, proto, args)			\
 									\
-static void ftrace_profile_##call(proto);				\
+static void ftrace_profile_##name(proto);				\
 									\
-static int ftrace_profile_enable_##call(void)				\
+static int ftrace_profile_enable_##name(struct ftrace_event_call *unused)\
 {									\
-	return register_trace_##call(ftrace_profile_##call);		\
+	return register_trace_##name(ftrace_profile_##name);		\
 }									\
 									\
-static void ftrace_profile_disable_##call(void)				\
+static void ftrace_profile_disable_##name(struct ftrace_event_call *unused)\
 {									\
-	unregister_trace_##call(ftrace_profile_##call);			\
+	unregister_trace_##name(ftrace_profile_##name);			\
 }
 
+#undef DEFINE_EVENT_PRINT
+#define DEFINE_EVENT_PRINT(template, name, proto, args, print)	\
+	DEFINE_EVENT(template, name, PARAMS(proto), PARAMS(args))
+
 #include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
 
 #endif
@@ -423,7 +557,7 @@ static void ftrace_profile_disable_##call(void)				\
  *	event_trace_printk(_RET_IP_, "<call>: " <fmt>);
  * }
  *
- * static int ftrace_reg_event_<call>(void)
+ * static int ftrace_reg_event_<call>(struct ftrace_event_call *unused)
  * {
  *	int ret;
  *
@@ -434,7 +568,7 @@ static void ftrace_profile_disable_##call(void)				\
  *	return ret;
  * }
  *
- * static void ftrace_unreg_event_<call>(void)
+ * static void ftrace_unreg_event_<call>(struct ftrace_event_call *unused)
  * {
  *	unregister_trace_<call>(ftrace_event_<call>);
  * }
@@ -469,7 +603,7 @@ static void ftrace_profile_disable_##call(void)				\
  *	trace_current_buffer_unlock_commit(buffer, event, irq_flags, pc);
  * }
  *
- * static int ftrace_raw_reg_event_<call>(void)
+ * static int ftrace_raw_reg_event_<call>(struct ftrace_event_call *unused)
  * {
  *	int ret;
  *
@@ -480,7 +614,7 @@ static void ftrace_profile_disable_##call(void)				\
  *	return ret;
  * }
  *
- * static void ftrace_unreg_event_<call>(void)
+ * static void ftrace_unreg_event_<call>(struct ftrace_event_call *unused)
  * {
  *	unregister_trace_<call>(ftrace_raw_event_<call>);
  * }
@@ -489,7 +623,7 @@ static void ftrace_profile_disable_##call(void)				\
  *	.trace			= ftrace_raw_output_<call>, <-- stage 2
  * };
  *
- * static int ftrace_raw_init_event_<call>(void)
+ * static int ftrace_raw_init_event_<call>(struct ftrace_event_call *unused)
  * {
  *	int id;
  *
@@ -547,15 +681,13 @@ static void ftrace_profile_disable_##call(void)				\
 #define __assign_str(dst, src)						\
 	strcpy(__get_str(dst), src);
 
-#undef TRACE_EVENT
-#define TRACE_EVENT(call, proto, args, tstruct, assign, print)		\
+#undef DECLARE_EVENT_CLASS
+#define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print)	\
 									\
-static struct ftrace_event_call event_##call;				\
-									\
-static void ftrace_raw_event_##call(proto)				\
+static void ftrace_raw_event_id_##call(struct ftrace_event_call *event_call, \
+				       proto)				\
 {									\
 	struct ftrace_data_offsets_##call __maybe_unused __data_offsets;\
-	struct ftrace_event_call *event_call = &event_##call;		\
 	struct ring_buffer_event *event;				\
 	struct ftrace_raw_##call *entry;				\
 	struct ring_buffer *buffer;					\
@@ -569,7 +701,7 @@ static void ftrace_raw_event_##call(proto)				\
 	__data_size = ftrace_get_offsets_##call(&__data_offsets, args); \
 									\
 	event = trace_current_buffer_lock_reserve(&buffer,		\
-				 event_##call.id,			\
+				 event_call->id,			\
 				 sizeof(*entry) + __data_size,		\
 				 irq_flags, pc);			\
 	if (!event)							\
@@ -584,9 +716,17 @@ static void ftrace_raw_event_##call(proto)				\
 	if (!filter_current_check_discard(buffer, event_call, entry, event)) \
 		trace_nowake_buffer_unlock_commit(buffer,		\
 						  event, irq_flags, pc); \
+}
+
+#undef DEFINE_EVENT
+#define DEFINE_EVENT(template, call, proto, args)			\
+									\
+static void ftrace_raw_event_##call(proto)				\
+{									\
+	ftrace_raw_event_id_##template(&event_##call, args);		\
 }									\
 									\
-static int ftrace_raw_reg_event_##call(void *ptr)			\
+static int ftrace_raw_reg_event_##call(struct ftrace_event_call *unused)\
 {									\
 	int ret;							\
 									\
@@ -597,7 +737,7 @@ static int ftrace_raw_reg_event_##call(void *ptr)			\
 	return ret;							\
 }									\
 									\
-static void ftrace_raw_unreg_event_##call(void *ptr)			\
+static void ftrace_raw_unreg_event_##call(struct ftrace_event_call *unused)\
 {									\
 	unregister_trace_##call(ftrace_raw_event_##call);		\
 }									\
@@ -606,7 +746,7 @@ static struct trace_event ftrace_event_type_##call = {			\
 	.trace			= ftrace_raw_output_##call,		\
 };									\
 									\
-static int ftrace_raw_init_event_##call(void)				\
+static int ftrace_raw_init_event_##call(struct ftrace_event_call *unused)\
 {									\
 	int id;								\
 									\
@@ -616,7 +756,36 @@ static int ftrace_raw_init_event_##call(void)				\
 	event_##call.id = id;						\
 	INIT_LIST_HEAD(&event_##call.fields);				\
 	return 0;							\
-}									\
+}
+
+#undef DEFINE_EVENT_PRINT
+#define DEFINE_EVENT_PRINT(template, name, proto, args, print)	\
+	DEFINE_EVENT(template, name, PARAMS(proto), PARAMS(args))
+
+#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
+
+#undef DECLARE_EVENT_CLASS
+#define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print)
+
+#undef DEFINE_EVENT
+#define DEFINE_EVENT(template, call, proto, args)			\
+									\
+static struct ftrace_event_call __used					\
+__attribute__((__aligned__(4)))						\
+__attribute__((section("_ftrace_events"))) event_##call = {		\
+	.name			= #call,				\
+	.system			= __stringify(TRACE_SYSTEM),		\
+	.event			= &ftrace_event_type_##call,		\
+	.raw_init		= ftrace_raw_init_event_##call,		\
+	.regfunc		= ftrace_raw_reg_event_##call,		\
+	.unregfunc		= ftrace_raw_unreg_event_##call,	\
+	.show_format		= ftrace_format_##template,		\
+	.define_fields		= ftrace_define_fields_##template,	\
+	_TRACE_PROFILE_INIT(call)					\
+}
+
+#undef DEFINE_EVENT_PRINT
+#define DEFINE_EVENT_PRINT(template, call, proto, args, print)		\
 									\
 static struct ftrace_event_call __used					\
 __attribute__((__aligned__(4)))						\
@@ -628,7 +797,7 @@ __attribute__((section("_ftrace_events"))) event_##call = {		\
 	.regfunc		= ftrace_raw_reg_event_##call,		\
 	.unregfunc		= ftrace_raw_unreg_event_##call,	\
 	.show_format		= ftrace_format_##call,			\
-	.define_fields		= ftrace_define_fields_##call,		\
+	.define_fields		= ftrace_define_fields_##template,	\
 	_TRACE_PROFILE_INIT(call)					\
 }
 
@@ -646,6 +815,7 @@ __attribute__((section("_ftrace_events"))) event_##call = {		\
  *	struct ftrace_event_call *event_call = &event_<call>;
  *	extern void perf_tp_event(int, u64, u64, void *, int);
  *	struct ftrace_raw_##call *entry;
+ *	struct perf_trace_buf *trace_buf;
  *	u64 __addr = 0, __count = 1;
  *	unsigned long irq_flags;
  *	struct trace_entry *ent;
@@ -670,14 +840,25 @@ __attribute__((section("_ftrace_events"))) event_##call = {		\
  *	__cpu = smp_processor_id();
  *
  *	if (in_nmi())
- *		raw_data = rcu_dereference(trace_profile_buf_nmi);
+ *		trace_buf = rcu_dereference(perf_trace_buf_nmi);
  *	else
- *		raw_data = rcu_dereference(trace_profile_buf);
+ *		trace_buf = rcu_dereference(perf_trace_buf);
  *
- *	if (!raw_data)
+ *	if (!trace_buf)
  *		goto end;
  *
- *	raw_data = per_cpu_ptr(raw_data, __cpu);
+ *	trace_buf = per_cpu_ptr(trace_buf, __cpu);
+ *
+ * 	// Avoid recursion from perf that could mess up the buffer
+ * 	if (trace_buf->recursion++)
+ *		goto end_recursion;
+ *
+ * 	raw_data = trace_buf->buf;
+ *
+ *	// Make recursion update visible before entering perf_tp_event
+ *	// so that we protect from perf recursions.
+ *
+ *	barrier();
  *
  *	//zero dead bytes from alignment to avoid stack leak to userspace:
  *	*(u64 *)(&raw_data[__entry_size - sizeof(u64)]) = 0ULL;
@@ -704,21 +885,26 @@ __attribute__((section("_ftrace_events"))) event_##call = {		\
 #undef __perf_count
 #define __perf_count(c) __count = (c)
 
-#undef TRACE_EVENT
-#define TRACE_EVENT(call, proto, args, tstruct, assign, print)		\
-static void ftrace_profile_##call(proto)				\
+#undef DECLARE_EVENT_CLASS
+#define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print)	\
+static void								\
+ftrace_profile_templ_##call(struct ftrace_event_call *event_call,	\
+			    proto)					\
 {									\
 	struct ftrace_data_offsets_##call __maybe_unused __data_offsets;\
-	struct ftrace_event_call *event_call = &event_##call;		\
-	extern void perf_tp_event(int, u64, u64, void *, int);	\
+	extern int perf_swevent_get_recursion_context(void);		\
+	extern void perf_swevent_put_recursion_context(int rctx);	\
+	extern void perf_tp_event(int, u64, u64, void *, int);		\
 	struct ftrace_raw_##call *entry;				\
 	u64 __addr = 0, __count = 1;					\
 	unsigned long irq_flags;					\
 	struct trace_entry *ent;					\
 	int __entry_size;						\
 	int __data_size;						\
+	char *trace_buf;						\
 	char *raw_data;							\
 	int __cpu;							\
+	int rctx;							\
 	int pc;								\
 									\
 	pc = preempt_count();						\
@@ -733,17 +919,22 @@ static void ftrace_profile_##call(proto)				\
 		return;							\
 									\
 	local_irq_save(irq_flags);					\
+									\
+	rctx = perf_swevent_get_recursion_context();			\
+	if (rctx < 0)							\
+		goto end_recursion;					\
+									\
 	__cpu = smp_processor_id();					\
 									\
 	if (in_nmi())							\
-		raw_data = rcu_dereference(trace_profile_buf_nmi);		\
+		trace_buf = rcu_dereference(perf_trace_buf_nmi);	\
 	else								\
-		raw_data = rcu_dereference(trace_profile_buf);		\
+		trace_buf = rcu_dereference(perf_trace_buf);		\
 									\
-	if (!raw_data)							\
+	if (!trace_buf)							\
 		goto end;						\
 									\
-	raw_data = per_cpu_ptr(raw_data, __cpu);			\
+	raw_data = per_cpu_ptr(trace_buf, __cpu);			\
 									\
 	*(u64 *)(&raw_data[__entry_size - sizeof(u64)]) = 0ULL;		\
 	entry = (struct ftrace_raw_##call *)raw_data;			\
@@ -759,10 +950,25 @@ static void ftrace_profile_##call(proto)				\
 			     __entry_size);				\
 									\
 end:									\
+	perf_swevent_put_recursion_context(rctx);			\
+end_recursion:								\
 	local_irq_restore(irq_flags);					\
 									\
 }
 
+#undef DEFINE_EVENT
+#define DEFINE_EVENT(template, call, proto, args)		\
+static void ftrace_profile_##call(proto)			\
+{								\
+	struct ftrace_event_call *event_call = &event_##call;	\
+								\
+	ftrace_profile_templ_##template(event_call, args);	\
+}
+
+#undef DEFINE_EVENT_PRINT
+#define DEFINE_EVENT_PRINT(template, name, proto, args, print)	\
+	DEFINE_EVENT(template, name, PARAMS(proto), PARAMS(args))
+
 #include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
 #endif /* CONFIG_EVENT_PROFILE */