* [PATCH 07/60] KVM: SVM: Add support for the SEV-SNP #HV IPI NAE event
From: Jörg Rödel @ 2026-06-08 14:41 UTC (permalink / raw)
To: Paolo Bonzini, Sean Christopherson
Cc: Tom Lendacky, ashish.kalra, michael.roth, nsaenz, anelkz,
James.Bottomley, Melody Wang, kvm, linux-kernel, kvmarm,
loongarch, linux-mips, linuxppc-dev, kvm-riscv, x86, coconut-svsm,
joerg.roedel
In-Reply-To: <20260608144252.351443-1-joro@8bytes.org>
From: Melody Wang <huibo.wang@amd.com>
The #HV IPI NAE event allows the guest to send an IPI to other vCPUs in the
guest when the Restricted Injection feature is enabled. Implement the NAE
event as per GHCB specification.
Co-developed-by: Thomas Lendacky <thomas.lendacky@amd.com>
Signed-off-by: Thomas Lendacky <thomas.lendacky@amd.com>
Signed-off-by: Melody Wang <huibo.wang@amd.com>
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
---
arch/x86/include/uapi/asm/svm.h | 1 +
arch/x86/kvm/lapic.c | 24 +++++++++++++++++++++++-
arch/x86/kvm/lapic.h | 2 ++
arch/x86/kvm/svm/sev.c | 28 ++++++++++++++++++++++++++++
4 files changed, 54 insertions(+), 1 deletion(-)
diff --git a/arch/x86/include/uapi/asm/svm.h b/arch/x86/include/uapi/asm/svm.h
index d84a13ac4627..d281dd21c540 100644
--- a/arch/x86/include/uapi/asm/svm.h
+++ b/arch/x86/include/uapi/asm/svm.h
@@ -122,6 +122,7 @@
#define SVM_VMGEXIT_HVDB_SET 1
#define SVM_VMGEXIT_HVDB_QUERY 2
#define SVM_VMGEXIT_HVDB_CLEAR 3
+#define SVM_VMGEXIT_HV_IPI 0x80000015ull
#define SVM_VMGEXIT_SNP_RUN_VMPL 0x80000018ull
#define SVM_VMGEXIT_SAVIC 0x8000001aull
#define SVM_VMGEXIT_SAVIC_REGISTER_GPA 0
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 4078e624ca66..ab40a2e4ab9d 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -2558,7 +2558,7 @@ static int kvm_lapic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val)
static int apic_mmio_write(struct kvm_vcpu *vcpu, struct kvm_io_device *this,
gpa_t address, int len, const void *data)
{
- struct kvm_lapic *apic = to_lapic(this);
+ struct kvm_lapic *apic = this ? to_lapic(this) : vcpu->arch.apic;
unsigned int offset = address - apic->base_address;
u32 val;
@@ -3583,3 +3583,25 @@ void kvm_lapic_exit(void)
static_key_deferred_flush(&apic_sw_disabled);
WARN_ON(static_branch_unlikely(&apic_sw_disabled.key));
}
+
+/* Send IPI by writing ICR with MSR write when X2APIC enabled, with mmio write when XAPIC enabled */
+int kvm_xapic_x2apic_send_ipi(struct kvm_vcpu *vcpu, u64 data)
+{
+ u32 icr_msr_addr = APIC_BASE_MSR + (APIC_ICR >> 4);
+ struct kvm_lapic *apic = vcpu->arch.apic;
+ gpa_t gpa = apic->base_address + APIC_ICR;
+
+ if (!kvm_lapic_enabled(vcpu))
+ return 1;
+
+ if (vcpu->arch.apic_base & X2APIC_ENABLE) {
+ if (!kvm_x2apic_msr_write(vcpu, icr_msr_addr, data))
+ return 0;
+ } else {
+ if (!apic_mmio_write(vcpu, NULL, gpa, 4, &data))
+ return 0;
+ }
+
+ return 1;
+}
+EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_xapic_x2apic_send_ipi);
diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h
index 274885af4ebc..afd440c88981 100644
--- a/arch/x86/kvm/lapic.h
+++ b/arch/x86/kvm/lapic.h
@@ -156,6 +156,8 @@ int kvm_hv_vapic_msr_read(struct kvm_vcpu *vcpu, u32 msr, u64 *data);
int kvm_lapic_set_pv_eoi(struct kvm_vcpu *vcpu, u64 data, unsigned long len);
void kvm_lapic_exit(void);
+int kvm_xapic_x2apic_send_ipi(struct kvm_vcpu *vcpu, u64 data);
+
u64 kvm_lapic_readable_reg_mask(struct kvm_lapic *apic);
static inline void kvm_lapic_set_irr(int vec, struct kvm_lapic *apic)
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 369fb1e36f58..d04f71836ef7 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -35,6 +35,7 @@
#include "svm_ops.h"
#include "cpuid.h"
#include "trace.h"
+#include "lapic.h"
#define GHCB_VERSION_MAX 2ULL
#define GHCB_VERSION_MIN 1ULL
@@ -3538,6 +3539,10 @@ static int sev_es_validate_vmgexit(struct vcpu_svm *svm)
if (!is_sev_snp_guest(vcpu))
goto vmgexit_err;
break;
+ case SVM_VMGEXIT_HV_IPI:
+ if (!sev_snp_guest(vcpu->kvm))
+ goto vmgexit_err;
+ break;
default:
reason = GHCB_ERR_INVALID_EVENT;
goto vmgexit_err;
@@ -4416,6 +4421,22 @@ static int sev_snp_hv_doorbell_page(struct vcpu_svm *svm)
return 0;
}
+static int sev_snp_hv_ipi(struct vcpu_svm *svm)
+{
+ struct kvm_vcpu *vcpu = &svm->vcpu;
+ u64 icr_info;
+
+ if (!sev_snp_guest(vcpu->kvm))
+ return -EINVAL;
+
+ icr_info = svm->vmcb->control.exit_info_1;
+
+ if (kvm_xapic_x2apic_send_ipi(vcpu, icr_info))
+ return -EINVAL;
+
+ return 0;
+}
+
static int sev_handle_vmgexit_msr_protocol(struct vcpu_svm *svm)
{
struct vmcb_control_area *control = &svm->vmcb->control;
@@ -4698,6 +4719,13 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu)
ghcb_set_sw_exit_info_2(svm->sev_es.ghcb, GHCB_ERR_INVALID_INPUT);
}
+ ret = 1;
+ break;
+ case SVM_VMGEXIT_HV_IPI:
+ if (sev_snp_hv_ipi(svm)) {
+ ghcb_set_sw_exit_info_1(svm->sev_es.ghcb, 2);
+ ghcb_set_sw_exit_info_2(svm->sev_es.ghcb, GHCB_ERR_INVALID_INPUT);
+ }
ret = 1;
break;
case SVM_VMGEXIT_UNSUPPORTED_EVENT:
--
2.53.0
^ permalink raw reply related
* [PATCH 22/60] kvm: Move kvm_vcpu pid members to struct kvm_vcpu_common
From: Jörg Rödel @ 2026-06-08 14:42 UTC (permalink / raw)
To: Paolo Bonzini, Sean Christopherson
Cc: Tom Lendacky, ashish.kalra, michael.roth, nsaenz, anelkz,
James.Bottomley, Melody Wang, kvm, linux-kernel, kvmarm,
loongarch, linux-mips, linuxppc-dev, kvm-riscv, x86, coconut-svsm,
joerg.roedel
In-Reply-To: <20260608144252.351443-1-joro@8bytes.org>
From: Joerg Roedel <joerg.roedel@amd.com>
These are the same across all planes for one VCPU, so make then
shared.
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
---
arch/arm64/include/asm/kvm_host.h | 2 +-
arch/arm64/kvm/arm.c | 2 +-
include/linux/kvm_host.h | 5 ++--
virt/kvm/kvm_main.c | 44 ++++++++++++++++---------------
4 files changed, 28 insertions(+), 25 deletions(-)
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index a49042bfa801..32dc484781f0 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -1270,7 +1270,7 @@ int __kvm_arm_vcpu_set_events(struct kvm_vcpu *vcpu,
void kvm_arm_halt_guest(struct kvm *kvm);
void kvm_arm_resume_guest(struct kvm *kvm);
-#define vcpu_has_run_once(vcpu) (!!READ_ONCE((vcpu)->pid))
+#define vcpu_has_run_once(vcpu) (!!READ_ONCE((vcpu)->common->pid))
#ifndef __KVM_NVHE_HYPERVISOR__
#define kvm_call_hyp_nvhe(f, ...) \
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 001f83f737ea..1e2f42134b74 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -726,7 +726,7 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
if (!cpumask_test_cpu(cpu, vcpu->kvm->arch.supported_cpus))
vcpu_set_on_unsupported_cpu(vcpu);
- vcpu->arch.pid = pid_nr(vcpu->pid);
+ vcpu->arch.pid = pid_nr(vcpu->common->pid);
}
void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 3c72a462ccfa..73786712495d 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -346,6 +346,9 @@ struct kvm_vcpu_common {
int mode;
u64 requests;
+ struct pid *pid;
+ rwlock_t pid_lock;
+
/* Scheduling state */
#ifdef CONFIG_PREEMPT_NOTIFIERS
struct preempt_notifier preempt_notifier;
@@ -368,8 +371,6 @@ struct kvm_vcpu {
struct kvm_run *run;
- struct pid *pid;
- rwlock_t pid_lock;
int sigset_active;
sigset_t sigset;
unsigned int halt_poll_ns;
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 7ea20d96bc89..af3c4e0081b8 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -475,6 +475,9 @@ static int kvm_vcpu_init_common(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned
common->kvm = kvm;
common->current_vcpu = vcpu;
+ common->pid = NULL;
+ rwlock_init(&common->pid_lock);
+
common->wants_to_run = false;
common->preempted = false;
common->ready = false;
@@ -510,8 +513,6 @@ static void kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id)
vcpu->kvm = kvm;
vcpu->plane = kvm->planes[0];
vcpu->vcpu_id = id;
- vcpu->pid = NULL;
- rwlock_init(&vcpu->pid_lock);
kvm_async_pf_vcpu_init(vcpu);
kvm_vcpu_set_in_spin_loop(vcpu, false);
@@ -539,6 +540,12 @@ static void kvm_vcpu_common_destroy(struct kvm_vcpu *vcpu)
kvm->created_vcpus--;
mutex_unlock(&common->kvm->lock);
+ /*
+ * No need for rcu_read_lock as VCPU_RUN is the only place that changes
+ * the common->pid pointer, and at destruction time all file descriptors
+ * are already gone.
+ */
+ put_pid(common->pid);
kfree(common);
}
@@ -549,13 +556,6 @@ static void kvm_vcpu_destroy(struct kvm_vcpu *vcpu)
kvm_vcpu_common_destroy(vcpu);
kvm_dirty_ring_free(&vcpu->dirty_ring);
- /*
- * No need for rcu_read_lock as VCPU_RUN is the only place that changes
- * the vcpu->pid pointer, and at destruction time all file descriptors
- * are already gone.
- */
- put_pid(vcpu->pid);
-
free_page((unsigned long)vcpu->run);
kmem_cache_free(kvm_vcpu_cache, vcpu);
}
@@ -3996,16 +3996,17 @@ EXPORT_SYMBOL_FOR_KVM_INTERNAL(__kvm_vcpu_kick);
int kvm_vcpu_yield_to(struct kvm_vcpu *target)
{
+ struct kvm_vcpu_common *common = target->common;
struct task_struct *task = NULL;
int ret;
- if (!read_trylock(&target->pid_lock))
+ if (!read_trylock(&common->pid_lock))
return 0;
- if (target->pid)
- task = get_pid_task(target->pid, PIDTYPE_PID);
+ if (common->pid)
+ task = get_pid_task(common->pid, PIDTYPE_PID);
- read_unlock(&target->pid_lock);
+ read_unlock(&common->pid_lock);
if (!task)
return 0;
@@ -4258,9 +4259,9 @@ static int vcpu_get_pid(void *data, u64 *val)
{
struct kvm_vcpu *vcpu = data;
- read_lock(&vcpu->pid_lock);
- *val = pid_nr(vcpu->pid);
- read_unlock(&vcpu->pid_lock);
+ read_lock(&vcpu->common->pid_lock);
+ *val = pid_nr(vcpu->common->pid);
+ read_unlock(&vcpu->common->pid_lock);
return 0;
}
@@ -4558,6 +4559,7 @@ static long kvm_vcpu_ioctl(struct file *filp,
return -EINTR;
switch (ioctl) {
case KVM_RUN: {
+ struct kvm_vcpu_common *common = vcpu->common;
struct pid *oldpid;
r = -EINVAL;
if (arg)
@@ -4569,7 +4571,7 @@ static long kvm_vcpu_ioctl(struct file *filp,
* read vcpu->pid while this vCPU is in KVM_RUN, e.g. to yield
* directly to this vCPU
*/
- oldpid = vcpu->pid;
+ oldpid = common->pid;
if (unlikely(oldpid != task_pid(current))) {
/* The thread running this VCPU changed. */
struct pid *newpid;
@@ -4579,15 +4581,15 @@ static long kvm_vcpu_ioctl(struct file *filp,
break;
newpid = get_task_pid(current, PIDTYPE_PID);
- write_lock(&vcpu->pid_lock);
- vcpu->pid = newpid;
- write_unlock(&vcpu->pid_lock);
+ write_lock(&common->pid_lock);
+ common->pid = newpid;
+ write_unlock(&common->pid_lock);
put_pid(oldpid);
}
vcpu->common->wants_to_run = !READ_ONCE(vcpu->run->immediate_exit__unsafe);
r = kvm_arch_vcpu_ioctl_run(vcpu);
- vcpu->common->wants_to_run = false;
+ common->wants_to_run = false;
/*
* FIXME: Remove this hack once all KVM architectures
--
2.53.0
^ permalink raw reply related
* [PATCH 02/60] KVM: SVM: Add support for the SEV-SNP #HV doorbell page NAE event
From: Jörg Rödel @ 2026-06-08 14:41 UTC (permalink / raw)
To: Paolo Bonzini, Sean Christopherson
Cc: Tom Lendacky, ashish.kalra, michael.roth, nsaenz, anelkz,
James.Bottomley, Melody Wang, kvm, linux-kernel, kvmarm,
loongarch, linux-mips, linuxppc-dev, kvm-riscv, x86, coconut-svsm,
joerg.roedel
In-Reply-To: <20260608144252.351443-1-joro@8bytes.org>
From: Melody Wang <huibo.wang@amd.com>
To support Restricted Injection, the SEV-SNP guest must register a doorbell
page for use with #HV. This is done using the #HV doorbell page NAE event.
This event consists of four actions: GET_PREFERRED, SET, QUERY, CLEAR.
Implement it per the GHCB specification.
Co-developed-by: Thomas Lendacky <thomas.lendacky@amd.com>
Signed-off-by: Thomas Lendacky <thomas.lendacky@amd.com>
Signed-off-by: Melody Wang <huibo.wang@amd.com>
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
---
arch/x86/include/uapi/asm/svm.h | 5 +++
arch/x86/kvm/svm/sev.c | 71 +++++++++++++++++++++++++++++++++
arch/x86/kvm/svm/svm.c | 3 ++
arch/x86/kvm/svm/svm.h | 2 +
4 files changed, 81 insertions(+)
diff --git a/arch/x86/include/uapi/asm/svm.h b/arch/x86/include/uapi/asm/svm.h
index 010a45c9f614..d84a13ac4627 100644
--- a/arch/x86/include/uapi/asm/svm.h
+++ b/arch/x86/include/uapi/asm/svm.h
@@ -117,6 +117,11 @@
#define SVM_VMGEXIT_AP_CREATE_ON_INIT 0
#define SVM_VMGEXIT_AP_CREATE 1
#define SVM_VMGEXIT_AP_DESTROY 2
+#define SVM_VMGEXIT_HVDB_PAGE 0x80000014ull
+#define SVM_VMGEXIT_HVDB_GET_PREFERRED 0
+#define SVM_VMGEXIT_HVDB_SET 1
+#define SVM_VMGEXIT_HVDB_QUERY 2
+#define SVM_VMGEXIT_HVDB_CLEAR 3
#define SVM_VMGEXIT_SNP_RUN_VMPL 0x80000018ull
#define SVM_VMGEXIT_SAVIC 0x8000001aull
#define SVM_VMGEXIT_SAVIC_REGISTER_GPA 0
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 6c6a6d663e29..b9ad1169cb2c 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -3522,6 +3522,10 @@ static int sev_es_validate_vmgexit(struct vcpu_svm *svm)
control->exit_info_1 == control->exit_info_2)
goto vmgexit_err;
break;
+ case SVM_VMGEXIT_HVDB_PAGE:
+ if (!is_sev_snp_guest(vcpu))
+ goto vmgexit_err;
+ break;
default:
reason = GHCB_ERR_INVALID_EVENT;
goto vmgexit_err;
@@ -4341,6 +4345,65 @@ static int snp_handle_ext_guest_req(struct vcpu_svm *svm, gpa_t req_gpa, gpa_t r
return 1; /* resume guest */
}
+static int sev_snp_hv_doorbell_page(struct vcpu_svm *svm)
+{
+ struct kvm_vcpu *vcpu = &svm->vcpu;
+ struct kvm_host_map hvdb_map;
+ gpa_t hvdb_gpa;
+ u64 request;
+
+ if (!is_sev_snp_guest(vcpu))
+ return -EINVAL;
+
+ request = svm->vmcb->control.exit_info_1;
+ hvdb_gpa = svm->vmcb->control.exit_info_2;
+
+ switch (request) {
+ case SVM_VMGEXIT_HVDB_GET_PREFERRED:
+ ghcb_set_sw_exit_info_2(svm->sev_es.ghcb, ~0ULL);
+ break;
+ case SVM_VMGEXIT_HVDB_SET:
+ svm->sev_es.hvdb_gpa = INVALID_PAGE;
+
+ if (!PAGE_ALIGNED(hvdb_gpa)) {
+ vcpu_unimpl(vcpu, "vmgexit: unaligned #HV doorbell page address [%#llx] from guest\n",
+ hvdb_gpa);
+ return -EINVAL;
+ }
+
+ if (!page_address_valid(vcpu, hvdb_gpa)) {
+ vcpu_unimpl(vcpu, "vmgexit: invalid #HV doorbell page address [%#llx] from guest\n",
+ hvdb_gpa);
+ return -EINVAL;
+ }
+
+ /* Map and unmap the GPA just to be sure the GPA is valid */
+ if (kvm_vcpu_map(vcpu, gpa_to_gfn(hvdb_gpa), &hvdb_map)) {
+ vcpu_unimpl(vcpu, "vmgexit: error mapping #HV doorbell page [%#llx] from guest\n",
+ hvdb_gpa);
+ return -EINVAL;
+ }
+ kvm_vcpu_unmap(vcpu, &hvdb_map);
+
+ svm->sev_es.hvdb_gpa = hvdb_gpa;
+ fallthrough;
+ case SVM_VMGEXIT_HVDB_QUERY:
+ ghcb_set_sw_exit_info_2(svm->sev_es.ghcb, svm->sev_es.hvdb_gpa);
+ break;
+ case SVM_VMGEXIT_HVDB_CLEAR:
+ svm->sev_es.hvdb_gpa = INVALID_PAGE;
+ break;
+ default:
+ svm->sev_es.hvdb_gpa = INVALID_PAGE;
+
+ vcpu_unimpl(vcpu, "vmgexit: invalid #HV doorbell page request [%#llx] from guest\n",
+ request);
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
static int sev_handle_vmgexit_msr_protocol(struct vcpu_svm *svm)
{
struct vmcb_control_area *control = &svm->vmcb->control;
@@ -4617,6 +4680,14 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu)
case SVM_VMGEXIT_EXT_GUEST_REQUEST:
ret = snp_handle_ext_guest_req(svm, control->exit_info_1, control->exit_info_2);
break;
+ case SVM_VMGEXIT_HVDB_PAGE:
+ if (sev_snp_hv_doorbell_page(svm)) {
+ ghcb_set_sw_exit_info_1(svm->sev_es.ghcb, 2);
+ ghcb_set_sw_exit_info_2(svm->sev_es.ghcb, GHCB_ERR_INVALID_INPUT);
+ }
+
+ ret = 1;
+ break;
case SVM_VMGEXIT_UNSUPPORTED_EVENT:
vcpu_unimpl(vcpu,
"vmgexit: unsupported event - exit_info_1=%#llx, exit_info_2=%#llx\n",
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index e02a38da5296..7981e7583384 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -1277,6 +1277,9 @@ static void __svm_vcpu_reset(struct kvm_vcpu *vcpu)
svm->nmi_masked = false;
svm->awaiting_iret_completion = false;
+
+ if (is_sev_es_guest(vcpu))
+ svm->sev_es.hvdb_gpa = INVALID_PAGE;
}
static void svm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index 5137416be593..fb956c37c941 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -270,6 +270,8 @@ struct vcpu_sev_es_state {
gpa_t snp_vmsa_gpa;
bool snp_ap_waiting_for_reset;
bool snp_has_guest_vmsa;
+
+ gpa_t hvdb_gpa;
};
struct vcpu_svm {
--
2.53.0
^ permalink raw reply related
* [PATCH v4 5/5] sparc: Remove remaining defconfig references to the pktcdvd driver
From: Catalin Iacob @ 2026-06-08 14:29 UTC (permalink / raw)
To: Thomas Bogendoerfer, Madhavan Srinivasan, Michael Ellerman,
Nicholas Piggin, Christophe Leroy (CS GROUP), Rich Felker,
John Paul Adrian Glaubitz, David S. Miller, Andreas Larsson,
James E.J. Bottomley, Martin K. Petersen, Jens Axboe
Cc: linux-mips, linux-kernel, linuxppc-dev, linux-sh, sparclinux,
linux-scsi, Catalin Iacob
In-Reply-To: <20260608-remove-pktcdvd-references-v4-0-72f88b04cc87@gmail.com>
Commit 1cea5180f2f8 ("block: remove pktcdvd driver") left behind some
CONFIG_CONFIG_CDROM_PKTCDVD* references in defconfigs. Remove them.
Signed-off-by: Catalin Iacob <iacobcatalin@gmail.com>
---
arch/sparc/configs/sparc64_defconfig | 2 --
1 file changed, 2 deletions(-)
diff --git a/arch/sparc/configs/sparc64_defconfig b/arch/sparc/configs/sparc64_defconfig
index 632081a262ba..4abea39281cd 100644
--- a/arch/sparc/configs/sparc64_defconfig
+++ b/arch/sparc/configs/sparc64_defconfig
@@ -60,8 +60,6 @@ CONFIG_CONNECTOR=m
CONFIG_BLK_DEV_LOOP=m
CONFIG_BLK_DEV_CRYPTOLOOP=m
CONFIG_BLK_DEV_NBD=m
-CONFIG_CDROM_PKTCDVD=m
-CONFIG_CDROM_PKTCDVD_WCACHE=y
CONFIG_ATA_OVER_ETH=m
CONFIG_SUNVDC=m
CONFIG_ATA=y
--
2.54.0
^ permalink raw reply related
* [PATCH v4 4/5] sh: Remove remaining defconfig reference to the pktcdvd driver
From: Catalin Iacob @ 2026-06-08 14:29 UTC (permalink / raw)
To: Thomas Bogendoerfer, Madhavan Srinivasan, Michael Ellerman,
Nicholas Piggin, Christophe Leroy (CS GROUP), Rich Felker,
John Paul Adrian Glaubitz, David S. Miller, Andreas Larsson,
James E.J. Bottomley, Martin K. Petersen, Jens Axboe
Cc: linux-mips, linux-kernel, linuxppc-dev, linux-sh, sparclinux,
linux-scsi, Catalin Iacob
In-Reply-To: <20260608-remove-pktcdvd-references-v4-0-72f88b04cc87@gmail.com>
Commit 1cea5180f2f8 ("block: remove pktcdvd driver") left behind a
CONFIG_CONFIG_CDROM_PKTCDVD reference in defconfigs. Remove it.
Signed-off-by: Catalin Iacob <iacobcatalin@gmail.com>
---
arch/sh/configs/sh2007_defconfig | 1 -
1 file changed, 1 deletion(-)
diff --git a/arch/sh/configs/sh2007_defconfig b/arch/sh/configs/sh2007_defconfig
index 5d9080499485..f287a41cd38c 100644
--- a/arch/sh/configs/sh2007_defconfig
+++ b/arch/sh/configs/sh2007_defconfig
@@ -45,7 +45,6 @@ CONFIG_NETWORK_SECMARK=y
CONFIG_NET_PKTGEN=y
CONFIG_BLK_DEV_LOOP=y
CONFIG_BLK_DEV_RAM=y
-CONFIG_CDROM_PKTCDVD=y
CONFIG_RAID_ATTRS=y
CONFIG_SCSI=y
CONFIG_BLK_DEV_SD=y
--
2.54.0
^ permalink raw reply related
* [PATCH v4 3/5] powerpc: Remove remaining defconfig references to the pktcdvd driver
From: Catalin Iacob @ 2026-06-08 14:29 UTC (permalink / raw)
To: Thomas Bogendoerfer, Madhavan Srinivasan, Michael Ellerman,
Nicholas Piggin, Christophe Leroy (CS GROUP), Rich Felker,
John Paul Adrian Glaubitz, David S. Miller, Andreas Larsson,
James E.J. Bottomley, Martin K. Petersen, Jens Axboe
Cc: linux-mips, linux-kernel, linuxppc-dev, linux-sh, sparclinux,
linux-scsi, Catalin Iacob
In-Reply-To: <20260608-remove-pktcdvd-references-v4-0-72f88b04cc87@gmail.com>
Commit 1cea5180f2f8 ("block: remove pktcdvd driver") left behind some
CONFIG_CONFIG_CDROM_PKTCDVD references in defconfigs. Remove them.
Signed-off-by: Catalin Iacob <iacobcatalin@gmail.com>
---
arch/powerpc/configs/g5_defconfig | 1 -
arch/powerpc/configs/ppc6xx_defconfig | 1 -
2 files changed, 2 deletions(-)
diff --git a/arch/powerpc/configs/g5_defconfig b/arch/powerpc/configs/g5_defconfig
index 5ca1676e6058..647775f6d174 100644
--- a/arch/powerpc/configs/g5_defconfig
+++ b/arch/powerpc/configs/g5_defconfig
@@ -57,7 +57,6 @@ CONFIG_BLK_DEV_LOOP=y
CONFIG_BLK_DEV_NBD=m
CONFIG_BLK_DEV_RAM=y
CONFIG_BLK_DEV_RAM_SIZE=65536
-CONFIG_CDROM_PKTCDVD=m
CONFIG_BLK_DEV_SD=y
CONFIG_CHR_DEV_ST=y
CONFIG_BLK_DEV_SR=y
diff --git a/arch/powerpc/configs/ppc6xx_defconfig b/arch/powerpc/configs/ppc6xx_defconfig
index eda1fec7ffd9..5c3e25fd8edd 100644
--- a/arch/powerpc/configs/ppc6xx_defconfig
+++ b/arch/powerpc/configs/ppc6xx_defconfig
@@ -306,7 +306,6 @@ CONFIG_BLK_DEV_LOOP=m
CONFIG_BLK_DEV_NBD=m
CONFIG_BLK_DEV_RAM=y
CONFIG_BLK_DEV_RAM_SIZE=16384
-CONFIG_CDROM_PKTCDVD=m
CONFIG_VIRTIO_BLK=m
CONFIG_ENCLOSURE_SERVICES=m
CONFIG_SENSORS_TSL2550=m
--
2.54.0
^ permalink raw reply related
* [PATCH v4 2/5] mips: Remove remaining defconfig references to the pktcdvd driver
From: Catalin Iacob @ 2026-06-08 14:29 UTC (permalink / raw)
To: Thomas Bogendoerfer, Madhavan Srinivasan, Michael Ellerman,
Nicholas Piggin, Christophe Leroy (CS GROUP), Rich Felker,
John Paul Adrian Glaubitz, David S. Miller, Andreas Larsson,
James E.J. Bottomley, Martin K. Petersen, Jens Axboe
Cc: linux-mips, linux-kernel, linuxppc-dev, linux-sh, sparclinux,
linux-scsi, Catalin Iacob
In-Reply-To: <20260608-remove-pktcdvd-references-v4-0-72f88b04cc87@gmail.com>
Commit 1cea5180f2f8 ("block: remove pktcdvd driver") left behind some
CONFIG_CONFIG_CDROM_PKTCDVD references in defconfigs. Remove them.
Signed-off-by: Catalin Iacob <iacobcatalin@gmail.com>
---
arch/mips/configs/fuloong2e_defconfig | 1 -
arch/mips/configs/ip22_defconfig | 1 -
arch/mips/configs/ip27_defconfig | 1 -
arch/mips/configs/ip30_defconfig | 1 -
arch/mips/configs/jazz_defconfig | 1 -
arch/mips/configs/malta_defconfig | 1 -
arch/mips/configs/malta_kvm_defconfig | 1 -
arch/mips/configs/maltaup_xpa_defconfig | 1 -
arch/mips/configs/rm200_defconfig | 1 -
arch/mips/configs/sb1250_swarm_defconfig | 1 -
10 files changed, 10 deletions(-)
diff --git a/arch/mips/configs/fuloong2e_defconfig b/arch/mips/configs/fuloong2e_defconfig
index b6fe3c962464..840130a73992 100644
--- a/arch/mips/configs/fuloong2e_defconfig
+++ b/arch/mips/configs/fuloong2e_defconfig
@@ -89,7 +89,6 @@ CONFIG_MTD_CFI_STAA=m
CONFIG_MTD_PHYSMAP=m
CONFIG_BLK_DEV_LOOP=y
CONFIG_BLK_DEV_RAM=m
-CONFIG_CDROM_PKTCDVD=m
CONFIG_ATA_OVER_ETH=m
CONFIG_BLK_DEV_SD=y
CONFIG_BLK_DEV_SR=y
diff --git a/arch/mips/configs/ip22_defconfig b/arch/mips/configs/ip22_defconfig
index e123848f94ab..61f09cc9ac12 100644
--- a/arch/mips/configs/ip22_defconfig
+++ b/arch/mips/configs/ip22_defconfig
@@ -177,7 +177,6 @@ CONFIG_NET_ACT_SIMP=m
CONFIG_NET_ACT_SKBEDIT=m
CONFIG_RFKILL=m
CONFIG_CONNECTOR=m
-CONFIG_CDROM_PKTCDVD=m
CONFIG_ATA_OVER_ETH=m
CONFIG_RAID_ATTRS=m
CONFIG_SCSI=y
diff --git a/arch/mips/configs/ip27_defconfig b/arch/mips/configs/ip27_defconfig
index fea0ccee6948..60da9cf71b72 100644
--- a/arch/mips/configs/ip27_defconfig
+++ b/arch/mips/configs/ip27_defconfig
@@ -83,7 +83,6 @@ CONFIG_CFG80211=m
CONFIG_MAC80211=m
CONFIG_RFKILL=m
CONFIG_BLK_DEV_LOOP=y
-CONFIG_CDROM_PKTCDVD=m
CONFIG_ATA_OVER_ETH=m
CONFIG_SCSI=y
CONFIG_BLK_DEV_SD=y
diff --git a/arch/mips/configs/ip30_defconfig b/arch/mips/configs/ip30_defconfig
index 718f3060d9fa..5c2911ff9a87 100644
--- a/arch/mips/configs/ip30_defconfig
+++ b/arch/mips/configs/ip30_defconfig
@@ -77,7 +77,6 @@ CONFIG_NET_ACT_PEDIT=m
CONFIG_NET_ACT_SKBEDIT=m
# CONFIG_VGA_ARB is not set
CONFIG_BLK_DEV_LOOP=y
-CONFIG_CDROM_PKTCDVD=m
CONFIG_ATA_OVER_ETH=m
CONFIG_SCSI=y
CONFIG_BLK_DEV_SD=y
diff --git a/arch/mips/configs/jazz_defconfig b/arch/mips/configs/jazz_defconfig
index a790c2610fd3..dd3486b8d1fc 100644
--- a/arch/mips/configs/jazz_defconfig
+++ b/arch/mips/configs/jazz_defconfig
@@ -33,7 +33,6 @@ CONFIG_BLK_DEV_FD=m
CONFIG_BLK_DEV_LOOP=m
CONFIG_BLK_DEV_NBD=m
CONFIG_BLK_DEV_RAM=m
-CONFIG_CDROM_PKTCDVD=m
CONFIG_ATA_OVER_ETH=m
CONFIG_RAID_ATTRS=m
CONFIG_SCSI=y
diff --git a/arch/mips/configs/malta_defconfig b/arch/mips/configs/malta_defconfig
index 81704ec67f09..b10dac71f400 100644
--- a/arch/mips/configs/malta_defconfig
+++ b/arch/mips/configs/malta_defconfig
@@ -224,7 +224,6 @@ CONFIG_BLK_DEV_FD=m
CONFIG_BLK_DEV_LOOP=m
CONFIG_BLK_DEV_NBD=m
CONFIG_BLK_DEV_RAM=y
-CONFIG_CDROM_PKTCDVD=m
CONFIG_ATA_OVER_ETH=m
CONFIG_RAID_ATTRS=m
CONFIG_BLK_DEV_SD=y
diff --git a/arch/mips/configs/malta_kvm_defconfig b/arch/mips/configs/malta_kvm_defconfig
index 82a97f58bce1..bdd5d99884e3 100644
--- a/arch/mips/configs/malta_kvm_defconfig
+++ b/arch/mips/configs/malta_kvm_defconfig
@@ -228,7 +228,6 @@ CONFIG_BLK_DEV_FD=m
CONFIG_BLK_DEV_LOOP=m
CONFIG_BLK_DEV_NBD=m
CONFIG_BLK_DEV_RAM=y
-CONFIG_CDROM_PKTCDVD=m
CONFIG_ATA_OVER_ETH=m
CONFIG_RAID_ATTRS=m
CONFIG_BLK_DEV_SD=y
diff --git a/arch/mips/configs/maltaup_xpa_defconfig b/arch/mips/configs/maltaup_xpa_defconfig
index 0f9ef20744f9..523c0ff329ac 100644
--- a/arch/mips/configs/maltaup_xpa_defconfig
+++ b/arch/mips/configs/maltaup_xpa_defconfig
@@ -226,7 +226,6 @@ CONFIG_BLK_DEV_FD=m
CONFIG_BLK_DEV_LOOP=m
CONFIG_BLK_DEV_NBD=m
CONFIG_BLK_DEV_RAM=y
-CONFIG_CDROM_PKTCDVD=m
CONFIG_ATA_OVER_ETH=m
CONFIG_RAID_ATTRS=m
CONFIG_BLK_DEV_SD=y
diff --git a/arch/mips/configs/rm200_defconfig b/arch/mips/configs/rm200_defconfig
index ad9fbd0cbb38..60054e54bc5a 100644
--- a/arch/mips/configs/rm200_defconfig
+++ b/arch/mips/configs/rm200_defconfig
@@ -177,7 +177,6 @@ CONFIG_PARIDE_ON26=m
CONFIG_BLK_DEV_LOOP=m
CONFIG_BLK_DEV_NBD=m
CONFIG_BLK_DEV_RAM=m
-CONFIG_CDROM_PKTCDVD=m
CONFIG_ATA_OVER_ETH=m
CONFIG_RAID_ATTRS=m
CONFIG_SCSI=y
diff --git a/arch/mips/configs/sb1250_swarm_defconfig b/arch/mips/configs/sb1250_swarm_defconfig
index 4a25b8d3e507..a50a7c097542 100644
--- a/arch/mips/configs/sb1250_swarm_defconfig
+++ b/arch/mips/configs/sb1250_swarm_defconfig
@@ -43,7 +43,6 @@ CONFIG_FW_LOADER=m
CONFIG_CONNECTOR=m
CONFIG_BLK_DEV_RAM=y
CONFIG_BLK_DEV_RAM_SIZE=9220
-CONFIG_CDROM_PKTCDVD=m
CONFIG_ATA_OVER_ETH=m
CONFIG_RAID_ATTRS=m
CONFIG_BLK_DEV_SD=y
--
2.54.0
^ permalink raw reply related
* [PATCH v4 0/5] Remove remaining references to the pktcdvd driver
From: Catalin Iacob @ 2026-06-08 14:29 UTC (permalink / raw)
To: Thomas Bogendoerfer, Madhavan Srinivasan, Michael Ellerman,
Nicholas Piggin, Christophe Leroy (CS GROUP), Rich Felker,
John Paul Adrian Glaubitz, David S. Miller, Andreas Larsson,
James E.J. Bottomley, Martin K. Petersen, Jens Axboe
Cc: linux-mips, linux-kernel, linuxppc-dev, linux-sh, sparclinux,
linux-scsi, Catalin Iacob
In-Reply-To: <20260530-remove-pktcdvd-references-v1-1-aa56941d4315@gmail.com>
Found this incidentally while looking at kernel sources to understand
what pktcdvd is
Signed-off-by: Catalin Iacob <iacobcatalin@gmail.com>
---
Changes in v4:
- Combined the removal of the export and moving the declaration to the
private header info the same patch as requested by Bart. No code
change.
- Link to v3: https://patch.msgid.link/20260604-remove-pktcdvd-references-v3-0-e2f06fb4eef4@gmail.com
Changes in v3:
- Split the defconfig changes in one patch per arch
- Add patch to move the declaration of scsi_device_from_queue to the
private header as suggested by John
- Link to v2: https://patch.msgid.link/20260603-remove-pktcdvd-references-v2-1-c4402154d53a@gmail.com
Changes in v2:
- Reworded commit message on John Paul Adrian's suggestion to be about
the removed references not the export symbol
- Link to v1: https://patch.msgid.link/20260530-remove-pktcdvd-references-v1-1-aa56941d4315@gmail.com
To: "James E.J. Bottomley" <James.Bottomley@HansenPartnership.com>
To: "Martin K. Petersen" <martin.petersen@oracle.com>
To: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
To: Madhavan Srinivasan <maddy@linux.ibm.com>
To: Michael Ellerman <mpe@ellerman.id.au>
To: Nicholas Piggin <npiggin@gmail.com>
To: "Christophe Leroy (CS GROUP)" <chleroy@kernel.org>
To: Rich Felker <dalias@libc.org>
To: John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de>
To: "David S. Miller" <davem@davemloft.net>
To: Andreas Larsson <andreas@gaisler.com>
Cc: linux-scsi@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Cc: linux-mips@vger.kernel.org
Cc: linuxppc-dev@lists.ozlabs.org
Cc: linux-sh@vger.kernel.org
Cc: sparclinux@vger.kernel.org
---
Catalin Iacob (5):
scsi: core: Remove export for scsi_device_from_queue()
mips: Remove remaining defconfig references to the pktcdvd driver
powerpc: Remove remaining defconfig references to the pktcdvd driver
sh: Remove remaining defconfig reference to the pktcdvd driver
sparc: Remove remaining defconfig references to the pktcdvd driver
arch/mips/configs/fuloong2e_defconfig | 1 -
arch/mips/configs/ip22_defconfig | 1 -
arch/mips/configs/ip27_defconfig | 1 -
arch/mips/configs/ip30_defconfig | 1 -
arch/mips/configs/jazz_defconfig | 1 -
arch/mips/configs/malta_defconfig | 1 -
arch/mips/configs/malta_kvm_defconfig | 1 -
arch/mips/configs/maltaup_xpa_defconfig | 1 -
arch/mips/configs/rm200_defconfig | 1 -
arch/mips/configs/sb1250_swarm_defconfig | 1 -
arch/powerpc/configs/g5_defconfig | 1 -
arch/powerpc/configs/ppc6xx_defconfig | 1 -
arch/sh/configs/sh2007_defconfig | 1 -
arch/sparc/configs/sparc64_defconfig | 2 --
drivers/scsi/scsi_lib.c | 8 --------
drivers/scsi/scsi_priv.h | 1 +
include/scsi/scsi_device.h | 1 -
17 files changed, 1 insertion(+), 24 deletions(-)
---
base-commit: 4549871118cf616eecdd2d939f78e3b9e1dddc48
change-id: 20260530-remove-pktcdvd-references-9d5c6362a5de
Best regards,
--
Catalin Iacob <iacobcatalin@gmail.com>
^ permalink raw reply
* [PATCH v4 1/5] scsi: core: Remove export for scsi_device_from_queue()
From: Catalin Iacob @ 2026-06-08 14:29 UTC (permalink / raw)
To: Thomas Bogendoerfer, Madhavan Srinivasan, Michael Ellerman,
Nicholas Piggin, Christophe Leroy (CS GROUP), Rich Felker,
John Paul Adrian Glaubitz, David S. Miller, Andreas Larsson,
James E.J. Bottomley, Martin K. Petersen, Jens Axboe
Cc: linux-mips, linux-kernel, linuxppc-dev, linux-sh, sparclinux,
linux-scsi, Catalin Iacob
In-Reply-To: <20260608-remove-pktcdvd-references-v4-0-72f88b04cc87@gmail.com>
Commit 1cea5180f2f8 ("block: remove pktcdvd driver") left behind an
export that is now dead code. Remove it and move the declaration of
scsi_device_from_queue() to drivers/scsi/scsi_priv.h.
Signed-off-by: Catalin Iacob <iacobcatalin@gmail.com>
---
drivers/scsi/scsi_lib.c | 8 --------
drivers/scsi/scsi_priv.h | 1 +
include/scsi/scsi_device.h | 1 -
3 files changed, 1 insertion(+), 9 deletions(-)
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 85eef401925a..b67f0dc79499 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -2224,14 +2224,6 @@ struct scsi_device *scsi_device_from_queue(struct request_queue *q)
return sdev;
}
-/*
- * pktcdvd should have been integrated into the SCSI layers, but for historical
- * reasons like the old IDE driver it isn't. This export allows it to safely
- * probe if a given device is a SCSI one and only attach to that.
- */
-#ifdef CONFIG_CDROM_PKTCDVD_MODULE
-EXPORT_SYMBOL_GPL(scsi_device_from_queue);
-#endif
/**
* scsi_block_requests - Utility function used by low-level drivers to prevent
diff --git a/drivers/scsi/scsi_priv.h b/drivers/scsi/scsi_priv.h
index 7a193cc04e5b..37e5601be2b8 100644
--- a/drivers/scsi/scsi_priv.h
+++ b/drivers/scsi/scsi_priv.h
@@ -102,6 +102,7 @@ void scsi_eh_done(struct scsi_cmnd *scmd);
/* scsi_lib.c */
extern void scsi_device_unbusy(struct scsi_device *sdev, struct scsi_cmnd *cmd);
+extern struct scsi_device *scsi_device_from_queue(struct request_queue *q);
extern void scsi_queue_insert(struct scsi_cmnd *cmd,
enum scsi_qc_status reason);
extern void scsi_io_completion(struct scsi_cmnd *, unsigned int);
diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h
index 9c2a7bbe5891..9f716497a959 100644
--- a/include/scsi/scsi_device.h
+++ b/include/scsi/scsi_device.h
@@ -407,7 +407,6 @@ void scsi_attach_vpd(struct scsi_device *sdev);
void scsi_cdl_check(struct scsi_device *sdev);
int scsi_cdl_enable(struct scsi_device *sdev, bool enable);
-extern struct scsi_device *scsi_device_from_queue(struct request_queue *q);
extern int __must_check scsi_device_get(struct scsi_device *);
extern void scsi_device_put(struct scsi_device *);
extern struct scsi_device *scsi_device_lookup(struct Scsi_Host *,
--
2.54.0
^ permalink raw reply related
* Re: [PATCH] KVM: PPC: Book3S HV: Validate arch_compat against host compatibility mode
From: Vaibhav Jain @ 2026-06-08 14:19 UTC (permalink / raw)
To: Gautam Menghani
Cc: Amit Machhiwal, linuxppc-dev, Madhavan Srinivasan,
Harsh Prateek Bora, Ritesh Harjani, Anushree Mathur,
Nicholas Piggin, Michael Ellerman, Christophe Leroy (CS GROUP),
kvm, stable, linux-kernel
In-Reply-To: <aiaAPQmWG7JXGoGn@Gautams-MacBook-Pro.local>
Gautam Menghani <gautam@linux.ibm.com> writes:
> On Fri, Jun 05, 2026 at 12:55:50PM +0530, Vaibhav Jain wrote:
>> Hi Gautam,
>>
>> Thanks for testing this patch. Few questions:
>> Gautam Menghani <gautam@linux.ibm.com> writes:
>>
>> > On Wed, Jun 03, 2026 at 07:45:39PM +0530, Amit Machhiwal wrote:
>> >> On IBM POWER systems, newer processor generations can operate in
>> >> compatibility modes corresponding to earlier generations. This becomes
>> >> relevant for nested virtualization, where nested KVM guests may need to
>> >> run with a specific processor compatibility level.
>> >>
>> <snip>
>> >
>> > I booted a KVM guest on LPAR with this patch in the following scenarios:
>> <snip>
>>
>> > 3. P11 guest on P11 host booted in P10 compat mode: No error observed
>> This should have resulted in an error since booting a P11 guest on P10
>> compat mode host is not allowed with/without this patch. Can you please
>> check your test env and share the boot results.
>
> - lscpu output (host P11 LPAR booted in p10 compat mode)
> # lscpu 03:35:13 [3/3]
> Architecture: ppc64le
> Byte Order: Little Endian
> CPU(s): 960
> On-line CPU(s) list: 0-959
> Model name: POWER10 (architected), altivec supported
> Model: 2.0 (pvr 0082 0200)
> Thread(s) per core: 8
> Core(s) per socket: 15
> Socket(s): 8
> Physical sockets: 4
> Physical chips: 2
> Physical cores/chip: 16
>
>
> - lscpu output from guest
> # lscpu
> Architecture: ppc64le
> Byte Order: Little Endian
> CPU(s): 4
> On-line CPU(s) list: 0-3
> Model name: Power11 (raw), altivec supported
> Model: 2.0 (pvr 0082 0200)
> Thread(s) per core: 1
> Core(s) per socket: 4
> Socket(s): 1
>
Argh, this doesnt look right. The kernel patch should have prevented the
P11 compat guest boot on P10 compat host. Looks like you havent used the
corrosponding Qemu patch [1] that could have prevented this from
happening.
Had a off mailing list discussion with Amit on how to address this issue
and he will be sending a new version of the patch to address this issue.
[1] https://lore.kernel.org/all/20260502140021.69712-2-amachhiw@linux.ibm.com/
>
>
> - QEMU command line
> /usr/bin/qemu-system-ppc64 -device virtio-blk-pci,drive=drive0,id=virtblk0 \
> -drive file=/home/gautam/images/fc41.qcow2,format=qcow2,if=none,id=drive0 \
> -m 100G -smp 4 -cpu host -nographic -machine pseries,ic-mode=xics -accel kvm
>
>
> Thanks,
> Gautam
>
--
Cheers
~ Vaibhav
^ permalink raw reply
* Re: [kvm-unit-tests RFC PATCH 1/6] powerpc: add pmu tests
From: Thomas Huth @ 2026-06-08 13:57 UTC (permalink / raw)
To: Chinmay Rath
Cc: npiggin, harshpb, lvivier, linuxppc-dev, kvm, andrew.jones, sbhat
In-Reply-To: <b7aa2c73-be32-47e2-8452-e626845f4d3e@redhat.com>
On 08/06/2026 14.45, Thomas Huth wrote:
> On 02/06/2026 08.48, Chinmay Rath wrote:
>> From: Nicholas Piggin <npiggin@gmail.com>
>>
>> Add some initial PMU testing.
>>
>> - PMC5/6 tests
>> - PMAE / PMI test
>> - BHRB basic tests
>>
>> Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
>> Signed-off-by: Chinmay Rath <rathc@linux.ibm.com>
>> ---
>> lib/powerpc/asm/processor.h | 2 +
>> lib/powerpc/asm/reg.h | 9 +
>> lib/powerpc/asm/setup.h | 1 +
>> lib/powerpc/setup.c | 20 ++
>> powerpc/Makefile.common | 3 +-
>> powerpc/pmu.c | 567 ++++++++++++++++++++++++++++++++++++
>> powerpc/unittests.cfg | 3 +
>> 7 files changed, 604 insertions(+), 1 deletion(-)
>> create mode 100644 powerpc/pmu.c
>
> Hi Chinmay,
>
> the problem with Clang on Travis [*] still seems to persist:
>
> https://app.travis-ci.com/github/huth/kvm-unit-tests/jobs/639614142
>
> Could you please have a look?
>
> Thanks,
> Thomas
>
>
> [*] This already happened with Nicolas' last version:
>
> https://www.spinics.net/lists/kvm/msg351218.html
I managed to get access to a ppc64 machine. The error is:
/tmp/pmu-eab466.s: Assembler messages:
/tmp/pmu-eab466.s:1649: Error: unrecognized opcode: `ldat'
clang: error: assembler command failed with exit code 1 (use -v to see
invocation)
make: *** [<builtin>: powerpc/pmu.o] Error 1
HTH,
Thomas
^ permalink raw reply
* [PATCH 3/3] ASoC: bcm: cygnus: use scoped child node loop
From: Cássio Gabriel @ 2026-06-08 13:39 UTC (permalink / raw)
To: Srinivas Kandagatla, Mark Brown, Takashi Iwai, Liam Girdwood,
Jaroslav Kysela, Herve Codina, Shengjiu Wang, Xiubo Li,
Fabio Estevam, Nicolin Chen, Ray Jui, Scott Branden,
Broadcom internal kernel review list
Cc: linux-sound, linux-arm-msm, linux-kernel, linuxppc-dev,
linux-arm-kernel, notify, Cássio Gabriel
In-Reply-To: <20260608-asoc-of-node-scoped-cleanup-v1-0-9e3ac518dc2e@gmail.com>
cygnus_ssp_probe() manually puts the current child node before returning
from the child parsing loop on error.
Use for_each_available_child_of_node_scoped() so the current child node is
released automatically on early return and normal loop exit.
Signed-off-by: Cássio Gabriel <cassiogabrielcontato@gmail.com>
---
sound/soc/bcm/cygnus-ssp.c | 10 ++++------
1 file changed, 4 insertions(+), 6 deletions(-)
diff --git a/sound/soc/bcm/cygnus-ssp.c b/sound/soc/bcm/cygnus-ssp.c
index e0ce0232eb1e..47706ae0a31f 100644
--- a/sound/soc/bcm/cygnus-ssp.c
+++ b/sound/soc/bcm/cygnus-ssp.c
@@ -1298,7 +1298,6 @@ static int audio_clk_init(struct platform_device *pdev,
static int cygnus_ssp_probe(struct platform_device *pdev)
{
struct device *dev = &pdev->dev;
- struct device_node *child_node;
struct cygnus_audio *cygaud;
int err;
int node_count;
@@ -1331,16 +1330,15 @@ static int cygnus_ssp_probe(struct platform_device *pdev)
active_port_count = 0;
- for_each_available_child_of_node(pdev->dev.of_node, child_node) {
+ for_each_available_child_of_node_scoped(pdev->dev.of_node, child_node) {
err = parse_ssp_child_node(pdev, child_node, cygaud,
&cygnus_ssp_dai[active_port_count]);
/* negative is err, 0 is active and good, 1 is disabled */
- if (err < 0) {
- of_node_put(child_node);
+ if (err < 0)
return err;
- }
- else if (!err) {
+
+ if (!err) {
dev_dbg(dev, "Activating DAI: %s\n",
cygnus_ssp_dai[active_port_count].name);
active_port_count++;
--
2.54.0
^ permalink raw reply related
* [PATCH 2/3] ASoC: fsl: fsl_qmc_audio: use scoped child node loop
From: Cássio Gabriel @ 2026-06-08 13:39 UTC (permalink / raw)
To: Srinivas Kandagatla, Mark Brown, Takashi Iwai, Liam Girdwood,
Jaroslav Kysela, Herve Codina, Shengjiu Wang, Xiubo Li,
Fabio Estevam, Nicolin Chen, Ray Jui, Scott Branden,
Broadcom internal kernel review list
Cc: linux-sound, linux-arm-msm, linux-kernel, linuxppc-dev,
linux-arm-kernel, notify, Cássio Gabriel
In-Reply-To: <20260608-asoc-of-node-scoped-cleanup-v1-0-9e3ac518dc2e@gmail.com>
qmc_audio_probe() manually puts the current child node before returning
from the DAI parsing loop on error.
Use for_each_available_child_of_node_scoped() so the current child node is
released automatically on early return and normal loop exit.
Signed-off-by: Cássio Gabriel <cassiogabrielcontato@gmail.com>
---
sound/soc/fsl/fsl_qmc_audio.c | 7 ++-----
1 file changed, 2 insertions(+), 5 deletions(-)
diff --git a/sound/soc/fsl/fsl_qmc_audio.c b/sound/soc/fsl/fsl_qmc_audio.c
index 76e014dfb6d7..d0f644573f49 100644
--- a/sound/soc/fsl/fsl_qmc_audio.c
+++ b/sound/soc/fsl/fsl_qmc_audio.c
@@ -905,7 +905,6 @@ static int qmc_audio_probe(struct platform_device *pdev)
{
struct device_node *np = pdev->dev.of_node;
struct qmc_audio *qmc_audio;
- struct device_node *child;
unsigned int i;
int ret;
@@ -931,14 +930,12 @@ static int qmc_audio_probe(struct platform_device *pdev)
}
i = 0;
- for_each_available_child_of_node(np, child) {
+ for_each_available_child_of_node_scoped(np, child) {
ret = qmc_audio_dai_parse(qmc_audio, child,
qmc_audio->dais + i,
qmc_audio->dai_drivers + i);
- if (ret) {
- of_node_put(child);
+ if (ret)
return ret;
- }
i++;
}
--
2.54.0
^ permalink raw reply related
* [PATCH 1/3] ASoC: qcom: common: use scoped OF node handling
From: Cássio Gabriel @ 2026-06-08 13:39 UTC (permalink / raw)
To: Srinivas Kandagatla, Mark Brown, Takashi Iwai, Liam Girdwood,
Jaroslav Kysela, Herve Codina, Shengjiu Wang, Xiubo Li,
Fabio Estevam, Nicolin Chen, Ray Jui, Scott Branden,
Broadcom internal kernel review list
Cc: linux-sound, linux-arm-msm, linux-kernel, linuxppc-dev,
linux-arm-kernel, notify, Cássio Gabriel
In-Reply-To: <20260608-asoc-of-node-scoped-cleanup-v1-0-9e3ac518dc2e@gmail.com>
qcom_snd_parse_of() manually drops the link child node and the
cpu/platform/codec child nodes on error paths and at the end of each
iteration.
Use for_each_available_child_of_node_scoped() for the link node and
__free(device_node) for the named child nodes. This keeps the existing
ownership rules for DAI component phandle references, while removing the
manual cleanup labels from a path that has previously needed OF refcount
fixes.
Signed-off-by: Cássio Gabriel <cassiogabrielcontato@gmail.com>
---
sound/soc/qcom/common.c | 47 +++++++++++++++--------------------------------
1 file changed, 15 insertions(+), 32 deletions(-)
diff --git a/sound/soc/qcom/common.c b/sound/soc/qcom/common.c
index cf1f3a767cee..edc4611691f7 100644
--- a/sound/soc/qcom/common.c
+++ b/sound/soc/qcom/common.c
@@ -25,10 +25,6 @@ static const struct snd_soc_dapm_widget qcom_jack_snd_widgets[] = {
int qcom_snd_parse_of(struct snd_soc_card *card)
{
- struct device_node *np;
- struct device_node *codec = NULL;
- struct device_node *platform = NULL;
- struct device_node *cpu = NULL;
struct device *dev = card->dev;
struct snd_soc_dai_link *link;
struct of_phandle_args args;
@@ -82,12 +78,10 @@ int qcom_snd_parse_of(struct snd_soc_card *card)
card->num_links = num_links;
link = card->dai_link;
- for_each_available_child_of_node(dev->of_node, np) {
+ for_each_available_child_of_node_scoped(dev->of_node, np) {
dlc = devm_kcalloc(dev, 2, sizeof(*dlc), GFP_KERNEL);
- if (!dlc) {
- ret = -ENOMEM;
- goto err_put_np;
- }
+ if (!dlc)
+ return -ENOMEM;
link->cpus = &dlc[0];
link->platforms = &dlc[1];
@@ -98,32 +92,33 @@ int qcom_snd_parse_of(struct snd_soc_card *card)
ret = of_property_read_string(np, "link-name", &link->name);
if (ret) {
dev_err(card->dev, "error getting codec dai_link name\n");
- goto err_put_np;
+ return ret;
}
- cpu = of_get_child_by_name(np, "cpu");
- platform = of_get_child_by_name(np, "platform");
- codec = of_get_child_by_name(np, "codec");
+ struct device_node *cpu __free(device_node) =
+ of_get_child_by_name(np, "cpu");
+ struct device_node *platform __free(device_node) =
+ of_get_child_by_name(np, "platform");
+ struct device_node *codec __free(device_node) =
+ of_get_child_by_name(np, "codec");
if (!cpu) {
dev_err(dev, "%s: Can't find cpu DT node\n", link->name);
- ret = -EINVAL;
- goto err;
+ return -EINVAL;
}
ret = snd_soc_of_get_dlc(cpu, &args, link->cpus, 0);
if (ret) {
dev_err_probe(card->dev, ret,
"%s: error getting cpu dai name\n", link->name);
- goto err;
+ return ret;
}
link->id = args.args[0];
if (link->id >= LPASS_MAX_PORT) {
dev_err(dev, "%s: Invalid cpu dai id %d\n", link->name, link->id);
- ret = -EINVAL;
- goto err;
+ return -EINVAL;
}
if (platform) {
@@ -132,8 +127,7 @@ int qcom_snd_parse_of(struct snd_soc_card *card)
0);
if (!link->platforms->of_node) {
dev_err(card->dev, "%s: platform dai not found\n", link->name);
- ret = -EINVAL;
- goto err;
+ return -EINVAL;
}
} else {
link->platforms->of_node = link->cpus->of_node;
@@ -144,7 +138,7 @@ int qcom_snd_parse_of(struct snd_soc_card *card)
if (ret < 0) {
dev_err_probe(card->dev, ret,
"%s: codec dai not found\n", link->name);
- goto err;
+ return ret;
}
if (platform) {
@@ -167,10 +161,6 @@ int qcom_snd_parse_of(struct snd_soc_card *card)
link->stream_name = link->name;
link++;
-
- of_node_put(cpu);
- of_node_put(codec);
- of_node_put(platform);
}
if (!card->dapm_widgets) {
@@ -179,13 +169,6 @@ int qcom_snd_parse_of(struct snd_soc_card *card)
}
return 0;
-err:
- of_node_put(cpu);
- of_node_put(codec);
- of_node_put(platform);
-err_put_np:
- of_node_put(np);
- return ret;
}
EXPORT_SYMBOL_GPL(qcom_snd_parse_of);
--
2.54.0
^ permalink raw reply related
* [PATCH 0/3] ASoC: use scoped OF node handling in manual cleanup paths
From: Cássio Gabriel @ 2026-06-08 13:39 UTC (permalink / raw)
To: Srinivas Kandagatla, Mark Brown, Takashi Iwai, Liam Girdwood,
Jaroslav Kysela, Herve Codina, Shengjiu Wang, Xiubo Li,
Fabio Estevam, Nicolin Chen, Ray Jui, Scott Branden,
Broadcom internal kernel review list
Cc: linux-sound, linux-arm-msm, linux-kernel, linuxppc-dev,
linux-arm-kernel, notify, Cássio Gabriel
Some ASoC drivers still manually release child OF nodes
when leaving child-node iteration loops early.
Convert these focused cases to scoped OF node cleanup
so early returns and normal loop exits keep the same node
lifetime handling without explicit of_node_put() calls.
- Patch 1 updates qcom_snd_parse_of() to use
for_each_available_child_of_node_scoped() for link nodes and
__free(device_node) for temporary cpu/platform/codec child nodes.
- Patch 2 updates fsl_qmc_audio to use
for_each_available_child_of_node_scoped() for DAI child-node parsing.
- Patch 3 updates cygnus-ssp to use
for_each_available_child_of_node_scoped() for SSP child-node parsing.
Signed-off-by: Cássio Gabriel <cassiogabrielcontato@gmail.com>
---
Cássio Gabriel (3):
ASoC: qcom: common: use scoped OF node handling
ASoC: fsl: fsl_qmc_audio: use scoped child node loop
ASoC: bcm: cygnus: use scoped child node loop
sound/soc/bcm/cygnus-ssp.c | 10 ++++-----
sound/soc/fsl/fsl_qmc_audio.c | 7 ++-----
sound/soc/qcom/common.c | 47 ++++++++++++++-----------------------------
3 files changed, 21 insertions(+), 43 deletions(-)
---
base-commit: 112b3b39550d94f94eb7e44fd865716835d9aab2
Best regards,
--
Cássio Gabriel <cassiogabrielcontato@gmail.com>
^ permalink raw reply
* Re: [BUG] kernel BUG in team driver: buffer overflow in team_add_slave()
From: Jiayuan Chen @ 2026-06-08 12:12 UTC (permalink / raw)
To: Yeswanth Krishna, netdev, venkat88; +Cc: linux-kernel, linuxppc-dev
In-Reply-To: <3ad19e86-234c-408f-896e-0d6c774fea49@linux.ibm.com>
On 6/8/26 6:00 PM, Yeswanth Krishna wrote:
> Hi Team ,
>
> I encountered a kernel crash while running selftests on kernel 7.1.0-rc6
> on a POWER10 system. The crash occurs when adding a slave device to a
> team interface, triggered by FORTIFY_SOURCE detecting a buffer overflow.
>
> **System Information:**
> - Kernel: 7.1.0-rc6-160099.42-default+ (commit d548c6f4301b)
> - Architecture: powerpc64le (ppc64le)
> - Hardware: IBM POWER10 (9043-MRX), pSeries
> - Config: CONFIG_FORTIFY_SOURCE=y
>
> **Crash Location:**
>
> [ 3492.897824][T77143] kernel BUG at lib/string_helpers.c:1044!
> [ 3492.898057][T77143] NIP [c000000000ac1120] __fortify_panic+0x18/0x28
> [ 3492.898096][T77143] [c00000000efdb350] [c00800000b857a18]
> team_add_slave+0xc60/0xcc0 [team]
>
>
> **Call Trace:**
>
> __fortify_panic+0x18/0x28
> team_add_slave+0xc60/0xcc0 [team]
> do_set_master+0x19c/0x240
> do_setlink.isra.0+0x388/0x1450
> rtnl_newlink+0xac8/0x1030
> rtnetlink_rcv_msg+0x450/0x530
> netlink_rcv_skb+0x74/0x1b0
> rtnetlink_rcv+0x24/0x40
> netlink_unicast+0x2e0/0x430
> netlink_sendmsg+0x210/0x580
> ____sys_sendmsg+0x30c/0x470
> ___sys_sendmsg+0x94/0xf0
> __sys_sendmsg+0x84/0x100
> system_call_exception+0x154/0x2b0
>
> **Reproducer:**
> The crash is 100% reproducible via selftests:
> ```bash
> cd tools/testing/selftests
> make -C drivers/net/team run_tests
I tried this under x86, but the warning was not triggered with
CONFIG_FORTIFY_SOURCE.
Hope somebody who has a PPC system can test it.
^ permalink raw reply
* [RFC PATCH 4/4] perf data: Add --to-trace-dat option for converting perf.data tracepoint events into trace.dat format
From: Tanushree Shah @ 2026-06-08 12:59 UTC (permalink / raw)
To: acme, jolsa, adrian.hunter, vmolnaro, mpetlan, tmricht, maddy,
irogers, namhyung, linux-kernel
Cc: linux-perf-users, linuxppc-dev, atrajeev, hbathini, Tejas.Manhas1,
Tanushree.Shah, Shivani.Nittor, Tanushree Shah
In-Reply-To: <20260608125951.90425-2-tshah@linux.ibm.com>
Add new command-line option to perf data convert for generating
trace.dat output files.
The --to-trace-dat option:
- Accepts output filename for trace.dat format
- Mutually exclusive with --to-ctf and --to-json
- Calls trace_convert__perf2dat() to perform conversion
Usage:
$ perf record -e sched:* -a sleep 1
$ perf data convert --to-trace-dat=trace.dat
$ trace-cmd report trace.dat
Signed-off-by: Tanushree Shah <tshah@linux.ibm.com>
---
tools/perf/builtin-data.c | 38 ++++++++++++++++++++++++++++++++++++--
1 file changed, 36 insertions(+), 2 deletions(-)
diff --git a/tools/perf/builtin-data.c b/tools/perf/builtin-data.c
index 4c08ccb8c06b..96ccab77456a 100644
--- a/tools/perf/builtin-data.c
+++ b/tools/perf/builtin-data.c
@@ -30,6 +30,9 @@ static const char *data_usage[] = {
static const char *to_json;
static const char *to_ctf;
+#ifdef HAVE_LIBTRACEEVENT
+ static const char *trace_dat_output;
+#endif
static struct perf_data_convert_opts opts = {
.force = false,
.all = false,
@@ -48,6 +51,10 @@ static const struct option data_options[] = {
OPT_BOOLEAN(0, "all", &opts.all, "Convert all events"),
OPT_STRING(0, "time", &opts.time_str, "str",
"Time span of interest (start,stop)"),
+#ifdef HAVE_LIBTRACEEVENT
+ OPT_STRING(0, "to-trace-dat", &trace_dat_output,
+ "file", "Convert to trace.dat format using perf.data tracepoints"),
+#endif
OPT_END()
};
@@ -65,16 +72,43 @@ static int cmd_data_convert(int argc, const char **argv)
pr_err("You cannot specify both --to-ctf and --to-json.\n");
return -1;
}
+#ifdef HAVE_LIBTRACEEVENT
+ if (trace_dat_output && (to_json || to_ctf)) {
+ pr_err("You cannot specify --to-trace-dat with --to-ctf or --to-json.\n");
+ return -1;
+ }
+#endif
+
#ifdef HAVE_LIBBABELTRACE_SUPPORT
+ #ifdef HAVE_LIBTRACEEVENT
+ if (!to_json && !to_ctf && !trace_dat_output) {
+ pr_err("You must specify one of --to-ctf, --to-json, or --to-trace-dat.\n");
+ return -1;
+ }
+ #else
if (!to_json && !to_ctf) {
pr_err("You must specify one of --to-ctf or --to-json.\n");
return -1;
}
+ #endif
#else
+ #ifdef HAVE_LIBTRACEEVENT
+ if (!to_json && !trace_dat_output) {
+ pr_err("You must specify --to-json or --to-trace-dat.\n");
+ return -1;
+ }
+ #else
if (!to_json) {
pr_err("You must specify --to-json.\n");
- return -1;
-}
+ return -1
+ }
+ #endif
+#endif
+
+#ifdef HAVE_LIBTRACEEVENT
+ if (trace_dat_output)
+ return trace_convert__perf2dat(input_name ? input_name : "perf.data",
+ trace_dat_output, &opts);
#endif
if (to_json)
--
2.53.0
^ permalink raw reply related
* [RFC PATCH 3/4] perf data-convert: Add perf.data to trace.dat conversion backend
From: Tanushree Shah @ 2026-06-08 12:59 UTC (permalink / raw)
To: acme, jolsa, adrian.hunter, vmolnaro, mpetlan, tmricht, maddy,
irogers, namhyung, linux-kernel
Cc: linux-perf-users, linuxppc-dev, atrajeev, hbathini, Tejas.Manhas1,
Tanushree.Shah, Shivani.Nittor, Tanushree Shah
In-Reply-To: <20260608125951.90425-2-tshah@linux.ibm.com>
Add data-convert-trace.c implementing trace_convert__perf2dat() to
convert perf.data tracepoint events to trace.dat format.
process_sample_event() is invoked for each PERF_TYPE_TRACEPOINT sample
during perf_session__process_events(), storing raw event bytes per-cpu
via trace_dat__collect_cpu_event().
Once all samples are collected:
- trace_dat__write_options_section1() writes the OPTIONS section with
CPUCOUNT, TRACECLOCK, HEADER_INFO, FTRACE_EVENTS, EVENT_FORMATS,
KALLSYMS, CMDLINES and DONE options.
- trace_dat__write__options_section2() writes the OPTIONS section with
BUFFER option holding per-cpu data offset placeholders and the DONE
option.
- trace_dat__write_flyrecord_section() builds ring buffer pages
per-cpu and patches BUFFER option with final offsets and sizes
Per-cpu buffers are sized to tep_get_page_size() from the session
tep handle and released on all exit paths.
Signed-off-by: Tanushree Shah <tshah@linux.ibm.com>
---
tools/perf/util/Build | 1 +
tools/perf/util/data-convert-trace.c | 152 +++++++++++++++++++++++++++
tools/perf/util/data-convert.h | 4 +
3 files changed, 157 insertions(+)
create mode 100644 tools/perf/util/data-convert-trace.c
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index c000d8032d25..88022b24e170 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -236,6 +236,7 @@ ifeq ($(CONFIG_LIBTRACEEVENT),y)
endif
perf-util-y += data-convert-json.o
+perf-util-$(CONFIG_LIBTRACEEVENT) += data-convert-trace.o
perf-util-y += scripting-engines/
diff --git a/tools/perf/util/data-convert-trace.c b/tools/perf/util/data-convert-trace.c
new file mode 100644
index 000000000000..e4f8b817be36
--- /dev/null
+++ b/tools/perf/util/data-convert-trace.c
@@ -0,0 +1,152 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright 2026, IBM Corporation
+ * Author: Tanushree Shah <tshah@linux.ibm.com>
+ *
+ * data-convert-trace.c
+ *
+ * Implements perf.data to trace.dat format conversion for tracepoint events.
+ */
+
+#include <errno.h>
+#include <inttypes.h>
+#include <linux/compiler.h>
+#include <linux/err.h>
+
+#include "data-convert.h"
+#include "session.h"
+#include "evsel.h"
+#include "tool.h"
+#include "debug.h"
+#include "trace-dat.h"
+#include "trace-event.h"
+#include "event.h"
+#include "sample.h"
+#include "evlist.h"
+
+struct trace_convert {
+ struct perf_tool tool;
+ u64 events_count;
+};
+
+/* Store raw tracepoint event data in per-cpu buffer for trace.dat flyrecord */
+static int process_sample_event(const struct perf_tool *tool,
+ union perf_event *event __maybe_unused,
+ struct perf_sample *sample,
+ struct evsel *evsel,
+ struct machine *machine __maybe_unused)
+{
+ struct trace_convert *tc = container_of(tool, struct trace_convert, tool);
+
+ /* Collect raw tracepoint data per-cpu */
+ if (trace_dat_fp && sample->raw_size > 0 &&
+ evsel->core.attr.type == PERF_TYPE_TRACEPOINT) {
+ if (trace_dat__collect_cpu_event(sample->cpu, sample->time,
+ sample->raw_data, sample->raw_size) < 0) {
+ pr_err("Failed to collect CPU event\n");
+ return -ENOMEM;
+ }
+ tc->events_count++;
+ }
+
+ return 0;
+}
+
+/* Convert perf.data tracepoint events to trace.dat format */
+int trace_convert__perf2dat(const char *input, const char *to_trace,
+ struct perf_data_convert_opts *opts)
+{
+ struct perf_session *session;
+ struct trace_convert tc = {
+ .events_count = 0,
+ };
+ struct perf_data data = {
+ .path = input,
+ .mode = PERF_DATA_MODE_READ,
+ .force = opts->force,
+ };
+ int ret = -EINVAL;
+ bool cpu_buffers_initialized = false;
+
+ /* Initialize tool with all required callbacks */
+ perf_tool__init(&tc.tool, /*ordered_events=*/true);
+ tc.tool.sample = process_sample_event;
+
+ /* Open output trace.dat file */
+ trace_dat_fp = fopen(to_trace, "wb");
+ if (!trace_dat_fp) {
+ pr_err("Failed to open output file: %s\n", to_trace);
+ return -EINVAL;
+ }
+
+ /* Open perf.data session - this writes trace.dat metadata sections */
+ session = perf_session__new(&data, &tc.tool);
+ if (IS_ERR(session)) {
+ pr_err("Failed to open perf.data file\n");
+ ret = PTR_ERR(session);
+ goto out_close;
+ }
+
+ /* Initialize per-CPU buffers for flyrecord data */
+ if (session->tevent.pevent) {
+ trace_dat_page_size = tep_get_page_size(session->tevent.pevent);
+ if (trace_dat__init_cpu_buffers(session->header.env.nr_cpus_online) < 0) {
+ pr_err("Failed to initialize CPU buffers\n");
+ ret = -ENOMEM;
+ goto out_delete;
+ }
+ cpu_buffers_initialized = true;
+ }
+
+ /* Process all events - collects raw data per-cpu */
+ ret = perf_session__process_events(session);
+ if (ret < 0) {
+ pr_err("Failed to process events\n");
+ goto out_delete;
+ }
+
+ /* Skip file creation if no tracepoint events found */
+ if (tc.events_count == 0) {
+ pr_warning("No tracepoint events found in '%s', skipping trace.dat creation\n",
+ input);
+ ret = -EINVAL;
+ goto out_delete;
+ }
+
+ /* Write trace.dat options and flyrecord sections */
+ if (trace_dat__write_options_section1() < 0) {
+ pr_err("Failed to write options section1\n");
+ ret = -EIO;
+ goto out_delete;
+ }
+ if (trace_dat__write_options_section2() < 0) {
+ pr_err("Failed to write options section2\n");
+ ret = -EIO;
+ goto out_delete;
+ }
+ if (trace_dat__write_flyrecord_section() < 0) {
+ pr_err("Failed to write flyrecord section\n");
+ ret = -EIO;
+ goto out_delete;
+ }
+
+ pr_info("[ perf data convert: Converted '%s' into trace.dat format '%s' ]\n",
+ input, to_trace);
+ pr_info("[ perf data convert: Converted %llu events ]\n",
+ (unsigned long long)tc.events_count);
+
+ ret = 0;
+
+out_delete:
+ if (cpu_buffers_initialized)
+ trace_dat__free_cpu_buffers();
+ perf_session__delete(session);
+out_close:
+ if (trace_dat_fp) {
+ fclose(trace_dat_fp);
+ trace_dat_fp = NULL;
+ }
+ if (ret != 0)
+ unlink(to_trace);
+ return ret;
+}
diff --git a/tools/perf/util/data-convert.h b/tools/perf/util/data-convert.h
index ee651fa680a1..d958e68367fe 100644
--- a/tools/perf/util/data-convert.h
+++ b/tools/perf/util/data-convert.h
@@ -19,4 +19,8 @@ int bt_convert__perf2ctf(const char *input_name, const char *to_ctf,
int bt_convert__perf2json(const char *input_name, const char *to_ctf,
struct perf_data_convert_opts *opts);
+#ifdef HAVE_LIBTRACEEVENT
+int trace_convert__perf2dat(const char *input, const char *to_trace,
+ struct perf_data_convert_opts *opts);
+#endif /* HAVE_LIBTRACEEVENT */
#endif /* __DATA_CONVERT_H */
--
2.53.0
^ permalink raw reply related
* [RFC PATCH 2/4] perf/trace-event: Write trace.dat metadata sections during parsing
From: Tanushree Shah @ 2026-06-08 12:59 UTC (permalink / raw)
To: acme, jolsa, adrian.hunter, vmolnaro, mpetlan, tmricht, maddy,
irogers, namhyung, linux-kernel
Cc: linux-perf-users, linuxppc-dev, atrajeev, hbathini, Tejas.Manhas1,
Tanushree.Shah, Shivani.Nittor, Tanushree Shah
In-Reply-To: <20260608125951.90425-2-tshah@linux.ibm.com>
Perf already captures the tracing metadata as a part of
data section in perf.data
When trace_dat_fp is set, write trace.dat compatible metadata
sections using the perf provided raw buffers.
Sections written:
- Initial format header (magic, version, endian, long_size,
page_size, compression, options_offset placeholder)
- Section 16: HEADER INFO (header_page + header_event)
- Section 17: FTRACE EVENT FORMATS
- Section 18: EVENT FORMATS (per system/event format files)
- Section 19: KALLSYMS
- Section 21: CMDLINES
- Section 15: STRINGS (written last after all sections)
Signed-off-by: Tanushree Shah <tshah@linux.ibm.com>
---
tools/perf/util/trace-event-read.c | 259 ++++++++++++++++++++++++++++-
1 file changed, 252 insertions(+), 7 deletions(-)
diff --git a/tools/perf/util/trace-event-read.c b/tools/perf/util/trace-event-read.c
index ecbbb93f0185..815577703c2e 100644
--- a/tools/perf/util/trace-event-read.c
+++ b/tools/perf/util/trace-event-read.c
@@ -19,6 +19,7 @@
#include "trace-event.h"
#include "debug.h"
#include "util.h"
+#include "trace-dat.h"
static int input_fd;
@@ -145,10 +146,9 @@ static char *read_string(void)
static int read_proc_kallsyms(struct tep_handle *pevent)
{
unsigned int size;
+ char *buf;
size = read4(pevent);
- if (!size)
- return 0;
/*
* Just skip it, now that we configure libtraceevent to use the
* tools/perf/ symbol resolver.
@@ -160,11 +160,56 @@ static int read_proc_kallsyms(struct tep_handle *pevent)
* payload", so that older tools can continue reading it and interpret
* it as "no kallsyms payload is present".
*/
- lseek(input_fd, size, SEEK_CUR);
+ /* Write kallsyms section with empty payload if no data */
+ if (!size) {
+ if (trace_dat_fp) {
+ unsigned short section_id = TRACE_DAT_SECTION_KALLSYMS;
+ unsigned short flags = 0;
+ unsigned long long section_size = sizeof(unsigned int);
+ unsigned int kallsyms_data = 0;
+ unsigned int string_id = STRID_KALLSYMS;
+
+ trace_dat_kallsyms_offset = ftell(trace_dat_fp);
+ if (!fwrite(§ion_id, sizeof(unsigned short), 1, trace_dat_fp) ||
+ !fwrite(&flags, sizeof(unsigned short), 1, trace_dat_fp) ||
+ !fwrite(&string_id, sizeof(unsigned int), 1, trace_dat_fp) ||
+ !fwrite(§ion_size, sizeof(unsigned long long), 1, trace_dat_fp) ||
+ !fwrite(&kallsyms_data, sizeof(unsigned int), 1, trace_dat_fp))
+ return -EIO;
+ }
+ return 0;
+ }
+ buf = malloc(size);
+ if (buf == NULL)
+ return -1;
+ if (read(input_fd, buf, size) < 0) {
+ free(buf);
+ return -1;
+ }
trace_data_size += size;
+ /* Write kallsyms section with data */
+ if (trace_dat_fp) {
+ unsigned short section_id = TRACE_DAT_SECTION_KALLSYMS;
+ unsigned int string_id = STRID_KALLSYMS;
+ unsigned long long section_size = sizeof(unsigned int) + size;
+ unsigned short flags = 0;
+
+ trace_dat_kallsyms_offset = ftell(trace_dat_fp);
+ if (!fwrite(§ion_id, sizeof(unsigned short), 1, trace_dat_fp) ||
+ !fwrite(&flags, sizeof(unsigned short), 1, trace_dat_fp) ||
+ !fwrite(&string_id, sizeof(unsigned int), 1, trace_dat_fp) ||
+ !fwrite(§ion_size, sizeof(unsigned long long), 1, trace_dat_fp) ||
+ !fwrite(&size, sizeof(unsigned int), 1, trace_dat_fp) ||
+ !fwrite(buf, 1, size, trace_dat_fp)) {
+ free(buf);
+ return -EIO;
+ }
+ }
+ free(buf);
return 0;
}
+
static int read_ftrace_printk(struct tep_handle *pevent)
{
unsigned int size;
@@ -195,6 +240,13 @@ static int read_ftrace_printk(struct tep_handle *pevent)
static int read_header_files(struct tep_handle *pevent)
{
unsigned long long size;
+ unsigned long long header_page_size;
+ unsigned long long header_event_size;
+ char *header_event;
+ unsigned short section_id;
+ unsigned short flags;
+ unsigned int string_id;
+ unsigned long long section_size;
char *header_page;
char buf[BUFSIZ];
int ret = 0;
@@ -209,6 +261,7 @@ static int read_header_files(struct tep_handle *pevent)
size = read8(pevent);
+ header_page_size = size;
header_page = malloc(size);
if (header_page == NULL)
return -1;
@@ -227,19 +280,59 @@ static int read_header_files(struct tep_handle *pevent)
*/
tep_set_long_size(pevent, tep_get_header_page_size(pevent));
}
- free(header_page);
- if (do_read(buf, 13) < 0)
+ if (do_read(buf, 13) < 0) {
+ free(header_page);
return -1;
+ }
if (memcmp(buf, "header_event", 13) != 0) {
pr_debug("did not read header event");
+ free(header_page);
return -1;
}
size = read8(pevent);
- skip(size);
+ if (trace_dat_fp) {
+ header_event_size = size;
+ header_event = malloc(size);
+ if (header_event == NULL) {
+ free(header_page);
+ return -1;
+ }
+ if (do_read(header_event, size) < 0) {
+ free(header_page);
+ free(header_event);
+ return -1;
+ }
+ /* Write header_page and header_event to trace.dat */
+ section_id = TRACE_DAT_SECTION_HEADER;
+ flags = 0;
+ string_id = STRID_HEADERS;
+ section_size = 12 + 8 + header_page_size + 13 + 8 +
+ header_event_size;
+
+ trace_dat_header_info_offset = ftell(trace_dat_fp);
+ if (!fwrite(§ion_id, sizeof(unsigned short), 1, trace_dat_fp) ||
+ !fwrite(&flags, sizeof(unsigned short), 1, trace_dat_fp) ||
+ !fwrite(&string_id, sizeof(unsigned int), 1, trace_dat_fp) ||
+ !fwrite(§ion_size, sizeof(unsigned long long), 1, trace_dat_fp) ||
+ !fwrite("header_page\0", 1, 12, trace_dat_fp) ||
+ !fwrite(&header_page_size, sizeof(unsigned long long), 1, trace_dat_fp) ||
+ !fwrite(header_page, 1, header_page_size, trace_dat_fp) ||
+ !fwrite("header_event\0", 1, 13, trace_dat_fp) ||
+ !fwrite(&header_event_size, sizeof(unsigned long long), 1, trace_dat_fp) ||
+ !fwrite(header_event, 1, header_event_size, trace_dat_fp)) {
+ free(header_page);
+ free(header_event);
+ return -EIO;
+ }
+ free(header_event);
+ } else {
+ skip(size);
+ }
+ free(header_page);
return ret;
}
@@ -259,6 +352,13 @@ static int read_ftrace_file(struct tep_handle *pevent, unsigned long long size)
pr_debug("error reading ftrace file.\n");
goto out;
}
+ if (trace_dat_fp) {
+ if (!fwrite(&size, sizeof(unsigned long long), 1, trace_dat_fp) ||
+ !fwrite(buf, 1, size, trace_dat_fp)) {
+ free(buf);
+ return -EIO;
+ }
+ }
ret = parse_ftrace_file(pevent, buf, size);
if (ret < 0)
@@ -283,6 +383,13 @@ static int read_event_file(struct tep_handle *pevent, char *sys,
ret = do_read(buf, size);
if (ret < 0)
goto out;
+ if (trace_dat_fp) {
+ if (!fwrite(&size, sizeof(unsigned long long), 1, trace_dat_fp) ||
+ !fwrite(buf, 1, size, trace_dat_fp)) {
+ free(buf);
+ return -EIO;
+ }
+ }
ret = parse_event_file(pevent, buf, size, sys);
if (ret < 0)
@@ -298,8 +405,31 @@ static int read_ftrace_files(struct tep_handle *pevent)
int count;
int i;
int ret;
+ long section_size_pos = 0;
+ long count_pos = 0;
+ unsigned long long section_size = 0;
+ long end_pos;
count = read4(pevent);
+ /* Write ftrace formats section to trace.dat output file */
+ if (trace_dat_fp) {
+ unsigned short section_id = TRACE_DAT_SECTION_FTRACE;
+ unsigned short flags = 0;
+ unsigned int string_id = STRID_FTRACE_FORMATS;
+
+ trace_dat_ftrace_format_offset = ftell(trace_dat_fp);
+
+ if (!fwrite(§ion_id, sizeof(unsigned short), 1, trace_dat_fp) ||
+ !fwrite(&flags, sizeof(unsigned short), 1, trace_dat_fp) ||
+ !fwrite(&string_id, sizeof(unsigned int), 1, trace_dat_fp))
+ return -EIO;
+ section_size_pos = ftell(trace_dat_fp);
+ if (!fwrite(§ion_size, sizeof(unsigned long long), 1, trace_dat_fp))
+ return -EIO;
+ count_pos = ftell(trace_dat_fp);
+ if (!fwrite(&count, sizeof(unsigned int), 1, trace_dat_fp))
+ return -EIO;
+ }
for (i = 0; i < count; i++) {
size = read8(pevent);
@@ -307,6 +437,16 @@ static int read_ftrace_files(struct tep_handle *pevent)
if (ret)
return ret;
}
+ /* Fill in section size after writing all ftrace files */
+ if (trace_dat_fp) {
+ end_pos = ftell(trace_dat_fp);
+ section_size = end_pos - count_pos;
+ fseek(trace_dat_fp, section_size_pos, SEEK_SET);
+ if (!fwrite(§ion_size, sizeof(unsigned long long), 1, trace_dat_fp))
+ return -EIO;
+ fseek(trace_dat_fp, end_pos, SEEK_SET);
+ }
+
return 0;
}
@@ -318,8 +458,30 @@ static int read_event_files(struct tep_handle *pevent)
int count;
int i,x;
int ret;
+ long section_size_pos = 0;
+ long sys_count_pos = 0;
+ unsigned long long section_size = 0;
+ long end_pos;
systems = read4(pevent);
+ /* Write event formats section to trace.dat output file */
+ if (trace_dat_fp) {
+ unsigned short section_id = TRACE_DAT_SECTION_EVENTS;
+ unsigned short flags = 0;
+ unsigned int string_id = STRID_EVENT_FORMATS;
+
+ trace_dat_events_format_offset = ftell(trace_dat_fp);
+ if (!fwrite(§ion_id, sizeof(unsigned short), 1, trace_dat_fp) ||
+ !fwrite(&flags, sizeof(unsigned short), 1, trace_dat_fp) ||
+ !fwrite(&string_id, sizeof(unsigned int), 1, trace_dat_fp))
+ return -EIO;
+ section_size_pos = ftell(trace_dat_fp);
+ if (!fwrite(§ion_size, sizeof(unsigned long long), 1, trace_dat_fp))
+ return -EIO;
+ sys_count_pos = ftell(trace_dat_fp);
+ if (!fwrite(&systems, sizeof(unsigned int), 1, trace_dat_fp))
+ return -EIO;
+ }
for (i = 0; i < systems; i++) {
sys = read_string();
@@ -327,6 +489,11 @@ static int read_event_files(struct tep_handle *pevent)
return -1;
count = read4(pevent);
+ if (trace_dat_fp) {
+ if (!fwrite(sys, 1, strlen(sys) + 1, trace_dat_fp) ||
+ !fwrite(&count, sizeof(unsigned int), 1, trace_dat_fp))
+ return -EIO;
+ }
for (x=0; x < count; x++) {
size = read8(pevent);
@@ -338,6 +505,16 @@ static int read_event_files(struct tep_handle *pevent)
}
free(sys);
}
+ /* Fill in section size after writing all event files */
+ if (trace_dat_fp) {
+ end_pos = ftell(trace_dat_fp);
+ section_size = end_pos - sys_count_pos;
+ fseek(trace_dat_fp, section_size_pos, SEEK_SET);
+ if (!fwrite(§ion_size, sizeof(unsigned long long), 1, trace_dat_fp))
+ return -EIO;
+ fseek(trace_dat_fp, end_pos, SEEK_SET);
+ }
+
return 0;
}
@@ -349,8 +526,25 @@ static int read_saved_cmdline(struct tep_handle *pevent)
/* it can have 0 size */
size = read8(pevent);
- if (!size)
+ /* Write cmdlines section with empty payload if no data */
+ if (!size) {
+ if (trace_dat_fp) {
+ unsigned short section_id = TRACE_DAT_SECTION_CMDLINE;
+ unsigned short flags = 0;
+ unsigned int string_id = STRID_CMDLINES;
+ unsigned long long section_size = sizeof(unsigned long long);
+ unsigned long long section_data = 0;
+
+ trace_dat_cmdline_offset = ftell(trace_dat_fp);
+ if (!fwrite(§ion_id, sizeof(unsigned short), 1, trace_dat_fp) ||
+ !fwrite(&flags, sizeof(unsigned short), 1, trace_dat_fp) ||
+ !fwrite(&string_id, sizeof(unsigned int), 1, trace_dat_fp) ||
+ !fwrite(§ion_size, sizeof(unsigned long long), 1, trace_dat_fp) ||
+ !fwrite(§ion_data, sizeof(unsigned long long), 1, trace_dat_fp))
+ return -EIO;
+ }
return 0;
+ }
buf = malloc(size + 1);
if (buf == NULL) {
@@ -363,6 +557,23 @@ static int read_saved_cmdline(struct tep_handle *pevent)
pr_debug("error reading saved cmdlines\n");
goto out;
}
+ /* Write cmdlines section with data */
+ if (trace_dat_fp) {
+ unsigned short section_id = TRACE_DAT_SECTION_CMDLINE;
+ unsigned short flags = 0;
+ unsigned int string_id = STRID_CMDLINES;
+ unsigned long long section_size = sizeof(unsigned long long) + size;
+
+ trace_dat_cmdline_offset = ftell(trace_dat_fp);
+ if (!fwrite(§ion_id, sizeof(unsigned short), 1, trace_dat_fp) ||
+ !fwrite(&flags, sizeof(unsigned short), 1, trace_dat_fp) ||
+ !fwrite(&string_id, sizeof(unsigned int), 1, trace_dat_fp) ||
+ !fwrite(§ion_size, sizeof(unsigned long long), 1, trace_dat_fp) ||
+ !fwrite(&size, sizeof(unsigned long long), 1, trace_dat_fp) ||
+ !fwrite(buf, 1, size, trace_dat_fp))
+ return -EIO;
+ }
+
buf[ret] = '\0';
parse_saved_cmdline(pevent, buf, size);
@@ -387,6 +598,7 @@ ssize_t trace_report(int fd, struct trace_event *tevent, bool __repipe)
int file_page_size;
struct tep_handle *pevent = NULL;
int err;
+ char magic_buf[10];
repipe = __repipe;
input_fd = fd;
@@ -398,12 +610,17 @@ ssize_t trace_report(int fd, struct trace_event *tevent, bool __repipe)
return -1;
}
+ if (trace_dat_fp)
+ memcpy(magic_buf, buf, 3);
+
if (do_read(buf, 7) < 0)
return -1;
if (memcmp(buf, "tracing", 7) != 0) {
pr_debug("not a trace file (missing 'tracing' tag)");
return -1;
}
+ if (trace_dat_fp)
+ memcpy(magic_buf + 3, buf, 7);
version = read_string();
if (version == NULL)
@@ -440,6 +657,28 @@ ssize_t trace_report(int fd, struct trace_event *tevent, bool __repipe)
tep_set_long_size(pevent, file_long_size);
tep_set_page_size(pevent, file_page_size);
+ /* Write initial file header to trace.dat */
+ if (trace_dat_fp) {
+ unsigned char endian = file_bigendian;
+ unsigned char long_size = file_long_size;
+ unsigned int page_size = file_page_size;
+ unsigned long long placeholder = 0;
+ char trace_dat_version = TRACE_DAT_VERSION;
+
+ if (!fwrite(magic_buf, 1, 10, trace_dat_fp) || /* magic + "tracing" */
+ !fwrite(&trace_dat_version, 1, 2, trace_dat_fp) ||
+ !fwrite(&endian, 1, 1, trace_dat_fp) ||
+ !fwrite(&long_size, 1, 1, trace_dat_fp) ||
+ !fwrite(&page_size, sizeof(unsigned int), 1, trace_dat_fp) ||
+ !fwrite("none", 1, 4, trace_dat_fp) ||
+ !fwrite("\0", 1, 1, trace_dat_fp) ||
+ !fwrite("\0", 1, 1, trace_dat_fp))
+ return -EIO;
+ trace_dat_options_offset = ftell(trace_dat_fp);
+ if (!fwrite(&placeholder, sizeof(unsigned long long), 1, trace_dat_fp))
+ return -EIO;
+ }
+
err = read_header_files(pevent);
if (err)
goto out;
@@ -460,6 +699,12 @@ ssize_t trace_report(int fd, struct trace_event *tevent, bool __repipe)
if (err)
goto out;
}
+ /* Write strings section to trace.dat output file */
+ if (trace_dat_fp) {
+ err = trace_dat__write_strings_section();
+ if (err)
+ goto out;
+ }
size = trace_data_size;
repipe = false;
--
2.53.0
^ permalink raw reply related
* [RFC PATCH 1/4] perf/trace-dat: Add trace.dat export infrastructure
From: Tanushree Shah @ 2026-06-08 12:59 UTC (permalink / raw)
To: acme, jolsa, adrian.hunter, vmolnaro, mpetlan, tmricht, maddy,
irogers, namhyung, linux-kernel
Cc: linux-perf-users, linuxppc-dev, atrajeev, hbathini, Tejas.Manhas1,
Tanushree.Shah, Shivani.Nittor, Tanushree Shah
In-Reply-To: <20260608125951.90425-2-tshah@linux.ibm.com>
Add new utility files util/trace-dat.c and util/trace-dat.h
implementing the infrastructure for exporting perf.data tracepoints
to trace.dat format compatible with trace-cmd and KernelShark.
trace-dat.c defines all globals and functions needed for:
- Per-cpu raw event buffer management (init_cpu_buffers,
collect_cpu_event, free_cpu_buffers)
- ftrace ring buffer page construction (write_page, write_cpu_dat)
- trace.dat section writers (write_strings_section,
write_options_section1, write_options_section2,
write_flyrecord_section)
trace-dat.h declares all globals and function prototypes to be
used by data-convert-trace.c and trace-event-read.c.
Signed-off-by: Tanushree Shah <tshah@linux.ibm.com>
---
tools/perf/util/Build | 1 +
tools/perf/util/trace-dat.c | 705 ++++++++++++++++++++++++++++++++++++
tools/perf/util/trace-dat.h | 79 ++++
3 files changed, 785 insertions(+)
create mode 100644 tools/perf/util/trace-dat.c
create mode 100644 tools/perf/util/trace-dat.h
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 70cc91d00804..c000d8032d25 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -98,6 +98,7 @@ perf-util-y += trace-event-scripting.o
perf-util-$(CONFIG_LIBTRACEEVENT) += trace-event.o
perf-util-$(CONFIG_LIBTRACEEVENT) += trace-event-parse.o
perf-util-$(CONFIG_LIBTRACEEVENT) += trace-event-read.o
+perf-util-$(CONFIG_LIBTRACEEVENT) += trace-dat.o
perf-util-y += sort.o
perf-util-y += hist.o
perf-util-y += util.o
diff --git a/tools/perf/util/trace-dat.c b/tools/perf/util/trace-dat.c
new file mode 100644
index 000000000000..aa34a7b89b7a
--- /dev/null
+++ b/tools/perf/util/trace-dat.c
@@ -0,0 +1,705 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright 2026, IBM Corporation
+ * Author: Tanushree Shah <tshah@linux.ibm.com>
+ *
+ * trace-dat.c
+ *
+ * This file implements the trace.dat format writer for perf tool.
+ * It collects trace events from multiple CPUs and writes them in
+ * the trace-cmd compatible format.
+ */
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <errno.h>
+#include "api/fs/tracing_path.h"
+#include "trace-dat.h"
+#include "trace-event.h"
+#include "session.h"
+#include "header.h"
+#include "../perf.h"
+#include "debug.h"
+
+/* ftrace ring buffer constants for trace.dat flyrecord section
+ *
+ * Each page has a 16-byte header (timestamp + commit size), followed by
+ * variable-length records. Each record has a 4-byte header word encoding:
+ * Bits 0-4: Type/Length field (5 bits, masked by TYPE_LEN_MASK)
+ * Bits 5-31: Time delta from page base timestamp (27 bits, masked by TIME_MASK)
+ */
+#define TRACE_DAT_RECORD_HEADER_SIZE 16 /* Page header: 8-byte ts + 8-byte commit */
+#define TRACE_DAT_RECORD_TYPE_LEN_MASK 0x1F /* Extract lower 5 bits for type/length */
+#define TRACE_DAT_RECORD_TIME_SHIFT 5 /* Shift to extract time delta */
+#define TRACE_DAT_RECORD_TIME_MASK 0x07FFFFFF /* Mask for 27-bit time delta */
+#define TRACE_DAT_WORD_SIZE 4 /* Records aligned to 4-byte boundaries */
+#define TRACE_DAT_WORD_ALIGN_MASK 3
+
+/* Initial capacity for per-CPU event buffer (grows by doubling) */
+#define INITIAL_EVENT_CAPACITY 1024
+/* Initial capacity for page record array (grows by doubling) */
+#define INITIAL_PAGE_RECORD_CAPACITY 64
+/* Buffer size for reading trace_clock string from debugfs/tracefs */
+#define CLOCK_BUFFER_SIZE 256
+
+FILE *trace_dat_fp;
+int trace_dat_page_size;
+int trace_dat_nr_cpus;
+long trace_dat_options_offset;
+long trace_dat_header_info_offset;
+long trace_dat_events_format_offset;
+long trace_dat_ftrace_format_offset;
+long trace_dat_kallsyms_offset;
+long trace_dat_cmdline_offset;
+long trace_dat_next_options_offset;
+
+
+/**
+ * struct cpu_event - Single trace event from a CPU
+ * @ts: Timestamp of the event
+ * @raw: Raw event data
+ * @raw_size: Size of raw event data in bytes
+ */
+struct cpu_event {
+ unsigned long long ts;
+ void *raw;
+ unsigned int raw_size;
+};
+
+/**
+ * struct cpu_events - Collection of trace events for a single CPU
+ * @events: Array of events
+ * @count: Number of events currently stored
+ * @capacity: Maximum number of events that can be stored
+ */
+struct cpu_events {
+ struct cpu_event *events;
+ int count;
+ int capacity;
+};
+
+static struct cpu_events *trace_cpu_data;
+static long *buffer_opt_cpu_offsets_pos;
+static long opt_payload_start;
+
+/* Allocate per-cpu event buffers for tracepoint data collection */
+int trace_dat__init_cpu_buffers(int nr_cpus)
+{
+ trace_cpu_data = calloc(nr_cpus, sizeof(struct cpu_events));
+ if (!trace_cpu_data)
+ return -ENOMEM;
+ buffer_opt_cpu_offsets_pos = calloc(nr_cpus, sizeof(long));
+ if (!buffer_opt_cpu_offsets_pos) {
+ free(trace_cpu_data);
+ trace_cpu_data = NULL;
+ return -ENOMEM;
+ }
+ trace_dat_nr_cpus = nr_cpus;
+ return 0;
+}
+
+/* Store raw tracepoint event data in per-cpu buffer for trace.dat
+ * flyrecord
+ */
+int trace_dat__collect_cpu_event(int cpu, unsigned long long ts,
+ void *raw, unsigned int raw_size)
+{
+ struct cpu_events *cpu_events;
+
+ if (!trace_cpu_data || cpu < 0 || cpu >= trace_dat_nr_cpus)
+ return -EINVAL;
+
+ if (!raw || raw_size == 0)
+ return -EINVAL;
+
+ cpu_events = &trace_cpu_data[cpu];
+
+ if (cpu_events->count >= cpu_events->capacity) {
+ cpu_events->capacity = cpu_events->capacity ?
+ cpu_events->capacity * 2 : INITIAL_EVENT_CAPACITY;
+ cpu_events->events = realloc(cpu_events->events,
+ cpu_events->capacity * sizeof(*cpu_events->events));
+ if (!cpu_events->events)
+ return -ENOMEM;
+ }
+
+ cpu_events->events[cpu_events->count].ts = ts;
+ cpu_events->events[cpu_events->count].raw = malloc(raw_size);
+ if (!cpu_events->events[cpu_events->count].raw)
+ return -ENOMEM;
+
+ memcpy(cpu_events->events[cpu_events->count].raw, raw, raw_size);
+ cpu_events->events[cpu_events->count].raw_size = raw_size;
+ cpu_events->count++;
+
+ return 0;
+}
+
+/* Write a single page of trace records */
+static int trace_dat__write_page(FILE *fp, unsigned long long base_ts,
+ char **records, int *rec_sizes, int nr_recs)
+{
+ unsigned long long commit = 0;
+ int offset = TRACE_DAT_RECORD_HEADER_SIZE;
+ int i;
+ char *page;
+
+ page = calloc(1, trace_dat_page_size);
+ if (!page)
+ return -ENOMEM;
+
+ for (i = 0; i < nr_recs; i++) {
+ memcpy(page + offset, records[i], rec_sizes[i]);
+ offset += rec_sizes[i];
+ commit += rec_sizes[i];
+ }
+
+ memcpy(page, &base_ts, sizeof(base_ts));
+ memcpy(page + sizeof(base_ts), &commit, sizeof(commit));
+
+ if (!fwrite(page, 1, trace_dat_page_size, fp)) {
+ free(page);
+ return -EIO;
+ }
+ free(page);
+
+ return 0;
+}
+
+/* Write all trace data for a single CPU as trace.dat flyrecord pages */
+static int trace_dat__write_cpu_dat(FILE *fp, int cpu, unsigned long long *file_offset_out)
+{
+ struct cpu_events *cpu_events = &trace_cpu_data[cpu];
+ unsigned long long base_ts;
+ unsigned long long file_offset;
+ char **page_records = NULL;
+ int *page_rec_sizes = NULL;
+ int page_cap = 0;
+ int nr_page_recs = 0;
+ int page_size_used = 0;
+ int ret = 0;
+ int i, j;
+
+ file_offset = ftell(fp);
+ *file_offset_out = file_offset;
+
+ if (cpu_events->count == 0) {
+ char *empty_page = calloc(1, trace_dat_page_size);
+
+ if (!empty_page)
+ return -ENOMEM;
+ if (!fwrite(empty_page, 1, trace_dat_page_size, fp)) {
+ free(empty_page);
+ return -EIO;
+ }
+ free(empty_page);
+ return 0;
+ }
+
+ base_ts = cpu_events->events[0].ts;
+
+ for (i = 0; i < cpu_events->count; i++) {
+ struct cpu_event *event = &cpu_events->events[i];
+ unsigned long long time_delta = event->ts - base_ts;
+ unsigned int data_len = event->raw_size;
+ unsigned int words = (data_len + TRACE_DAT_WORD_ALIGN_MASK) / TRACE_DAT_WORD_SIZE;
+ unsigned int type_len = words & TRACE_DAT_RECORD_TYPE_LEN_MASK;
+ unsigned int hdr_word = ((time_delta & TRACE_DAT_RECORD_TIME_MASK) <<
+ TRACE_DAT_RECORD_TIME_SHIFT) | type_len;
+ int rec_size;
+ char *rec;
+
+ rec_size = TRACE_DAT_WORD_SIZE + data_len;
+ if (rec_size % TRACE_DAT_WORD_SIZE)
+ rec_size += TRACE_DAT_WORD_SIZE - (rec_size % TRACE_DAT_WORD_SIZE);
+
+ rec = calloc(1, rec_size);
+ if (!rec)
+ return -ENOMEM;
+ memcpy(rec, &hdr_word, TRACE_DAT_WORD_SIZE);
+ memcpy(rec + TRACE_DAT_WORD_SIZE, event->raw, data_len);
+
+ if (page_size_used + rec_size > trace_dat_page_size -
+ TRACE_DAT_RECORD_HEADER_SIZE) {
+ ret = trace_dat__write_page(fp, base_ts,
+ page_records, page_rec_sizes, nr_page_recs);
+ for (j = 0; j < nr_page_recs; j++)
+ free(page_records[j]);
+ nr_page_recs = 0;
+ page_size_used = 0;
+ base_ts = event->ts;
+ if (ret < 0)
+ goto out_free;
+ }
+
+ if (nr_page_recs >= page_cap) {
+ char **tmp_records;
+ int *tmp_sizes;
+
+ page_cap = page_cap ? page_cap * 2 : INITIAL_PAGE_RECORD_CAPACITY;
+ tmp_records = realloc(page_records, page_cap * sizeof(char *));
+ tmp_sizes = realloc(page_rec_sizes, page_cap * sizeof(int));
+ if (!tmp_records || !tmp_sizes) {
+ ret = -ENOMEM;
+ goto out_free;
+ }
+ page_records = tmp_records;
+ page_rec_sizes = tmp_sizes;
+ }
+ page_records[nr_page_recs] = rec;
+ page_rec_sizes[nr_page_recs] = rec_size;
+ nr_page_recs++;
+ page_size_used += rec_size;
+ }
+
+ if (nr_page_recs > 0) {
+ ret = trace_dat__write_page(fp, base_ts,
+ page_records, page_rec_sizes, nr_page_recs);
+ }
+out_free:
+ for (j = 0; j < nr_page_recs; j++)
+ free(page_records[j]);
+ free(page_records);
+ free(page_rec_sizes);
+ return ret;
+}
+
+/* Write the strings section containing section name lookup table */
+int trace_dat__write_strings_section(void)
+{
+ unsigned short section_id = TRACE_DAT_SECTION_STRINGS;
+ unsigned short flags = 0;
+ unsigned long long section_size = 0;
+ static const char * const section_names[] = {
+ "headers", /* offset 0 - strid for section 16 */
+ "ftrace event formats", /* offset 8 - strid for section 17 */
+ "events format", /* offset 29 - strid for section 18 */
+ "kallsyms", /* offset 43 - strid for section 19 */
+ "cmdlines", /* offset 52 - strid for section 21 */
+ "strings", /* offset 61 - strid for section 15 */
+ "options", /* offset 69 - strid for options 1 */
+ "options", /* offset 77 - strid for options 2 */
+ "buffer-flyrecord", /* offset 85 - strid for flyrecord 3 */
+ NULL
+ };
+
+ /* string_id points to "strings" string itself */
+ unsigned int string_id = STRID_STRINGS;
+ int i;
+
+ if (!trace_dat_fp)
+ return -EBADF;
+
+ for (i = 0; section_names[i] != NULL; i++)
+ section_size += strlen(section_names[i]) + 1;
+
+ /* write section header */
+ if (!fwrite(§ion_id, sizeof(unsigned short), 1, trace_dat_fp) ||
+ !fwrite(&flags, sizeof(unsigned short), 1, trace_dat_fp) ||
+ !fwrite(&string_id, sizeof(unsigned int), 1, trace_dat_fp) ||
+ !fwrite(§ion_size, sizeof(unsigned long long), 1, trace_dat_fp))
+ return -EIO;
+
+ /* write strings */
+ for (i = 0; section_names[i] != NULL; i++)
+ if (!fwrite(section_names[i], 1, strlen(section_names[i]) + 1, trace_dat_fp))
+ return -EIO;
+ return 0;
+}
+
+/* Writes options section containing CPUCOUNT, TRACECLOCK, EVENT_FORMAT, HEADER_INFO,
+ * FTRACE_EVENTS, KALLSYMS, CMDLINES options, ending with DONE option pointing to next section.
+ */
+int trace_dat__write_options_section1(void)
+{
+ unsigned short section_id = TRACE_DAT_SECTION_OPTIONS;
+ unsigned short flags = 0;
+ unsigned int string_id = STRID_OPTIONS_1;
+ unsigned long long section_size = 0;
+ long section_size_pos;
+ long payload_start;
+ unsigned long long section_start;
+ unsigned short opt_id;
+ unsigned int opt_size;
+ char clock_buf[CLOCK_BUFFER_SIZE];
+ FILE *clock_file;
+ size_t bytes_read;
+ char *path;
+ unsigned long long next_offset;
+ long end_pos;
+
+ if (!trace_dat_fp)
+ return -EBADF;
+
+ /* fill options_offset in initial format */
+ section_start = ftell(trace_dat_fp);
+
+ if (fseek(trace_dat_fp, trace_dat_options_offset, SEEK_SET) < 0 ||
+ !fwrite(§ion_start, sizeof(unsigned long long), 1, trace_dat_fp) ||
+ fseek(trace_dat_fp, 0, SEEK_END) < 0)
+ return -EIO;
+
+ /* write section header */
+ if (!fwrite(§ion_id, sizeof(unsigned short), 1, trace_dat_fp) ||
+ !fwrite(&flags, sizeof(unsigned short), 1, trace_dat_fp) ||
+ !fwrite(&string_id, sizeof(unsigned int), 1, trace_dat_fp))
+ return -EIO;
+ section_size_pos = ftell(trace_dat_fp);
+ if (!fwrite(§ion_size, sizeof(unsigned long long), 1, trace_dat_fp))
+ return -EIO;
+
+ payload_start = ftell(trace_dat_fp);
+
+ /* CPUCOUNT option */
+ opt_id = TRACE_DAT_OPTION_CPUCOUNT;
+ opt_size = sizeof(unsigned int);
+
+ if (!fwrite(&opt_id, sizeof(unsigned short), 1, trace_dat_fp) ||
+ !fwrite(&opt_size, sizeof(unsigned int), 1, trace_dat_fp) ||
+ !fwrite(&trace_dat_nr_cpus, sizeof(unsigned int), 1, trace_dat_fp))
+ return -EIO;
+
+ /* TRACECLOCK option */
+ opt_id = TRACE_DAT_OPTION_TRACECLOCK;
+
+ path = get_tracing_file("trace_clock");
+ clock_file = fopen(path, "r");
+ put_tracing_file(path);
+ if (clock_file) {
+ bytes_read = fread(clock_buf, 1, sizeof(clock_buf) - 1, clock_file);
+ fclose(clock_file);
+ clock_buf[bytes_read] = '\0';
+ } else {
+ strcpy(clock_buf, "local\n");
+ bytes_read = strlen(clock_buf);
+ }
+ opt_size = bytes_read + 1;
+ if (!fwrite(&opt_id, sizeof(unsigned short), 1, trace_dat_fp) ||
+ !fwrite(&opt_size, sizeof(unsigned int), 1, trace_dat_fp) ||
+ !fwrite(clock_buf, 1, opt_size, trace_dat_fp))
+ return -EIO;
+
+ /* EVENT option */
+ opt_id = TRACE_DAT_OPTION_EVENT;
+ opt_size = sizeof(unsigned long long);
+
+ if (!fwrite(&opt_id, sizeof(unsigned short), 1, trace_dat_fp) ||
+ !fwrite(&opt_size, sizeof(unsigned int), 1, trace_dat_fp) ||
+ !fwrite(&trace_dat_events_format_offset, sizeof(unsigned long long),
+ 1, trace_dat_fp))
+ return -EIO;
+
+ /* HEADER option */
+ opt_id = TRACE_DAT_OPTION_HEADER;
+ opt_size = sizeof(unsigned long long);
+
+ if (!fwrite(&opt_id, sizeof(unsigned short), 1, trace_dat_fp) ||
+ !fwrite(&opt_size, sizeof(unsigned int), 1, trace_dat_fp) ||
+ !fwrite(&trace_dat_header_info_offset, sizeof(unsigned long long),
+ 1, trace_dat_fp))
+ return -EIO;
+
+ /* FTRACE option */
+ opt_id = TRACE_DAT_OPTION_FTRACE;
+ opt_size = sizeof(unsigned long long);
+
+ if (!fwrite(&opt_id, sizeof(unsigned short), 1, trace_dat_fp) ||
+ !fwrite(&opt_size, sizeof(unsigned int), 1, trace_dat_fp) ||
+ !fwrite(&trace_dat_ftrace_format_offset, sizeof(unsigned long long),
+ 1, trace_dat_fp))
+ return -EIO;
+
+ /* KALLSYMS option */
+ opt_id = TRACE_DAT_OPTION_KALLSYMS;
+ opt_size = sizeof(unsigned long long);
+
+ if (!fwrite(&opt_id, sizeof(unsigned short), 1, trace_dat_fp) ||
+ !fwrite(&opt_size, sizeof(unsigned int), 1, trace_dat_fp) ||
+ !fwrite(&trace_dat_kallsyms_offset, sizeof(unsigned long long),
+ 1, trace_dat_fp))
+ return -EIO;
+
+ /* CMDLINE option */
+ opt_id = TRACE_DAT_OPTION_CMDLINE;
+ opt_size = sizeof(unsigned long long);
+
+ if (!fwrite(&opt_id, sizeof(unsigned short), 1, trace_dat_fp) ||
+ !fwrite(&opt_size, sizeof(unsigned int), 1, trace_dat_fp) ||
+ !fwrite(&trace_dat_cmdline_offset, sizeof(unsigned long long),
+ 1, trace_dat_fp))
+ return -EIO;
+
+ /* DONE option id - next_options_offset filled later */
+ opt_id = TRACE_DAT_OPTION_DONE;
+ opt_size = sizeof(unsigned long long);
+ next_offset = 0; /* placeholder */
+
+ trace_dat_next_options_offset = ftell(trace_dat_fp);
+ if (!fwrite(&opt_id, sizeof(unsigned short), 1, trace_dat_fp) ||
+ !fwrite(&opt_size, sizeof(unsigned int), 1, trace_dat_fp) ||
+ !fwrite(&next_offset, sizeof(unsigned long long), 1, trace_dat_fp))
+ return -EIO;
+
+ /* fill section size */
+ end_pos = ftell(trace_dat_fp);
+
+ section_size = end_pos - payload_start;
+ if (fseek(trace_dat_fp, section_size_pos, SEEK_SET) < 0 ||
+ !fwrite(§ion_size, sizeof(unsigned long long), 1, trace_dat_fp) ||
+ fseek(trace_dat_fp, end_pos, SEEK_SET) < 0)
+ return -EIO;
+
+ return 0;
+
+}
+
+/* Writes options section containing BUFFER option with flyrecord section
+ * (flyrecord section offset, clock type, page size, CPU count,
+ * per-CPU offsets/sizes) and DONE option.
+ */
+int trace_dat__write_options_section2(void)
+{
+ unsigned short section_id = TRACE_DAT_SECTION_OPTIONS;
+ unsigned short flags = 0;
+ unsigned int string_id = STRID_OPTIONS_2;
+ unsigned long long section_size = 0;
+ long section_size_pos;
+ long payload_start;
+ int cpu;
+ unsigned short opt_id = TRACE_DAT_OPTION_BUFFER;
+ unsigned int opt_size = 0;
+ long opt_size_pos;
+ unsigned long long data_offset = 0;
+ unsigned int page_size = (unsigned int)trace_dat_page_size;
+ const char *clock = "local";
+ unsigned long long next;
+ long end_pos;
+ unsigned long long cpu_offset;
+ unsigned long long cpu_size;
+ unsigned short done_id;
+ unsigned int done_size;
+
+ if (!trace_dat_fp)
+ return -EINVAL;
+
+ /* fill done1 next offset - points to this section */
+ next = ftell(trace_dat_fp);
+
+ if (fseek(trace_dat_fp, trace_dat_next_options_offset + 2 + 4, SEEK_SET) < 0 ||
+ !fwrite(&next, sizeof(unsigned long long), 1, trace_dat_fp) ||
+ fseek(trace_dat_fp, 0, SEEK_END) < 0)
+ return -EIO;
+
+ /* write section header */
+ if (!fwrite(§ion_id, sizeof(unsigned short), 1, trace_dat_fp) ||
+ !fwrite(&flags, sizeof(unsigned short), 1, trace_dat_fp) ||
+ !fwrite(&string_id, sizeof(unsigned int), 1, trace_dat_fp))
+ return -EIO;
+ section_size_pos = ftell(trace_dat_fp);
+ if (!fwrite(§ion_size, sizeof(unsigned long long), 1, trace_dat_fp))
+ return -EIO;
+
+ payload_start = ftell(trace_dat_fp);
+
+ /* BUFFER option */
+ if (!fwrite(&opt_id, sizeof(unsigned short), 1, trace_dat_fp))
+ return -EIO;
+ opt_size_pos = ftell(trace_dat_fp);
+ if (!fwrite(&opt_size, sizeof(unsigned int), 1, trace_dat_fp))
+ return -EIO;
+ opt_payload_start = ftell(trace_dat_fp);
+
+ /* data_offset placeholder */
+ if (!fwrite(&data_offset, sizeof(unsigned long long), 1, trace_dat_fp) ||
+ !fwrite("\0", 1, 1, trace_dat_fp) ||
+ !fwrite(clock, 1, strlen(clock) + 1, trace_dat_fp) ||
+ !fwrite(&page_size, sizeof(unsigned int), 1, trace_dat_fp) ||
+ !fwrite(&trace_dat_nr_cpus, sizeof(unsigned int), 1, trace_dat_fp))
+ return -EIO;
+
+ /* per cpu: cpu_id + offset placeholder + size */
+ for (cpu = 0; cpu < trace_dat_nr_cpus; cpu++) {
+ cpu_offset = 0; /* filled in write_flyrecord */
+ cpu_size = 0; /* filled in write_flyrecord */
+
+ if (!fwrite(&cpu, sizeof(unsigned int), 1, trace_dat_fp))
+ return -EIO;
+ buffer_opt_cpu_offsets_pos[cpu] = ftell(trace_dat_fp);
+ if (!fwrite(&cpu_offset, sizeof(unsigned long long), 1, trace_dat_fp) ||
+ !fwrite(&cpu_size, sizeof(unsigned long long), 1, trace_dat_fp))
+ return -EIO;
+ }
+
+ /* fill opt_size */
+ end_pos = ftell(trace_dat_fp);
+
+ opt_size = end_pos - opt_payload_start;
+ fseek(trace_dat_fp, opt_size_pos, SEEK_SET);
+ if (!fwrite(&opt_size, sizeof(unsigned int), 1, trace_dat_fp))
+ return -EIO;
+ fseek(trace_dat_fp, end_pos, SEEK_SET);
+
+ /* DONE id=0 */
+ done_id = TRACE_DAT_OPTION_DONE;
+ done_size = sizeof(unsigned long long);
+ /* No additional options sections follow this one */
+ next = 0;
+
+ if (!fwrite(&done_id, sizeof(unsigned short), 1, trace_dat_fp) ||
+ !fwrite(&done_size, sizeof(unsigned int), 1, trace_dat_fp) ||
+ !fwrite(&next, sizeof(unsigned long long), 1, trace_dat_fp))
+ return -EIO;
+
+ /* fill section size */
+ end_pos = ftell(trace_dat_fp);
+
+ section_size = end_pos - payload_start;
+ fseek(trace_dat_fp, section_size_pos, SEEK_SET);
+ if (!fwrite(§ion_size, sizeof(unsigned long long), 1, trace_dat_fp))
+ return -EIO;
+ fseek(trace_dat_fp, end_pos, SEEK_SET);
+
+ return 0;
+
+}
+
+int trace_dat__write_flyrecord_section(void)
+{
+ unsigned short section_id = TRACE_DAT_SECTION_FLYRECORD;
+ unsigned short flags = 0;
+ unsigned int string_id = STRID_BUFFER_FLYRECORD;
+ unsigned long long section_size = 0;
+ long section_size_pos;
+ long flyrecord_start;
+ long after_header;
+ long padding_needed;
+ unsigned long long *cpu_offsets;
+ unsigned long long *cpu_sizes;
+ int cpu;
+ int ret = 0;
+ char *pad;
+ unsigned long long start;
+ long end_pos;
+
+ if (!trace_dat_fp)
+ return -EINVAL;
+
+ cpu_offsets = calloc(trace_dat_nr_cpus, sizeof(unsigned long long));
+ cpu_sizes = calloc(trace_dat_nr_cpus, sizeof(unsigned long long));
+ if (!cpu_offsets || !cpu_sizes) {
+ ret = -ENOMEM;
+ goto cleanup;
+ }
+ flyrecord_start = ftell(trace_dat_fp);
+ if (flyrecord_start < 0) {
+ ret = -EIO;
+ goto cleanup;
+ }
+
+ /* section header */
+ if (!fwrite(§ion_id, sizeof(unsigned short), 1, trace_dat_fp) ||
+ !fwrite(&flags, sizeof(unsigned short), 1, trace_dat_fp) ||
+ !fwrite(&string_id, sizeof(unsigned int), 1, trace_dat_fp)) {
+ ret = -EIO;
+ goto cleanup;
+ }
+ section_size_pos = ftell(trace_dat_fp);
+ if (!fwrite(§ion_size, sizeof(unsigned long long), 1, trace_dat_fp)) {
+ ret = -EIO;
+ goto cleanup;
+ }
+
+ /* Align to page boundary */
+ after_header = ftell(trace_dat_fp);
+ padding_needed = (trace_dat_page_size -
+ (after_header % trace_dat_page_size)) % trace_dat_page_size;
+
+ if (padding_needed > 0) {
+ pad = calloc(1, padding_needed);
+
+ if (!fwrite(pad, 1, padding_needed, trace_dat_fp)) {
+ free(pad);
+ ret = -EIO;
+ goto cleanup;
+ }
+ free(pad);
+ }
+
+ /* write per-cpu trace data */
+ for (cpu = 0; cpu < trace_dat_nr_cpus; cpu++) {
+ start = ftell(trace_dat_fp);
+
+ ret = trace_dat__write_cpu_dat(trace_dat_fp, cpu, &cpu_offsets[cpu]);
+
+ if (ret < 0) {
+ pr_err("Failed to write CPU %d data\n", cpu);
+ goto cleanup;
+ }
+ cpu_sizes[cpu] = ftell(trace_dat_fp) - start;
+ }
+
+ /* fill section size */
+ end_pos = ftell(trace_dat_fp);
+
+ section_size = end_pos - flyrecord_start;
+ if (fseek(trace_dat_fp, section_size_pos, SEEK_SET) < 0 ||
+ !fwrite(§ion_size, sizeof(unsigned long long), 1, trace_dat_fp)) {
+ ret = -EIO;
+ goto cleanup;
+ }
+ if (fseek(trace_dat_fp, end_pos, SEEK_SET) < 0) {
+ ret = -EIO;
+ goto cleanup;
+ }
+
+ /* fill cpu offsets and sizes in BUFFER option */
+ for (cpu = 0; cpu < trace_dat_nr_cpus; cpu++) {
+ if (fseek(trace_dat_fp, buffer_opt_cpu_offsets_pos[cpu], SEEK_SET) < 0 ||
+ !fwrite(&cpu_offsets[cpu], sizeof(unsigned long long), 1, trace_dat_fp) ||
+ !fwrite(&cpu_sizes[cpu], sizeof(unsigned long long), 1, trace_dat_fp)) {
+ ret = -EIO;
+ goto cleanup;
+ }
+ }
+
+ /* fill data offset in buffer option */
+ if (fseek(trace_dat_fp, opt_payload_start, SEEK_SET) < 0 ||
+ !fwrite(&flyrecord_start, sizeof(unsigned long long), 1, trace_dat_fp)) {
+ ret = -EIO;
+ goto cleanup;
+ }
+
+ if (fseek(trace_dat_fp, 0, SEEK_END) < 0) {
+ ret = -EIO;
+ goto cleanup;
+ }
+
+
+cleanup:
+ free(cpu_offsets);
+ free(cpu_sizes);
+ return ret;
+}
+
+/* Free all per-CPU event buffers */
+void trace_dat__free_cpu_buffers(void)
+{
+ int cpu;
+
+ if (!trace_cpu_data)
+ return;
+
+ for (cpu = 0; cpu < trace_dat_nr_cpus; cpu++) {
+ int i;
+
+ for (i = 0; i < trace_cpu_data[cpu].count; i++)
+ free(trace_cpu_data[cpu].events[i].raw);
+ free(trace_cpu_data[cpu].events);
+ }
+ free(trace_cpu_data);
+ trace_cpu_data = NULL;
+ free(buffer_opt_cpu_offsets_pos);
+ buffer_opt_cpu_offsets_pos = NULL;
+ trace_dat_nr_cpus = 0;
+}
diff --git a/tools/perf/util/trace-dat.h b/tools/perf/util/trace-dat.h
new file mode 100644
index 000000000000..7667a440330c
--- /dev/null
+++ b/tools/perf/util/trace-dat.h
@@ -0,0 +1,79 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright 2026, IBM Corporation
+ * Author: Tanushree Shah <tshah@linux.ibm.com>
+ */
+
+#ifndef __PERF_TRACE_DAT_H
+#define __PERF_TRACE_DAT_H
+
+#include <stdio.h>
+
+/* trace.dat file format version */
+#define TRACE_DAT_VERSION '7'
+
+/*
+ * Section IDs for trace.dat format
+ */
+#define TRACE_DAT_SECTION_OPTIONS 0
+#define TRACE_DAT_SECTION_FLYRECORD 3
+#define TRACE_DAT_SECTION_STRINGS 15
+#define TRACE_DAT_SECTION_HEADER 16
+#define TRACE_DAT_SECTION_FTRACE 17
+#define TRACE_DAT_SECTION_EVENTS 18
+#define TRACE_DAT_SECTION_KALLSYMS 19
+#define TRACE_DAT_SECTION_CMDLINE 21
+
+/*
+ * Option IDs for trace.dat options sections
+ */
+#define TRACE_DAT_OPTION_DONE 0
+#define TRACE_DAT_OPTION_BUFFER 3
+#define TRACE_DAT_OPTION_TRACECLOCK 4
+#define TRACE_DAT_OPTION_CPUCOUNT 8
+#define TRACE_DAT_OPTION_HEADER 16
+#define TRACE_DAT_OPTION_FTRACE 17
+#define TRACE_DAT_OPTION_EVENT 18
+#define TRACE_DAT_OPTION_KALLSYMS 19
+#define TRACE_DAT_OPTION_CMDLINE 21
+
+/*
+ * String offsets in the strings section
+ * These point to null-terminated strings used as section names
+ */
+#define STRID_HEADERS 0
+#define STRID_FTRACE_FORMATS 8
+#define STRID_EVENT_FORMATS 29
+#define STRID_KALLSYMS 43
+#define STRID_CMDLINES 52
+#define STRID_STRINGS 61
+#define STRID_OPTIONS_1 69
+#define STRID_OPTIONS_2 77
+#define STRID_BUFFER_FLYRECORD 85
+
+struct perf_session;
+
+extern FILE *trace_dat_fp;
+extern int trace_dat_page_size;
+extern int trace_dat_nr_cpus;
+extern long trace_dat_options_offset;
+extern long trace_dat_header_info_offset;
+extern long trace_dat_events_format_offset;
+extern long trace_dat_ftrace_format_offset;
+extern long trace_dat_kallsyms_offset;
+extern long trace_dat_cmdline_offset;
+extern long trace_dat_next_options_offset;
+
+/* collect and manage per-cpu tracepoint event buffers */
+int trace_dat__init_cpu_buffers(int nr_cpus);
+int trace_dat__collect_cpu_event(int cpu, unsigned long long ts,
+ void *raw, unsigned int raw_size);
+void trace_dat__free_cpu_buffers(void);
+
+/* write trace.dat file sections */
+int trace_dat__write_options_section1(void);
+int trace_dat__write_options_section2(void);
+int trace_dat__write_flyrecord_section(void);
+int trace_dat__write_strings_section(void);
+
+#endif /* __PERF_TRACE_DAT_H */
--
2.53.0
^ permalink raw reply related
* [RFC PATCH 0/4] perf: Add perf.data tracepoint events to trace.dat conversion
From: Tanushree Shah @ 2026-06-08 12:59 UTC (permalink / raw)
To: acme, jolsa, adrian.hunter, vmolnaro, mpetlan, tmricht, maddy,
irogers, namhyung, linux-kernel
Cc: linux-perf-users, linuxppc-dev, atrajeev, hbathini, Tejas.Manhas1,
Tanushree.Shah, Shivani.Nittor, Tanushree Shah
This RFC patch series introduces support for converting perf.data files
containing tracepoint events into trace.dat format, enabling seamless
visualization and analysis using KerneShark.
======================
Background and Motivation
======================
Currently, perf and trace-cmd operate as separate tracing ecosystems with
incompatible data formats. Users who collect tracepoint data with
'perf record' cannot easily visualize it in KernelShark's graphical
timeline view or leverage trace-cmd's analysis capabilities.
This creates workflow friction when users need to:
- Visualize perf tracepoint data in KernelShark's interactive graphical
timeline
- Share trace data between perf and trace-cmd workflows and toolchains
- Perform architecture-independent conversion and analysis of traces
This conversion bridge eliminates these barriers by enabling seamless
data exchange between perf and trace-cmd ecosystems, allowing users to
choose the best tool for each analysis phase.
======================
Implementation Overview
======================
The series implements the trace.dat file format specification (version 7)
within perf's data conversion framework.
**Patch 1/4: Core trace.dat Export Infrastructure**
Introduces util/trace-dat.c and util/trace-dat.h implementing:
- Per-CPU raw event buffer management (init, collect, free)
- Ftrace ring buffer page construction
- trace.dat section writers (strings, options, flyrecord sections)
**Patch 2/4: Metadata Integration**
Extends util/trace-event-read.c to write trace.dat metadata during
perf.data
parsing:
- Initial format header (magic, version, endian, page size, compression)
- Section 16: HEADER INFO (header_page + header_event)
- Section 17: FTRACE EVENT FORMATS
- Section 18: EVENT FORMATS (per system/event format files)
- Section 19: KALLSYMS
- Section 21: CMDLINES
- Section 15: STRINGS (written last after all sections)
**Patch 3/4: Conversion Backend**
Implements util/data-convert-trace.c with trace_convert__perf2dat()
function:
- Processes PERF_TYPE_TRACEPOINT samples via process_sample_event()
- Collects raw event data per-CPU using trace_dat__collect_cpu_event()
- Writes OPTIONS sections (CPUCOUNT, TRACECLOCK, metadata offsets)
- Writes FLYRECORD section with per-CPU ring buffer pages
**Patch 4/4: User Interface**
Extends tools/perf/builtin-data.c with --to-trace-dat option:
- Adds command-line option for trace.dat output
- Mutually exclusive with --to-ctf and --to-json
- Calls trace_convert__perf2dat() to perform conversion
======================
Current Implementation Details
======================
**trace.dat Format Version:**
The implementation currently targets trace.dat format version 7, which
is the stable version supported by current trace-cmd releases (v3.x).
This version is hardcoded to ensure compatibility with existing
trace-cmd and KernelShark installations. Future enhancements could add
version negotiation or support for newer format versions as they become
standardized.
**Compression Strategy:**
Compression is explicitly disabled (set to NONE) in the generated
trace.dat files.
This design choice:
- Simplifies the initial implementation and testing
- Ensures maximum compatibility across trace-cmd versions
- Avoids external compression library dependencies
Future work could add support for various compression algorithms (zlib,
zstd, lz4) with runtime selection via command-line options, significantly
reducing file sizes for large traces.
======================
Usage Example
======================
```bash
*Record tracepoint events with perf*
perf record -e sched:sched_switch -e sched:sched_wakeup -a sleep 10
*Convert to trace.dat format*
perf data convert --to-trace-dat=output.dat
*Verify trace.dat structure*
trace-cmd dump --summary output.dat
*Analyze with trace-cmd*
trace-cmd report output.dat
*Visualize in KernelShark*
kernelshark output.dat
```
**Conversion Output:**
```
[ perf data convert: Converted 'perf.data' into trace.dat format
'output.dat' ]
[ perf data convert: Converted 2684 events ]
```
**trace-cmd dump --summary Output:**
```
Tracing meta data in file output.dat:
[Initial format]
7 [Version]
0 [Little endian]
8 [Bytes in a long]
65536 [Page size, bytes]
none [Compression algorithm]
[Compression version]
[buffer "", "local" clock, 65536 page size, 16 cpus, 1048576 bytes
flyrecord data]
[10 options]
[Saved command lines, 0 bytes]
[Kallsyms, 0 bytes]
[Ftrace format, 0 events]
[Header page, 206 bytes]
[Header event, 205 bytes]
[Events format, 1 systems]
[9 sections]
```
======================
Testing and Verification
======================
The series has been extensively tested with:
- Various tracepoint events (sched, irq, syscalls, block I/O)
- Mixed recordings containing both tracepoint and non-tracepoint events
only tracepoints converted)
- Verification with trace-cmd report and KernelShark visualization
- Memory leak testing with Valgrind (0 bytes leaked)
- Cross-architecture testing (x86_64, ppc64le)
All generated trace.dat files successfully open in:
- trace-cmd report (v3.1+)
- KernelShark (v2.0+)
======================
Next Steps
======================
We would highly appreciate reviews, comments, and feedback on:
- The overall architectural approach and integration points
- Compatibility considerations with trace-cmd ecosystem
- Performance characteristics for large-scale traces
- Additional use cases or workflow scenarios
- Future enhancement priorities
Tanushree Shah (4):
perf/trace-dat: Add trace.dat export infrastructure
perf/trace-event: Write trace.dat metadata sections during parsing
perf data-convert: Add perf.data to trace.dat conversion backend
perf data: Add --to-trace-dat option for converting perf.data
tracepoint events into trace.dat format
tools/perf/builtin-data.c | 38 +-
tools/perf/util/Build | 2 +
tools/perf/util/data-convert-trace.c | 152 ++++++
tools/perf/util/data-convert.h | 4 +
tools/perf/util/trace-dat.c | 705 +++++++++++++++++++++++++++
tools/perf/util/trace-dat.h | 79 +++
tools/perf/util/trace-event-read.c | 259 +++++++++-
7 files changed, 1230 insertions(+), 9 deletions(-)
create mode 100644 tools/perf/util/data-convert-trace.c
create mode 100644 tools/perf/util/trace-dat.c
create mode 100644 tools/perf/util/trace-dat.h
--
2.53.0
^ permalink raw reply
* Re: [kvm-unit-tests RFC PATCH 4/6] powerpc: gitlab CI update
From: Thomas Huth @ 2026-06-08 12:48 UTC (permalink / raw)
To: Chinmay Rath
Cc: npiggin, harshpb, lvivier, linuxppc-dev, kvm, andrew.jones, sbhat
In-Reply-To: <20260602064806.3101025-5-rathc@linux.ibm.com>
On 02/06/2026 08.48, Chinmay Rath wrote:
> From: Nicholas Piggin <npiggin@gmail.com>
>
> Change to using a gitlab-ci test group instead of specifying all
> tests in .gitlab-ci.yml, and adds a few additional tests (smp, atomics)
> that are known to work in CI.
>
> To control overhead, ppc64be is used to test 64k page size, ppc64le is
> used to test 4k page size.
>
> Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
> Signed-off-by: Chinmay Rath <rathc@linux.ibm.com>
> ---
> .gitlab-ci.yml | 53 ++++++++-----------------------------------
> powerpc/unittests.cfg | 36 ++++++++++++++++++++++-------
> 2 files changed, 37 insertions(+), 52 deletions(-)
I don't like the idea of handling this differently for powerpc compared to
the other architectures ... so please either also provide (separate) patches
for the other architectures, too, or drop this patch.
Thanks
Thomas
^ permalink raw reply
* Re: [kvm-unit-tests RFC PATCH 1/6] powerpc: add pmu tests
From: Thomas Huth @ 2026-06-08 12:45 UTC (permalink / raw)
To: Chinmay Rath
Cc: npiggin, harshpb, lvivier, linuxppc-dev, kvm, andrew.jones, sbhat
In-Reply-To: <20260602064806.3101025-2-rathc@linux.ibm.com>
On 02/06/2026 08.48, Chinmay Rath wrote:
> From: Nicholas Piggin <npiggin@gmail.com>
>
> Add some initial PMU testing.
>
> - PMC5/6 tests
> - PMAE / PMI test
> - BHRB basic tests
>
> Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
> Signed-off-by: Chinmay Rath <rathc@linux.ibm.com>
> ---
> lib/powerpc/asm/processor.h | 2 +
> lib/powerpc/asm/reg.h | 9 +
> lib/powerpc/asm/setup.h | 1 +
> lib/powerpc/setup.c | 20 ++
> powerpc/Makefile.common | 3 +-
> powerpc/pmu.c | 567 ++++++++++++++++++++++++++++++++++++
> powerpc/unittests.cfg | 3 +
> 7 files changed, 604 insertions(+), 1 deletion(-)
> create mode 100644 powerpc/pmu.c
Hi Chinmay,
the problem with Clang on Travis [*] still seems to persist:
https://app.travis-ci.com/github/huth/kvm-unit-tests/jobs/639614142
Could you please have a look?
Thanks,
Thomas
[*] This already happened with Nicolas' last version:
https://www.spinics.net/lists/kvm/msg351218.html
^ permalink raw reply
* Re: [BUG] kernel BUG in team driver: buffer overflow in team_add_slave()
From: Yeswanth Krishna @ 2026-06-08 12:04 UTC (permalink / raw)
To: netdev, venkat88; +Cc: linux-kernel, linuxppc-dev
In-Reply-To: <3ad19e86-234c-408f-896e-0d6c774fea49@linux.ibm.com>
Please add this tag Reported-by: yeswanth <yeswanth@linux.ibm.com>
On 08/06/26 3:30 pm, Yeswanth Krishna wrote:
> Hi Team ,
>
> I encountered a kernel crash while running selftests on kernel 7.1.0-rc6
> on a POWER10 system. The crash occurs when adding a slave device to a
> team interface, triggered by FORTIFY_SOURCE detecting a buffer overflow.
>
> **System Information:**
> - Kernel: 7.1.0-rc6-160099.42-default+ (commit d548c6f4301b)
> - Architecture: powerpc64le (ppc64le)
> - Hardware: IBM POWER10 (9043-MRX), pSeries
> - Config: CONFIG_FORTIFY_SOURCE=y
>
> **Crash Location:**
>
> [ 3492.897824][T77143] kernel BUG at lib/string_helpers.c:1044!
> [ 3492.898057][T77143] NIP [c000000000ac1120] __fortify_panic+0x18/0x28
> [ 3492.898096][T77143] [c00000000efdb350] [c00800000b857a18]
> team_add_slave+0xc60/0xcc0 [team]
>
>
> **Call Trace:**
>
> __fortify_panic+0x18/0x28
> team_add_slave+0xc60/0xcc0 [team]
> do_set_master+0x19c/0x240
> do_setlink.isra.0+0x388/0x1450
> rtnl_newlink+0xac8/0x1030
> rtnetlink_rcv_msg+0x450/0x530
> netlink_rcv_skb+0x74/0x1b0
> rtnetlink_rcv+0x24/0x40
> netlink_unicast+0x2e0/0x430
> netlink_sendmsg+0x210/0x580
> ____sys_sendmsg+0x30c/0x470
> ___sys_sendmsg+0x94/0xf0
> __sys_sendmsg+0x84/0x100
> system_call_exception+0x154/0x2b0
>
> **Reproducer:**
> The crash is 100% reproducible via selftests:
> ```bash
> cd tools/testing/selftests
> make -C drivers/net/team run_tests
>
> Please add below reported-by tag:
> yeswanth <yeswanth@linux.ibm.com>
>
>
> Thanks,
> Yeswanth Krishna
>
^ permalink raw reply
* [PATCH next] drivers/bus/fsl-mc: Use strscpy() to copy strings into arrays
From: david.laight.linux @ 2026-06-08 9:54 UTC (permalink / raw)
To: Kees Cook, linux-hardening, linux-kernel, linuxppc-dev
Cc: Arnd Bergmann, Ioana Ciornei, David Laight
From: David Laight <david.laight.linux@gmail.com>
Replacing strcpy() with strscpy() ensures than overflow of the target
buffer cannot happen.
Signed-off-by: David Laight <david.laight.linux@gmail.com>
---
This is one of a group of patches that remove potentially unbounded
strcpy() calls.
They are mostly replaced by strscpy() or, when strlen() has just been
called, with memcpy() (usually including the '\0').
Calls with copy string literals into arrays are left unchanged.
They are safe and easily detected as such.
The changes were made by getting the compiler to detect the calls and
then fixing the code by hand.
Note that all the changes are only compile tested.
Some Makefiles were changed to allow files to contain strcpy().
As well as 'difficult to fix' files, this included 'show' functions
as they really need to use sysfs_emit() or seq_printf().
All the patches are being sent individually to avoid very long cc lists.
Apologies for the terse commit messages and likely unexpected tags.
(There are about 100 patches in total.)
drivers/bus/fsl-mc/fsl-mc-bus.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/bus/fsl-mc/fsl-mc-bus.c b/drivers/bus/fsl-mc/fsl-mc-bus.c
index 221146e4860b..372175fe169c 100644
--- a/drivers/bus/fsl-mc/fsl-mc-bus.c
+++ b/drivers/bus/fsl-mc/fsl-mc-bus.c
@@ -903,7 +903,7 @@ struct fsl_mc_device *fsl_mc_get_endpoint(struct fsl_mc_device *mc_dev,
int state, err;
mc_bus_dev = to_fsl_mc_device(mc_dev->dev.parent);
- strcpy(endpoint1.type, mc_dev->obj_desc.type);
+ strscpy(endpoint1.type, mc_dev->obj_desc.type);
endpoint1.id = mc_dev->obj_desc.id;
endpoint1.if_id = if_id;
@@ -920,7 +920,7 @@ struct fsl_mc_device *fsl_mc_get_endpoint(struct fsl_mc_device *mc_dev,
return ERR_PTR(err);
}
- strcpy(endpoint_desc.type, endpoint2.type);
+ strscpy(endpoint_desc.type, endpoint2.type);
endpoint_desc.id = endpoint2.id;
endpoint = fsl_mc_device_lookup(&endpoint_desc, mc_bus_dev);
if (endpoint)
--
2.39.5
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox