Skip to contentSkip to conversation

uprobes/x86: Fix red zone issue for optimized uprobes

PATCH Applied Jiri Olsa 7 participants 42 messages Jul 3 – Jul 4

Subsystems (11)
x86 Kselftest BPF perf events +7 more subsystems
lore
Share & tools
lore

Jiri Olsa

author reviewer
#0 lore raw

v6 cover uprobes/x86: Fix red zone issue for optimized uprobes

hi,
Andrii reported an issue with optimized uprobes [1] that can clobber redzone area with call instruction storing return address on stack where user code may keep temporary data without adjusting rsp.

Fixing this by moving the optimized uprobes on top of 10-bytes nop instruction, so we can squeeze another instruction to escape the redzone area before doing the call.

Note we need upstream update first for patch 3 (github.com/libbpf/usdt), if we decide to take this change.

thanks,
jirka

v1: https://lore.kernel.org/bpf/[email protected]/
v2: https://lore.kernel.org/bpf/[email protected]/
v3: https://lore.kernel.org/bpf/[email protected]/
v4: https://lore.kernel.org/bpf/[email protected]/
v5: https://lore.kernel.org/bpf/[email protected]/

v6 changes:
- added upstream commit ref for patch#8
- release link in test_uprobe_fork_optimized [ci/asan]

v5 changes:
- several selftests changes and reviewed-by tags [Jakub]
- add more comments in int3_update_unoptimize [Andrii]
- several other minor changes and acks [Oleg]
- move insn_decode out of uprobe_init_insn to simplify the code
- align uprobe_red_zone_test to 64 to make sure nop10 is not on page boundary

v4 changes:
- do not use 2nd int3 (ont +5 offset) because the call instruction is allways the same for the given nop10 address [Andrii/Peter]
- unmap unused trampoline vma after unsuccesfull optimization [sashiko]
- small change to patch#2 moved user_64bit_mode earlier in the path and pass/use mm_struct pointer directly from arch_uprobe_optimize instead of gettting current->mm
Andrii, keeping your ack, please shout otherwise

v3 changes:
- use nop10 update suggested by Peter in [2]
- remove struct uprobe_trampoline object, use vma objects directly instead
- selftests fixes [sashiko]
- ack from Andrii

v2 changes:
- several selftest fixes [sashiko]
- consolidate is_lea_insn and is_call_insn insto single check [Jakub Sitnicki]
- use proper mm_struct object in __in_uprobe_trampoline check [sashiko]
- allow to copy uprobe trampolines vma objects on fork [sashiko]
- change uprobe syscall detection error from -ENXIO to -EPROTO [Andrii]
- added fork/clone tests
- I kept the selftest changes and nop5->nop10 changes in separate commits for easier review, we can squash them later if we want to keep bisect working properly

[1] https://lore.kernel.org/bpf/[email protected]/
[2] https://lore.kernel.org/bpf/[email protected]/#t
---
Andrii Nakryiko (1):
selftests/bpf: Add tests for uprobe nop10 red zone clobbering

Jiri Olsa (12):
uprobes/x86: Use proper mm_struct in __in_uprobe_trampoline uprobes/x86: Remove struct uprobe_trampoline object uprobes/x86: Do not leak trampoline vma mapping on optimization failure uprobes/x86: Allow to copy uprobe trampolines on fork uprobes/x86: Move optimized uprobe from nop5 to nop10
libbpf: Change has_nop_combo to work on top of nop10
libbpf: Detect uprobe syscall with new error
selftests/bpf: Emit nop,nop10 instructions combo for x86_64 arch selftests/bpf: Change uprobe syscall tests to use nop10 selftests/bpf: Change uprobe/usdt trigger bench code to use nop10 selftests/bpf: Add reattach tests for uprobe syscall selftests/bpf: Add tests for forked/cloned optimized uprobes

 arch/x86/kernel/uprobes.c                               | 416 +++++++++++++++++++++++++++++++++++++++++++-----------------------------
 include/linux/uprobes.h                                 |   5 -
 kernel/events/uprobes.c                                 |  10 --
 kernel/fork.c                                           |   1 -
 tools/lib/bpf/features.c                                |   4 +-
 tools/lib/bpf/usdt.c                                    |  16 +--
 tools/testing/selftests/bpf/bench.c                     |  20 ++--
 tools/testing/selftests/bpf/benchs/bench_trigger.c      |  38 +++----
 tools/testing/selftests/bpf/benchs/run_bench_uprobes.sh |   2 +-
 tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c | 325 ++++++++++++++++++++++++++++++++++++++++++++++++++++----
 tools/testing/selftests/bpf/prog_tests/usdt.c           |  74 +++++++++++--
 tools/testing/selftests/bpf/progs/test_usdt.c           |  25 +++++
 tools/testing/selftests/bpf/usdt.h                      |   2 +-
 tools/testing/selftests/bpf/usdt_2.c                    |  15 ++-
 14 files changed, 697 insertions(+), 256 deletions(-)
author reviewer
#1 lore raw

PATCH v6 1/13 uprobes/x86: Use proper mm_struct in __in_uprobe_trampoline

In the unregister path we use __in_uprobe_trampoline check with current->mm for the VMA lookup, which is wrong, because we are in the tracer context, not the traced process.

Add mm_struct pointer argument to __in_uprobe_trampoline and changing related callers to pass proper mm_struct pointer.

Fixes ba2bfc97b462 ("uprobes/x86: Add support to optimize uprobes")
---
 arch/x86/kernel/uprobes.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)
arch/x86/kernel/uprobes.c +7 -7
index ebb1baf1eb1d..2be6707e3320 100644
@@ -761,9 +761,9 @@ void arch_uprobe_clear_state(struct mm_struct *mm)
 		destroy_uprobe_trampoline(tramp);
 }
 
-static bool __in_uprobe_trampoline(unsigned long ip)
+static bool __in_uprobe_trampoline(struct mm_struct *mm, unsigned long ip)
 {
-	struct vm_area_struct *vma = vma_lookup(current->mm, ip);
+	struct vm_area_struct *vma = vma_lookup(mm, ip);
 
 	return vma && vma_is_special_mapping(vma, &tramp_mapping);
 }
@@ -776,14 +776,14 @@ static bool in_uprobe_trampoline(unsigned long ip)
 
 	rcu_read_lock();
 	if (mmap_lock_speculate_try_begin(mm, &seq)) {
-		found = __in_uprobe_trampoline(ip);
+		found = __in_uprobe_trampoline(mm, ip);
 		retry = mmap_lock_speculate_retry(mm, seq);
 	}
 	rcu_read_unlock();
 
 	if (retry) {
 		mmap_read_lock(mm);
-		found = __in_uprobe_trampoline(ip);
+		found = __in_uprobe_trampoline(mm, ip);
 		mmap_read_unlock(mm);
 	}
 	return found;
@@ -1044,7 +1044,7 @@ static int copy_from_vaddr(struct mm_struct *mm, unsigned long vaddr, void *dst,
 	return 0;
 }
 
-static bool __is_optimized(uprobe_opcode_t *insn, unsigned long vaddr)
+static bool __is_optimized(struct mm_struct *mm, uprobe_opcode_t *insn, unsigned long vaddr)
 {
 	struct __packed __arch_relative_insn {
 		u8 op;
@@ -1053,7 +1053,7 @@ static bool __is_optimized(uprobe_opcode_t *insn, unsigned long vaddr)
 
 	if (!is_call_insn(insn))
 		return false;
-	return __in_uprobe_trampoline(vaddr + 5 + call->raddr);
+	return __in_uprobe_trampoline(mm, vaddr + 5 + call->raddr);
 }
 
 static int is_optimized(struct mm_struct *mm, unsigned long vaddr)
@@ -1064,7 +1064,7 @@ static int is_optimized(struct mm_struct *mm, unsigned long vaddr)
 	err = copy_from_vaddr(mm, vaddr, &insn, 5);
 	if (err)
 		return err;
-	return __is_optimized((uprobe_opcode_t *)&insn, vaddr);
+	return __is_optimized(mm, (uprobe_opcode_t *)&insn, vaddr);
 }
 
 static bool should_optimize(struct arch_uprobe *auprobe)
Signature · 1 line
2.54.0
author reviewer
#2 lore raw

PATCH v6 2/13 uprobes/x86: Remove struct uprobe_trampoline object

In reply to Jiri Olsa

Removing struct uprobe_trampoline object and it's tracking code, because it's not needed. We can do same thing directly on top of struct vm_area_struct objects.

This makes the code simpler and allows easy propagation of the trampoline vma object into child process in following change.

Note the original code called destroy_uprobe_trampoline if the optimiation failed, but it only freed the struct uprobe_trampoline object, not the vma. The new vma leak is fixed in following change.

---
 arch/x86/kernel/uprobes.c | 106 ++++++++------------------------------
 include/linux/uprobes.h   |   5 --
 kernel/events/uprobes.c   |  10 ----
 kernel/fork.c             |   1 -
 4 files changed, 22 insertions(+), 100 deletions(-)
arch/x86/kernel/uprobes.c +22 -84
index 2be6707e3320..d2933cf77cd3 100644
@@ -631,11 +631,6 @@ static struct vm_special_mapping tramp_mapping = {
 	.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);
@@ -682,83 +677,28 @@ static unsigned long find_nearest_trampoline(unsigned long vaddr)
 	return high_tramp;
 }
 
-static struct uprobe_trampoline *create_uprobe_trampoline(unsigned long vaddr)
+static struct vm_area_struct *get_uprobe_trampoline(struct mm_struct *mm, unsigned long vaddr)
 {
-	struct pt_regs *regs = task_pt_regs(current);
-	struct mm_struct *mm = current->mm;
-	struct uprobe_trampoline *tramp;
+	VMA_ITERATOR(vmi, mm, 0);
 	struct vm_area_struct *vma;
 
-	if (!user_64bit_mode(regs))
-		return NULL;
+	if (vaddr > TASK_SIZE || vaddr < PAGE_SIZE)
+		return ERR_PTR(-EINVAL);
+
+	for_each_vma(vmi, vma) {
+		if (!vma_is_special_mapping(vma, &tramp_mapping))
+			continue;
+		if (is_reachable_by_call(vma->vm_start, vaddr))
+			return vma;
+	}
 
 	vaddr = find_nearest_trampoline(vaddr);
 	if (IS_ERR_VALUE(vaddr))
-		return NULL;
+		return ERR_PTR(vaddr);
 
-	tramp = kzalloc_obj(*tramp);
-	if (unlikely(!tramp))
-		return NULL;
-
-	tramp->vaddr = vaddr;
-	vma = _install_special_mapping(mm, tramp->vaddr, PAGE_SIZE,
+	return _install_special_mapping(mm, 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;
-}
-
-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);
 }
 
 static bool __in_uprobe_trampoline(struct mm_struct *mm, unsigned long ip)
@@ -1111,21 +1051,19 @@ int set_orig_insn(struct arch_uprobe *auprobe, struct vm_area_struct *vma,
 static int __arch_uprobe_optimize(struct arch_uprobe *auprobe, struct mm_struct *mm,
 				  unsigned long vaddr)
 {
-	struct uprobe_trampoline *tramp;
-	struct vm_area_struct *vma;
-	bool new = false;
-	int err = 0;
+	struct pt_regs *regs = task_pt_regs(current);
+	struct vm_area_struct *vma, *tramp;
+	int ret;
 
+	if (!user_64bit_mode(regs))
+		return -EINVAL;
 	vma = find_vma(mm, vaddr);
 	if (!vma)
 		return -EINVAL;
-	tramp = get_uprobe_trampoline(vaddr, &new);
-	if (!tramp)
-		return -EINVAL;
-	err = swbp_optimize(auprobe, vma, vaddr, tramp->vaddr);
-	if (WARN_ON_ONCE(err) && new)
-		destroy_uprobe_trampoline(tramp);
-	return err;
+	tramp = get_uprobe_trampoline(mm, vaddr);
+	if (IS_ERR(tramp))
+		return PTR_ERR(tramp);
+	return WARN_ON_ONCE(swbp_optimize(auprobe, vma, vaddr, tramp->vm_start));
 }
 
 void arch_uprobe_optimize(struct arch_uprobe *auprobe, unsigned long vaddr)
include/linux/uprobes.h +0 -5
index f548fea2adec..18be159bbc34 100644
@@ -186,9 +186,6 @@ 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,
@@ -238,8 +235,6 @@ 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);
 extern void handle_syscall_uprobe(struct pt_regs *regs, unsigned long bp_vaddr);
 extern void arch_uprobe_optimize(struct arch_uprobe *auprobe, unsigned long vaddr);
 extern unsigned long arch_uprobe_get_xol_area(void);
kernel/events/uprobes.c +0 -10
index 4084e926e284..b5c516168f84 100644
@@ -1806,14 +1806,6 @@ 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.
  */
@@ -1825,8 +1817,6 @@ 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 +0 -1
index 13e38e89a1f3..00b52c7314d1 100644
@@ -1064,7 +1064,6 @@ 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
 }
 
Signature · 1 line
2.54.0
merge bot Applied
#3 lore raw

[tip: perf/core] uprobes/x86: Remove struct uprobe_trampoline object

The following commit has been merged into the perf/core branch of tip:

The following commit has been merged into the perf/core branch of tip:

Commit-ID:     38af0dd6a266057002eacb170c08298ea912fb0a
Gitweb:        https://git.kernel.org/tip/38af0dd6a266057002eacb170c08298ea912fb0a
Author:        Jiri Olsa <[email protected]>
AuthorDate:    Fri, 03 Jul 2026 13:49:06 +02:00
Committer:     Peter Zijlstra <[email protected]>
CommitterDate: Fri, 03 Jul 2026 16:30:35 +02:00

uprobes/x86: Remove struct uprobe_trampoline object

Removing struct uprobe_trampoline object and it's tracking code, because it's not needed. We can do same thing directly on top of struct vm_area_struct objects.

This makes the code simpler and allows easy propagation of the trampoline vma object into child process in following change.

Note the original code called destroy_uprobe_trampoline if the optimiation failed, but it only freed the struct uprobe_trampoline object, not the vma. The new vma leak is fixed in following change.

---
 arch/x86/kernel/uprobes.c | 106 +++++++------------------------------
 include/linux/uprobes.h   |   5 +--
 kernel/events/uprobes.c   |  10 +---
 kernel/fork.c             |   1 +-
 4 files changed, 22 insertions(+), 100 deletions(-)
arch/x86/kernel/uprobes.c +22 -84
index 3af979f..a76203a 100644
@@ -631,11 +631,6 @@ static struct vm_special_mapping tramp_mapping = {
 	.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);
@@ -682,83 +677,28 @@ static unsigned long find_nearest_trampoline(unsigned long vaddr)
 	return high_tramp;
 }
 
-static struct uprobe_trampoline *create_uprobe_trampoline(unsigned long vaddr)
+static struct vm_area_struct *get_uprobe_trampoline(struct mm_struct *mm, unsigned long vaddr)
 {
-	struct pt_regs *regs = task_pt_regs(current);
-	struct mm_struct *mm = current->mm;
-	struct uprobe_trampoline *tramp;
+	VMA_ITERATOR(vmi, mm, 0);
 	struct vm_area_struct *vma;
 
-	if (!user_64bit_mode(regs))
-		return NULL;
+	if (vaddr > TASK_SIZE || vaddr < PAGE_SIZE)
+		return ERR_PTR(-EINVAL);
+
+	for_each_vma(vmi, vma) {
+		if (!vma_is_special_mapping(vma, &tramp_mapping))
+			continue;
+		if (is_reachable_by_call(vma->vm_start, vaddr))
+			return vma;
+	}
 
 	vaddr = find_nearest_trampoline(vaddr);
 	if (IS_ERR_VALUE(vaddr))
-		return NULL;
+		return ERR_PTR(vaddr);
 
-	tramp = kzalloc_obj(*tramp);
-	if (unlikely(!tramp))
-		return NULL;
-
-	tramp->vaddr = vaddr;
-	vma = _install_special_mapping(mm, tramp->vaddr, PAGE_SIZE,
+	return _install_special_mapping(mm, 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;
-}
-
-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);
 }
 
 static bool __in_uprobe_trampoline(struct mm_struct *mm, unsigned long ip)
@@ -1111,21 +1051,19 @@ int set_orig_insn(struct arch_uprobe *auprobe, struct vm_area_struct *vma,
 static int __arch_uprobe_optimize(struct arch_uprobe *auprobe, struct mm_struct *mm,
 				  unsigned long vaddr)
 {
-	struct uprobe_trampoline *tramp;
-	struct vm_area_struct *vma;
-	bool new = false;
-	int err = 0;
+	struct pt_regs *regs = task_pt_regs(current);
+	struct vm_area_struct *vma, *tramp;
+	int ret;
 
+	if (!user_64bit_mode(regs))
+		return -EINVAL;
 	vma = find_vma(mm, vaddr);
 	if (!vma)
 		return -EINVAL;
-	tramp = get_uprobe_trampoline(vaddr, &new);
-	if (!tramp)
-		return -EINVAL;
-	err = swbp_optimize(auprobe, vma, vaddr, tramp->vaddr);
-	if (WARN_ON_ONCE(err) && new)
-		destroy_uprobe_trampoline(tramp);
-	return err;
+	tramp = get_uprobe_trampoline(mm, vaddr);
+	if (IS_ERR(tramp))
+		return PTR_ERR(tramp);
+	return WARN_ON_ONCE(swbp_optimize(auprobe, vma, vaddr, tramp->vm_start));
 }
 
 void arch_uprobe_optimize(struct arch_uprobe *auprobe, unsigned long vaddr)
include/linux/uprobes.h +0 -5
index f548fea..18be159 100644
@@ -186,9 +186,6 @@ 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,
@@ -238,8 +235,6 @@ 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);
 extern void handle_syscall_uprobe(struct pt_regs *regs, unsigned long bp_vaddr);
 extern void arch_uprobe_optimize(struct arch_uprobe *auprobe, unsigned long vaddr);
 extern unsigned long arch_uprobe_get_xol_area(void);
kernel/events/uprobes.c +0 -10
index 4084e92..b5c5161 100644
@@ -1806,14 +1806,6 @@ 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.
  */
@@ -1825,8 +1817,6 @@ 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 +0 -1
index 13e38e8..00b52c7 100644
@@ -1064,7 +1064,6 @@ 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
 }
 
author reviewer
#4 lore raw

PATCH v6 3/13 uprobes/x86: Do not leak trampoline vma mapping on optimization failure

In reply to Jiri Olsa

In case the optimization fails, we leak new-ly created trampoline vma mapping (in case we just created it), let's unmap it.

Fixes ba2bfc97b462 ("uprobes/x86: Add support to optimize uprobes")
---
 arch/x86/kernel/uprobes.c | 14 +++++++++++---
 1 file changed, 11 insertions(+), 3 deletions(-)
arch/x86/kernel/uprobes.c +11 -3
index d2933cf77cd3..5730d41eb5f2 100644
@@ -677,11 +677,14 @@ static unsigned long find_nearest_trampoline(unsigned long vaddr)
 	return high_tramp;
 }
 
-static struct vm_area_struct *get_uprobe_trampoline(struct mm_struct *mm, unsigned long vaddr)
+static struct vm_area_struct *get_uprobe_trampoline(struct mm_struct *mm, unsigned long vaddr,
+						    bool *new_mapping)
 {
 	VMA_ITERATOR(vmi, mm, 0);
 	struct vm_area_struct *vma;
 
+	*new_mapping = false;
+
 	if (vaddr > TASK_SIZE || vaddr < PAGE_SIZE)
 		return ERR_PTR(-EINVAL);
 
@@ -696,6 +699,7 @@ static struct vm_area_struct *get_uprobe_trampoline(struct mm_struct *mm, unsign
 	if (IS_ERR_VALUE(vaddr))
 		return ERR_PTR(vaddr);
 
+	*new_mapping = true;
 	return _install_special_mapping(mm, vaddr, PAGE_SIZE,
 				VM_READ|VM_EXEC|VM_MAYEXEC|VM_MAYREAD|VM_DONTCOPY|VM_IO,
 				&tramp_mapping);
@@ -1053,6 +1057,7 @@ static int __arch_uprobe_optimize(struct arch_uprobe *auprobe, struct mm_struct
 {
 	struct pt_regs *regs = task_pt_regs(current);
 	struct vm_area_struct *vma, *tramp;
+	bool new_mapping;
 	int ret;
 
 	if (!user_64bit_mode(regs))
@@ -1060,10 +1065,13 @@ static int __arch_uprobe_optimize(struct arch_uprobe *auprobe, struct mm_struct
 	vma = find_vma(mm, vaddr);
 	if (!vma)
 		return -EINVAL;
-	tramp = get_uprobe_trampoline(mm, vaddr);
+	tramp = get_uprobe_trampoline(mm, vaddr, &new_mapping);
 	if (IS_ERR(tramp))
 		return PTR_ERR(tramp);
-	return WARN_ON_ONCE(swbp_optimize(auprobe, vma, vaddr, tramp->vm_start));
+	ret = swbp_optimize(auprobe, vma, vaddr, tramp->vm_start);
+	if (WARN_ON_ONCE(ret) && new_mapping)
+		WARN_ON_ONCE(do_munmap(mm, tramp->vm_start, PAGE_SIZE, NULL));
+	return ret;
 }
 
 void arch_uprobe_optimize(struct arch_uprobe *auprobe, unsigned long vaddr)
Signature · 1 line
2.54.0
#5 lore raw

Re: [PATCHv6 03/13] uprobes/x86: Do not leak trampoline vma mapping on optimization failure

Should the Fixes: tag point to f4216a203c5d ("uprobes/x86: Remove struct uprobe_trampoline object") instead?
Quoted 6 lines

uprobes/x86: Do not leak trampoline vma mapping on optimization failure

In case the optimization fails, we leak new-ly created trampoline vma mapping (in case we just created it), let's unmap it.

Fixes ba2bfc97b462 ("uprobes/x86: Add support to optimize uprobes")

Should the Fixes: tag point to f4216a203c5d ("uprobes/x86: Remove struct uprobe_trampoline object") instead?

The commit message of f4216a203c5d explicitly states: "Note the original code called destroy_uprobe_trampoline if the optimiation failed, but it only freed the struct uprobe_trampoline object, not the vma. The new vma leak is fixed in following change."

This commit (ba6320f8c716) appears to be that following change fixing the new vma leak introduced by f4216a203c5d.

Quoted 2 lines

---
AI reviewed your patch. Please fix the bug or email reply why it's not a bug.
See: https://github.com/kernel-patches/vmtest/blob/master/ci/claude/README.md

CI run summary: https://github.com/kernel-patches/bpf/actions/runs/28659696456

maintainer
#6 lore raw

Re: [PATCHv6 03/13] uprobes/x86: Do not leak trampoline vma mapping on optimization failure

In reply to Jiri Olsa
Quoted 6 lines · Jiri Olsa

In case the optimization fails, we leak new-ly created trampoline vma mapping (in case we just created it), let's unmap it.

Fixes ba2bfc97b462 ("uprobes/x86: Add support to optimize uprobes")

What is the intention here? That is, Patch 1 has a Fixes and is already in tip/perf/urgent (from v5), patch 2 does not have Fixes, this patch
(3) has Fixes and appears to rely on patch 2.

So should I stick both 2,3 into perf/urgent or what?

#7 lore raw

Re: [PATCHv6 03/13] uprobes/x86: Do not leak trampoline vma mapping on optimization failure

Quoted 8 lines · Peter Zijlstra
Quoted 6 lines · Jiri Olsa

In case the optimization fails, we leak new-ly created trampoline vma mapping (in case we just created it), let's unmap it.

Fixes ba2bfc97b462 ("uprobes/x86: Add support to optimize uprobes")
Quoted 5 lines

What is the intention here? That is, Patch 1 has a Fixes and is already in tip/perf/urgent (from v5), patch 2 does not have Fixes, this patch
(3) has Fixes and appears to rely on patch 2.

So should I stick both 2,3 into perf/urgent or what?

patch 3 fixes the vma mapping leak, and it is done on top of bigger change in patch 2

I think we are ok without patch 3 in perf/urgent, but if we want to have it there, it needs patch 2

jirka

merge bot Applied
#8 lore raw

[tip: perf/core] uprobes/x86: Do not leak trampoline vma mapping on optimization failure

In reply to Jiri Olsa
The following commit has been merged into the perf/core branch of tip:

The following commit has been merged into the perf/core branch of tip:

Commit-ID:     07c308eb2bcfe4727ba669e1ba6f5b0ba7d2696e
Gitweb:        https://git.kernel.org/tip/07c308eb2bcfe4727ba669e1ba6f5b0ba7d2696e
Author:        Jiri Olsa <[email protected]>
AuthorDate:    Fri, 03 Jul 2026 13:49:07 +02:00
Committer:     Peter Zijlstra <[email protected]>
CommitterDate: Fri, 03 Jul 2026 16:30:35 +02:00

uprobes/x86: Do not leak trampoline vma mapping on optimization failure

In case the optimization fails, we leak new-ly created trampoline vma mapping (in case we just created it), let's unmap it.

Fixes ba2bfc97b462 ("uprobes/x86: Add support to optimize uprobes")
---
 arch/x86/kernel/uprobes.c | 14 +++++++++++---
 1 file changed, 11 insertions(+), 3 deletions(-)
arch/x86/kernel/uprobes.c +11 -3
index a76203a..7f82056 100644
@@ -677,11 +677,14 @@ static unsigned long find_nearest_trampoline(unsigned long vaddr)
 	return high_tramp;
 }
 
-static struct vm_area_struct *get_uprobe_trampoline(struct mm_struct *mm, unsigned long vaddr)
+static struct vm_area_struct *get_uprobe_trampoline(struct mm_struct *mm, unsigned long vaddr,
+						    bool *new_mapping)
 {
 	VMA_ITERATOR(vmi, mm, 0);
 	struct vm_area_struct *vma;
 
+	*new_mapping = false;
+
 	if (vaddr > TASK_SIZE || vaddr < PAGE_SIZE)
 		return ERR_PTR(-EINVAL);
 
@@ -696,6 +699,7 @@ static struct vm_area_struct *get_uprobe_trampoline(struct mm_struct *mm, unsign
 	if (IS_ERR_VALUE(vaddr))
 		return ERR_PTR(vaddr);
 
+	*new_mapping = true;
 	return _install_special_mapping(mm, vaddr, PAGE_SIZE,
 				VM_READ|VM_EXEC|VM_MAYEXEC|VM_MAYREAD|VM_DONTCOPY|VM_IO,
 				&tramp_mapping);
@@ -1053,6 +1057,7 @@ static int __arch_uprobe_optimize(struct arch_uprobe *auprobe, struct mm_struct 
 {
 	struct pt_regs *regs = task_pt_regs(current);
 	struct vm_area_struct *vma, *tramp;
+	bool new_mapping;
 	int ret;
 
 	if (!user_64bit_mode(regs))
@@ -1060,10 +1065,13 @@ static int __arch_uprobe_optimize(struct arch_uprobe *auprobe, struct mm_struct 
 	vma = find_vma(mm, vaddr);
 	if (!vma)
 		return -EINVAL;
-	tramp = get_uprobe_trampoline(mm, vaddr);
+	tramp = get_uprobe_trampoline(mm, vaddr, &new_mapping);
 	if (IS_ERR(tramp))
 		return PTR_ERR(tramp);
-	return WARN_ON_ONCE(swbp_optimize(auprobe, vma, vaddr, tramp->vm_start));
+	ret = swbp_optimize(auprobe, vma, vaddr, tramp->vm_start);
+	if (WARN_ON_ONCE(ret) && new_mapping)
+		WARN_ON_ONCE(do_munmap(mm, tramp->vm_start, PAGE_SIZE, NULL));
+	return ret;
 }
 
 void arch_uprobe_optimize(struct arch_uprobe *auprobe, unsigned long vaddr)
author reviewer
#9 lore raw

PATCH v6 4/13 uprobes/x86: Allow to copy uprobe trampolines on fork

In reply to Jiri Olsa

When we do fork or clone without CLONE_VM the new process won't have uprobe trampoline vma objects and at the same time it will have optimized code calling that trampoline and crash.

Fixing this by allowing vma uprobe trampoline objects to be copied on fork to the new process.

Fixes ba2bfc97b462 ("uprobes/x86: Add support to optimize uprobes")
---
 arch/x86/kernel/uprobes.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
arch/x86/kernel/uprobes.c +1 -1
index 5730d41eb5f2..af5af7d67999 100644
@@ -701,7 +701,7 @@ static struct vm_area_struct *get_uprobe_trampoline(struct mm_struct *mm, unsign
 
 	*new_mapping = true;
 	return _install_special_mapping(mm, vaddr, PAGE_SIZE,
-				VM_READ|VM_EXEC|VM_MAYEXEC|VM_MAYREAD|VM_DONTCOPY|VM_IO,
+				VM_READ|VM_EXEC|VM_MAYEXEC|VM_MAYREAD|VM_IO,
 				&tramp_mapping);
 }
 
Signature · 1 line
2.54.0
merge bot Applied
#10 lore raw

[tip: perf/core] uprobes/x86: Allow to copy uprobe trampolines on fork

The following commit has been merged into the perf/core branch of tip:

The following commit has been merged into the perf/core branch of tip:

Commit-ID:     d9a48e77f6fe0c11d3cdfcbbcbf4a98ec402e55a
Gitweb:        https://git.kernel.org/tip/d9a48e77f6fe0c11d3cdfcbbcbf4a98ec402e55a
Author:        Jiri Olsa <[email protected]>
AuthorDate:    Fri, 03 Jul 2026 13:49:08 +02:00
Committer:     Peter Zijlstra <[email protected]>
CommitterDate: Fri, 03 Jul 2026 16:30:35 +02:00

uprobes/x86: Allow to copy uprobe trampolines on fork

When we do fork or clone without CLONE_VM the new process won't have uprobe trampoline vma objects and at the same time it will have optimized code calling that trampoline and crash.

Fixing this by allowing vma uprobe trampoline objects to be copied on fork to the new process.

Fixes ba2bfc97b462 ("uprobes/x86: Add support to optimize uprobes")
---
 arch/x86/kernel/uprobes.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
arch/x86/kernel/uprobes.c +1 -1
index 7f82056..ba7ca62 100644
@@ -701,7 +701,7 @@ static struct vm_area_struct *get_uprobe_trampoline(struct mm_struct *mm, unsign
 
 	*new_mapping = true;
 	return _install_special_mapping(mm, vaddr, PAGE_SIZE,
-				VM_READ|VM_EXEC|VM_MAYEXEC|VM_MAYREAD|VM_DONTCOPY|VM_IO,
+				VM_READ|VM_EXEC|VM_MAYEXEC|VM_MAYREAD|VM_IO,
 				&tramp_mapping);
 }
 
author reviewer
#11 lore raw

PATCH v6 5/13 uprobes/x86: Move optimized uprobe from nop5 to nop10

In reply to Jiri Olsa

Andrii reported an issue with optimized uprobes [1] that can clobber redzone area with call instruction storing return address on stack where user code may keep temporary data without adjusting rsp.

Fixing this by moving the optimized uprobes on top of 10-bytes nop instruction, so we can squeeze another instruction to escape the redzone area before doing the call, like:

lea -0x80(%rsp), %rsp
call tramp

Note the lea instruction is used to adjust the rsp register without changing the flags.

We use nop10 and following transformation to optimized instructions above and back as suggested by Peterz [2].

Optimize path (int3_update_optimize):

1) Initial state after set_swbp() installed the uprobe:
cc 2e 0f 1f 84 00 00 00 00 00

From offset 0 this is INT3 followed by the tail of the original 10-byte NOP.

After a previous unoptimization bytes 5..9 may still contain the old call instruction, which remains valid for threads already there.

2) Rewrite the LEA tail and call displacement:
cc [8d 64 24 80 e8 d0 d1 d2 d3]

From offset 0 this traps on the uprobe INT3. Bytes 1..9 are not executable entry points while byte 0 is trapped.

3) Publish the first LEA byte:

      [48] 8d 64 24 80 e8 d0 d1 d2 d3

     From offset 0 this is:
        lea -0x80(%rsp), %rsp
        call <uprobe-trampoline>

Unoptimize path (int3_update_unoptimize):

1) Initial optimized state:
48 8d 64 24 80 e8 d0 d1 d2 d3
Same as 3) above.

2) Trap new entries before restoring the NOP bytes:
[cc] 8d 64 24 80 e8 d0 d1 d2 d3

From offset 0 this traps. A thread that had already executed the LEA can still reach the intact CALL at offset 5.

3) Restore bytes 1..4 of the original NOP while keeping byte 0 trapped and byte 5 as CALL.
cc [2e 0f 1f 84] e8 d0 d1 d2 d3

From offset 0 this still traps. Offset 5 is still the CALL for any thread that was already past the first LEA byte.

4) Publish the first byte of the original NOP:
[66] 2e 0f 1f 84 e8 d0 d1 d2 d3

From offset 0 this is the restored 10-byte NOP; the CALL opcode and displacement are now only NOP operands. Offset 5 still decodes as CALL for a thread that was already there.

Tthere is only a single target uprobe-trampoline for the given nop10 instruction address, so the CALL instruction will not be changed across unoptimization/optimization cycles.
Therefore, any task that is preempted at the CALL instruction is guaranteed to observe that CALL and not anything else.

Note as explained in [2] we need to use following nop10:
PF1 PF2 ESC NOPL MOD SIB DISP32
NOP10: 0x66, 0x2e, 0x0f, 0x1f, 0x84, 0x00, 0x00, 0x00, 0x00, 0x00 -- cs nopw 0x00000000(%rax,%rax,1)

which means we need to allow 0x2e prefix which maps to INAT_PFX_CS attribute in is_prefix_bad function.

Also changing the uprobe syscall error when called out of uprobe trampoline to -EPROTO, so we are able to detect the fixed kernel.

The optimized uprobe performance stays the same:

        uprobe-nop     :    3.129 ± 0.013M/s
        uprobe-push    :    3.045 ± 0.006M/s
        uprobe-ret     :    1.095 ± 0.004M/s
  -->   uprobe-nop10   :    7.170 ± 0.020M/s
        uretprobe-nop  :    2.143 ± 0.021M/s
        uretprobe-push :    2.090 ± 0.000M/s
        uretprobe-ret  :    0.942 ± 0.000M/s
  -->   uretprobe-nop10:    3.381 ± 0.003M/s
        usdt-nop       :    3.245 ± 0.004M/s
  -->   usdt-nop10     :    7.256 ± 0.023M/s

[1] https://lore.kernel.org/bpf/[email protected]/
[2] https://lore.kernel.org/bpf/[email protected]/#t

Fixes ba2bfc97b462 ("uprobes/x86: Add support to optimize uprobes")
Assisted-by Codex:GPT-5.5
---
 arch/x86/kernel/uprobes.c | 292 ++++++++++++++++++++++++++++----------
 1 file changed, 216 insertions(+), 76 deletions(-)
arch/x86/kernel/uprobes.c +216 -76
index af5af7d67999..521a120a0c78 100644
@@ -276,15 +276,9 @@ static bool is_prefix_bad(struct insn *insn)
 	return false;
 }
 
-static int uprobe_init_insn(struct arch_uprobe *auprobe, struct insn *insn, bool x86_64)
+static int uprobe_init_insn(struct arch_uprobe *auprobe, struct insn *insn)
 {
-	enum insn_mode m = x86_64 ? INSN_MODE_64 : INSN_MODE_32;
 	u32 volatile *good_insns;
-	int ret;
-
-	ret = insn_decode(insn, auprobe->insn, sizeof(auprobe->insn), m);
-	if (ret < 0)
-		return -ENOEXEC;
 
 	if (is_prefix_bad(insn))
 		return -ENOTSUPP;
@@ -293,7 +287,7 @@ static int uprobe_init_insn(struct arch_uprobe *auprobe, struct insn *insn, bool
 	if (insn_masking_exception(insn))
 		return -ENOTSUPP;
 
-	if (x86_64)
+	if (insn->x86_64)
 		good_insns = good_insns_64;
 	else
 		good_insns = good_insns_32;
@@ -631,9 +625,29 @@ static struct vm_special_mapping tramp_mapping = {
 	.pages  = tramp_mapping_pages,
 };
 
+
+#define LEA_INSN_SIZE		5
+#define OPT_INSN_SIZE		(LEA_INSN_SIZE + CALL_INSN_SIZE)
+#define REDZONE_SIZE		0x80
+
+static const u8 lea_rsp[] = { 0x48, 0x8d, 0x64, 0x24, 0x80 };
+
+static bool is_opt_insns(const uprobe_opcode_t *insn)
+{
+	return !memcmp(insn, lea_rsp, LEA_INSN_SIZE) &&
+	       insn[LEA_INSN_SIZE] == CALL_INSN_OPCODE;
+}
+
+static bool is_swbp_opt_insns(uprobe_opcode_t *insn)
+{
+	return is_swbp_insn(&insn[0]) &&
+	       !memcmp(&insn[1], &lea_rsp[1], LEA_INSN_SIZE - 1) &&
+	       insn[LEA_INSN_SIZE] == CALL_INSN_OPCODE;
+}
+
 static bool is_reachable_by_call(unsigned long vtramp, unsigned long vaddr)
 {
-	long delta = (long)(vaddr + 5 - vtramp);
+	long delta = (long)(vaddr + OPT_INSN_SIZE - vtramp);
 
 	return delta >= INT_MIN && delta <= INT_MAX;
 }
@@ -646,7 +660,7 @@ static unsigned long find_nearest_trampoline(unsigned long vaddr)
 	};
 	unsigned long low_limit, high_limit;
 	unsigned long low_tramp, high_tramp;
-	unsigned long call_end = vaddr + 5;
+	unsigned long call_end = vaddr + OPT_INSN_SIZE;
 
 	if (check_add_overflow(call_end, INT_MIN, &low_limit))
 		low_limit = PAGE_SIZE;
@@ -754,7 +768,7 @@ SYSCALL_DEFINE0(uprobe)
 
 	/* Allow execution only from uprobe trampolines. */
 	if (!in_uprobe_trampoline(regs->ip))
-		return -ENXIO;
+		return -EPROTO;
 
 	err = copy_from_user(&args, (void __user *)regs->sp, sizeof(args));
 	if (err)
@@ -770,8 +784,8 @@ SYSCALL_DEFINE0(uprobe)
 	regs->ax  = args.ax;
 	regs->r11 = args.r11;
 	regs->cx  = args.cx;
-	regs->ip  = args.retaddr - 5;
-	regs->sp += sizeof(args);
+	regs->ip  = args.retaddr - OPT_INSN_SIZE;
+	regs->sp += sizeof(args) + REDZONE_SIZE;
 	regs->orig_ax = -1;
 
 	sp = regs->sp;
@@ -788,12 +802,12 @@ SYSCALL_DEFINE0(uprobe)
 	 */
 	if (regs->sp != sp) {
 		/* skip the trampoline call */
-		if (args.retaddr - 5 == regs->ip)
-			regs->ip += 5;
+		if (args.retaddr - OPT_INSN_SIZE == regs->ip)
+			regs->ip += OPT_INSN_SIZE;
 		return regs->ax;
 	}
 
-	regs->sp -= sizeof(args);
+	regs->sp -= sizeof(args) + REDZONE_SIZE;
 
 	/* for the case uprobe_consumer has changed ax/r11/cx */
 	args.ax  = regs->ax;
@@ -801,7 +815,7 @@ SYSCALL_DEFINE0(uprobe)
 	args.cx  = regs->cx;
 
 	/* keep return address unless we are instructed otherwise */
-	if (args.retaddr - 5 != regs->ip)
+	if (args.retaddr - OPT_INSN_SIZE != regs->ip)
 		args.retaddr = regs->ip;
 
 	if (shstk_push(args.retaddr) == -EFAULT)
@@ -835,7 +849,7 @@ asm (
 	"pop %rax\n"
 	"pop %r11\n"
 	"pop %rcx\n"
-	"ret\n"
+	"ret $" __stringify(REDZONE_SIZE) "\n"
 	"int3\n"
 	".balign " __stringify(PAGE_SIZE) "\n"
 	".popsection\n"
@@ -853,7 +867,8 @@ late_initcall(arch_uprobes_init);
 
 enum {
 	EXPECT_SWBP,
-	EXPECT_CALL,
+	EXPECT_OPTIMIZED,
+	EXPECT_SWBP_OPTIMIZED,
 };
 
 struct write_opcode_ctx {
@@ -861,30 +876,29 @@ struct write_opcode_ctx {
 	int expect;
 };
 
-static int is_call_insn(uprobe_opcode_t *insn)
-{
-	return *insn == CALL_INSN_OPCODE;
-}
-
 /*
- * Verification callback used by int3_update uprobe_write calls to make sure
- * the underlying instruction is as expected - either int3 or call.
+ * Verification callback used by uprobe_write calls to make sure the underlying
+ * instruction is in the expected stage of the INT3 update sequence.
  */
 static int verify_insn(struct page *page, unsigned long vaddr, uprobe_opcode_t *new_opcode,
 		       int nbytes, void *data)
 {
 	struct write_opcode_ctx *ctx = data;
-	uprobe_opcode_t old_opcode[5];
+	uprobe_opcode_t old_opcode[OPT_INSN_SIZE];
 
-	uprobe_copy_from_page(page, ctx->base, (uprobe_opcode_t *) &old_opcode, 5);
+	uprobe_copy_from_page(page, ctx->base, old_opcode, OPT_INSN_SIZE);
 
 	switch (ctx->expect) {
 	case EXPECT_SWBP:
 		if (is_swbp_insn(&old_opcode[0]))
 			return 1;
 		break;
-	case EXPECT_CALL:
-		if (is_call_insn(&old_opcode[0]))
+	case EXPECT_OPTIMIZED:
+		if (is_opt_insns(&old_opcode[0]))
+			return 1;
+		break;
+	case EXPECT_SWBP_OPTIMIZED:
+		if (is_swbp_opt_insns(&old_opcode[0]))
 			return 1;
 		break;
 	}
@@ -893,48 +907,122 @@ static int verify_insn(struct page *page, unsigned long vaddr, uprobe_opcode_t *
 }
 
 /*
- * Modify multi-byte instructions by using INT3 breakpoints on SMP.
+ * Modify the optimized instruction by using INT3 breakpoints on SMP.
  * We completely avoid using stop_machine() here, and achieve the
  * synchronization using INT3 breakpoints and SMP cross-calls.
  * (borrowed comment from smp_text_poke_batch_finish)
  *
- * The way it is done:
- *   - Add an INT3 trap to the address that will be patched
- *   - SMP sync all CPUs
- *   - Update all but the first byte of the patched range
- *   - SMP sync all CPUs
- *   - Replace the first byte (INT3) by the first byte of the replacing opcode
- *   - SMP sync all CPUs
+ * For optimization (int3_update_optimize):
+ *   1) Start with the uprobe INT3 trap already installed
+ *   2) Update everything but the first byte
+ *   3) Replace the first INT3 by the first byte of the LEA instruction
+ *
+ * For unoptimization (int3_update_unoptimize):
+ *   1) Start with the optimized uprobe lea/call instructions
+ *   2) Add an INT3 trap to the address that will be patched
+ *   3) Restore the NOP bytes before the call opcode
+ *   4) Replace the first INT3 by the first byte of the NOP instruction
+ *
+ * Note that unoptimization deliberately keeps the call opcode and displacement
+ * in bytes 5..9. Those bytes become operands of the restored 10-byte NOP.
+ *
+ * Since there is only a single target uprobe-trampoline for the given nop10
+ * instruction address, the CALL instruction will not be changed across
+ * unoptimization/optimization cycles.
+ * Therefore, any task that is preempted at the CALL instruction is guaranteed
+ * to observe that CALL and not anything else.
  */
-static int int3_update(struct arch_uprobe *auprobe, struct vm_area_struct *vma,
-		       unsigned long vaddr, char *insn, bool optimize)
+static int int3_update_optimize(struct arch_uprobe *auprobe, struct vm_area_struct *vma,
+				unsigned long vaddr, uprobe_opcode_t *insn)
 {
-	uprobe_opcode_t int3 = UPROBE_SWBP_INSN;
 	struct write_opcode_ctx ctx = {
 		.base = vaddr,
 	};
 	int err;
 
 	/*
-	 * Write int3 trap.
+	 * 1) Initial state after set_swbp() installed the uprobe:
+	 *    cc 2e 0f 1f 84 00 00 00 00 00
 	 *
-	 * The swbp_optimize path comes with breakpoint already installed,
-	 * so we can skip this step for optimize == true.
+	 *    After a previous unoptimization bytes 5..9 may still contain the
+	 *    old call instruction, which remains valid for threads already there.
 	 */
-	if (!optimize) {
-		ctx.expect = EXPECT_CALL;
-		err = uprobe_write(auprobe, vma, vaddr, &int3, 1, verify_insn,
-				   true /* is_register */, false /* do_update_ref_ctr */,
-				   &ctx);
-		if (err)
-			return err;
-	}
+	smp_text_poke_sync_each_cpu();
+
+	/*
+	 * 2) Rewrite the LEA tail and call displacement:
+	 *    cc [8d 64 24 80 e8 d0 d1 d2 d3]
+	 */
+	ctx.expect = EXPECT_SWBP;
+	err = uprobe_write(auprobe, vma, vaddr + 1, insn + 1,
+			   OPT_INSN_SIZE - 1, verify_insn,
+			   true /* is_register */, false /* do_update_ref_ctr */,
+			   &ctx);
+	if (err)
+		return err;
+
+	smp_text_poke_sync_each_cpu();
+
+	/*
+	 * 3) Publish the first LEA byte:
+	 *    [48] 8d 64 24 80 e8 d0 d1 d2 d3
+	 *
+	 *    From offset 0 this is:
+	 *      lea -0x80(%rsp), %rsp
+	 *      call <uprobe-trampoline>
+	 */
+	ctx.expect = EXPECT_SWBP_OPTIMIZED;
+	err = uprobe_write(auprobe, vma, vaddr, insn, 1, verify_insn,
+			   true /* is_register */, false /* do_update_ref_ctr */,
+			   &ctx);
+	if (err)
+		goto error;
 
 	smp_text_poke_sync_each_cpu();
+	return 0;
 
-	/* Write all but the first byte of the patched range. */
+error:
+	/*
+	 * In all intermediate states byte 0 is INT3, so EXPECT_SWBP covers every
+	 * case. Restore NOP bytes 1..4, but keep the valid CALL at bytes 5..9
+	 * for a thread that had already executed the LEA before a previous
+	 * unoptimization.
+	 */
 	ctx.expect = EXPECT_SWBP;
-	err = uprobe_write(auprobe, vma, vaddr + 1, insn + 1, 4, verify_insn,
+	uprobe_write(auprobe, vma, vaddr + 1, auprobe->insn + 1,
+		     LEA_INSN_SIZE - 1, verify_insn, true, false, &ctx);
+	smp_text_poke_sync_each_cpu();
+	return err;
+}
+
+static int int3_update_unoptimize(struct arch_uprobe *auprobe, struct vm_area_struct *vma,
+				  unsigned long vaddr, uprobe_opcode_t *insn)
+{
+	uprobe_opcode_t int3 = UPROBE_SWBP_INSN;
+	struct write_opcode_ctx ctx = {
+		.base = vaddr,
+		.expect = EXPECT_OPTIMIZED,
+	};
+	int err;
+
+	/*
+	 * Note the first two uprobe_write calls use is_register=true, because they
+	 * are intermediate patching states while the probe is still active, so
+	 * we force the exclusive anonymous page for the update.
+	 * Also we use do_update_ref_ctr=false because refctr was already updated by
+	 * the initial int3 install.
+	 *
+	 * The last uprobe_write to nop10 instruction is called with is_register=false
+	 * and do_update_ref_ctr=true to trigger the refctr update and to instruct
+	 * uprobe_write to zap the anonymous page if it now matches the file page.
+	 *
+	 * 1) Initial optimized state:
+	 *    48 8d 64 24 80 e8 d0 d1 d2 d3
+	 *
+	 * 2) Trap new entries before restoring the NOP bytes:
+	 *    [cc] 8d 64 24 80 e8 d0 d1 d2 d3
+	 */
+	err = uprobe_write(auprobe, vma, vaddr, &int3, 1, verify_insn,
 			   true /* is_register */, false /* do_update_ref_ctr */,
 			   &ctx);
 	if (err)
@@ -943,13 +1031,31 @@ static int int3_update(struct arch_uprobe *auprobe, struct vm_area_struct *vma,
 	smp_text_poke_sync_each_cpu();
 
 	/*
-	 * Write first byte.
+	 * 3) Restore bytes 1..4 of the original NOP while keeping byte 0 trapped
+	 *    and byte 5 as CALL:
+	 *    cc [2e 0f 1f 84] e8 d0 d1 d2 d3
+	 */
+	ctx.expect = EXPECT_SWBP_OPTIMIZED;
+	err = uprobe_write(auprobe, vma, vaddr + 1, insn + 1,
+			   LEA_INSN_SIZE - 1, verify_insn,
+			   true /* is_register */, false /* do_update_ref_ctr */,
+			   &ctx);
+	if (err)
+		return err;
+
+	smp_text_poke_sync_each_cpu();
+
+	/*
+	 * 4) Publish the first byte of the original NOP:
+	 *    [66] 2e 0f 1f 84 e8 d0 d1 d2 d3
 	 *
-	 * The swbp_unoptimize needs to finish uprobe removal together
-	 * with ref_ctr update, using uprobe_write with proper flags.
+	 * From offset 0 this is the restored 10-byte NOP; the CALL opcode and
+	 * displacement are now only NOP operands.  Offset 5 still decodes as
+	 * CALL for a thread that was already there.
 	 */
+	ctx.expect = EXPECT_SWBP;
 	err = uprobe_write(auprobe, vma, vaddr, insn, 1, verify_insn,
-			   optimize /* is_register */, !optimize /* do_update_ref_ctr */,
+			   false /* is_register */, true /* do_update_ref_ctr */,
 			   &ctx);
 	if (err)
 		return err;
@@ -961,17 +1067,25 @@ static int int3_update(struct arch_uprobe *auprobe, struct vm_area_struct *vma,
 static int swbp_optimize(struct arch_uprobe *auprobe, struct vm_area_struct *vma,
 			 unsigned long vaddr, unsigned long tramp)
 {
-	u8 call[5];
+	u8 insn[OPT_INSN_SIZE], *call = &insn[LEA_INSN_SIZE];
 
-	__text_gen_insn(call, CALL_INSN_OPCODE, (const void *) vaddr,
+	/*
+	 * We have nop10 instruction (with first byte overwritten to int3),
+	 * changing it to:
+	 *   lea -0x80(%rsp), %rsp
+	 *   call tramp
+	 */
+	memcpy(insn, lea_rsp, LEA_INSN_SIZE);
+	__text_gen_insn(call, CALL_INSN_OPCODE,
+			(const void *) (vaddr + LEA_INSN_SIZE),
 			(const void *) tramp, CALL_INSN_SIZE);
-	return int3_update(auprobe, vma, vaddr, call, true /* optimize */);
+	return int3_update_optimize(auprobe, vma, vaddr, insn);
 }
 
 static int swbp_unoptimize(struct arch_uprobe *auprobe, struct vm_area_struct *vma,
 			   unsigned long vaddr)
 {
-	return int3_update(auprobe, vma, vaddr, auprobe->insn, false /* optimize */);
+	return int3_update_unoptimize(auprobe, vma, vaddr, auprobe->insn);
 }
 
 static int copy_from_vaddr(struct mm_struct *mm, unsigned long vaddr, void *dst, int len)
@@ -993,19 +1107,19 @@ static bool __is_optimized(struct mm_struct *mm, uprobe_opcode_t *insn, unsigned
 	struct __packed __arch_relative_insn {
 		u8 op;
 		s32 raddr;
-	} *call = (struct __arch_relative_insn *) insn;
+	} *call = (struct __arch_relative_insn *)(insn + LEA_INSN_SIZE);
 
-	if (!is_call_insn(insn))
+	if (!is_opt_insns(insn))
 		return false;
-	return __in_uprobe_trampoline(mm, vaddr + 5 + call->raddr);
+	return __in_uprobe_trampoline(mm, vaddr + OPT_INSN_SIZE + call->raddr);
 }
 
 static int is_optimized(struct mm_struct *mm, unsigned long vaddr)
 {
-	uprobe_opcode_t insn[5];
+	uprobe_opcode_t insn[OPT_INSN_SIZE];
 	int err;
 
-	err = copy_from_vaddr(mm, vaddr, &insn, 5);
+	err = copy_from_vaddr(mm, vaddr, &insn, OPT_INSN_SIZE);
 	if (err)
 		return err;
 	return __is_optimized(mm, (uprobe_opcode_t *)&insn, vaddr);
@@ -1077,7 +1191,7 @@ static int __arch_uprobe_optimize(struct arch_uprobe *auprobe, struct mm_struct
 void arch_uprobe_optimize(struct arch_uprobe *auprobe, unsigned long vaddr)
 {
 	struct mm_struct *mm = current->mm;
-	uprobe_opcode_t insn[5];
+	uprobe_opcode_t insn[OPT_INSN_SIZE];
 
 	if (!should_optimize(auprobe))
 		return;
@@ -1088,7 +1202,7 @@ void arch_uprobe_optimize(struct arch_uprobe *auprobe, unsigned long vaddr)
 	 * Check if some other thread already optimized the uprobe for us,
 	 * if it's the case just go away silently.
 	 */
-	if (copy_from_vaddr(mm, vaddr, &insn, 5))
+	if (copy_from_vaddr(mm, vaddr, &insn, OPT_INSN_SIZE))
 		goto unlock;
 	if (!is_swbp_insn((uprobe_opcode_t*) &insn))
 		goto unlock;
@@ -1104,16 +1218,32 @@ void arch_uprobe_optimize(struct arch_uprobe *auprobe, unsigned long vaddr)
 	mmap_write_unlock(mm);
 }
 
+static bool is_optimizable_nop10(struct insn *insn)
+{
+	static const u8 nop10_prefix[] = {
+		0x66, 0x2e, 0x0f, 0x1f, 0x84
+	};
+
+	/*
+	 * Restrict this to the 10-byte NOP form whose last 5 bytes are
+	 * SIB/displacement operands. Unoptimization keeps the call opcode and
+	 * displacement in those bytes, so other NOP encodings are not safe.
+	 */
+	return insn->length == OPT_INSN_SIZE &&
+	       insn_is_nop(insn) &&
+	       !memcmp(insn->kaddr, nop10_prefix, ARRAY_SIZE(nop10_prefix));
+}
+
 static bool can_optimize(struct insn *insn, unsigned long vaddr)
 {
-	if (!insn->x86_64 || insn->length != 5)
+	if (!insn->x86_64)
 		return false;
 
-	if (!insn_is_nop(insn))
+	if (!is_optimizable_nop10(insn))
 		return false;
 
 	/* We can't do cross page atomic writes yet. */
-	return PAGE_SIZE - (vaddr & ~PAGE_MASK) >= 5;
+	return PAGE_SIZE - (vaddr & ~PAGE_MASK) >= OPT_INSN_SIZE;
 }
 #else /* 32-bit: */
 /*
@@ -1485,16 +1615,26 @@ static int push_setup_xol_ops(struct arch_uprobe *auprobe, struct insn *insn)
  */
 int arch_uprobe_analyze_insn(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long addr)
 {
+	enum insn_mode m = is_64bit_mm(mm) ? INSN_MODE_64 : INSN_MODE_32;
 	u8 fix_ip_or_call = UPROBE_FIX_IP;
 	struct insn insn;
 	int ret;
 
-	ret = uprobe_init_insn(auprobe, &insn, is_64bit_mm(mm));
-	if (ret)
-		return ret;
+	ret = insn_decode(&insn, auprobe->insn, sizeof(auprobe->insn), m);
+	if (ret < 0)
+		return -ENOEXEC;
 
-	if (can_optimize(&insn, addr))
+	/*
+	 * No need to check instruction in uprobe_init_insn in case we
+	 * are on top of optimizable nop10.
+	 */
+	if (can_optimize(&insn, addr)) {
 		set_bit(ARCH_UPROBE_FLAG_CAN_OPTIMIZE, &auprobe->flags);
+	} else {
+		ret = uprobe_init_insn(auprobe, &insn);
+		if (ret)
+			return ret;
+	}
 
 	ret = branch_setup_xol_ops(auprobe, &insn);
 	if (ret != -ENOSYS)
Signature · 1 line
2.54.0
merge bot Applied
#12 lore raw

[tip: perf/core] uprobes/x86: Move optimized uprobe from nop5 to nop10

The following commit has been merged into the perf/core branch of tip:

The following commit has been merged into the perf/core branch of tip:

Commit-ID:     554ba38456dad8053a1a80afe6ae6da9eff745cc
Gitweb:        https://git.kernel.org/tip/554ba38456dad8053a1a80afe6ae6da9eff745cc
Author:        Jiri Olsa <[email protected]>
AuthorDate:    Fri, 03 Jul 2026 13:49:09 +02:00
Committer:     Peter Zijlstra <[email protected]>
CommitterDate: Fri, 03 Jul 2026 16:30:36 +02:00

uprobes/x86: Move optimized uprobe from nop5 to nop10

Andrii reported an issue with optimized uprobes [1] that can clobber redzone area with call instruction storing return address on stack where user code may keep temporary data without adjusting rsp.

Fixing this by moving the optimized uprobes on top of 10-bytes nop instruction, so we can squeeze another instruction to escape the redzone area before doing the call, like:

lea -0x80(%rsp), %rsp
call tramp

Note the lea instruction is used to adjust the rsp register without changing the flags.

We use nop10 and following transformation to optimized instructions above and back as suggested by Peterz [2].

Optimize path (int3_update_optimize):

1) Initial state after set_swbp() installed the uprobe:
cc 2e 0f 1f 84 00 00 00 00 00

From offset 0 this is INT3 followed by the tail of the original 10-byte NOP.

After a previous unoptimization bytes 5..9 may still contain the old call instruction, which remains valid for threads already there.

2) Rewrite the LEA tail and call displacement:
cc [8d 64 24 80 e8 d0 d1 d2 d3]

From offset 0 this traps on the uprobe INT3. Bytes 1..9 are not executable entry points while byte 0 is trapped.

3) Publish the first LEA byte:

      [48] 8d 64 24 80 e8 d0 d1 d2 d3

     From offset 0 this is:
        lea -0x80(%rsp), %rsp
        call <uprobe-trampoline>

Unoptimize path (int3_update_unoptimize):

1) Initial optimized state:
48 8d 64 24 80 e8 d0 d1 d2 d3
Same as 3) above.

2) Trap new entries before restoring the NOP bytes:
[cc] 8d 64 24 80 e8 d0 d1 d2 d3

From offset 0 this traps. A thread that had already executed the LEA can still reach the intact CALL at offset 5.

3) Restore bytes 1..4 of the original NOP while keeping byte 0 trapped and byte 5 as CALL.
cc [2e 0f 1f 84] e8 d0 d1 d2 d3

From offset 0 this still traps. Offset 5 is still the CALL for any thread that was already past the first LEA byte.

4) Publish the first byte of the original NOP:
[66] 2e 0f 1f 84 e8 d0 d1 d2 d3

From offset 0 this is the restored 10-byte NOP; the CALL opcode and displacement are now only NOP operands. Offset 5 still decodes as CALL for a thread that was already there.

Tthere is only a single target uprobe-trampoline for the given nop10 instruction address, so the CALL instruction will not be changed across unoptimization/optimization cycles.
Therefore, any task that is preempted at the CALL instruction is guaranteed to observe that CALL and not anything else.

Note as explained in [2] we need to use following nop10:
PF1 PF2 ESC NOPL MOD SIB DISP32
NOP10: 0x66, 0x2e, 0x0f, 0x1f, 0x84, 0x00, 0x00, 0x00, 0x00, 0x00 -- cs nopw 0x00000000(%rax,%rax,1)

which means we need to allow 0x2e prefix which maps to INAT_PFX_CS attribute in is_prefix_bad function.

Also changing the uprobe syscall error when called out of uprobe trampoline to -EPROTO, so we are able to detect the fixed kernel.

The optimized uprobe performance stays the same:

        uprobe-nop     :    3.129 ± 0.013M/s
        uprobe-push    :    3.045 ± 0.006M/s
        uprobe-ret     :    1.095 ± 0.004M/s
  -->   uprobe-nop10   :    7.170 ± 0.020M/s
        uretprobe-nop  :    2.143 ± 0.021M/s
        uretprobe-push :    2.090 ± 0.000M/s
        uretprobe-ret  :    0.942 ± 0.000M/s
  -->   uretprobe-nop10:    3.381 ± 0.003M/s
        usdt-nop       :    3.245 ± 0.004M/s
  -->   usdt-nop10     :    7.256 ± 0.023M/s

[1] https://lore.kernel.org/bpf/[email protected]/
[2] https://lore.kernel.org/bpf/[email protected]/#t

---
 arch/x86/kernel/uprobes.c | 292 +++++++++++++++++++++++++++----------
 1 file changed, 216 insertions(+), 76 deletions(-)
arch/x86/kernel/uprobes.c +216 -76
index ba7ca62..65a2de8 100644
@@ -276,15 +276,9 @@ static bool is_prefix_bad(struct insn *insn)
 	return false;
 }
 
-static int uprobe_init_insn(struct arch_uprobe *auprobe, struct insn *insn, bool x86_64)
+static int uprobe_init_insn(struct arch_uprobe *auprobe, struct insn *insn)
 {
-	enum insn_mode m = x86_64 ? INSN_MODE_64 : INSN_MODE_32;
 	u32 volatile *good_insns;
-	int ret;
-
-	ret = insn_decode(insn, auprobe->insn, sizeof(auprobe->insn), m);
-	if (ret < 0)
-		return -ENOEXEC;
 
 	if (is_prefix_bad(insn))
 		return -ENOTSUPP;
@@ -293,7 +287,7 @@ static int uprobe_init_insn(struct arch_uprobe *auprobe, struct insn *insn, bool
 	if (insn_masking_exception(insn))
 		return -ENOTSUPP;
 
-	if (x86_64)
+	if (insn->x86_64)
 		good_insns = good_insns_64;
 	else
 		good_insns = good_insns_32;
@@ -631,9 +625,29 @@ static struct vm_special_mapping tramp_mapping = {
 	.pages  = tramp_mapping_pages,
 };
 
+
+#define LEA_INSN_SIZE		5
+#define OPT_INSN_SIZE		(LEA_INSN_SIZE + CALL_INSN_SIZE)
+#define REDZONE_SIZE		0x80
+
+static const u8 lea_rsp[] = { 0x48, 0x8d, 0x64, 0x24, 0x80 };
+
+static bool is_opt_insns(const uprobe_opcode_t *insn)
+{
+	return !memcmp(insn, lea_rsp, LEA_INSN_SIZE) &&
+	       insn[LEA_INSN_SIZE] == CALL_INSN_OPCODE;
+}
+
+static bool is_swbp_opt_insns(uprobe_opcode_t *insn)
+{
+	return is_swbp_insn(&insn[0]) &&
+	       !memcmp(&insn[1], &lea_rsp[1], LEA_INSN_SIZE - 1) &&
+	       insn[LEA_INSN_SIZE] == CALL_INSN_OPCODE;
+}
+
 static bool is_reachable_by_call(unsigned long vtramp, unsigned long vaddr)
 {
-	long delta = (long)(vaddr + 5 - vtramp);
+	long delta = (long)(vaddr + OPT_INSN_SIZE - vtramp);
 
 	return delta >= INT_MIN && delta <= INT_MAX;
 }
@@ -646,7 +660,7 @@ static unsigned long find_nearest_trampoline(unsigned long vaddr)
 	};
 	unsigned long low_limit, high_limit;
 	unsigned long low_tramp, high_tramp;
-	unsigned long call_end = vaddr + 5;
+	unsigned long call_end = vaddr + OPT_INSN_SIZE;
 
 	if (check_add_overflow(call_end, INT_MIN, &low_limit))
 		low_limit = PAGE_SIZE;
@@ -754,7 +768,7 @@ SYSCALL_DEFINE0(uprobe)
 
 	/* Allow execution only from uprobe trampolines. */
 	if (!in_uprobe_trampoline(regs->ip))
-		return -ENXIO;
+		return -EPROTO;
 
 	err = copy_from_user(&args, (void __user *)regs->sp, sizeof(args));
 	if (err)
@@ -770,8 +784,8 @@ SYSCALL_DEFINE0(uprobe)
 	regs->ax  = args.ax;
 	regs->r11 = args.r11;
 	regs->cx  = args.cx;
-	regs->ip  = args.retaddr - 5;
-	regs->sp += sizeof(args);
+	regs->ip  = args.retaddr - OPT_INSN_SIZE;
+	regs->sp += sizeof(args) + REDZONE_SIZE;
 	regs->orig_ax = -1;
 
 	sp = regs->sp;
@@ -788,12 +802,12 @@ SYSCALL_DEFINE0(uprobe)
 	 */
 	if (regs->sp != sp) {
 		/* skip the trampoline call */
-		if (args.retaddr - 5 == regs->ip)
-			regs->ip += 5;
+		if (args.retaddr - OPT_INSN_SIZE == regs->ip)
+			regs->ip += OPT_INSN_SIZE;
 		return regs->ax;
 	}
 
-	regs->sp -= sizeof(args);
+	regs->sp -= sizeof(args) + REDZONE_SIZE;
 
 	/* for the case uprobe_consumer has changed ax/r11/cx */
 	args.ax  = regs->ax;
@@ -801,7 +815,7 @@ SYSCALL_DEFINE0(uprobe)
 	args.cx  = regs->cx;
 
 	/* keep return address unless we are instructed otherwise */
-	if (args.retaddr - 5 != regs->ip)
+	if (args.retaddr - OPT_INSN_SIZE != regs->ip)
 		args.retaddr = regs->ip;
 
 	if (shstk_push(args.retaddr) == -EFAULT)
@@ -835,7 +849,7 @@ asm (
 	"pop %rax\n"
 	"pop %r11\n"
 	"pop %rcx\n"
-	"ret\n"
+	"ret $" __stringify(REDZONE_SIZE) "\n"
 	"int3\n"
 	".balign " __stringify(PAGE_SIZE) "\n"
 	".popsection\n"
@@ -853,7 +867,8 @@ late_initcall(arch_uprobes_init);
 
 enum {
 	EXPECT_SWBP,
-	EXPECT_CALL,
+	EXPECT_OPTIMIZED,
+	EXPECT_SWBP_OPTIMIZED,
 };
 
 struct write_opcode_ctx {
@@ -861,30 +876,29 @@ struct write_opcode_ctx {
 	int expect;
 };
 
-static int is_call_insn(uprobe_opcode_t *insn)
-{
-	return *insn == CALL_INSN_OPCODE;
-}
-
 /*
- * Verification callback used by int3_update uprobe_write calls to make sure
- * the underlying instruction is as expected - either int3 or call.
+ * Verification callback used by uprobe_write calls to make sure the underlying
+ * instruction is in the expected stage of the INT3 update sequence.
  */
 static int verify_insn(struct page *page, unsigned long vaddr, uprobe_opcode_t *new_opcode,
 		       int nbytes, void *data)
 {
 	struct write_opcode_ctx *ctx = data;
-	uprobe_opcode_t old_opcode[5];
+	uprobe_opcode_t old_opcode[OPT_INSN_SIZE];
 
-	uprobe_copy_from_page(page, ctx->base, (uprobe_opcode_t *) &old_opcode, 5);
+	uprobe_copy_from_page(page, ctx->base, old_opcode, OPT_INSN_SIZE);
 
 	switch (ctx->expect) {
 	case EXPECT_SWBP:
 		if (is_swbp_insn(&old_opcode[0]))
 			return 1;
 		break;
-	case EXPECT_CALL:
-		if (is_call_insn(&old_opcode[0]))
+	case EXPECT_OPTIMIZED:
+		if (is_opt_insns(&old_opcode[0]))
+			return 1;
+		break;
+	case EXPECT_SWBP_OPTIMIZED:
+		if (is_swbp_opt_insns(&old_opcode[0]))
 			return 1;
 		break;
 	}
@@ -893,48 +907,122 @@ static int verify_insn(struct page *page, unsigned long vaddr, uprobe_opcode_t *
 }
 
 /*
- * Modify multi-byte instructions by using INT3 breakpoints on SMP.
+ * Modify the optimized instruction by using INT3 breakpoints on SMP.
  * We completely avoid using stop_machine() here, and achieve the
  * synchronization using INT3 breakpoints and SMP cross-calls.
  * (borrowed comment from smp_text_poke_batch_finish)
  *
- * The way it is done:
- *   - Add an INT3 trap to the address that will be patched
- *   - SMP sync all CPUs
- *   - Update all but the first byte of the patched range
- *   - SMP sync all CPUs
- *   - Replace the first byte (INT3) by the first byte of the replacing opcode
- *   - SMP sync all CPUs
+ * For optimization (int3_update_optimize):
+ *   1) Start with the uprobe INT3 trap already installed
+ *   2) Update everything but the first byte
+ *   3) Replace the first INT3 by the first byte of the LEA instruction
+ *
+ * For unoptimization (int3_update_unoptimize):
+ *   1) Start with the optimized uprobe lea/call instructions
+ *   2) Add an INT3 trap to the address that will be patched
+ *   3) Restore the NOP bytes before the call opcode
+ *   4) Replace the first INT3 by the first byte of the NOP instruction
+ *
+ * Note that unoptimization deliberately keeps the call opcode and displacement
+ * in bytes 5..9. Those bytes become operands of the restored 10-byte NOP.
+ *
+ * Since there is only a single target uprobe-trampoline for the given nop10
+ * instruction address, the CALL instruction will not be changed across
+ * unoptimization/optimization cycles.
+ * Therefore, any task that is preempted at the CALL instruction is guaranteed
+ * to observe that CALL and not anything else.
  */
-static int int3_update(struct arch_uprobe *auprobe, struct vm_area_struct *vma,
-		       unsigned long vaddr, char *insn, bool optimize)
+static int int3_update_optimize(struct arch_uprobe *auprobe, struct vm_area_struct *vma,
+				unsigned long vaddr, uprobe_opcode_t *insn)
 {
-	uprobe_opcode_t int3 = UPROBE_SWBP_INSN;
 	struct write_opcode_ctx ctx = {
 		.base = vaddr,
 	};
 	int err;
 
 	/*
-	 * Write int3 trap.
+	 * 1) Initial state after set_swbp() installed the uprobe:
+	 *    cc 2e 0f 1f 84 00 00 00 00 00
 	 *
-	 * The swbp_optimize path comes with breakpoint already installed,
-	 * so we can skip this step for optimize == true.
+	 *    After a previous unoptimization bytes 5..9 may still contain the
+	 *    old call instruction, which remains valid for threads already there.
 	 */
-	if (!optimize) {
-		ctx.expect = EXPECT_CALL;
-		err = uprobe_write(auprobe, vma, vaddr, &int3, 1, verify_insn,
-				   true /* is_register */, false /* do_update_ref_ctr */,
-				   &ctx);
-		if (err)
-			return err;
-	}
+	smp_text_poke_sync_each_cpu();
+
+	/*
+	 * 2) Rewrite the LEA tail and call displacement:
+	 *    cc [8d 64 24 80 e8 d0 d1 d2 d3]
+	 */
+	ctx.expect = EXPECT_SWBP;
+	err = uprobe_write(auprobe, vma, vaddr + 1, insn + 1,
+			   OPT_INSN_SIZE - 1, verify_insn,
+			   true /* is_register */, false /* do_update_ref_ctr */,
+			   &ctx);
+	if (err)
+		return err;
+
+	smp_text_poke_sync_each_cpu();
+
+	/*
+	 * 3) Publish the first LEA byte:
+	 *    [48] 8d 64 24 80 e8 d0 d1 d2 d3
+	 *
+	 *    From offset 0 this is:
+	 *      lea -0x80(%rsp), %rsp
+	 *      call <uprobe-trampoline>
+	 */
+	ctx.expect = EXPECT_SWBP_OPTIMIZED;
+	err = uprobe_write(auprobe, vma, vaddr, insn, 1, verify_insn,
+			   true /* is_register */, false /* do_update_ref_ctr */,
+			   &ctx);
+	if (err)
+		goto error;
 
 	smp_text_poke_sync_each_cpu();
+	return 0;
 
-	/* Write all but the first byte of the patched range. */
+error:
+	/*
+	 * In all intermediate states byte 0 is INT3, so EXPECT_SWBP covers every
+	 * case. Restore NOP bytes 1..4, but keep the valid CALL at bytes 5..9
+	 * for a thread that had already executed the LEA before a previous
+	 * unoptimization.
+	 */
 	ctx.expect = EXPECT_SWBP;
-	err = uprobe_write(auprobe, vma, vaddr + 1, insn + 1, 4, verify_insn,
+	uprobe_write(auprobe, vma, vaddr + 1, auprobe->insn + 1,
+		     LEA_INSN_SIZE - 1, verify_insn, true, false, &ctx);
+	smp_text_poke_sync_each_cpu();
+	return err;
+}
+
+static int int3_update_unoptimize(struct arch_uprobe *auprobe, struct vm_area_struct *vma,
+				  unsigned long vaddr, uprobe_opcode_t *insn)
+{
+	uprobe_opcode_t int3 = UPROBE_SWBP_INSN;
+	struct write_opcode_ctx ctx = {
+		.base = vaddr,
+		.expect = EXPECT_OPTIMIZED,
+	};
+	int err;
+
+	/*
+	 * Note the first two uprobe_write calls use is_register=true, because they
+	 * are intermediate patching states while the probe is still active, so
+	 * we force the exclusive anonymous page for the update.
+	 * Also we use do_update_ref_ctr=false because refctr was already updated by
+	 * the initial int3 install.
+	 *
+	 * The last uprobe_write to nop10 instruction is called with is_register=false
+	 * and do_update_ref_ctr=true to trigger the refctr update and to instruct
+	 * uprobe_write to zap the anonymous page if it now matches the file page.
+	 *
+	 * 1) Initial optimized state:
+	 *    48 8d 64 24 80 e8 d0 d1 d2 d3
+	 *
+	 * 2) Trap new entries before restoring the NOP bytes:
+	 *    [cc] 8d 64 24 80 e8 d0 d1 d2 d3
+	 */
+	err = uprobe_write(auprobe, vma, vaddr, &int3, 1, verify_insn,
 			   true /* is_register */, false /* do_update_ref_ctr */,
 			   &ctx);
 	if (err)
@@ -943,13 +1031,31 @@ static int int3_update(struct arch_uprobe *auprobe, struct vm_area_struct *vma,
 	smp_text_poke_sync_each_cpu();
 
 	/*
-	 * Write first byte.
+	 * 3) Restore bytes 1..4 of the original NOP while keeping byte 0 trapped
+	 *    and byte 5 as CALL:
+	 *    cc [2e 0f 1f 84] e8 d0 d1 d2 d3
+	 */
+	ctx.expect = EXPECT_SWBP_OPTIMIZED;
+	err = uprobe_write(auprobe, vma, vaddr + 1, insn + 1,
+			   LEA_INSN_SIZE - 1, verify_insn,
+			   true /* is_register */, false /* do_update_ref_ctr */,
+			   &ctx);
+	if (err)
+		return err;
+
+	smp_text_poke_sync_each_cpu();
+
+	/*
+	 * 4) Publish the first byte of the original NOP:
+	 *    [66] 2e 0f 1f 84 e8 d0 d1 d2 d3
 	 *
-	 * The swbp_unoptimize needs to finish uprobe removal together
-	 * with ref_ctr update, using uprobe_write with proper flags.
+	 * From offset 0 this is the restored 10-byte NOP; the CALL opcode and
+	 * displacement are now only NOP operands.  Offset 5 still decodes as
+	 * CALL for a thread that was already there.
 	 */
+	ctx.expect = EXPECT_SWBP;
 	err = uprobe_write(auprobe, vma, vaddr, insn, 1, verify_insn,
-			   optimize /* is_register */, !optimize /* do_update_ref_ctr */,
+			   false /* is_register */, true /* do_update_ref_ctr */,
 			   &ctx);
 	if (err)
 		return err;
@@ -961,17 +1067,25 @@ static int int3_update(struct arch_uprobe *auprobe, struct vm_area_struct *vma,
 static int swbp_optimize(struct arch_uprobe *auprobe, struct vm_area_struct *vma,
 			 unsigned long vaddr, unsigned long tramp)
 {
-	u8 call[5];
+	u8 insn[OPT_INSN_SIZE], *call = &insn[LEA_INSN_SIZE];
 
-	__text_gen_insn(call, CALL_INSN_OPCODE, (const void *) vaddr,
+	/*
+	 * We have nop10 instruction (with first byte overwritten to int3),
+	 * changing it to:
+	 *   lea -0x80(%rsp), %rsp
+	 *   call tramp
+	 */
+	memcpy(insn, lea_rsp, LEA_INSN_SIZE);
+	__text_gen_insn(call, CALL_INSN_OPCODE,
+			(const void *) (vaddr + LEA_INSN_SIZE),
 			(const void *) tramp, CALL_INSN_SIZE);
-	return int3_update(auprobe, vma, vaddr, call, true /* optimize */);
+	return int3_update_optimize(auprobe, vma, vaddr, insn);
 }
 
 static int swbp_unoptimize(struct arch_uprobe *auprobe, struct vm_area_struct *vma,
 			   unsigned long vaddr)
 {
-	return int3_update(auprobe, vma, vaddr, auprobe->insn, false /* optimize */);
+	return int3_update_unoptimize(auprobe, vma, vaddr, auprobe->insn);
 }
 
 static int copy_from_vaddr(struct mm_struct *mm, unsigned long vaddr, void *dst, int len)
@@ -993,19 +1107,19 @@ static bool __is_optimized(struct mm_struct *mm, uprobe_opcode_t *insn, unsigned
 	struct __packed __arch_relative_insn {
 		u8 op;
 		s32 raddr;
-	} *call = (struct __arch_relative_insn *) insn;
+	} *call = (struct __arch_relative_insn *)(insn + LEA_INSN_SIZE);
 
-	if (!is_call_insn(insn))
+	if (!is_opt_insns(insn))
 		return false;
-	return __in_uprobe_trampoline(mm, vaddr + 5 + call->raddr);
+	return __in_uprobe_trampoline(mm, vaddr + OPT_INSN_SIZE + call->raddr);
 }
 
 static int is_optimized(struct mm_struct *mm, unsigned long vaddr)
 {
-	uprobe_opcode_t insn[5];
+	uprobe_opcode_t insn[OPT_INSN_SIZE];
 	int err;
 
-	err = copy_from_vaddr(mm, vaddr, &insn, 5);
+	err = copy_from_vaddr(mm, vaddr, &insn, OPT_INSN_SIZE);
 	if (err)
 		return err;
 	return __is_optimized(mm, (uprobe_opcode_t *)&insn, vaddr);
@@ -1077,7 +1191,7 @@ static int __arch_uprobe_optimize(struct arch_uprobe *auprobe, struct mm_struct 
 void arch_uprobe_optimize(struct arch_uprobe *auprobe, unsigned long vaddr)
 {
 	struct mm_struct *mm = current->mm;
-	uprobe_opcode_t insn[5];
+	uprobe_opcode_t insn[OPT_INSN_SIZE];
 
 	if (!should_optimize(auprobe))
 		return;
@@ -1088,7 +1202,7 @@ void arch_uprobe_optimize(struct arch_uprobe *auprobe, unsigned long vaddr)
 	 * Check if some other thread already optimized the uprobe for us,
 	 * if it's the case just go away silently.
 	 */
-	if (copy_from_vaddr(mm, vaddr, &insn, 5))
+	if (copy_from_vaddr(mm, vaddr, &insn, OPT_INSN_SIZE))
 		goto unlock;
 	if (!is_swbp_insn((uprobe_opcode_t*) &insn))
 		goto unlock;
@@ -1104,16 +1218,32 @@ unlock:
 	mmap_write_unlock(mm);
 }
 
+static bool is_optimizable_nop10(struct insn *insn)
+{
+	static const u8 nop10_prefix[] = {
+		0x66, 0x2e, 0x0f, 0x1f, 0x84
+	};
+
+	/*
+	 * Restrict this to the 10-byte NOP form whose last 5 bytes are
+	 * SIB/displacement operands. Unoptimization keeps the call opcode and
+	 * displacement in those bytes, so other NOP encodings are not safe.
+	 */
+	return insn->length == OPT_INSN_SIZE &&
+	       insn_is_nop(insn) &&
+	       !memcmp(insn->kaddr, nop10_prefix, ARRAY_SIZE(nop10_prefix));
+}
+
 static bool can_optimize(struct insn *insn, unsigned long vaddr)
 {
-	if (!insn->x86_64 || insn->length != 5)
+	if (!insn->x86_64)
 		return false;
 
-	if (!insn_is_nop(insn))
+	if (!is_optimizable_nop10(insn))
 		return false;
 
 	/* We can't do cross page atomic writes yet. */
-	return PAGE_SIZE - (vaddr & ~PAGE_MASK) >= 5;
+	return PAGE_SIZE - (vaddr & ~PAGE_MASK) >= OPT_INSN_SIZE;
 }
 #else /* 32-bit: */
 /*
@@ -1495,16 +1625,26 @@ static int push_setup_xol_ops(struct arch_uprobe *auprobe, struct insn *insn)
  */
 int arch_uprobe_analyze_insn(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long addr)
 {
+	enum insn_mode m = is_64bit_mm(mm) ? INSN_MODE_64 : INSN_MODE_32;
 	u8 fix_ip_or_call = UPROBE_FIX_IP;
 	struct insn insn;
 	int ret;
 
-	ret = uprobe_init_insn(auprobe, &insn, is_64bit_mm(mm));
-	if (ret)
-		return ret;
+	ret = insn_decode(&insn, auprobe->insn, sizeof(auprobe->insn), m);
+	if (ret < 0)
+		return -ENOEXEC;
 
-	if (can_optimize(&insn, addr))
+	/*
+	 * No need to check instruction in uprobe_init_insn in case we
+	 * are on top of optimizable nop10.
+	 */
+	if (can_optimize(&insn, addr)) {
 		set_bit(ARCH_UPROBE_FLAG_CAN_OPTIMIZE, &auprobe->flags);
+	} else {
+		ret = uprobe_init_insn(auprobe, &insn);
+		if (ret)
+			return ret;
+	}
 
 	ret = branch_setup_xol_ops(auprobe, &insn);
 	if (ret != -ENOSYS)
author reviewer
#13 lore raw

PATCH v6 6/13 libbpf: Change has_nop_combo to work on top of nop10

In reply to Jiri Olsa

We now expect nop combo with 10 bytes nop instead of 5 bytes nop, fixing has_nop_combo to reflect that.

Fixes 41a5c7df4466 ("libbpf: Add support to detect nop,nop5 instructions combo for usdt probe")
---
 tools/lib/bpf/usdt.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)
tools/lib/bpf/usdt.c +8 -8
index db9432adb967..2e56e3ab5b6c 100644
@@ -305,7 +305,7 @@ struct usdt_manager *usdt_manager_new(struct bpf_object *obj)
 
 	/*
 	 * Detect kernel support for uprobe() syscall, it's presence means we can
-	 * take advantage of faster nop5 uprobe handling.
+	 * take advantage of faster nop10 uprobe handling.
 	 * Added in: 56101b69c919 ("uprobes/x86: Add uprobe syscall to speed up uprobe")
 	 */
 	man->has_uprobe_syscall = kernel_supports(obj, FEAT_UPROBE_SYSCALL);
@@ -605,14 +605,14 @@ static int parse_usdt_spec(struct usdt_spec *spec, const struct usdt_note *note,
 #if defined(__x86_64__)
 static bool has_nop_combo(int fd, long off)
 {
-	unsigned char nop_combo[6] = {
-		0x90, 0x0f, 0x1f, 0x44, 0x00, 0x00 /* nop,nop5 */
+	unsigned char nop_combo[11] = {
+		0x90, 0x66, 0x2e, 0x0f, 0x1f, 0x84, 0x00, 0x00, 0x00, 0x00, 0x00,
 	};
-	unsigned char buf[6];
+	unsigned char buf[11];
 
-	if (pread(fd, buf, 6, off) != 6)
+	if (pread(fd, buf, 11, off) != 11)
 		return false;
-	return memcmp(buf, nop_combo, 6) == 0;
+	return memcmp(buf, nop_combo, 11) == 0;
 }
 #else
 static bool has_nop_combo(int fd, long off)
@@ -825,8 +825,8 @@ static int collect_usdt_targets(struct usdt_manager *man, struct elf_fd *elf_fd,
 		memset(target, 0, sizeof(*target));
 
 		/*
-		 * We have uprobe syscall and usdt with nop,nop5 instructions combo,
-		 * so we can place the uprobe directly on nop5 (+1) and get this probe
+		 * We have uprobe syscall and usdt with nop,nop10 instructions combo,
+		 * so we can place the uprobe directly on nop10 (+1) and get this probe
 		 * optimized.
 		 */
 		if (man->has_uprobe_syscall && has_nop_combo(elf_fd->fd, usdt_rel_ip)) {
Signature · 1 line
2.54.0
#14 lore raw

Re: [PATCHv6 06/13] libbpf: Change has_nop_combo to work on top of nop10

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider: - [Medium] Dropping support for the `nop5` combo in `has_nop_combo()` breaks the BPF USDT selftests. --

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [Medium] Dropping support for the nop5 combo in has_nop_combo() breaks the BPF USDT selftests. --

commit dc8c1772a19cbe96786096f839e442eb211041bc
Author: Jiri Olsa <[email protected]>

libbpf: Change has_nop_combo to work on top of nop10

This patch modifies the USDT has_nop_combo() function to exclusively check for an 11-byte nop,nop10 sequence, replacing the previous 6-byte nop,nop5 check. This aligns the detection logic with newer kernel support for faster uprobe handling using nop10.

Quoted 4 lines
tools/lib/bpf/usdt.c +0 -0
index 57fb82bb81b58..d2ecd3daab961 100644

[ ... ]

Quoted 8 lines
tools/lib/bpf/usdt.c +2 -2
@@ -604,14 +604,14 @@ static int parse_usdt_spec(struct usdt_spec *spec, const struct usdt_note *note,
 #if defined(__x86_64__)
 static bool has_nop_combo(int fd, long off)
 {
-	unsigned char nop_combo[6] = {
-		0x90, 0x0f, 0x1f, 0x44, 0x00, 0x00 /* nop,nop5 */
+	unsigned char nop_combo[11] = {
+		0x90, 0x66, 0x2e, 0x0f, 0x1f, 0x84, 0x00, 0x00, 0x00, 0x00, 0x00,

tools/lib/bpf/usdt.c static int parse_usdt_spec(struct usdt_spec *spec, const struct usdt_note *note, · line 615

Quoted 10 lines
tools/lib/bpf/usdt.c +3 -3
 	};
-	unsigned char buf[6];
+	unsigned char buf[11];
 
-	if (pread(fd, buf, 6, off) != 6)
+	if (pread(fd, buf, 11, off) != 11)
 		return false;
-	return memcmp(buf, nop_combo, 6) == 0;
+	return memcmp(buf, nop_combo, 11) == 0;
 }

[Severity: Medium]
Will dropping support for the nop5 combo here break the BPF USDT selftests?

The selftest in tools/testing/selftests/bpf/prog_tests/usdt.c still generates and expects the nop,nop5 combination for usdt_2. Because this function now returns false for nop5, collect_usdt_targets() skips the usdt_abs_ip++ optimization.

This causes the uprobe to be placed directly at addr_2, overwriting the nop with an int3 (0xcc) breakpoint, which makes the test assertion fail:

tools/testing/selftests/bpf/prog_tests/usdt.c:subtest_optimized_attach() {
    ...
    /* usdt_2 USDT probe has nop,nop5 instructions combo */
    addr_2 = find_instr(usdt_2, nop1_nop5_combo, 6);
    if (!ASSERT_OK_PTR(addr_2, "usdt_2_find_nop1_nop5_combo"))
        return;
    ...
    /* nop stays on addr_2 address */
    ASSERT_EQ(*addr_2, 0x90, "nop");
}

Does the test suite also need to be updated to generate and expect nop,nop10?

Signature · 1 line
Sashiko AI review · https://sashiko.dev/#/patchset/[email protected]?part=1
merge bot Applied
#15 lore raw

[tip: perf/core] libbpf: Change has_nop_combo to work on top of nop10

In reply to Jiri Olsa
The following commit has been merged into the perf/core branch of tip:

The following commit has been merged into the perf/core branch of tip:

Commit-ID:     c005cd83b07a0ea1ffe3115f321ed3190fb3894b
Gitweb:        https://git.kernel.org/tip/c005cd83b07a0ea1ffe3115f321ed3190fb3894b
Author:        Jiri Olsa <[email protected]>
AuthorDate:    Fri, 03 Jul 2026 13:49:10 +02:00
Committer:     Peter Zijlstra <[email protected]>
CommitterDate: Fri, 03 Jul 2026 16:30:36 +02:00

libbpf: Change has_nop_combo to work on top of nop10

We now expect nop combo with 10 bytes nop instead of 5 bytes nop, fixing has_nop_combo to reflect that.

Fixes 41a5c7df4466 ("libbpf: Add support to detect nop,nop5 instructions combo for usdt probe")
Fixes af734a7ddb4e ("uprobes/x86: Move optimized uprobe from nop5 to nop10")
---
 tools/lib/bpf/usdt.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)
tools/lib/bpf/usdt.c +8 -8
index 57fb82b..d2ecd3d 100644
@@ -305,7 +305,7 @@ struct usdt_manager *usdt_manager_new(struct bpf_object *obj)
 
 	/*
 	 * Detect kernel support for uprobe() syscall, it's presence means we can
-	 * take advantage of faster nop5 uprobe handling.
+	 * take advantage of faster nop10 uprobe handling.
 	 * Added in: 56101b69c919 ("uprobes/x86: Add uprobe syscall to speed up uprobe")
 	 */
 	man->has_uprobe_syscall = kernel_supports(obj, FEAT_UPROBE_SYSCALL);
@@ -604,14 +604,14 @@ static int parse_usdt_spec(struct usdt_spec *spec, const struct usdt_note *note,
 #if defined(__x86_64__)
 static bool has_nop_combo(int fd, long off)
 {
-	unsigned char nop_combo[6] = {
-		0x90, 0x0f, 0x1f, 0x44, 0x00, 0x00 /* nop,nop5 */
+	unsigned char nop_combo[11] = {
+		0x90, 0x66, 0x2e, 0x0f, 0x1f, 0x84, 0x00, 0x00, 0x00, 0x00, 0x00,
 	};
-	unsigned char buf[6];
+	unsigned char buf[11];
 
-	if (pread(fd, buf, 6, off) != 6)
+	if (pread(fd, buf, 11, off) != 11)
 		return false;
-	return memcmp(buf, nop_combo, 6) == 0;
+	return memcmp(buf, nop_combo, 11) == 0;
 }
 #else
 static bool has_nop_combo(int fd, long off)
@@ -822,8 +822,8 @@ static int collect_usdt_targets(struct usdt_manager *man, struct elf_fd *elf_fd,
 		memset(target, 0, sizeof(*target));
 
 		/*
-		 * We have uprobe syscall and usdt with nop,nop5 instructions combo,
-		 * so we can place the uprobe directly on nop5 (+1) and get this probe
+		 * We have uprobe syscall and usdt with nop,nop10 instructions combo,
+		 * so we can place the uprobe directly on nop10 (+1) and get this probe
 		 * optimized.
 		 */
 		if (man->has_uprobe_syscall && has_nop_combo(elf_fd->fd, usdt_rel_ip)) {
#16 lore raw

Re: [tip: perf/core] libbpf: Change has_nop_combo to work on top of nop10

Quoted 9 lines · * tip-bot2 for Jiri Olsa <[email protected]> wrote:

The following commit has been merged into the perf/core branch of tip:

Commit-ID:     c005cd83b07a0ea1ffe3115f321ed3190fb3894b
Gitweb:        https://git.kernel.org/tip/c005cd83b07a0ea1ffe3115f321ed3190fb3894b
Author:        Jiri Olsa <[email protected]>
AuthorDate:    Fri, 03 Jul 2026 13:49:10 +02:00
Committer:     Peter Zijlstra <[email protected]>
CommitterDate: Fri, 03 Jul 2026 16:30:36 +02:00
Quoted 7 lines

libbpf: Change has_nop_combo to work on top of nop10

We now expect nop combo with 10 bytes nop instead of 5 bytes nop, fixing has_nop_combo to reflect that.

Fixes 41a5c7df4466 ("libbpf: Add support to detect nop,nop5 instructions combo for usdt probe")
Fixes af734a7ddb4e ("uprobes/x86: Move optimized uprobe from nop5 to nop10")

The second Fixes tag is bogus in this commit too - I fixed it to:

554ba38456da ("uprobes/x86: Move optimized uprobe from nop5 to nop10")

Thanks,

Ingo

merge bot Applied
#17 lore raw

[tip: perf/core] libbpf: Change has_nop_combo to work on top of nop10

In reply to Jiri Olsa
The following commit has been merged into the perf/core branch of tip:

The following commit has been merged into the perf/core branch of tip:

Commit-ID:     ee2862439e5c8763cee84e910706fdc5b97bc879
Gitweb:        https://git.kernel.org/tip/ee2862439e5c8763cee84e910706fdc5b97bc879
Author:        Jiri Olsa <[email protected]>
AuthorDate:    Fri, 03 Jul 2026 13:49:10 +02:00
Committer:     Ingo Molnar <[email protected]>
CommitterDate: Sat, 04 Jul 2026 10:54:59 +02:00

libbpf: Change has_nop_combo to work on top of nop10

We now expect nop combo with 10 bytes nop instead of 5 bytes nop, fixing has_nop_combo to reflect that.

Fixes 41a5c7df4466 ("libbpf: Add support to detect nop,nop5 instructions combo for usdt probe")
Fixes 554ba38456da ("uprobes/x86: Move optimized uprobe from nop5 to nop10")
---
 tools/lib/bpf/usdt.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)
tools/lib/bpf/usdt.c +8 -8
index 57fb82b..d2ecd3d 100644
@@ -305,7 +305,7 @@ struct usdt_manager *usdt_manager_new(struct bpf_object *obj)
 
 	/*
 	 * Detect kernel support for uprobe() syscall, it's presence means we can
-	 * take advantage of faster nop5 uprobe handling.
+	 * take advantage of faster nop10 uprobe handling.
 	 * Added in: 56101b69c919 ("uprobes/x86: Add uprobe syscall to speed up uprobe")
 	 */
 	man->has_uprobe_syscall = kernel_supports(obj, FEAT_UPROBE_SYSCALL);
@@ -604,14 +604,14 @@ static int parse_usdt_spec(struct usdt_spec *spec, const struct usdt_note *note,
 #if defined(__x86_64__)
 static bool has_nop_combo(int fd, long off)
 {
-	unsigned char nop_combo[6] = {
-		0x90, 0x0f, 0x1f, 0x44, 0x00, 0x00 /* nop,nop5 */
+	unsigned char nop_combo[11] = {
+		0x90, 0x66, 0x2e, 0x0f, 0x1f, 0x84, 0x00, 0x00, 0x00, 0x00, 0x00,
 	};
-	unsigned char buf[6];
+	unsigned char buf[11];
 
-	if (pread(fd, buf, 6, off) != 6)
+	if (pread(fd, buf, 11, off) != 11)
 		return false;
-	return memcmp(buf, nop_combo, 6) == 0;
+	return memcmp(buf, nop_combo, 11) == 0;
 }
 #else
 static bool has_nop_combo(int fd, long off)
@@ -822,8 +822,8 @@ static int collect_usdt_targets(struct usdt_manager *man, struct elf_fd *elf_fd,
 		memset(target, 0, sizeof(*target));
 
 		/*
-		 * We have uprobe syscall and usdt with nop,nop5 instructions combo,
-		 * so we can place the uprobe directly on nop5 (+1) and get this probe
+		 * We have uprobe syscall and usdt with nop,nop10 instructions combo,
+		 * so we can place the uprobe directly on nop10 (+1) and get this probe
 		 * optimized.
 		 */
 		if (man->has_uprobe_syscall && has_nop_combo(elf_fd->fd, usdt_rel_ip)) {
author reviewer
#18 lore raw

PATCH v6 7/13 libbpf: Detect uprobe syscall with new error

In reply to Jiri Olsa

In the previous optimized uprobe fix we changed the syscall error used for its detection from ENXIO to EPROTO.

Changing related probe_uprobe_syscall detection check.

Fixes 05738da0efa1 ("libbpf: Add uprobe syscall feature detection")
---
 tools/lib/bpf/features.c                                | 4 ++--
 tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)
tools/lib/bpf/features.c +2 -2
index b7e388f99d0b..e5641fa60163 100644
@@ -577,10 +577,10 @@ static int probe_ldimm64_full_range_off(int token_fd)
 static int probe_uprobe_syscall(int token_fd)
 {
 	/*
-	 * If kernel supports uprobe() syscall, it will return -ENXIO when called
+	 * If kernel supports uprobe() syscall, it will return -EPROTO when called
 	 * from the outside of a kernel-generated uprobe trampoline.
 	 */
-	return syscall(__NR_uprobe) < 0 && errno == ENXIO;
+	return syscall(__NR_uprobe) < 0 && errno == EPROTO;
 }
 #else
 static int probe_uprobe_syscall(int token_fd)
tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c +1 -1
index 955a37751b52..c944136252c6 100644
@@ -762,7 +762,7 @@ static void test_uprobe_error(void)
 	long err = syscall(__NR_uprobe);
 
 	ASSERT_EQ(err, -1, "error");
-	ASSERT_EQ(errno, ENXIO, "errno");
+	ASSERT_EQ(errno, EPROTO, "errno");
 }
 
 static void __test_uprobe_syscall(void)
Signature · 1 line
2.54.0
merge bot Applied
#19 lore raw

[tip: perf/core] libbpf: Detect uprobe syscall with new error

The following commit has been merged into the perf/core branch of tip:

The following commit has been merged into the perf/core branch of tip:

Commit-ID:     c450c804b641003e0328e4b2ebf55c05f67e3d08
Gitweb:        https://git.kernel.org/tip/c450c804b641003e0328e4b2ebf55c05f67e3d08
Author:        Jiri Olsa <[email protected]>
AuthorDate:    Fri, 03 Jul 2026 13:49:11 +02:00
Committer:     Peter Zijlstra <[email protected]>
CommitterDate: Fri, 03 Jul 2026 16:30:36 +02:00

libbpf: Detect uprobe syscall with new error

In the previous optimized uprobe fix we changed the syscall error used for its detection from ENXIO to EPROTO.

Changing related probe_uprobe_syscall detection check.

Fixes 05738da0efa1 ("libbpf: Add uprobe syscall feature detection")
Fixes af734a7ddb4e ("uprobes/x86: Move optimized uprobe from nop5 to nop10")
Fixes 40b54d7e3dab ("uprobes/x86: Move optimized uprobe from nop5 to nop10")
Fixes 5c3c59c7952a ("uprobes/x86: Move optimized uprobe from nop5 to nop10")
---
 tools/lib/bpf/features.c                                | 4 ++--
 tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)
tools/lib/bpf/features.c +2 -2
index b7e388f..e5641fa 100644
@@ -577,10 +577,10 @@ static int probe_ldimm64_full_range_off(int token_fd)
 static int probe_uprobe_syscall(int token_fd)
 {
 	/*
-	 * If kernel supports uprobe() syscall, it will return -ENXIO when called
+	 * If kernel supports uprobe() syscall, it will return -EPROTO when called
 	 * from the outside of a kernel-generated uprobe trampoline.
 	 */
-	return syscall(__NR_uprobe) < 0 && errno == ENXIO;
+	return syscall(__NR_uprobe) < 0 && errno == EPROTO;
 }
 #else
 static int probe_uprobe_syscall(int token_fd)
tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c +1 -1
index 955a377..c944136 100644
@@ -762,7 +762,7 @@ static void test_uprobe_error(void)
 	long err = syscall(__NR_uprobe);
 
 	ASSERT_EQ(err, -1, "error");
-	ASSERT_EQ(errno, ENXIO, "errno");
+	ASSERT_EQ(errno, EPROTO, "errno");
 }
 
 static void __test_uprobe_syscall(void)
#20 lore raw

Re: [tip: perf/core] libbpf: Detect uprobe syscall with new error

Quoted 14 lines · * tip-bot2 for Jiri Olsa <[email protected]> wrote:

The following commit has been merged into the perf/core branch of tip:

Commit-ID:     c450c804b641003e0328e4b2ebf55c05f67e3d08
Gitweb:        https://git.kernel.org/tip/c450c804b641003e0328e4b2ebf55c05f67e3d08
Author:        Jiri Olsa <[email protected]>
AuthorDate:    Fri, 03 Jul 2026 13:49:11 +02:00
Committer:     Peter Zijlstra <[email protected]>
CommitterDate: Fri, 03 Jul 2026 16:30:36 +02:00

libbpf: Detect uprobe syscall with new error

In the previous optimized uprobe fix we changed the syscall error used for its detection from ENXIO to EPROTO.

Quoted 6 lines

Changing related probe_uprobe_syscall detection check.

Fixes 05738da0efa1 ("libbpf: Add uprobe syscall feature detection")
Fixes af734a7ddb4e ("uprobes/x86: Move optimized uprobe from nop5 to nop10")
Fixes 40b54d7e3dab ("uprobes/x86: Move optimized uprobe from nop5 to nop10")
Fixes 5c3c59c7952a ("uprobes/x86: Move optimized uprobe from nop5 to nop10")

The last 3 Fixes tags are bogus (just like the triplication itself), those SHA1's don't exist anymore due to rebases.

I suppose it's meant to be:

Fixes 554ba38456da ("uprobes/x86: Move optimized uprobe from nop5 to nop10")

But why are we applying and then fixing later on a regression in an earlier commit in the same series to begin with??

Anyway, I've fixed up the tag mishaps in a rebase in tip:perf/core, but can we please not do something like this in the future?

Thanks,

Ingo

merge bot Applied
#21 lore raw

[tip: perf/core] libbpf: Detect uprobe syscall with new error

In reply to Jiri Olsa
The following commit has been merged into the perf/core branch of tip:

The following commit has been merged into the perf/core branch of tip:

Commit-ID:     8cae54c586084c81ab80f6ab020192eb2ce7aa0b
Gitweb:        https://git.kernel.org/tip/8cae54c586084c81ab80f6ab020192eb2ce7aa0b
Author:        Jiri Olsa <[email protected]>
AuthorDate:    Fri, 03 Jul 2026 13:49:11 +02:00
Committer:     Ingo Molnar <[email protected]>
CommitterDate: Sat, 04 Jul 2026 10:56:30 +02:00

libbpf: Detect uprobe syscall with new error

In the previous optimized uprobe fix we changed the syscall error used for its detection from ENXIO to EPROTO.

Changing related probe_uprobe_syscall detection check.

Fixes 05738da0efa1 ("libbpf: Add uprobe syscall feature detection")
Fixes 554ba38456da ("uprobes/x86: Move optimized uprobe from nop5 to nop10")
---
 tools/lib/bpf/features.c                                | 4 ++--
 tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)
tools/lib/bpf/features.c +2 -2
index b7e388f..e5641fa 100644
@@ -577,10 +577,10 @@ static int probe_ldimm64_full_range_off(int token_fd)
 static int probe_uprobe_syscall(int token_fd)
 {
 	/*
-	 * If kernel supports uprobe() syscall, it will return -ENXIO when called
+	 * If kernel supports uprobe() syscall, it will return -EPROTO when called
 	 * from the outside of a kernel-generated uprobe trampoline.
 	 */
-	return syscall(__NR_uprobe) < 0 && errno == ENXIO;
+	return syscall(__NR_uprobe) < 0 && errno == EPROTO;
 }
 #else
 static int probe_uprobe_syscall(int token_fd)
tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c +1 -1
index 955a377..c944136 100644
@@ -762,7 +762,7 @@ static void test_uprobe_error(void)
 	long err = syscall(__NR_uprobe);
 
 	ASSERT_EQ(err, -1, "error");
-	ASSERT_EQ(errno, ENXIO, "errno");
+	ASSERT_EQ(errno, EPROTO, "errno");
 }
 
 static void __test_uprobe_syscall(void)
author reviewer
#22 lore raw

PATCH v6 8/13 selftests/bpf: Emit nop,nop10 instructions combo for x86_64 arch

In reply to Jiri Olsa

Syncing latest usdt.h change [1].

Now that we have nop10 optimization support in kernel, let's emit nop,nop10 for usdt probe. We leave it up to the library to use desirable nop instruction.

[1] https://github.com/libbpf/usdt/commit/9018f82577d1dad7ed628d9efdaffc09f8f2241b

---
 tools/testing/selftests/bpf/usdt.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
tools/testing/selftests/bpf/usdt.h +1 -1
index c71e21df38b3..75687f50f4e2 100644
@@ -313,7 +313,7 @@ struct usdt_sema { volatile unsigned short active; };
 #if defined(__ia64__) || defined(__s390__) || defined(__s390x__)
 #define USDT_NOP			nop 0
 #elif defined(__x86_64__)
-#define USDT_NOP                       .byte 0x90, 0x0f, 0x1f, 0x44, 0x00, 0x0 /* nop, nop5 */
+#define USDT_NOP                       .byte 0x90, 0x66, 0x2e, 0x0f, 0x1f, 0x84, 0x00, 0x00, 0x00, 0x00, 0x00 /* nop, nop10 */
 #else
 #define USDT_NOP			nop
 #endif
Signature · 1 line
2.54.0
#23 lore raw

Re: [PATCHv6 08/13] selftests/bpf: Emit nop,nop10 instructions combo for x86_64 arch

Thank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider: - [High] Incomplete update of USDT_NOP causes selftest failures and silent loss of libbpf uprobe…

Thank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider:
- [High] Incomplete update of USDT_NOP causes selftest failures and silent loss of libbpf uprobe optimization.
- [Medium] The x86 uprobes subsystem does not support optimizing nop10 instructions, contradicting the commit message's claim. --

commit 0e159bff3c4759d25ce27fa625273c5dc59c418b
Author: Jiri Olsa <[email protected]>

selftests/bpf: Emit nop,nop10 instructions combo for x86_64 arch

This commit updates the USDT_NOP macro for x86_64 to emit a nop,nop10 instruction sequence instead of nop,nop5. This syncs the latest changes from libbpf usdt.h, leaving it up to the library to use the desirable nop instruction.

Quoted 2 lines

Now that we have nop10 optimization support in kernel, let's emit nop,nop10 for usdt probe.

[Severity: Medium]
Is this description accurate regarding kernel support for nop10 optimization?

Looking at x86 uprobes in arch/x86/kernel/uprobes.c:can_optimize(), the kernel explicitly restricts optimizations to 5-byte instructions:

    if (!insn->x86_64 || insn->length != 5)
        return false;

Does the current kernel actually support optimizing a 10-byte nop, or will this fail the instruction length check and refuse to optimize?

Quoted 4 lines
tools/testing/selftests/bpf/usdt.h +0 -0
index c71e21df38b32..75687f50f4e21 100644

[ ... ]

tools/testing/selftests/bpf/usdt.h struct usdt_sema { volatile unsigned short active; }; · line 316

Quoted 6 lines
tools/testing/selftests/bpf/usdt.h +1 -1
@@ -313,7 +313,7 @@ struct usdt_sema { volatile unsigned short active; };
 #if defined(__ia64__) || defined(__s390__) || defined(__s390x__)
 #define USDT_NOP			nop 0
 #elif defined(__x86_64__)
-#define USDT_NOP                       .byte 0x90, 0x0f, 0x1f, 0x44, 0x00, 0x0 /* nop, nop5 */
+#define USDT_NOP                       .byte 0x90, 0x66, 0x2e, 0x0f, 0x1f, 0x84, 0x00, 0x00, 0x00, 0x00, 0x00 /* nop, nop10 */

[Severity: High]
Will this incomplete update cause selftest failures and a silent loss of uprobe optimization in libbpf?

The selftest suite in tools/testing/selftests/bpf/prog_tests/usdt.c expects the old 6-byte sequence and will fail an assertion when it cannot find it in subtest_optimized_attach():

    addr_2 = find_instr(usdt_2, nop1_nop5_combo, 6);
    if (!ASSERT_OK_PTR(addr_2, "usdt_2_find_nop1_nop5_combo"))

Additionally, libbpf hardcodes the old 6-byte sequence in tools/lib/bpf/usdt.c:has_nop_combo():

    unsigned char nop_combo[6] = {
        0x90, 0x0f, 0x1f, 0x44, 0x00, 0x00 /* nop,nop5 */
    };

Without updating these locations, won't libbpf fail to detect the new 11-byte sequence, causing it to fall back to the 1-byte nop which cannot be optimized?

Signature · 1 line
Sashiko AI review · https://sashiko.dev/#/patchset/[email protected]?part=1
merge bot Applied
#24 lore raw

[tip: perf/core] selftests/bpf: Emit nop,nop10 instructions combo for x86_64 arch

In reply to Jiri Olsa
The following commit has been merged into the perf/core branch of tip:

The following commit has been merged into the perf/core branch of tip:

Commit-ID:     d44c12dbeff02180f1e9cadb52d5c939cfb3f75f
Gitweb:        https://git.kernel.org/tip/d44c12dbeff02180f1e9cadb52d5c939cfb3f75f
Author:        Jiri Olsa <[email protected]>
AuthorDate:    Fri, 03 Jul 2026 13:49:12 +02:00
Committer:     Peter Zijlstra <[email protected]>
CommitterDate: Fri, 03 Jul 2026 16:30:37 +02:00

selftests/bpf: Emit nop,nop10 instructions combo for x86_64 arch

Syncing latest usdt.h change [1].

Now that we have nop10 optimization support in kernel, let's emit nop,nop10 for usdt probe. We leave it up to the library to use desirable nop instruction.

[1] https://github.com/libbpf/usdt/commit/9018f82577d1dad7ed628d9efdaffc09f8f2241b

---
 tools/testing/selftests/bpf/usdt.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
tools/testing/selftests/bpf/usdt.h +1 -1
index c71e21d..75687f5 100644
@@ -313,7 +313,7 @@ struct usdt_sema { volatile unsigned short active; };
 #if defined(__ia64__) || defined(__s390__) || defined(__s390x__)
 #define USDT_NOP			nop 0
 #elif defined(__x86_64__)
-#define USDT_NOP                       .byte 0x90, 0x0f, 0x1f, 0x44, 0x00, 0x0 /* nop, nop5 */
+#define USDT_NOP                       .byte 0x90, 0x66, 0x2e, 0x0f, 0x1f, 0x84, 0x00, 0x00, 0x00, 0x00, 0x00 /* nop, nop10 */
 #else
 #define USDT_NOP			nop
 #endif
merge bot Applied
#25 lore raw

[tip: perf/core] selftests/bpf: Emit nop,nop10 instructions combo for x86_64 arch

In reply to Jiri Olsa
The following commit has been merged into the perf/core branch of tip:

The following commit has been merged into the perf/core branch of tip:

Commit-ID:     6d91200bcbb52020f33a26f9e92ba309b804fdba
Gitweb:        https://git.kernel.org/tip/6d91200bcbb52020f33a26f9e92ba309b804fdba
Author:        Jiri Olsa <[email protected]>
AuthorDate:    Fri, 03 Jul 2026 13:49:12 +02:00
Committer:     Ingo Molnar <[email protected]>
CommitterDate: Sat, 04 Jul 2026 10:56:56 +02:00

selftests/bpf: Emit nop,nop10 instructions combo for x86_64 arch

Syncing latest usdt.h change [1].

Now that we have nop10 optimization support in kernel, let's emit nop,nop10 for usdt probe. We leave it up to the library to use desirable nop instruction.

[1] https://github.com/libbpf/usdt/commit/9018f82577d1dad7ed628d9efdaffc09f8f2241b

---
 tools/testing/selftests/bpf/usdt.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
tools/testing/selftests/bpf/usdt.h +1 -1
index c71e21d..75687f5 100644
@@ -313,7 +313,7 @@ struct usdt_sema { volatile unsigned short active; };
 #if defined(__ia64__) || defined(__s390__) || defined(__s390x__)
 #define USDT_NOP			nop 0
 #elif defined(__x86_64__)
-#define USDT_NOP                       .byte 0x90, 0x0f, 0x1f, 0x44, 0x00, 0x0 /* nop, nop5 */
+#define USDT_NOP                       .byte 0x90, 0x66, 0x2e, 0x0f, 0x1f, 0x84, 0x00, 0x00, 0x00, 0x00, 0x00 /* nop, nop10 */
 #else
 #define USDT_NOP			nop
 #endif
author reviewer
#26 lore raw

PATCH v6 9/13 selftests/bpf: Change uprobe syscall tests to use nop10

In reply to Jiri Olsa

Optimized uprobes are now on top of 10-bytes nop instructions, reflect that in existing tests.

---
 .../selftests/bpf/benchs/bench_trigger.c      |  2 +-
 .../selftests/bpf/prog_tests/uprobe_syscall.c | 30 +++++++++++--------
 tools/testing/selftests/bpf/prog_tests/usdt.c | 25 +++++++++-------
 tools/testing/selftests/bpf/usdt_2.c          |  2 +-
 4 files changed, 34 insertions(+), 25 deletions(-)
tools/testing/selftests/bpf/benchs/bench_trigger.c +1 -1
index 2f22ec61667b..a60b8173cdc4 100644
@@ -398,7 +398,7 @@ static void *uprobe_producer_ret(void *input)
 #ifdef __x86_64__
 __nocf_check __weak void uprobe_target_nop5(void)
 {
-	asm volatile (".byte 0x0f, 0x1f, 0x44, 0x00, 0x00");
+	asm volatile (".byte 0x66, 0x2e, 0x0f, 0x1f, 0x84, 0x00, 0x00, 0x00, 0x00, 0x00");
 }
 
 static void *uprobe_producer_nop5(void *input)
tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c +17 -13
index c944136252c6..ba50071ace40 100644
@@ -17,7 +17,7 @@
 #include "uprobe_syscall_executed.skel.h"
 #include "bpf/libbpf_internal.h"
 
-#define USDT_NOP .byte 0x0f, 0x1f, 0x44, 0x00, 0x00
+#define USDT_NOP .byte 0x66, 0x2e, 0x0f, 0x1f, 0x84, 0x00, 0x00, 0x00, 0x00, 0x00
 #include "usdt.h"
 
 #pragma GCC diagnostic ignored "-Wattributes"
@@ -26,7 +26,7 @@ __attribute__((aligned(16)))
 __nocf_check __weak __naked unsigned long uprobe_regs_trigger(void)
 {
 	asm volatile (
-		".byte 0x0f, 0x1f, 0x44, 0x00, 0x00\n" /* nop5 */
+		".byte 0x66, 0x2e, 0x0f, 0x1f, 0x84, 0x00, 0x00, 0x00, 0x00, 0x00\n" /* nop10 */
 		"movq $0xdeadbeef, %rax\n"
 		"ret\n"
 	);
@@ -345,9 +345,9 @@ static void test_uretprobe_syscall_call(void)
 __attribute__((aligned(16)))
 __nocf_check __weak __naked void uprobe_test(void)
 {
-	asm volatile ("					\n"
-		".byte 0x0f, 0x1f, 0x44, 0x00, 0x00	\n"
-		"ret					\n"
+	asm volatile (
+		".byte 0x66, 0x2e, 0x0f, 0x1f, 0x84, 0x00, 0x00, 0x00, 0x00, 0x00\n" /* nop10 */
+		"ret\n"
 	);
 }
 
@@ -388,14 +388,15 @@ static int find_uprobes_trampoline(void *tramp_addr)
 	return ret;
 }
 
-static unsigned char nop5[5] = { 0x0f, 0x1f, 0x44, 0x00, 0x00 };
+static unsigned char nop10[10]  = { 0x66, 0x2e, 0x0f, 0x1f, 0x84, 0x00, 0x00, 0x00, 0x00, 0x00 };
+static unsigned char lea_rsp[5] = { 0x48, 0x8d, 0x64, 0x24, 0x80 };
 
-static void *find_nop5(void *fn)
+static void *find_nop10(void *fn)
 {
 	int i;
 
-	for (i = 0; i < 10; i++) {
-		if (!memcmp(nop5, fn + i, 5))
+	for (i = 0; i < 128; i++) {
+		if (!memcmp(nop10, fn + i, 10))
 			return fn + i;
 	}
 	return NULL;
@@ -420,7 +421,8 @@ static void *check_attach(struct uprobe_syscall_executed *skel, trigger_t trigge
 	ASSERT_EQ(skel->bss->executed, executed, "executed");
 
 	/* .. and check the trampoline is as expected. */
-	call = (struct __arch_relative_insn *) addr;
+	ASSERT_OK(memcmp(addr, lea_rsp, 5), "lea_rsp");
+	call = (struct __arch_relative_insn *)(addr + 5);
 	tramp = (void *) (call + 1) + call->raddr;
 	ASSERT_EQ(call->op, 0xe8, "call");
 	ASSERT_OK(find_uprobes_trampoline(tramp), "uprobes_trampoline");
@@ -430,9 +432,11 @@ static void *check_attach(struct uprobe_syscall_executed *skel, trigger_t trigge
 
 static void check_detach(void *addr, void *tramp)
 {
+	static const unsigned char nop10_prefix[] = { 0x66, 0x2e, 0x0f, 0x1f, 0x84 };
+
 	/* [uprobes_trampoline] stays after detach */
 	ASSERT_OK(find_uprobes_trampoline(tramp), "uprobes_trampoline");
-	ASSERT_OK(memcmp(addr, nop5, 5), "nop5");
+	ASSERT_OK(memcmp(addr, nop10_prefix, 5), "nop10_prefix");
 }
 
 static void check(struct uprobe_syscall_executed *skel, struct bpf_link *link,
@@ -568,8 +572,8 @@ static void test_uprobe_usdt(void)
 	void *addr;
 
 	errno = 0;
-	addr = find_nop5(usdt_test);
-	if (!ASSERT_OK_PTR(addr, "find_nop5"))
+	addr = find_nop10(usdt_test);
+	if (!ASSERT_OK_PTR(addr, "find_nop10"))
 		return;
 
 	skel = uprobe_syscall_executed__open_and_load();
tools/testing/selftests/bpf/prog_tests/usdt.c +15 -10
index 69759b27794d..fda3a298ccfc 100644
@@ -252,7 +252,7 @@ extern void usdt_1(void);
 extern void usdt_2(void);
 
 static unsigned char nop1[1] = { 0x90 };
-static unsigned char nop1_nop5_combo[6] = { 0x90, 0x0f, 0x1f, 0x44, 0x00, 0x00 };
+static unsigned char nop1_nop10_combo[11] = { 0x90, 0x66, 0x2e, 0x0f, 0x1f, 0x84, 0x00, 0x00, 0x00, 0x00, 0x00 };
 
 static void *find_instr(void *fn, unsigned char *instr, size_t cnt)
 {
@@ -271,17 +271,17 @@ static void subtest_optimized_attach(void)
 	__u8 *addr_1, *addr_2;
 
 	/* usdt_1 USDT probe has single nop instruction */
-	addr_1 = find_instr(usdt_1, nop1_nop5_combo, 6);
-	if (!ASSERT_NULL(addr_1, "usdt_1_find_nop1_nop5_combo"))
+	addr_1 = find_instr(usdt_1, nop1_nop10_combo, 11);
+	if (!ASSERT_NULL(addr_1, "usdt_1_find_nop1_nop10_combo"))
 		return;
 
 	addr_1 = find_instr(usdt_1, nop1, 1);
 	if (!ASSERT_OK_PTR(addr_1, "usdt_1_find_nop1"))
 		return;
 
-	/* usdt_2 USDT probe has nop,nop5 instructions combo */
-	addr_2 = find_instr(usdt_2, nop1_nop5_combo, 6);
-	if (!ASSERT_OK_PTR(addr_2, "usdt_2_find_nop1_nop5_combo"))
+	/* usdt_2 USDT probe has nop,nop10 instructions combo */
+	addr_2 = find_instr(usdt_2, nop1_nop10_combo, 11);
+	if (!ASSERT_OK_PTR(addr_2, "usdt_2_find_nop1_nop10_combo"))
 		return;
 
 	skel = test_usdt__open_and_load();
@@ -309,12 +309,12 @@ static void subtest_optimized_attach(void)
 
 	bpf_link__destroy(skel->links.usdt_executed);
 
-	/* we expect the nop5 ip */
+	/* we expect the nop10 ip */
 	skel->bss->expected_ip = (unsigned long) addr_2 + 1;
 
 	/*
 	 * Attach program on top of usdt_2 which is probe defined on top
-	 * of nop1,nop5 combo, so the probe gets optimized on top of nop5.
+	 * of nop1,nop10 combo, so the probe gets optimized on top of nop10.
 	 */
 	skel->links.usdt_executed = bpf_program__attach_usdt(skel->progs.usdt_executed,
 						     0 /*self*/, "/proc/self/exe",
@@ -328,8 +328,13 @@ static void subtest_optimized_attach(void)
 	/* nop stays on addr_2 address */
 	ASSERT_EQ(*addr_2, 0x90, "nop");
 
-	/* call is on addr_2 + 1 address */
-	ASSERT_EQ(*(addr_2 + 1), 0xe8, "call");
+	/*
+	 * lea -0x80(%rsp), %rsp
+	 * call ...
+	 */
+	static unsigned char expected[] = { 0x48, 0x8d, 0x64, 0x24, 0x80, 0xe8 };
+
+	ASSERT_MEMEQ(addr_2 + 1, expected, sizeof(expected), "lea_and_call");
 	ASSERT_EQ(skel->bss->executed, 4, "executed");
 
 cleanup:
tools/testing/selftests/bpf/usdt_2.c +1 -1
index 789883aaca4c..b359b389f6c0 100644
@@ -3,7 +3,7 @@
 #if defined(__x86_64__)
 
 /*
- * Include usdt.h with default nop,nop5 instructions combo.
+ * Include usdt.h with default nop,nop10 instructions combo.
  */
 #include "usdt.h"
 
Signature · 1 line
2.54.0
#27 lore raw

Re: [PATCHv6 09/13] selftests/bpf: Change uprobe syscall tests to use nop10

Thank you for your contribution! Sashiko AI review found 3 potential issue(s) to consider: - [Medium] The default `USDT_NOP` macro in `usdt.h` was not updated to `nop10`, causing `usdt_2.c` to…

Thank you for your contribution! Sashiko AI review found 3 potential issue(s) to consider:
- [Medium] The default USDT_NOP macro in usdt.h was not updated to nop10, causing usdt_2.c to compile with a 6-byte NOP and breaking the selftest.
- [Medium] Libbpf's USDT attachment logic is unaware of nop10, preventing the IP shift for optimized uprobes and causing them to fall back to unoptimized traps.
- [Medium] The check_detach function only verifies that the first 5 bytes of the nop10 instruction are restored upon uprobe detachment, leaving the remaining 5 bytes unverified. --

commit b3e7e5fee8889d2f95596f44b09c53ec9e3d2d6c
Author: Jiri Olsa <[email protected]>

selftests/bpf: Change uprobe syscall tests to use nop10

Optimized uprobes are now on top of 10-bytes nop instructions, reflect that in existing tests.

Quoted 4 lines
tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c +0 -0
index 955a37751b52d..0bb37435ce97b 100644

[ ... ]

tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c static void *check_attach(struct uprobe_syscall_executed *skel, trigger_t trigge · line 440

Quoted 11 lines
tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c +3 -1
@@ -430,9 +432,11 @@ static void *check_attach(struct uprobe_syscall_executed *skel, trigger_t trigge
 
 static void check_detach(void *addr, void *tramp)
 {
+	static const unsigned char nop10_prefix[] = { 0x66, 0x2e, 0x0f, 0x1f, 0x84 };
+
 	/* [uprobes_trampoline] stays after detach */
 	ASSERT_OK(find_uprobes_trampoline(tramp), "uprobes_trampoline");
-	ASSERT_OK(memcmp(addr, nop5, 5), "nop5");
+	ASSERT_OK(memcmp(addr, nop10_prefix, 5), "nop10_prefix");
 }

[Severity: Medium]
Should check_detach() verify the full 10 bytes?

Since the optimized uprobe modifies a 10-byte instruction sequence, only verifying the first 5 bytes might leave incomplete detachments unverified. If the detachment logic fails to correctly restore the last 5 bytes, it could lead to a corrupted memory access when executing the NOP.

Quoted 4 lines
tools/testing/selftests/bpf/prog_tests/usdt.c +0 -0
index 69759b27794d7..fda3a298ccfc7 100644

[ ... ]

tools/testing/selftests/bpf/prog_tests/usdt.c static void subtest_optimized_attach(void) · line 337

Quoted 13 lines
tools/testing/selftests/bpf/prog_tests/usdt.c +7 -2
@@ -328,8 +328,13 @@ static void subtest_optimized_attach(void)
 	/* nop stays on addr_2 address */
 	ASSERT_EQ(*addr_2, 0x90, "nop");
 
-	/* call is on addr_2 + 1 address */
-	ASSERT_EQ(*(addr_2 + 1), 0xe8, "call");
+	/*
+	 * lea -0x80(%rsp), %rsp
+	 * call ...
+	 */
+	static unsigned char expected[] = { 0x48, 0x8d, 0x64, 0x24, 0x80, 0xe8 };
+
+	ASSERT_MEMEQ(addr_2 + 1, expected, sizeof(expected), "lea_and_call");

[Severity: Medium]
Does libbpf need to be updated to recognize the new nop10 sequence?

Looking at has_nop_combo() in tools/lib/bpf/usdt.c, it still explicitly checks for the 6-byte nop combo:

    unsigned char nop_combo[6] = {
        0x90, 0x0f, 0x1f, 0x44, 0x00, 0x00 /* nop,nop5 */
    };

If libbpf encounters the new nop10 sequence, it won't advance the instruction pointer and will fall back to an unoptimized trap instead of using lea and call. This would cause the ASSERT_MEMEQ here to fail.

tools/testing/selftests/bpf/usdt_2.c line 8

Quoted 12 lines
tools/testing/selftests/bpf/usdt_2.c +1 -1
index 789883aaca4c3..b359b389f6c00 100644
@@ -3,7 +3,7 @@
 #if defined(__x86_64__)
 
 /*
- * Include usdt.h with default nop,nop5 instructions combo.
+ * Include usdt.h with default nop,nop10 instructions combo.
  */
 #include "usdt.h"

[Severity: Medium]
Does tools/testing/selftests/bpf/usdt.h need to be updated to define the new 11-byte sequence for USDT_NOP?

The test in prog_tests/usdt.c searches for nop1_nop10_combo:

    addr_2 = find_instr(usdt_2, nop1_nop10_combo, 11);
    if (!ASSERT_OK_PTR(addr_2, "usdt_2_find_nop1_nop10_combo"))
        return;

Because USDT_NOP in usdt.h was not modified in this patch, it still generates the old 6-byte sequence. This will cause find_instr() to return NULL, resulting in the test failing.

Signature · 1 line
Sashiko AI review · https://sashiko.dev/#/patchset/[email protected]?part=1
merge bot Applied
#28 lore raw

[tip: perf/core] selftests/bpf: Change uprobe syscall tests to use nop10

In reply to Jiri Olsa
The following commit has been merged into the perf/core branch of tip:

The following commit has been merged into the perf/core branch of tip:

Commit-ID:     a35027e832db8cb1a9ff24f36001292afd7ef29b
Gitweb:        https://git.kernel.org/tip/a35027e832db8cb1a9ff24f36001292afd7ef29b
Author:        Jiri Olsa <[email protected]>
AuthorDate:    Fri, 03 Jul 2026 13:49:13 +02:00
Committer:     Peter Zijlstra <[email protected]>
CommitterDate: Fri, 03 Jul 2026 16:30:37 +02:00

selftests/bpf: Change uprobe syscall tests to use nop10

Optimized uprobes are now on top of 10-bytes nop instructions, reflect that in existing tests.

---
 tools/testing/selftests/bpf/benchs/bench_trigger.c      |  2 +-
 tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c | 30 ++++----
 tools/testing/selftests/bpf/prog_tests/usdt.c           | 25 ++++---
 tools/testing/selftests/bpf/usdt_2.c                    |  2 +-
 4 files changed, 34 insertions(+), 25 deletions(-)
tools/testing/selftests/bpf/benchs/bench_trigger.c +1 -1
index 2f22ec6..a60b817 100644
@@ -398,7 +398,7 @@ static void *uprobe_producer_ret(void *input)
 #ifdef __x86_64__
 __nocf_check __weak void uprobe_target_nop5(void)
 {
-	asm volatile (".byte 0x0f, 0x1f, 0x44, 0x00, 0x00");
+	asm volatile (".byte 0x66, 0x2e, 0x0f, 0x1f, 0x84, 0x00, 0x00, 0x00, 0x00, 0x00");
 }
 
 static void *uprobe_producer_nop5(void *input)
tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c +17 -13
index c944136..ba50071 100644
@@ -17,7 +17,7 @@
 #include "uprobe_syscall_executed.skel.h"
 #include "bpf/libbpf_internal.h"
 
-#define USDT_NOP .byte 0x0f, 0x1f, 0x44, 0x00, 0x00
+#define USDT_NOP .byte 0x66, 0x2e, 0x0f, 0x1f, 0x84, 0x00, 0x00, 0x00, 0x00, 0x00
 #include "usdt.h"
 
 #pragma GCC diagnostic ignored "-Wattributes"
@@ -26,7 +26,7 @@ __attribute__((aligned(16)))
 __nocf_check __weak __naked unsigned long uprobe_regs_trigger(void)
 {
 	asm volatile (
-		".byte 0x0f, 0x1f, 0x44, 0x00, 0x00\n" /* nop5 */
+		".byte 0x66, 0x2e, 0x0f, 0x1f, 0x84, 0x00, 0x00, 0x00, 0x00, 0x00\n" /* nop10 */
 		"movq $0xdeadbeef, %rax\n"
 		"ret\n"
 	);
@@ -345,9 +345,9 @@ cleanup:
 __attribute__((aligned(16)))
 __nocf_check __weak __naked void uprobe_test(void)
 {
-	asm volatile ("					\n"
-		".byte 0x0f, 0x1f, 0x44, 0x00, 0x00	\n"
-		"ret					\n"
+	asm volatile (
+		".byte 0x66, 0x2e, 0x0f, 0x1f, 0x84, 0x00, 0x00, 0x00, 0x00, 0x00\n" /* nop10 */
+		"ret\n"
 	);
 }
 
@@ -388,14 +388,15 @@ static int find_uprobes_trampoline(void *tramp_addr)
 	return ret;
 }
 
-static unsigned char nop5[5] = { 0x0f, 0x1f, 0x44, 0x00, 0x00 };
+static unsigned char nop10[10]  = { 0x66, 0x2e, 0x0f, 0x1f, 0x84, 0x00, 0x00, 0x00, 0x00, 0x00 };
+static unsigned char lea_rsp[5] = { 0x48, 0x8d, 0x64, 0x24, 0x80 };
 
-static void *find_nop5(void *fn)
+static void *find_nop10(void *fn)
 {
 	int i;
 
-	for (i = 0; i < 10; i++) {
-		if (!memcmp(nop5, fn + i, 5))
+	for (i = 0; i < 128; i++) {
+		if (!memcmp(nop10, fn + i, 10))
 			return fn + i;
 	}
 	return NULL;
@@ -420,7 +421,8 @@ static void *check_attach(struct uprobe_syscall_executed *skel, trigger_t trigge
 	ASSERT_EQ(skel->bss->executed, executed, "executed");
 
 	/* .. and check the trampoline is as expected. */
-	call = (struct __arch_relative_insn *) addr;
+	ASSERT_OK(memcmp(addr, lea_rsp, 5), "lea_rsp");
+	call = (struct __arch_relative_insn *)(addr + 5);
 	tramp = (void *) (call + 1) + call->raddr;
 	ASSERT_EQ(call->op, 0xe8, "call");
 	ASSERT_OK(find_uprobes_trampoline(tramp), "uprobes_trampoline");
@@ -430,9 +432,11 @@ static void *check_attach(struct uprobe_syscall_executed *skel, trigger_t trigge
 
 static void check_detach(void *addr, void *tramp)
 {
+	static const unsigned char nop10_prefix[] = { 0x66, 0x2e, 0x0f, 0x1f, 0x84 };
+
 	/* [uprobes_trampoline] stays after detach */
 	ASSERT_OK(find_uprobes_trampoline(tramp), "uprobes_trampoline");
-	ASSERT_OK(memcmp(addr, nop5, 5), "nop5");
+	ASSERT_OK(memcmp(addr, nop10_prefix, 5), "nop10_prefix");
 }
 
 static void check(struct uprobe_syscall_executed *skel, struct bpf_link *link,
@@ -568,8 +572,8 @@ static void test_uprobe_usdt(void)
 	void *addr;
 
 	errno = 0;
-	addr = find_nop5(usdt_test);
-	if (!ASSERT_OK_PTR(addr, "find_nop5"))
+	addr = find_nop10(usdt_test);
+	if (!ASSERT_OK_PTR(addr, "find_nop10"))
 		return;
 
 	skel = uprobe_syscall_executed__open_and_load();
tools/testing/selftests/bpf/prog_tests/usdt.c +15 -10
index 69759b2..fda3a29 100644
@@ -252,7 +252,7 @@ extern void usdt_1(void);
 extern void usdt_2(void);
 
 static unsigned char nop1[1] = { 0x90 };
-static unsigned char nop1_nop5_combo[6] = { 0x90, 0x0f, 0x1f, 0x44, 0x00, 0x00 };
+static unsigned char nop1_nop10_combo[11] = { 0x90, 0x66, 0x2e, 0x0f, 0x1f, 0x84, 0x00, 0x00, 0x00, 0x00, 0x00 };
 
 static void *find_instr(void *fn, unsigned char *instr, size_t cnt)
 {
@@ -271,17 +271,17 @@ static void subtest_optimized_attach(void)
 	__u8 *addr_1, *addr_2;
 
 	/* usdt_1 USDT probe has single nop instruction */
-	addr_1 = find_instr(usdt_1, nop1_nop5_combo, 6);
-	if (!ASSERT_NULL(addr_1, "usdt_1_find_nop1_nop5_combo"))
+	addr_1 = find_instr(usdt_1, nop1_nop10_combo, 11);
+	if (!ASSERT_NULL(addr_1, "usdt_1_find_nop1_nop10_combo"))
 		return;
 
 	addr_1 = find_instr(usdt_1, nop1, 1);
 	if (!ASSERT_OK_PTR(addr_1, "usdt_1_find_nop1"))
 		return;
 
-	/* usdt_2 USDT probe has nop,nop5 instructions combo */
-	addr_2 = find_instr(usdt_2, nop1_nop5_combo, 6);
-	if (!ASSERT_OK_PTR(addr_2, "usdt_2_find_nop1_nop5_combo"))
+	/* usdt_2 USDT probe has nop,nop10 instructions combo */
+	addr_2 = find_instr(usdt_2, nop1_nop10_combo, 11);
+	if (!ASSERT_OK_PTR(addr_2, "usdt_2_find_nop1_nop10_combo"))
 		return;
 
 	skel = test_usdt__open_and_load();
@@ -309,12 +309,12 @@ static void subtest_optimized_attach(void)
 
 	bpf_link__destroy(skel->links.usdt_executed);
 
-	/* we expect the nop5 ip */
+	/* we expect the nop10 ip */
 	skel->bss->expected_ip = (unsigned long) addr_2 + 1;
 
 	/*
 	 * Attach program on top of usdt_2 which is probe defined on top
-	 * of nop1,nop5 combo, so the probe gets optimized on top of nop5.
+	 * of nop1,nop10 combo, so the probe gets optimized on top of nop10.
 	 */
 	skel->links.usdt_executed = bpf_program__attach_usdt(skel->progs.usdt_executed,
 						     0 /*self*/, "/proc/self/exe",
@@ -328,8 +328,13 @@ static void subtest_optimized_attach(void)
 	/* nop stays on addr_2 address */
 	ASSERT_EQ(*addr_2, 0x90, "nop");
 
-	/* call is on addr_2 + 1 address */
-	ASSERT_EQ(*(addr_2 + 1), 0xe8, "call");
+	/*
+	 * lea -0x80(%rsp), %rsp
+	 * call ...
+	 */
+	static unsigned char expected[] = { 0x48, 0x8d, 0x64, 0x24, 0x80, 0xe8 };
+
+	ASSERT_MEMEQ(addr_2 + 1, expected, sizeof(expected), "lea_and_call");
 	ASSERT_EQ(skel->bss->executed, 4, "executed");
 
 cleanup:
tools/testing/selftests/bpf/usdt_2.c +1 -1
index 789883a..b359b38 100644
@@ -3,7 +3,7 @@
 #if defined(__x86_64__)
 
 /*
- * Include usdt.h with default nop,nop5 instructions combo.
+ * Include usdt.h with default nop,nop10 instructions combo.
  */
 #include "usdt.h"
 
merge bot Applied
#29 lore raw

[tip: perf/core] selftests/bpf: Change uprobe syscall tests to use nop10

In reply to Jiri Olsa
The following commit has been merged into the perf/core branch of tip:

The following commit has been merged into the perf/core branch of tip:

Commit-ID:     ec0596a0208318d66be7ae946c8964c41dccaa8d
Gitweb:        https://git.kernel.org/tip/ec0596a0208318d66be7ae946c8964c41dccaa8d
Author:        Jiri Olsa <[email protected]>
AuthorDate:    Fri, 03 Jul 2026 13:49:13 +02:00
Committer:     Ingo Molnar <[email protected]>
CommitterDate: Sat, 04 Jul 2026 10:57:04 +02:00

selftests/bpf: Change uprobe syscall tests to use nop10

Optimized uprobes are now on top of 10-bytes nop instructions, reflect that in existing tests.

---
 tools/testing/selftests/bpf/benchs/bench_trigger.c      |  2 +-
 tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c | 30 ++++----
 tools/testing/selftests/bpf/prog_tests/usdt.c           | 25 ++++---
 tools/testing/selftests/bpf/usdt_2.c                    |  2 +-
 4 files changed, 34 insertions(+), 25 deletions(-)
tools/testing/selftests/bpf/benchs/bench_trigger.c +1 -1
index 2f22ec6..a60b817 100644
@@ -398,7 +398,7 @@ static void *uprobe_producer_ret(void *input)
 #ifdef __x86_64__
 __nocf_check __weak void uprobe_target_nop5(void)
 {
-	asm volatile (".byte 0x0f, 0x1f, 0x44, 0x00, 0x00");
+	asm volatile (".byte 0x66, 0x2e, 0x0f, 0x1f, 0x84, 0x00, 0x00, 0x00, 0x00, 0x00");
 }
 
 static void *uprobe_producer_nop5(void *input)
tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c +17 -13
index c944136..ba50071 100644
@@ -17,7 +17,7 @@
 #include "uprobe_syscall_executed.skel.h"
 #include "bpf/libbpf_internal.h"
 
-#define USDT_NOP .byte 0x0f, 0x1f, 0x44, 0x00, 0x00
+#define USDT_NOP .byte 0x66, 0x2e, 0x0f, 0x1f, 0x84, 0x00, 0x00, 0x00, 0x00, 0x00
 #include "usdt.h"
 
 #pragma GCC diagnostic ignored "-Wattributes"
@@ -26,7 +26,7 @@ __attribute__((aligned(16)))
 __nocf_check __weak __naked unsigned long uprobe_regs_trigger(void)
 {
 	asm volatile (
-		".byte 0x0f, 0x1f, 0x44, 0x00, 0x00\n" /* nop5 */
+		".byte 0x66, 0x2e, 0x0f, 0x1f, 0x84, 0x00, 0x00, 0x00, 0x00, 0x00\n" /* nop10 */
 		"movq $0xdeadbeef, %rax\n"
 		"ret\n"
 	);
@@ -345,9 +345,9 @@ cleanup:
 __attribute__((aligned(16)))
 __nocf_check __weak __naked void uprobe_test(void)
 {
-	asm volatile ("					\n"
-		".byte 0x0f, 0x1f, 0x44, 0x00, 0x00	\n"
-		"ret					\n"
+	asm volatile (
+		".byte 0x66, 0x2e, 0x0f, 0x1f, 0x84, 0x00, 0x00, 0x00, 0x00, 0x00\n" /* nop10 */
+		"ret\n"
 	);
 }
 
@@ -388,14 +388,15 @@ static int find_uprobes_trampoline(void *tramp_addr)
 	return ret;
 }
 
-static unsigned char nop5[5] = { 0x0f, 0x1f, 0x44, 0x00, 0x00 };
+static unsigned char nop10[10]  = { 0x66, 0x2e, 0x0f, 0x1f, 0x84, 0x00, 0x00, 0x00, 0x00, 0x00 };
+static unsigned char lea_rsp[5] = { 0x48, 0x8d, 0x64, 0x24, 0x80 };
 
-static void *find_nop5(void *fn)
+static void *find_nop10(void *fn)
 {
 	int i;
 
-	for (i = 0; i < 10; i++) {
-		if (!memcmp(nop5, fn + i, 5))
+	for (i = 0; i < 128; i++) {
+		if (!memcmp(nop10, fn + i, 10))
 			return fn + i;
 	}
 	return NULL;
@@ -420,7 +421,8 @@ static void *check_attach(struct uprobe_syscall_executed *skel, trigger_t trigge
 	ASSERT_EQ(skel->bss->executed, executed, "executed");
 
 	/* .. and check the trampoline is as expected. */
-	call = (struct __arch_relative_insn *) addr;
+	ASSERT_OK(memcmp(addr, lea_rsp, 5), "lea_rsp");
+	call = (struct __arch_relative_insn *)(addr + 5);
 	tramp = (void *) (call + 1) + call->raddr;
 	ASSERT_EQ(call->op, 0xe8, "call");
 	ASSERT_OK(find_uprobes_trampoline(tramp), "uprobes_trampoline");
@@ -430,9 +432,11 @@ static void *check_attach(struct uprobe_syscall_executed *skel, trigger_t trigge
 
 static void check_detach(void *addr, void *tramp)
 {
+	static const unsigned char nop10_prefix[] = { 0x66, 0x2e, 0x0f, 0x1f, 0x84 };
+
 	/* [uprobes_trampoline] stays after detach */
 	ASSERT_OK(find_uprobes_trampoline(tramp), "uprobes_trampoline");
-	ASSERT_OK(memcmp(addr, nop5, 5), "nop5");
+	ASSERT_OK(memcmp(addr, nop10_prefix, 5), "nop10_prefix");
 }
 
 static void check(struct uprobe_syscall_executed *skel, struct bpf_link *link,
@@ -568,8 +572,8 @@ static void test_uprobe_usdt(void)
 	void *addr;
 
 	errno = 0;
-	addr = find_nop5(usdt_test);
-	if (!ASSERT_OK_PTR(addr, "find_nop5"))
+	addr = find_nop10(usdt_test);
+	if (!ASSERT_OK_PTR(addr, "find_nop10"))
 		return;
 
 	skel = uprobe_syscall_executed__open_and_load();
tools/testing/selftests/bpf/prog_tests/usdt.c +15 -10
index 69759b2..fda3a29 100644
@@ -252,7 +252,7 @@ extern void usdt_1(void);
 extern void usdt_2(void);
 
 static unsigned char nop1[1] = { 0x90 };
-static unsigned char nop1_nop5_combo[6] = { 0x90, 0x0f, 0x1f, 0x44, 0x00, 0x00 };
+static unsigned char nop1_nop10_combo[11] = { 0x90, 0x66, 0x2e, 0x0f, 0x1f, 0x84, 0x00, 0x00, 0x00, 0x00, 0x00 };
 
 static void *find_instr(void *fn, unsigned char *instr, size_t cnt)
 {
@@ -271,17 +271,17 @@ static void subtest_optimized_attach(void)
 	__u8 *addr_1, *addr_2;
 
 	/* usdt_1 USDT probe has single nop instruction */
-	addr_1 = find_instr(usdt_1, nop1_nop5_combo, 6);
-	if (!ASSERT_NULL(addr_1, "usdt_1_find_nop1_nop5_combo"))
+	addr_1 = find_instr(usdt_1, nop1_nop10_combo, 11);
+	if (!ASSERT_NULL(addr_1, "usdt_1_find_nop1_nop10_combo"))
 		return;
 
 	addr_1 = find_instr(usdt_1, nop1, 1);
 	if (!ASSERT_OK_PTR(addr_1, "usdt_1_find_nop1"))
 		return;
 
-	/* usdt_2 USDT probe has nop,nop5 instructions combo */
-	addr_2 = find_instr(usdt_2, nop1_nop5_combo, 6);
-	if (!ASSERT_OK_PTR(addr_2, "usdt_2_find_nop1_nop5_combo"))
+	/* usdt_2 USDT probe has nop,nop10 instructions combo */
+	addr_2 = find_instr(usdt_2, nop1_nop10_combo, 11);
+	if (!ASSERT_OK_PTR(addr_2, "usdt_2_find_nop1_nop10_combo"))
 		return;
 
 	skel = test_usdt__open_and_load();
@@ -309,12 +309,12 @@ static void subtest_optimized_attach(void)
 
 	bpf_link__destroy(skel->links.usdt_executed);
 
-	/* we expect the nop5 ip */
+	/* we expect the nop10 ip */
 	skel->bss->expected_ip = (unsigned long) addr_2 + 1;
 
 	/*
 	 * Attach program on top of usdt_2 which is probe defined on top
-	 * of nop1,nop5 combo, so the probe gets optimized on top of nop5.
+	 * of nop1,nop10 combo, so the probe gets optimized on top of nop10.
 	 */
 	skel->links.usdt_executed = bpf_program__attach_usdt(skel->progs.usdt_executed,
 						     0 /*self*/, "/proc/self/exe",
@@ -328,8 +328,13 @@ static void subtest_optimized_attach(void)
 	/* nop stays on addr_2 address */
 	ASSERT_EQ(*addr_2, 0x90, "nop");
 
-	/* call is on addr_2 + 1 address */
-	ASSERT_EQ(*(addr_2 + 1), 0xe8, "call");
+	/*
+	 * lea -0x80(%rsp), %rsp
+	 * call ...
+	 */
+	static unsigned char expected[] = { 0x48, 0x8d, 0x64, 0x24, 0x80, 0xe8 };
+
+	ASSERT_MEMEQ(addr_2 + 1, expected, sizeof(expected), "lea_and_call");
 	ASSERT_EQ(skel->bss->executed, 4, "executed");
 
 cleanup:
tools/testing/selftests/bpf/usdt_2.c +1 -1
index 789883a..b359b38 100644
@@ -3,7 +3,7 @@
 #if defined(__x86_64__)
 
 /*
- * Include usdt.h with default nop,nop5 instructions combo.
+ * Include usdt.h with default nop,nop10 instructions combo.
  */
 #include "usdt.h"
 
author reviewer
#30 lore raw

PATCH v6 10/13 selftests/bpf: Change uprobe/usdt trigger bench code to use nop10

In reply to Jiri Olsa

Changing uprobe/usdt trigger bench code to use nop10 instead of nop5. Also changing run_bench_uprobes.sh to use nop10 triggers.

---
 tools/testing/selftests/bpf/bench.c           | 20 +++++------
 .../selftests/bpf/benchs/bench_trigger.c      | 36 +++++++++----------
 .../selftests/bpf/benchs/run_bench_uprobes.sh |  2 +-
 3 files changed, 29 insertions(+), 29 deletions(-)
tools/testing/selftests/bpf/bench.c +10 -10
index 3d9d2cd7764b..c4a3a6b3eb83 100644
@@ -539,12 +539,12 @@ extern const struct bench bench_trig_uretprobe_multi_push;
 extern const struct bench bench_trig_uprobe_multi_ret;
 extern const struct bench bench_trig_uretprobe_multi_ret;
 #ifdef __x86_64__
-extern const struct bench bench_trig_uprobe_nop5;
-extern const struct bench bench_trig_uretprobe_nop5;
-extern const struct bench bench_trig_uprobe_multi_nop5;
-extern const struct bench bench_trig_uretprobe_multi_nop5;
+extern const struct bench bench_trig_uprobe_nop10;
+extern const struct bench bench_trig_uretprobe_nop10;
+extern const struct bench bench_trig_uprobe_multi_nop10;
+extern const struct bench bench_trig_uretprobe_multi_nop10;
 extern const struct bench bench_trig_usdt_nop;
-extern const struct bench bench_trig_usdt_nop5;
+extern const struct bench bench_trig_usdt_nop10;
 #endif
 
 extern const struct bench bench_rb_libbpf;
@@ -622,12 +622,12 @@ static const struct bench *benchs[] = {
 	&bench_trig_uprobe_multi_ret,
 	&bench_trig_uretprobe_multi_ret,
 #ifdef __x86_64__
-	&bench_trig_uprobe_nop5,
-	&bench_trig_uretprobe_nop5,
-	&bench_trig_uprobe_multi_nop5,
-	&bench_trig_uretprobe_multi_nop5,
+	&bench_trig_uprobe_nop10,
+	&bench_trig_uretprobe_nop10,
+	&bench_trig_uprobe_multi_nop10,
+	&bench_trig_uretprobe_multi_nop10,
 	&bench_trig_usdt_nop,
-	&bench_trig_usdt_nop5,
+	&bench_trig_usdt_nop10,
 #endif
 	/* ringbuf/perfbuf benchmarks */
 	&bench_rb_libbpf,
tools/testing/selftests/bpf/benchs/bench_trigger.c +18 -18
index a60b8173cdc4..61513efc167a 100644
@@ -396,15 +396,15 @@ static void *uprobe_producer_ret(void *input)
 }
 
 #ifdef __x86_64__
-__nocf_check __weak void uprobe_target_nop5(void)
+__nocf_check __weak void uprobe_target_nop10(void)
 {
 	asm volatile (".byte 0x66, 0x2e, 0x0f, 0x1f, 0x84, 0x00, 0x00, 0x00, 0x00, 0x00");
 }
 
-static void *uprobe_producer_nop5(void *input)
+static void *uprobe_producer_nop10(void *input)
 {
 	while (true)
-		uprobe_target_nop5();
+		uprobe_target_nop10();
 	return NULL;
 }
 
@@ -418,7 +418,7 @@ static void *uprobe_producer_usdt_nop(void *input)
 	return NULL;
 }
 
-static void *uprobe_producer_usdt_nop5(void *input)
+static void *uprobe_producer_usdt_nop10(void *input)
 {
 	while (true)
 		usdt_2();
@@ -542,24 +542,24 @@ static void uretprobe_multi_ret_setup(void)
 }
 
 #ifdef __x86_64__
-static void uprobe_nop5_setup(void)
+static void uprobe_nop10_setup(void)
 {
-	usetup(false, false /* !use_multi */, &uprobe_target_nop5);
+	usetup(false, false /* !use_multi */, &uprobe_target_nop10);
 }
 
-static void uretprobe_nop5_setup(void)
+static void uretprobe_nop10_setup(void)
 {
-	usetup(true, false /* !use_multi */, &uprobe_target_nop5);
+	usetup(true, false /* !use_multi */, &uprobe_target_nop10);
 }
 
-static void uprobe_multi_nop5_setup(void)
+static void uprobe_multi_nop10_setup(void)
 {
-	usetup(false, true /* use_multi */, &uprobe_target_nop5);
+	usetup(false, true /* use_multi */, &uprobe_target_nop10);
 }
 
-static void uretprobe_multi_nop5_setup(void)
+static void uretprobe_multi_nop10_setup(void)
 {
-	usetup(true, true /* use_multi */, &uprobe_target_nop5);
+	usetup(true, true /* use_multi */, &uprobe_target_nop10);
 }
 
 static void usdt_setup(const char *name)
@@ -598,7 +598,7 @@ static void usdt_nop_setup(void)
 	usdt_setup("usdt_1");
 }
 
-static void usdt_nop5_setup(void)
+static void usdt_nop10_setup(void)
 {
 	usdt_setup("usdt_2");
 }
@@ -665,10 +665,10 @@ BENCH_TRIG_USERMODE(uretprobe_multi_nop, nop, "uretprobe-multi-nop");
 BENCH_TRIG_USERMODE(uretprobe_multi_push, push, "uretprobe-multi-push");
 BENCH_TRIG_USERMODE(uretprobe_multi_ret, ret, "uretprobe-multi-ret");
 #ifdef __x86_64__
-BENCH_TRIG_USERMODE(uprobe_nop5, nop5, "uprobe-nop5");
-BENCH_TRIG_USERMODE(uretprobe_nop5, nop5, "uretprobe-nop5");
-BENCH_TRIG_USERMODE(uprobe_multi_nop5, nop5, "uprobe-multi-nop5");
-BENCH_TRIG_USERMODE(uretprobe_multi_nop5, nop5, "uretprobe-multi-nop5");
+BENCH_TRIG_USERMODE(uprobe_nop10, nop10, "uprobe-nop10");
+BENCH_TRIG_USERMODE(uretprobe_nop10, nop10, "uretprobe-nop10");
+BENCH_TRIG_USERMODE(uprobe_multi_nop10, nop10, "uprobe-multi-nop10");
+BENCH_TRIG_USERMODE(uretprobe_multi_nop10, nop10, "uretprobe-multi-nop10");
 BENCH_TRIG_USERMODE(usdt_nop, usdt_nop, "usdt-nop");
-BENCH_TRIG_USERMODE(usdt_nop5, usdt_nop5, "usdt-nop5");
+BENCH_TRIG_USERMODE(usdt_nop10, usdt_nop10, "usdt-nop10");
 #endif
tools/testing/selftests/bpf/benchs/run_bench_uprobes.sh +1 -1
index 9ec59423b949..e490b337e960 100755
@@ -2,7 +2,7 @@
 
 set -eufo pipefail
 
-for i in usermode-count syscall-count {uprobe,uretprobe}-{nop,push,ret,nop5} usdt-nop usdt-nop5
+for i in usermode-count syscall-count {uprobe,uretprobe}-{nop,push,ret,nop10} usdt-nop usdt-nop10
 do
 	summary=$(sudo ./bench -w2 -d5 -a trig-$i | tail -n1 | cut -d'(' -f1 | cut -d' ' -f3-)
 	printf "%-15s: %s\n" $i "$summary"
Signature · 1 line
2.54.0
merge bot Applied
#31 lore raw

[tip: perf/core] selftests/bpf: Change uprobe/usdt trigger bench code to use nop10

The following commit has been merged into the perf/core branch of tip:

The following commit has been merged into the perf/core branch of tip:

Commit-ID:     c2535542f80aa7a74dc43261b6fb1da43ef894d5
Gitweb:        https://git.kernel.org/tip/c2535542f80aa7a74dc43261b6fb1da43ef894d5
Author:        Jiri Olsa <[email protected]>
AuthorDate:    Fri, 03 Jul 2026 13:49:14 +02:00
Committer:     Peter Zijlstra <[email protected]>
CommitterDate: Fri, 03 Jul 2026 16:30:37 +02:00

selftests/bpf: Change uprobe/usdt trigger bench code to use nop10

Changing uprobe/usdt trigger bench code to use nop10 instead of nop5. Also changing run_bench_uprobes.sh to use nop10 triggers.

---
 tools/testing/selftests/bpf/bench.c                     | 20 ++--
 tools/testing/selftests/bpf/benchs/bench_trigger.c      | 36 ++++----
 tools/testing/selftests/bpf/benchs/run_bench_uprobes.sh |  2 +-
 3 files changed, 29 insertions(+), 29 deletions(-)
tools/testing/selftests/bpf/bench.c +10 -10
index 3d9d2cd..c4a3a6b 100644
@@ -539,12 +539,12 @@ extern const struct bench bench_trig_uretprobe_multi_push;
 extern const struct bench bench_trig_uprobe_multi_ret;
 extern const struct bench bench_trig_uretprobe_multi_ret;
 #ifdef __x86_64__
-extern const struct bench bench_trig_uprobe_nop5;
-extern const struct bench bench_trig_uretprobe_nop5;
-extern const struct bench bench_trig_uprobe_multi_nop5;
-extern const struct bench bench_trig_uretprobe_multi_nop5;
+extern const struct bench bench_trig_uprobe_nop10;
+extern const struct bench bench_trig_uretprobe_nop10;
+extern const struct bench bench_trig_uprobe_multi_nop10;
+extern const struct bench bench_trig_uretprobe_multi_nop10;
 extern const struct bench bench_trig_usdt_nop;
-extern const struct bench bench_trig_usdt_nop5;
+extern const struct bench bench_trig_usdt_nop10;
 #endif
 
 extern const struct bench bench_rb_libbpf;
@@ -622,12 +622,12 @@ static const struct bench *benchs[] = {
 	&bench_trig_uprobe_multi_ret,
 	&bench_trig_uretprobe_multi_ret,
 #ifdef __x86_64__
-	&bench_trig_uprobe_nop5,
-	&bench_trig_uretprobe_nop5,
-	&bench_trig_uprobe_multi_nop5,
-	&bench_trig_uretprobe_multi_nop5,
+	&bench_trig_uprobe_nop10,
+	&bench_trig_uretprobe_nop10,
+	&bench_trig_uprobe_multi_nop10,
+	&bench_trig_uretprobe_multi_nop10,
 	&bench_trig_usdt_nop,
-	&bench_trig_usdt_nop5,
+	&bench_trig_usdt_nop10,
 #endif
 	/* ringbuf/perfbuf benchmarks */
 	&bench_rb_libbpf,
tools/testing/selftests/bpf/benchs/bench_trigger.c +18 -18
index a60b817..61513ef 100644
@@ -396,15 +396,15 @@ static void *uprobe_producer_ret(void *input)
 }
 
 #ifdef __x86_64__
-__nocf_check __weak void uprobe_target_nop5(void)
+__nocf_check __weak void uprobe_target_nop10(void)
 {
 	asm volatile (".byte 0x66, 0x2e, 0x0f, 0x1f, 0x84, 0x00, 0x00, 0x00, 0x00, 0x00");
 }
 
-static void *uprobe_producer_nop5(void *input)
+static void *uprobe_producer_nop10(void *input)
 {
 	while (true)
-		uprobe_target_nop5();
+		uprobe_target_nop10();
 	return NULL;
 }
 
@@ -418,7 +418,7 @@ static void *uprobe_producer_usdt_nop(void *input)
 	return NULL;
 }
 
-static void *uprobe_producer_usdt_nop5(void *input)
+static void *uprobe_producer_usdt_nop10(void *input)
 {
 	while (true)
 		usdt_2();
@@ -542,24 +542,24 @@ static void uretprobe_multi_ret_setup(void)
 }
 
 #ifdef __x86_64__
-static void uprobe_nop5_setup(void)
+static void uprobe_nop10_setup(void)
 {
-	usetup(false, false /* !use_multi */, &uprobe_target_nop5);
+	usetup(false, false /* !use_multi */, &uprobe_target_nop10);
 }
 
-static void uretprobe_nop5_setup(void)
+static void uretprobe_nop10_setup(void)
 {
-	usetup(true, false /* !use_multi */, &uprobe_target_nop5);
+	usetup(true, false /* !use_multi */, &uprobe_target_nop10);
 }
 
-static void uprobe_multi_nop5_setup(void)
+static void uprobe_multi_nop10_setup(void)
 {
-	usetup(false, true /* use_multi */, &uprobe_target_nop5);
+	usetup(false, true /* use_multi */, &uprobe_target_nop10);
 }
 
-static void uretprobe_multi_nop5_setup(void)
+static void uretprobe_multi_nop10_setup(void)
 {
-	usetup(true, true /* use_multi */, &uprobe_target_nop5);
+	usetup(true, true /* use_multi */, &uprobe_target_nop10);
 }
 
 static void usdt_setup(const char *name)
@@ -598,7 +598,7 @@ static void usdt_nop_setup(void)
 	usdt_setup("usdt_1");
 }
 
-static void usdt_nop5_setup(void)
+static void usdt_nop10_setup(void)
 {
 	usdt_setup("usdt_2");
 }
@@ -665,10 +665,10 @@ BENCH_TRIG_USERMODE(uretprobe_multi_nop, nop, "uretprobe-multi-nop");
 BENCH_TRIG_USERMODE(uretprobe_multi_push, push, "uretprobe-multi-push");
 BENCH_TRIG_USERMODE(uretprobe_multi_ret, ret, "uretprobe-multi-ret");
 #ifdef __x86_64__
-BENCH_TRIG_USERMODE(uprobe_nop5, nop5, "uprobe-nop5");
-BENCH_TRIG_USERMODE(uretprobe_nop5, nop5, "uretprobe-nop5");
-BENCH_TRIG_USERMODE(uprobe_multi_nop5, nop5, "uprobe-multi-nop5");
-BENCH_TRIG_USERMODE(uretprobe_multi_nop5, nop5, "uretprobe-multi-nop5");
+BENCH_TRIG_USERMODE(uprobe_nop10, nop10, "uprobe-nop10");
+BENCH_TRIG_USERMODE(uretprobe_nop10, nop10, "uretprobe-nop10");
+BENCH_TRIG_USERMODE(uprobe_multi_nop10, nop10, "uprobe-multi-nop10");
+BENCH_TRIG_USERMODE(uretprobe_multi_nop10, nop10, "uretprobe-multi-nop10");
 BENCH_TRIG_USERMODE(usdt_nop, usdt_nop, "usdt-nop");
-BENCH_TRIG_USERMODE(usdt_nop5, usdt_nop5, "usdt-nop5");
+BENCH_TRIG_USERMODE(usdt_nop10, usdt_nop10, "usdt-nop10");
 #endif
tools/testing/selftests/bpf/benchs/run_bench_uprobes.sh +1 -1
index 9ec5942..e490b33 100755
@@ -2,7 +2,7 @@
 
 set -eufo pipefail
 
-for i in usermode-count syscall-count {uprobe,uretprobe}-{nop,push,ret,nop5} usdt-nop usdt-nop5
+for i in usermode-count syscall-count {uprobe,uretprobe}-{nop,push,ret,nop10} usdt-nop usdt-nop10
 do
 	summary=$(sudo ./bench -w2 -d5 -a trig-$i | tail -n1 | cut -d'(' -f1 | cut -d' ' -f3-)
 	printf "%-15s: %s\n" $i "$summary"
merge bot Applied
#32 lore raw

[tip: perf/core] selftests/bpf: Change uprobe/usdt trigger bench code to use nop10

In reply to Jiri Olsa
The following commit has been merged into the perf/core branch of tip:

The following commit has been merged into the perf/core branch of tip:

Commit-ID:     b2cf7c41e4f12f76f6f7b6a21194367cf8d3e7b9
Gitweb:        https://git.kernel.org/tip/b2cf7c41e4f12f76f6f7b6a21194367cf8d3e7b9
Author:        Jiri Olsa <[email protected]>
AuthorDate:    Fri, 03 Jul 2026 13:49:14 +02:00
Committer:     Ingo Molnar <[email protected]>
CommitterDate: Sat, 04 Jul 2026 10:57:13 +02:00

selftests/bpf: Change uprobe/usdt trigger bench code to use nop10

Changing uprobe/usdt trigger bench code to use nop10 instead of nop5. Also changing run_bench_uprobes.sh to use nop10 triggers.

---
 tools/testing/selftests/bpf/bench.c                     | 20 ++--
 tools/testing/selftests/bpf/benchs/bench_trigger.c      | 36 ++++----
 tools/testing/selftests/bpf/benchs/run_bench_uprobes.sh |  2 +-
 3 files changed, 29 insertions(+), 29 deletions(-)
tools/testing/selftests/bpf/bench.c +10 -10
index 3d9d2cd..c4a3a6b 100644
@@ -539,12 +539,12 @@ extern const struct bench bench_trig_uretprobe_multi_push;
 extern const struct bench bench_trig_uprobe_multi_ret;
 extern const struct bench bench_trig_uretprobe_multi_ret;
 #ifdef __x86_64__
-extern const struct bench bench_trig_uprobe_nop5;
-extern const struct bench bench_trig_uretprobe_nop5;
-extern const struct bench bench_trig_uprobe_multi_nop5;
-extern const struct bench bench_trig_uretprobe_multi_nop5;
+extern const struct bench bench_trig_uprobe_nop10;
+extern const struct bench bench_trig_uretprobe_nop10;
+extern const struct bench bench_trig_uprobe_multi_nop10;
+extern const struct bench bench_trig_uretprobe_multi_nop10;
 extern const struct bench bench_trig_usdt_nop;
-extern const struct bench bench_trig_usdt_nop5;
+extern const struct bench bench_trig_usdt_nop10;
 #endif
 
 extern const struct bench bench_rb_libbpf;
@@ -622,12 +622,12 @@ static const struct bench *benchs[] = {
 	&bench_trig_uprobe_multi_ret,
 	&bench_trig_uretprobe_multi_ret,
 #ifdef __x86_64__
-	&bench_trig_uprobe_nop5,
-	&bench_trig_uretprobe_nop5,
-	&bench_trig_uprobe_multi_nop5,
-	&bench_trig_uretprobe_multi_nop5,
+	&bench_trig_uprobe_nop10,
+	&bench_trig_uretprobe_nop10,
+	&bench_trig_uprobe_multi_nop10,
+	&bench_trig_uretprobe_multi_nop10,
 	&bench_trig_usdt_nop,
-	&bench_trig_usdt_nop5,
+	&bench_trig_usdt_nop10,
 #endif
 	/* ringbuf/perfbuf benchmarks */
 	&bench_rb_libbpf,
tools/testing/selftests/bpf/benchs/bench_trigger.c +18 -18
index a60b817..61513ef 100644
@@ -396,15 +396,15 @@ static void *uprobe_producer_ret(void *input)
 }
 
 #ifdef __x86_64__
-__nocf_check __weak void uprobe_target_nop5(void)
+__nocf_check __weak void uprobe_target_nop10(void)
 {
 	asm volatile (".byte 0x66, 0x2e, 0x0f, 0x1f, 0x84, 0x00, 0x00, 0x00, 0x00, 0x00");
 }
 
-static void *uprobe_producer_nop5(void *input)
+static void *uprobe_producer_nop10(void *input)
 {
 	while (true)
-		uprobe_target_nop5();
+		uprobe_target_nop10();
 	return NULL;
 }
 
@@ -418,7 +418,7 @@ static void *uprobe_producer_usdt_nop(void *input)
 	return NULL;
 }
 
-static void *uprobe_producer_usdt_nop5(void *input)
+static void *uprobe_producer_usdt_nop10(void *input)
 {
 	while (true)
 		usdt_2();
@@ -542,24 +542,24 @@ static void uretprobe_multi_ret_setup(void)
 }
 
 #ifdef __x86_64__
-static void uprobe_nop5_setup(void)
+static void uprobe_nop10_setup(void)
 {
-	usetup(false, false /* !use_multi */, &uprobe_target_nop5);
+	usetup(false, false /* !use_multi */, &uprobe_target_nop10);
 }
 
-static void uretprobe_nop5_setup(void)
+static void uretprobe_nop10_setup(void)
 {
-	usetup(true, false /* !use_multi */, &uprobe_target_nop5);
+	usetup(true, false /* !use_multi */, &uprobe_target_nop10);
 }
 
-static void uprobe_multi_nop5_setup(void)
+static void uprobe_multi_nop10_setup(void)
 {
-	usetup(false, true /* use_multi */, &uprobe_target_nop5);
+	usetup(false, true /* use_multi */, &uprobe_target_nop10);
 }
 
-static void uretprobe_multi_nop5_setup(void)
+static void uretprobe_multi_nop10_setup(void)
 {
-	usetup(true, true /* use_multi */, &uprobe_target_nop5);
+	usetup(true, true /* use_multi */, &uprobe_target_nop10);
 }
 
 static void usdt_setup(const char *name)
@@ -598,7 +598,7 @@ static void usdt_nop_setup(void)
 	usdt_setup("usdt_1");
 }
 
-static void usdt_nop5_setup(void)
+static void usdt_nop10_setup(void)
 {
 	usdt_setup("usdt_2");
 }
@@ -665,10 +665,10 @@ BENCH_TRIG_USERMODE(uretprobe_multi_nop, nop, "uretprobe-multi-nop");
 BENCH_TRIG_USERMODE(uretprobe_multi_push, push, "uretprobe-multi-push");
 BENCH_TRIG_USERMODE(uretprobe_multi_ret, ret, "uretprobe-multi-ret");
 #ifdef __x86_64__
-BENCH_TRIG_USERMODE(uprobe_nop5, nop5, "uprobe-nop5");
-BENCH_TRIG_USERMODE(uretprobe_nop5, nop5, "uretprobe-nop5");
-BENCH_TRIG_USERMODE(uprobe_multi_nop5, nop5, "uprobe-multi-nop5");
-BENCH_TRIG_USERMODE(uretprobe_multi_nop5, nop5, "uretprobe-multi-nop5");
+BENCH_TRIG_USERMODE(uprobe_nop10, nop10, "uprobe-nop10");
+BENCH_TRIG_USERMODE(uretprobe_nop10, nop10, "uretprobe-nop10");
+BENCH_TRIG_USERMODE(uprobe_multi_nop10, nop10, "uprobe-multi-nop10");
+BENCH_TRIG_USERMODE(uretprobe_multi_nop10, nop10, "uretprobe-multi-nop10");
 BENCH_TRIG_USERMODE(usdt_nop, usdt_nop, "usdt-nop");
-BENCH_TRIG_USERMODE(usdt_nop5, usdt_nop5, "usdt-nop5");
+BENCH_TRIG_USERMODE(usdt_nop10, usdt_nop10, "usdt-nop10");
 #endif
tools/testing/selftests/bpf/benchs/run_bench_uprobes.sh +1 -1
index 9ec5942..e490b33 100755
@@ -2,7 +2,7 @@
 
 set -eufo pipefail
 
-for i in usermode-count syscall-count {uprobe,uretprobe}-{nop,push,ret,nop5} usdt-nop usdt-nop5
+for i in usermode-count syscall-count {uprobe,uretprobe}-{nop,push,ret,nop10} usdt-nop usdt-nop10
 do
 	summary=$(sudo ./bench -w2 -d5 -a trig-$i | tail -n1 | cut -d'(' -f1 | cut -d' ' -f3-)
 	printf "%-15s: %s\n" $i "$summary"
author reviewer
#33 lore raw

PATCH v6 11/13 selftests/bpf: Add reattach tests for uprobe syscall

In reply to Jiri Olsa

Adding reattach tests for uprobe syscall tests to make sure we can re-attach and optimize same uprobe multiple times.

---
 .../selftests/bpf/prog_tests/uprobe_syscall.c | 130 ++++++++++++++++--
 1 file changed, 120 insertions(+), 10 deletions(-)
tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c +120 -10
index ba50071ace40..7711018f8acd 100644
@@ -404,6 +404,16 @@ static void *find_nop10(void *fn)
 
 typedef void (__attribute__((nocf_check)) *trigger_t)(void);
 
+static void check_attach_notrigger(struct uprobe_syscall_executed *skel,
+				   void *addr, int executed)
+{
+	unsigned char *op = addr;
+
+	/* Make sure bpf program was not executed. */
+	ASSERT_EQ(skel->bss->executed, executed, "executed");
+	ASSERT_EQ(*op, 0xcc, "int3");
+}
+
 static void *check_attach(struct uprobe_syscall_executed *skel, trigger_t trigger,
 			  void *addr, int executed)
 {
@@ -430,23 +440,26 @@ static void *check_attach(struct uprobe_syscall_executed *skel, trigger_t trigge
 	return tramp;
 }
 
-static void check_detach(void *addr, void *tramp)
+static bool check_detach(void *addr, void *tramp)
 {
 	static const unsigned char nop10_prefix[] = { 0x66, 0x2e, 0x0f, 0x1f, 0x84 };
+	bool ok = true;
 
 	/* [uprobes_trampoline] stays after detach */
-	ASSERT_OK(find_uprobes_trampoline(tramp), "uprobes_trampoline");
-	ASSERT_OK(memcmp(addr, nop10_prefix, 5), "nop10_prefix");
+	ok &= ASSERT_OK(find_uprobes_trampoline(tramp), "uprobes_trampoline");
+	ok &= ASSERT_OK(memcmp(addr, nop10_prefix, 5), "nop10_prefix");
+	return ok;
 }
 
-static void check(struct uprobe_syscall_executed *skel, struct bpf_link *link,
-		  trigger_t trigger, void *addr, int executed)
+static void *check(struct uprobe_syscall_executed *skel, struct bpf_link *link,
+		   trigger_t trigger, void *addr, int executed)
 {
 	void *tramp;
 
 	tramp = check_attach(skel, trigger, addr, executed);
 	bpf_link__destroy(link);
 	check_detach(addr, tramp);
+	return tramp;
 }
 
 static void test_uprobe_legacy(void)
@@ -457,6 +470,7 @@ static void test_uprobe_legacy(void)
 	);
 	struct bpf_link *link;
 	unsigned long offset;
+	void *tramp;
 
 	offset = get_uprobe_offset(&uprobe_test);
 	if (!ASSERT_GE(offset, 0, "get_uprobe_offset"))
@@ -474,7 +488,30 @@ static void test_uprobe_legacy(void)
 	if (!ASSERT_OK_PTR(link, "bpf_program__attach_uprobe_opts"))
 		goto cleanup;
 
-	check(skel, link, uprobe_test, uprobe_test, 2);
+	tramp = check(skel, link, uprobe_test, uprobe_test, 2);
+
+	/* reattach and detach without triggering optimization */
+	link = bpf_program__attach_uprobe_opts(skel->progs.test_uprobe,
+					       0, "/proc/self/exe", offset, NULL);
+	if (!ASSERT_OK_PTR(link, "bpf_program__attach_uprobe_opts"))
+		goto cleanup;
+
+	check_attach_notrigger(skel, uprobe_test, 2);
+
+	bpf_link__destroy(link);
+	if (!check_detach(uprobe_test, tramp))
+		goto cleanup;
+
+	uprobe_test();
+	ASSERT_EQ(skel->bss->executed, 2, "executed_no_probe");
+
+	/* reattach with triggering optimization */
+	link = bpf_program__attach_uprobe_opts(skel->progs.test_uprobe,
+				0, "/proc/self/exe", offset, NULL);
+	if (!ASSERT_OK_PTR(link, "bpf_program__attach_uprobe_opts"))
+		goto cleanup;
+
+	check(skel, link, uprobe_test, uprobe_test, 4);
 
 	/* uretprobe */
 	skel->bss->executed = 0;
@@ -496,6 +533,7 @@ static void test_uprobe_multi(void)
 	LIBBPF_OPTS(bpf_uprobe_multi_opts, opts);
 	struct bpf_link *link;
 	unsigned long offset;
+	void *tramp;
 
 	offset = get_uprobe_offset(&uprobe_test);
 	if (!ASSERT_GE(offset, 0, "get_uprobe_offset"))
@@ -516,7 +554,30 @@ static void test_uprobe_multi(void)
 	if (!ASSERT_OK_PTR(link, "bpf_program__attach_uprobe_multi"))
 		goto cleanup;
 
-	check(skel, link, uprobe_test, uprobe_test, 2);
+	tramp = check(skel, link, uprobe_test, uprobe_test, 2);
+
+	/* reattach and detach without triggering optimization */
+	link = bpf_program__attach_uprobe_multi(skel->progs.test_uprobe_multi,
+				0, "/proc/self/exe", NULL, &opts);
+	if (!ASSERT_OK_PTR(link, "bpf_program__attach_uprobe_multi"))
+		goto cleanup;
+
+	check_attach_notrigger(skel, uprobe_test, 2);
+
+	bpf_link__destroy(link);
+	if (!check_detach(uprobe_test, tramp))
+		goto cleanup;
+
+	uprobe_test();
+	ASSERT_EQ(skel->bss->executed, 2, "executed_no_probe");
+
+	/* reattach with triggering optimization */
+	link = bpf_program__attach_uprobe_multi(skel->progs.test_uprobe_multi,
+				0, "/proc/self/exe", NULL, &opts);
+	if (!ASSERT_OK_PTR(link, "bpf_program__attach_uprobe_multi"))
+		goto cleanup;
+
+	check(skel, link, uprobe_test, uprobe_test, 4);
 
 	/* uretprobe.multi */
 	skel->bss->executed = 0;
@@ -540,6 +601,7 @@ static void test_uprobe_session(void)
 	);
 	struct bpf_link *link;
 	unsigned long offset;
+	void *tramp;
 
 	offset = get_uprobe_offset(&uprobe_test);
 	if (!ASSERT_GE(offset, 0, "get_uprobe_offset"))
@@ -559,7 +621,30 @@ static void test_uprobe_session(void)
 	if (!ASSERT_OK_PTR(link, "bpf_program__attach_uprobe_multi"))
 		goto cleanup;
 
-	check(skel, link, uprobe_test, uprobe_test, 4);
+	tramp = check(skel, link, uprobe_test, uprobe_test, 4);
+
+	/* reattach and detach without triggering optimization */
+	link = bpf_program__attach_uprobe_multi(skel->progs.test_uprobe_session,
+				0, "/proc/self/exe", NULL, &opts);
+	if (!ASSERT_OK_PTR(link, "bpf_program__attach_uprobe_multi"))
+		goto cleanup;
+
+	check_attach_notrigger(skel, uprobe_test, 4);
+
+	bpf_link__destroy(link);
+	if (!check_detach(uprobe_test, tramp))
+		goto cleanup;
+
+	uprobe_test();
+	ASSERT_EQ(skel->bss->executed, 4, "executed_no_probe");
+
+	/* reattach with triggering optimization */
+	link = bpf_program__attach_uprobe_multi(skel->progs.test_uprobe_session,
+				0, "/proc/self/exe", NULL, &opts);
+	if (!ASSERT_OK_PTR(link, "bpf_program__attach_uprobe_multi"))
+		goto cleanup;
+
+	check(skel, link, uprobe_test, uprobe_test, 8);
 
 cleanup:
 	uprobe_syscall_executed__destroy(skel);
@@ -569,7 +654,7 @@ static void test_uprobe_usdt(void)
 {
 	struct uprobe_syscall_executed *skel;
 	struct bpf_link *link;
-	void *addr;
+	void *addr, *tramp;
 
 	errno = 0;
 	addr = find_nop10(usdt_test);
@@ -588,7 +673,32 @@ static void test_uprobe_usdt(void)
 	if (!ASSERT_OK_PTR(link, "bpf_program__attach_usdt"))
 		goto cleanup;
 
-	check(skel, link, usdt_test, addr, 2);
+	tramp = check(skel, link, usdt_test, addr, 2);
+
+	/* reattach and detach without triggering optimization */
+	link = bpf_program__attach_usdt(skel->progs.test_usdt,
+				-1 /* all PIDs */, "/proc/self/exe",
+				"optimized_uprobe", "usdt", NULL);
+	if (!ASSERT_OK_PTR(link, "bpf_program__attach_usdt"))
+		goto cleanup;
+
+	check_attach_notrigger(skel, addr, 2);
+
+	bpf_link__destroy(link);
+	if (!check_detach(addr, tramp))
+		goto cleanup;
+
+	usdt_test();
+	ASSERT_EQ(skel->bss->executed, 2, "executed_no_probe");
+
+	/* reattach with triggering optimization */
+	link = bpf_program__attach_usdt(skel->progs.test_usdt,
+				-1 /* all PIDs */, "/proc/self/exe",
+				"optimized_uprobe", "usdt", NULL);
+	if (!ASSERT_OK_PTR(link, "bpf_program__attach_usdt"))
+		goto cleanup;
+
+	check(skel, link, usdt_test, addr, 4);
 
 cleanup:
 	uprobe_syscall_executed__destroy(skel);
Signature · 1 line
2.54.0
merge bot Applied
#34 lore raw

[tip: perf/core] selftests/bpf: Add reattach tests for uprobe syscall

The following commit has been merged into the perf/core branch of tip:

The following commit has been merged into the perf/core branch of tip:

Commit-ID:     9ca3f372c5b1afdf825b65db4719ca89bf24696b
Gitweb:        https://git.kernel.org/tip/9ca3f372c5b1afdf825b65db4719ca89bf24696b
Author:        Jiri Olsa <[email protected]>
AuthorDate:    Fri, 03 Jul 2026 13:49:15 +02:00
Committer:     Peter Zijlstra <[email protected]>
CommitterDate: Fri, 03 Jul 2026 16:30:37 +02:00

selftests/bpf: Add reattach tests for uprobe syscall

Adding reattach tests for uprobe syscall tests to make sure we can re-attach and optimize same uprobe multiple times.

---
 tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c | 130 ++++++-
 1 file changed, 120 insertions(+), 10 deletions(-)
tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c +120 -10
index ba50071..7711018 100644
@@ -404,6 +404,16 @@ static void *find_nop10(void *fn)
 
 typedef void (__attribute__((nocf_check)) *trigger_t)(void);
 
+static void check_attach_notrigger(struct uprobe_syscall_executed *skel,
+				   void *addr, int executed)
+{
+	unsigned char *op = addr;
+
+	/* Make sure bpf program was not executed. */
+	ASSERT_EQ(skel->bss->executed, executed, "executed");
+	ASSERT_EQ(*op, 0xcc, "int3");
+}
+
 static void *check_attach(struct uprobe_syscall_executed *skel, trigger_t trigger,
 			  void *addr, int executed)
 {
@@ -430,23 +440,26 @@ static void *check_attach(struct uprobe_syscall_executed *skel, trigger_t trigge
 	return tramp;
 }
 
-static void check_detach(void *addr, void *tramp)
+static bool check_detach(void *addr, void *tramp)
 {
 	static const unsigned char nop10_prefix[] = { 0x66, 0x2e, 0x0f, 0x1f, 0x84 };
+	bool ok = true;
 
 	/* [uprobes_trampoline] stays after detach */
-	ASSERT_OK(find_uprobes_trampoline(tramp), "uprobes_trampoline");
-	ASSERT_OK(memcmp(addr, nop10_prefix, 5), "nop10_prefix");
+	ok &= ASSERT_OK(find_uprobes_trampoline(tramp), "uprobes_trampoline");
+	ok &= ASSERT_OK(memcmp(addr, nop10_prefix, 5), "nop10_prefix");
+	return ok;
 }
 
-static void check(struct uprobe_syscall_executed *skel, struct bpf_link *link,
-		  trigger_t trigger, void *addr, int executed)
+static void *check(struct uprobe_syscall_executed *skel, struct bpf_link *link,
+		   trigger_t trigger, void *addr, int executed)
 {
 	void *tramp;
 
 	tramp = check_attach(skel, trigger, addr, executed);
 	bpf_link__destroy(link);
 	check_detach(addr, tramp);
+	return tramp;
 }
 
 static void test_uprobe_legacy(void)
@@ -457,6 +470,7 @@ static void test_uprobe_legacy(void)
 	);
 	struct bpf_link *link;
 	unsigned long offset;
+	void *tramp;
 
 	offset = get_uprobe_offset(&uprobe_test);
 	if (!ASSERT_GE(offset, 0, "get_uprobe_offset"))
@@ -474,7 +488,30 @@ static void test_uprobe_legacy(void)
 	if (!ASSERT_OK_PTR(link, "bpf_program__attach_uprobe_opts"))
 		goto cleanup;
 
-	check(skel, link, uprobe_test, uprobe_test, 2);
+	tramp = check(skel, link, uprobe_test, uprobe_test, 2);
+
+	/* reattach and detach without triggering optimization */
+	link = bpf_program__attach_uprobe_opts(skel->progs.test_uprobe,
+					       0, "/proc/self/exe", offset, NULL);
+	if (!ASSERT_OK_PTR(link, "bpf_program__attach_uprobe_opts"))
+		goto cleanup;
+
+	check_attach_notrigger(skel, uprobe_test, 2);
+
+	bpf_link__destroy(link);
+	if (!check_detach(uprobe_test, tramp))
+		goto cleanup;
+
+	uprobe_test();
+	ASSERT_EQ(skel->bss->executed, 2, "executed_no_probe");
+
+	/* reattach with triggering optimization */
+	link = bpf_program__attach_uprobe_opts(skel->progs.test_uprobe,
+				0, "/proc/self/exe", offset, NULL);
+	if (!ASSERT_OK_PTR(link, "bpf_program__attach_uprobe_opts"))
+		goto cleanup;
+
+	check(skel, link, uprobe_test, uprobe_test, 4);
 
 	/* uretprobe */
 	skel->bss->executed = 0;
@@ -496,6 +533,7 @@ static void test_uprobe_multi(void)
 	LIBBPF_OPTS(bpf_uprobe_multi_opts, opts);
 	struct bpf_link *link;
 	unsigned long offset;
+	void *tramp;
 
 	offset = get_uprobe_offset(&uprobe_test);
 	if (!ASSERT_GE(offset, 0, "get_uprobe_offset"))
@@ -516,7 +554,30 @@ static void test_uprobe_multi(void)
 	if (!ASSERT_OK_PTR(link, "bpf_program__attach_uprobe_multi"))
 		goto cleanup;
 
-	check(skel, link, uprobe_test, uprobe_test, 2);
+	tramp = check(skel, link, uprobe_test, uprobe_test, 2);
+
+	/* reattach and detach without triggering optimization */
+	link = bpf_program__attach_uprobe_multi(skel->progs.test_uprobe_multi,
+				0, "/proc/self/exe", NULL, &opts);
+	if (!ASSERT_OK_PTR(link, "bpf_program__attach_uprobe_multi"))
+		goto cleanup;
+
+	check_attach_notrigger(skel, uprobe_test, 2);
+
+	bpf_link__destroy(link);
+	if (!check_detach(uprobe_test, tramp))
+		goto cleanup;
+
+	uprobe_test();
+	ASSERT_EQ(skel->bss->executed, 2, "executed_no_probe");
+
+	/* reattach with triggering optimization */
+	link = bpf_program__attach_uprobe_multi(skel->progs.test_uprobe_multi,
+				0, "/proc/self/exe", NULL, &opts);
+	if (!ASSERT_OK_PTR(link, "bpf_program__attach_uprobe_multi"))
+		goto cleanup;
+
+	check(skel, link, uprobe_test, uprobe_test, 4);
 
 	/* uretprobe.multi */
 	skel->bss->executed = 0;
@@ -540,6 +601,7 @@ static void test_uprobe_session(void)
 	);
 	struct bpf_link *link;
 	unsigned long offset;
+	void *tramp;
 
 	offset = get_uprobe_offset(&uprobe_test);
 	if (!ASSERT_GE(offset, 0, "get_uprobe_offset"))
@@ -559,7 +621,30 @@ static void test_uprobe_session(void)
 	if (!ASSERT_OK_PTR(link, "bpf_program__attach_uprobe_multi"))
 		goto cleanup;
 
-	check(skel, link, uprobe_test, uprobe_test, 4);
+	tramp = check(skel, link, uprobe_test, uprobe_test, 4);
+
+	/* reattach and detach without triggering optimization */
+	link = bpf_program__attach_uprobe_multi(skel->progs.test_uprobe_session,
+				0, "/proc/self/exe", NULL, &opts);
+	if (!ASSERT_OK_PTR(link, "bpf_program__attach_uprobe_multi"))
+		goto cleanup;
+
+	check_attach_notrigger(skel, uprobe_test, 4);
+
+	bpf_link__destroy(link);
+	if (!check_detach(uprobe_test, tramp))
+		goto cleanup;
+
+	uprobe_test();
+	ASSERT_EQ(skel->bss->executed, 4, "executed_no_probe");
+
+	/* reattach with triggering optimization */
+	link = bpf_program__attach_uprobe_multi(skel->progs.test_uprobe_session,
+				0, "/proc/self/exe", NULL, &opts);
+	if (!ASSERT_OK_PTR(link, "bpf_program__attach_uprobe_multi"))
+		goto cleanup;
+
+	check(skel, link, uprobe_test, uprobe_test, 8);
 
 cleanup:
 	uprobe_syscall_executed__destroy(skel);
@@ -569,7 +654,7 @@ static void test_uprobe_usdt(void)
 {
 	struct uprobe_syscall_executed *skel;
 	struct bpf_link *link;
-	void *addr;
+	void *addr, *tramp;
 
 	errno = 0;
 	addr = find_nop10(usdt_test);
@@ -588,7 +673,32 @@ static void test_uprobe_usdt(void)
 	if (!ASSERT_OK_PTR(link, "bpf_program__attach_usdt"))
 		goto cleanup;
 
-	check(skel, link, usdt_test, addr, 2);
+	tramp = check(skel, link, usdt_test, addr, 2);
+
+	/* reattach and detach without triggering optimization */
+	link = bpf_program__attach_usdt(skel->progs.test_usdt,
+				-1 /* all PIDs */, "/proc/self/exe",
+				"optimized_uprobe", "usdt", NULL);
+	if (!ASSERT_OK_PTR(link, "bpf_program__attach_usdt"))
+		goto cleanup;
+
+	check_attach_notrigger(skel, addr, 2);
+
+	bpf_link__destroy(link);
+	if (!check_detach(addr, tramp))
+		goto cleanup;
+
+	usdt_test();
+	ASSERT_EQ(skel->bss->executed, 2, "executed_no_probe");
+
+	/* reattach with triggering optimization */
+	link = bpf_program__attach_usdt(skel->progs.test_usdt,
+				-1 /* all PIDs */, "/proc/self/exe",
+				"optimized_uprobe", "usdt", NULL);
+	if (!ASSERT_OK_PTR(link, "bpf_program__attach_usdt"))
+		goto cleanup;
+
+	check(skel, link, usdt_test, addr, 4);
 
 cleanup:
 	uprobe_syscall_executed__destroy(skel);
merge bot Applied
#35 lore raw

[tip: perf/core] selftests/bpf: Add reattach tests for uprobe syscall

In reply to Jiri Olsa
The following commit has been merged into the perf/core branch of tip:

The following commit has been merged into the perf/core branch of tip:

Commit-ID:     28d57db3e8d4e687b7ece4b047429908f123908e
Gitweb:        https://git.kernel.org/tip/28d57db3e8d4e687b7ece4b047429908f123908e
Author:        Jiri Olsa <[email protected]>
AuthorDate:    Fri, 03 Jul 2026 13:49:15 +02:00
Committer:     Ingo Molnar <[email protected]>
CommitterDate: Sat, 04 Jul 2026 10:57:21 +02:00

selftests/bpf: Add reattach tests for uprobe syscall

Adding reattach tests for uprobe syscall tests to make sure we can re-attach and optimize same uprobe multiple times.

---
 tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c | 130 ++++++-
 1 file changed, 120 insertions(+), 10 deletions(-)
tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c +120 -10
index ba50071..7711018 100644
@@ -404,6 +404,16 @@ static void *find_nop10(void *fn)
 
 typedef void (__attribute__((nocf_check)) *trigger_t)(void);
 
+static void check_attach_notrigger(struct uprobe_syscall_executed *skel,
+				   void *addr, int executed)
+{
+	unsigned char *op = addr;
+
+	/* Make sure bpf program was not executed. */
+	ASSERT_EQ(skel->bss->executed, executed, "executed");
+	ASSERT_EQ(*op, 0xcc, "int3");
+}
+
 static void *check_attach(struct uprobe_syscall_executed *skel, trigger_t trigger,
 			  void *addr, int executed)
 {
@@ -430,23 +440,26 @@ static void *check_attach(struct uprobe_syscall_executed *skel, trigger_t trigge
 	return tramp;
 }
 
-static void check_detach(void *addr, void *tramp)
+static bool check_detach(void *addr, void *tramp)
 {
 	static const unsigned char nop10_prefix[] = { 0x66, 0x2e, 0x0f, 0x1f, 0x84 };
+	bool ok = true;
 
 	/* [uprobes_trampoline] stays after detach */
-	ASSERT_OK(find_uprobes_trampoline(tramp), "uprobes_trampoline");
-	ASSERT_OK(memcmp(addr, nop10_prefix, 5), "nop10_prefix");
+	ok &= ASSERT_OK(find_uprobes_trampoline(tramp), "uprobes_trampoline");
+	ok &= ASSERT_OK(memcmp(addr, nop10_prefix, 5), "nop10_prefix");
+	return ok;
 }
 
-static void check(struct uprobe_syscall_executed *skel, struct bpf_link *link,
-		  trigger_t trigger, void *addr, int executed)
+static void *check(struct uprobe_syscall_executed *skel, struct bpf_link *link,
+		   trigger_t trigger, void *addr, int executed)
 {
 	void *tramp;
 
 	tramp = check_attach(skel, trigger, addr, executed);
 	bpf_link__destroy(link);
 	check_detach(addr, tramp);
+	return tramp;
 }
 
 static void test_uprobe_legacy(void)
@@ -457,6 +470,7 @@ static void test_uprobe_legacy(void)
 	);
 	struct bpf_link *link;
 	unsigned long offset;
+	void *tramp;
 
 	offset = get_uprobe_offset(&uprobe_test);
 	if (!ASSERT_GE(offset, 0, "get_uprobe_offset"))
@@ -474,7 +488,30 @@ static void test_uprobe_legacy(void)
 	if (!ASSERT_OK_PTR(link, "bpf_program__attach_uprobe_opts"))
 		goto cleanup;
 
-	check(skel, link, uprobe_test, uprobe_test, 2);
+	tramp = check(skel, link, uprobe_test, uprobe_test, 2);
+
+	/* reattach and detach without triggering optimization */
+	link = bpf_program__attach_uprobe_opts(skel->progs.test_uprobe,
+					       0, "/proc/self/exe", offset, NULL);
+	if (!ASSERT_OK_PTR(link, "bpf_program__attach_uprobe_opts"))
+		goto cleanup;
+
+	check_attach_notrigger(skel, uprobe_test, 2);
+
+	bpf_link__destroy(link);
+	if (!check_detach(uprobe_test, tramp))
+		goto cleanup;
+
+	uprobe_test();
+	ASSERT_EQ(skel->bss->executed, 2, "executed_no_probe");
+
+	/* reattach with triggering optimization */
+	link = bpf_program__attach_uprobe_opts(skel->progs.test_uprobe,
+				0, "/proc/self/exe", offset, NULL);
+	if (!ASSERT_OK_PTR(link, "bpf_program__attach_uprobe_opts"))
+		goto cleanup;
+
+	check(skel, link, uprobe_test, uprobe_test, 4);
 
 	/* uretprobe */
 	skel->bss->executed = 0;
@@ -496,6 +533,7 @@ static void test_uprobe_multi(void)
 	LIBBPF_OPTS(bpf_uprobe_multi_opts, opts);
 	struct bpf_link *link;
 	unsigned long offset;
+	void *tramp;
 
 	offset = get_uprobe_offset(&uprobe_test);
 	if (!ASSERT_GE(offset, 0, "get_uprobe_offset"))
@@ -516,7 +554,30 @@ static void test_uprobe_multi(void)
 	if (!ASSERT_OK_PTR(link, "bpf_program__attach_uprobe_multi"))
 		goto cleanup;
 
-	check(skel, link, uprobe_test, uprobe_test, 2);
+	tramp = check(skel, link, uprobe_test, uprobe_test, 2);
+
+	/* reattach and detach without triggering optimization */
+	link = bpf_program__attach_uprobe_multi(skel->progs.test_uprobe_multi,
+				0, "/proc/self/exe", NULL, &opts);
+	if (!ASSERT_OK_PTR(link, "bpf_program__attach_uprobe_multi"))
+		goto cleanup;
+
+	check_attach_notrigger(skel, uprobe_test, 2);
+
+	bpf_link__destroy(link);
+	if (!check_detach(uprobe_test, tramp))
+		goto cleanup;
+
+	uprobe_test();
+	ASSERT_EQ(skel->bss->executed, 2, "executed_no_probe");
+
+	/* reattach with triggering optimization */
+	link = bpf_program__attach_uprobe_multi(skel->progs.test_uprobe_multi,
+				0, "/proc/self/exe", NULL, &opts);
+	if (!ASSERT_OK_PTR(link, "bpf_program__attach_uprobe_multi"))
+		goto cleanup;
+
+	check(skel, link, uprobe_test, uprobe_test, 4);
 
 	/* uretprobe.multi */
 	skel->bss->executed = 0;
@@ -540,6 +601,7 @@ static void test_uprobe_session(void)
 	);
 	struct bpf_link *link;
 	unsigned long offset;
+	void *tramp;
 
 	offset = get_uprobe_offset(&uprobe_test);
 	if (!ASSERT_GE(offset, 0, "get_uprobe_offset"))
@@ -559,7 +621,30 @@ static void test_uprobe_session(void)
 	if (!ASSERT_OK_PTR(link, "bpf_program__attach_uprobe_multi"))
 		goto cleanup;
 
-	check(skel, link, uprobe_test, uprobe_test, 4);
+	tramp = check(skel, link, uprobe_test, uprobe_test, 4);
+
+	/* reattach and detach without triggering optimization */
+	link = bpf_program__attach_uprobe_multi(skel->progs.test_uprobe_session,
+				0, "/proc/self/exe", NULL, &opts);
+	if (!ASSERT_OK_PTR(link, "bpf_program__attach_uprobe_multi"))
+		goto cleanup;
+
+	check_attach_notrigger(skel, uprobe_test, 4);
+
+	bpf_link__destroy(link);
+	if (!check_detach(uprobe_test, tramp))
+		goto cleanup;
+
+	uprobe_test();
+	ASSERT_EQ(skel->bss->executed, 4, "executed_no_probe");
+
+	/* reattach with triggering optimization */
+	link = bpf_program__attach_uprobe_multi(skel->progs.test_uprobe_session,
+				0, "/proc/self/exe", NULL, &opts);
+	if (!ASSERT_OK_PTR(link, "bpf_program__attach_uprobe_multi"))
+		goto cleanup;
+
+	check(skel, link, uprobe_test, uprobe_test, 8);
 
 cleanup:
 	uprobe_syscall_executed__destroy(skel);
@@ -569,7 +654,7 @@ static void test_uprobe_usdt(void)
 {
 	struct uprobe_syscall_executed *skel;
 	struct bpf_link *link;
-	void *addr;
+	void *addr, *tramp;
 
 	errno = 0;
 	addr = find_nop10(usdt_test);
@@ -588,7 +673,32 @@ static void test_uprobe_usdt(void)
 	if (!ASSERT_OK_PTR(link, "bpf_program__attach_usdt"))
 		goto cleanup;
 
-	check(skel, link, usdt_test, addr, 2);
+	tramp = check(skel, link, usdt_test, addr, 2);
+
+	/* reattach and detach without triggering optimization */
+	link = bpf_program__attach_usdt(skel->progs.test_usdt,
+				-1 /* all PIDs */, "/proc/self/exe",
+				"optimized_uprobe", "usdt", NULL);
+	if (!ASSERT_OK_PTR(link, "bpf_program__attach_usdt"))
+		goto cleanup;
+
+	check_attach_notrigger(skel, addr, 2);
+
+	bpf_link__destroy(link);
+	if (!check_detach(addr, tramp))
+		goto cleanup;
+
+	usdt_test();
+	ASSERT_EQ(skel->bss->executed, 2, "executed_no_probe");
+
+	/* reattach with triggering optimization */
+	link = bpf_program__attach_usdt(skel->progs.test_usdt,
+				-1 /* all PIDs */, "/proc/self/exe",
+				"optimized_uprobe", "usdt", NULL);
+	if (!ASSERT_OK_PTR(link, "bpf_program__attach_usdt"))
+		goto cleanup;
+
+	check(skel, link, usdt_test, addr, 4);
 
 cleanup:
 	uprobe_syscall_executed__destroy(skel);
author reviewer
#36 lore raw

PATCH v6 12/13 selftests/bpf: Add tests for uprobe nop10 red zone clobbering

In reply to Jiri Olsa

From: Andrii Nakryiko <[email protected]>

The uprobe nop5 optimization used to replace a 5-byte NOP with a 5-byte CALL to a trampoline. The CALL pushes a return address onto the stack at [rsp-8], clobbering whatever was stored there.

On x86-64, the red zone is the 128 bytes below rsp that user code may use for temporary storage without adjusting rsp. Compilers can place USDT argument operands there, generating specs like "8@-8(%rbp)" when rbp == rsp. With the CALL-based optimization, the return address overwrites that argument before the BPF-side USDT argument fetch runs.

Add two tests for this case. The uprobe_syscall subtest stores known values at -8(%rsp), -16(%rsp), and -24(%rsp), executes an optimized nop10 uprobe, and verifies the red-zone data is still intact. The USDT subtest triggers a probe in a function where the compiler places three USDT operands in the red zone and verifies that all 10 optimized invocations deliver the expected argument values to BPF.

On an unfixed kernel, the first hit goes through the INT3 path and later hits use the optimized CALL path, so the red-zone checks fail after optimization.

---
 .../selftests/bpf/prog_tests/uprobe_syscall.c | 77 +++++++++++++++++++
 tools/testing/selftests/bpf/prog_tests/usdt.c | 49 ++++++++++++
 tools/testing/selftests/bpf/progs/test_usdt.c | 25 ++++++
 tools/testing/selftests/bpf/usdt_2.c          | 13 ++++
 4 files changed, 164 insertions(+)
tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c +77 -0
index 7711018f8acd..ff07e5df9a65 100644
@@ -357,6 +357,50 @@ __nocf_check __weak void usdt_test(void)
 	USDT(optimized_uprobe, usdt);
 }
 
+/*
+ * Assembly-level red zone clobbering test. Stores known values in the
+ * red zone (below RSP), executes a nop10 (uprobe site), and checks that
+ * the values survived. Returns 0 if intact, 1 if clobbered.
+ *
+ * The nop5 optimization used CALL (which pushes a return address to
+ * [rsp-8]), the value at -8(%rsp) was overwritten. The nop10 optimization
+ * should escape that by moving stackpointer below the redzone before
+ * doing the CALL.
+ *
+ * Align the code at 64 bytes, to make sure nop10 is not on page boundary.
+ */
+__attribute__((aligned(64)))
+__nocf_check __weak __naked unsigned long uprobe_red_zone_test(void)
+{
+	asm volatile (
+		"movabs $0x1111111111111111, %%rax\n"
+		"movq   %%rax, -8(%%rsp)\n"
+		"movabs $0x2222222222222222, %%rax\n"
+		"movq   %%rax, -16(%%rsp)\n"
+		"movabs $0x3333333333333333, %%rax\n"
+		"movq   %%rax, -24(%%rsp)\n"
+
+		".byte 0x66, 0x2e, 0x0f, 0x1f, 0x84, 0x00, 0x00, 0x00, 0x00, 0x00\n" /* nop10: uprobe site */
+
+		"movabs $0x1111111111111111, %%rax\n"
+		"cmpq   %%rax, -8(%%rsp)\n"
+		"jne    1f\n"
+		"movabs $0x2222222222222222, %%rax\n"
+		"cmpq   %%rax, -16(%%rsp)\n"
+		"jne    1f\n"
+		"movabs $0x3333333333333333, %%rax\n"
+		"cmpq   %%rax, -24(%%rsp)\n"
+		"jne    1f\n"
+
+		"xorl   %%eax, %%eax\n"
+		"retq\n"
+		"1:\n"
+		"movl   $1, %%eax\n"
+		"retq\n"
+		::: "rax", "memory"
+	);
+}
+
 static int find_uprobes_trampoline(void *tramp_addr)
 {
 	void *start, *end;
@@ -871,6 +915,37 @@ static void test_uprobe_race(void)
 #define __NR_uprobe 336
 #endif
 
+static void test_uprobe_red_zone(void)
+{
+	struct uprobe_syscall_executed *skel;
+	struct bpf_link *link;
+	void *nop10_addr;
+	size_t offset;
+	int i;
+
+	nop10_addr = find_nop10(uprobe_red_zone_test);
+	if (!ASSERT_NEQ(nop10_addr, NULL, "find_nop10"))
+		return;
+
+	skel = uprobe_syscall_executed__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open_and_load"))
+		return;
+
+	offset = get_uprobe_offset(nop10_addr);
+	link = bpf_program__attach_uprobe_opts(skel->progs.test_uprobe,
+			0, "/proc/self/exe", offset, NULL);
+	if (!ASSERT_OK_PTR(link, "attach_uprobe"))
+		goto cleanup;
+
+	for (i = 0; i < 10; i++)
+		ASSERT_EQ(uprobe_red_zone_test(), 0, "red_zone_intact");
+
+	bpf_link__destroy(link);
+
+cleanup:
+	uprobe_syscall_executed__destroy(skel);
+}
+
 static void test_uprobe_error(void)
 {
 	long err = syscall(__NR_uprobe);
@@ -897,6 +972,8 @@ static void __test_uprobe_syscall(void)
 		test_uprobe_usdt();
 	if (test__start_subtest("uprobe_race"))
 		test_uprobe_race();
+	if (test__start_subtest("uprobe_red_zone"))
+		test_uprobe_red_zone();
 	if (test__start_subtest("uprobe_error"))
 		test_uprobe_error();
 	if (test__start_subtest("uprobe_regs_equal"))
tools/testing/selftests/bpf/prog_tests/usdt.c +49 -0

67 lines not on this page · raw message

tools/testing/selftests/bpf/progs/test_usdt.c +25 -0
index f00cb52874e0..0ee78fb050a1 100644
@@ -149,5 +149,30 @@ int usdt_executed(struct pt_regs *ctx)
 		executed++;
 	return 0;
 }
+
+int arg_total;
+int arg_bad;
+long arg_last[3];
+long expected_arg[3];
+int expected_pid;
+
+SEC("usdt")
+int BPF_USDT(usdt_check_arg, long arg1, long arg2, long arg3)
+{
+	if (expected_pid != (bpf_get_current_pid_tgid() >> 32))
+		return 0;
+
+	__sync_fetch_and_add(&arg_total, 1);
+	arg_last[0] = arg1;
+	arg_last[1] = arg2;
+	arg_last[2] = arg3;
+
+	if (arg1 != expected_arg[0] ||
+	    arg2 != expected_arg[1] ||
+	    arg3 != expected_arg[2])
+		__sync_fetch_and_add(&arg_bad, 1);
+
+	return 0;
+}
 #endif
 char _license[] SEC("license") = "GPL";
tools/testing/selftests/bpf/usdt_2.c +13 -0
index b359b389f6c0..5e38f8605b02 100644
@@ -13,4 +13,17 @@ void usdt_2(void)
 	USDT(optimized_attach, usdt_2);
 }
 
+static volatile unsigned long usdt_red_zone_arg1 = 0xDEADBEEF;
+static volatile unsigned long usdt_red_zone_arg2 = 0xCAFEBABE;
+static volatile unsigned long usdt_red_zone_arg3 = 0xFEEDFACE;
+
+void __attribute__((noinline)) usdt_red_zone_trigger(void)
+{
+	unsigned long a1 = usdt_red_zone_arg1;
+	unsigned long a2 = usdt_red_zone_arg2;
+	unsigned long a3 = usdt_red_zone_arg3;
+
+	USDT(optimized_attach, usdt_red_zone, a1, a2, a3);
+}
+
 #endif
Signature · 1 line
2.54.0
#37 lore raw

[tip: perf/core] selftests/bpf: Add tests for uprobe nop10 red zone clobbering

The following commit has been merged into the perf/core branch of tip:

The following commit has been merged into the perf/core branch of tip:

Commit-ID:     b8fe67dbac02714957f3ac9aac70973947433edd
Gitweb:        https://git.kernel.org/tip/b8fe67dbac02714957f3ac9aac70973947433edd
Author:        Andrii Nakryiko <[email protected]>
AuthorDate:    Fri, 03 Jul 2026 13:49:16 +02:00
Committer:     Peter Zijlstra <[email protected]>
CommitterDate: Fri, 03 Jul 2026 16:30:38 +02:00

selftests/bpf: Add tests for uprobe nop10 red zone clobbering

The uprobe nop5 optimization used to replace a 5-byte NOP with a 5-byte CALL to a trampoline. The CALL pushes a return address onto the stack at [rsp-8], clobbering whatever was stored there.

On x86-64, the red zone is the 128 bytes below rsp that user code may use for temporary storage without adjusting rsp. Compilers can place USDT argument operands there, generating specs like "8@-8(%rbp)" when rbp == rsp. With the CALL-based optimization, the return address overwrites that argument before the BPF-side USDT argument fetch runs.

Add two tests for this case. The uprobe_syscall subtest stores known values at -8(%rsp), -16(%rsp), and -24(%rsp), executes an optimized nop10 uprobe, and verifies the red-zone data is still intact. The USDT subtest triggers a probe in a function where the compiler places three USDT operands in the red zone and verifies that all 10 optimized invocations deliver the expected argument values to BPF.

On an unfixed kernel, the first hit goes through the INT3 path and later hits use the optimized CALL path, so the red-zone checks fail after optimization.

---
 tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c | 77 ++++++++-
 tools/testing/selftests/bpf/prog_tests/usdt.c           | 49 +++++-
 tools/testing/selftests/bpf/progs/test_usdt.c           | 25 +++-
 tools/testing/selftests/bpf/usdt_2.c                    | 13 +-
 4 files changed, 164 insertions(+)
tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c +77 -0
index 7711018..ff07e5d 100644
@@ -357,6 +357,50 @@ __nocf_check __weak void usdt_test(void)
 	USDT(optimized_uprobe, usdt);
 }
 
+/*
+ * Assembly-level red zone clobbering test. Stores known values in the
+ * red zone (below RSP), executes a nop10 (uprobe site), and checks that
+ * the values survived. Returns 0 if intact, 1 if clobbered.
+ *
+ * The nop5 optimization used CALL (which pushes a return address to
+ * [rsp-8]), the value at -8(%rsp) was overwritten. The nop10 optimization
+ * should escape that by moving stackpointer below the redzone before
+ * doing the CALL.
+ *
+ * Align the code at 64 bytes, to make sure nop10 is not on page boundary.
+ */
+__attribute__((aligned(64)))
+__nocf_check __weak __naked unsigned long uprobe_red_zone_test(void)
+{
+	asm volatile (
+		"movabs $0x1111111111111111, %%rax\n"
+		"movq   %%rax, -8(%%rsp)\n"
+		"movabs $0x2222222222222222, %%rax\n"
+		"movq   %%rax, -16(%%rsp)\n"
+		"movabs $0x3333333333333333, %%rax\n"
+		"movq   %%rax, -24(%%rsp)\n"
+
+		".byte 0x66, 0x2e, 0x0f, 0x1f, 0x84, 0x00, 0x00, 0x00, 0x00, 0x00\n" /* nop10: uprobe site */
+
+		"movabs $0x1111111111111111, %%rax\n"
+		"cmpq   %%rax, -8(%%rsp)\n"
+		"jne    1f\n"
+		"movabs $0x2222222222222222, %%rax\n"
+		"cmpq   %%rax, -16(%%rsp)\n"
+		"jne    1f\n"
+		"movabs $0x3333333333333333, %%rax\n"
+		"cmpq   %%rax, -24(%%rsp)\n"
+		"jne    1f\n"
+
+		"xorl   %%eax, %%eax\n"
+		"retq\n"
+		"1:\n"
+		"movl   $1, %%eax\n"
+		"retq\n"
+		::: "rax", "memory"
+	);
+}
+
 static int find_uprobes_trampoline(void *tramp_addr)
 {
 	void *start, *end;
@@ -871,6 +915,37 @@ cleanup:
 #define __NR_uprobe 336
 #endif
 
+static void test_uprobe_red_zone(void)
+{
+	struct uprobe_syscall_executed *skel;
+	struct bpf_link *link;
+	void *nop10_addr;
+	size_t offset;
+	int i;
+
+	nop10_addr = find_nop10(uprobe_red_zone_test);
+	if (!ASSERT_NEQ(nop10_addr, NULL, "find_nop10"))
+		return;
+
+	skel = uprobe_syscall_executed__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open_and_load"))
+		return;
+
+	offset = get_uprobe_offset(nop10_addr);
+	link = bpf_program__attach_uprobe_opts(skel->progs.test_uprobe,
+			0, "/proc/self/exe", offset, NULL);
+	if (!ASSERT_OK_PTR(link, "attach_uprobe"))
+		goto cleanup;
+
+	for (i = 0; i < 10; i++)
+		ASSERT_EQ(uprobe_red_zone_test(), 0, "red_zone_intact");
+
+	bpf_link__destroy(link);
+
+cleanup:
+	uprobe_syscall_executed__destroy(skel);
+}
+
 static void test_uprobe_error(void)
 {
 	long err = syscall(__NR_uprobe);
@@ -897,6 +972,8 @@ static void __test_uprobe_syscall(void)
 		test_uprobe_usdt();
 	if (test__start_subtest("uprobe_race"))
 		test_uprobe_race();
+	if (test__start_subtest("uprobe_red_zone"))
+		test_uprobe_red_zone();
 	if (test__start_subtest("uprobe_error"))
 		test_uprobe_error();
 	if (test__start_subtest("uprobe_regs_equal"))
tools/testing/selftests/bpf/prog_tests/usdt.c +49 -0

67 lines not on this page · raw message

tools/testing/selftests/bpf/progs/test_usdt.c +25 -0
index f00cb52..0ee78fb 100644
@@ -149,5 +149,30 @@ int usdt_executed(struct pt_regs *ctx)
 		executed++;
 	return 0;
 }
+
+int arg_total;
+int arg_bad;
+long arg_last[3];
+long expected_arg[3];
+int expected_pid;
+
+SEC("usdt")
+int BPF_USDT(usdt_check_arg, long arg1, long arg2, long arg3)
+{
+	if (expected_pid != (bpf_get_current_pid_tgid() >> 32))
+		return 0;
+
+	__sync_fetch_and_add(&arg_total, 1);
+	arg_last[0] = arg1;
+	arg_last[1] = arg2;
+	arg_last[2] = arg3;
+
+	if (arg1 != expected_arg[0] ||
+	    arg2 != expected_arg[1] ||
+	    arg3 != expected_arg[2])
+		__sync_fetch_and_add(&arg_bad, 1);
+
+	return 0;
+}
 #endif
 char _license[] SEC("license") = "GPL";
tools/testing/selftests/bpf/usdt_2.c +13 -0
index b359b38..5e38f86 100644
@@ -13,4 +13,17 @@ void usdt_2(void)
 	USDT(optimized_attach, usdt_2);
 }
 
+static volatile unsigned long usdt_red_zone_arg1 = 0xDEADBEEF;
+static volatile unsigned long usdt_red_zone_arg2 = 0xCAFEBABE;
+static volatile unsigned long usdt_red_zone_arg3 = 0xFEEDFACE;
+
+void __attribute__((noinline)) usdt_red_zone_trigger(void)
+{
+	unsigned long a1 = usdt_red_zone_arg1;
+	unsigned long a2 = usdt_red_zone_arg2;
+	unsigned long a3 = usdt_red_zone_arg3;
+
+	USDT(optimized_attach, usdt_red_zone, a1, a2, a3);
+}
+
 #endif
#38 lore raw

[tip: perf/core] selftests/bpf: Add tests for uprobe nop10 red zone clobbering

In reply to Jiri Olsa
The following commit has been merged into the perf/core branch of tip:

The following commit has been merged into the perf/core branch of tip:

Commit-ID:     eccf368562bb2f79d2cded2030cfdce91afc9080
Gitweb:        https://git.kernel.org/tip/eccf368562bb2f79d2cded2030cfdce91afc9080
Author:        Andrii Nakryiko <[email protected]>
AuthorDate:    Fri, 03 Jul 2026 13:49:16 +02:00
Committer:     Ingo Molnar <[email protected]>
CommitterDate: Sat, 04 Jul 2026 10:57:27 +02:00

selftests/bpf: Add tests for uprobe nop10 red zone clobbering

The uprobe nop5 optimization used to replace a 5-byte NOP with a 5-byte CALL to a trampoline. The CALL pushes a return address onto the stack at [rsp-8], clobbering whatever was stored there.

On x86-64, the red zone is the 128 bytes below rsp that user code may use for temporary storage without adjusting rsp. Compilers can place USDT argument operands there, generating specs like "8@-8(%rbp)" when rbp == rsp. With the CALL-based optimization, the return address overwrites that argument before the BPF-side USDT argument fetch runs.

Add two tests for this case. The uprobe_syscall subtest stores known values at -8(%rsp), -16(%rsp), and -24(%rsp), executes an optimized nop10 uprobe, and verifies the red-zone data is still intact. The USDT subtest triggers a probe in a function where the compiler places three USDT operands in the red zone and verifies that all 10 optimized invocations deliver the expected argument values to BPF.

On an unfixed kernel, the first hit goes through the INT3 path and later hits use the optimized CALL path, so the red-zone checks fail after optimization.

---
 tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c | 77 ++++++++-
 tools/testing/selftests/bpf/prog_tests/usdt.c           | 49 +++++-
 tools/testing/selftests/bpf/progs/test_usdt.c           | 25 +++-
 tools/testing/selftests/bpf/usdt_2.c                    | 13 +-
 4 files changed, 164 insertions(+)
tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c +77 -0
index 7711018..ff07e5d 100644
@@ -357,6 +357,50 @@ __nocf_check __weak void usdt_test(void)
 	USDT(optimized_uprobe, usdt);
 }
 
+/*
+ * Assembly-level red zone clobbering test. Stores known values in the
+ * red zone (below RSP), executes a nop10 (uprobe site), and checks that
+ * the values survived. Returns 0 if intact, 1 if clobbered.
+ *
+ * The nop5 optimization used CALL (which pushes a return address to
+ * [rsp-8]), the value at -8(%rsp) was overwritten. The nop10 optimization
+ * should escape that by moving stackpointer below the redzone before
+ * doing the CALL.
+ *
+ * Align the code at 64 bytes, to make sure nop10 is not on page boundary.
+ */
+__attribute__((aligned(64)))
+__nocf_check __weak __naked unsigned long uprobe_red_zone_test(void)
+{
+	asm volatile (
+		"movabs $0x1111111111111111, %%rax\n"
+		"movq   %%rax, -8(%%rsp)\n"
+		"movabs $0x2222222222222222, %%rax\n"
+		"movq   %%rax, -16(%%rsp)\n"
+		"movabs $0x3333333333333333, %%rax\n"
+		"movq   %%rax, -24(%%rsp)\n"
+
+		".byte 0x66, 0x2e, 0x0f, 0x1f, 0x84, 0x00, 0x00, 0x00, 0x00, 0x00\n" /* nop10: uprobe site */
+
+		"movabs $0x1111111111111111, %%rax\n"
+		"cmpq   %%rax, -8(%%rsp)\n"
+		"jne    1f\n"
+		"movabs $0x2222222222222222, %%rax\n"
+		"cmpq   %%rax, -16(%%rsp)\n"
+		"jne    1f\n"
+		"movabs $0x3333333333333333, %%rax\n"
+		"cmpq   %%rax, -24(%%rsp)\n"
+		"jne    1f\n"
+
+		"xorl   %%eax, %%eax\n"
+		"retq\n"
+		"1:\n"
+		"movl   $1, %%eax\n"
+		"retq\n"
+		::: "rax", "memory"
+	);
+}
+
 static int find_uprobes_trampoline(void *tramp_addr)
 {
 	void *start, *end;
@@ -871,6 +915,37 @@ cleanup:
 #define __NR_uprobe 336
 #endif
 
+static void test_uprobe_red_zone(void)
+{
+	struct uprobe_syscall_executed *skel;
+	struct bpf_link *link;
+	void *nop10_addr;
+	size_t offset;
+	int i;
+
+	nop10_addr = find_nop10(uprobe_red_zone_test);
+	if (!ASSERT_NEQ(nop10_addr, NULL, "find_nop10"))
+		return;
+
+	skel = uprobe_syscall_executed__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open_and_load"))
+		return;
+
+	offset = get_uprobe_offset(nop10_addr);
+	link = bpf_program__attach_uprobe_opts(skel->progs.test_uprobe,
+			0, "/proc/self/exe", offset, NULL);
+	if (!ASSERT_OK_PTR(link, "attach_uprobe"))
+		goto cleanup;
+
+	for (i = 0; i < 10; i++)
+		ASSERT_EQ(uprobe_red_zone_test(), 0, "red_zone_intact");
+
+	bpf_link__destroy(link);
+
+cleanup:
+	uprobe_syscall_executed__destroy(skel);
+}
+
 static void test_uprobe_error(void)
 {
 	long err = syscall(__NR_uprobe);
@@ -897,6 +972,8 @@ static void __test_uprobe_syscall(void)
 		test_uprobe_usdt();
 	if (test__start_subtest("uprobe_race"))
 		test_uprobe_race();
+	if (test__start_subtest("uprobe_red_zone"))
+		test_uprobe_red_zone();
 	if (test__start_subtest("uprobe_error"))
 		test_uprobe_error();
 	if (test__start_subtest("uprobe_regs_equal"))
tools/testing/selftests/bpf/prog_tests/usdt.c +49 -0

67 lines not on this page · raw message

tools/testing/selftests/bpf/progs/test_usdt.c +25 -0
index f00cb52..0ee78fb 100644
@@ -149,5 +149,30 @@ int usdt_executed(struct pt_regs *ctx)
 		executed++;
 	return 0;
 }
+
+int arg_total;
+int arg_bad;
+long arg_last[3];
+long expected_arg[3];
+int expected_pid;
+
+SEC("usdt")
+int BPF_USDT(usdt_check_arg, long arg1, long arg2, long arg3)
+{
+	if (expected_pid != (bpf_get_current_pid_tgid() >> 32))
+		return 0;
+
+	__sync_fetch_and_add(&arg_total, 1);
+	arg_last[0] = arg1;
+	arg_last[1] = arg2;
+	arg_last[2] = arg3;
+
+	if (arg1 != expected_arg[0] ||
+	    arg2 != expected_arg[1] ||
+	    arg3 != expected_arg[2])
+		__sync_fetch_and_add(&arg_bad, 1);
+
+	return 0;
+}
 #endif
 char _license[] SEC("license") = "GPL";
tools/testing/selftests/bpf/usdt_2.c +13 -0
index b359b38..5e38f86 100644
@@ -13,4 +13,17 @@ void usdt_2(void)
 	USDT(optimized_attach, usdt_2);
 }
 
+static volatile unsigned long usdt_red_zone_arg1 = 0xDEADBEEF;
+static volatile unsigned long usdt_red_zone_arg2 = 0xCAFEBABE;
+static volatile unsigned long usdt_red_zone_arg3 = 0xFEEDFACE;
+
+void __attribute__((noinline)) usdt_red_zone_trigger(void)
+{
+	unsigned long a1 = usdt_red_zone_arg1;
+	unsigned long a2 = usdt_red_zone_arg2;
+	unsigned long a3 = usdt_red_zone_arg3;
+
+	USDT(optimized_attach, usdt_red_zone, a1, a2, a3);
+}
+
 #endif
author reviewer
#39 lore raw

PATCH v6 13/13 selftests/bpf: Add tests for forked/cloned optimized uprobes

In reply to Jiri Olsa

Adding tests for forked/cloned optimized uprobes and make sure the child can properly execute optimized probe for both fork (dups mm) and clone with CLONE_VM.

---
 .../selftests/bpf/prog_tests/uprobe_syscall.c | 88 +++++++++++++++++++
 1 file changed, 88 insertions(+)
tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c +88 -0
index ff07e5df9a65..e193206fc5d2 100644
@@ -4,6 +4,8 @@
 
 #ifdef __x86_64__
 
+#define _GNU_SOURCE
+#include <sched.h>
 #include <unistd.h>
 #include <asm/ptrace.h>
 #include <linux/compiler.h>
@@ -13,6 +15,7 @@
 #include <sys/syscall.h>
 #include <sys/prctl.h>
 #include <asm/prctl.h>
+#include <stdnoreturn.h>
 #include "uprobe_syscall.skel.h"
 #include "uprobe_syscall_executed.skel.h"
 #include "bpf/libbpf_internal.h"
@@ -954,6 +957,87 @@ static void test_uprobe_error(void)
 	ASSERT_EQ(errno, EPROTO, "errno");
 }
 
+__attribute__((aligned(16)))
+__nocf_check __weak __naked void uprobe_fork_test(void)
+{
+	asm volatile (
+		".byte 0x66, 0x2e, 0x0f, 0x1f, 0x84, 0x00, 0x00, 0x00, 0x00, 0x00\n" /* nop10 */
+		"ret\n"
+	);
+}
+
+static noreturn int child_func(void *arg)
+{
+	struct uprobe_syscall_executed *skel = arg;
+
+	/* Make sure the child's probe is still there and optimized.. */
+	if (memcmp(uprobe_fork_test, lea_rsp, sizeof(lea_rsp)))
+		_exit(1);
+
+	skel->bss->pid = getpid();
+
+	/* .. and it executes properly. */
+	uprobe_fork_test();
+
+	if (skel->bss->executed != 3)
+		_exit(2);
+
+	_exit(0);
+}
+
+static void test_uprobe_fork_optimized(bool clone_vm)
+{
+	struct uprobe_syscall_executed *skel = NULL;
+	unsigned long offset;
+	int pid, status, err;
+	char stack[65535];
+
+	offset = get_uprobe_offset(&uprobe_fork_test);
+	if (!ASSERT_GE(offset, 0, "get_uprobe_offset"))
+		return;
+
+	skel = uprobe_syscall_executed__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open_and_load"))
+		goto cleanup;
+
+	skel->links.test_uprobe = bpf_program__attach_uprobe_opts(skel->progs.test_uprobe,
+					-1, "/proc/self/exe", offset, NULL);
+	if (!ASSERT_OK_PTR(skel->links.test_uprobe, "attach_uprobe"))
+		goto cleanup;
+
+	skel->bss->pid = getpid();
+
+	/* Trigger optimization of uprobe in uprobe_fork_test.  */
+	uprobe_fork_test();
+	uprobe_fork_test();
+
+	/* Make sure it got optimied. */
+	if (!ASSERT_OK(memcmp(uprobe_fork_test, lea_rsp, sizeof(lea_rsp)), "optimized"))
+		goto cleanup;
+
+	if (clone_vm) {
+		pid = clone(child_func, stack + sizeof(stack), CLONE_VM|SIGCHLD, skel);
+		if (!ASSERT_GT(pid, 0, "clone"))
+			goto cleanup;
+	} else {
+		pid = fork();
+		if (!ASSERT_GE(pid, 0, "fork"))
+			goto cleanup;
+		if (pid == 0)
+			child_func(skel);
+	}
+
+	/* Wait for the child and verify it exited properly with 0. */
+	err = waitpid(pid, &status, 0);
+	if (ASSERT_EQ(err, pid, "waitpid")) {
+		ASSERT_EQ(WIFEXITED(status), 1, "child_exited");
+		ASSERT_EQ(WEXITSTATUS(status), 0, "child_exit_code");
+	}
+
+cleanup:
+	uprobe_syscall_executed__destroy(skel);
+}
+
 static void __test_uprobe_syscall(void)
 {
 	if (test__start_subtest("uretprobe_regs_equal"))
@@ -974,6 +1058,10 @@ static void __test_uprobe_syscall(void)
 		test_uprobe_race();
 	if (test__start_subtest("uprobe_red_zone"))
 		test_uprobe_red_zone();
+	if (test__start_subtest("uprobe_optimized_fork"))
+		test_uprobe_fork_optimized(false);
+	if (test__start_subtest("uprobe_optimized_clone_vm"))
+		test_uprobe_fork_optimized(true);
 	if (test__start_subtest("uprobe_error"))
 		test_uprobe_error();
 	if (test__start_subtest("uprobe_regs_equal"))
Signature · 1 line
2.54.0
merge bot Applied
#40 lore raw

[tip: perf/core] selftests/bpf: Add tests for forked/cloned optimized uprobes

The following commit has been merged into the perf/core branch of tip:

The following commit has been merged into the perf/core branch of tip:

Commit-ID:     e33df6e877d49ce127674ae0fe6b4d9ecc90d845
Gitweb:        https://git.kernel.org/tip/e33df6e877d49ce127674ae0fe6b4d9ecc90d845
Author:        Jiri Olsa <[email protected]>
AuthorDate:    Fri, 03 Jul 2026 13:49:17 +02:00
Committer:     Peter Zijlstra <[email protected]>
CommitterDate: Fri, 03 Jul 2026 16:30:38 +02:00

selftests/bpf: Add tests for forked/cloned optimized uprobes

Adding tests for forked/cloned optimized uprobes and make sure the child can properly execute optimized probe for both fork (dups mm) and clone with CLONE_VM.

---
 tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c | 88 ++++++++-
 1 file changed, 88 insertions(+)
tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c +88 -0
index ff07e5d..e193206 100644
@@ -4,6 +4,8 @@
 
 #ifdef __x86_64__
 
+#define _GNU_SOURCE
+#include <sched.h>
 #include <unistd.h>
 #include <asm/ptrace.h>
 #include <linux/compiler.h>
@@ -13,6 +15,7 @@
 #include <sys/syscall.h>
 #include <sys/prctl.h>
 #include <asm/prctl.h>
+#include <stdnoreturn.h>
 #include "uprobe_syscall.skel.h"
 #include "uprobe_syscall_executed.skel.h"
 #include "bpf/libbpf_internal.h"
@@ -954,6 +957,87 @@ static void test_uprobe_error(void)
 	ASSERT_EQ(errno, EPROTO, "errno");
 }
 
+__attribute__((aligned(16)))
+__nocf_check __weak __naked void uprobe_fork_test(void)
+{
+	asm volatile (
+		".byte 0x66, 0x2e, 0x0f, 0x1f, 0x84, 0x00, 0x00, 0x00, 0x00, 0x00\n" /* nop10 */
+		"ret\n"
+	);
+}
+
+static noreturn int child_func(void *arg)
+{
+	struct uprobe_syscall_executed *skel = arg;
+
+	/* Make sure the child's probe is still there and optimized.. */
+	if (memcmp(uprobe_fork_test, lea_rsp, sizeof(lea_rsp)))
+		_exit(1);
+
+	skel->bss->pid = getpid();
+
+	/* .. and it executes properly. */
+	uprobe_fork_test();
+
+	if (skel->bss->executed != 3)
+		_exit(2);
+
+	_exit(0);
+}
+
+static void test_uprobe_fork_optimized(bool clone_vm)
+{
+	struct uprobe_syscall_executed *skel = NULL;
+	unsigned long offset;
+	int pid, status, err;
+	char stack[65535];
+
+	offset = get_uprobe_offset(&uprobe_fork_test);
+	if (!ASSERT_GE(offset, 0, "get_uprobe_offset"))
+		return;
+
+	skel = uprobe_syscall_executed__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open_and_load"))
+		goto cleanup;
+
+	skel->links.test_uprobe = bpf_program__attach_uprobe_opts(skel->progs.test_uprobe,
+					-1, "/proc/self/exe", offset, NULL);
+	if (!ASSERT_OK_PTR(skel->links.test_uprobe, "attach_uprobe"))
+		goto cleanup;
+
+	skel->bss->pid = getpid();
+
+	/* Trigger optimization of uprobe in uprobe_fork_test.  */
+	uprobe_fork_test();
+	uprobe_fork_test();
+
+	/* Make sure it got optimied. */
+	if (!ASSERT_OK(memcmp(uprobe_fork_test, lea_rsp, sizeof(lea_rsp)), "optimized"))
+		goto cleanup;
+
+	if (clone_vm) {
+		pid = clone(child_func, stack + sizeof(stack), CLONE_VM|SIGCHLD, skel);
+		if (!ASSERT_GT(pid, 0, "clone"))
+			goto cleanup;
+	} else {
+		pid = fork();
+		if (!ASSERT_GE(pid, 0, "fork"))
+			goto cleanup;
+		if (pid == 0)
+			child_func(skel);
+	}
+
+	/* Wait for the child and verify it exited properly with 0. */
+	err = waitpid(pid, &status, 0);
+	if (ASSERT_EQ(err, pid, "waitpid")) {
+		ASSERT_EQ(WIFEXITED(status), 1, "child_exited");
+		ASSERT_EQ(WEXITSTATUS(status), 0, "child_exit_code");
+	}
+
+cleanup:
+	uprobe_syscall_executed__destroy(skel);
+}
+
 static void __test_uprobe_syscall(void)
 {
 	if (test__start_subtest("uretprobe_regs_equal"))
@@ -974,6 +1058,10 @@ static void __test_uprobe_syscall(void)
 		test_uprobe_race();
 	if (test__start_subtest("uprobe_red_zone"))
 		test_uprobe_red_zone();
+	if (test__start_subtest("uprobe_optimized_fork"))
+		test_uprobe_fork_optimized(false);
+	if (test__start_subtest("uprobe_optimized_clone_vm"))
+		test_uprobe_fork_optimized(true);
 	if (test__start_subtest("uprobe_error"))
 		test_uprobe_error();
 	if (test__start_subtest("uprobe_regs_equal"))
merge bot Applied
#41 lore raw

[tip: perf/core] selftests/bpf: Add tests for forked/cloned optimized uprobes

In reply to Jiri Olsa
The following commit has been merged into the perf/core branch of tip:

The following commit has been merged into the perf/core branch of tip:

Commit-ID:     d7ebbae57de3f37ff42b6f67f40cc67827b23c4f
Gitweb:        https://git.kernel.org/tip/d7ebbae57de3f37ff42b6f67f40cc67827b23c4f
Author:        Jiri Olsa <[email protected]>
AuthorDate:    Fri, 03 Jul 2026 13:49:17 +02:00
Committer:     Ingo Molnar <[email protected]>
CommitterDate: Sat, 04 Jul 2026 10:59:06 +02:00

selftests/bpf: Add tests for forked/cloned optimized uprobes

Adding tests for forked/cloned optimized uprobes and make sure the child can properly execute optimized probe for both fork (dups mm) and clone with CLONE_VM.

---
 tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c | 88 ++++++++-
 1 file changed, 88 insertions(+)
tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c +88 -0
index ff07e5d..e193206 100644
@@ -4,6 +4,8 @@
 
 #ifdef __x86_64__
 
+#define _GNU_SOURCE
+#include <sched.h>
 #include <unistd.h>
 #include <asm/ptrace.h>
 #include <linux/compiler.h>
@@ -13,6 +15,7 @@
 #include <sys/syscall.h>
 #include <sys/prctl.h>
 #include <asm/prctl.h>
+#include <stdnoreturn.h>
 #include "uprobe_syscall.skel.h"
 #include "uprobe_syscall_executed.skel.h"
 #include "bpf/libbpf_internal.h"
@@ -954,6 +957,87 @@ static void test_uprobe_error(void)
 	ASSERT_EQ(errno, EPROTO, "errno");
 }
 
+__attribute__((aligned(16)))
+__nocf_check __weak __naked void uprobe_fork_test(void)
+{
+	asm volatile (
+		".byte 0x66, 0x2e, 0x0f, 0x1f, 0x84, 0x00, 0x00, 0x00, 0x00, 0x00\n" /* nop10 */
+		"ret\n"
+	);
+}
+
+static noreturn int child_func(void *arg)
+{
+	struct uprobe_syscall_executed *skel = arg;
+
+	/* Make sure the child's probe is still there and optimized.. */
+	if (memcmp(uprobe_fork_test, lea_rsp, sizeof(lea_rsp)))
+		_exit(1);
+
+	skel->bss->pid = getpid();
+
+	/* .. and it executes properly. */
+	uprobe_fork_test();
+
+	if (skel->bss->executed != 3)
+		_exit(2);
+
+	_exit(0);
+}
+
+static void test_uprobe_fork_optimized(bool clone_vm)
+{
+	struct uprobe_syscall_executed *skel = NULL;
+	unsigned long offset;
+	int pid, status, err;
+	char stack[65535];
+
+	offset = get_uprobe_offset(&uprobe_fork_test);
+	if (!ASSERT_GE(offset, 0, "get_uprobe_offset"))
+		return;
+
+	skel = uprobe_syscall_executed__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open_and_load"))
+		goto cleanup;
+
+	skel->links.test_uprobe = bpf_program__attach_uprobe_opts(skel->progs.test_uprobe,
+					-1, "/proc/self/exe", offset, NULL);
+	if (!ASSERT_OK_PTR(skel->links.test_uprobe, "attach_uprobe"))
+		goto cleanup;
+
+	skel->bss->pid = getpid();
+
+	/* Trigger optimization of uprobe in uprobe_fork_test.  */
+	uprobe_fork_test();
+	uprobe_fork_test();
+
+	/* Make sure it got optimied. */
+	if (!ASSERT_OK(memcmp(uprobe_fork_test, lea_rsp, sizeof(lea_rsp)), "optimized"))
+		goto cleanup;
+
+	if (clone_vm) {
+		pid = clone(child_func, stack + sizeof(stack), CLONE_VM|SIGCHLD, skel);
+		if (!ASSERT_GT(pid, 0, "clone"))
+			goto cleanup;
+	} else {
+		pid = fork();
+		if (!ASSERT_GE(pid, 0, "fork"))
+			goto cleanup;
+		if (pid == 0)
+			child_func(skel);
+	}
+
+	/* Wait for the child and verify it exited properly with 0. */
+	err = waitpid(pid, &status, 0);
+	if (ASSERT_EQ(err, pid, "waitpid")) {
+		ASSERT_EQ(WIFEXITED(status), 1, "child_exited");
+		ASSERT_EQ(WEXITSTATUS(status), 0, "child_exit_code");
+	}
+
+cleanup:
+	uprobe_syscall_executed__destroy(skel);
+}
+
 static void __test_uprobe_syscall(void)
 {
 	if (test__start_subtest("uretprobe_regs_equal"))
@@ -974,6 +1058,10 @@ static void __test_uprobe_syscall(void)
 		test_uprobe_race();
 	if (test__start_subtest("uprobe_red_zone"))
 		test_uprobe_red_zone();
+	if (test__start_subtest("uprobe_optimized_fork"))
+		test_uprobe_fork_optimized(false);
+	if (test__start_subtest("uprobe_optimized_clone_vm"))
+		test_uprobe_fork_optimized(true);
 	if (test__start_subtest("uprobe_error"))
 		test_uprobe_error();
 	if (test__start_subtest("uprobe_regs_equal"))