Merge branch 'x86/pebs' into x86-v28-for-linus-phase1

Conflicts:
	include/asm-x86/ds.h
Signed-off-by: Ingo Molnar <mingo@elte.hu>

arch/x86/Kconfig.cpu

@@ -418,3 +418,21 @@ config X86_MINIMUM_CPU_FAMILY
 config X86_DEBUGCTLMSR
 	def_bool y
 	depends on !(MK6 || MWINCHIPC6 || MWINCHIP2 || MWINCHIP3D || MCYRIXIII || M586MMX || M586TSC || M586 || M486 || M386)
+
+config X86_DS
+	bool "Debug Store support"
+	default y
+	help
+	  Add support for Debug Store.
+	  This allows the kernel to provide a memory buffer to the hardware
+	  to store various profiling and tracing events.
+
+config X86_PTRACE_BTS
+	bool "ptrace interface to Branch Trace Store"
+	default y
+	depends on (X86_DS && X86_DEBUGCTLMSR)
+	help
+	  Add a ptrace interface to allow collecting an execution trace
+	  of the traced task.
+	  This collects control flow changes in a (cyclic) buffer and allows
+	  debuggers to fill in the gaps and show an execution trace of the debuggee.

arch/x86/kernel/cpu/intel.c

@@ -222,10 +222,11 @@ static void __cpuinit init_intel(struct cpuinfo_x86 *c)
 			set_cpu_cap(c, X86_FEATURE_BTS);
 		if (!(l1 & (1<<12)))
 			set_cpu_cap(c, X86_FEATURE_PEBS);
+		ds_init_intel(c);
 	}
 
 	if (cpu_has_bts)
-		ds_init_intel(c);
+		ptrace_bts_init_intel(c);
 
 	/*
 	 * See if we have a good local APIC by checking for buggy Pentia,

arch/x86/kernel/process_32.c

@@ -277,6 +277,14 @@ void exit_thread(void)
 		tss->x86_tss.io_bitmap_base = INVALID_IO_BITMAP_OFFSET;
 		put_cpu();
 	}
+#ifdef CONFIG_X86_DS
+	/* Free any DS contexts that have not been properly released. */
+	if (unlikely(current->thread.ds_ctx)) {
+		/* we clear debugctl to make sure DS is not used. */
+		update_debugctlmsr(0);
+		ds_free(current->thread.ds_ctx);
+	}
+#endif /* CONFIG_X86_DS */
 }
 
 void flush_thread(void)
@@ -438,6 +446,35 @@ int set_tsc_mode(unsigned int val)
 	return 0;
 }
 
+#ifdef CONFIG_X86_DS
+static int update_debugctl(struct thread_struct *prev,
+			struct thread_struct *next, unsigned long debugctl)
+{
+	unsigned long ds_prev = 0;
+	unsigned long ds_next = 0;
+
+	if (prev->ds_ctx)
+		ds_prev = (unsigned long)prev->ds_ctx->ds;
+	if (next->ds_ctx)
+		ds_next = (unsigned long)next->ds_ctx->ds;
+
+	if (ds_next != ds_prev) {
+		/* we clear debugctl to make sure DS
+		 * is not in use when we change it */
+		debugctl = 0;
+		update_debugctlmsr(0);
+		wrmsr(MSR_IA32_DS_AREA, ds_next, 0);
+	}
+	return debugctl;
+}
+#else
+static int update_debugctl(struct thread_struct *prev,
+			struct thread_struct *next, unsigned long debugctl)
+{
+	return debugctl;
+}
+#endif /* CONFIG_X86_DS */
+
 static noinline void
 __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p,
 		 struct tss_struct *tss)
@@ -448,14 +485,7 @@ __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p,
 	prev = &prev_p->thread;
 	next = &next_p->thread;
 
-	debugctl = prev->debugctlmsr;
-	if (next->ds_area_msr != prev->ds_area_msr) {
-		/* we clear debugctl to make sure DS
-		 * is not in use when we change it */
-		debugctl = 0;
-		update_debugctlmsr(0);
-		wrmsr(MSR_IA32_DS_AREA, next->ds_area_msr, 0);
-	}
+	debugctl = update_debugctl(prev, next, prev->debugctlmsr);
 
 	if (next->debugctlmsr != debugctl)
 		update_debugctlmsr(next->debugctlmsr);
@@ -479,13 +509,13 @@ __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p,
 			hard_enable_TSC();
 	}
 
-#ifdef X86_BTS
+#ifdef CONFIG_X86_PTRACE_BTS
 	if (test_tsk_thread_flag(prev_p, TIF_BTS_TRACE_TS))
 		ptrace_bts_take_timestamp(prev_p, BTS_TASK_DEPARTS);
 
 	if (test_tsk_thread_flag(next_p, TIF_BTS_TRACE_TS))
 		ptrace_bts_take_timestamp(next_p, BTS_TASK_ARRIVES);
-#endif
+#endif /* CONFIG_X86_PTRACE_BTS */
 
 
 	if (!test_tsk_thread_flag(next_p, TIF_IO_BITMAP)) {

arch/x86/kernel/process_64.c

@@ -240,6 +240,14 @@ void exit_thread(void)
 		t->io_bitmap_max = 0;
 		put_cpu();
 	}
+#ifdef CONFIG_X86_DS
+	/* Free any DS contexts that have not been properly released. */
+	if (unlikely(t->ds_ctx)) {
+		/* we clear debugctl to make sure DS is not used. */
+		update_debugctlmsr(0);
+		ds_free(t->ds_ctx);
+	}
+#endif /* CONFIG_X86_DS */
 }
 
 void flush_thread(void)
@@ -473,13 +481,27 @@ static inline void __switch_to_xtra(struct task_struct *prev_p,
 	next = &next_p->thread;
 
 	debugctl = prev->debugctlmsr;
-	if (next->ds_area_msr != prev->ds_area_msr) {
-		/* we clear debugctl to make sure DS
-		 * is not in use when we change it */
-		debugctl = 0;
-		update_debugctlmsr(0);
-		wrmsrl(MSR_IA32_DS_AREA, next->ds_area_msr);
+
+#ifdef CONFIG_X86_DS
+	{
+		unsigned long ds_prev = 0, ds_next = 0;
+
+		if (prev->ds_ctx)
+			ds_prev = (unsigned long)prev->ds_ctx->ds;
+		if (next->ds_ctx)
+			ds_next = (unsigned long)next->ds_ctx->ds;
+
+		if (ds_next != ds_prev) {
+			/*
+			 * We clear debugctl to make sure DS
+			 * is not in use when we change it:
+			 */
+			debugctl = 0;
+			update_debugctlmsr(0);
+			wrmsrl(MSR_IA32_DS_AREA, ds_next);
+		}
 	}
+#endif /* CONFIG_X86_DS */
 
 	if (next->debugctlmsr != debugctl)
 		update_debugctlmsr(next->debugctlmsr);
@@ -517,13 +539,13 @@ static inline void __switch_to_xtra(struct task_struct *prev_p,
 		memset(tss->io_bitmap, 0xff, prev->io_bitmap_max);
 	}
 
-#ifdef X86_BTS
+#ifdef CONFIG_X86_PTRACE_BTS
 	if (test_tsk_thread_flag(prev_p, TIF_BTS_TRACE_TS))
 		ptrace_bts_take_timestamp(prev_p, BTS_TASK_DEPARTS);
 
 	if (test_tsk_thread_flag(next_p, TIF_BTS_TRACE_TS))
 		ptrace_bts_take_timestamp(next_p, BTS_TASK_ARRIVES);
-#endif
+#endif /* CONFIG_X86_PTRACE_BTS */
 }
 
 /*

include/asm-x86/ds.h

@@ -2,71 +2,237 @@
  * Debug Store (DS) support
  *
  * This provides a low-level interface to the hardware's Debug Store
- * feature that is used for last branch recording (LBR) and
+ * feature that is used for branch trace store (BTS) and
  * precise-event based sampling (PEBS).
  *
- * Different architectures use a different DS layout/pointer size.
- * The below functions therefore work on a void*.
+ * It manages:
+ * - per-thread and per-cpu allocation of BTS and PEBS
+ * - buffer memory allocation (optional)
+ * - buffer overflow handling
+ * - buffer access
  *
+ * It assumes:
+ * - get_task_struct on all parameter tasks
+ * - current is allowed to trace parameter tasks
  *
- * Since there is no user for PEBS, yet, only LBR (or branch
- * trace store, BTS) is supported.
  *
- *
- * Copyright (C) 2007 Intel Corporation.
- * Markus Metzger <markus.t.metzger@intel.com>, Dec 2007
+ * Copyright (C) 2007-2008 Intel Corporation.
+ * Markus Metzger <markus.t.metzger@intel.com>, 2007-2008
  */
 
 #ifndef ASM_X86__DS_H
 #define ASM_X86__DS_H
 
+#ifdef CONFIG_X86_DS
+
 #include <linux/types.h>
 #include <linux/init.h>
 
-struct cpuinfo_x86;
 
+struct task_struct;
 
-/* a branch trace record entry
+/*
+ * Request BTS or PEBS
+ *
+ * Due to alignement constraints, the actual buffer may be slightly
+ * smaller than the requested or provided buffer.
  *
- * In order to unify the interface between various processor versions,
- * we use the below data structure for all processors.
+ * Returns 0 on success; -Eerrno otherwise
+ *
+ * task: the task to request recording for;
+ *       NULL for per-cpu recording on the current cpu
+ * base: the base pointer for the (non-pageable) buffer;
+ *       NULL if buffer allocation requested
+ * size: the size of the requested or provided buffer
+ * ovfl: pointer to a function to be called on buffer overflow;
+ *       NULL if cyclic buffer requested
  */
-enum bts_qualifier {
-	BTS_INVALID = 0,
-	BTS_BRANCH,
-	BTS_TASK_ARRIVES,
-	BTS_TASK_DEPARTS
-};
+typedef void (*ds_ovfl_callback_t)(struct task_struct *);
+extern int ds_request_bts(struct task_struct *task, void *base, size_t size,
+			  ds_ovfl_callback_t ovfl);
+extern int ds_request_pebs(struct task_struct *task, void *base, size_t size,
+			   ds_ovfl_callback_t ovfl);
+
+/*
+ * Release BTS or PEBS resources
+ *
+ * Frees buffers allocated on ds_request.
+ *
+ * Returns 0 on success; -Eerrno otherwise
+ *
+ * task: the task to release resources for;
+ *       NULL to release resources for the current cpu
+ */
+extern int ds_release_bts(struct task_struct *task);
+extern int ds_release_pebs(struct task_struct *task);
+
+/*
+ * Return the (array) index of the write pointer.
+ * (assuming an array of BTS/PEBS records)
+ *
+ * Returns -Eerrno on error
+ *
+ * task: the task to access;
+ *       NULL to access the current cpu
+ * pos (out): if not NULL, will hold the result
+ */
+extern int ds_get_bts_index(struct task_struct *task, size_t *pos);
+extern int ds_get_pebs_index(struct task_struct *task, size_t *pos);
+
+/*
+ * Return the (array) index one record beyond the end of the array.
+ * (assuming an array of BTS/PEBS records)
+ *
+ * Returns -Eerrno on error
+ *
+ * task: the task to access;
+ *       NULL to access the current cpu
+ * pos (out): if not NULL, will hold the result
+ */
+extern int ds_get_bts_end(struct task_struct *task, size_t *pos);
+extern int ds_get_pebs_end(struct task_struct *task, size_t *pos);
+
+/*
+ * Provide a pointer to the BTS/PEBS record at parameter index.
+ * (assuming an array of BTS/PEBS records)
+ *
+ * The pointer points directly into the buffer. The user is
+ * responsible for copying the record.
+ *
+ * Returns the size of a single record on success; -Eerrno on error
+ *
+ * task: the task to access;
+ *       NULL to access the current cpu
+ * index: the index of the requested record
+ * record (out): pointer to the requested record
+ */
+extern int ds_access_bts(struct task_struct *task,
+			 size_t index, const void **record);
+extern int ds_access_pebs(struct task_struct *task,
+			  size_t index, const void **record);
+
+/*
+ * Write one or more BTS/PEBS records at the write pointer index and
+ * advance the write pointer.
+ *
+ * If size is not a multiple of the record size, trailing bytes are
+ * zeroed out.
+ *
+ * May result in one or more overflow notifications.
+ *
+ * If called during overflow handling, that is, with index >=
+ * interrupt threshold, the write will wrap around.
+ *
+ * An overflow notification is given if and when the interrupt
+ * threshold is reached during or after the write.
+ *
+ * Returns the number of bytes written or -Eerrno.
+ *
+ * task: the task to access;
+ *       NULL to access the current cpu
+ * buffer: the buffer to write
+ * size: the size of the buffer
+ */
+extern int ds_write_bts(struct task_struct *task,
+			const void *buffer, size_t size);
+extern int ds_write_pebs(struct task_struct *task,
+			 const void *buffer, size_t size);
+
+/*
+ * Same as ds_write_bts/pebs, but omit ownership checks.
+ *
+ * This is needed to have some other task than the owner of the
+ * BTS/PEBS buffer or the parameter task itself write into the
+ * respective buffer.
+ */
+extern int ds_unchecked_write_bts(struct task_struct *task,
+				  const void *buffer, size_t size);
+extern int ds_unchecked_write_pebs(struct task_struct *task,
+				   const void *buffer, size_t size);
+
+/*
+ * Reset the write pointer of the BTS/PEBS buffer.
+ *
+ * Returns 0 on success; -Eerrno on error
+ *
+ * task: the task to access;
+ *       NULL to access the current cpu
+ */
+extern int ds_reset_bts(struct task_struct *task);
+extern int ds_reset_pebs(struct task_struct *task);
+
+/*
+ * Clear the BTS/PEBS buffer and reset the write pointer.
+ * The entire buffer will be zeroed out.
+ *
+ * Returns 0 on success; -Eerrno on error
+ *
+ * task: the task to access;
+ *       NULL to access the current cpu
+ */
+extern int ds_clear_bts(struct task_struct *task);
+extern int ds_clear_pebs(struct task_struct *task);
+
+/*
+ * Provide the PEBS counter reset value.
+ *
+ * Returns 0 on success; -Eerrno on error
+ *
+ * task: the task to access;
+ *       NULL to access the current cpu
+ * value (out): the counter reset value
+ */
+extern int ds_get_pebs_reset(struct task_struct *task, u64 *value);
+
+/*
+ * Set the PEBS counter reset value.
+ *
+ * Returns 0 on success; -Eerrno on error
+ *
+ * task: the task to access;
+ *       NULL to access the current cpu
+ * value: the new counter reset value
+ */
+extern int ds_set_pebs_reset(struct task_struct *task, u64 value);
+
+/*
+ * Initialization
+ */
+struct cpuinfo_x86;
+extern void __cpuinit ds_init_intel(struct cpuinfo_x86 *);
+
+
 
-struct bts_struct {
-	u64 qualifier;
-	union {
-		/* BTS_BRANCH */
-		struct {
-			u64 from_ip;
-			u64 to_ip;
-		} lbr;
-		/* BTS_TASK_ARRIVES or
-		   BTS_TASK_DEPARTS */
-		u64 jiffies;
-	} variant;
+/*
+ * The DS context - part of struct thread_struct.
+ */
+struct ds_context {
+	/* pointer to the DS configuration; goes into MSR_IA32_DS_AREA */
+	unsigned char *ds;
+	/* the owner of the BTS and PEBS configuration, respectively */
+	struct task_struct *owner[2];
+	/* buffer overflow notification function for BTS and PEBS */
+	ds_ovfl_callback_t callback[2];
+	/* the original buffer address */
+	void *buffer[2];
+	/* the number of allocated pages for on-request allocated buffers */
+	unsigned int pages[2];
+	/* use count */
+	unsigned long count;
+	/* a pointer to the context location inside the thread_struct
+	 * or the per_cpu context array */
+	struct ds_context **this;
+	/* a pointer to the task owning this context, or NULL, if the
+	 * context is owned by a cpu */
+	struct task_struct *task;
 };
 
-/* Overflow handling mechanisms */
-#define DS_O_SIGNAL	1 /* send overflow signal */
-#define DS_O_WRAP	2 /* wrap around */
-
-extern int ds_allocate(void **, size_t);
-extern int ds_free(void **);
-extern int ds_get_bts_size(void *);
-extern int ds_get_bts_end(void *);
-extern int ds_get_bts_index(void *);
-extern int ds_set_overflow(void *, int);
-extern int ds_get_overflow(void *);
-extern int ds_clear(void *);
-extern int ds_read_bts(void *, int, struct bts_struct *);
-extern int ds_write_bts(void *, const struct bts_struct *);
-extern unsigned long ds_debugctl_mask(void);
-extern void __cpuinit ds_init_intel(struct cpuinfo_x86 *c);
+/* called by exit_thread() to free leftover contexts */
+extern void ds_free(struct ds_context *context);
+
+#else /* CONFIG_X86_DS */
+
+#define ds_init_intel(config) do {} while (0)
 
+#endif /* CONFIG_X86_DS */
 #endif /* ASM_X86__DS_H */

include/asm-x86/processor.h

@@ -20,6 +20,7 @@ struct mm_struct;
 #include <asm/msr.h>
 #include <asm/desc_defs.h>
 #include <asm/nops.h>
+#include <asm/ds.h>
 
 #include <linux/personality.h>
 #include <linux/cpumask.h>
@@ -411,9 +412,14 @@ struct thread_struct {
 	unsigned		io_bitmap_max;
 /* MSR_IA32_DEBUGCTLMSR value to switch in if TIF_DEBUGCTLMSR is set.  */
 	unsigned long	debugctlmsr;
-/* Debug Store - if not 0 points to a DS Save Area configuration;
- *               goes into MSR_IA32_DS_AREA */
-	unsigned long	ds_area_msr;
+#ifdef CONFIG_X86_DS
+/* Debug Store context; see include/asm-x86/ds.h; goes into MSR_IA32_DS_AREA */
+	struct ds_context	*ds_ctx;
+#endif /* CONFIG_X86_DS */
+#ifdef CONFIG_X86_PTRACE_BTS
+/* the signal to send on a bts buffer overflow */
+	unsigned int	bts_ovfl_signal;
+#endif /* CONFIG_X86_PTRACE_BTS */
 };
 
 static inline unsigned long native_get_debugreg(int regno)

include/asm-x86/ptrace-abi.h

@@ -80,8 +80,9 @@
 
 #define PTRACE_SINGLEBLOCK	33	/* resume execution until next branch */
 
-#ifndef __ASSEMBLY__
+#ifdef CONFIG_X86_PTRACE_BTS
 
+#ifndef __ASSEMBLY__
 #include <asm/types.h>
 
 /* configuration/status structure used in PTRACE_BTS_CONFIG and
@@ -97,20 +98,20 @@ struct ptrace_bts_config {
 	/* actual size of bts_struct in bytes */
 	__u32 bts_size;
 };
-#endif
+#endif /* __ASSEMBLY__ */
 
 #define PTRACE_BTS_O_TRACE	0x1 /* branch trace */
 #define PTRACE_BTS_O_SCHED	0x2 /* scheduling events w/ jiffies */
 #define PTRACE_BTS_O_SIGNAL     0x4 /* send SIG<signal> on buffer overflow
 				       instead of wrapping around */
-#define PTRACE_BTS_O_CUT_SIZE	0x8 /* cut requested size to max available
-				       instead of failing */
+#define PTRACE_BTS_O_ALLOC	0x8 /* (re)allocate buffer */
 
 #define PTRACE_BTS_CONFIG	40
 /* Configure branch trace recording.
    ADDR points to a struct ptrace_bts_config.
    DATA gives the size of that buffer.
-   A new buffer is allocated, iff the size changes.
+   A new buffer is allocated, if requested in the flags.
+   An overflow signal may only be requested for new buffers.
    Returns the number of bytes read.
 */
 #define PTRACE_BTS_STATUS	41
@@ -119,7 +120,7 @@ struct ptrace_bts_config {
    Returns the number of bytes written.
 */
 #define PTRACE_BTS_SIZE		42
-/* Return the number of available BTS records.
+/* Return the number of available BTS records for draining.
    DATA and ADDR are ignored.
 */
 #define PTRACE_BTS_GET		43
@@ -139,5 +140,6 @@ struct ptrace_bts_config {
    BTS records are read from oldest to newest.
    Returns number of BTS records drained.
 */
+#endif /* CONFIG_X86_PTRACE_BTS */
 
 #endif /* ASM_X86__PTRACE_ABI_H */

include/asm-x86/ptrace.h

@@ -127,14 +127,48 @@ struct pt_regs {
 #endif /* __KERNEL__ */
 #endif /* !__i386__ */
 
+
+#ifdef CONFIG_X86_PTRACE_BTS
+/* a branch trace record entry
+ *
+ * In order to unify the interface between various processor versions,
+ * we use the below data structure for all processors.
+ */
+enum bts_qualifier {
+	BTS_INVALID = 0,
+	BTS_BRANCH,
+	BTS_TASK_ARRIVES,
+	BTS_TASK_DEPARTS
+};
+
+struct bts_struct {
+	__u64 qualifier;
+	union {
+		/* BTS_BRANCH */
+		struct {
+			__u64 from_ip;
+			__u64 to_ip;
+		} lbr;
+		/* BTS_TASK_ARRIVES or
+		   BTS_TASK_DEPARTS */
+		__u64 jiffies;
+	} variant;
+};
+#endif /* CONFIG_X86_PTRACE_BTS */
+
 #ifdef __KERNEL__
 
-/* the DS BTS struct is used for ptrace as well */
-#include <asm/ds.h>
+#include <linux/init.h>
 
+struct cpuinfo_x86;
 struct task_struct;
 
+#ifdef CONFIG_X86_PTRACE_BTS
+extern void __cpuinit ptrace_bts_init_intel(struct cpuinfo_x86 *);
 extern void ptrace_bts_take_timestamp(struct task_struct *, enum bts_qualifier);
+#else
+#define ptrace_bts_init_intel(config) do {} while (0)
+#endif /* CONFIG_X86_PTRACE_BTS */
 
 extern unsigned long profile_pc(struct pt_regs *regs);