uprobes/x86: Add mapping for optimized uprobe trampolines

Adding support to add special mapping for user space trampoline with
following functions:

  uprobe_trampoline_get - find or add uprobe_trampoline
  uprobe_trampoline_put - remove or destroy uprobe_trampoline

The user space trampoline is exported as arch specific user space special
mapping through tramp_mapping, which is initialized in following changes
with new uprobe syscall.

The uprobe trampoline needs to be callable/reachable from the probed address,
so while searching for available address we use is_reachable_by_call function
to decide if the uprobe trampoline is callable from the probe address.

All uprobe_trampoline objects are stored in uprobes_state object and are
cleaned up when the process mm_struct goes down. Adding new arch hooks
for that, because this change is x86_64 specific.

Locking is provided by callers in following changes.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Oleg Nesterov <oleg@redhat.com>
Acked-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Link: https://lore.kernel.org/r/20250720112133.244369-9-jolsa@kernel.org

arch/x86/kernel/uprobes.c

@@ -608,6 +608,150 @@ static void riprel_post_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
 		*sr = utask->autask.saved_scratch_register;
 	}
 }
+
+static int tramp_mremap(const struct vm_special_mapping *sm, struct vm_area_struct *new_vma)
+{
+	return -EPERM;
+}
+
+static struct page *tramp_mapping_pages[2] __ro_after_init;
+
+static struct vm_special_mapping tramp_mapping = {
+	.name   = "[uprobes-trampoline]",
+	.mremap = tramp_mremap,
+	.pages  = tramp_mapping_pages,
+};
+
+struct uprobe_trampoline {
+	struct hlist_node	node;
+	unsigned long		vaddr;
+};
+
+static bool is_reachable_by_call(unsigned long vtramp, unsigned long vaddr)
+{
+	long delta = (long)(vaddr + 5 - vtramp);
+
+	return delta >= INT_MIN && delta <= INT_MAX;
+}
+
+static unsigned long find_nearest_trampoline(unsigned long vaddr)
+{
+	struct vm_unmapped_area_info info = {
+		.length     = PAGE_SIZE,
+		.align_mask = ~PAGE_MASK,
+	};
+	unsigned long low_limit, high_limit;
+	unsigned long low_tramp, high_tramp;
+	unsigned long call_end = vaddr + 5;
+
+	if (check_add_overflow(call_end, INT_MIN, &low_limit))
+		low_limit = PAGE_SIZE;
+
+	high_limit = call_end + INT_MAX;
+
+	/* Search up from the caller address. */
+	info.low_limit = call_end;
+	info.high_limit = min(high_limit, TASK_SIZE);
+	high_tramp = vm_unmapped_area(&info);
+
+	/* Search down from the caller address. */
+	info.low_limit = max(low_limit, PAGE_SIZE);
+	info.high_limit = call_end;
+	info.flags = VM_UNMAPPED_AREA_TOPDOWN;
+	low_tramp = vm_unmapped_area(&info);
+
+	if (IS_ERR_VALUE(high_tramp) && IS_ERR_VALUE(low_tramp))
+		return -ENOMEM;
+	if (IS_ERR_VALUE(high_tramp))
+		return low_tramp;
+	if (IS_ERR_VALUE(low_tramp))
+		return high_tramp;
+
+	/* Return address that's closest to the caller address. */
+	if (call_end - low_tramp < high_tramp - call_end)
+		return low_tramp;
+	return high_tramp;
+}
+
+static struct uprobe_trampoline *create_uprobe_trampoline(unsigned long vaddr)
+{
+	struct pt_regs *regs = task_pt_regs(current);
+	struct mm_struct *mm = current->mm;
+	struct uprobe_trampoline *tramp;
+	struct vm_area_struct *vma;
+
+	if (!user_64bit_mode(regs))
+		return NULL;
+
+	vaddr = find_nearest_trampoline(vaddr);
+	if (IS_ERR_VALUE(vaddr))
+		return NULL;
+
+	tramp = kzalloc(sizeof(*tramp), GFP_KERNEL);
+	if (unlikely(!tramp))
+		return NULL;
+
+	tramp->vaddr = vaddr;
+	vma = _install_special_mapping(mm, tramp->vaddr, PAGE_SIZE,
+				VM_READ|VM_EXEC|VM_MAYEXEC|VM_MAYREAD|VM_DONTCOPY|VM_IO,
+				&tramp_mapping);
+	if (IS_ERR(vma)) {
+		kfree(tramp);
+		return NULL;
+	}
+	return tramp;
+}
+
+__maybe_unused
+static struct uprobe_trampoline *get_uprobe_trampoline(unsigned long vaddr, bool *new)
+{
+	struct uprobes_state *state = &current->mm->uprobes_state;
+	struct uprobe_trampoline *tramp = NULL;
+
+	if (vaddr > TASK_SIZE || vaddr < PAGE_SIZE)
+		return NULL;
+
+	hlist_for_each_entry(tramp, &state->head_tramps, node) {
+		if (is_reachable_by_call(tramp->vaddr, vaddr)) {
+			*new = false;
+			return tramp;
+		}
+	}
+
+	tramp = create_uprobe_trampoline(vaddr);
+	if (!tramp)
+		return NULL;
+
+	*new = true;
+	hlist_add_head(&tramp->node, &state->head_tramps);
+	return tramp;
+}
+
+static void destroy_uprobe_trampoline(struct uprobe_trampoline *tramp)
+{
+	/*
+	 * We do not unmap and release uprobe trampoline page itself,
+	 * because there's no easy way to make sure none of the threads
+	 * is still inside the trampoline.
+	 */
+	hlist_del(&tramp->node);
+	kfree(tramp);
+}
+
+void arch_uprobe_init_state(struct mm_struct *mm)
+{
+	INIT_HLIST_HEAD(&mm->uprobes_state.head_tramps);
+}
+
+void arch_uprobe_clear_state(struct mm_struct *mm)
+{
+	struct uprobes_state *state = &mm->uprobes_state;
+	struct uprobe_trampoline *tramp;
+	struct hlist_node *n;
+
+	hlist_for_each_entry_safe(tramp, n, &state->head_tramps, node)
+		destroy_uprobe_trampoline(tramp);
+}
 #else /* 32-bit: */
 /*
  * No RIP-relative addressing on 32-bit

include/linux/uprobes.h

@@ -17,6 +17,7 @@
 #include <linux/wait.h>
 #include <linux/timer.h>
 #include <linux/seqlock.h>
+#include <linux/mutex.h>
 
 struct uprobe;
 struct vm_area_struct;
@@ -185,6 +186,9 @@ struct xol_area;
 
 struct uprobes_state {
 	struct xol_area		*xol_area;
+#ifdef CONFIG_X86_64
+	struct hlist_head	head_tramps;
+#endif
 };
 
 typedef int (*uprobe_write_verify_t)(struct page *page, unsigned long vaddr,
@@ -233,6 +237,8 @@ extern void uprobe_handle_trampoline(struct pt_regs *regs);
 extern void *arch_uretprobe_trampoline(unsigned long *psize);
 extern unsigned long uprobe_get_trampoline_vaddr(void);
 extern void uprobe_copy_from_page(struct page *page, unsigned long vaddr, void *dst, int len);
+extern void arch_uprobe_clear_state(struct mm_struct *mm);
+extern void arch_uprobe_init_state(struct mm_struct *mm);
 #else /* !CONFIG_UPROBES */
 struct uprobes_state {
 };

kernel/events/uprobes.c

@@ -1801,6 +1801,14 @@ static struct xol_area *get_xol_area(void)
 	return area;
 }
 
+void __weak arch_uprobe_clear_state(struct mm_struct *mm)
+{
+}
+
+void __weak arch_uprobe_init_state(struct mm_struct *mm)
+{
+}
+
 /*
  * uprobe_clear_state - Free the area allocated for slots.
  */
@@ -1812,6 +1820,8 @@ void uprobe_clear_state(struct mm_struct *mm)
 	delayed_uprobe_remove(NULL, mm);
 	mutex_unlock(&delayed_uprobe_lock);
 
+	arch_uprobe_clear_state(mm);
+
 	if (!area)
 		return;
 

kernel/fork.c

@@ -1015,6 +1015,7 @@ static void mm_init_uprobes_state(struct mm_struct *mm)
 {
 #ifdef CONFIG_UPROBES
 	mm->uprobes_state.xol_area = NULL;
+	arch_uprobe_init_state(mm);
 #endif
 }