hw-breakpoints: Rewrite the hw-breakpoints layer on top of perf events

This patch rebase the implementation of the breakpoints API on top of
perf events instances.

Each breakpoints are now perf events that handle the
register scheduling, thread/cpu attachment, etc..

The new layering is now made as follows:

       ptrace       kgdb      ftrace   perf syscall
          \          |          /         /
           \         |         /         /
                                        /
            Core breakpoint API        /
                                      /
                     |               /
                     |              /

              Breakpoints perf events

                     |
                     |

               Breakpoints PMU ---- Debug Register constraints handling
                                    (Part of core breakpoint API)
                     |
                     |

             Hardware debug registers

Reasons of this rewrite:

- Use the centralized/optimized pmu registers scheduling,
  implying an easier arch integration
- More powerful register handling: perf attributes (pinned/flexible
  events, exclusive/non-exclusive, tunable period, etc...)

Impact:

- New perf ABI: the hardware breakpoints counters
- Ptrace breakpoints setting remains tricky and still needs some per
  thread breakpoints references.

Todo (in the order):

- Support breakpoints perf counter events for perf tools (ie: implement
  perf_bpcounter_event())
- Support from perf tools

Changes in v2:

- Follow the perf "event " rename
- The ptrace regression have been fixed (ptrace breakpoint perf events
  weren't released when a task ended)
- Drop the struct hw_breakpoint and store generic fields in
  perf_event_attr.
- Separate core and arch specific headers, drop
  asm-generic/hw_breakpoint.h and create linux/hw_breakpoint.h
- Use new generic len/type for breakpoint
- Handle off case: when breakpoints api is not supported by an arch

Changes in v3:

- Fix broken CONFIG_KVM, we need to propagate the breakpoint api
  changes to kvm when we exit the guest and restore the bp registers
  to the host.

Changes in v4:

- Drop the hw_breakpoint_restore() stub as it is only used by KVM
- EXPORT_SYMBOL_GPL hw_breakpoint_restore() as KVM can be built as a
  module
- Restore the breakpoints unconditionally on kvm guest exit:
  TIF_DEBUG_THREAD doesn't anymore cover every cases of running
  breakpoints and vcpu->arch.switch_db_regs might not always be
  set when the guest used debug registers.
  (Waiting for a reliable optimization)

Changes in v5:

- Split-up the asm-generic/hw-breakpoint.h moving to
  linux/hw_breakpoint.h into a separate patch
- Optimize the breakpoints restoring while switching from kvm guest
  to host. We only want to restore the state if we have active
  breakpoints to the host, otherwise we don't care about messed-up
  address registers.
- Add asm/hw_breakpoint.h to Kbuild
- Fix bad breakpoint type in trace_selftest.c

Changes in v6:

- Fix wrong header inclusion in trace.h (triggered a build
  error with CONFIG_FTRACE_SELFTEST

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Prasad <prasad@linux.vnet.ibm.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Jan Kiszka <jan.kiszka@web.de>
Cc: Jiri Slaby <jirislaby@gmail.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Avi Kivity <avi@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Masami Hiramatsu <mhiramat@redhat.com>
Cc: Paul Mundt <lethal@linux-sh.org>

2 files changed, 144 insertions, 125 deletions

diff --git a/include/linux/hw_breakpoint.h b/include/linux/hw_breakpoint.h
index 61ccc8f17ea..7eba9b92e5f 100644
--- a/include/linux/hw_breakpoint.h
+++ b/include/linux/hw_breakpoint.h
@@ -1,136 +1,131 @@
 #ifndef _LINUX_HW_BREAKPOINT_H
 #define _LINUX_HW_BREAKPOINT_H
 
+#include <linux/perf_event.h>
 
-#ifdef	__KERNEL__
-#include <linux/list.h>
-#include <linux/types.h>
-#include <linux/kallsyms.h>
-
-/**
- * struct hw_breakpoint - unified kernel/user-space hardware breakpoint
- * @triggered: callback invoked after target address access
- * @info: arch-specific breakpoint info (address, length, and type)
- *
- * %hw_breakpoint structures are the kernel's way of representing
- * hardware breakpoints.  These are data breakpoints
- * (also known as "watchpoints", triggered on data access), and the breakpoint's
- * target address can be located in either kernel space or user space.
- *
- * The breakpoint's address, length, and type are highly
- * architecture-specific.  The values are encoded in the @info field; you
- * specify them when registering the breakpoint.  To examine the encoded
- * values use hw_breakpoint_get_{kaddress,uaddress,len,type}(), declared
- * below.
- *
- * The address is specified as a regular kernel pointer (for kernel-space
- * breakponts) or as an %__user pointer (for user-space breakpoints).
- * With register_user_hw_breakpoint(), the address must refer to a
- * location in user space.  The breakpoint will be active only while the
- * requested task is running.  Conversely with
- * register_kernel_hw_breakpoint(), the address must refer to a location
- * in kernel space, and the breakpoint will be active on all CPUs
- * regardless of the current task.
- *
- * The length is the breakpoint's extent in bytes, which is subject to
- * certain limitations.  include/asm/hw_breakpoint.h contains macros
- * defining the available lengths for a specific architecture.  Note that
- * the address's alignment must match the length.  The breakpoint will
- * catch accesses to any byte in the range from address to address +
- * (length - 1).
- *
- * The breakpoint's type indicates the sort of access that will cause it
- * to trigger.  Possible values may include:
- *
- * 	%HW_BREAKPOINT_RW (triggered on read or write access),
- * 	%HW_BREAKPOINT_WRITE (triggered on write access), and
- * 	%HW_BREAKPOINT_READ (triggered on read access).
- *
- * Appropriate macros are defined in include/asm/hw_breakpoint.h; not all
- * possibilities are available on all architectures.  Execute breakpoints
- * must have length equal to the special value %HW_BREAKPOINT_LEN_EXECUTE.
- *
- * When a breakpoint gets hit, the @triggered callback is
- * invoked in_interrupt with a pointer to the %hw_breakpoint structure and the
- * processor registers.
- * Data breakpoints occur after the memory access has taken place.
- * Breakpoints are disabled during execution @triggered, to avoid
- * recursive traps and allow unhindered access to breakpointed memory.
- *
- * This sample code sets a breakpoint on pid_max and registers a callback
- * function for writes to that variable.  Note that it is not portable
- * as written, because not all architectures support HW_BREAKPOINT_LEN_4.
- *
- * ----------------------------------------------------------------------
- *
- * #include <asm/hw_breakpoint.h>
- *
- * struct hw_breakpoint my_bp;
- *
- * static void my_triggered(struct hw_breakpoint *bp, struct pt_regs *regs)
- * {
- * 	printk(KERN_DEBUG "Inside triggered routine of breakpoint exception\n");
- * 	dump_stack();
- *  	.......<more debugging output>........
- * }
- *
- * static struct hw_breakpoint my_bp;
- *
- * static int init_module(void)
- * {
- *	..........<do anything>............
- *	my_bp.info.type = HW_BREAKPOINT_WRITE;
- *	my_bp.info.len = HW_BREAKPOINT_LEN_4;
- *
- *	my_bp.installed = (void *)my_bp_installed;
- *
- *	rc = register_kernel_hw_breakpoint(&my_bp);
- *	..........<do anything>............
- * }
- *
- * static void cleanup_module(void)
- * {
- *	..........<do anything>............
- *	unregister_kernel_hw_breakpoint(&my_bp);
- *	..........<do anything>............
- * }
- *
- * ----------------------------------------------------------------------
- */
-struct hw_breakpoint {
-	void (*triggered)(struct hw_breakpoint *, struct pt_regs *);
-	struct arch_hw_breakpoint info;
+enum {
+	HW_BREAKPOINT_LEN_1 = 1,
+	HW_BREAKPOINT_LEN_2 = 2,
+	HW_BREAKPOINT_LEN_4 = 4,
+	HW_BREAKPOINT_LEN_8 = 8,
 };
 
-/*
- * len and type values are defined in include/asm/hw_breakpoint.h.
- * Available values vary according to the architecture.  On i386 the
- * possibilities are:
- *
- *	HW_BREAKPOINT_LEN_1
- *	HW_BREAKPOINT_LEN_2
- *	HW_BREAKPOINT_LEN_4
- *	HW_BREAKPOINT_RW
- *	HW_BREAKPOINT_READ
- *
- * On other architectures HW_BREAKPOINT_LEN_8 may be available, and the
- * 1-, 2-, and 4-byte lengths may be unavailable.  There also may be
- * HW_BREAKPOINT_WRITE.  You can use #ifdef to check at compile time.
- */
+enum {
+	HW_BREAKPOINT_R = 1,
+	HW_BREAKPOINT_W = 2,
+	HW_BREAKPOINT_X = 4,
+};
+
+static inline struct arch_hw_breakpoint *counter_arch_bp(struct perf_event *bp)
+{
+	return &bp->hw.info;
+}
+
+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;
+}
+
+#ifdef CONFIG_HAVE_HW_BREAKPOINT
+extern struct perf_event *
+register_user_hw_breakpoint(unsigned long addr,
+			    int len,
+			    int type,
+			    perf_callback_t triggered,
+			    struct task_struct *tsk,
+			    bool active);
+
+/* FIXME: only change from the attr, and don't unregister */
+extern struct perf_event *
+modify_user_hw_breakpoint(struct perf_event *bp,
+			  unsigned long addr,
+			  int len,
+			  int type,
+			  perf_callback_t triggered,
+			  struct task_struct *tsk,
+			  bool active);
 
-extern int register_user_hw_breakpoint(struct task_struct *tsk,
-					struct hw_breakpoint *bp);
-extern int modify_user_hw_breakpoint(struct task_struct *tsk,
-					struct hw_breakpoint *bp);
-extern void unregister_user_hw_breakpoint(struct task_struct *tsk,
-						struct hw_breakpoint *bp);
 /*
  * Kernel breakpoints are not associated with any particular thread.
  */
-extern int register_kernel_hw_breakpoint(struct hw_breakpoint *bp);
-extern void unregister_kernel_hw_breakpoint(struct hw_breakpoint *bp);
+extern struct perf_event *
+register_wide_hw_breakpoint_cpu(unsigned long addr,
+				int len,
+				int type,
+				perf_callback_t triggered,
+				int cpu,
+				bool active);
+
+extern struct perf_event **
+register_wide_hw_breakpoint(unsigned long addr,
+			    int len,
+			    int type,
+			    perf_callback_t triggered,
+			    bool active);
+
+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);
+
+#else /* !CONFIG_HAVE_HW_BREAKPOINT */
+
+static inline struct perf_event *
+register_user_hw_breakpoint(unsigned long addr,
+			    int len,
+			    int type,
+			    perf_callback_t triggered,
+			    struct task_struct *tsk,
+			    bool active)		{ return NULL; }
+static inline struct perf_event *
+modify_user_hw_breakpoint(struct perf_event *bp,
+			  unsigned long addr,
+			  int len,
+			  int type,
+			  perf_callback_t triggered,
+			  struct task_struct *tsk,
+			  bool active)			{ return NULL; }
+static inline struct perf_event *
+register_wide_hw_breakpoint_cpu(unsigned long addr,
+				int len,
+				int type,
+				perf_callback_t triggered,
+				int cpu,
+				bool active)		{ return NULL; }
+static inline struct perf_event **
+register_wide_hw_breakpoint(unsigned long addr,
+			    int len,
+			    int type,
+			    perf_callback_t triggered,
+			    bool active)		{ 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)	{ }
 
-extern unsigned int hbp_kernel_pos;
+#endif /* CONFIG_HAVE_HW_BREAKPOINT */
 
-#endif	/* __KERNEL__ */
-#endif	/* _LINUX_HW_BREAKPOINT_H */
+#endif /* _LINUX_HW_BREAKPOINT_H */
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 8d54e6d25ee..cead64ea6c1 100644
--- a/include/linux/perf_event.h
+++ b/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 */
 };
@@ -207,6 +212,15 @@ 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;
@@ -476,6 +490,11 @@ struct hw_perf_event {
 			atomic64_t	count;
 			struct hrtimer	hrtimer;
 		};
+#ifdef CONFIG_HAVE_HW_BREAKPOINT
+		union { /* breakpoint */
+			struct arch_hw_breakpoint	info;
+		};
+#endif
 	};
 	atomic64_t			prev_count;
 	u64				sample_period;
@@ -588,7 +607,7 @@ 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;
@@ -643,6 +662,8 @@ struct perf_event {
 
 	perf_callback_t			callback;
 
+	perf_callback_t			event_callback;
+
 #endif /* CONFIG_PERF_EVENTS */
 };
 
@@ -831,6 +852,7 @@ 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 : \
@@ -865,6 +887,8 @@ 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)		{ }