Merge tag 'perf-tools-fixes-for-v7.0-1-2026-03-13' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools

Pull perf tools fixes from Arnaldo Carvalho de Melo:

 - Fix stale build ID in module MMAP2 records in events synthesized for
   pre-existing processes

 - Fix rust cross compilation

 - hashmap__new() error pointer return handling fixes

 - Fix off-by-one bug in outside of functions check on the disasm code

 - Update header copies of kernel headers, including prctl.h, mount.h,
   fs.h, irq_vectors.h, perf_event.h, gfp_types.h, kvm.h, cpufeatures.h
   msr-index.h, also the syscall tables files that introduced the
   'rseq_slice_yield' syscall

 - Finish removal of ETM_OPT_* on the ARM coresight support, needed to
   sync the coresight-pmu.h header with the kernel sources

 - Make in-target rule robust against too long argument error

* tag 'perf-tools-fixes-for-v7.0-1-2026-03-13' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools: (22 commits)
  perf synthetic-events: Fix stale build ID in module MMAP2 records
  perf annotate loongarch: Fix off-by-one bug in outside check
  perf ftrace: Fix hashmap__new() error checking
  perf annotate: Fix hashmap__new() error checking
  perf cs-etm: Sync coresight-pmu.h header with the kernel sources
  perf cs-etm: Finish removal of ETM_OPT_*
  tools headers UAPI: Update tools' copy of linux/coresight-pmu.h
  tools headers: Update the syscall tables and unistd.h, to support the new 'rseq_slice_yield' syscall
  perf disasm: Fix off-by-one bug in outside check
  tools arch x86: Sync msr-index.h to pick MSR_{OMR_[0-3],CORE_PERF_GLOBAL_STATUS_SET}
  tools headers UAPI: Sync x86's asm/kvm.h with the kernel sources
  tools headers x86 cpufeatures: Sync with the kernel sources
  tools headers UAPI: Sync linux/kvm.h with the kernel sources
  tools headers: Update the linux/gfp_types.h copy with the kernel sources
  perf beauty: Update the linux/perf_event.h copy with the kernel sources
  perf beauty: Update the arch/x86/include/asm/irq_vectors.h copy with the kernel sources
  perf beauty: Sync UAPI linux/fs.h with kernel sources
  perf beauty: Sync linux/mount.h copy with the kernel sources
  tools build: Fix rust cross compilation
  perf build: Prevent "argument list too long" error
  ...

Author: torvalds

tools/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 */

tools/arch/x86/include/asm/cpufeatures.h

@@ -84,7 +84,7 @@
 #define X86_FEATURE_PEBS		( 3*32+12) /* "pebs" Precise-Event Based Sampling */
 #define X86_FEATURE_BTS			( 3*32+13) /* "bts" Branch Trace Store */
 #define X86_FEATURE_SYSCALL32		( 3*32+14) /* syscall in IA32 userspace */
-#define X86_FEATURE_SYSENTER32		( 3*32+15) /* sysenter in IA32 userspace */
+#define X86_FEATURE_SYSFAST32		( 3*32+15) /* sysenter/syscall in IA32 userspace */
 #define X86_FEATURE_REP_GOOD		( 3*32+16) /* "rep_good" REP microcode works well */
 #define X86_FEATURE_AMD_LBR_V2		( 3*32+17) /* "amd_lbr_v2" AMD Last Branch Record Extension Version 2 */
 #define X86_FEATURE_CLEAR_CPU_BUF	( 3*32+18) /* Clear CPU buffers using VERW */
@@ -326,6 +326,7 @@
 #define X86_FEATURE_AMX_FP16		(12*32+21) /* AMX fp16 Support */
 #define X86_FEATURE_AVX_IFMA            (12*32+23) /* Support for VPMADD52[H,L]UQ */
 #define X86_FEATURE_LAM			(12*32+26) /* "lam" Linear Address Masking */
+#define X86_FEATURE_MOVRS		(12*32+31) /* MOVRS instructions */
 
 /* AMD-defined CPU features, CPUID level 0x80000008 (EBX), word 13 */
 #define X86_FEATURE_CLZERO		(13*32+ 0) /* "clzero" CLZERO instruction */
@@ -472,6 +473,7 @@
 #define X86_FEATURE_GP_ON_USER_CPUID	(20*32+17) /* User CPUID faulting */
 
 #define X86_FEATURE_PREFETCHI		(20*32+20) /* Prefetch Data/Instruction to Cache Level */
+#define X86_FEATURE_ERAPS		(20*32+24) /* Enhanced Return Address Predictor Security */
 #define X86_FEATURE_SBPB		(20*32+27) /* Selective Branch Prediction Barrier */
 #define X86_FEATURE_IBPB_BRTYPE		(20*32+28) /* MSR_PRED_CMD[IBPB] flushes all branch type predictions */
 #define X86_FEATURE_SRSO_NO		(20*32+29) /* CPU is not affected by SRSO */

tools/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
 
@@ -1219,6 +1224,7 @@
 #define MSR_CORE_PERF_GLOBAL_STATUS	0x0000038e
 #define MSR_CORE_PERF_GLOBAL_CTRL	0x0000038f
 #define MSR_CORE_PERF_GLOBAL_OVF_CTRL	0x00000390
+#define MSR_CORE_PERF_GLOBAL_STATUS_SET	0x00000391
 
 #define MSR_PERF_METRICS		0x00000329
 

tools/arch/x86/include/uapi/asm/kvm.h

@@ -503,6 +503,7 @@ struct kvm_sync_regs {
 #define KVM_X86_GRP_SEV			1
 #  define KVM_X86_SEV_VMSA_FEATURES	0
 #  define KVM_X86_SNP_POLICY_BITS	1
+#  define KVM_X86_SEV_SNP_REQ_CERTS	2
 
 struct kvm_vmx_nested_state_data {
 	__u8 vmcs12[KVM_STATE_NESTED_VMX_VMCS_SIZE];
@@ -743,6 +744,7 @@ enum sev_cmd_id {
 	KVM_SEV_SNP_LAUNCH_START = 100,
 	KVM_SEV_SNP_LAUNCH_UPDATE,
 	KVM_SEV_SNP_LAUNCH_FINISH,
+	KVM_SEV_SNP_ENABLE_REQ_CERTS,
 
 	KVM_SEV_NR_MAX,
 };
@@ -914,8 +916,10 @@ struct kvm_sev_snp_launch_finish {
 	__u64 pad1[4];
 };
 
-#define KVM_X2APIC_API_USE_32BIT_IDS            (1ULL << 0)
-#define KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK  (1ULL << 1)
+#define KVM_X2APIC_API_USE_32BIT_IDS			_BITULL(0)
+#define KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK		_BITULL(1)
+#define KVM_X2APIC_ENABLE_SUPPRESS_EOI_BROADCAST	_BITULL(2)
+#define KVM_X2APIC_DISABLE_SUPPRESS_EOI_BROADCAST	_BITULL(3)
 
 struct kvm_hyperv_eventfd {
 	__u32 conn_id;

tools/build/Build.include

@@ -98,6 +98,15 @@ c_flags_2 = $(filter-out $(CFLAGS_REMOVE_$(basetarget).o), $(c_flags_1))
 c_flags   = $(filter-out $(CFLAGS_REMOVE_$(obj)), $(c_flags_2))
 cxx_flags = -Wp,-MD,$(depfile) -Wp,-MT,$@ $(CXXFLAGS) -D"BUILD_STR(s)=\#s" $(CXXFLAGS_$(basetarget).o) $(CXXFLAGS_$(obj))
 
+###
+# Rust flags to be used on rule definition, includes:
+# - global $(RUST_FLAGS)
+# - per target Rust flags
+# - per object Rust flags
+rust_flags_1 = $(RUST_FLAGS) $(RUST_FLAGS_$(basetarget).o) $(RUST_FLAGS_$(obj))
+rust_flags_2 = $(filter-out $(RUST_FLAGS_REMOVE_$(basetarget).o), $(rust_flags_1))
+rust_flags   = $(filter-out $(RUST_FLAGS_REMOVE_$(obj)), $(rust_flags_2))
+
 ###
 ## HOSTCC C flags
 

tools/build/Makefile.build

@@ -70,11 +70,13 @@ quiet_cmd_gen = GEN     $@
 # If there's nothing to link, create empty $@ object.
 quiet_cmd_ld_multi = LD      $@
       cmd_ld_multi = $(if $(strip $(obj-y)),\
-                     $(LD) -r -o $@  $(filter $(obj-y),$^),rm -f $@; $(AR) rcs $@)
+                     printf "$(objprefix)%s " $(patsubst $(objprefix)%,%,$(filter $(obj-y),$^)) | \
+                     xargs $(LD) -r -o $@,rm -f $@; $(AR) rcs $@)
 
 quiet_cmd_host_ld_multi = HOSTLD  $@
       cmd_host_ld_multi = $(if $(strip $(obj-y)),\
-                          $(HOSTLD) -r -o $@  $(filter $(obj-y),$^),rm -f $@; $(HOSTAR) rcs $@)
+                          printf "$(objprefix)%s " $(patsubst $(objprefix)%,%,$(filter $(obj-y),$^)) | \
+                          xargs $(HOSTLD) -r -o $@,rm -f $@; $(HOSTAR) rcs $@)
 
 rust_common_cmd = \
 	$(RUSTC) $(rust_flags) \

tools/include/linux/coresight-pmu.h

@@ -21,30 +21,6 @@
  */
 #define CORESIGHT_LEGACY_CPU_TRACE_ID(cpu)  (0x10 + (cpu * 2))
 
-/*
- * Below are the definition of bit offsets for perf option, and works as
- * arbitrary values for all ETM versions.
- *
- * Most of them are orignally from ETMv3.5/PTM's ETMCR config, therefore,
- * ETMv3.5/PTM doesn't define ETMCR config bits with prefix "ETM3_" and
- * directly use below macros as config bits.
- */
-#define ETM_OPT_BRANCH_BROADCAST 8
-#define ETM_OPT_CYCACC		12
-#define ETM_OPT_CTXTID		14
-#define ETM_OPT_CTXTID2		15
-#define ETM_OPT_TS		28
-#define ETM_OPT_RETSTK		29
-
-/* ETMv4 CONFIGR programming bits for the ETM OPTs */
-#define ETM4_CFG_BIT_BB         3
-#define ETM4_CFG_BIT_CYCACC	4
-#define ETM4_CFG_BIT_CTXTID	6
-#define ETM4_CFG_BIT_VMID	7
-#define ETM4_CFG_BIT_TS		11
-#define ETM4_CFG_BIT_RETSTK	12
-#define ETM4_CFG_BIT_VMID_OPT	15
-
 /*
  * Interpretation of the PERF_RECORD_AUX_OUTPUT_HW_ID payload.
  * Used to associate a CPU with the CoreSight Trace ID.

tools/include/linux/gfp_types.h

@@ -139,6 +139,8 @@ enum {
  * %__GFP_ACCOUNT causes the allocation to be accounted to kmemcg.
  *
  * %__GFP_NO_OBJ_EXT causes slab allocation to have no object extension.
+ * mark_obj_codetag_empty() should be called upon freeing for objects allocated
+ * with this flag to indicate that their NULL tags are expected and normal.
  */
 #define __GFP_RECLAIMABLE ((__force gfp_t)___GFP_RECLAIMABLE)
 #define __GFP_WRITE	((__force gfp_t)___GFP_WRITE)
@@ -309,8 +311,10 @@ enum {
  *
  * %GFP_ATOMIC users can not sleep and need the allocation to succeed. A lower
  * watermark is applied to allow access to "atomic reserves".
- * The current implementation doesn't support NMI and few other strict
- * non-preemptive contexts (e.g. raw_spin_lock). The same applies to %GFP_NOWAIT.
+ * The current implementation doesn't support NMI, nor contexts that disable
+ * preemption under PREEMPT_RT. This includes raw_spin_lock() and plain
+ * preempt_disable() - see "Memory allocation" in
+ * Documentation/core-api/real-time/differences.rst for more info.
  *
  * %GFP_KERNEL is typical for kernel-internal allocations. The caller requires
  * %ZONE_NORMAL or a lower zone for direct access but can direct reclaim.
@@ -321,6 +325,7 @@ enum {
  * %GFP_NOWAIT is for kernel allocations that should not stall for direct
  * reclaim, start physical IO or use any filesystem callback.  It is very
  * likely to fail to allocate memory, even for very small allocations.
+ * The same restrictions on calling contexts apply as for %GFP_ATOMIC.
  *
  * %GFP_NOIO will use direct reclaim to discard clean pages or slab pages
  * that do not require the starting of any physical IO.

tools/include/uapi/asm-generic/unistd.h

@@ -860,8 +860,11 @@ __SYSCALL(__NR_file_setattr, sys_file_setattr)
 #define __NR_listns 470
 __SYSCALL(__NR_listns, sys_listns)
 
+#define __NR_rseq_slice_yield 471
+__SYSCALL(__NR_rseq_slice_yield, sys_rseq_slice_yield)
+
 #undef __NR_syscalls
-#define __NR_syscalls 471
+#define __NR_syscalls 472
 
 /*
  * 32 bit systems traditionally used different

tools/include/uapi/linux/kvm.h

@@ -135,6 +135,12 @@ struct kvm_xen_exit {
 	} u;
 };
 
+struct kvm_exit_snp_req_certs {
+	__u64 gpa;
+	__u64 npages;
+	__u64 ret;
+};
+
 #define KVM_S390_GET_SKEYS_NONE   1
 #define KVM_S390_SKEYS_MAX        1048576
 
@@ -180,6 +186,8 @@ struct kvm_xen_exit {
 #define KVM_EXIT_MEMORY_FAULT     39
 #define KVM_EXIT_TDX              40
 #define KVM_EXIT_ARM_SEA          41
+#define KVM_EXIT_ARM_LDST64B      42
+#define KVM_EXIT_SNP_REQ_CERTS    43
 
 /* For KVM_EXIT_INTERNAL_ERROR */
 /* Emulate instruction failed. */
@@ -402,7 +410,7 @@ struct kvm_run {
 		} eoi;
 		/* KVM_EXIT_HYPERV */
 		struct kvm_hyperv_exit hyperv;
-		/* KVM_EXIT_ARM_NISV */
+		/* KVM_EXIT_ARM_NISV / KVM_EXIT_ARM_LDST64B */
 		struct {
 			__u64 esr_iss;
 			__u64 fault_ipa;
@@ -482,6 +490,8 @@ struct kvm_run {
 			__u64 gva;
 			__u64 gpa;
 		} arm_sea;
+		/* KVM_EXIT_SNP_REQ_CERTS */
+		struct kvm_exit_snp_req_certs snp_req_certs;
 		/* Fix the size of the union. */
 		char padding[256];
 	};
@@ -974,6 +984,7 @@ struct kvm_enable_cap {
 #define KVM_CAP_GUEST_MEMFD_FLAGS 244
 #define KVM_CAP_ARM_SEA_TO_USER 245
 #define KVM_CAP_S390_USER_OPEREXEC 246
+#define KVM_CAP_S390_KEYOP 247
 
 struct kvm_irq_routing_irqchip {
 	__u32 irqchip;
@@ -1219,6 +1230,16 @@ struct kvm_vfio_spapr_tce {
 	__s32	tablefd;
 };
 
+#define KVM_S390_KEYOP_ISKE 0x01
+#define KVM_S390_KEYOP_RRBE 0x02
+#define KVM_S390_KEYOP_SSKE 0x03
+struct kvm_s390_keyop {
+	__u64 guest_addr;
+	__u8  key;
+	__u8  operation;
+	__u8  pad[6];
+};
+
 /*
  * KVM_CREATE_VCPU receives as a parameter the vcpu slot, and returns
  * a vcpu fd.
@@ -1238,6 +1259,7 @@ struct kvm_vfio_spapr_tce {
 #define KVM_S390_UCAS_MAP        _IOW(KVMIO, 0x50, struct kvm_s390_ucas_mapping)
 #define KVM_S390_UCAS_UNMAP      _IOW(KVMIO, 0x51, struct kvm_s390_ucas_mapping)
 #define KVM_S390_VCPU_FAULT	 _IOW(KVMIO, 0x52, unsigned long)
+#define KVM_S390_KEYOP           _IOWR(KVMIO, 0x53, struct kvm_s390_keyop)
 
 /* Device model IOC */
 #define KVM_CREATE_IRQCHIP        _IO(KVMIO,   0x60)