Merge tag 'perf-core-2025-01-20' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull performance events updates from Ingo Molnar:
 "Seqlock optimizations that arose in a perf context and were merged
  into the perf tree:

   - seqlock: Add raw_seqcount_try_begin (Suren Baghdasaryan)
   - mm: Convert mm_lock_seq to a proper seqcount (Suren Baghdasaryan)
   - mm: Introduce mmap_lock_speculate_{try_begin|retry} (Suren
     Baghdasaryan)
   - mm/gup: Use raw_seqcount_try_begin() (Peter Zijlstra)

  Core perf enhancements:

   - Reduce 'struct page' footprint of perf by mapping pages in advance
     (Lorenzo Stoakes)
   - Save raw sample data conditionally based on sample type (Yabin Cui)
   - Reduce sampling overhead by checking sample_type in
     perf_sample_save_callchain() and perf_sample_save_brstack() (Yabin
     Cui)
   - Export perf_exclude_event() (Namhyung Kim)

  Uprobes scalability enhancements: (Andrii Nakryiko)

   - Simplify find_active_uprobe_rcu() VMA checks
   - Add speculative lockless VMA-to-inode-to-uprobe resolution
   - Simplify session consumer tracking
   - Decouple return_instance list traversal and freeing
   - Ensure return_instance is detached from the list before freeing
   - Reuse return_instances between multiple uretprobes within task
   - Guard against kmemdup() failing in dup_return_instance()

  AMD core PMU driver enhancements:

   - Relax privilege filter restriction on AMD IBS (Namhyung Kim)

  AMD RAPL energy counters support: (Dhananjay Ugwekar)

   - Introduce topology_logical_core_id() (K Prateek Nayak)
   - Remove the unused get_rapl_pmu_cpumask() function
   - Remove the cpu_to_rapl_pmu() function
   - Rename rapl_pmu variables
   - Make rapl_model struct global
   - Add arguments to the init and cleanup functions
   - Modify the generic variable names to *_pkg*
   - Remove the global variable rapl_msrs
   - Move the cntr_mask to rapl_pmus struct
   - Add core energy counter support for AMD CPUs

  Intel core PMU driver enhancements:

   - Support RDPMC 'metrics clear mode' feature (Kan Liang)
   - Clarify adaptive PEBS processing (Kan Liang)
   - Factor out functions for PEBS records processing (Kan Liang)
   - Simplify the PEBS records processing for adaptive PEBS (Kan Liang)

  Intel uncore driver enhancements: (Kan Liang)

   - Convert buggy pmu->func_id use to pmu->registered
   - Support more units on Granite Rapids"

* tag 'perf-core-2025-01-20' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (33 commits)
  perf: map pages in advance
  perf/x86/intel/uncore: Support more units on Granite Rapids
  perf/x86/intel/uncore: Clean up func_id
  perf/x86/intel: Support RDPMC metrics clear mode
  uprobes: Guard against kmemdup() failing in dup_return_instance()
  perf/x86: Relax privilege filter restriction on AMD IBS
  perf/core: Export perf_exclude_event()
  uprobes: Reuse return_instances between multiple uretprobes within task
  uprobes: Ensure return_instance is detached from the list before freeing
  uprobes: Decouple return_instance list traversal and freeing
  uprobes: Simplify session consumer tracking
  uprobes: add speculative lockless VMA-to-inode-to-uprobe resolution
  uprobes: simplify find_active_uprobe_rcu() VMA checks
  mm: introduce mmap_lock_speculate_{try_begin|retry}
  mm: convert mm_lock_seq to a proper seqcount
  mm/gup: Use raw_seqcount_try_begin()
  seqlock: add raw_seqcount_try_begin
  perf/x86/rapl: Add core energy counter support for AMD CPUs
  perf/x86/rapl: Move the cntr_mask to rapl_pmus struct
  perf/x86/rapl: Remove the global variable rapl_msrs
  ...

5 files changed, 276 insertions, 140 deletions

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 065f9188b44a..bcb09e011e9e 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -6277,41 +6277,6 @@ unlock:
 }
 EXPORT_SYMBOL_GPL(perf_event_update_userpage);
 
-static vm_fault_t perf_mmap_fault(struct vm_fault *vmf)
-{
-	struct perf_event *event = vmf->vma->vm_file->private_data;
-	struct perf_buffer *rb;
-	vm_fault_t ret = VM_FAULT_SIGBUS;
-
-	if (vmf->flags & FAULT_FLAG_MKWRITE) {
-		if (vmf->pgoff == 0)
-			ret = 0;
-		return ret;
-	}
-
-	rcu_read_lock();
-	rb = rcu_dereference(event->rb);
-	if (!rb)
-		goto unlock;
-
-	if (vmf->pgoff && (vmf->flags & FAULT_FLAG_WRITE))
-		goto unlock;
-
-	vmf->page = perf_mmap_to_page(rb, vmf->pgoff);
-	if (!vmf->page)
-		goto unlock;
-
-	get_page(vmf->page);
-	vmf->page->mapping = vmf->vma->vm_file->f_mapping;
-	vmf->page->index   = vmf->pgoff;
-
-	ret = 0;
-unlock:
-	rcu_read_unlock();
-
-	return ret;
-}
-
 static void ring_buffer_attach(struct perf_event *event,
 			       struct perf_buffer *rb)
 {
@@ -6551,13 +6516,87 @@ out_put:
 	ring_buffer_put(rb); /* could be last */
 }
 
+static vm_fault_t perf_mmap_pfn_mkwrite(struct vm_fault *vmf)
+{
+	/* The first page is the user control page, others are read-only. */
+	return vmf->pgoff == 0 ? 0 : VM_FAULT_SIGBUS;
+}
+
 static const struct vm_operations_struct perf_mmap_vmops = {
 	.open		= perf_mmap_open,
 	.close		= perf_mmap_close, /* non mergeable */
-	.fault		= perf_mmap_fault,
-	.page_mkwrite	= perf_mmap_fault,
+	.pfn_mkwrite	= perf_mmap_pfn_mkwrite,
 };
 
+static int map_range(struct perf_buffer *rb, struct vm_area_struct *vma)
+{
+	unsigned long nr_pages = vma_pages(vma);
+	int err = 0;
+	unsigned long pagenum;
+
+	/*
+	 * We map this as a VM_PFNMAP VMA.
+	 *
+	 * This is not ideal as this is designed broadly for mappings of PFNs
+	 * referencing memory-mapped I/O ranges or non-system RAM i.e. for which
+	 * !pfn_valid(pfn).
+	 *
+	 * We are mapping kernel-allocated memory (memory we manage ourselves)
+	 * which would more ideally be mapped using vm_insert_page() or a
+	 * similar mechanism, that is as a VM_MIXEDMAP mapping.
+	 *
+	 * However this won't work here, because:
+	 *
+	 * 1. It uses vma->vm_page_prot, but this field has not been completely
+	 *    setup at the point of the f_op->mmp() hook, so we are unable to
+	 *    indicate that this should be mapped CoW in order that the
+	 *    mkwrite() hook can be invoked to make the first page R/W and the
+	 *    rest R/O as desired.
+	 *
+	 * 2. Anything other than a VM_PFNMAP of valid PFNs will result in
+	 *    vm_normal_page() returning a struct page * pointer, which means
+	 *    vm_ops->page_mkwrite() will be invoked rather than
+	 *    vm_ops->pfn_mkwrite(), and this means we have to set page->mapping
+	 *    to work around retry logic in the fault handler, however this
+	 *    field is no longer allowed to be used within struct page.
+	 *
+	 * 3. Having a struct page * made available in the fault logic also
+	 *    means that the page gets put on the rmap and becomes
+	 *    inappropriately accessible and subject to map and ref counting.
+	 *
+	 * Ideally we would have a mechanism that could explicitly express our
+	 * desires, but this is not currently the case, so we instead use
+	 * VM_PFNMAP.
+	 *
+	 * We manage the lifetime of these mappings with internal refcounts (see
+	 * perf_mmap_open() and perf_mmap_close()) so we ensure the lifetime of
+	 * this mapping is maintained correctly.
+	 */
+	for (pagenum = 0; pagenum < nr_pages; pagenum++) {
+		unsigned long va = vma->vm_start + PAGE_SIZE * pagenum;
+		struct page *page = perf_mmap_to_page(rb, vma->vm_pgoff + pagenum);
+
+		if (page == NULL) {
+			err = -EINVAL;
+			break;
+		}
+
+		/* Map readonly, perf_mmap_pfn_mkwrite() called on write fault. */
+		err = remap_pfn_range(vma, va, page_to_pfn(page), PAGE_SIZE,
+				      vm_get_page_prot(vma->vm_flags & ~VM_SHARED));
+		if (err)
+			break;
+	}
+
+#ifdef CONFIG_MMU
+	/* Clear any partial mappings on error. */
+	if (err)
+		zap_page_range_single(vma, vma->vm_start, nr_pages * PAGE_SIZE, NULL);
+#endif
+
+	return err;
+}
+
 static int perf_mmap(struct file *file, struct vm_area_struct *vma)
 {
 	struct perf_event *event = file->private_data;
@@ -6682,6 +6721,8 @@ again:
 			goto again;
 		}
 
+		/* We need the rb to map pages. */
+		rb = event->rb;
 		goto unlock;
 	}
 
@@ -6776,6 +6817,9 @@ aux_unlock:
 	vm_flags_set(vma, VM_DONTCOPY | VM_DONTEXPAND | VM_DONTDUMP);
 	vma->vm_ops = &perf_mmap_vmops;
 
+	if (!ret)
+		ret = map_range(rb, vma);
+
 	if (event->pmu->event_mapped)
 		event->pmu->event_mapped(event, vma->vm_mm);
 
@@ -10039,8 +10083,7 @@ static void perf_swevent_event(struct perf_event *event, u64 nr,
 	perf_swevent_overflow(event, 0, data, regs);
 }
 
-static int perf_exclude_event(struct perf_event *event,
-			      struct pt_regs *regs)
+int perf_exclude_event(struct perf_event *event, struct pt_regs *regs)
 {
 	if (event->hw.state & PERF_HES_STOPPED)
 		return 1;
@@ -10425,9 +10468,9 @@ static struct pmu perf_tracepoint = {
 };
 
 static int perf_tp_filter_match(struct perf_event *event,
-				struct perf_sample_data *data)
+				struct perf_raw_record *raw)
 {
-	void *record = data->raw->frag.data;
+	void *record = raw->frag.data;
 
 	/* only top level events have filters set */
 	if (event->parent)
@@ -10439,7 +10482,7 @@ static int perf_tp_filter_match(struct perf_event *event,
 }
 
 static int perf_tp_event_match(struct perf_event *event,
-				struct perf_sample_data *data,
+				struct perf_raw_record *raw,
 				struct pt_regs *regs)
 {
 	if (event->hw.state & PERF_HES_STOPPED)
@@ -10450,7 +10493,7 @@ static int perf_tp_event_match(struct perf_event *event,
 	if (event->attr.exclude_kernel && !user_mode(regs))
 		return 0;
 
-	if (!perf_tp_filter_match(event, data))
+	if (!perf_tp_filter_match(event, raw))
 		return 0;
 
 	return 1;
@@ -10476,6 +10519,7 @@ EXPORT_SYMBOL_GPL(perf_trace_run_bpf_submit);
 static void __perf_tp_event_target_task(u64 count, void *record,
 					struct pt_regs *regs,
 					struct perf_sample_data *data,
+					struct perf_raw_record *raw,
 					struct perf_event *event)
 {
 	struct trace_entry *entry = record;
@@ -10485,13 +10529,17 @@ static void __perf_tp_event_target_task(u64 count, void *record,
 	/* Cannot deliver synchronous signal to other task. */
 	if (event->attr.sigtrap)
 		return;
-	if (perf_tp_event_match(event, data, regs))
+	if (perf_tp_event_match(event, raw, regs)) {
+		perf_sample_data_init(data, 0, 0);
+		perf_sample_save_raw_data(data, event, raw);
 		perf_swevent_event(event, count, data, regs);
+	}
 }
 
 static void perf_tp_event_target_task(u64 count, void *record,
 				      struct pt_regs *regs,
 				      struct perf_sample_data *data,
+				      struct perf_raw_record *raw,
 				      struct perf_event_context *ctx)
 {
 	unsigned int cpu = smp_processor_id();
@@ -10499,15 +10547,15 @@ static void perf_tp_event_target_task(u64 count, void *record,
 	struct perf_event *event, *sibling;
 
 	perf_event_groups_for_cpu_pmu(event, &ctx->pinned_groups, cpu, pmu) {
-		__perf_tp_event_target_task(count, record, regs, data, event);
+		__perf_tp_event_target_task(count, record, regs, data, raw, event);
 		for_each_sibling_event(sibling, event)
-			__perf_tp_event_target_task(count, record, regs, data, sibling);
+			__perf_tp_event_target_task(count, record, regs, data, raw, sibling);
 	}
 
 	perf_event_groups_for_cpu_pmu(event, &ctx->flexible_groups, cpu, pmu) {
-		__perf_tp_event_target_task(count, record, regs, data, event);
+		__perf_tp_event_target_task(count, record, regs, data, raw, event);
 		for_each_sibling_event(sibling, event)
-			__perf_tp_event_target_task(count, record, regs, data, sibling);
+			__perf_tp_event_target_task(count, record, regs, data, raw, sibling);
 	}
 }
 
@@ -10525,15 +10573,10 @@ void perf_tp_event(u16 event_type, u64 count, void *record, int entry_size,
 		},
 	};
 
-	perf_sample_data_init(&data, 0, 0);
-	perf_sample_save_raw_data(&data, &raw);
-
 	perf_trace_buf_update(record, event_type);
 
 	hlist_for_each_entry_rcu(event, head, hlist_entry) {
-		if (perf_tp_event_match(event, &data, regs)) {
-			perf_swevent_event(event, count, &data, regs);
-
+		if (perf_tp_event_match(event, &raw, regs)) {
 			/*
 			 * Here use the same on-stack perf_sample_data,
 			 * some members in data are event-specific and
@@ -10543,7 +10586,8 @@ void perf_tp_event(u16 event_type, u64 count, void *record, int entry_size,
 			 * because data->sample_flags is set.
 			 */
 			perf_sample_data_init(&data, 0, 0);
-			perf_sample_save_raw_data(&data, &raw);
+			perf_sample_save_raw_data(&data, event, &raw);
+			perf_swevent_event(event, count, &data, regs);
 		}
 	}
 
@@ -10560,7 +10604,7 @@ void perf_tp_event(u16 event_type, u64 count, void *record, int entry_size,
 			goto unlock;
 
 		raw_spin_lock(&ctx->lock);
-		perf_tp_event_target_task(count, record, regs, &data, ctx);
+		perf_tp_event_target_task(count, record, regs, &data, &raw, ctx);
 		raw_spin_unlock(&ctx->lock);
 unlock:
 		rcu_read_unlock();
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index 4f46f688d0d4..180509132d4b 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -643,7 +643,6 @@ static void rb_free_aux_page(struct perf_buffer *rb, int idx)
 	struct page *page = virt_to_page(rb->aux_pages[idx]);
 
 	ClearPagePrivate(page);
-	page->mapping = NULL;
 	__free_page(page);
 }
 
@@ -819,7 +818,6 @@ static void perf_mmap_free_page(void *addr)
 {
 	struct page *page = virt_to_page(addr);
 
-	page->mapping = NULL;
 	__free_page(page);
 }
 
@@ -890,28 +888,13 @@ __perf_mmap_to_page(struct perf_buffer *rb, unsigned long pgoff)
 	return vmalloc_to_page((void *)rb->user_page + pgoff * PAGE_SIZE);
 }
 
-static void perf_mmap_unmark_page(void *addr)
-{
-	struct page *page = vmalloc_to_page(addr);
-
-	page->mapping = NULL;
-}
-
 static void rb_free_work(struct work_struct *work)
 {
 	struct perf_buffer *rb;
-	void *base;
-	int i, nr;
 
 	rb = container_of(work, struct perf_buffer, work);
-	nr = data_page_nr(rb);
-
-	base = rb->user_page;
-	/* The '<=' counts in the user page. */
-	for (i = 0; i <= nr; i++)
-		perf_mmap_unmark_page(base + (i * PAGE_SIZE));
 
-	vfree(base);
+	vfree(rb->user_page);
 	kfree(rb);
 }
 
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 5d71ef85420c..e421a5f2ec7d 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -1888,9 +1888,33 @@ unsigned long uprobe_get_trap_addr(struct pt_regs *regs)
 	return instruction_pointer(regs);
 }
 
-static struct return_instance *free_ret_instance(struct return_instance *ri, bool cleanup_hprobe)
+static void ri_pool_push(struct uprobe_task *utask, struct return_instance *ri)
 {
-	struct return_instance *next = ri->next;
+	ri->cons_cnt = 0;
+	ri->next = utask->ri_pool;
+	utask->ri_pool = ri;
+}
+
+static struct return_instance *ri_pool_pop(struct uprobe_task *utask)
+{
+	struct return_instance *ri = utask->ri_pool;
+
+	if (likely(ri))
+		utask->ri_pool = ri->next;
+
+	return ri;
+}
+
+static void ri_free(struct return_instance *ri)
+{
+	kfree(ri->extra_consumers);
+	kfree_rcu(ri, rcu);
+}
+
+static void free_ret_instance(struct uprobe_task *utask,
+			      struct return_instance *ri, bool cleanup_hprobe)
+{
+	unsigned seq;
 
 	if (cleanup_hprobe) {
 		enum hprobe_state hstate;
@@ -1899,8 +1923,22 @@ static struct return_instance *free_ret_instance(struct return_instance *ri, boo
 		hprobe_finalize(&ri->hprobe, hstate);
 	}
 
-	kfree_rcu(ri, rcu);
-	return next;
+	/*
+	 * At this point return_instance is unlinked from utask's
+	 * return_instances list and this has become visible to ri_timer().
+	 * If seqcount now indicates that ri_timer's return instance
+	 * processing loop isn't active, we can return ri into the pool of
+	 * to-be-reused return instances for future uretprobes. If ri_timer()
+	 * happens to be running right now, though, we fallback to safety and
+	 * just perform RCU-delated freeing of ri.
+	 */
+	if (raw_seqcount_try_begin(&utask->ri_seqcount, seq)) {
+		/* immediate reuse of ri without RCU GP is OK */
+		ri_pool_push(utask, ri);
+	} else {
+		/* we might be racing with ri_timer(), so play it safe */
+		ri_free(ri);
+	}
 }
 
 /*
@@ -1910,7 +1948,7 @@ static struct return_instance *free_ret_instance(struct return_instance *ri, boo
 void uprobe_free_utask(struct task_struct *t)
 {
 	struct uprobe_task *utask = t->utask;
-	struct return_instance *ri;
+	struct return_instance *ri, *ri_next;
 
 	if (!utask)
 		return;
@@ -1921,8 +1959,19 @@ void uprobe_free_utask(struct task_struct *t)
 	timer_delete_sync(&utask->ri_timer);
 
 	ri = utask->return_instances;
-	while (ri)
-		ri = free_ret_instance(ri, true /* cleanup_hprobe */);
+	while (ri) {
+		ri_next = ri->next;
+		free_ret_instance(utask, ri, true /* cleanup_hprobe */);
+		ri = ri_next;
+	}
+
+	/* free_ret_instance() above might add to ri_pool, so this loop should come last */
+	ri = utask->ri_pool;
+	while (ri) {
+		ri_next = ri->next;
+		ri_free(ri);
+		ri = ri_next;
+	}
 
 	kfree(utask);
 }
@@ -1942,8 +1991,12 @@ static void ri_timer(struct timer_list *timer)
 	/* RCU protects return_instance from freeing. */
 	guard(rcu)();
 
+	write_seqcount_begin(&utask->ri_seqcount);
+
 	for_each_ret_instance_rcu(ri, utask->return_instances)
 		hprobe_expire(&ri->hprobe, false);
+
+	write_seqcount_end(&utask->ri_seqcount);
 }
 
 static struct uprobe_task *alloc_utask(void)
@@ -1955,6 +2008,7 @@ static struct uprobe_task *alloc_utask(void)
 		return NULL;
 
 	timer_setup(&utask->ri_timer, ri_timer, 0);
+	seqcount_init(&utask->ri_seqcount);
 
 	return utask;
 }
@@ -1974,32 +2028,40 @@ static struct uprobe_task *get_utask(void)
 	return current->utask;
 }
 
-static size_t ri_size(int consumers_cnt)
+static struct return_instance *alloc_return_instance(struct uprobe_task *utask)
 {
 	struct return_instance *ri;
 
-	return sizeof(*ri) + sizeof(ri->consumers[0]) * consumers_cnt;
-}
-
-#define DEF_CNT 4
-
-static struct return_instance *alloc_return_instance(void)
-{
-	struct return_instance *ri;
+	ri = ri_pool_pop(utask);
+	if (ri)
+		return ri;
 
-	ri = kzalloc(ri_size(DEF_CNT), GFP_KERNEL);
+	ri = kzalloc(sizeof(*ri), GFP_KERNEL);
 	if (!ri)
 		return ZERO_SIZE_PTR;
 
-	ri->consumers_cnt = DEF_CNT;
 	return ri;
 }
 
 static struct return_instance *dup_return_instance(struct return_instance *old)
 {
-	size_t size = ri_size(old->consumers_cnt);
+	struct return_instance *ri;
+
+	ri = kmemdup(old, sizeof(*ri), GFP_KERNEL);
+	if (!ri)
+		return NULL;
 
-	return kmemdup(old, size, GFP_KERNEL);
+	if (unlikely(old->cons_cnt > 1)) {
+		ri->extra_consumers = kmemdup(old->extra_consumers,
+					      sizeof(ri->extra_consumers[0]) * (old->cons_cnt - 1),
+					      GFP_KERNEL);
+		if (!ri->extra_consumers) {
+			kfree(ri);
+			return NULL;
+		}
+	}
+
+	return ri;
 }
 
 static int dup_utask(struct task_struct *t, struct uprobe_task *o_utask)
@@ -2108,14 +2170,17 @@ unsigned long uprobe_get_trampoline_vaddr(void)
 static void cleanup_return_instances(struct uprobe_task *utask, bool chained,
 					struct pt_regs *regs)
 {
-	struct return_instance *ri = utask->return_instances;
+	struct return_instance *ri = utask->return_instances, *ri_next;
 	enum rp_check ctx = chained ? RP_CHECK_CHAIN_CALL : RP_CHECK_CALL;
 
 	while (ri && !arch_uretprobe_is_alive(ri, ctx, regs)) {
-		ri = free_ret_instance(ri, true /* cleanup_hprobe */);
+		ri_next = ri->next;
+		rcu_assign_pointer(utask->return_instances, ri_next);
 		utask->depth--;
+
+		free_ret_instance(utask, ri, true /* cleanup_hprobe */);
+		ri = ri_next;
 	}
-	rcu_assign_pointer(utask->return_instances, ri);
 }
 
 static void prepare_uretprobe(struct uprobe *uprobe, struct pt_regs *regs,
@@ -2180,7 +2245,7 @@ static void prepare_uretprobe(struct uprobe *uprobe, struct pt_regs *regs,
 
 	return;
 free:
-	kfree(ri);
+	ri_free(ri);
 }
 
 /* Prepare to single-step probed instruction out of line. */
@@ -2294,6 +2359,47 @@ static int is_trap_at_addr(struct mm_struct *mm, unsigned long vaddr)
 	return is_trap_insn(&opcode);
 }
 
+static struct uprobe *find_active_uprobe_speculative(unsigned long bp_vaddr)
+{
+	struct mm_struct *mm = current->mm;
+	struct uprobe *uprobe = NULL;
+	struct vm_area_struct *vma;
+	struct file *vm_file;
+	loff_t offset;
+	unsigned int seq;
+
+	guard(rcu)();
+
+	if (!mmap_lock_speculate_try_begin(mm, &seq))
+		return NULL;
+
+	vma = vma_lookup(mm, bp_vaddr);
+	if (!vma)
+		return NULL;
+
+	/*
+	 * vm_file memory can be reused for another instance of struct file,
+	 * but can't be freed from under us, so it's safe to read fields from
+	 * it, even if the values are some garbage values; ultimately
+	 * find_uprobe_rcu() + mmap_lock_speculation_end() check will ensure
+	 * that whatever we speculatively found is correct
+	 */
+	vm_file = READ_ONCE(vma->vm_file);
+	if (!vm_file)
+		return NULL;
+
+	offset = (loff_t)(vma->vm_pgoff << PAGE_SHIFT) + (bp_vaddr - vma->vm_start);
+	uprobe = find_uprobe_rcu(vm_file->f_inode, offset);
+	if (!uprobe)
+		return NULL;
+
+	/* now double check that nothing about MM changed */
+	if (mmap_lock_speculate_retry(mm, seq))
+		return NULL;
+
+	return uprobe;
+}
+
 /* assumes being inside RCU protected region */
 static struct uprobe *find_active_uprobe_rcu(unsigned long bp_vaddr, int *is_swbp)
 {
@@ -2301,10 +2407,14 @@ static struct uprobe *find_active_uprobe_rcu(unsigned long bp_vaddr, int *is_swb
 	struct uprobe *uprobe = NULL;
 	struct vm_area_struct *vma;
 
+	uprobe = find_active_uprobe_speculative(bp_vaddr);
+	if (uprobe)
+		return uprobe;
+
 	mmap_read_lock(mm);
 	vma = vma_lookup(mm, bp_vaddr);
 	if (vma) {
-		if (valid_vma(vma, false)) {
+		if (vma->vm_file) {
 			struct inode *inode = file_inode(vma->vm_file);
 			loff_t offset = vaddr_to_offset(vma, bp_vaddr);
 
@@ -2324,25 +2434,27 @@ static struct uprobe *find_active_uprobe_rcu(unsigned long bp_vaddr, int *is_swb
 	return uprobe;
 }
 
-static struct return_instance*
-push_consumer(struct return_instance *ri, int idx, __u64 id, __u64 cookie)
+static struct return_instance *push_consumer(struct return_instance *ri, __u64 id, __u64 cookie)
 {
+	struct return_consumer *ric;
+
 	if (unlikely(ri == ZERO_SIZE_PTR))
 		return ri;
 
-	if (unlikely(idx >= ri->consumers_cnt)) {
-		struct return_instance *old_ri = ri;
-
-		ri->consumers_cnt += DEF_CNT;
-		ri = krealloc(old_ri, ri_size(old_ri->consumers_cnt), GFP_KERNEL);
-		if (!ri) {
-			kfree(old_ri);
+	if (unlikely(ri->cons_cnt > 0)) {
+		ric = krealloc(ri->extra_consumers, sizeof(*ric) * ri->cons_cnt, GFP_KERNEL);
+		if (!ric) {
+			ri_free(ri);
 			return ZERO_SIZE_PTR;
 		}
+		ri->extra_consumers = ric;
 	}
 
-	ri->consumers[idx].id = id;
-	ri->consumers[idx].cookie = cookie;
+	ric = likely(ri->cons_cnt == 0) ? &ri->consumer : &ri->extra_consumers[ri->cons_cnt - 1];
+	ric->id = id;
+	ric->cookie = cookie;
+
+	ri->cons_cnt++;
 	return ri;
 }
 
@@ -2350,14 +2462,17 @@ static struct return_consumer *
 return_consumer_find(struct return_instance *ri, int *iter, int id)
 {
 	struct return_consumer *ric;
-	int idx = *iter;
+	int idx;
 
-	for (ric = &ri->consumers[idx]; idx < ri->consumers_cnt; idx++, ric++) {
+	for (idx = *iter; idx < ri->cons_cnt; idx++)
+	{
+		ric = likely(idx == 0) ? &ri->consumer : &ri->extra_consumers[idx - 1];
 		if (ric->id == id) {
 			*iter = idx + 1;
 			return ric;
 		}
 	}
+
 	return NULL;
 }
 
@@ -2371,9 +2486,9 @@ static void handler_chain(struct uprobe *uprobe, struct pt_regs *regs)
 	struct uprobe_consumer *uc;
 	bool has_consumers = false, remove = true;
 	struct return_instance *ri = NULL;
-	int push_idx = 0;
+	struct uprobe_task *utask = current->utask;
 
-	current->utask->auprobe = &uprobe->arch;
+	utask->auprobe = &uprobe->arch;
 
 	list_for_each_entry_rcu(uc, &uprobe->consumers, cons_node, rcu_read_lock_trace_held()) {
 		bool session = uc->handler && uc->ret_handler;
@@ -2393,21 +2508,15 @@ static void handler_chain(struct uprobe *uprobe, struct pt_regs *regs)
 			continue;
 
 		if (!ri)
-			ri = alloc_return_instance();
+			ri = alloc_return_instance(utask);
 
 		if (session)
-			ri = push_consumer(ri, push_idx++, uc->id, cookie);
+			ri = push_consumer(ri, uc->id, cookie);
 	}
-	current->utask->auprobe = NULL;
+	utask->auprobe = NULL;
 
-	if (!ZERO_OR_NULL_PTR(ri)) {
-		/*
-		 * The push_idx value has the final number of return consumers,
-		 * and ri->consumers_cnt has number of allocated consumers.
-		 */
-		ri->consumers_cnt = push_idx;
+	if (!ZERO_OR_NULL_PTR(ri))
 		prepare_uretprobe(uprobe, regs, ri);
-	}
 
 	if (remove && has_consumers) {
 		down_read(&uprobe->register_rwsem);
@@ -2461,7 +2570,7 @@ static struct return_instance *find_next_ret_chain(struct return_instance *ri)
 void uprobe_handle_trampoline(struct pt_regs *regs)
 {
 	struct uprobe_task *utask;
-	struct return_instance *ri, *next;
+	struct return_instance *ri, *ri_next, *next_chain;
 	struct uprobe *uprobe;
 	enum hprobe_state hstate;
 	bool valid;
@@ -2481,8 +2590,8 @@ void uprobe_handle_trampoline(struct pt_regs *regs)
 		 * or NULL; the latter case means that nobody but ri->func
 		 * could hit this trampoline on return. TODO: sigaltstack().
 		 */
-		next = find_next_ret_chain(ri);
-		valid = !next || arch_uretprobe_is_alive(next, RP_CHECK_RET, regs);
+		next_chain = find_next_ret_chain(ri);
+		valid = !next_chain || arch_uretprobe_is_alive(next_chain, RP_CHECK_RET, regs);
 
 		instruction_pointer_set(regs, ri->orig_ret_vaddr);
 		do {
@@ -2494,7 +2603,9 @@ void uprobe_handle_trampoline(struct pt_regs *regs)
 			 * trampoline addresses on the stack are replaced with correct
 			 * original return addresses
 			 */
-			rcu_assign_pointer(utask->return_instances, ri->next);
+			ri_next = ri->next;
+			rcu_assign_pointer(utask->return_instances, ri_next);
+			utask->depth--;
 
 			uprobe = hprobe_consume(&ri->hprobe, &hstate);
 			if (valid)
@@ -2502,9 +2613,9 @@ void uprobe_handle_trampoline(struct pt_regs *regs)
 			hprobe_finalize(&ri->hprobe, hstate);
 
 			/* We already took care of hprobe, no need to waste more time on that. */
-			ri = free_ret_instance(ri, false /* !cleanup_hprobe */);
-			utask->depth--;
-		} while (ri != next);
+			free_ret_instance(utask, ri, false /* !cleanup_hprobe */);
+			ri = ri_next;
+		} while (ri != next_chain);
 	} while (!valid);
 
 	return;
diff --git a/kernel/fork.c b/kernel/fork.c
index 9b301180fd41..ded49f18cd95 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -448,7 +448,7 @@ static bool vma_lock_alloc(struct vm_area_struct *vma)
 		return false;
 
 	init_rwsem(&vma->vm_lock->lock);
-	vma->vm_lock_seq = -1;
+	vma->vm_lock_seq = UINT_MAX;
 
 	return true;
 }
@@ -1262,9 +1262,6 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p,
 	seqcount_init(&mm->write_protect_seq);
 	mmap_init_lock(mm);
 	INIT_LIST_HEAD(&mm->mmlist);
-#ifdef CONFIG_PER_VMA_LOCK
-	mm->mm_lock_seq = 0;
-#endif
 	mm_pgtables_bytes_init(mm);
 	mm->map_count = 0;
 	mm->locked_vm = 0;
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 1b8db5aee9d3..9f2f65767639 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -619,7 +619,8 @@ static const struct bpf_func_proto bpf_perf_event_read_value_proto = {
 
 static __always_inline u64
 __bpf_perf_event_output(struct pt_regs *regs, struct bpf_map *map,
-			u64 flags, struct perf_sample_data *sd)
+			u64 flags, struct perf_raw_record *raw,
+			struct perf_sample_data *sd)
 {
 	struct bpf_array *array = container_of(map, struct bpf_array, map);
 	unsigned int cpu = smp_processor_id();
@@ -644,6 +645,8 @@ __bpf_perf_event_output(struct pt_regs *regs, struct bpf_map *map,
 	if (unlikely(event->oncpu != cpu))
 		return -EOPNOTSUPP;
 
+	perf_sample_save_raw_data(sd, event, raw);
+
 	return perf_event_output(event, sd, regs);
 }
 
@@ -687,9 +690,8 @@ BPF_CALL_5(bpf_perf_event_output, struct pt_regs *, regs, struct bpf_map *, map,
 	}
 
 	perf_sample_data_init(sd, 0, 0);
-	perf_sample_save_raw_data(sd, &raw);
 
-	err = __bpf_perf_event_output(regs, map, flags, sd);
+	err = __bpf_perf_event_output(regs, map, flags, &raw, sd);
 out:
 	this_cpu_dec(bpf_trace_nest_level);
 	preempt_enable();
@@ -748,9 +750,8 @@ u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size,
 
 	perf_fetch_caller_regs(regs);
 	perf_sample_data_init(sd, 0, 0);
-	perf_sample_save_raw_data(sd, &raw);
 
-	ret = __bpf_perf_event_output(regs, map, flags, sd);
+	ret = __bpf_perf_event_output(regs, map, flags, &raw, sd);
 out:
 	this_cpu_dec(bpf_event_output_nest_level);
 	preempt_enable();