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
  ...

kernel/events/core.c

@@ -394,6 +394,7 @@ static atomic_t nr_switch_events __read_mostly;
 static atomic_t nr_ksymbol_events __read_mostly;
 static atomic_t nr_bpf_events __read_mostly;
 static atomic_t nr_cgroup_events __read_mostly;
+static atomic_t nr_text_poke_events __read_mostly;
 
 static LIST_HEAD(pmus);
 static DEFINE_MUTEX(pmus_lock);
@@ -1237,12 +1238,26 @@ static void get_ctx(struct perf_event_context *ctx)
 	refcount_inc(&ctx->refcount);
 }
 
+static void *alloc_task_ctx_data(struct pmu *pmu)
+{
+	if (pmu->task_ctx_cache)
+		return kmem_cache_zalloc(pmu->task_ctx_cache, GFP_KERNEL);
+
+	return NULL;
+}
+
+static void free_task_ctx_data(struct pmu *pmu, void *task_ctx_data)
+{
+	if (pmu->task_ctx_cache && task_ctx_data)
+		kmem_cache_free(pmu->task_ctx_cache, task_ctx_data);
+}
+
 static void free_ctx(struct rcu_head *head)
 {
 	struct perf_event_context *ctx;
 
 	ctx = container_of(head, struct perf_event_context, rcu_head);
-	kfree(ctx->task_ctx_data);
+	free_task_ctx_data(ctx->pmu, ctx->task_ctx_data);
 	kfree(ctx);
 }
 
@@ -4470,7 +4485,7 @@ find_get_context(struct pmu *pmu, struct task_struct *task,
 		goto errout;
 
 	if (event->attach_state & PERF_ATTACH_TASK_DATA) {
-		task_ctx_data = kzalloc(pmu->task_ctx_size, GFP_KERNEL);
+		task_ctx_data = alloc_task_ctx_data(pmu);
 		if (!task_ctx_data) {
 			err = -ENOMEM;
 			goto errout;
@@ -4528,11 +4543,11 @@ retry:
 		}
 	}
 
-	kfree(task_ctx_data);
+	free_task_ctx_data(pmu, task_ctx_data);
 	return ctx;
 
 errout:
-	kfree(task_ctx_data);
+	free_task_ctx_data(pmu, task_ctx_data);
 	return ERR_PTR(err);
 }
 
@@ -4575,7 +4590,7 @@ static bool is_sb_event(struct perf_event *event)
 	if (attr->mmap || attr->mmap_data || attr->mmap2 ||
 	    attr->comm || attr->comm_exec ||
 	    attr->task || attr->ksymbol ||
-	    attr->context_switch ||
+	    attr->context_switch || attr->text_poke ||
 	    attr->bpf_event)
 		return true;
 	return false;
@@ -4651,6 +4666,8 @@ static void unaccount_event(struct perf_event *event)
 		atomic_dec(&nr_ksymbol_events);
 	if (event->attr.bpf_event)
 		atomic_dec(&nr_bpf_events);
+	if (event->attr.text_poke)
+		atomic_dec(&nr_text_poke_events);
 
 	if (dec) {
 		if (!atomic_add_unless(&perf_sched_count, -1, 1))
@@ -8628,6 +8645,89 @@ void perf_event_bpf_event(struct bpf_prog *prog,
 	perf_iterate_sb(perf_event_bpf_output, &bpf_event, NULL);
 }
 
+struct perf_text_poke_event {
+	const void		*old_bytes;
+	const void		*new_bytes;
+	size_t			pad;
+	u16			old_len;
+	u16			new_len;
+
+	struct {
+		struct perf_event_header	header;
+
+		u64				addr;
+	} event_id;
+};
+
+static int perf_event_text_poke_match(struct perf_event *event)
+{
+	return event->attr.text_poke;
+}
+
+static void perf_event_text_poke_output(struct perf_event *event, void *data)
+{
+	struct perf_text_poke_event *text_poke_event = data;
+	struct perf_output_handle handle;
+	struct perf_sample_data sample;
+	u64 padding = 0;
+	int ret;
+
+	if (!perf_event_text_poke_match(event))
+		return;
+
+	perf_event_header__init_id(&text_poke_event->event_id.header, &sample, event);
+
+	ret = perf_output_begin(&handle, event, text_poke_event->event_id.header.size);
+	if (ret)
+		return;
+
+	perf_output_put(&handle, text_poke_event->event_id);
+	perf_output_put(&handle, text_poke_event->old_len);
+	perf_output_put(&handle, text_poke_event->new_len);
+
+	__output_copy(&handle, text_poke_event->old_bytes, text_poke_event->old_len);
+	__output_copy(&handle, text_poke_event->new_bytes, text_poke_event->new_len);
+
+	if (text_poke_event->pad)
+		__output_copy(&handle, &padding, text_poke_event->pad);
+
+	perf_event__output_id_sample(event, &handle, &sample);
+
+	perf_output_end(&handle);
+}
+
+void perf_event_text_poke(const void *addr, const void *old_bytes,
+			  size_t old_len, const void *new_bytes, size_t new_len)
+{
+	struct perf_text_poke_event text_poke_event;
+	size_t tot, pad;
+
+	if (!atomic_read(&nr_text_poke_events))
+		return;
+
+	tot  = sizeof(text_poke_event.old_len) + old_len;
+	tot += sizeof(text_poke_event.new_len) + new_len;
+	pad  = ALIGN(tot, sizeof(u64)) - tot;
+
+	text_poke_event = (struct perf_text_poke_event){
+		.old_bytes    = old_bytes,
+		.new_bytes    = new_bytes,
+		.pad          = pad,
+		.old_len      = old_len,
+		.new_len      = new_len,
+		.event_id  = {
+			.header = {
+				.type = PERF_RECORD_TEXT_POKE,
+				.misc = PERF_RECORD_MISC_KERNEL,
+				.size = sizeof(text_poke_event.event_id) + tot + pad,
+			},
+			.addr = (unsigned long)addr,
+		},
+	};
+
+	perf_iterate_sb(perf_event_text_poke_output, &text_poke_event, NULL);
+}
+
 void perf_event_itrace_started(struct perf_event *event)
 {
 	event->attach_state |= PERF_ATTACH_ITRACE;
@@ -10945,6 +11045,8 @@ static void account_event(struct perf_event *event)
 		atomic_inc(&nr_ksymbol_events);
 	if (event->attr.bpf_event)
 		atomic_inc(&nr_bpf_events);
+	if (event->attr.text_poke)
+		atomic_inc(&nr_text_poke_events);
 
 	if (inc) {
 		/*
@@ -12409,8 +12511,7 @@ inherit_event(struct perf_event *parent_event,
 	    !child_ctx->task_ctx_data) {
 		struct pmu *pmu = child_event->pmu;
 
-		child_ctx->task_ctx_data = kzalloc(pmu->task_ctx_size,
-						   GFP_KERNEL);
+		child_ctx->task_ctx_data = alloc_task_ctx_data(pmu);
 		if (!child_ctx->task_ctx_data) {
 			free_event(child_event);
 			return ERR_PTR(-ENOMEM);

kernel/kallsyms.c

@@ -24,6 +24,7 @@
 #include <linux/slab.h>
 #include <linux/filter.h>
 #include <linux/ftrace.h>
+#include <linux/kprobes.h>
 #include <linux/compiler.h>
 
 /*
@@ -437,6 +438,7 @@ struct kallsym_iter {
 	loff_t pos_arch_end;
 	loff_t pos_mod_end;
 	loff_t pos_ftrace_mod_end;
+	loff_t pos_bpf_end;
 	unsigned long value;
 	unsigned int nameoff; /* If iterating in core kernel symbols. */
 	char type;
@@ -480,6 +482,11 @@ static int get_ksymbol_mod(struct kallsym_iter *iter)
 	return 1;
 }
 
+/*
+ * ftrace_mod_get_kallsym() may also get symbols for pages allocated for ftrace
+ * purposes. In that case "__builtin__ftrace" is used as a module name, even
+ * though "__builtin__ftrace" is not a module.
+ */
 static int get_ksymbol_ftrace_mod(struct kallsym_iter *iter)
 {
 	int ret = ftrace_mod_get_kallsym(iter->pos - iter->pos_mod_end,
@@ -496,11 +503,33 @@ static int get_ksymbol_ftrace_mod(struct kallsym_iter *iter)
 
 static int get_ksymbol_bpf(struct kallsym_iter *iter)
 {
+	int ret;
+
 	strlcpy(iter->module_name, "bpf", MODULE_NAME_LEN);
 	iter->exported = 0;
-	return bpf_get_kallsym(iter->pos - iter->pos_ftrace_mod_end,
-			       &iter->value, &iter->type,
-			       iter->name) < 0 ? 0 : 1;
+	ret = bpf_get_kallsym(iter->pos - iter->pos_ftrace_mod_end,
+			      &iter->value, &iter->type,
+			      iter->name);
+	if (ret < 0) {
+		iter->pos_bpf_end = iter->pos;
+		return 0;
+	}
+
+	return 1;
+}
+
+/*
+ * This uses "__builtin__kprobes" as a module name for symbols for pages
+ * allocated for kprobes' purposes, even though "__builtin__kprobes" is not a
+ * module.
+ */
+static int get_ksymbol_kprobe(struct kallsym_iter *iter)
+{
+	strlcpy(iter->module_name, "__builtin__kprobes", MODULE_NAME_LEN);
+	iter->exported = 0;
+	return kprobe_get_kallsym(iter->pos - iter->pos_bpf_end,
+				  &iter->value, &iter->type,
+				  iter->name) < 0 ? 0 : 1;
 }
 
 /* Returns space to next name. */
@@ -527,6 +556,7 @@ static void reset_iter(struct kallsym_iter *iter, loff_t new_pos)
 		iter->pos_arch_end = 0;
 		iter->pos_mod_end = 0;
 		iter->pos_ftrace_mod_end = 0;
+		iter->pos_bpf_end = 0;
 	}
 }
 
@@ -551,7 +581,11 @@ static int update_iter_mod(struct kallsym_iter *iter, loff_t pos)
 	    get_ksymbol_ftrace_mod(iter))
 		return 1;
 
-	return get_ksymbol_bpf(iter);
+	if ((!iter->pos_bpf_end || iter->pos_bpf_end > pos) &&
+	    get_ksymbol_bpf(iter))
+		return 1;
+
+	return get_ksymbol_kprobe(iter);
 }
 
 /* Returns false if pos at or past end of file. */

kernel/kprobes.c

@@ -35,6 +35,7 @@
 #include <linux/ftrace.h>
 #include <linux/cpu.h>
 #include <linux/jump_label.h>
+#include <linux/perf_event.h>
 
 #include <asm/sections.h>
 #include <asm/cacheflush.h>
@@ -123,6 +124,7 @@ struct kprobe_insn_cache kprobe_insn_slots = {
 	.mutex = __MUTEX_INITIALIZER(kprobe_insn_slots.mutex),
 	.alloc = alloc_insn_page,
 	.free = free_insn_page,
+	.sym = KPROBE_INSN_PAGE_SYM,
 	.pages = LIST_HEAD_INIT(kprobe_insn_slots.pages),
 	.insn_size = MAX_INSN_SIZE,
 	.nr_garbage = 0,
@@ -188,6 +190,10 @@ kprobe_opcode_t *__get_insn_slot(struct kprobe_insn_cache *c)
 	kip->cache = c;
 	list_add_rcu(&kip->list, &c->pages);
 	slot = kip->insns;
+
+	/* Record the perf ksymbol register event after adding the page */
+	perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_OOL, (unsigned long)kip->insns,
+			   PAGE_SIZE, false, c->sym);
 out:
 	mutex_unlock(&c->mutex);
 	return slot;
@@ -206,6 +212,13 @@ static int collect_one_slot(struct kprobe_insn_page *kip, int idx)
 		 * next time somebody inserts a probe.
 		 */
 		if (!list_is_singular(&kip->list)) {
+			/*
+			 * Record perf ksymbol unregister event before removing
+			 * the page.
+			 */
+			perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_OOL,
+					   (unsigned long)kip->insns, PAGE_SIZE, true,
+					   kip->cache->sym);
 			list_del_rcu(&kip->list);
 			synchronize_rcu();
 			kip->cache->free(kip->insns);
@@ -295,12 +308,34 @@ bool __is_insn_slot_addr(struct kprobe_insn_cache *c, unsigned long addr)
 	return ret;
 }
 
+int kprobe_cache_get_kallsym(struct kprobe_insn_cache *c, unsigned int *symnum,
+			     unsigned long *value, char *type, char *sym)
+{
+	struct kprobe_insn_page *kip;
+	int ret = -ERANGE;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(kip, &c->pages, list) {
+		if ((*symnum)--)
+			continue;
+		strlcpy(sym, c->sym, KSYM_NAME_LEN);
+		*type = 't';
+		*value = (unsigned long)kip->insns;
+		ret = 0;
+		break;
+	}
+	rcu_read_unlock();
+
+	return ret;
+}
+
 #ifdef CONFIG_OPTPROBES
 /* For optimized_kprobe buffer */
 struct kprobe_insn_cache kprobe_optinsn_slots = {
 	.mutex = __MUTEX_INITIALIZER(kprobe_optinsn_slots.mutex),
 	.alloc = alloc_insn_page,
 	.free = free_insn_page,
+	.sym = KPROBE_OPTINSN_PAGE_SYM,
 	.pages = LIST_HEAD_INIT(kprobe_optinsn_slots.pages),
 	/* .insn_size is initialized later */
 	.nr_garbage = 0,
@@ -563,8 +598,6 @@ static void kprobe_optimizer(struct work_struct *work)
 	mutex_lock(&kprobe_mutex);
 	cpus_read_lock();
 	mutex_lock(&text_mutex);
-	/* Lock modules while optimizing kprobes */
-	mutex_lock(&module_mutex);
 
 	/*
 	 * Step 1: Unoptimize kprobes and collect cleaned (unused and disarmed)
@@ -589,7 +622,6 @@ static void kprobe_optimizer(struct work_struct *work)
 	/* Step 4: Free cleaned kprobes after quiesence period */
 	do_free_cleaned_kprobes();
 
-	mutex_unlock(&module_mutex);
 	mutex_unlock(&text_mutex);
 	cpus_read_unlock();
 
@@ -2232,6 +2264,28 @@ static void kprobe_remove_ksym_blacklist(unsigned long entry)
 	kprobe_remove_area_blacklist(entry, entry + 1);
 }
 
+int __weak arch_kprobe_get_kallsym(unsigned int *symnum, unsigned long *value,
+				   char *type, char *sym)
+{
+	return -ERANGE;
+}
+
+int kprobe_get_kallsym(unsigned int symnum, unsigned long *value, char *type,
+		       char *sym)
+{
+#ifdef __ARCH_WANT_KPROBES_INSN_SLOT
+	if (!kprobe_cache_get_kallsym(&kprobe_insn_slots, &symnum, value, type, sym))
+		return 0;
+#ifdef CONFIG_OPTPROBES
+	if (!kprobe_cache_get_kallsym(&kprobe_optinsn_slots, &symnum, value, type, sym))
+		return 0;
+#endif
+#endif
+	if (!arch_kprobe_get_kallsym(&symnum, value, type, sym))
+		return 0;
+	return -ERANGE;
+}
+
 int __init __weak arch_populate_kprobe_blacklist(void)
 {
 	return 0;

kernel/trace/ftrace.c

@@ -2764,6 +2764,50 @@ void __weak arch_ftrace_trampoline_free(struct ftrace_ops *ops)
 {
 }
 
+/* List of trace_ops that have allocated trampolines */
+static LIST_HEAD(ftrace_ops_trampoline_list);
+
+static void ftrace_add_trampoline_to_kallsyms(struct ftrace_ops *ops)
+{
+	lockdep_assert_held(&ftrace_lock);
+	list_add_rcu(&ops->list, &ftrace_ops_trampoline_list);
+}
+
+static void ftrace_remove_trampoline_from_kallsyms(struct ftrace_ops *ops)
+{
+	lockdep_assert_held(&ftrace_lock);
+	list_del_rcu(&ops->list);
+}
+
+/*
+ * "__builtin__ftrace" is used as a module name in /proc/kallsyms for symbols
+ * for pages allocated for ftrace purposes, even though "__builtin__ftrace" is
+ * not a module.
+ */
+#define FTRACE_TRAMPOLINE_MOD "__builtin__ftrace"
+#define FTRACE_TRAMPOLINE_SYM "ftrace_trampoline"
+
+static void ftrace_trampoline_free(struct ftrace_ops *ops)
+{
+	if (ops && (ops->flags & FTRACE_OPS_FL_ALLOC_TRAMP) &&
+	    ops->trampoline) {
+		/*
+		 * Record the text poke event before the ksymbol unregister
+		 * event.
+		 */
+		perf_event_text_poke((void *)ops->trampoline,
+				     (void *)ops->trampoline,
+				     ops->trampoline_size, NULL, 0);
+		perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_OOL,
+				   ops->trampoline, ops->trampoline_size,
+				   true, FTRACE_TRAMPOLINE_SYM);
+		/* Remove from kallsyms after the perf events */
+		ftrace_remove_trampoline_from_kallsyms(ops);
+	}
+
+	arch_ftrace_trampoline_free(ops);
+}
+
 static void ftrace_startup_enable(int command)
 {
 	if (saved_ftrace_func != ftrace_trace_function) {
@@ -2934,7 +2978,7 @@ int ftrace_shutdown(struct ftrace_ops *ops, int command)
 			synchronize_rcu_tasks();
 
  free_ops:
-		arch_ftrace_trampoline_free(ops);
+		ftrace_trampoline_free(ops);
 	}
 
 	return 0;
@@ -6178,6 +6222,27 @@ struct ftrace_mod_map {
 	unsigned int		num_funcs;
 };
 
+static int ftrace_get_trampoline_kallsym(unsigned int symnum,
+					 unsigned long *value, char *type,
+					 char *name, char *module_name,
+					 int *exported)
+{
+	struct ftrace_ops *op;
+
+	list_for_each_entry_rcu(op, &ftrace_ops_trampoline_list, list) {
+		if (!op->trampoline || symnum--)
+			continue;
+		*value = op->trampoline;
+		*type = 't';
+		strlcpy(name, FTRACE_TRAMPOLINE_SYM, KSYM_NAME_LEN);
+		strlcpy(module_name, FTRACE_TRAMPOLINE_MOD, MODULE_NAME_LEN);
+		*exported = 0;
+		return 0;
+	}
+
+	return -ERANGE;
+}
+
 #ifdef CONFIG_MODULES
 
 #define next_to_ftrace_page(p) container_of(p, struct ftrace_page, next)
@@ -6514,6 +6579,7 @@ int ftrace_mod_get_kallsym(unsigned int symnum, unsigned long *value,
 {
 	struct ftrace_mod_map *mod_map;
 	struct ftrace_mod_func *mod_func;
+	int ret;
 
 	preempt_disable();
 	list_for_each_entry_rcu(mod_map, &ftrace_mod_maps, list) {
@@ -6540,8 +6606,10 @@ int ftrace_mod_get_kallsym(unsigned int symnum, unsigned long *value,
 		WARN_ON(1);
 		break;
 	}
+	ret = ftrace_get_trampoline_kallsym(symnum, value, type, name,
+					    module_name, exported);
 	preempt_enable();
-	return -ERANGE;
+	return ret;
 }
 
 #else
@@ -6553,6 +6621,18 @@ allocate_ftrace_mod_map(struct module *mod,
 {
 	return NULL;
 }
+int ftrace_mod_get_kallsym(unsigned int symnum, unsigned long *value,
+			   char *type, char *name, char *module_name,
+			   int *exported)
+{
+	int ret;
+
+	preempt_disable();
+	ret = ftrace_get_trampoline_kallsym(symnum, value, type, name,
+					    module_name, exported);
+	preempt_enable();
+	return ret;
+}
 #endif /* CONFIG_MODULES */
 
 struct ftrace_init_func {
@@ -6733,7 +6813,24 @@ void __weak arch_ftrace_update_trampoline(struct ftrace_ops *ops)
 
 static void ftrace_update_trampoline(struct ftrace_ops *ops)
 {
+	unsigned long trampoline = ops->trampoline;
+
 	arch_ftrace_update_trampoline(ops);
+	if (ops->trampoline && ops->trampoline != trampoline &&
+	    (ops->flags & FTRACE_OPS_FL_ALLOC_TRAMP)) {
+		/* Add to kallsyms before the perf events */
+		ftrace_add_trampoline_to_kallsyms(ops);
+		perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_OOL,
+				   ops->trampoline, ops->trampoline_size, false,
+				   FTRACE_TRAMPOLINE_SYM);
+		/*
+		 * Record the perf text poke event after the ksymbol register
+		 * event.
+		 */
+		perf_event_text_poke((void *)ops->trampoline, NULL, 0,
+				     (void *)ops->trampoline,
+				     ops->trampoline_size);
+	}
 }
 
 void ftrace_init_trace_array(struct trace_array *tr)