3 files changed, 271 insertions, 232 deletions

diff --git a/kernel/events/core.c b/kernel/events/core.c
index f34c99f8ce8f..22fdf0c187cd 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -207,6 +207,19 @@ static void perf_ctx_unlock(struct perf_cpu_context *cpuctx,
 	__perf_ctx_unlock(&cpuctx->ctx);
 }
 
+typedef struct {
+	struct perf_cpu_context *cpuctx;
+	struct perf_event_context *ctx;
+} class_perf_ctx_lock_t;
+
+static inline void class_perf_ctx_lock_destructor(class_perf_ctx_lock_t *_T)
+{ perf_ctx_unlock(_T->cpuctx, _T->ctx); }
+
+static inline class_perf_ctx_lock_t
+class_perf_ctx_lock_constructor(struct perf_cpu_context *cpuctx,
+				struct perf_event_context *ctx)
+{ perf_ctx_lock(cpuctx, ctx); return (class_perf_ctx_lock_t){ cpuctx, ctx }; }
+
 #define TASK_TOMBSTONE ((void *)-1L)
 
 static bool is_kernel_event(struct perf_event *event)
@@ -938,13 +951,19 @@ static void perf_cgroup_switch(struct task_struct *task)
 	if (READ_ONCE(cpuctx->cgrp) == NULL)
 		return;
 
-	WARN_ON_ONCE(cpuctx->ctx.nr_cgroups == 0);
-
 	cgrp = perf_cgroup_from_task(task, NULL);
 	if (READ_ONCE(cpuctx->cgrp) == cgrp)
 		return;
 
-	perf_ctx_lock(cpuctx, cpuctx->task_ctx);
+	guard(perf_ctx_lock)(cpuctx, cpuctx->task_ctx);
+	/*
+	 * Re-check, could've raced vs perf_remove_from_context().
+	 */
+	if (READ_ONCE(cpuctx->cgrp) == NULL)
+		return;
+
+	WARN_ON_ONCE(cpuctx->ctx.nr_cgroups == 0);
+
 	perf_ctx_disable(&cpuctx->ctx, true);
 
 	ctx_sched_out(&cpuctx->ctx, NULL, EVENT_ALL|EVENT_CGROUP);
@@ -962,7 +981,6 @@ static void perf_cgroup_switch(struct task_struct *task)
 	ctx_sched_in(&cpuctx->ctx, NULL, EVENT_ALL|EVENT_CGROUP);
 
 	perf_ctx_enable(&cpuctx->ctx, true);
-	perf_ctx_unlock(cpuctx, cpuctx->task_ctx);
 }
 
 static int perf_cgroup_ensure_storage(struct perf_event *event,
@@ -2120,18 +2138,6 @@ list_del_event(struct perf_event *event, struct perf_event_context *ctx)
 	if (event->group_leader == event)
 		del_event_from_groups(event, ctx);
 
-	/*
-	 * If event was in error state, then keep it
-	 * that way, otherwise bogus counts will be
-	 * returned on read(). The only way to get out
-	 * of error state is by explicit re-enabling
-	 * of the event
-	 */
-	if (event->state > PERF_EVENT_STATE_OFF) {
-		perf_cgroup_event_disable(event, ctx);
-		perf_event_set_state(event, PERF_EVENT_STATE_OFF);
-	}
-
 	ctx->generation++;
 	event->pmu_ctx->nr_events--;
 }
@@ -2149,8 +2155,9 @@ perf_aux_output_match(struct perf_event *event, struct perf_event *aux_event)
 }
 
 static void put_event(struct perf_event *event);
-static void event_sched_out(struct perf_event *event,
-			    struct perf_event_context *ctx);
+static void __event_disable(struct perf_event *event,
+			    struct perf_event_context *ctx,
+			    enum perf_event_state state);
 
 static void perf_put_aux_event(struct perf_event *event)
 {
@@ -2183,8 +2190,7 @@ static void perf_put_aux_event(struct perf_event *event)
 		 * state so that we don't try to schedule it again. Note
 		 * that perf_event_enable() will clear the ERROR status.
 		 */
-		event_sched_out(iter, ctx);
-		perf_event_set_state(event, PERF_EVENT_STATE_ERROR);
+		__event_disable(iter, ctx, PERF_EVENT_STATE_ERROR);
 	}
 }
 
@@ -2242,18 +2248,6 @@ static inline struct list_head *get_event_list(struct perf_event *event)
 				    &event->pmu_ctx->flexible_active;
 }
 
-/*
- * Events that have PERF_EV_CAP_SIBLING require being part of a group and
- * cannot exist on their own, schedule them out and move them into the ERROR
- * state. Also see _perf_event_enable(), it will not be able to recover
- * this ERROR state.
- */
-static inline void perf_remove_sibling_event(struct perf_event *event)
-{
-	event_sched_out(event, event->ctx);
-	perf_event_set_state(event, PERF_EVENT_STATE_ERROR);
-}
-
 static void perf_group_detach(struct perf_event *event)
 {
 	struct perf_event *leader = event->group_leader;
@@ -2289,8 +2283,15 @@ static void perf_group_detach(struct perf_event *event)
 	 */
 	list_for_each_entry_safe(sibling, tmp, &event->sibling_list, sibling_list) {
 
+		/*
+		 * Events that have PERF_EV_CAP_SIBLING require being part of
+		 * a group and cannot exist on their own, schedule them out
+		 * and move them into the ERROR state. Also see
+		 * _perf_event_enable(), it will not be able to recover this
+		 * ERROR state.
+		 */
 		if (sibling->event_caps & PERF_EV_CAP_SIBLING)
-			perf_remove_sibling_event(sibling);
+			__event_disable(sibling, ctx, PERF_EVENT_STATE_ERROR);
 
 		sibling->group_leader = sibling;
 		list_del_init(&sibling->sibling_list);
@@ -2493,11 +2494,14 @@ __perf_remove_from_context(struct perf_event *event,
 		state = PERF_EVENT_STATE_EXIT;
 	if (flags & DETACH_REVOKE)
 		state = PERF_EVENT_STATE_REVOKED;
-	if (flags & DETACH_DEAD) {
-		event->pending_disable = 1;
+	if (flags & DETACH_DEAD)
 		state = PERF_EVENT_STATE_DEAD;
-	}
+
 	event_sched_out(event, ctx);
+
+	if (event->state > PERF_EVENT_STATE_OFF)
+		perf_cgroup_event_disable(event, ctx);
+
 	perf_event_set_state(event, min(event->state, state));
 
 	if (flags & DETACH_GROUP)
@@ -2562,6 +2566,15 @@ static void perf_remove_from_context(struct perf_event *event, unsigned long fla
 	event_function_call(event, __perf_remove_from_context, (void *)flags);
 }
 
+static void __event_disable(struct perf_event *event,
+			    struct perf_event_context *ctx,
+			    enum perf_event_state state)
+{
+	event_sched_out(event, ctx);
+	perf_cgroup_event_disable(event, ctx);
+	perf_event_set_state(event, state);
+}
+
 /*
  * Cross CPU call to disable a performance event
  */
@@ -2576,13 +2589,18 @@ static void __perf_event_disable(struct perf_event *event,
 	perf_pmu_disable(event->pmu_ctx->pmu);
 	ctx_time_update_event(ctx, event);
 
+	/*
+	 * When disabling a group leader, the whole group becomes ineligible
+	 * to run, so schedule out the full group.
+	 */
 	if (event == event->group_leader)
 		group_sched_out(event, ctx);
-	else
-		event_sched_out(event, ctx);
 
-	perf_event_set_state(event, PERF_EVENT_STATE_OFF);
-	perf_cgroup_event_disable(event, ctx);
+	/*
+	 * But only mark the leader OFF; the siblings will remain
+	 * INACTIVE.
+	 */
+	__event_disable(event, ctx, PERF_EVENT_STATE_OFF);
 
 	perf_pmu_enable(event->pmu_ctx->pmu);
 }
@@ -2656,8 +2674,8 @@ static void perf_event_unthrottle(struct perf_event *event, bool start)
 
 static void perf_event_throttle(struct perf_event *event)
 {
-	event->pmu->stop(event, 0);
 	event->hw.interrupts = MAX_INTERRUPTS;
+	event->pmu->stop(event, 0);
 	if (event == event->group_leader)
 		perf_log_throttle(event, 0);
 }
@@ -7186,18 +7204,18 @@ void perf_event_wakeup(struct perf_event *event)
 static void perf_sigtrap(struct perf_event *event)
 {
 	/*
-	 * We'd expect this to only occur if the irq_work is delayed and either
-	 * ctx->task or current has changed in the meantime. This can be the
-	 * case on architectures that do not implement arch_irq_work_raise().
+	 * Both perf_pending_task() and perf_pending_irq() can race with the
+	 * task exiting.
 	 */
-	if (WARN_ON_ONCE(event->ctx->task != current))
+	if (current->flags & PF_EXITING)
 		return;
 
 	/*
-	 * Both perf_pending_task() and perf_pending_irq() can race with the
-	 * task exiting.
+	 * We'd expect this to only occur if the irq_work is delayed and either
+	 * ctx->task or current has changed in the meantime. This can be the
+	 * case on architectures that do not implement arch_irq_work_raise().
 	 */
-	if (current->flags & PF_EXITING)
+	if (WARN_ON_ONCE(event->ctx->task != current))
 		return;
 
 	send_sig_perf((void __user *)event->pending_addr,
@@ -7233,15 +7251,15 @@ static void __perf_pending_disable(struct perf_event *event)
 	 *  CPU-A			CPU-B
 	 *
 	 *  perf_event_disable_inatomic()
-	 *    @pending_disable = CPU-A;
+	 *    @pending_disable = 1;
 	 *    irq_work_queue();
 	 *
 	 *  sched-out
-	 *    @pending_disable = -1;
+	 *    @pending_disable = 0;
 	 *
 	 *				sched-in
 	 *				perf_event_disable_inatomic()
-	 *				  @pending_disable = CPU-B;
+	 *				  @pending_disable = 1;
 	 *				  irq_work_queue(); // FAILS
 	 *
 	 *  irq_work_run()
@@ -7439,6 +7457,10 @@ perf_sample_ustack_size(u16 stack_size, u16 header_size,
 	if (!regs)
 		return 0;
 
+	/* No mm, no stack, no dump. */
+	if (!current->mm)
+		return 0;
+
 	/*
 	 * Check if we fit in with the requested stack size into the:
 	 * - TASK_SIZE
@@ -8150,6 +8172,9 @@ perf_callchain(struct perf_event *event, struct pt_regs *regs)
 	const u32 max_stack = event->attr.sample_max_stack;
 	struct perf_callchain_entry *callchain;
 
+	if (!current->mm)
+		user = false;
+
 	if (!kernel && !user)
 		return &__empty_callchain;
 
@@ -11091,7 +11116,7 @@ static int perf_uprobe_event_init(struct perf_event *event)
 	if (event->attr.type != perf_uprobe.type)
 		return -ENOENT;
 
-	if (!perfmon_capable())
+	if (!capable(CAP_SYS_ADMIN))
 		return -EACCES;
 
 	/*
@@ -11749,7 +11774,12 @@ static void perf_swevent_cancel_hrtimer(struct perf_event *event)
 {
 	struct hw_perf_event *hwc = &event->hw;
 
-	if (is_sampling_event(event)) {
+	/*
+	 * The throttle can be triggered in the hrtimer handler.
+	 * The HRTIMER_NORESTART should be used to stop the timer,
+	 * rather than hrtimer_cancel(). See perf_swevent_hrtimer()
+	 */
+	if (is_sampling_event(event) && (hwc->interrupts != MAX_INTERRUPTS)) {
 		ktime_t remaining = hrtimer_get_remaining(&hwc->hrtimer);
 		local64_set(&hwc->period_left, ktime_to_ns(remaining));
 
@@ -11804,7 +11834,8 @@ static void cpu_clock_event_start(struct perf_event *event, int flags)
 static void cpu_clock_event_stop(struct perf_event *event, int flags)
 {
 	perf_swevent_cancel_hrtimer(event);
-	cpu_clock_event_update(event);
+	if (flags & PERF_EF_UPDATE)
+		cpu_clock_event_update(event);
 }
 
 static int cpu_clock_event_add(struct perf_event *event, int flags)
@@ -11882,7 +11913,8 @@ static void task_clock_event_start(struct perf_event *event, int flags)
 static void task_clock_event_stop(struct perf_event *event, int flags)
 {
 	perf_swevent_cancel_hrtimer(event);
-	task_clock_event_update(event, event->ctx->time);
+	if (flags & PERF_EF_UPDATE)
+		task_clock_event_update(event, event->ctx->time);
 }
 
 static int task_clock_event_add(struct perf_event *event, int flags)
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index d2aef87c7e9f..aa9a759e824f 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -441,7 +441,7 @@ void *perf_aux_output_begin(struct perf_output_handle *handle,
 		 * store that will be enabled on successful return
 		 */
 		if (!handle->size) { /* A, matches D */
-			event->pending_disable = smp_processor_id();
+			perf_event_disable_inatomic(handle->event);
 			perf_output_wakeup(handle);
 			WRITE_ONCE(rb->aux_nest, 0);
 			goto err_put;
@@ -526,7 +526,7 @@ void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size)
 
 	if (wakeup) {
 		if (handle->aux_flags & PERF_AUX_FLAG_TRUNCATED)
-			handle->event->pending_disable = smp_processor_id();
+			perf_event_disable_inatomic(handle->event);
 		perf_output_wakeup(handle);
 	}
 
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 8d783b5882b6..4c965ba77f9f 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -29,6 +29,7 @@
 #include <linux/workqueue.h>
 #include <linux/srcu.h>
 #include <linux/oom.h>          /* check_stable_address_space */
+#include <linux/pagewalk.h>
 
 #include <linux/uprobes.h>
 
@@ -152,91 +153,6 @@ static loff_t vaddr_to_offset(struct vm_area_struct *vma, unsigned long vaddr)
 }
 
 /**
- * __replace_page - replace page in vma by new page.
- * based on replace_page in mm/ksm.c
- *
- * @vma:      vma that holds the pte pointing to page
- * @addr:     address the old @page is mapped at
- * @old_page: the page we are replacing by new_page
- * @new_page: the modified page we replace page by
- *
- * If @new_page is NULL, only unmap @old_page.
- *
- * Returns 0 on success, negative error code otherwise.
- */
-static int __replace_page(struct vm_area_struct *vma, unsigned long addr,
-				struct page *old_page, struct page *new_page)
-{
-	struct folio *old_folio = page_folio(old_page);
-	struct folio *new_folio;
-	struct mm_struct *mm = vma->vm_mm;
-	DEFINE_FOLIO_VMA_WALK(pvmw, old_folio, vma, addr, 0);
-	int err;
-	struct mmu_notifier_range range;
-	pte_t pte;
-
-	mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, addr,
-				addr + PAGE_SIZE);
-
-	if (new_page) {
-		new_folio = page_folio(new_page);
-		err = mem_cgroup_charge(new_folio, vma->vm_mm, GFP_KERNEL);
-		if (err)
-			return err;
-	}
-
-	/* For folio_free_swap() below */
-	folio_lock(old_folio);
-
-	mmu_notifier_invalidate_range_start(&range);
-	err = -EAGAIN;
-	if (!page_vma_mapped_walk(&pvmw))
-		goto unlock;
-	VM_BUG_ON_PAGE(addr != pvmw.address, old_page);
-	pte = ptep_get(pvmw.pte);
-
-	/*
-	 * Handle PFN swap PTES, such as device-exclusive ones, that actually
-	 * map pages: simply trigger GUP again to fix it up.
-	 */
-	if (unlikely(!pte_present(pte))) {
-		page_vma_mapped_walk_done(&pvmw);
-		goto unlock;
-	}
-
-	if (new_page) {
-		folio_get(new_folio);
-		folio_add_new_anon_rmap(new_folio, vma, addr, RMAP_EXCLUSIVE);
-		folio_add_lru_vma(new_folio, vma);
-	} else
-		/* no new page, just dec_mm_counter for old_page */
-		dec_mm_counter(mm, MM_ANONPAGES);
-
-	if (!folio_test_anon(old_folio)) {
-		dec_mm_counter(mm, mm_counter_file(old_folio));
-		inc_mm_counter(mm, MM_ANONPAGES);
-	}
-
-	flush_cache_page(vma, addr, pte_pfn(pte));
-	ptep_clear_flush(vma, addr, pvmw.pte);
-	if (new_page)
-		set_pte_at(mm, addr, pvmw.pte,
-			   mk_pte(new_page, vma->vm_page_prot));
-
-	folio_remove_rmap_pte(old_folio, old_page, vma);
-	if (!folio_mapped(old_folio))
-		folio_free_swap(old_folio);
-	page_vma_mapped_walk_done(&pvmw);
-	folio_put(old_folio);
-
-	err = 0;
- unlock:
-	mmu_notifier_invalidate_range_end(&range);
-	folio_unlock(old_folio);
-	return err;
-}
-
-/**
  * is_swbp_insn - check if instruction is breakpoint instruction.
  * @insn: instruction to be checked.
  * Default implementation of is_swbp_insn
@@ -463,6 +379,95 @@ static int update_ref_ctr(struct uprobe *uprobe, struct mm_struct *mm,
 	return ret;
 }
 
+static bool orig_page_is_identical(struct vm_area_struct *vma,
+		unsigned long vaddr, struct page *page, bool *pmd_mappable)
+{
+	const pgoff_t index = vaddr_to_offset(vma, vaddr) >> PAGE_SHIFT;
+	struct folio *orig_folio = filemap_get_folio(vma->vm_file->f_mapping,
+						    index);
+	struct page *orig_page;
+	bool identical;
+
+	if (IS_ERR(orig_folio))
+		return false;
+	orig_page = folio_file_page(orig_folio, index);
+
+	*pmd_mappable = folio_test_pmd_mappable(orig_folio);
+	identical = folio_test_uptodate(orig_folio) &&
+		    pages_identical(page, orig_page);
+	folio_put(orig_folio);
+	return identical;
+}
+
+static int __uprobe_write_opcode(struct vm_area_struct *vma,
+		struct folio_walk *fw, struct folio *folio,
+		unsigned long opcode_vaddr, uprobe_opcode_t opcode)
+{
+	const unsigned long vaddr = opcode_vaddr & PAGE_MASK;
+	const bool is_register = !!is_swbp_insn(&opcode);
+	bool pmd_mappable;
+
+	/* For now, we'll only handle PTE-mapped folios. */
+	if (fw->level != FW_LEVEL_PTE)
+		return -EFAULT;
+
+	/*
+	 * See can_follow_write_pte(): we'd actually prefer a writable PTE here,
+	 * but the VMA might not be writable.
+	 */
+	if (!pte_write(fw->pte)) {
+		if (!PageAnonExclusive(fw->page))
+			return -EFAULT;
+		if (unlikely(userfaultfd_pte_wp(vma, fw->pte)))
+			return -EFAULT;
+		/* SOFTDIRTY is handled via pte_mkdirty() below. */
+	}
+
+	/*
+	 * We'll temporarily unmap the page and flush the TLB, such that we can
+	 * modify the page atomically.
+	 */
+	flush_cache_page(vma, vaddr, pte_pfn(fw->pte));
+	fw->pte = ptep_clear_flush(vma, vaddr, fw->ptep);
+	copy_to_page(fw->page, opcode_vaddr, &opcode, UPROBE_SWBP_INSN_SIZE);
+
+	/*
+	 * When unregistering, we may only zap a PTE if uffd is disabled and
+	 * there are no unexpected folio references ...
+	 */
+	if (is_register || userfaultfd_missing(vma) ||
+	    (folio_ref_count(folio) != folio_mapcount(folio) + 1 +
+	     folio_test_swapcache(folio) * folio_nr_pages(folio)))
+		goto remap;
+
+	/*
+	 * ... and the mapped page is identical to the original page that
+	 * would get faulted in on next access.
+	 */
+	if (!orig_page_is_identical(vma, vaddr, fw->page, &pmd_mappable))
+		goto remap;
+
+	dec_mm_counter(vma->vm_mm, MM_ANONPAGES);
+	folio_remove_rmap_pte(folio, fw->page, vma);
+	if (!folio_mapped(folio) && folio_test_swapcache(folio) &&
+	     folio_trylock(folio)) {
+		folio_free_swap(folio);
+		folio_unlock(folio);
+	}
+	folio_put(folio);
+
+	return pmd_mappable;
+remap:
+	/*
+	 * Make sure that our copy_to_page() changes become visible before the
+	 * set_pte_at() write.
+	 */
+	smp_wmb();
+	/* We modified the page. Make sure to mark the PTE dirty. */
+	set_pte_at(vma->vm_mm, vaddr, fw->ptep, pte_mkdirty(fw->pte));
+	return 0;
+}
+
 /*
  * NOTE:
  * Expect the breakpoint instruction to be the smallest size instruction for
@@ -474,146 +479,146 @@ static int update_ref_ctr(struct uprobe *uprobe, struct mm_struct *mm,
  *
  * uprobe_write_opcode - write the opcode at a given virtual address.
  * @auprobe: arch specific probepoint information.
- * @mm: the probed process address space.
- * @vaddr: the virtual address to store the opcode.
- * @opcode: opcode to be written at @vaddr.
+ * @vma: the probed virtual memory area.
+ * @opcode_vaddr: the virtual address to store the opcode.
+ * @opcode: opcode to be written at @opcode_vaddr.
  *
  * Called with mm->mmap_lock held for read or write.
  * Return 0 (success) or a negative errno.
  */
-int uprobe_write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm,
-			unsigned long vaddr, uprobe_opcode_t opcode)
+int uprobe_write_opcode(struct arch_uprobe *auprobe, struct vm_area_struct *vma,
+		const unsigned long opcode_vaddr, uprobe_opcode_t opcode)
 {
+	const unsigned long vaddr = opcode_vaddr & PAGE_MASK;
+	struct mm_struct *mm = vma->vm_mm;
 	struct uprobe *uprobe;
-	struct page *old_page, *new_page;
-	struct vm_area_struct *vma;
 	int ret, is_register, ref_ctr_updated = 0;
-	bool orig_page_huge = false;
 	unsigned int gup_flags = FOLL_FORCE;
+	struct mmu_notifier_range range;
+	struct folio_walk fw;
+	struct folio *folio;
+	struct page *page;
 
 	is_register = is_swbp_insn(&opcode);
 	uprobe = container_of(auprobe, struct uprobe, arch);
 
-retry:
+	if (WARN_ON_ONCE(!is_cow_mapping(vma->vm_flags)))
+		return -EINVAL;
+
+	/*
+	 * When registering, we have to break COW to get an exclusive anonymous
+	 * page that we can safely modify. Use FOLL_WRITE to trigger a write
+	 * fault if required. When unregistering, we might be lucky and the
+	 * anon page is already gone. So defer write faults until really
+	 * required. Use FOLL_SPLIT_PMD, because __uprobe_write_opcode()
+	 * cannot deal with PMDs yet.
+	 */
 	if (is_register)
-		gup_flags |= FOLL_SPLIT_PMD;
-	/* Read the page with vaddr into memory */
-	old_page = get_user_page_vma_remote(mm, vaddr, gup_flags, &vma);
-	if (IS_ERR(old_page))
-		return PTR_ERR(old_page);
+		gup_flags |= FOLL_WRITE | FOLL_SPLIT_PMD;
 
-	ret = verify_opcode(old_page, vaddr, &opcode);
+retry:
+	ret = get_user_pages_remote(mm, vaddr, 1, gup_flags, &page, NULL);
 	if (ret <= 0)
-		goto put_old;
-
-	if (is_zero_page(old_page)) {
-		ret = -EINVAL;
-		goto put_old;
-	}
+		goto out;
+	folio = page_folio(page);
 
-	if (WARN(!is_register && PageCompound(old_page),
-		 "uprobe unregister should never work on compound page\n")) {
-		ret = -EINVAL;
-		goto put_old;
+	ret = verify_opcode(page, opcode_vaddr, &opcode);
+	if (ret <= 0) {
+		folio_put(folio);
+		goto out;
 	}
 
 	/* We are going to replace instruction, update ref_ctr. */
 	if (!ref_ctr_updated && uprobe->ref_ctr_offset) {
 		ret = update_ref_ctr(uprobe, mm, is_register ? 1 : -1);
-		if (ret)
-			goto put_old;
+		if (ret) {
+			folio_put(folio);
+			goto out;
+		}
 
 		ref_ctr_updated = 1;
 	}
 
 	ret = 0;
-	if (!is_register && !PageAnon(old_page))
-		goto put_old;
-
-	ret = anon_vma_prepare(vma);
-	if (ret)
-		goto put_old;
-
-	ret = -ENOMEM;
-	new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, vaddr);
-	if (!new_page)
-		goto put_old;
-
-	__SetPageUptodate(new_page);
-	copy_highpage(new_page, old_page);
-	copy_to_page(new_page, vaddr, &opcode, UPROBE_SWBP_INSN_SIZE);
+	if (unlikely(!folio_test_anon(folio))) {
+		VM_WARN_ON_ONCE(is_register);
+		folio_put(folio);
+		goto out;
+	}
 
 	if (!is_register) {
-		struct page *orig_page;
-		pgoff_t index;
-
-		VM_BUG_ON_PAGE(!PageAnon(old_page), old_page);
-
-		index = vaddr_to_offset(vma, vaddr & PAGE_MASK) >> PAGE_SHIFT;
-		orig_page = find_get_page(vma->vm_file->f_inode->i_mapping,
-					  index);
-
-		if (orig_page) {
-			if (PageUptodate(orig_page) &&
-			    pages_identical(new_page, orig_page)) {
-				/* let go new_page */
-				put_page(new_page);
-				new_page = NULL;
-
-				if (PageCompound(orig_page))
-					orig_page_huge = true;
-			}
-			put_page(orig_page);
-		}
+		/*
+		 * In the common case, we'll be able to zap the page when
+		 * unregistering. So trigger MMU notifiers now, as we won't
+		 * be able to do it under PTL.
+		 */
+		mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm,
+					vaddr, vaddr + PAGE_SIZE);
+		mmu_notifier_invalidate_range_start(&range);
 	}
 
-	ret = __replace_page(vma, vaddr & PAGE_MASK, old_page, new_page);
-	if (new_page)
-		put_page(new_page);
-put_old:
-	put_page(old_page);
+	ret = -EAGAIN;
+	/* Walk the page tables again, to perform the actual update. */
+	if (folio_walk_start(&fw, vma, vaddr, 0)) {
+		if (fw.page == page)
+			ret = __uprobe_write_opcode(vma, &fw, folio, opcode_vaddr, opcode);
+		folio_walk_end(&fw, vma);
+	}
+
+	if (!is_register)
+		mmu_notifier_invalidate_range_end(&range);
 
-	if (unlikely(ret == -EAGAIN))
+	folio_put(folio);
+	switch (ret) {
+	case -EFAULT:
+		gup_flags |= FOLL_WRITE | FOLL_SPLIT_PMD;
+		fallthrough;
+	case -EAGAIN:
 		goto retry;
+	default:
+		break;
+	}
 
+out:
 	/* Revert back reference counter if instruction update failed. */
-	if (ret && is_register && ref_ctr_updated)
+	if (ret < 0 && is_register && ref_ctr_updated)
 		update_ref_ctr(uprobe, mm, -1);
 
 	/* try collapse pmd for compound page */
-	if (!ret && orig_page_huge)
+	if (ret > 0)
 		collapse_pte_mapped_thp(mm, vaddr, false);
 
-	return ret;
+	return ret < 0 ? ret : 0;
 }
 
 /**
  * set_swbp - store breakpoint at a given address.
  * @auprobe: arch specific probepoint information.
- * @mm: the probed process address space.
+ * @vma: the probed virtual memory area.
  * @vaddr: the virtual address to insert the opcode.
  *
  * For mm @mm, store the breakpoint instruction at @vaddr.
  * Return 0 (success) or a negative errno.
  */
-int __weak set_swbp(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr)
+int __weak set_swbp(struct arch_uprobe *auprobe, struct vm_area_struct *vma,
+		unsigned long vaddr)
 {
-	return uprobe_write_opcode(auprobe, mm, vaddr, UPROBE_SWBP_INSN);
+	return uprobe_write_opcode(auprobe, vma, vaddr, UPROBE_SWBP_INSN);
 }
 
 /**
  * set_orig_insn - Restore the original instruction.
- * @mm: the probed process address space.
+ * @vma: the probed virtual memory area.
  * @auprobe: arch specific probepoint information.
  * @vaddr: the virtual address to insert the opcode.
  *
  * For mm @mm, restore the original opcode (opcode) at @vaddr.
  * Return 0 (success) or a negative errno.
  */
-int __weak
-set_orig_insn(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr)
+int __weak set_orig_insn(struct arch_uprobe *auprobe,
+		struct vm_area_struct *vma, unsigned long vaddr)
 {
-	return uprobe_write_opcode(auprobe, mm, vaddr,
+	return uprobe_write_opcode(auprobe, vma, vaddr,
 			*(uprobe_opcode_t *)&auprobe->insn);
 }
 
@@ -1134,10 +1139,10 @@ static bool filter_chain(struct uprobe *uprobe, struct mm_struct *mm)
 	return ret;
 }
 
-static int
-install_breakpoint(struct uprobe *uprobe, struct mm_struct *mm,
-			struct vm_area_struct *vma, unsigned long vaddr)
+static int install_breakpoint(struct uprobe *uprobe, struct vm_area_struct *vma,
+		unsigned long vaddr)
 {
+	struct mm_struct *mm = vma->vm_mm;
 	bool first_uprobe;
 	int ret;
 
@@ -1153,7 +1158,7 @@ install_breakpoint(struct uprobe *uprobe, struct mm_struct *mm,
 	if (first_uprobe)
 		set_bit(MMF_HAS_UPROBES, &mm->flags);
 
-	ret = set_swbp(&uprobe->arch, mm, vaddr);
+	ret = set_swbp(&uprobe->arch, vma, vaddr);
 	if (!ret)
 		clear_bit(MMF_RECALC_UPROBES, &mm->flags);
 	else if (first_uprobe)
@@ -1162,11 +1167,13 @@ install_breakpoint(struct uprobe *uprobe, struct mm_struct *mm,
 	return ret;
 }
 
-static int
-remove_breakpoint(struct uprobe *uprobe, struct mm_struct *mm, unsigned long vaddr)
+static int remove_breakpoint(struct uprobe *uprobe, struct vm_area_struct *vma,
+		unsigned long vaddr)
 {
+	struct mm_struct *mm = vma->vm_mm;
+
 	set_bit(MMF_RECALC_UPROBES, &mm->flags);
-	return set_orig_insn(&uprobe->arch, mm, vaddr);
+	return set_orig_insn(&uprobe->arch, vma, vaddr);
 }
 
 struct map_info {
@@ -1296,10 +1303,10 @@ register_for_each_vma(struct uprobe *uprobe, struct uprobe_consumer *new)
 		if (is_register) {
 			/* consult only the "caller", new consumer. */
 			if (consumer_filter(new, mm))
-				err = install_breakpoint(uprobe, mm, vma, info->vaddr);
+				err = install_breakpoint(uprobe, vma, info->vaddr);
 		} else if (test_bit(MMF_HAS_UPROBES, &mm->flags)) {
 			if (!filter_chain(uprobe, mm))
-				err |= remove_breakpoint(uprobe, mm, info->vaddr);
+				err |= remove_breakpoint(uprobe, vma, info->vaddr);
 		}
 
  unlock:
@@ -1472,7 +1479,7 @@ static int unapply_uprobe(struct uprobe *uprobe, struct mm_struct *mm)
 			continue;
 
 		vaddr = offset_to_vaddr(vma, uprobe->offset);
-		err |= remove_breakpoint(uprobe, mm, vaddr);
+		err |= remove_breakpoint(uprobe, vma, vaddr);
 	}
 	mmap_read_unlock(mm);
 
@@ -1610,7 +1617,7 @@ int uprobe_mmap(struct vm_area_struct *vma)
 		if (!fatal_signal_pending(current) &&
 		    filter_chain(uprobe, vma->vm_mm)) {
 			unsigned long vaddr = offset_to_vaddr(vma, uprobe->offset);
-			install_breakpoint(uprobe, vma->vm_mm, vma, vaddr);
+			install_breakpoint(uprobe, vma, vaddr);
 		}
 		put_uprobe(uprobe);
 	}