summaryrefslogtreecommitdiff
path: root/arch/x86/include
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2026-02-10 12:00:46 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2026-02-10 12:00:46 -0800
commit4d84667627c4ff70826b349c449bbaf63b9af4e5 (patch)
tree27340dbd3ed4e7bbb8b95f53c1af4c4733331a47 /arch/x86/include
parenta9aabb3b839aba094ed80861054993785c61462c (diff)
parent7db06e329af30dcb170a6782c1714217ad65033d (diff)
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 ...
Diffstat (limited to 'arch/x86/include')
-rw-r--r--arch/x86/include/asm/amd/ibs.h2
-rw-r--r--arch/x86/include/asm/hardirq.h3
-rw-r--r--arch/x86/include/asm/idtentry.h6
-rw-r--r--arch/x86/include/asm/irq_vectors.h4
-rw-r--r--arch/x86/include/asm/msr-index.h5
-rw-r--r--arch/x86/include/asm/perf_event.h14
-rw-r--r--arch/x86/include/asm/unwind_user.h27
7 files changed, 44 insertions, 17 deletions
diff --git a/arch/x86/include/asm/amd/ibs.h b/arch/x86/include/asm/amd/ibs.h
index 3ee5903982c2..fcc8a5abe54e 100644
--- a/arch/x86/include/asm/amd/ibs.h
+++ b/arch/x86/include/asm/amd/ibs.h
@@ -110,7 +110,7 @@ union ibs_op_data3 {
__u64 ld_op:1, /* 0: load op */
st_op:1, /* 1: store op */
dc_l1tlb_miss:1, /* 2: data cache L1TLB miss */
- dc_l2tlb_miss:1, /* 3: data cache L2TLB hit in 2M page */
+ dc_l2tlb_miss:1, /* 3: data cache L2TLB miss in 2M page */
dc_l1tlb_hit_2m:1, /* 4: data cache L1TLB hit in 2M page */
dc_l1tlb_hit_1g:1, /* 5: data cache L1TLB hit in 1G page */
dc_l2tlb_hit_2m:1, /* 6: data cache L2TLB hit in 2M page */
diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h
index 6b6d472baa0b..9314642ae93c 100644
--- a/arch/x86/include/asm/hardirq.h
+++ b/arch/x86/include/asm/hardirq.h
@@ -19,6 +19,9 @@ typedef struct {
unsigned int kvm_posted_intr_wakeup_ipis;
unsigned int kvm_posted_intr_nested_ipis;
#endif
+#ifdef CONFIG_GUEST_PERF_EVENTS
+ unsigned int perf_guest_mediated_pmis;
+#endif
unsigned int x86_platform_ipis; /* arch dependent */
unsigned int apic_perf_irqs;
unsigned int apic_irq_work_irqs;
diff --git a/arch/x86/include/asm/idtentry.h b/arch/x86/include/asm/idtentry.h
index 3218770670d3..42bf6a58ec36 100644
--- a/arch/x86/include/asm/idtentry.h
+++ b/arch/x86/include/asm/idtentry.h
@@ -746,6 +746,12 @@ DECLARE_IDTENTRY_SYSVEC(POSTED_INTR_NESTED_VECTOR, sysvec_kvm_posted_intr_nested
# define fred_sysvec_kvm_posted_intr_nested_ipi NULL
#endif
+# ifdef CONFIG_GUEST_PERF_EVENTS
+DECLARE_IDTENTRY_SYSVEC(PERF_GUEST_MEDIATED_PMI_VECTOR, sysvec_perf_guest_mediated_pmi_handler);
+#else
+# define fred_sysvec_perf_guest_mediated_pmi_handler NULL
+#endif
+
# ifdef CONFIG_X86_POSTED_MSI
DECLARE_IDTENTRY_SYSVEC(POSTED_MSI_NOTIFICATION_VECTOR, sysvec_posted_msi_notification);
#else
diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h
index 47051871b436..85253fc8e384 100644
--- a/arch/x86/include/asm/irq_vectors.h
+++ b/arch/x86/include/asm/irq_vectors.h
@@ -77,7 +77,9 @@
*/
#define IRQ_WORK_VECTOR 0xf6
-/* 0xf5 - unused, was UV_BAU_MESSAGE */
+/* IRQ vector for PMIs when running a guest with a mediated PMU. */
+#define PERF_GUEST_MEDIATED_PMI_VECTOR 0xf5
+
#define DEFERRED_ERROR_VECTOR 0xf4
/* Vector on which hypervisor callbacks will be delivered */
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 3d0a0950d20a..6d1b69ea01c2 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -263,6 +263,11 @@
#define MSR_SNOOP_RSP_0 0x00001328
#define MSR_SNOOP_RSP_1 0x00001329
+#define MSR_OMR_0 0x000003e0
+#define MSR_OMR_1 0x000003e1
+#define MSR_OMR_2 0x000003e2
+#define MSR_OMR_3 0x000003e3
+
#define MSR_LBR_SELECT 0x000001c8
#define MSR_LBR_TOS 0x000001c9
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 7276ba70c88a..ff5acb8b199b 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -33,6 +33,7 @@
#define ARCH_PERFMON_EVENTSEL_CMASK 0xFF000000ULL
#define ARCH_PERFMON_EVENTSEL_BR_CNTR (1ULL << 35)
#define ARCH_PERFMON_EVENTSEL_EQ (1ULL << 36)
+#define ARCH_PERFMON_EVENTSEL_RDPMC_USER_DISABLE (1ULL << 37)
#define ARCH_PERFMON_EVENTSEL_UMASK2 (0xFFULL << 40)
#define INTEL_FIXED_BITS_STRIDE 4
@@ -40,6 +41,7 @@
#define INTEL_FIXED_0_USER (1ULL << 1)
#define INTEL_FIXED_0_ANYTHREAD (1ULL << 2)
#define INTEL_FIXED_0_ENABLE_PMI (1ULL << 3)
+#define INTEL_FIXED_0_RDPMC_USER_DISABLE (1ULL << 33)
#define INTEL_FIXED_3_METRICS_CLEAR (1ULL << 2)
#define HSW_IN_TX (1ULL << 32)
@@ -50,7 +52,7 @@
#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)
+ ICL_FIXED_0_ADAPTIVE | INTEL_FIXED_0_RDPMC_USER_DISABLE)
#define intel_fixed_bits_by_idx(_idx, _bits) \
((_bits) << ((_idx) * INTEL_FIXED_BITS_STRIDE))
@@ -226,7 +228,9 @@ union cpuid35_ebx {
unsigned int umask2:1;
/* EQ-bit Supported */
unsigned int eq:1;
- unsigned int reserved:30;
+ /* rdpmc user disable Supported */
+ unsigned int rdpmc_user_disable:1;
+ unsigned int reserved:29;
} split;
unsigned int full;
};
@@ -301,6 +305,7 @@ struct x86_pmu_capability {
unsigned int events_mask;
int events_mask_len;
unsigned int pebs_ept :1;
+ unsigned int mediated :1;
};
/*
@@ -759,6 +764,11 @@ static inline void perf_events_lapic_init(void) { }
static inline void perf_check_microcode(void) { }
#endif
+#ifdef CONFIG_PERF_GUEST_MEDIATED_PMU
+extern void perf_load_guest_lvtpc(u32 guest_lvtpc);
+extern void perf_put_guest_lvtpc(void);
+#endif
+
#if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_INTEL)
extern struct perf_guest_switch_msr *perf_guest_get_msrs(int *nr, void *data);
extern void x86_perf_get_lbr(struct x86_pmu_lbr *lbr);
diff --git a/arch/x86/include/asm/unwind_user.h b/arch/x86/include/asm/unwind_user.h
index 12064284bc4e..6e469044e4de 100644
--- a/arch/x86/include/asm/unwind_user.h
+++ b/arch/x86/include/asm/unwind_user.h
@@ -2,11 +2,23 @@
#ifndef _ASM_X86_UNWIND_USER_H
#define _ASM_X86_UNWIND_USER_H
-#ifdef CONFIG_HAVE_UNWIND_USER_FP
+#ifdef CONFIG_UNWIND_USER
#include <asm/ptrace.h>
#include <asm/uprobes.h>
+static inline int unwind_user_word_size(struct pt_regs *regs)
+{
+ /* We can't unwind VM86 stacks */
+ if (regs->flags & X86_VM_MASK)
+ return 0;
+ return user_64bit_mode(regs) ? 8 : 4;
+}
+
+#endif /* CONFIG_UNWIND_USER */
+
+#ifdef CONFIG_HAVE_UNWIND_USER_FP
+
#define ARCH_INIT_USER_FP_FRAME(ws) \
.cfa_off = 2*(ws), \
.ra_off = -1*(ws), \
@@ -19,22 +31,11 @@
.fp_off = 0, \
.use_fp = false,
-static inline int unwind_user_word_size(struct pt_regs *regs)
-{
- /* We can't unwind VM86 stacks */
- if (regs->flags & X86_VM_MASK)
- return 0;
-#ifdef CONFIG_X86_64
- if (!user_64bit_mode(regs))
- return sizeof(int);
-#endif
- return sizeof(long);
-}
-
static inline bool unwind_user_at_function_start(struct pt_regs *regs)
{
return is_uprobe_at_func_entry(regs);
}
+#define unwind_user_at_function_start unwind_user_at_function_start
#endif /* CONFIG_HAVE_UNWIND_USER_FP */