Merge tag 'perf-core-2025-09-26' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull performance events updates from Ingo Molnar:
 "Core perf code updates:

   - Convert mmap() related reference counts to refcount_t. This is in
     reaction to the recently fixed refcount bugs, which could have been
     detected earlier and could have mitigated the bug somewhat (Thomas
     Gleixner, Peter Zijlstra)

   - Clean up and simplify the callchain code, in preparation for
     sframes (Steven Rostedt, Josh Poimboeuf)

  Uprobes updates:

   - Add support to optimize usdt probes on x86-64, which gives a
     substantial speedup (Jiri Olsa)

   - Cleanups and fixes on x86 (Peter Zijlstra)

  PMU driver updates:

   - Various optimizations and fixes to the Intel PMU driver (Dapeng Mi)

  Misc cleanups and fixes:

   - Remove redundant __GFP_NOWARN (Qianfeng Rong)"

* tag 'perf-core-2025-09-26' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (57 commits)
  selftests/bpf: Fix uprobe_sigill test for uprobe syscall error value
  uprobes/x86: Return error from uprobe syscall when not called from trampoline
  perf: Skip user unwind if the task is a kernel thread
  perf: Simplify get_perf_callchain() user logic
  perf: Use current->flags & PF_KTHREAD|PF_USER_WORKER instead of current->mm == NULL
  perf: Have get_perf_callchain() return NULL if crosstask and user are set
  perf: Remove get_perf_callchain() init_nr argument
  perf/x86: Print PMU counters bitmap in x86_pmu_show_pmu_cap()
  perf/x86/intel: Add ICL_FIXED_0_ADAPTIVE bit into INTEL_FIXED_BITS_MASK
  perf/x86/intel: Change macro GLOBAL_CTRL_EN_PERF_METRICS to BIT_ULL(48)
  perf/x86: Add PERF_CAP_PEBS_TIMING_INFO flag
  perf/x86/intel: Fix IA32_PMC_x_CFG_B MSRs access error
  perf/x86/intel: Use early_initcall() to hook bts_init()
  uprobes: Remove redundant __GFP_NOWARN
  selftests/seccomp: validate uprobe syscall passes through seccomp
  seccomp: passthrough uprobe systemcall without filtering
  selftests/bpf: Fix uprobe syscall shadow stack test
  selftests/bpf: Change test_uretprobe_regs_change for uprobe and uretprobe
  selftests/bpf: Add uprobe_regs_equal test
  selftests/bpf: Add optimized usdt variant for basic usdt test
  ...

arch/arm/probes/uprobes/core.c

@@ -30,7 +30,7 @@ int set_swbp(struct arch_uprobe *auprobe, struct vm_area_struct *vma,
 	     unsigned long vaddr)
 {
 	return uprobe_write_opcode(auprobe, vma, vaddr,
-		   __opcode_to_mem_arm(auprobe->bpinsn));
+		   __opcode_to_mem_arm(auprobe->bpinsn), true);
 }
 
 bool arch_uprobe_ignore(struct arch_uprobe *auprobe, struct pt_regs *regs)

arch/x86/entry/syscalls/syscall_64.tbl

@@ -345,6 +345,7 @@
 333	common	io_pgetevents		sys_io_pgetevents
 334	common	rseq			sys_rseq
 335	common	uretprobe		sys_uretprobe
+336	common	uprobe			sys_uprobe
 # don't use numbers 387 through 423, add new calls after the last
 # 'common' entry
 424	common	pidfd_send_signal	sys_pidfd_send_signal

arch/x86/events/core.c

@@ -2069,13 +2069,15 @@ static void _x86_pmu_read(struct perf_event *event)
 
 void x86_pmu_show_pmu_cap(struct pmu *pmu)
 {
-	pr_info("... version:                %d\n",     x86_pmu.version);
-	pr_info("... bit width:              %d\n",     x86_pmu.cntval_bits);
-	pr_info("... generic registers:      %d\n",     x86_pmu_num_counters(pmu));
-	pr_info("... value mask:             %016Lx\n", x86_pmu.cntval_mask);
-	pr_info("... max period:             %016Lx\n", x86_pmu.max_period);
-	pr_info("... fixed-purpose events:   %d\n",     x86_pmu_num_counters_fixed(pmu));
-	pr_info("... event mask:             %016Lx\n", hybrid(pmu, intel_ctrl));
+	pr_info("... version:                   %d\n", x86_pmu.version);
+	pr_info("... bit width:                 %d\n", x86_pmu.cntval_bits);
+	pr_info("... generic counters:          %d\n", x86_pmu_num_counters(pmu));
+	pr_info("... generic bitmap:            %016llx\n", hybrid(pmu, cntr_mask64));
+	pr_info("... fixed-purpose counters:    %d\n", x86_pmu_num_counters_fixed(pmu));
+	pr_info("... fixed-purpose bitmap:      %016llx\n", hybrid(pmu, fixed_cntr_mask64));
+	pr_info("... value mask:                %016llx\n", x86_pmu.cntval_mask);
+	pr_info("... max period:                %016llx\n", x86_pmu.max_period);
+	pr_info("... global_ctrl mask:          %016llx\n", hybrid(pmu, intel_ctrl));
 }
 
 static int __init init_hw_perf_events(void)

arch/x86/events/intel/bts.c

@@ -643,4 +643,4 @@ static __init int bts_init(void)
 
 	return perf_pmu_register(&bts_pmu, "intel_bts", -1);
 }
-arch_initcall(bts_init);
+early_initcall(bts_init);

arch/x86/events/intel/core.c

@@ -2845,8 +2845,8 @@ static void intel_pmu_enable_fixed(struct perf_event *event)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
-	u64 mask, bits = 0;
 	int idx = hwc->idx;
+	u64 bits = 0;
 
 	if (is_topdown_idx(idx)) {
 		struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
@@ -2885,14 +2885,10 @@ static void intel_pmu_enable_fixed(struct perf_event *event)
 
 	idx -= INTEL_PMC_IDX_FIXED;
 	bits = intel_fixed_bits_by_idx(idx, bits);
-	mask = intel_fixed_bits_by_idx(idx, INTEL_FIXED_BITS_MASK);
-
-	if (x86_pmu.intel_cap.pebs_baseline && event->attr.precise_ip) {
+	if (x86_pmu.intel_cap.pebs_baseline && event->attr.precise_ip)
 		bits |= intel_fixed_bits_by_idx(idx, ICL_FIXED_0_ADAPTIVE);
-		mask |= intel_fixed_bits_by_idx(idx, ICL_FIXED_0_ADAPTIVE);
-	}
 
-	cpuc->fixed_ctrl_val &= ~mask;
+	cpuc->fixed_ctrl_val &= ~intel_fixed_bits_by_idx(idx, INTEL_FIXED_BITS_MASK);
 	cpuc->fixed_ctrl_val |= bits;
 }
 
@@ -2997,7 +2993,8 @@ static void intel_pmu_acr_late_setup(struct cpu_hw_events *cpuc)
 			if (event->group_leader != leader->group_leader)
 				break;
 			for_each_set_bit(idx, (unsigned long *)&event->attr.config2, X86_PMC_IDX_MAX) {
-				if (WARN_ON_ONCE(i + idx > cpuc->n_events))
+				if (i + idx >= cpuc->n_events ||
+				    !is_acr_event_group(cpuc->event_list[i + idx]))
 					return;
 				__set_bit(cpuc->assign[i + idx], (unsigned long *)&event->hw.config1);
 			}
@@ -5318,9 +5315,9 @@ static void intel_pmu_check_hybrid_pmus(struct x86_hybrid_pmu *pmu)
 						0, x86_pmu_num_counters(&pmu->pmu), 0, 0);
 
 	if (pmu->intel_cap.perf_metrics)
-		pmu->intel_ctrl |= 1ULL << GLOBAL_CTRL_EN_PERF_METRICS;
+		pmu->intel_ctrl |= GLOBAL_CTRL_EN_PERF_METRICS;
 	else
-		pmu->intel_ctrl &= ~(1ULL << GLOBAL_CTRL_EN_PERF_METRICS);
+		pmu->intel_ctrl &= ~GLOBAL_CTRL_EN_PERF_METRICS;
 
 	intel_pmu_check_event_constraints(pmu->event_constraints,
 					  pmu->cntr_mask64,
@@ -5455,7 +5452,7 @@ static void intel_pmu_cpu_starting(int cpu)
 		rdmsrq(MSR_IA32_PERF_CAPABILITIES, perf_cap.capabilities);
 		if (!perf_cap.perf_metrics) {
 			x86_pmu.intel_cap.perf_metrics = 0;
-			x86_pmu.intel_ctrl &= ~(1ULL << GLOBAL_CTRL_EN_PERF_METRICS);
+			x86_pmu.intel_ctrl &= ~GLOBAL_CTRL_EN_PERF_METRICS;
 		}
 	}
 
@@ -7789,7 +7786,7 @@ __init int intel_pmu_init(void)
 	}
 
 	if (!is_hybrid() && x86_pmu.intel_cap.perf_metrics)
-		x86_pmu.intel_ctrl |= 1ULL << GLOBAL_CTRL_EN_PERF_METRICS;
+		x86_pmu.intel_ctrl |= GLOBAL_CTRL_EN_PERF_METRICS;
 
 	if (x86_pmu.intel_cap.pebs_timing_info)
 		x86_pmu.flags |= PMU_FL_RETIRE_LATENCY;

arch/x86/include/asm/msr-index.h

@@ -315,12 +315,14 @@
 #define PERF_CAP_PT_IDX			16
 
 #define MSR_PEBS_LD_LAT_THRESHOLD	0x000003f6
-#define PERF_CAP_PEBS_TRAP             BIT_ULL(6)
-#define PERF_CAP_ARCH_REG              BIT_ULL(7)
-#define PERF_CAP_PEBS_FORMAT           0xf00
-#define PERF_CAP_PEBS_BASELINE         BIT_ULL(14)
-#define PERF_CAP_PEBS_MASK	(PERF_CAP_PEBS_TRAP | PERF_CAP_ARCH_REG | \
-				 PERF_CAP_PEBS_FORMAT | PERF_CAP_PEBS_BASELINE)
+#define PERF_CAP_PEBS_TRAP		BIT_ULL(6)
+#define PERF_CAP_ARCH_REG		BIT_ULL(7)
+#define PERF_CAP_PEBS_FORMAT		0xf00
+#define PERF_CAP_PEBS_BASELINE		BIT_ULL(14)
+#define PERF_CAP_PEBS_TIMING_INFO	BIT_ULL(17)
+#define PERF_CAP_PEBS_MASK		(PERF_CAP_PEBS_TRAP | PERF_CAP_ARCH_REG | \
+					 PERF_CAP_PEBS_FORMAT | PERF_CAP_PEBS_BASELINE | \
+					 PERF_CAP_PEBS_TIMING_INFO)
 
 #define MSR_IA32_RTIT_CTL		0x00000570
 #define RTIT_CTL_TRACEEN		BIT(0)

arch/x86/include/asm/perf_event.h

@@ -35,7 +35,6 @@
 #define ARCH_PERFMON_EVENTSEL_EQ			(1ULL << 36)
 #define ARCH_PERFMON_EVENTSEL_UMASK2			(0xFFULL << 40)
 
-#define INTEL_FIXED_BITS_MASK				0xFULL
 #define INTEL_FIXED_BITS_STRIDE			4
 #define INTEL_FIXED_0_KERNEL				(1ULL << 0)
 #define INTEL_FIXED_0_USER				(1ULL << 1)
@@ -48,6 +47,11 @@
 #define ICL_EVENTSEL_ADAPTIVE				(1ULL << 34)
 #define ICL_FIXED_0_ADAPTIVE				(1ULL << 32)
 
+#define INTEL_FIXED_BITS_MASK					\
+	(INTEL_FIXED_0_KERNEL | INTEL_FIXED_0_USER |		\
+	 INTEL_FIXED_0_ANYTHREAD | INTEL_FIXED_0_ENABLE_PMI |	\
+	 ICL_FIXED_0_ADAPTIVE)
+
 #define intel_fixed_bits_by_idx(_idx, _bits)			\
 	((_bits) << ((_idx) * INTEL_FIXED_BITS_STRIDE))
 
@@ -430,7 +434,7 @@ static inline bool is_topdown_idx(int idx)
 #define GLOBAL_STATUS_TRACE_TOPAPMI		BIT_ULL(GLOBAL_STATUS_TRACE_TOPAPMI_BIT)
 #define GLOBAL_STATUS_PERF_METRICS_OVF_BIT	48
 
-#define GLOBAL_CTRL_EN_PERF_METRICS		48
+#define GLOBAL_CTRL_EN_PERF_METRICS		BIT_ULL(48)
 /*
  * We model guest LBR event tracing as another fixed-mode PMC like BTS.
  *

arch/x86/include/asm/shstk.h

@@ -23,6 +23,8 @@ int setup_signal_shadow_stack(struct ksignal *ksig);
 int restore_signal_shadow_stack(void);
 int shstk_update_last_frame(unsigned long val);
 bool shstk_is_enabled(void);
+int shstk_pop(u64 *val);
+int shstk_push(u64 val);
 #else
 static inline long shstk_prctl(struct task_struct *task, int option,
 			       unsigned long arg2) { return -EINVAL; }
@@ -35,6 +37,8 @@ static inline int setup_signal_shadow_stack(struct ksignal *ksig) { return 0; }
 static inline int restore_signal_shadow_stack(void) { return 0; }
 static inline int shstk_update_last_frame(unsigned long val) { return 0; }
 static inline bool shstk_is_enabled(void) { return false; }
+static inline int shstk_pop(u64 *val) { return -ENOTSUPP; }
+static inline int shstk_push(u64 val) { return -ENOTSUPP; }
 #endif /* CONFIG_X86_USER_SHADOW_STACK */
 
 #endif /* __ASSEMBLER__ */

arch/x86/include/asm/uprobes.h

@@ -20,6 +20,11 @@ typedef u8 uprobe_opcode_t;
 #define UPROBE_SWBP_INSN		0xcc
 #define UPROBE_SWBP_INSN_SIZE		   1
 
+enum {
+	ARCH_UPROBE_FLAG_CAN_OPTIMIZE   = 0,
+	ARCH_UPROBE_FLAG_OPTIMIZE_FAIL  = 1,
+};
+
 struct uprobe_xol_ops;
 
 struct arch_uprobe {
@@ -45,6 +50,8 @@ struct arch_uprobe {
 			u8	ilen;
 		}			push;
 	};
+
+	unsigned long flags;
 };
 
 struct arch_uprobe_task {

arch/x86/kernel/shstk.c

@@ -246,6 +246,46 @@ static unsigned long get_user_shstk_addr(void)
 	return ssp;
 }
 
+int shstk_pop(u64 *val)
+{
+	int ret = 0;
+	u64 ssp;
+
+	if (!features_enabled(ARCH_SHSTK_SHSTK))
+		return -ENOTSUPP;
+
+	fpregs_lock_and_load();
+
+	rdmsrq(MSR_IA32_PL3_SSP, ssp);
+	if (val && get_user(*val, (__user u64 *)ssp))
+		ret = -EFAULT;
+	else
+		wrmsrq(MSR_IA32_PL3_SSP, ssp + SS_FRAME_SIZE);
+	fpregs_unlock();
+
+	return ret;
+}
+
+int shstk_push(u64 val)
+{
+	u64 ssp;
+	int ret;
+
+	if (!features_enabled(ARCH_SHSTK_SHSTK))
+		return -ENOTSUPP;
+
+	fpregs_lock_and_load();
+
+	rdmsrq(MSR_IA32_PL3_SSP, ssp);
+	ssp -= SS_FRAME_SIZE;
+	ret = write_user_shstk_64((__user void *)ssp, val);
+	if (!ret)
+		wrmsrq(MSR_IA32_PL3_SSP, ssp);
+	fpregs_unlock();
+
+	return ret;
+}
+
 #define SHSTK_DATA_BIT BIT(63)
 
 static int put_shstk_data(u64 __user *addr, u64 data)

arch/x86/kvm/pmu.h

@@ -13,7 +13,7 @@
 #define MSR_IA32_MISC_ENABLE_PMU_RO_MASK (MSR_IA32_MISC_ENABLE_PEBS_UNAVAIL |	\
 					  MSR_IA32_MISC_ENABLE_BTS_UNAVAIL)
 
-/* retrieve the 4 bits for EN and PMI out of IA32_FIXED_CTR_CTRL */
+/* retrieve a fixed counter bits out of IA32_FIXED_CTR_CTRL */
 #define fixed_ctrl_field(ctrl_reg, idx) \
 	(((ctrl_reg) >> ((idx) * INTEL_FIXED_BITS_STRIDE)) & INTEL_FIXED_BITS_MASK)
 

include/linux/perf_event.h

@@ -859,7 +859,7 @@ struct perf_event {
 
 	/* mmap bits */
 	struct mutex			mmap_mutex;
-	atomic_t			mmap_count;
+	refcount_t			mmap_count;
 
 	struct perf_buffer		*rb;
 	struct list_head		rb_entry;
@@ -1719,7 +1719,7 @@ DECLARE_PER_CPU(struct perf_callchain_entry, perf_callchain_entry);
 extern void perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs);
 extern void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs);
 extern struct perf_callchain_entry *
-get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user,
+get_perf_callchain(struct pt_regs *regs, bool kernel, bool user,
 		   u32 max_stack, bool crosstask, bool add_mark);
 extern int get_callchain_buffers(int max_stack);
 extern void put_callchain_buffers(void);

include/linux/syscalls.h

@@ -1005,6 +1005,8 @@ asmlinkage long sys_ioperm(unsigned long from, unsigned long num, int on);
 
 asmlinkage long sys_uretprobe(void);
 
+asmlinkage long sys_uprobe(void);
+
 /* pciconfig: alpha, arm, arm64, ia64, sparc */
 asmlinkage long sys_pciconfig_read(unsigned long bus, unsigned long dfn,
 				unsigned long off, unsigned long len,

include/linux/uprobes.h

@@ -17,6 +17,7 @@
 #include <linux/wait.h>
 #include <linux/timer.h>
 #include <linux/seqlock.h>
+#include <linux/mutex.h>
 
 struct uprobe;
 struct vm_area_struct;
@@ -185,8 +186,14 @@ 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,
+				     uprobe_opcode_t *insn, int nbytes, void *data);
+
 extern void __init uprobes_init(void);
 extern int set_swbp(struct arch_uprobe *aup, struct vm_area_struct *vma, unsigned long vaddr);
 extern int set_orig_insn(struct arch_uprobe *aup, struct vm_area_struct *vma, unsigned long vaddr);
@@ -194,7 +201,11 @@ extern bool is_swbp_insn(uprobe_opcode_t *insn);
 extern bool is_trap_insn(uprobe_opcode_t *insn);
 extern unsigned long uprobe_get_swbp_addr(struct pt_regs *regs);
 extern unsigned long uprobe_get_trap_addr(struct pt_regs *regs);
-extern int uprobe_write_opcode(struct arch_uprobe *auprobe, struct vm_area_struct *vma, unsigned long vaddr, uprobe_opcode_t);
+extern int uprobe_write_opcode(struct arch_uprobe *auprobe, struct vm_area_struct *vma, unsigned long vaddr, uprobe_opcode_t,
+			       bool is_register);
+extern int uprobe_write(struct arch_uprobe *auprobe, struct vm_area_struct *vma, const unsigned long opcode_vaddr,
+			uprobe_opcode_t *insn, int nbytes, uprobe_write_verify_t verify, bool is_register, bool do_update_ref_ctr,
+			void *data);
 extern struct uprobe *uprobe_register(struct inode *inode, loff_t offset, loff_t ref_ctr_offset, struct uprobe_consumer *uc);
 extern int uprobe_apply(struct uprobe *uprobe, struct uprobe_consumer *uc, bool);
 extern void uprobe_unregister_nosync(struct uprobe *uprobe, struct uprobe_consumer *uc);
@@ -224,8 +235,13 @@ extern bool arch_uprobe_ignore(struct arch_uprobe *aup, struct pt_regs *regs);
 extern void arch_uprobe_copy_ixol(struct page *page, unsigned long vaddr,
 					 void *src, unsigned long len);
 extern void uprobe_handle_trampoline(struct pt_regs *regs);
-extern void *arch_uprobe_trampoline(unsigned long *psize);
+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);
 #else /* !CONFIG_UPROBES */
 struct uprobes_state {
 };

kernel/bpf/stackmap.c

@@ -314,7 +314,7 @@ BPF_CALL_3(bpf_get_stackid, struct pt_regs *, regs, struct bpf_map *, map,
 	if (max_depth > sysctl_perf_event_max_stack)
 		max_depth = sysctl_perf_event_max_stack;
 
-	trace = get_perf_callchain(regs, 0, kernel, user, max_depth,
+	trace = get_perf_callchain(regs, kernel, user, max_depth,
 				   false, false);
 
 	if (unlikely(!trace))
@@ -451,7 +451,7 @@ static long __bpf_get_stack(struct pt_regs *regs, struct task_struct *task,
 	else if (kernel && task)
 		trace = get_callchain_entry_for_task(task, max_depth);
 	else
-		trace = get_perf_callchain(regs, 0, kernel, user, max_depth,
+		trace = get_perf_callchain(regs, kernel, user, max_depth,
 					   crosstask, false);
 
 	if (unlikely(!trace) || trace->nr < skip) {

kernel/events/callchain.c

@@ -217,22 +217,26 @@ static void fixup_uretprobe_trampoline_entries(struct perf_callchain_entry *entr
 }
 
 struct perf_callchain_entry *
-get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user,
+get_perf_callchain(struct pt_regs *regs, bool kernel, bool user,
 		   u32 max_stack, bool crosstask, bool add_mark)
 {
 	struct perf_callchain_entry *entry;
 	struct perf_callchain_entry_ctx ctx;
 	int rctx, start_entry_idx;
 
+	/* crosstask is not supported for user stacks */
+	if (crosstask && user && !kernel)
+		return NULL;
+
 	entry = get_callchain_entry(&rctx);
 	if (!entry)
 		return NULL;
 
-	ctx.entry     = entry;
-	ctx.max_stack = max_stack;
-	ctx.nr	      = entry->nr = init_nr;
-	ctx.contexts       = 0;
-	ctx.contexts_maxed = false;
+	ctx.entry		= entry;
+	ctx.max_stack		= max_stack;
+	ctx.nr			= entry->nr = 0;
+	ctx.contexts		= 0;
+	ctx.contexts_maxed	= false;
 
 	if (kernel && !user_mode(regs)) {
 		if (add_mark)
@@ -240,25 +244,19 @@ get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user,
 		perf_callchain_kernel(&ctx, regs);
 	}
 
-	if (user) {
+	if (user && !crosstask) {
 		if (!user_mode(regs)) {
-			if  (current->mm)
-				regs = task_pt_regs(current);
-			else
-				regs = NULL;
-		}
-
-		if (regs) {
-			if (crosstask)
+			if (current->flags & (PF_KTHREAD | PF_USER_WORKER))
 				goto exit_put;
-
-			if (add_mark)
-				perf_callchain_store_context(&ctx, PERF_CONTEXT_USER);
-
-			start_entry_idx = entry->nr;
-			perf_callchain_user(&ctx, regs);
-			fixup_uretprobe_trampoline_entries(entry, start_entry_idx);
+			regs = task_pt_regs(current);
 		}
+
+		if (add_mark)
+			perf_callchain_store_context(&ctx, PERF_CONTEXT_USER);
+
+		start_entry_idx = entry->nr;
+		perf_callchain_user(&ctx, regs);
+		fixup_uretprobe_trampoline_entries(entry, start_entry_idx);
 	}
 
 exit_put:

kernel/events/internal.h

@@ -35,7 +35,7 @@ struct perf_buffer {
 	spinlock_t			event_lock;
 	struct list_head		event_list;
 
-	atomic_t			mmap_count;
+	refcount_t			mmap_count;
 	unsigned long			mmap_locked;
 	struct user_struct		*mmap_user;
 
@@ -47,7 +47,7 @@ struct perf_buffer {
 	unsigned long			aux_pgoff;
 	int				aux_nr_pages;
 	int				aux_overwrite;
-	atomic_t			aux_mmap_count;
+	refcount_t			aux_mmap_count;
 	unsigned long			aux_mmap_locked;
 	void				(*free_aux)(void *);
 	refcount_t			aux_refcount;

kernel/events/ring_buffer.c

@@ -400,7 +400,7 @@ void *perf_aux_output_begin(struct perf_output_handle *handle,
 	 * the same order, see perf_mmap_close. Otherwise we end up freeing
 	 * aux pages in this path, which is a bug, because in_atomic().
 	 */
-	if (!atomic_read(&rb->aux_mmap_count))
+	if (!refcount_read(&rb->aux_mmap_count))
 		goto err;
 
 	if (!refcount_inc_not_zero(&rb->aux_refcount))