Merge tag 'perf-core-2026-02-09' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull performance event updates from Ingo Molnar:
 "x86 PMU driver updates:

   - Add support for the core PMU for Intel Diamond Rapids (DMR) CPUs
     (Dapeng Mi)

     Compared to previous iterations of the Intel PMU code, there's been
     a lot of changes, which center around three main areas:

      - Introduce the OFF-MODULE RESPONSE (OMR) facility to replace the
        Off-Core Response (OCR) facility

      - New PEBS data source encoding layout

      - Support the new "RDPMC user disable" feature

   - Likewise, a large series adds uncore PMU support for Intel Diamond
     Rapids (DMR) CPUs (Zide Chen)

     This centers around these four main areas:

      - DMR may have two Integrated I/O and Memory Hub (IMH) dies,
        separate from the compute tile (CBB) dies. Each CBB and each IMH
        die has its own discovery domain.

      - Unlike prior CPUs that retrieve the global discovery table
        portal exclusively via PCI or MSR, DMR uses PCI for IMH PMON
        discovery and MSR for CBB PMON discovery.

      - DMR introduces several new PMON types: SCA, HAMVF, D2D_ULA, UBR,
        PCIE4, CRS, CPC, ITC, OTC, CMS, and PCIE6.

      - IIO free-running counters in DMR are MMIO-based, unlike SPR.

   - Also add support for Add missing PMON units for Intel Panther Lake,
     and support Nova Lake (NVL), which largely maps to Panther Lake.
     (Zide Chen)

   - KVM integration: Add support for mediated vPMUs (by Kan Liang and
     Sean Christopherson, with fixes and cleanups by Peter Zijlstra,
     Sandipan Das and Mingwei Zhang)

   - Add Intel cstate driver to support for Wildcat Lake (WCL) CPUs,
     which are a low-power variant of Panther Lake (Zide Chen)

   - Add core, cstate and MSR PMU support for the Airmont NP Intel CPU
     (aka MaxLinear Lightning Mountain), which maps to the existing
     Airmont code (Martin Schiller)

  Performance enhancements:

   - Speed up kexec shutdown by avoiding unnecessary cross CPU calls
     (Jan H. Schönherr)

   - Fix slow perf_event_task_exit() with LBR callstacks (Namhyung Kim)

  User-space stack unwinding support:

   - Various cleanups and refactorings in preparation to generalize the
     unwinding code for other architectures (Jens Remus)

  Uprobes updates:

   - Transition from kmap_atomic to kmap_local_page (Keke Ming)

   - Fix incorrect lockdep condition in filter_chain() (Breno Leitao)

   - Fix XOL allocation failure for 32-bit tasks (Oleg Nesterov)

  Misc fixes and cleanups:

   - s390: Remove kvm_types.h from Kbuild (Randy Dunlap)

   - x86/intel/uncore: Convert comma to semicolon (Chen Ni)

   - x86/uncore: Clean up const mismatch (Greg Kroah-Hartman)

   - x86/ibs: Fix typo in dc_l2tlb_miss comment (Xiang-Bin Shi)"

* tag 'perf-core-2026-02-09' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (58 commits)
  s390: remove kvm_types.h from Kbuild
  uprobes: Fix incorrect lockdep condition in filter_chain()
  x86/ibs: Fix typo in dc_l2tlb_miss comment
  x86/uprobes: Fix XOL allocation failure for 32-bit tasks
  perf/x86/intel/uncore: Convert comma to semicolon
  perf/x86/intel: Add support for rdpmc user disable feature
  perf/x86: Use macros to replace magic numbers in attr_rdpmc
  perf/x86/intel: Add core PMU support for Novalake
  perf/x86/intel: Add support for PEBS memory auxiliary info field in NVL
  perf/x86/intel: Add core PMU support for DMR
  perf/x86/intel: Add support for PEBS memory auxiliary info field in DMR
  perf/x86/intel: Support the 4 new OMR MSRs introduced in DMR and NVL
  perf/core: Fix slow perf_event_task_exit() with LBR callstacks
  perf/core: Speed up kexec shutdown by avoiding unnecessary cross CPU calls
  uprobes: use kmap_local_page() for temporary page mappings
  arm/uprobes: use kmap_local_page() in arch_uprobe_copy_ixol()
  mips/uprobes: use kmap_local_page() in arch_uprobe_copy_ixol()
  arm64/uprobes: use kmap_local_page() in arch_uprobe_copy_ixol()
  riscv/uprobes: use kmap_local_page() in arch_uprobe_copy_ixol()
  perf/x86/intel/uncore: Add Nova Lake support
  ...

5 files changed, 71 insertions, 11 deletions

diff --git a/include/asm-generic/Kbuild b/include/asm-generic/Kbuild
index 295c94a3ccc1..9aff61e7b8f2 100644
--- a/include/asm-generic/Kbuild
+++ b/include/asm-generic/Kbuild
@@ -32,6 +32,7 @@ mandatory-y += irq_work.h
 mandatory-y += kdebug.h
 mandatory-y += kmap_size.h
 mandatory-y += kprobes.h
+mandatory-y += kvm_types.h
 mandatory-y += linkage.h
 mandatory-y += local.h
 mandatory-y += local64.h
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 9ded2e582c60..48d851fbd8ea 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -305,6 +305,7 @@ struct perf_event_pmu_context;
 #define PERF_PMU_CAP_EXTENDED_HW_TYPE	0x0100
 #define PERF_PMU_CAP_AUX_PAUSE		0x0200
 #define PERF_PMU_CAP_AUX_PREFER_LARGE	0x0400
+#define PERF_PMU_CAP_MEDIATED_VPMU	0x0800
 
 /**
  * pmu::scope
@@ -998,6 +999,11 @@ struct perf_event_groups {
 	u64				index;
 };
 
+struct perf_time_ctx {
+	u64		time;
+	u64		stamp;
+	u64		offset;
+};
 
 /**
  * struct perf_event_context - event context structure
@@ -1036,9 +1042,12 @@ struct perf_event_context {
 	/*
 	 * Context clock, runs when context enabled.
 	 */
-	u64				time;
-	u64				timestamp;
-	u64				timeoffset;
+	struct perf_time_ctx		time;
+
+	/*
+	 * Context clock, runs when in the guest mode.
+	 */
+	struct perf_time_ctx		timeguest;
 
 	/*
 	 * These fields let us detect when two contexts have both
@@ -1171,9 +1180,8 @@ struct bpf_perf_event_data_kern {
  * This is a per-cpu dynamically allocated data structure.
  */
 struct perf_cgroup_info {
-	u64				time;
-	u64				timestamp;
-	u64				timeoffset;
+	struct perf_time_ctx		time;
+	struct perf_time_ctx		timeguest;
 	int				active;
 };
 
@@ -1669,6 +1677,8 @@ struct perf_guest_info_callbacks {
 	unsigned int			(*state)(void);
 	unsigned long			(*get_ip)(void);
 	unsigned int			(*handle_intel_pt_intr)(void);
+
+	void				(*handle_mediated_pmi)(void);
 };
 
 #ifdef CONFIG_GUEST_PERF_EVENTS
@@ -1678,6 +1688,7 @@ extern struct perf_guest_info_callbacks __rcu *perf_guest_cbs;
 DECLARE_STATIC_CALL(__perf_guest_state, *perf_guest_cbs->state);
 DECLARE_STATIC_CALL(__perf_guest_get_ip, *perf_guest_cbs->get_ip);
 DECLARE_STATIC_CALL(__perf_guest_handle_intel_pt_intr, *perf_guest_cbs->handle_intel_pt_intr);
+DECLARE_STATIC_CALL(__perf_guest_handle_mediated_pmi, *perf_guest_cbs->handle_mediated_pmi);
 
 static inline unsigned int perf_guest_state(void)
 {
@@ -1694,6 +1705,11 @@ static inline unsigned int perf_guest_handle_intel_pt_intr(void)
 	return static_call(__perf_guest_handle_intel_pt_intr)();
 }
 
+static inline void perf_guest_handle_mediated_pmi(void)
+{
+	static_call(__perf_guest_handle_mediated_pmi)();
+}
+
 extern void perf_register_guest_info_callbacks(struct perf_guest_info_callbacks *cbs);
 extern void perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks *cbs);
 
@@ -1914,6 +1930,13 @@ extern int perf_event_account_interrupt(struct perf_event *event);
 extern int perf_event_period(struct perf_event *event, u64 value);
 extern u64 perf_event_pause(struct perf_event *event, bool reset);
 
+#ifdef CONFIG_PERF_GUEST_MEDIATED_PMU
+int perf_create_mediated_pmu(void);
+void perf_release_mediated_pmu(void);
+void perf_load_guest_context(void);
+void perf_put_guest_context(void);
+#endif
+
 #else /* !CONFIG_PERF_EVENTS: */
 
 static inline void *
diff --git a/include/linux/unwind_user.h b/include/linux/unwind_user.h
index 7f7282516bf5..64618618febd 100644
--- a/include/linux/unwind_user.h
+++ b/include/linux/unwind_user.h
@@ -5,8 +5,22 @@
 #include <linux/unwind_user_types.h>
 #include <asm/unwind_user.h>
 
-#ifndef ARCH_INIT_USER_FP_FRAME
- #define ARCH_INIT_USER_FP_FRAME
+#ifndef CONFIG_HAVE_UNWIND_USER_FP
+
+#define ARCH_INIT_USER_FP_FRAME(ws)
+
+#endif
+
+#ifndef ARCH_INIT_USER_FP_ENTRY_FRAME
+#define ARCH_INIT_USER_FP_ENTRY_FRAME(ws)
+#endif
+
+#ifndef unwind_user_at_function_start
+static inline bool unwind_user_at_function_start(struct pt_regs *regs)
+{
+	return false;
+}
+#define unwind_user_at_function_start unwind_user_at_function_start
 #endif
 
 int unwind_user(struct unwind_stacktrace *trace, unsigned int max_entries);
diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h
index ee3d36eda45d..f548fea2adec 100644
--- a/include/linux/uprobes.h
+++ b/include/linux/uprobes.h
@@ -242,6 +242,7 @@ 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);
 #else /* !CONFIG_UPROBES */
 struct uprobes_state {
 };
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index 72f03153dd32..fd10aa8d697f 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -1330,14 +1330,16 @@ union perf_mem_data_src {
 			mem_snoopx  :  2, /* Snoop mode, ext */
 			mem_blk     :  3, /* Access blocked */
 			mem_hops    :  3, /* Hop level */
-			mem_rsvd    : 18;
+			mem_region  :  5, /* cache/memory regions */
+			mem_rsvd    : 13;
 	};
 };
 #elif defined(__BIG_ENDIAN_BITFIELD)
 union perf_mem_data_src {
 	__u64 val;
 	struct {
-		__u64	mem_rsvd    : 18,
+		__u64	mem_rsvd    : 13,
+			mem_region  :  5, /* cache/memory regions */
 			mem_hops    :  3, /* Hop level */
 			mem_blk     :  3, /* Access blocked */
 			mem_snoopx  :  2, /* Snoop mode, ext */
@@ -1394,7 +1396,7 @@ union perf_mem_data_src {
 #define PERF_MEM_LVLNUM_L4			0x0004 /* L4 */
 #define PERF_MEM_LVLNUM_L2_MHB			0x0005 /* L2 Miss Handling Buffer */
 #define PERF_MEM_LVLNUM_MSC			0x0006 /* Memory-side Cache */
-/* 0x007 available */
+#define PERF_MEM_LVLNUM_L0			0x0007 /* L0 */
 #define PERF_MEM_LVLNUM_UNC			0x0008 /* Uncached */
 #define PERF_MEM_LVLNUM_CXL			0x0009 /* CXL */
 #define PERF_MEM_LVLNUM_IO			0x000a /* I/O */
@@ -1447,6 +1449,25 @@ union perf_mem_data_src {
 /* 5-7 available */
 #define PERF_MEM_HOPS_SHIFT			43
 
+/* Cache/Memory region */
+#define PERF_MEM_REGION_NA		0x0  /* Invalid */
+#define PERF_MEM_REGION_RSVD		0x01 /* Reserved */
+#define PERF_MEM_REGION_L_SHARE		0x02 /* Local CA shared cache */
+#define PERF_MEM_REGION_L_NON_SHARE	0x03 /* Local CA non-shared cache */
+#define PERF_MEM_REGION_O_IO		0x04 /* Other CA IO agent */
+#define PERF_MEM_REGION_O_SHARE		0x05 /* Other CA shared cache */
+#define PERF_MEM_REGION_O_NON_SHARE	0x06 /* Other CA non-shared cache */
+#define PERF_MEM_REGION_MMIO		0x07 /* MMIO */
+#define PERF_MEM_REGION_MEM0		0x08 /* Memory region 0 */
+#define PERF_MEM_REGION_MEM1		0x09 /* Memory region 1 */
+#define PERF_MEM_REGION_MEM2		0x0a /* Memory region 2 */
+#define PERF_MEM_REGION_MEM3		0x0b /* Memory region 3 */
+#define PERF_MEM_REGION_MEM4		0x0c /* Memory region 4 */
+#define PERF_MEM_REGION_MEM5		0x0d /* Memory region 5 */
+#define PERF_MEM_REGION_MEM6		0x0e /* Memory region 6 */
+#define PERF_MEM_REGION_MEM7		0x0f /* Memory region 7 */
+#define PERF_MEM_REGION_SHIFT		46
+
 #define PERF_MEM_S(a, s) \
 	(((__u64)PERF_MEM_##a##_##s) << PERF_MEM_##a##_SHIFT)