Merge tag 'perf-core-2020-08-03' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf event updates from Ingo Molnar:
 "HW support updates:

   - Add uncore support for Intel Comet Lake

   - Add RAPL support for Hygon Fam18h

   - Add Intel "IIO stack to PMON mapping" support on Skylake-SP CPUs,
     which enumerates per device performance counters via sysfs and
     enables the perf stat --iiostat functionality

   - Add support for Intel "Architectural LBRs", which generalized the
     model specific LBR hardware tracing feature into a
     model-independent, architected performance monitoring feature.

     Usage is mostly seamless to tooling, as the pre-existing LBR
     features are kept, but there's a couple of advantages under the
     hood, such as faster context-switching, faster LBR reads, cleaner
     exposure of LBR features to guest kernels, etc.

     ( Since architectural LBRs are supported via XSAVE, there's related
       changes to the x86 FPU code as well. )

  ftrace/perf updates:

   - Add support to add a text poke event to record changes to kernel
     text (i.e. self-modifying code) in order to support tracers like
     Intel PT decoding through jump labels, kprobes and ftrace
     trampolines.

  Misc cleanups, smaller fixes..."

* tag 'perf-core-2020-08-03' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (47 commits)
  perf/x86/rapl: Add Hygon Fam18h RAPL support
  kprobes: Remove unnecessary module_mutex locking from kprobe_optimizer()
  x86/perf: Fix a typo
  perf: <linux/perf_event.h>: drop a duplicated word
  perf/x86/intel/lbr: Support XSAVES for arch LBR read
  perf/x86/intel/lbr: Support XSAVES/XRSTORS for LBR context switch
  x86/fpu/xstate: Add helpers for LBR dynamic supervisor feature
  x86/fpu/xstate: Support dynamic supervisor feature for LBR
  x86/fpu: Use proper mask to replace full instruction mask
  perf/x86: Remove task_ctx_size
  perf/x86/intel/lbr: Create kmem_cache for the LBR context data
  perf/core: Use kmem_cache to allocate the PMU specific data
  perf/core: Factor out functions to allocate/free the task_ctx_data
  perf/x86/intel/lbr: Support Architectural LBR
  perf/x86/intel/lbr: Factor out intel_pmu_store_lbr
  perf/x86/intel/lbr: Factor out rdlbr_all() and wrlbr_all()
  perf/x86/intel/lbr: Mark the {rd,wr}lbr_{to,from} wrappers __always_inline
  perf/x86/intel/lbr: Unify the stored format of LBR information
  perf/x86/intel/lbr: Support LBR_CTL
  perf/x86: Expose CPUID enumeration bits for arch LBR
  ...

4 files changed, 60 insertions, 8 deletions

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index e339dac91ee6..ce2c06f72e86 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -58,9 +58,6 @@ struct ftrace_direct_func;
 const char *
 ftrace_mod_address_lookup(unsigned long addr, unsigned long *size,
 		   unsigned long *off, char **modname, char *sym);
-int ftrace_mod_get_kallsym(unsigned int symnum, unsigned long *value,
-			   char *type, char *name,
-			   char *module_name, int *exported);
 #else
 static inline const char *
 ftrace_mod_address_lookup(unsigned long addr, unsigned long *size,
@@ -68,6 +65,13 @@ ftrace_mod_address_lookup(unsigned long addr, unsigned long *size,
 {
 	return NULL;
 }
+#endif
+
+#if defined(CONFIG_FUNCTION_TRACER) && defined(CONFIG_DYNAMIC_FTRACE)
+int ftrace_mod_get_kallsym(unsigned int symnum, unsigned long *value,
+			   char *type, char *name,
+			   char *module_name, int *exported);
+#else
 static inline int ftrace_mod_get_kallsym(unsigned int symnum, unsigned long *value,
 					 char *type, char *name,
 					 char *module_name, int *exported)
@@ -76,7 +80,6 @@ static inline int ftrace_mod_get_kallsym(unsigned int symnum, unsigned long *val
 }
 #endif
 
-
 #ifdef CONFIG_FUNCTION_TRACER
 
 extern int ftrace_enabled;
@@ -207,6 +210,7 @@ struct ftrace_ops {
 	struct ftrace_ops_hash		old_hash;
 	unsigned long			trampoline;
 	unsigned long			trampoline_size;
+	struct list_head		list;
 #endif
 };
 
diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h
index 6adf90f248d7..45b8cdc9fad7 100644
--- a/include/linux/kprobes.h
+++ b/include/linux/kprobes.h
@@ -242,6 +242,7 @@ struct kprobe_insn_cache {
 	struct mutex mutex;
 	void *(*alloc)(void);	/* allocate insn page */
 	void (*free)(void *);	/* free insn page */
+	const char *sym;	/* symbol for insn pages */
 	struct list_head pages; /* list of kprobe_insn_page */
 	size_t insn_size;	/* size of instruction slot */
 	int nr_garbage;
@@ -272,6 +273,10 @@ static inline bool is_kprobe_##__name##_slot(unsigned long addr)	\
 {									\
 	return __is_insn_slot_addr(&kprobe_##__name##_slots, addr);	\
 }
+#define KPROBE_INSN_PAGE_SYM		"kprobe_insn_page"
+#define KPROBE_OPTINSN_PAGE_SYM		"kprobe_optinsn_page"
+int kprobe_cache_get_kallsym(struct kprobe_insn_cache *c, unsigned int *symnum,
+			     unsigned long *value, char *type, char *sym);
 #else /* __ARCH_WANT_KPROBES_INSN_SLOT */
 #define DEFINE_INSN_CACHE_OPS(__name)					\
 static inline bool is_kprobe_##__name##_slot(unsigned long addr)	\
@@ -377,6 +382,11 @@ void dump_kprobe(struct kprobe *kp);
 void *alloc_insn_page(void);
 void free_insn_page(void *page);
 
+int kprobe_get_kallsym(unsigned int symnum, unsigned long *value, char *type,
+		       char *sym);
+
+int arch_kprobe_get_kallsym(unsigned int *symnum, unsigned long *value,
+			    char *type, char *sym);
 #else /* !CONFIG_KPROBES: */
 
 static inline int kprobes_built_in(void)
@@ -439,6 +449,11 @@ static inline bool within_kprobe_blacklist(unsigned long addr)
 {
 	return true;
 }
+static inline int kprobe_get_kallsym(unsigned int symnum, unsigned long *value,
+				     char *type, char *sym)
+{
+	return -ERANGE;
+}
 #endif /* CONFIG_KPROBES */
 static inline int disable_kretprobe(struct kretprobe *rp)
 {
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index b4bb32082342..0edd257a5916 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -366,7 +366,7 @@ struct pmu {
 	 * ->stop() with PERF_EF_UPDATE will read the counter and update
 	 *  period/count values like ->read() would.
 	 *
-	 * ->start() with PERF_EF_RELOAD will reprogram the the counter
+	 * ->start() with PERF_EF_RELOAD will reprogram the counter
 	 *  value, must be preceded by a ->stop() with PERF_EF_UPDATE.
 	 */
 	void (*start)			(struct perf_event *event, int flags);
@@ -419,10 +419,11 @@ struct pmu {
 	 */
 	void (*sched_task)		(struct perf_event_context *ctx,
 					bool sched_in);
+
 	/*
-	 * PMU specific data size
+	 * Kmem cache of PMU specific data
 	 */
-	size_t				task_ctx_size;
+	struct kmem_cache		*task_ctx_cache;
 
 	/*
 	 * PMU specific parts of task perf event context (i.e. ctx->task_ctx_data)
@@ -1232,6 +1233,9 @@ extern void perf_event_exec(void);
 extern void perf_event_comm(struct task_struct *tsk, bool exec);
 extern void perf_event_namespaces(struct task_struct *tsk);
 extern void perf_event_fork(struct task_struct *tsk);
+extern void perf_event_text_poke(const void *addr,
+				 const void *old_bytes, size_t old_len,
+				 const void *new_bytes, size_t new_len);
 
 /* Callchains */
 DECLARE_PER_CPU(struct perf_callchain_entry, perf_callchain_entry);
@@ -1479,6 +1483,11 @@ static inline void perf_event_exec(void)				{ }
 static inline void perf_event_comm(struct task_struct *tsk, bool exec)	{ }
 static inline void perf_event_namespaces(struct task_struct *tsk)	{ }
 static inline void perf_event_fork(struct task_struct *tsk)		{ }
+static inline void perf_event_text_poke(const void *addr,
+					const void *old_bytes,
+					size_t old_len,
+					const void *new_bytes,
+					size_t new_len)			{ }
 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)		{ }
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index 21a1edd08cbe..077e7ee69e3d 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -383,7 +383,8 @@ struct perf_event_attr {
 				bpf_event      :  1, /* include bpf events */
 				aux_output     :  1, /* generate AUX records instead of events */
 				cgroup         :  1, /* include cgroup events */
-				__reserved_1   : 31;
+				text_poke      :  1, /* include text poke events */
+				__reserved_1   : 30;
 
 	union {
 		__u32		wakeup_events;	  /* wakeup every n events */
@@ -1041,12 +1042,35 @@ enum perf_event_type {
 	 */
 	PERF_RECORD_CGROUP			= 19,
 
+	/*
+	 * Records changes to kernel text i.e. self-modified code. 'old_len' is
+	 * the number of old bytes, 'new_len' is the number of new bytes. Either
+	 * 'old_len' or 'new_len' may be zero to indicate, for example, the
+	 * addition or removal of a trampoline. 'bytes' contains the old bytes
+	 * followed immediately by the new bytes.
+	 *
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *	u64				addr;
+	 *	u16				old_len;
+	 *	u16				new_len;
+	 *	u8				bytes[];
+	 *	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_TEXT_POKE			= 20,
+
 	PERF_RECORD_MAX,			/* non-ABI */
 };
 
 enum perf_record_ksymbol_type {
 	PERF_RECORD_KSYMBOL_TYPE_UNKNOWN	= 0,
 	PERF_RECORD_KSYMBOL_TYPE_BPF		= 1,
+	/*
+	 * Out of line code such as kprobe-replaced instructions or optimized
+	 * kprobes or ftrace trampolines.
+	 */
+	PERF_RECORD_KSYMBOL_TYPE_OOL		= 2,
 	PERF_RECORD_KSYMBOL_TYPE_MAX		/* non-ABI */
 };