Merge branch 'core' of git://git.kernel.org/pub/scm/linux/kernel/git/rric/oprofile into perf/urgent

arch/s390/oprofile/Makefile

@@ -6,4 +6,4 @@ DRIVER_OBJS = $(addprefix ../../../drivers/oprofile/, \
 		oprofilefs.o oprofile_stats.o  \
 		timer_int.o )
 
-oprofile-y				:= $(DRIVER_OBJS) init.o backtrace.o
+oprofile-y :=	$(DRIVER_OBJS) init.o backtrace.o hwsampler.o

arch/s390/oprofile/hwsampler.h

+/*
+ * CPUMF HW sampler functions and internal structures
+ *
+ *    Copyright IBM Corp. 2010
+ *    Author(s): Heinz Graalfs <graalfs@de.ibm.com>
+ */
+
+#ifndef HWSAMPLER_H_
+#define HWSAMPLER_H_
+
+#include <linux/workqueue.h>
+
+struct hws_qsi_info_block          /* QUERY SAMPLING information block  */
+{ /* Bit(s) */
+	unsigned int b0_13:14;      /* 0-13: zeros                       */
+	unsigned int as:1;          /* 14: sampling authorisation control*/
+	unsigned int b15_21:7;      /* 15-21: zeros                      */
+	unsigned int es:1;          /* 22: sampling enable control       */
+	unsigned int b23_29:7;      /* 23-29: zeros                      */
+	unsigned int cs:1;          /* 30: sampling activation control   */
+	unsigned int:1;             /* 31: reserved                      */
+	unsigned int bsdes:16;      /* 4-5: size of sampling entry       */
+	unsigned int:16;            /* 6-7: reserved                     */
+	unsigned long min_sampl_rate; /* 8-15: minimum sampling interval */
+	unsigned long max_sampl_rate; /* 16-23: maximum sampling interval*/
+	unsigned long tear;         /* 24-31: TEAR contents              */
+	unsigned long dear;         /* 32-39: DEAR contents              */
+	unsigned int rsvrd0;        /* 40-43: reserved                   */
+	unsigned int cpu_speed;     /* 44-47: CPU speed                  */
+	unsigned long long rsvrd1;  /* 48-55: reserved                   */
+	unsigned long long rsvrd2;  /* 56-63: reserved                   */
+};
+
+struct hws_ssctl_request_block     /* SET SAMPLING CONTROLS req block   */
+{ /* bytes 0 - 7  Bit(s) */
+	unsigned int s:1;           /* 0: maximum buffer indicator       */
+	unsigned int h:1;           /* 1: part. level reserved for VM use*/
+	unsigned long b2_53:52;     /* 2-53: zeros                       */
+	unsigned int es:1;          /* 54: sampling enable control       */
+	unsigned int b55_61:7;      /* 55-61: - zeros                    */
+	unsigned int cs:1;          /* 62: sampling activation control   */
+	unsigned int b63:1;         /* 63: zero                          */
+	unsigned long interval;     /* 8-15: sampling interval           */
+	unsigned long tear;         /* 16-23: TEAR contents              */
+	unsigned long dear;         /* 24-31: DEAR contents              */
+	/* 32-63:                                                        */
+	unsigned long rsvrd1;       /* reserved                          */
+	unsigned long rsvrd2;       /* reserved                          */
+	unsigned long rsvrd3;       /* reserved                          */
+	unsigned long rsvrd4;       /* reserved                          */
+};
+
+struct hws_cpu_buffer {
+	unsigned long first_sdbt;       /* @ of 1st SDB-Table for this CP*/
+	unsigned long worker_entry;
+	unsigned long sample_overflow;  /* taken from SDB ...            */
+	struct hws_qsi_info_block qsi;
+	struct hws_ssctl_request_block ssctl;
+	struct work_struct worker;
+	atomic_t ext_params;
+	unsigned long req_alert;
+	unsigned long loss_of_sample_data;
+	unsigned long invalid_entry_address;
+	unsigned long incorrect_sdbt_entry;
+	unsigned long sample_auth_change_alert;
+	unsigned int finish:1;
+	unsigned int oom:1;
+	unsigned int stop_mode:1;
+};
+
+struct hws_data_entry {
+	unsigned int def:16;        /* 0-15  Data Entry Format           */
+	unsigned int R:4;           /* 16-19 reserved                    */
+	unsigned int U:4;           /* 20-23 Number of unique instruct.  */
+	unsigned int z:2;           /* zeros                             */
+	unsigned int T:1;           /* 26 PSW DAT mode                   */
+	unsigned int W:1;           /* 27 PSW wait state                 */
+	unsigned int P:1;           /* 28 PSW Problem state              */
+	unsigned int AS:2;          /* 29-30 PSW address-space control   */
+	unsigned int I:1;           /* 31 entry valid or invalid         */
+	unsigned int:16;
+	unsigned int prim_asn:16;   /* primary ASN                       */
+	unsigned long long ia;      /* Instruction Address               */
+	unsigned long long lpp;     /* Logical-Partition Program Param.  */
+	unsigned long long vpp;     /* Virtual-Machine Program Param.    */
+};
+
+struct hws_trailer_entry {
+	unsigned int f:1;           /* 0 - Block Full Indicator          */
+	unsigned int a:1;           /* 1 - Alert request control         */
+	unsigned long:62;           /* 2 - 63: Reserved                  */
+	unsigned long overflow;     /* 64 - sample Overflow count        */
+	unsigned long timestamp;    /* 16 - time-stamp                   */
+	unsigned long timestamp1;   /*                                   */
+	unsigned long reserved1;    /* 32 -Reserved                      */
+	unsigned long reserved2;    /*                                   */
+	unsigned long progusage1;   /* 48 - reserved for programming use */
+	unsigned long progusage2;   /*                                   */
+};
+
+int hwsampler_setup(void);
+int hwsampler_shutdown(void);
+int hwsampler_allocate(unsigned long sdbt, unsigned long sdb);
+int hwsampler_deallocate(void);
+long hwsampler_query_min_interval(void);
+long hwsampler_query_max_interval(void);
+int hwsampler_start_all(unsigned long interval);
+int hwsampler_stop_all(void);
+int hwsampler_deactivate(unsigned int cpu);
+int hwsampler_activate(unsigned int cpu);
+unsigned long hwsampler_get_sample_overflow_count(unsigned int cpu);
+
+#endif /*HWSAMPLER_H_*/

arch/s390/oprofile/init.c

@@ -4,23 +4,182 @@
  * S390 Version
  *   Copyright (C) 2003 IBM Deutschland Entwicklung GmbH, IBM Corporation
  *   Author(s): Thomas Spatzier (tspat@de.ibm.com)
+ *   Author(s): Mahesh Salgaonkar (mahesh@linux.vnet.ibm.com)
+ *   Author(s): Heinz Graalfs (graalfs@linux.vnet.ibm.com)
  *
- * @remark Copyright 2002 OProfile authors
+ * @remark Copyright 2002-2011 OProfile authors
  */
 
 #include <linux/oprofile.h>
 #include <linux/init.h>
 #include <linux/errno.h>
+#include <linux/oprofile.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+
+#include "../../../drivers/oprofile/oprof.h"
+#include "hwsampler.h"
+
+#define DEFAULT_INTERVAL	4096
+
+#define DEFAULT_SDBT_BLOCKS	1
+#define DEFAULT_SDB_BLOCKS	511
+
+static unsigned long oprofile_hw_interval = DEFAULT_INTERVAL;
+static unsigned long oprofile_min_interval;
+static unsigned long oprofile_max_interval;
+
+static unsigned long oprofile_sdbt_blocks = DEFAULT_SDBT_BLOCKS;
+static unsigned long oprofile_sdb_blocks = DEFAULT_SDB_BLOCKS;
 
+static int hwsampler_file;
+static int hwsampler_running;	/* start_mutex must be held to change */
+
+static struct oprofile_operations timer_ops;
 
 extern void s390_backtrace(struct pt_regs * const regs, unsigned int depth);
 
-int __init oprofile_arch_init(struct oprofile_operations* ops)
+static int oprofile_hwsampler_start(void)
+{
+	int retval;
+
+	hwsampler_running = hwsampler_file;
+
+	if (!hwsampler_running)
+		return timer_ops.start();
+
+	retval = hwsampler_allocate(oprofile_sdbt_blocks, oprofile_sdb_blocks);
+	if (retval)
+		return retval;
+
+	retval = hwsampler_start_all(oprofile_hw_interval);
+	if (retval)
+		hwsampler_deallocate();
+
+	return retval;
+}
+
+static void oprofile_hwsampler_stop(void)
+{
+	if (!hwsampler_running) {
+		timer_ops.stop();
+		return;
+	}
+
+	hwsampler_stop_all();
+	hwsampler_deallocate();
+	return;
+}
+
+static ssize_t hwsampler_read(struct file *file, char __user *buf,
+		size_t count, loff_t *offset)
+{
+	return oprofilefs_ulong_to_user(hwsampler_file, buf, count, offset);
+}
+
+static ssize_t hwsampler_write(struct file *file, char const __user *buf,
+		size_t count, loff_t *offset)
+{
+	unsigned long val;
+	int retval;
+
+	if (*offset)
+		return -EINVAL;
+
+	retval = oprofilefs_ulong_from_user(&val, buf, count);
+	if (retval)
+		return retval;
+
+	if (oprofile_started)
+		/*
+		 * save to do without locking as we set
+		 * hwsampler_running in start() when start_mutex is
+		 * held
+		 */
+		return -EBUSY;
+
+	hwsampler_file = val;
+
+	return count;
+}
+
+static const struct file_operations hwsampler_fops = {
+	.read		= hwsampler_read,
+	.write		= hwsampler_write,
+};
+
+static int oprofile_create_hwsampling_files(struct super_block *sb,
+						struct dentry *root)
+{
+	struct dentry *hw_dir;
+
+	/* reinitialize default values */
+	hwsampler_file = 1;
+
+	hw_dir = oprofilefs_mkdir(sb, root, "hwsampling");
+	if (!hw_dir)
+		return -EINVAL;
+
+	oprofilefs_create_file(sb, hw_dir, "hwsampler", &hwsampler_fops);
+	oprofilefs_create_ulong(sb, hw_dir, "hw_interval",
+				&oprofile_hw_interval);
+	oprofilefs_create_ro_ulong(sb, hw_dir, "hw_min_interval",
+				&oprofile_min_interval);
+	oprofilefs_create_ro_ulong(sb, hw_dir, "hw_max_interval",
+				&oprofile_max_interval);
+	oprofilefs_create_ulong(sb, hw_dir, "hw_sdbt_blocks",
+				&oprofile_sdbt_blocks);
+
+	return 0;
+}
+
+static int oprofile_hwsampler_init(struct oprofile_operations *ops)
+{
+	if (hwsampler_setup())
+		return -ENODEV;
+
+	/*
+	 * create hwsampler files only if hwsampler_setup() succeeds.
+	 */
+	oprofile_min_interval = hwsampler_query_min_interval();
+	if (oprofile_min_interval < 0) {
+		oprofile_min_interval = 0;
+		return -ENODEV;
+	}
+	oprofile_max_interval = hwsampler_query_max_interval();
+	if (oprofile_max_interval < 0) {
+		oprofile_max_interval = 0;
+		return -ENODEV;
+	}
+
+	if (oprofile_timer_init(ops))
+		return -ENODEV;
+
+	printk(KERN_INFO "oprofile: using hardware sampling\n");
+
+	memcpy(&timer_ops, ops, sizeof(timer_ops));
+
+	ops->start = oprofile_hwsampler_start;
+	ops->stop = oprofile_hwsampler_stop;
+	ops->create_files = oprofile_create_hwsampling_files;
+
+	return 0;
+}
+
+static void oprofile_hwsampler_exit(void)
+{
+	oprofile_timer_exit();
+	hwsampler_shutdown();
+}
+
+int __init oprofile_arch_init(struct oprofile_operations *ops)
 {
 	ops->backtrace = s390_backtrace;
-	return -ENODEV;
+
+	return oprofile_hwsampler_init(ops);
 }
 
 void oprofile_arch_exit(void)
 {
+	oprofile_hwsampler_exit();
 }

drivers/oprofile/cpu_buffer.c

@@ -258,8 +258,10 @@ op_add_sample(struct oprofile_cpu_buffer *cpu_buf,
  */
 static int
 log_sample(struct oprofile_cpu_buffer *cpu_buf, unsigned long pc,
-	   unsigned long backtrace, int is_kernel, unsigned long event)
+	   unsigned long backtrace, int is_kernel, unsigned long event,
+	   struct task_struct *task)
 {
+	struct task_struct *tsk = task ? task : current;
 	cpu_buf->sample_received++;
 
 	if (pc == ESCAPE_CODE) {
@@ -267,7 +269,7 @@ log_sample(struct oprofile_cpu_buffer *cpu_buf, unsigned long pc,
 		return 0;
 	}
 
-	if (op_add_code(cpu_buf, backtrace, is_kernel, current))
+	if (op_add_code(cpu_buf, backtrace, is_kernel, tsk))
 		goto fail;
 
 	if (op_add_sample(cpu_buf, pc, event))
@@ -292,7 +294,8 @@ static inline void oprofile_end_trace(struct oprofile_cpu_buffer *cpu_buf)
 
 static inline void
 __oprofile_add_ext_sample(unsigned long pc, struct pt_regs * const regs,
-			  unsigned long event, int is_kernel)
+			  unsigned long event, int is_kernel,
+			  struct task_struct *task)
 {
 	struct oprofile_cpu_buffer *cpu_buf = &__get_cpu_var(op_cpu_buffer);
 	unsigned long backtrace = oprofile_backtrace_depth;
@@ -301,7 +304,7 @@ __oprofile_add_ext_sample(unsigned long pc, struct pt_regs * const regs,
 	 * if log_sample() fail we can't backtrace since we lost the
 	 * source of this event
 	 */
-	if (!log_sample(cpu_buf, pc, backtrace, is_kernel, event))
+	if (!log_sample(cpu_buf, pc, backtrace, is_kernel, event, task))
 		/* failed */
 		return;
 
@@ -313,10 +316,17 @@ __oprofile_add_ext_sample(unsigned long pc, struct pt_regs * const regs,
 	oprofile_end_trace(cpu_buf);
 }
 
+void oprofile_add_ext_hw_sample(unsigned long pc, struct pt_regs * const regs,
+				unsigned long event, int is_kernel,
+				struct task_struct *task)
+{
+	__oprofile_add_ext_sample(pc, regs, event, is_kernel, task);
+}
+
 void oprofile_add_ext_sample(unsigned long pc, struct pt_regs * const regs,
 			     unsigned long event, int is_kernel)
 {
-	__oprofile_add_ext_sample(pc, regs, event, is_kernel);
+	__oprofile_add_ext_sample(pc, regs, event, is_kernel, NULL);
 }
 
 void oprofile_add_sample(struct pt_regs * const regs, unsigned long event)
@@ -332,7 +342,7 @@ void oprofile_add_sample(struct pt_regs * const regs, unsigned long event)
 		pc = ESCAPE_CODE; /* as this causes an early return. */
 	}
 
-	__oprofile_add_ext_sample(pc, regs, event, is_kernel);
+	__oprofile_add_ext_sample(pc, regs, event, is_kernel, NULL);
 }
 
 /*
@@ -403,7 +413,7 @@ int oprofile_write_commit(struct op_entry *entry)
 void oprofile_add_pc(unsigned long pc, int is_kernel, unsigned long event)
 {
 	struct oprofile_cpu_buffer *cpu_buf = &__get_cpu_var(op_cpu_buffer);
-	log_sample(cpu_buf, pc, 0, is_kernel, event);
+	log_sample(cpu_buf, pc, 0, is_kernel, event, NULL);
 }
 
 void oprofile_add_trace(unsigned long pc)

drivers/oprofile/timer_int.c

@@ -97,7 +97,7 @@ static struct notifier_block __refdata oprofile_cpu_notifier = {
 	.notifier_call = oprofile_cpu_notify,
 };
 
-int __init oprofile_timer_init(struct oprofile_operations *ops)
+int oprofile_timer_init(struct oprofile_operations *ops)
 {
 	int rc;
 
@@ -113,7 +113,7 @@ int __init oprofile_timer_init(struct oprofile_operations *ops)
 	return 0;
 }
 
-void __exit oprofile_timer_exit(void)
+void oprofile_timer_exit(void)
 {
 	unregister_hotcpu_notifier(&oprofile_cpu_notifier);
 }

include/linux/oprofile.h

@@ -106,6 +106,13 @@ void oprofile_add_sample(struct pt_regs * const regs, unsigned long event);
 void oprofile_add_ext_sample(unsigned long pc, struct pt_regs * const regs,
 				unsigned long event, int is_kernel);
 
+/**
+ * Add an hardware sample.
+ */
+void oprofile_add_ext_hw_sample(unsigned long pc, struct pt_regs * const regs,
+	unsigned long event, int is_kernel,
+	struct task_struct *task);
+
 /* Use this instead when the PC value is not from the regs. Doesn't
  * backtrace. */
 void oprofile_add_pc(unsigned long pc, int is_kernel, unsigned long event);