Merge branch 'perf/core' of git://git.kernel.org/pub/scm/linux/kernel/git/frederic/random-tracing into perf/core

arch/Kconfig

@@ -137,6 +137,17 @@ config HAVE_HW_BREAKPOINT
 	bool
 	depends on PERF_EVENTS
 
+config HAVE_MIXED_BREAKPOINTS_REGS
+	bool
+	depends on HAVE_HW_BREAKPOINT
+	help
+	  Depending on the arch implementation of hardware breakpoints,
+	  some of them have separate registers for data and instruction
+	  breakpoints addresses, others have mixed registers to store
+	  them but define the access type in a control register.
+	  Select this option if your arch implements breakpoints under the
+	  latter fashion.
+
 config HAVE_USER_RETURN_NOTIFIER
 	bool
 

arch/sh/Kconfig

@@ -44,6 +44,7 @@ config SUPERH32
 	select HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_ARCH_KGDB
 	select HAVE_HW_BREAKPOINT
+	select HAVE_MIXED_BREAKPOINTS_REGS
 	select PERF_EVENTS if HAVE_HW_BREAKPOINT
 	select ARCH_HIBERNATION_POSSIBLE if MMU
 

arch/sh/include/asm/hw_breakpoint.h

@@ -46,10 +46,14 @@ struct pmu;
 /* Maximum number of UBC channels */
 #define HBP_NUM		2
 
+static inline int hw_breakpoint_slots(int type)
+{
+	return HBP_NUM;
+}
+
 /* arch/sh/kernel/hw_breakpoint.c */
-extern int arch_check_va_in_userspace(unsigned long va, u16 hbp_len);
-extern int arch_validate_hwbkpt_settings(struct perf_event *bp,
-					 struct task_struct *tsk);
+extern int arch_check_bp_in_kernelspace(struct perf_event *bp);
+extern int arch_validate_hwbkpt_settings(struct perf_event *bp);
 extern int hw_breakpoint_exceptions_notify(struct notifier_block *unused,
 					   unsigned long val, void *data);
 

arch/sh/kernel/hw_breakpoint.c

@@ -119,26 +119,17 @@ static int get_hbp_len(u16 hbp_len)
 	return len_in_bytes;
 }
 
-/*
- * Check for virtual address in user space.
- */
-int arch_check_va_in_userspace(unsigned long va, u16 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)
+int arch_check_bp_in_kernelspace(struct perf_event *bp)
 {
 	unsigned int len;
+	unsigned long va;
+	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
 
-	len = get_hbp_len(hbp_len);
+	va = info->address;
+	len = get_hbp_len(info->len);
 
 	return (va >= TASK_SIZE) && ((va + len - 1) >= TASK_SIZE);
 }
@@ -226,8 +217,7 @@ static int arch_build_bp_info(struct perf_event *bp)
 /*
  * Validate the arch-specific HW Breakpoint register settings
  */
-int arch_validate_hwbkpt_settings(struct perf_event *bp,
-				  struct task_struct *tsk)
+int arch_validate_hwbkpt_settings(struct perf_event *bp)
 {
 	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
 	unsigned int align;
@@ -270,15 +260,6 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp,
 	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;
 }
 
@@ -363,8 +344,7 @@ static int __kprobes hw_breakpoint_handler(struct die_args *args)
 		perf_bp_event(bp, args->regs);
 
 		/* Deliver the signal to userspace */
-		if (arch_check_va_in_userspace(bp->attr.bp_addr,
-					       bp->attr.bp_len)) {
+		if (!arch_check_bp_in_kernelspace(bp)) {
 			siginfo_t info;
 
 			info.si_signo = args->signr;

arch/sh/kernel/ptrace_32.c

@@ -85,7 +85,7 @@ static int set_single_step(struct task_struct *tsk, unsigned long addr)
 
 	bp = thread->ptrace_bps[0];
 	if (!bp) {
-		hw_breakpoint_init(&attr);
+		ptrace_breakpoint_init(&attr);
 
 		attr.bp_addr = addr;
 		attr.bp_len = HW_BREAKPOINT_LEN_2;

arch/x86/Kconfig

@@ -53,6 +53,7 @@ config X86
 	select HAVE_KERNEL_LZMA
 	select HAVE_KERNEL_LZO
 	select HAVE_HW_BREAKPOINT
+	select HAVE_MIXED_BREAKPOINTS_REGS
 	select PERF_EVENTS
 	select ANON_INODES
 	select HAVE_ARCH_KMEMCHECK

arch/x86/include/asm/hw_breakpoint.h

@@ -41,12 +41,16 @@ struct arch_hw_breakpoint {
 /* Total number of available HW breakpoint registers */
 #define HBP_NUM 4
 
+static inline int hw_breakpoint_slots(int type)
+{
+	return HBP_NUM;
+}
+
 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 arch_check_bp_in_kernelspace(struct perf_event *bp);
+extern int arch_validate_hwbkpt_settings(struct perf_event *bp);
 extern int hw_breakpoint_exceptions_notify(struct notifier_block *unused,
 					   unsigned long val, void *data);
 

arch/x86/kernel/hw_breakpoint.c

@@ -188,26 +188,17 @@ static int get_hbp_len(u8 hbp_len)
 	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)
+int arch_check_bp_in_kernelspace(struct perf_event *bp)
 {
 	unsigned int len;
+	unsigned long va;
+	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
 
-	len = get_hbp_len(hbp_len);
+	va = info->address;
+	len = get_hbp_len(info->len);
 
 	return (va >= TASK_SIZE) && ((va + len - 1) >= TASK_SIZE);
 }
@@ -300,8 +291,7 @@ static int arch_build_bp_info(struct perf_event *bp)
 /*
  * Validate the arch-specific HW Breakpoint register settings
  */
-int arch_validate_hwbkpt_settings(struct perf_event *bp,
-				  struct task_struct *tsk)
+int arch_validate_hwbkpt_settings(struct perf_event *bp)
 {
 	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
 	unsigned int align;
@@ -314,16 +304,6 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp,
 
 	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;
@@ -350,15 +330,6 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp,
 	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;
 }
 

arch/x86/kernel/ptrace.c

@@ -688,7 +688,7 @@ static int ptrace_set_breakpoint_addr(struct task_struct *tsk, int nr,
 	struct perf_event_attr attr;
 
 	if (!t->ptrace_bps[nr]) {
-		hw_breakpoint_init(&attr);
+		ptrace_breakpoint_init(&attr);
 		/*
 		 * Put stub len and type to register (reserve) an inactive but
 		 * correct bp

include/linux/hw_breakpoint.h

@@ -9,9 +9,22 @@ enum {
 };
 
 enum {
-	HW_BREAKPOINT_R = 1,
-	HW_BREAKPOINT_W = 2,
-	HW_BREAKPOINT_X = 4,
+	HW_BREAKPOINT_EMPTY	= 0,
+	HW_BREAKPOINT_R		= 1,
+	HW_BREAKPOINT_W		= 2,
+	HW_BREAKPOINT_RW	= HW_BREAKPOINT_R | HW_BREAKPOINT_W,
+	HW_BREAKPOINT_X		= 4,
+	HW_BREAKPOINT_INVALID   = HW_BREAKPOINT_RW | HW_BREAKPOINT_X,
+};
+
+enum bp_type_idx {
+	TYPE_INST 	= 0,
+#ifdef CONFIG_HAVE_MIXED_BREAKPOINTS_REGS
+	TYPE_DATA	= 0,
+#else
+	TYPE_DATA	= 1,
+#endif
+	TYPE_MAX
 };
 
 #ifdef __KERNEL__
@@ -34,6 +47,12 @@ static inline void hw_breakpoint_init(struct perf_event_attr *attr)
 	attr->sample_period = 1;
 }
 
+static inline void ptrace_breakpoint_init(struct perf_event_attr *attr)
+{
+	hw_breakpoint_init(attr);
+	attr->exclude_kernel = 1;
+}
+
 static inline unsigned long hw_breakpoint_addr(struct perf_event *bp)
 {
 	return bp->attr.bp_addr;

kernel/hw_breakpoint.c

@@ -40,23 +40,29 @@
 #include <linux/percpu.h>
 #include <linux/sched.h>
 #include <linux/init.h>
+#include <linux/slab.h>
 #include <linux/cpu.h>
 #include <linux/smp.h>
 
 #include <linux/hw_breakpoint.h>
 
+
 /*
  * Constraints data
  */
 
 /* Number of pinned cpu breakpoints in a cpu */
-static DEFINE_PER_CPU(unsigned int, nr_cpu_bp_pinned);
+static DEFINE_PER_CPU(unsigned int, nr_cpu_bp_pinned[TYPE_MAX]);
 
 /* Number of pinned task breakpoints in a cpu */
-static DEFINE_PER_CPU(unsigned int, nr_task_bp_pinned[HBP_NUM]);
+static DEFINE_PER_CPU(unsigned int, *nr_task_bp_pinned[TYPE_MAX]);
 
 /* Number of non-pinned cpu/task breakpoints in a cpu */
-static DEFINE_PER_CPU(unsigned int, nr_bp_flexible);
+static DEFINE_PER_CPU(unsigned int, nr_bp_flexible[TYPE_MAX]);
+
+static int nr_slots[TYPE_MAX];
+
+static int constraints_initialized;
 
 /* Gather the number of total pinned and un-pinned bp in a cpuset */
 struct bp_busy_slots {
@@ -67,16 +73,29 @@ struct bp_busy_slots {
 /* Serialize accesses to the above constraints */
 static DEFINE_MUTEX(nr_bp_mutex);
 
+__weak int hw_breakpoint_weight(struct perf_event *bp)
+{
+	return 1;
+}
+
+static inline enum bp_type_idx find_slot_idx(struct perf_event *bp)
+{
+	if (bp->attr.bp_type & HW_BREAKPOINT_RW)
+		return TYPE_DATA;
+
+	return TYPE_INST;
+}
+
 /*
  * Report the maximum number of pinned breakpoints a task
  * have in this cpu
  */
-static unsigned int max_task_bp_pinned(int cpu)
+static unsigned int max_task_bp_pinned(int cpu, enum bp_type_idx type)
 {
 	int i;
-	unsigned int *tsk_pinned = per_cpu(nr_task_bp_pinned, cpu);
+	unsigned int *tsk_pinned = per_cpu(nr_task_bp_pinned[type], cpu);
 
-	for (i = HBP_NUM -1; i >= 0; i--) {
+	for (i = nr_slots[type] - 1; i >= 0; i--) {
 		if (tsk_pinned[i] > 0)
 			return i + 1;
 	}
@@ -84,7 +103,7 @@ static unsigned int max_task_bp_pinned(int cpu)
 	return 0;
 }
 
-static int task_bp_pinned(struct task_struct *tsk)
+static int task_bp_pinned(struct task_struct *tsk, enum bp_type_idx type)
 {
 	struct perf_event_context *ctx = tsk->perf_event_ctxp;
 	struct list_head *list;
@@ -105,7 +124,8 @@ static int task_bp_pinned(struct task_struct *tsk)
 	 */
 	list_for_each_entry(bp, list, event_entry) {
 		if (bp->attr.type == PERF_TYPE_BREAKPOINT)
-			count++;
+			if (find_slot_idx(bp) == type)
+				count += hw_breakpoint_weight(bp);
 	}
 
 	raw_spin_unlock_irqrestore(&ctx->lock, flags);
@@ -118,18 +138,19 @@ static int task_bp_pinned(struct task_struct *tsk)
  * a given cpu (cpu > -1) or in all of them (cpu = -1).
  */
 static void
-fetch_bp_busy_slots(struct bp_busy_slots *slots, struct perf_event *bp)
+fetch_bp_busy_slots(struct bp_busy_slots *slots, struct perf_event *bp,
+		    enum bp_type_idx type)
 {
 	int cpu = bp->cpu;
 	struct task_struct *tsk = bp->ctx->task;
 
 	if (cpu >= 0) {
-		slots->pinned = per_cpu(nr_cpu_bp_pinned, cpu);
+		slots->pinned = per_cpu(nr_cpu_bp_pinned[type], cpu);
 		if (!tsk)
-			slots->pinned += max_task_bp_pinned(cpu);
+			slots->pinned += max_task_bp_pinned(cpu, type);
 		else
-			slots->pinned += task_bp_pinned(tsk);
-		slots->flexible = per_cpu(nr_bp_flexible, cpu);
+			slots->pinned += task_bp_pinned(tsk, type);
+		slots->flexible = per_cpu(nr_bp_flexible[type], cpu);
 
 		return;
 	}
@@ -137,48 +158,66 @@ fetch_bp_busy_slots(struct bp_busy_slots *slots, struct perf_event *bp)
 	for_each_online_cpu(cpu) {
 		unsigned int nr;
 
-		nr = per_cpu(nr_cpu_bp_pinned, cpu);
+		nr = per_cpu(nr_cpu_bp_pinned[type], cpu);
 		if (!tsk)
-			nr += max_task_bp_pinned(cpu);
+			nr += max_task_bp_pinned(cpu, type);
 		else
-			nr += task_bp_pinned(tsk);
+			nr += task_bp_pinned(tsk, type);
 
 		if (nr > slots->pinned)
 			slots->pinned = nr;
 
-		nr = per_cpu(nr_bp_flexible, cpu);
+		nr = per_cpu(nr_bp_flexible[type], cpu);
 
 		if (nr > slots->flexible)
 			slots->flexible = nr;
 	}
 }
 
+/*
+ * For now, continue to consider flexible as pinned, until we can
+ * ensure no flexible event can ever be scheduled before a pinned event
+ * in a same cpu.
+ */
+static void
+fetch_this_slot(struct bp_busy_slots *slots, int weight)
+{
+	slots->pinned += weight;
+}
+
 /*
  * Add a pinned breakpoint for the given task in our constraint table
  */
-static void toggle_bp_task_slot(struct task_struct *tsk, int cpu, bool enable)
+static void toggle_bp_task_slot(struct task_struct *tsk, int cpu, bool enable,
+				enum bp_type_idx type, int weight)
 {
 	unsigned int *tsk_pinned;
-	int count = 0;
+	int old_count = 0;
+	int old_idx = 0;
+	int idx = 0;
 
-	count = task_bp_pinned(tsk);
+	old_count = task_bp_pinned(tsk, type);
+	old_idx = old_count - 1;
+	idx = old_idx + weight;
 
-	tsk_pinned = per_cpu(nr_task_bp_pinned, cpu);
+	tsk_pinned = per_cpu(nr_task_bp_pinned[type], cpu);
 	if (enable) {
-		tsk_pinned[count]++;
-		if (count > 0)
-			tsk_pinned[count-1]--;
+		tsk_pinned[idx]++;
+		if (old_count > 0)
+			tsk_pinned[old_idx]--;
 	} else {
-		tsk_pinned[count]--;
-		if (count > 0)
-			tsk_pinned[count-1]++;
+		tsk_pinned[idx]--;
+		if (old_count > 0)
+			tsk_pinned[old_idx]++;
 	}
 }
 
 /*
  * Add/remove the given breakpoint in our constraint table
  */
-static void toggle_bp_slot(struct perf_event *bp, bool enable)
+static void
+toggle_bp_slot(struct perf_event *bp, bool enable, enum bp_type_idx type,
+	       int weight)
 {
 	int cpu = bp->cpu;
 	struct task_struct *tsk = bp->ctx->task;
@@ -186,20 +225,20 @@ static void toggle_bp_slot(struct perf_event *bp, bool enable)
 	/* Pinned counter task profiling */
 	if (tsk) {
 		if (cpu >= 0) {
-			toggle_bp_task_slot(tsk, cpu, enable);
+			toggle_bp_task_slot(tsk, cpu, enable, type, weight);
 			return;
 		}
 
 		for_each_online_cpu(cpu)
-			toggle_bp_task_slot(tsk, cpu, enable);
+			toggle_bp_task_slot(tsk, cpu, enable, type, weight);
 		return;
 	}
 
 	/* Pinned counter cpu profiling */
 	if (enable)
-		per_cpu(nr_cpu_bp_pinned, bp->cpu)++;
+		per_cpu(nr_cpu_bp_pinned[type], bp->cpu) += weight;
 	else
-		per_cpu(nr_cpu_bp_pinned, bp->cpu)--;
+		per_cpu(nr_cpu_bp_pinned[type], bp->cpu) -= weight;
 }
 
 /*
@@ -246,14 +285,29 @@ static void toggle_bp_slot(struct perf_event *bp, bool enable)
 static int __reserve_bp_slot(struct perf_event *bp)
 {
 	struct bp_busy_slots slots = {0};
+	enum bp_type_idx type;
+	int weight;
 
-	fetch_bp_busy_slots(&slots, bp);
+	/* We couldn't initialize breakpoint constraints on boot */
+	if (!constraints_initialized)
+		return -ENOMEM;
+
+	/* Basic checks */
+	if (bp->attr.bp_type == HW_BREAKPOINT_EMPTY ||
+	    bp->attr.bp_type == HW_BREAKPOINT_INVALID)
+		return -EINVAL;
+
+	type = find_slot_idx(bp);
+	weight = hw_breakpoint_weight(bp);
+
+	fetch_bp_busy_slots(&slots, bp, type);
+	fetch_this_slot(&slots, weight);
 
 	/* Flexible counters need to keep at least one slot */
-	if (slots.pinned + (!!slots.flexible) == HBP_NUM)
+	if (slots.pinned + (!!slots.flexible) > nr_slots[type])
 		return -ENOSPC;
 
-	toggle_bp_slot(bp, true);
+	toggle_bp_slot(bp, true, type, weight);
 
 	return 0;
 }
@@ -273,7 +327,12 @@ int reserve_bp_slot(struct perf_event *bp)
 
 static void __release_bp_slot(struct perf_event *bp)
 {
-	toggle_bp_slot(bp, false);
+	enum bp_type_idx type;
+	int weight;
+
+	type = find_slot_idx(bp);
+	weight = hw_breakpoint_weight(bp);
+	toggle_bp_slot(bp, false, type, weight);
 }
 
 void release_bp_slot(struct perf_event *bp)
@@ -308,6 +367,28 @@ int dbg_release_bp_slot(struct perf_event *bp)
 	return 0;
 }
 
+static int validate_hw_breakpoint(struct perf_event *bp)
+{
+	int ret;
+
+	ret = arch_validate_hwbkpt_settings(bp);
+	if (ret)
+		return ret;
+
+	if (arch_check_bp_in_kernelspace(bp)) {
+		if (bp->attr.exclude_kernel)
+			return -EINVAL;
+		/*
+		 * Don't let unprivileged users set a breakpoint in the trap
+		 * path to avoid trap recursion attacks.
+		 */
+		if (!capable(CAP_SYS_ADMIN))
+			return -EPERM;
+	}
+
+	return 0;
+}
+
 int register_perf_hw_breakpoint(struct perf_event *bp)
 {
 	int ret;
@@ -316,17 +397,7 @@ int register_perf_hw_breakpoint(struct perf_event *bp)
 	if (ret)
 		return ret;
 
-	/*
-	 * Ptrace breakpoints can be temporary perf events only
-	 * meant to reserve a slot. In this case, it is created disabled and
-	 * we don't want to check the params right now (as we put a null addr)
-	 * But perf tools create events as disabled and we want to check
-	 * the params for them.
-	 * This is a quick hack that will be removed soon, once we remove
-	 * the tmp breakpoints from ptrace
-	 */
-	if (!bp->attr.disabled || !bp->overflow_handler)
-		ret = arch_validate_hwbkpt_settings(bp, bp->ctx->task);
+	ret = validate_hw_breakpoint(bp);
 
 	/* if arch_validate_hwbkpt_settings() fails then release bp slot */
 	if (ret)
@@ -373,7 +444,7 @@ int modify_user_hw_breakpoint(struct perf_event *bp, struct perf_event_attr *att
 	if (attr->disabled)
 		goto end;
 
-	err = arch_validate_hwbkpt_settings(bp, bp->ctx->task);
+	err = validate_hw_breakpoint(bp);
 	if (!err)
 		perf_event_enable(bp);
 
@@ -480,7 +551,36 @@ static struct notifier_block hw_breakpoint_exceptions_nb = {
 
 static int __init init_hw_breakpoint(void)
 {
+	unsigned int **task_bp_pinned;
+	int cpu, err_cpu;
+	int i;
+
+	for (i = 0; i < TYPE_MAX; i++)
+		nr_slots[i] = hw_breakpoint_slots(i);
+
+	for_each_possible_cpu(cpu) {
+		for (i = 0; i < TYPE_MAX; i++) {
+			task_bp_pinned = &per_cpu(nr_task_bp_pinned[i], cpu);
+			*task_bp_pinned = kzalloc(sizeof(int) * nr_slots[i],
+						  GFP_KERNEL);
+			if (!*task_bp_pinned)
+				goto err_alloc;
+		}
+	}
+
+	constraints_initialized = 1;
+
 	return register_die_notifier(&hw_breakpoint_exceptions_nb);
+
+ err_alloc:
+	for_each_possible_cpu(err_cpu) {
+		if (err_cpu == cpu)
+			break;
+		for (i = 0; i < TYPE_MAX; i++)
+			kfree(per_cpu(nr_task_bp_pinned[i], cpu));
+	}
+
+	return -ENOMEM;
 }
 core_initcall(init_hw_breakpoint);
 

kernel/trace/trace_ksym.c

@@ -34,12 +34,6 @@
 
 #include <asm/atomic.h>
 
-/*
- * For now, let us restrict the no. of symbols traced simultaneously to number
- * of available hardware breakpoint registers.
- */
-#define KSYM_TRACER_MAX HBP_NUM
-
 #define KSYM_TRACER_OP_LEN 3 /* rw- */
 
 struct trace_ksym {
@@ -53,7 +47,6 @@ struct trace_ksym {
 
 static struct trace_array *ksym_trace_array;
 
-static unsigned int ksym_filter_entry_count;
 static unsigned int ksym_tracing_enabled;
 
 static HLIST_HEAD(ksym_filter_head);
@@ -181,13 +174,6 @@ int process_new_ksym_entry(char *ksymname, int op, unsigned long addr)
 	struct trace_ksym *entry;
 	int ret = -ENOMEM;
 
-	if (ksym_filter_entry_count >= KSYM_TRACER_MAX) {
-		printk(KERN_ERR "ksym_tracer: Maximum limit:(%d) reached. No"
-		" new requests for tracing can be accepted now.\n",
-			KSYM_TRACER_MAX);
-		return -ENOSPC;
-	}
-
 	entry = kzalloc(sizeof(struct trace_ksym), GFP_KERNEL);
 	if (!entry)
 		return -ENOMEM;
@@ -203,13 +189,17 @@ int process_new_ksym_entry(char *ksymname, int op, unsigned long addr)
 
 	if (IS_ERR(entry->ksym_hbp)) {
 		ret = PTR_ERR(entry->ksym_hbp);
-		printk(KERN_INFO "ksym_tracer request failed. Try again"
-					" later!!\n");
+		if (ret == -ENOSPC) {
+			printk(KERN_ERR "ksym_tracer: Maximum limit reached."
+			" No new requests for tracing can be accepted now.\n");
+		} else {
+			printk(KERN_INFO "ksym_tracer request failed. Try again"
+					 " later!!\n");
+		}
 		goto err;
 	}
 
 	hlist_add_head_rcu(&(entry->ksym_hlist), &ksym_filter_head);
-	ksym_filter_entry_count++;
 
 	return 0;
 
@@ -265,7 +255,6 @@ static void __ksym_trace_reset(void)
 	hlist_for_each_entry_safe(entry, node, node1, &ksym_filter_head,
 								ksym_hlist) {
 		unregister_wide_hw_breakpoint(entry->ksym_hbp);
-		ksym_filter_entry_count--;
 		hlist_del_rcu(&(entry->ksym_hlist));
 		synchronize_rcu();
 		kfree(entry);
@@ -338,7 +327,6 @@ static ssize_t ksym_trace_filter_write(struct file *file,
 				goto out_unlock;
 		}
 		/* Error or "symbol:---" case: drop it */
-		ksym_filter_entry_count--;
 		hlist_del_rcu(&(entry->ksym_hlist));
 		synchronize_rcu();
 		kfree(entry);

tools/perf/Documentation/perf-trace-perl.txt

@@ -49,12 +49,10 @@ available as calls back into the perf executable (see below).
 As an example, the following perf record command can be used to record
 all sched_wakeup events in the system:
 
- # perf record -c 1 -f -a -M -R -e sched:sched_wakeup
+ # perf record -a -e sched:sched_wakeup
 
 Traces meant to be processed using a script should be recorded with
-the above options: -c 1 says to sample every event, -a to enable
-system-wide collection, -M to multiplex the output, and -R to collect
-raw samples.
+the above option: -a to enable system-wide collection.
 
 The format file for the sched_wakep event defines the following fields
 (see /sys/kernel/debug/tracing/events/sched/sched_wakeup/format):

tools/perf/Documentation/perf-trace-python.txt

@@ -93,7 +93,7 @@ don't care how it exited, so we'll use 'perf record' to record only
 the sys_enter events:
 
 ----
-# perf record -c 1 -f -a -M -R -e raw_syscalls:sys_enter
+# perf record -a -e raw_syscalls:sys_enter
 
 ^C[ perf record: Woken up 1 times to write data ]
 [ perf record: Captured and wrote 56.545 MB perf.data (~2470503 samples) ]
@@ -359,7 +359,7 @@ your script:
 # cat kernel-source/tools/perf/scripts/python/bin/syscall-counts-record
 
 #!/bin/bash
-perf record -c 1 -f -a -M -R -e raw_syscalls:sys_enter
+perf record -a -e raw_syscalls:sys_enter
 ----
 
 The 'report' script is also a shell script with the same base name as
@@ -449,12 +449,10 @@ available as calls back into the perf executable (see below).
 As an example, the following perf record command can be used to record
 all sched_wakeup events in the system:
 
- # perf record -c 1 -f -a -M -R -e sched:sched_wakeup
+ # perf record -a -e sched:sched_wakeup
 
 Traces meant to be processed using a script should be recorded with
-the above options: -c 1 says to sample every event, -a to enable
-system-wide collection, -M to multiplex the output, and -R to collect
-raw samples.
+the above option: -a to enable system-wide collection.
 
 The format file for the sched_wakep event defines the following fields
 (see /sys/kernel/debug/tracing/events/sched/sched_wakeup/format):

tools/perf/scripts/perl/bin/check-perf-trace-record

@@ -1,2 +1,2 @@
 #!/bin/bash
-perf record -c 1 -f -a -M -R -e kmem:kmalloc -e irq:softirq_entry -e kmem:kfree
+perf record -a -e kmem:kmalloc -e irq:softirq_entry -e kmem:kfree

tools/perf/scripts/perl/bin/failed-syscalls-record

@@ -1,2 +1,2 @@
 #!/bin/bash
-perf record -c 1 -f -a -M -R -e raw_syscalls:sys_exit $@
+perf record -a -e raw_syscalls:sys_exit $@

tools/perf/scripts/perl/bin/rw-by-file-record

@@ -1,3 +1,3 @@
 #!/bin/bash
-perf record -c 1 -f -a -M -R -e syscalls:sys_enter_read -e syscalls:sys_enter_write $@
+perf record -a -e syscalls:sys_enter_read -e syscalls:sys_enter_write $@
 

tools/perf/scripts/perl/bin/rw-by-pid-record

@@ -1,2 +1,2 @@
 #!/bin/bash
-perf record -c 1 -f -a -M -R -e syscalls:sys_enter_read -e syscalls:sys_exit_read -e syscalls:sys_enter_write -e syscalls:sys_exit_write $@
+perf record -a -e syscalls:sys_enter_read -e syscalls:sys_exit_read -e syscalls:sys_enter_write -e syscalls:sys_exit_write $@

tools/perf/scripts/perl/bin/rwtop-record

@@ -1,2 +1,2 @@
 #!/bin/bash
-perf record -c 1 -f -a -M -R -e syscalls:sys_enter_read -e syscalls:sys_exit_read -e syscalls:sys_enter_write -e syscalls:sys_exit_write $@
+perf record -a -e syscalls:sys_enter_read -e syscalls:sys_exit_read -e syscalls:sys_enter_write -e syscalls:sys_exit_write $@

tools/perf/scripts/perl/bin/wakeup-latency-record

@@ -1,5 +1,5 @@
 #!/bin/bash
-perf record -c 1 -f -a -M -R -e sched:sched_switch -e sched:sched_wakeup $@
+perf record -a -e sched:sched_switch -e sched:sched_wakeup $@
 
 
 

tools/perf/scripts/perl/bin/workqueue-stats-record

@@ -1,2 +1,2 @@
 #!/bin/bash
-perf record -c 1 -f -a -M -R -e workqueue:workqueue_creation -e workqueue:workqueue_destruction -e workqueue:workqueue_execution -e workqueue:workqueue_insertion $@
+perf record -a -e workqueue:workqueue_creation -e workqueue:workqueue_destruction -e workqueue:workqueue_execution -e workqueue:workqueue_insertion $@

tools/perf/scripts/python/bin/failed-syscalls-by-pid-record

@@ -1,2 +1,2 @@
 #!/bin/bash
-perf record -c 1 -f -a -M -R -e raw_syscalls:sys_exit $@
+perf record -a -e raw_syscalls:sys_exit $@

tools/perf/scripts/python/bin/sctop-record

@@ -1,2 +1,2 @@
 #!/bin/bash
-perf record -c 1 -f -a -M -R -e raw_syscalls:sys_enter $@
+perf record -a -e raw_syscalls:sys_enter $@

tools/perf/scripts/python/bin/syscall-counts-by-pid-record

@@ -1,2 +1,2 @@
 #!/bin/bash
-perf record -c 1 -f -a -M -R -e raw_syscalls:sys_enter $@
+perf record -a -e raw_syscalls:sys_enter $@

tools/perf/scripts/python/bin/syscall-counts-record

@@ -1,2 +1,2 @@
 #!/bin/bash
-perf record -c 1 -f -a -M -R -e raw_syscalls:sys_enter $@
+perf record -a -e raw_syscalls:sys_enter $@

tools/perf/util/trace-event-parse.c

@@ -691,11 +691,6 @@ static int __read_expected(enum event_type expect, const char *str,
 	return ret;
 }
 
-static int read_expected_warn(enum event_type expect, const char *str, bool warn)
-{
-	return __read_expected(expect, str, 1, warn);
-}
-
 static int read_expected(enum event_type expect, const char *str)
 {
 	return __read_expected(expect, str, 1, true);
@@ -3104,90 +3099,6 @@ static void print_args(struct print_arg *args)
 	}
 }
 
-static void parse_header_field(const char *field,
-			       int *offset, int *size, bool warn)
-{
-	char *token;
-	int type;
-
-	if (read_expected(EVENT_ITEM, "field") < 0)
-		return;
-	if (read_expected(EVENT_OP, ":") < 0)
-		return;
-
-	/* type */
-	if (read_expect_type(EVENT_ITEM, &token) < 0)
-		goto fail;
-	free_token(token);
-
-	if (read_expected_warn(EVENT_ITEM, field, warn) < 0)
-		return;
-	if (read_expected(EVENT_OP, ";") < 0)
-		return;
-	if (read_expected(EVENT_ITEM, "offset") < 0)
-		return;
-	if (read_expected(EVENT_OP, ":") < 0)
-		return;
-	if (read_expect_type(EVENT_ITEM, &token) < 0)
-		goto fail;
-	*offset = atoi(token);
-	free_token(token);
-	if (read_expected(EVENT_OP, ";") < 0)
-		return;
-	if (read_expected(EVENT_ITEM, "size") < 0)
-		return;
-	if (read_expected(EVENT_OP, ":") < 0)
-		return;
-	if (read_expect_type(EVENT_ITEM, &token) < 0)
-		goto fail;
-	*size = atoi(token);
-	free_token(token);
-	if (read_expected(EVENT_OP, ";") < 0)
-		return;
-	type = read_token(&token);
-	if (type != EVENT_NEWLINE) {
-		/* newer versions of the kernel have a "signed" type */
-		if (type != EVENT_ITEM)
-			goto fail;
-
-		if (strcmp(token, "signed") != 0)
-			goto fail;
-
-		free_token(token);
-
-		if (read_expected(EVENT_OP, ":") < 0)
-			return;
-
-		if (read_expect_type(EVENT_ITEM, &token))
-			goto fail;
-
-		free_token(token);
-		if (read_expected(EVENT_OP, ";") < 0)
-			return;
-
-		if (read_expect_type(EVENT_NEWLINE, &token))
-			goto fail;
-	}
- fail:
-	free_token(token);
-}
-
-int parse_header_page(char *buf, unsigned long size)
-{
-	init_input_buf(buf, size);
-
-	parse_header_field("timestamp", &header_page_ts_offset,
-			   &header_page_ts_size, true);
-	parse_header_field("commit", &header_page_size_offset,
-			   &header_page_size_size, true);
-	parse_header_field("overwrite", &header_page_overwrite_offset,
-			   &header_page_overwrite_size, false);
-	parse_header_field("data", &header_page_data_offset,
-			   &header_page_data_size, true);
-
-	return 0;
-}
-
 int parse_ftrace_file(char *buf, unsigned long size)
 {
 	struct format_field *field;

tools/perf/util/trace-event-read.c

@@ -53,6 +53,12 @@ static unsigned long	page_size;
 static ssize_t calc_data_size;
 static bool repipe;
 
+/* If it fails, the next read will report it */
+static void skip(int size)
+{
+	lseek(input_fd, size, SEEK_CUR);
+}
+
 static int do_read(int fd, void *buf, int size)
 {
 	int rsize = size;
@@ -184,7 +190,6 @@ static void read_ftrace_printk(void)
 static void read_header_files(void)
 {
 	unsigned long long size;
-	char *header_page;
 	char *header_event;
 	char buf[BUFSIZ];
 
@@ -194,10 +199,7 @@ static void read_header_files(void)
 		die("did not read header page");
 
 	size = read8();
-	header_page = malloc_or_die(size);
-	read_or_die(header_page, size);
-	parse_header_page(header_page, size);
-	free(header_page);
+	skip(size);
 
 	/*
 	 * The size field in the page is of type long,

tools/perf/util/trace-event.h

@@ -244,7 +244,6 @@ extern int header_page_data_size;
 
 extern bool latency_format;
 
-int parse_header_page(char *buf, unsigned long size);
 int trace_parse_common_type(void *data);
 int trace_parse_common_pid(void *data);
 int parse_common_pc(void *data);