perf tools fixes for v5.19: 3rd batch

- BPF program info linear (BPIL) data is accessed assuming 64-bit alignment
   resulting in undefined behavior as the data is just byte aligned. Fix it,
   Found using -fsanitize=undefined.
 
 - Fix 'perf offcpu' build on old kernels wrt task_struct's state/__state field.
 
 - Fix perf_event_attr.sample_type setting on the 'offcpu-time' event synthesized
   by the 'perf offcpu' tool.
 
 - Don't bail out when synthesizing PERF_RECORD_ events for pre-existing threads
   when one goes away while parsing its procfs entries.
 
 - Don't sort the task scan result from /proc, its not needed and introduces bugs
   when the main thread isn't the first one to be processed.
 
 - Fix uninitialized 'offset' variable on aarch64 in the unwind code.
 
 - Sync KVM headers with the kernel sources.
 
 Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
 -----BEGIN PGP SIGNATURE-----
 
 iHUEABYKAB0WIQR2GiIUctdOfX2qHhGyPKLppCJ+JwUCYsBFOAAKCRCyPKLppCJ+
 J+xcAQDYFjs4ZlDVSd4Oj4Mk6ukHz8/9dluKMeWGUswx7x1nSQEAjBTlOrj/Dsrc
 DR3s2lQpQWLk+vWiSLBBPMrYYcM62g4=
 =6rgi
 -----END PGP SIGNATURE-----

Merge tag 'perf-tools-fixes-for-v5.19-2022-07-02' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux

Pull perf tools fixes from Arnaldo Carvalho de Melo:

 - BPF program info linear (BPIL) data is accessed assuming 64-bit
   alignment resulting in undefined behavior as the data is just byte
   aligned. Fix it, Found using -fsanitize=undefined.

 - Fix 'perf offcpu' build on old kernels wrt task_struct's
   state/__state field.

 - Fix perf_event_attr.sample_type setting on the 'offcpu-time' event
   synthesized by the 'perf offcpu' tool.

 - Don't bail out when synthesizing PERF_RECORD_ events for pre-existing
   threads when one goes away while parsing its procfs entries.

 - Don't sort the task scan result from /proc, its not needed and
   introduces bugs when the main thread isn't the first one to be
   processed.

 - Fix uninitialized 'offset' variable on aarch64 in the unwind code.

 - Sync KVM headers with the kernel sources.

* tag 'perf-tools-fixes-for-v5.19-2022-07-02' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux:
  perf synthetic-events: Ignore dead threads during event synthesis
  perf synthetic-events: Don't sort the task scan result from /proc
  perf unwind: Fix unitialized 'offset' variable on aarch64
  tools headers UAPI: Sync linux/kvm.h with the kernel sources
  perf bpf: 8 byte align bpil data
  tools kvm headers arm64: Update KVM headers from the kernel sources
  perf offcpu: Accept allowed sample types only
  perf offcpu: Fix build failure on old kernels

tools/arch/arm64/include/uapi/asm/kvm.h

@@ -139,8 +139,10 @@ struct kvm_guest_debug_arch {
 	__u64 dbg_wvr[KVM_ARM_MAX_DBG_REGS];
 };
 
+#define KVM_DEBUG_ARCH_HSR_HIGH_VALID	(1 << 0)
 struct kvm_debug_exit_arch {
 	__u32 hsr;
+	__u32 hsr_high;	/* ESR_EL2[61:32] */
 	__u64 far;	/* used for watchpoints */
 };
 
@@ -332,6 +334,40 @@ struct kvm_arm_copy_mte_tags {
 #define KVM_ARM64_SVE_VLS_WORDS	\
 	((KVM_ARM64_SVE_VQ_MAX - KVM_ARM64_SVE_VQ_MIN) / 64 + 1)
 
+/* Bitmap feature firmware registers */
+#define KVM_REG_ARM_FW_FEAT_BMAP		(0x0016 << KVM_REG_ARM_COPROC_SHIFT)
+#define KVM_REG_ARM_FW_FEAT_BMAP_REG(r)		(KVM_REG_ARM64 | KVM_REG_SIZE_U64 | \
+						KVM_REG_ARM_FW_FEAT_BMAP |	\
+						((r) & 0xffff))
+
+#define KVM_REG_ARM_STD_BMAP			KVM_REG_ARM_FW_FEAT_BMAP_REG(0)
+
+enum {
+	KVM_REG_ARM_STD_BIT_TRNG_V1_0	= 0,
+#ifdef __KERNEL__
+	KVM_REG_ARM_STD_BMAP_BIT_COUNT,
+#endif
+};
+
+#define KVM_REG_ARM_STD_HYP_BMAP		KVM_REG_ARM_FW_FEAT_BMAP_REG(1)
+
+enum {
+	KVM_REG_ARM_STD_HYP_BIT_PV_TIME	= 0,
+#ifdef __KERNEL__
+	KVM_REG_ARM_STD_HYP_BMAP_BIT_COUNT,
+#endif
+};
+
+#define KVM_REG_ARM_VENDOR_HYP_BMAP		KVM_REG_ARM_FW_FEAT_BMAP_REG(2)
+
+enum {
+	KVM_REG_ARM_VENDOR_HYP_BIT_FUNC_FEAT	= 0,
+	KVM_REG_ARM_VENDOR_HYP_BIT_PTP		= 1,
+#ifdef __KERNEL__
+	KVM_REG_ARM_VENDOR_HYP_BMAP_BIT_COUNT,
+#endif
+};
+
 /* Device Control API: ARM VGIC */
 #define KVM_DEV_ARM_VGIC_GRP_ADDR	0
 #define KVM_DEV_ARM_VGIC_GRP_DIST_REGS	1

tools/include/uapi/linux/kvm.h

@@ -444,6 +444,9 @@ struct kvm_run {
 #define KVM_SYSTEM_EVENT_SHUTDOWN       1
 #define KVM_SYSTEM_EVENT_RESET          2
 #define KVM_SYSTEM_EVENT_CRASH          3
+#define KVM_SYSTEM_EVENT_WAKEUP         4
+#define KVM_SYSTEM_EVENT_SUSPEND        5
+#define KVM_SYSTEM_EVENT_SEV_TERM       6
 			__u32 type;
 			__u32 ndata;
 			union {
@@ -646,6 +649,7 @@ struct kvm_vapic_addr {
 #define KVM_MP_STATE_OPERATING         7
 #define KVM_MP_STATE_LOAD              8
 #define KVM_MP_STATE_AP_RESET_HOLD     9
+#define KVM_MP_STATE_SUSPENDED         10
 
 struct kvm_mp_state {
 	__u32 mp_state;
@@ -1150,8 +1154,9 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_S390_MEM_OP_EXTENSION 211
 #define KVM_CAP_PMU_CAPABILITY 212
 #define KVM_CAP_DISABLE_QUIRKS2 213
-/* #define KVM_CAP_VM_TSC_CONTROL 214 */
+#define KVM_CAP_VM_TSC_CONTROL 214
 #define KVM_CAP_SYSTEM_EVENT_DATA 215
+#define KVM_CAP_ARM_SYSTEM_SUSPEND 216
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -1240,6 +1245,7 @@ struct kvm_x86_mce {
 #define KVM_XEN_HVM_CONFIG_SHARED_INFO		(1 << 2)
 #define KVM_XEN_HVM_CONFIG_RUNSTATE		(1 << 3)
 #define KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL	(1 << 4)
+#define KVM_XEN_HVM_CONFIG_EVTCHN_SEND		(1 << 5)
 
 struct kvm_xen_hvm_config {
 	__u32 flags;
@@ -1478,7 +1484,8 @@ struct kvm_s390_ucas_mapping {
 #define KVM_SET_PIT2              _IOW(KVMIO,  0xa0, struct kvm_pit_state2)
 /* Available with KVM_CAP_PPC_GET_PVINFO */
 #define KVM_PPC_GET_PVINFO	  _IOW(KVMIO,  0xa1, struct kvm_ppc_pvinfo)
-/* Available with KVM_CAP_TSC_CONTROL */
+/* Available with KVM_CAP_TSC_CONTROL for a vCPU, or with
+*  KVM_CAP_VM_TSC_CONTROL to set defaults for a VM */
 #define KVM_SET_TSC_KHZ           _IO(KVMIO,  0xa2)
 #define KVM_GET_TSC_KHZ           _IO(KVMIO,  0xa3)
 /* Available with KVM_CAP_PCI_2_3 */
@@ -1694,6 +1701,32 @@ struct kvm_xen_hvm_attr {
 		struct {
 			__u64 gfn;
 		} shared_info;
+		struct {
+			__u32 send_port;
+			__u32 type; /* EVTCHNSTAT_ipi / EVTCHNSTAT_interdomain */
+			__u32 flags;
+#define KVM_XEN_EVTCHN_DEASSIGN		(1 << 0)
+#define KVM_XEN_EVTCHN_UPDATE		(1 << 1)
+#define KVM_XEN_EVTCHN_RESET		(1 << 2)
+			/*
+			 * Events sent by the guest are either looped back to
+			 * the guest itself (potentially on a different port#)
+			 * or signalled via an eventfd.
+			 */
+			union {
+				struct {
+					__u32 port;
+					__u32 vcpu;
+					__u32 priority;
+				} port;
+				struct {
+					__u32 port; /* Zero for eventfd */
+					__s32 fd;
+				} eventfd;
+				__u32 padding[4];
+			} deliver;
+		} evtchn;
+		__u32 xen_version;
 		__u64 pad[8];
 	} u;
 };
@@ -1702,11 +1735,17 @@ struct kvm_xen_hvm_attr {
 #define KVM_XEN_ATTR_TYPE_LONG_MODE		0x0
 #define KVM_XEN_ATTR_TYPE_SHARED_INFO		0x1
 #define KVM_XEN_ATTR_TYPE_UPCALL_VECTOR		0x2
+/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_EVTCHN_SEND */
+#define KVM_XEN_ATTR_TYPE_EVTCHN		0x3
+#define KVM_XEN_ATTR_TYPE_XEN_VERSION		0x4
 
 /* Per-vCPU Xen attributes */
 #define KVM_XEN_VCPU_GET_ATTR	_IOWR(KVMIO, 0xca, struct kvm_xen_vcpu_attr)
 #define KVM_XEN_VCPU_SET_ATTR	_IOW(KVMIO,  0xcb, struct kvm_xen_vcpu_attr)
 
+/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_EVTCHN_SEND */
+#define KVM_XEN_HVM_EVTCHN_SEND	_IOW(KVMIO,  0xd0, struct kvm_irq_routing_xen_evtchn)
+
 #define KVM_GET_SREGS2             _IOR(KVMIO,  0xcc, struct kvm_sregs2)
 #define KVM_SET_SREGS2             _IOW(KVMIO,  0xcd, struct kvm_sregs2)
 
@@ -1724,6 +1763,13 @@ struct kvm_xen_vcpu_attr {
 			__u64 time_blocked;
 			__u64 time_offline;
 		} runstate;
+		__u32 vcpu_id;
+		struct {
+			__u32 port;
+			__u32 priority;
+			__u64 expires_ns;
+		} timer;
+		__u8 vector;
 	} u;
 };
 
@@ -1734,6 +1780,10 @@ struct kvm_xen_vcpu_attr {
 #define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_CURRENT	0x3
 #define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_DATA	0x4
 #define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADJUST	0x5
+/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_EVTCHN_SEND */
+#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_ID		0x6
+#define KVM_XEN_VCPU_ATTR_TYPE_TIMER		0x7
+#define KVM_XEN_VCPU_ATTR_TYPE_UPCALL_VECTOR	0x8
 
 /* Secure Encrypted Virtualization command */
 enum sev_cmd_id {

tools/perf/util/bpf-utils.c

@@ -149,11 +149,10 @@ get_bpf_prog_info_linear(int fd, __u64 arrays)
 		count = bpf_prog_info_read_offset_u32(&info, desc->count_offset);
 		size  = bpf_prog_info_read_offset_u32(&info, desc->size_offset);
 
-		data_len += count * size;
+		data_len += roundup(count * size, sizeof(__u64));
 	}
 
 	/* step 3: allocate continuous memory */
-	data_len = roundup(data_len, sizeof(__u64));
 	info_linear = malloc(sizeof(struct perf_bpil) + data_len);
 	if (!info_linear)
 		return ERR_PTR(-ENOMEM);
@@ -180,7 +179,7 @@ get_bpf_prog_info_linear(int fd, __u64 arrays)
 		bpf_prog_info_set_offset_u64(&info_linear->info,
 					     desc->array_offset,
 					     ptr_to_u64(ptr));
-		ptr += count * size;
+		ptr += roundup(count * size, sizeof(__u64));
 	}
 
 	/* step 5: call syscall again to get required arrays */

tools/perf/util/bpf_off_cpu.c

@@ -265,6 +265,12 @@ int off_cpu_write(struct perf_session *session)
 
 	sample_type = evsel->core.attr.sample_type;
 
+	if (sample_type & ~OFFCPU_SAMPLE_TYPES) {
+		pr_err("not supported sample type: %llx\n",
+		       (unsigned long long)sample_type);
+		return -1;
+	}
+
 	if (sample_type & (PERF_SAMPLE_ID | PERF_SAMPLE_IDENTIFIER)) {
 		if (evsel->core.id)
 			sid = evsel->core.id[0];
@@ -319,7 +325,6 @@ int off_cpu_write(struct perf_session *session)
 		}
 		if (sample_type & PERF_SAMPLE_CGROUP)
 			data.array[n++] = key.cgroup_id;
-		/* TODO: handle more sample types */
 
 		size = n * sizeof(u64);
 		data.hdr.size = size;

tools/perf/util/bpf_skel/off_cpu.bpf.c

@@ -71,6 +71,11 @@ struct {
 	__uint(max_entries, 1);
 } cgroup_filter SEC(".maps");
 
+/* new kernel task_struct definition */
+struct task_struct___new {
+	long __state;
+} __attribute__((preserve_access_index));
+
 /* old kernel task_struct definition */
 struct task_struct___old {
 	long state;
@@ -93,15 +98,18 @@ const volatile bool uses_cgroup_v1 = false;
  */
 static inline int get_task_state(struct task_struct *t)
 {
-	if (bpf_core_field_exists(t->__state))
-		return BPF_CORE_READ(t, __state);
+	/* recast pointer to capture new type for compiler */
+	struct task_struct___new *t_new = (void *)t;
 
-	/* recast pointer to capture task_struct___old type for compiler */
+	if (bpf_core_field_exists(t_new->__state)) {
+		return BPF_CORE_READ(t_new, __state);
+	} else {
+		/* recast pointer to capture old type for compiler */
 		struct task_struct___old *t_old = (void *)t;
 
-	/* now use old "state" name of the field */
 		return BPF_CORE_READ(t_old, state);
 	}
+}
 
 static inline __u64 get_cgroup_id(struct task_struct *t)
 {

tools/perf/util/evsel.c

@@ -48,6 +48,7 @@
 #include "util.h"
 #include "hashmap.h"
 #include "pmu-hybrid.h"
+#include "off_cpu.h"
 #include "../perf-sys.h"
 #include "util/parse-branch-options.h"
 #include <internal/xyarray.h>
@@ -1102,6 +1103,11 @@ static void evsel__set_default_freq_period(struct record_opts *opts,
 	}
 }
 
+static bool evsel__is_offcpu_event(struct evsel *evsel)
+{
+	return evsel__is_bpf_output(evsel) && !strcmp(evsel->name, OFFCPU_EVENT);
+}
+
 /*
  * The enable_on_exec/disabled value strategy:
  *
@@ -1366,6 +1372,9 @@ void evsel__config(struct evsel *evsel, struct record_opts *opts,
 	 */
 	if (evsel__is_dummy_event(evsel))
 		evsel__reset_sample_bit(evsel, BRANCH_STACK);
+
+	if (evsel__is_offcpu_event(evsel))
+		evsel->core.attr.sample_type &= OFFCPU_SAMPLE_TYPES;
 }
 
 int evsel__set_filter(struct evsel *evsel, const char *filter)

tools/perf/util/off_cpu.h

@@ -1,6 +1,8 @@
 #ifndef PERF_UTIL_OFF_CPU_H
 #define PERF_UTIL_OFF_CPU_H
 
+#include <linux/perf_event.h>
+
 struct evlist;
 struct target;
 struct perf_session;
@@ -8,6 +10,13 @@ struct record_opts;
 
 #define OFFCPU_EVENT  "offcpu-time"
 
+#define OFFCPU_SAMPLE_TYPES  (PERF_SAMPLE_IDENTIFIER | PERF_SAMPLE_IP | \
+			      PERF_SAMPLE_TID | PERF_SAMPLE_TIME | \
+			      PERF_SAMPLE_ID | PERF_SAMPLE_CPU | \
+			      PERF_SAMPLE_PERIOD | PERF_SAMPLE_CALLCHAIN | \
+			      PERF_SAMPLE_CGROUP)
+
+
 #ifdef HAVE_BPF_SKEL
 int off_cpu_prepare(struct evlist *evlist, struct target *target,
 		    struct record_opts *opts);

tools/perf/util/synthetic-events.c

@@ -754,7 +754,7 @@ static int __event__synthesize_thread(union perf_event *comm_event,
 	snprintf(filename, sizeof(filename), "%s/proc/%d/task",
 		 machine->root_dir, pid);
 
-	n = scandir(filename, &dirent, filter_task, alphasort);
+	n = scandir(filename, &dirent, filter_task, NULL);
 	if (n < 0)
 		return n;
 
@@ -767,11 +767,12 @@ static int __event__synthesize_thread(union perf_event *comm_event,
 		if (*end)
 			continue;
 
-		rc = -1;
+		/* some threads may exit just after scan, ignore it */
 		if (perf_event__prepare_comm(comm_event, pid, _pid, machine,
 					     &tgid, &ppid, &kernel_thread) != 0)
-			break;
+			continue;
 
+		rc = -1;
 		if (perf_event__synthesize_fork(tool, fork_event, _pid, tgid,
 						ppid, process, machine) < 0)
 			break;
@@ -987,7 +988,7 @@ int perf_event__synthesize_threads(struct perf_tool *tool,
 		return 0;
 
 	snprintf(proc_path, sizeof(proc_path), "%s/proc", machine->root_dir);
-	n = scandir(proc_path, &dirent, filter_task, alphasort);
+	n = scandir(proc_path, &dirent, filter_task, NULL);
 	if (n < 0)
 		return err;
 

tools/perf/util/unwind-libunwind-local.c

@@ -197,7 +197,7 @@ static int elf_section_address_and_offset(int fd, const char *name, u64 *address
 #ifndef NO_LIBUNWIND_DEBUG_FRAME
 static u64 elf_section_offset(int fd, const char *name)
 {
-	u64 address, offset;
+	u64 address, offset = 0;
 
 	if (elf_section_address_and_offset(fd, name, &address, &offset))
 		return 0;