Merge branch 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf fixes from Thomas Gleixner:
 "A larger set of updates for perf.

  Kernel:

   - Handle the SBOX uncore monitoring correctly on Broadwell CPUs which
     do not have SBOX.

   - Store context switch out type in PERF_RECORD_SWITCH[_CPU_WIDE]. The
     percentage of preempting and non-preempting context switches help
     understanding the nature of workloads (CPU or IO bound) that are
     running on a machine. This adds the kernel facility and userspace
     changes needed to show this information in 'perf script' and 'perf
     report -D' (Alexey Budankov)

   - Remove a WARN_ON() in the trace/kprobes code which is pointless
     because the return error code is already telling the caller what's
     wrong.

   - Revert a fugly workaround for clang BPF targets.

   - Fix sample_max_stack maximum check and do not proceed when an error
     has been detect, return them to avoid misidentifying errors (Jiri
     Olsa)

   - Add SPDX idenitifiers and get rid of GPL boilderplate.

  Tools:

   - Synchronize kernel ABI headers, v4.17-rc1 (Ingo Molnar)

   - Support MAP_FIXED_NOREPLACE, noticed when updating the
     tools/include/ copies (Arnaldo Carvalho de Melo)

   - Add '\n' at the end of parse-options error messages (Ravi Bangoria)

   - Add s390 support for detailed/verbose PMU event description (Thomas
     Richter)

   - perf annotate fixes and improvements:

      * Allow showing offsets in more than just jump targets, use the
        new 'O' hotkey in the TUI, config ~/.perfconfig
        annotate.offset_level for it and for --stdio2 (Arnaldo Carvalho
        de Melo)

      * Use the resolved variable names from objdump disassembled lines
        to make them more compact, just like was already done for some
        instructions, like "mov", this eventually will be done more
        generally, but lets now add some more to the existing mechanism
        (Arnaldo Carvalho de Melo)

   - perf record fixes:

      * Change warning for missing topology sysfs entry to debug, as not
        all architectures have those files, s390 being one of those
        (Thomas Richter)

      * Remove old error messages about things that unlikely to be the
        root cause in modern systems (Andi Kleen)

   - perf sched fixes:

      * Fix -g/--call-graph documentation (Takuya Yamamoto)

   - perf stat:

      * Enable 1ms interval for printing event counters values in
        (Alexey Budankov)

   - perf test fixes:

      * Run dwarf unwind on arm32 (Kim Phillips)

      * Remove unused ptrace.h include from LLVM test, sidesteping older
        clang's lack of support for some asm constructs (Arnaldo
        Carvalho de Melo)

      * Fixup BPF test using epoll_pwait syscall function probe, to cope
        with the syscall routines renames performed in this development
        cycle (Arnaldo Carvalho de Melo)

   - perf version fixes:

      * Do not print info about HAVE_LIBAUDIT_SUPPORT in 'perf version
        --build-options' when HAVE_SYSCALL_TABLE_SUPPORT is true, as
        libaudit won't be used in that case, print info about
        syscall_table support instead (Jin Yao)

   - Build system fixes:

      * Use HAVE_..._SUPPORT used consistently (Jin Yao)

      * Restore READ_ONCE() C++ compatibility in tools/include (Mark
        Rutland)

      * Give hints about package names needed to build jvmti (Arnaldo
        Carvalho de Melo)"

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (37 commits)
  perf/x86/intel/uncore: Fix SBOX support for Broadwell CPUs
  perf/x86/intel/uncore: Revert "Remove SBOX support for Broadwell server"
  coresight: Move to SPDX identifier
  perf test BPF: Fixup BPF test using epoll_pwait syscall function probe
  perf tests mmap: Show which tracepoint is failing
  perf tools: Add '\n' at the end of parse-options error messages
  perf record: Remove suggestion to enable APIC
  perf record: Remove misleading error suggestion
  perf hists browser: Clarify top/report browser help
  perf mem: Allow all record/report options
  perf trace: Support MAP_FIXED_NOREPLACE
  perf: Remove superfluous allocation error check
  perf: Fix sample_max_stack maximum check
  perf: Return proper values for user stack errors
  perf list: Add s390 support for detailed/verbose PMU event description
  perf script: Extend misc field decoding with switch out event type
  perf report: Extend raw dump (-D) out with switch out event type
  perf/core: Store context switch out type in PERF_RECORD_SWITCH[_CPU_WIDE]
  tools/headers: Synchronize kernel ABI headers, v4.17-rc1
  trace_kprobe: Remove warning message "Could not insert probe at..."
  ...

arch/x86/events/intel/uncore_snbep.c

@@ -3028,10 +3028,27 @@ static struct intel_uncore_type bdx_uncore_cbox = {
 	.format_group		= &hswep_uncore_cbox_format_group,
 };
 
+static struct intel_uncore_type bdx_uncore_sbox = {
+	.name			= "sbox",
+	.num_counters		= 4,
+	.num_boxes		= 4,
+	.perf_ctr_bits		= 48,
+	.event_ctl		= HSWEP_S0_MSR_PMON_CTL0,
+	.perf_ctr		= HSWEP_S0_MSR_PMON_CTR0,
+	.event_mask		= HSWEP_S_MSR_PMON_RAW_EVENT_MASK,
+	.box_ctl		= HSWEP_S0_MSR_PMON_BOX_CTL,
+	.msr_offset		= HSWEP_SBOX_MSR_OFFSET,
+	.ops			= &hswep_uncore_sbox_msr_ops,
+	.format_group		= &hswep_uncore_sbox_format_group,
+};
+
+#define BDX_MSR_UNCORE_SBOX	3
+
 static struct intel_uncore_type *bdx_msr_uncores[] = {
 	&bdx_uncore_ubox,
 	&bdx_uncore_cbox,
 	&hswep_uncore_pcu,
+	&bdx_uncore_sbox,
 	NULL,
 };
 
@@ -3043,10 +3060,25 @@ static struct event_constraint bdx_uncore_pcu_constraints[] = {
 
 void bdx_uncore_cpu_init(void)
 {
+	int pkg = topology_phys_to_logical_pkg(0);
+
 	if (bdx_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores)
 		bdx_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores;
 	uncore_msr_uncores = bdx_msr_uncores;
 
+	/* BDX-DE doesn't have SBOX */
+	if (boot_cpu_data.x86_model == 86) {
+		uncore_msr_uncores[BDX_MSR_UNCORE_SBOX] = NULL;
+	/* Detect systems with no SBOXes */
+	} else if (uncore_extra_pci_dev[pkg].dev[HSWEP_PCI_PCU_3]) {
+		struct pci_dev *pdev;
+		u32 capid4;
+
+		pdev = uncore_extra_pci_dev[pkg].dev[HSWEP_PCI_PCU_3];
+		pci_read_config_dword(pdev, 0x94, &capid4);
+		if (((capid4 >> 6) & 0x3) == 0)
+			bdx_msr_uncores[BDX_MSR_UNCORE_SBOX] = NULL;
+	}
 	hswep_uncore_pcu.constraints = bdx_uncore_pcu_constraints;
 }
 
@@ -3264,6 +3296,11 @@ static const struct pci_device_id bdx_uncore_pci_ids[] = {
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f46),
 		.driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, 2),
 	},
+	{ /* PCU.3 (for Capability registers) */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6fc0),
+		.driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV,
+						   HSWEP_PCI_PCU_3),
+	},
 	{ /* end: all zeroes */ }
 };
 

arch/x86/include/asm/asm.h

@@ -136,7 +136,6 @@
 #endif
 
 #ifndef __ASSEMBLY__
-#ifndef __BPF__
 /*
  * This output constraint should be used for any inline asm which has a "call"
  * instruction.  Otherwise the asm may be inserted before the frame pointer
@@ -146,6 +145,5 @@
 register unsigned long current_stack_pointer asm(_ASM_SP);
 #define ASM_CALL_CONSTRAINT "+r" (current_stack_pointer)
 #endif
-#endif
 
 #endif /* _ASM_X86_ASM_H */

include/linux/coresight-pmu.h

+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Copyright(C) 2015 Linaro Limited. All rights reserved.
  * Author: Mathieu Poirier <mathieu.poirier@linaro.org>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published by
- * the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef _LINUX_CORESIGHT_PMU_H

include/uapi/linux/perf_event.h

@@ -650,11 +650,23 @@ struct perf_event_mmap_page {
 #define PERF_RECORD_MISC_COMM_EXEC		(1 << 13)
 #define PERF_RECORD_MISC_SWITCH_OUT		(1 << 13)
 /*
- * Indicates that the content of PERF_SAMPLE_IP points to
- * the actual instruction that triggered the event. See also
- * perf_event_attr::precise_ip.
+ * These PERF_RECORD_MISC_* flags below are safely reused
+ * for the following events:
+ *
+ *   PERF_RECORD_MISC_EXACT_IP           - PERF_RECORD_SAMPLE of precise events
+ *   PERF_RECORD_MISC_SWITCH_OUT_PREEMPT - PERF_RECORD_SWITCH* events
+ *
+ *
+ * PERF_RECORD_MISC_EXACT_IP:
+ *   Indicates that the content of PERF_SAMPLE_IP points to
+ *   the actual instruction that triggered the event. See also
+ *   perf_event_attr::precise_ip.
+ *
+ * PERF_RECORD_MISC_SWITCH_OUT_PREEMPT:
+ *   Indicates that thread was preempted in TASK_RUNNING state.
  */
 #define PERF_RECORD_MISC_EXACT_IP		(1 << 14)
+#define PERF_RECORD_MISC_SWITCH_OUT_PREEMPT	(1 << 14)
 /*
  * Reserve the last bit to indicate some extended misc field
  */

kernel/events/callchain.c

@@ -119,23 +119,20 @@ int get_callchain_buffers(int event_max_stack)
 		goto exit;
 	}
 
-	if (count > 1) {
-		/* If the allocation failed, give up */
-		if (!callchain_cpus_entries)
-			err = -ENOMEM;
-		/*
-		 * If requesting per event more than the global cap,
-		 * return a different error to help userspace figure
-		 * this out.
-		 *
-		 * And also do it here so that we have &callchain_mutex held.
-		 */
-		if (event_max_stack > sysctl_perf_event_max_stack)
-			err = -EOVERFLOW;
+	/*
+	 * If requesting per event more than the global cap,
+	 * return a different error to help userspace figure
+	 * this out.
+	 *
+	 * And also do it here so that we have &callchain_mutex held.
+	 */
+	if (event_max_stack > sysctl_perf_event_max_stack) {
+		err = -EOVERFLOW;
 		goto exit;
 	}
 
-	err = alloc_callchain_buffers();
+	if (count == 1)
+		err = alloc_callchain_buffers();
 exit:
 	if (err)
 		atomic_dec(&nr_callchain_events);

kernel/events/core.c

@@ -7587,6 +7587,10 @@ static void perf_event_switch(struct task_struct *task,
 		},
 	};
 
+	if (!sched_in && task->state == TASK_RUNNING)
+		switch_event.event_id.header.misc |=
+				PERF_RECORD_MISC_SWITCH_OUT_PREEMPT;
+
 	perf_iterate_sb(perf_event_switch_output,
 		       &switch_event,
 		       NULL);
@@ -10205,9 +10209,9 @@ static int perf_copy_attr(struct perf_event_attr __user *uattr,
 		 * __u16 sample size limit.
 		 */
 		if (attr->sample_stack_user >= USHRT_MAX)
-			ret = -EINVAL;
+			return -EINVAL;
 		else if (!IS_ALIGNED(attr->sample_stack_user, sizeof(u64)))
-			ret = -EINVAL;
+			return -EINVAL;
 	}
 
 	if (!attr->sample_max_stack)

kernel/trace/trace_kprobe.c

@@ -512,8 +512,6 @@ static int __register_trace_kprobe(struct trace_kprobe *tk)
 	if (ret == 0)
 		tk->tp.flags |= TP_FLAG_REGISTERED;
 	else {
-		pr_warn("Could not insert probe at %s+%lu: %d\n",
-			trace_kprobe_symbol(tk), trace_kprobe_offset(tk), ret);
 		if (ret == -ENOENT && trace_kprobe_is_on_module(tk)) {
 			pr_warn("This probe might be able to register after target module is loaded. Continue.\n");
 			ret = 0;

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

@@ -135,6 +135,15 @@ struct kvm_arch_memory_slot {
 #define KVM_REG_ARM_CRM_SHIFT		7
 #define KVM_REG_ARM_32_CRN_MASK		0x0000000000007800
 #define KVM_REG_ARM_32_CRN_SHIFT	11
+/*
+ * For KVM currently all guest registers are nonsecure, but we reserve a bit
+ * in the encoding to distinguish secure from nonsecure for AArch32 system
+ * registers that are banked by security. This is 1 for the secure banked
+ * register, and 0 for the nonsecure banked register or if the register is
+ * not banked by security.
+ */
+#define KVM_REG_ARM_SECURE_MASK	0x0000000010000000
+#define KVM_REG_ARM_SECURE_SHIFT	28
 
 #define ARM_CP15_REG_SHIFT_MASK(x,n) \
 	(((x) << KVM_REG_ARM_ ## n ## _SHIFT) & KVM_REG_ARM_ ## n ## _MASK)

tools/arch/x86/include/asm/required-features.h

@@ -53,12 +53,6 @@
 # define NEED_MOVBE	0
 #endif
 
-#ifdef CONFIG_X86_5LEVEL
-# define NEED_LA57	(1<<(X86_FEATURE_LA57 & 31))
-#else
-# define NEED_LA57	0
-#endif
-
 #ifdef CONFIG_X86_64
 #ifdef CONFIG_PARAVIRT
 /* Paravirtualized systems may not have PSE or PGE available */
@@ -104,7 +98,7 @@
 #define REQUIRED_MASK13	0
 #define REQUIRED_MASK14	0
 #define REQUIRED_MASK15	0
-#define REQUIRED_MASK16	(NEED_LA57)
+#define REQUIRED_MASK16	0
 #define REQUIRED_MASK17	0
 #define REQUIRED_MASK18	0
 #define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 19)

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

@@ -354,8 +354,25 @@ struct kvm_xcrs {
 	__u64 padding[16];
 };
 
-/* definition of registers in kvm_run */
+#define KVM_SYNC_X86_REGS      (1UL << 0)
+#define KVM_SYNC_X86_SREGS     (1UL << 1)
+#define KVM_SYNC_X86_EVENTS    (1UL << 2)
+
+#define KVM_SYNC_X86_VALID_FIELDS \
+	(KVM_SYNC_X86_REGS| \
+	 KVM_SYNC_X86_SREGS| \
+	 KVM_SYNC_X86_EVENTS)
+
+/* kvm_sync_regs struct included by kvm_run struct */
 struct kvm_sync_regs {
+	/* Members of this structure are potentially malicious.
+	 * Care must be taken by code reading, esp. interpreting,
+	 * data fields from them inside KVM to prevent TOCTOU and
+	 * double-fetch types of vulnerabilities.
+	 */
+	struct kvm_regs regs;
+	struct kvm_sregs sregs;
+	struct kvm_vcpu_events events;
 };
 
 #define KVM_X86_QUIRK_LINT0_REENABLED	(1 << 0)

tools/include/linux/compiler.h

@@ -151,11 +151,21 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s
  * required ordering.
  */
 
-#define READ_ONCE(x) \
-	({ union { typeof(x) __val; char __c[1]; } __u; __read_once_size(&(x), __u.__c, sizeof(x)); __u.__val; })
-
-#define WRITE_ONCE(x, val) \
-	({ union { typeof(x) __val; char __c[1]; } __u = { .__val = (val) }; __write_once_size(&(x), __u.__c, sizeof(x)); __u.__val; })
+#define READ_ONCE(x)					\
+({							\
+	union { typeof(x) __val; char __c[1]; } __u =	\
+		{ .__c = { 0 } };			\
+	__read_once_size(&(x), __u.__c, sizeof(x));	\
+	__u.__val;					\
+})
+
+#define WRITE_ONCE(x, val)				\
+({							\
+	union { typeof(x) __val; char __c[1]; } __u =	\
+		{ .__val = (val) }; 			\
+	__write_once_size(&(x), __u.__c, sizeof(x));	\
+	__u.__val;					\
+})
 
 
 #ifndef __fallthrough

tools/include/linux/coresight-pmu.h

+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Copyright(C) 2015 Linaro Limited. All rights reserved.
  * Author: Mathieu Poirier <mathieu.poirier@linaro.org>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published by
- * the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef _LINUX_CORESIGHT_PMU_H

tools/include/uapi/asm-generic/mman-common.h

@@ -27,6 +27,9 @@
 # define MAP_UNINITIALIZED 0x0		/* Don't support this flag */
 #endif
 
+/* 0x0100 - 0x80000 flags are defined in asm-generic/mman.h */
+#define MAP_FIXED_NOREPLACE	0x100000	/* MAP_FIXED which doesn't unmap underlying mapping */
+
 /*
  * Flags for mlock
  */

tools/include/uapi/linux/bpf.h

@@ -864,6 +864,7 @@ enum bpf_func_id {
 /* BPF_FUNC_skb_set_tunnel_key flags. */
 #define BPF_F_ZERO_CSUM_TX		(1ULL << 1)
 #define BPF_F_DONT_FRAGMENT		(1ULL << 2)
+#define BPF_F_SEQ_NUMBER		(1ULL << 3)
 
 /* BPF_FUNC_perf_event_output, BPF_FUNC_perf_event_read and
  * BPF_FUNC_perf_event_read_value flags.

tools/include/uapi/linux/if_link.h

@@ -941,4 +941,43 @@ enum {
 	IFLA_EVENT_BONDING_OPTIONS,	/* change in bonding options */
 };
 
+/* tun section */
+
+enum {
+	IFLA_TUN_UNSPEC,
+	IFLA_TUN_OWNER,
+	IFLA_TUN_GROUP,
+	IFLA_TUN_TYPE,
+	IFLA_TUN_PI,
+	IFLA_TUN_VNET_HDR,
+	IFLA_TUN_PERSIST,
+	IFLA_TUN_MULTI_QUEUE,
+	IFLA_TUN_NUM_QUEUES,
+	IFLA_TUN_NUM_DISABLED_QUEUES,
+	__IFLA_TUN_MAX,
+};
+
+#define IFLA_TUN_MAX (__IFLA_TUN_MAX - 1)
+
+/* rmnet section */
+
+#define RMNET_FLAGS_INGRESS_DEAGGREGATION         (1U << 0)
+#define RMNET_FLAGS_INGRESS_MAP_COMMANDS          (1U << 1)
+#define RMNET_FLAGS_INGRESS_MAP_CKSUMV4           (1U << 2)
+#define RMNET_FLAGS_EGRESS_MAP_CKSUMV4            (1U << 3)
+
+enum {
+	IFLA_RMNET_UNSPEC,
+	IFLA_RMNET_MUX_ID,
+	IFLA_RMNET_FLAGS,
+	__IFLA_RMNET_MAX,
+};
+
+#define IFLA_RMNET_MAX	(__IFLA_RMNET_MAX - 1)
+
+struct ifla_rmnet_flags {
+	__u32	flags;
+	__u32	mask;
+};
+
 #endif /* _UAPI_LINUX_IF_LINK_H */

tools/include/uapi/linux/kvm.h

@@ -396,6 +396,10 @@ struct kvm_run {
 		char padding[256];
 	};
 
+	/* 2048 is the size of the char array used to bound/pad the size
+	 * of the union that holds sync regs.
+	 */
+	#define SYNC_REGS_SIZE_BYTES 2048
 	/*
 	 * shared registers between kvm and userspace.
 	 * kvm_valid_regs specifies the register classes set by the host
@@ -407,7 +411,7 @@ struct kvm_run {
 	__u64 kvm_dirty_regs;
 	union {
 		struct kvm_sync_regs regs;
-		char padding[2048];
+		char padding[SYNC_REGS_SIZE_BYTES];
 	} s;
 };
 
@@ -936,6 +940,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_PPC_GET_CPU_CHAR 151
 #define KVM_CAP_S390_BPB 152
 #define KVM_CAP_GET_MSR_FEATURES 153
+#define KVM_CAP_HYPERV_EVENTFD 154
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -1375,6 +1380,10 @@ struct kvm_enc_region {
 #define KVM_MEMORY_ENCRYPT_REG_REGION    _IOR(KVMIO, 0xbb, struct kvm_enc_region)
 #define KVM_MEMORY_ENCRYPT_UNREG_REGION  _IOR(KVMIO, 0xbc, struct kvm_enc_region)
 
+/* Available with KVM_CAP_HYPERV_EVENTFD */
+#define KVM_HYPERV_EVENTFD        _IOW(KVMIO,  0xbd, struct kvm_hyperv_eventfd)
+
+
 /* Secure Encrypted Virtualization command */
 enum sev_cmd_id {
 	/* Guest initialization commands */
@@ -1515,4 +1524,14 @@ struct kvm_assigned_msix_entry {
 #define KVM_ARM_DEV_EL1_PTIMER		(1 << 1)
 #define KVM_ARM_DEV_PMU			(1 << 2)
 
+struct kvm_hyperv_eventfd {
+	__u32 conn_id;
+	__s32 fd;
+	__u32 flags;
+	__u32 padding[3];
+};
+
+#define KVM_HYPERV_CONN_ID_MASK		0x00ffffff
+#define KVM_HYPERV_EVENTFD_DEASSIGN	(1 << 0)
+
 #endif /* __LINUX_KVM_H */

tools/include/uapi/linux/perf_event.h

@@ -650,11 +650,23 @@ struct perf_event_mmap_page {
 #define PERF_RECORD_MISC_COMM_EXEC		(1 << 13)
 #define PERF_RECORD_MISC_SWITCH_OUT		(1 << 13)
 /*
- * Indicates that the content of PERF_SAMPLE_IP points to
- * the actual instruction that triggered the event. See also
- * perf_event_attr::precise_ip.
+ * These PERF_RECORD_MISC_* flags below are safely reused
+ * for the following events:
+ *
+ *   PERF_RECORD_MISC_EXACT_IP           - PERF_RECORD_SAMPLE of precise events
+ *   PERF_RECORD_MISC_SWITCH_OUT_PREEMPT - PERF_RECORD_SWITCH* events
+ *
+ *
+ * PERF_RECORD_MISC_EXACT_IP:
+ *   Indicates that the content of PERF_SAMPLE_IP points to
+ *   the actual instruction that triggered the event. See also
+ *   perf_event_attr::precise_ip.
+ *
+ * PERF_RECORD_MISC_SWITCH_OUT_PREEMPT:
+ *   Indicates that thread was preempted in TASK_RUNNING state.
  */
 #define PERF_RECORD_MISC_EXACT_IP		(1 << 14)
+#define PERF_RECORD_MISC_SWITCH_OUT_PREEMPT	(1 << 14)
 /*
  * Reserve the last bit to indicate some extended misc field
  */

tools/include/uapi/sound/asound.h

@@ -242,6 +242,7 @@ typedef int __bitwise snd_pcm_format_t;
 #define	SNDRV_PCM_FORMAT_DSD_U16_BE	((__force snd_pcm_format_t) 51) /* DSD, 2-byte samples DSD (x16), big endian */
 #define	SNDRV_PCM_FORMAT_DSD_U32_BE	((__force snd_pcm_format_t) 52) /* DSD, 4-byte samples DSD (x32), big endian */
 #define	SNDRV_PCM_FORMAT_LAST		SNDRV_PCM_FORMAT_DSD_U32_BE
+#define	SNDRV_PCM_FORMAT_FIRST		SNDRV_PCM_FORMAT_S8
 
 #ifdef SNDRV_LITTLE_ENDIAN
 #define	SNDRV_PCM_FORMAT_S16		SNDRV_PCM_FORMAT_S16_LE

tools/lib/subcmd/parse-options.c

@@ -433,7 +433,7 @@ static int parse_long_opt(struct parse_opt_ctx_t *p, const char *arg,
 
 	if (ambiguous_option) {
 		 fprintf(stderr,
-			 " Error: Ambiguous option: %s (could be --%s%s or --%s%s)",
+			 " Error: Ambiguous option: %s (could be --%s%s or --%s%s)\n",
 			 arg,
 			 (ambiguous_flags & OPT_UNSET) ?  "no-" : "",
 			 ambiguous_option->long_name,
@@ -458,7 +458,7 @@ static void check_typos(const char *arg, const struct option *options)
 		return;
 
 	if (strstarts(arg, "no-")) {
-		fprintf(stderr, " Error: did you mean `--%s` (with two dashes ?)", arg);
+		fprintf(stderr, " Error: did you mean `--%s` (with two dashes ?)\n", arg);
 		exit(129);
 	}
 
@@ -466,7 +466,7 @@ static void check_typos(const char *arg, const struct option *options)
 		if (!options->long_name)
 			continue;
 		if (strstarts(options->long_name, arg)) {
-			fprintf(stderr, " Error: did you mean `--%s` (with two dashes ?)", arg);
+			fprintf(stderr, " Error: did you mean `--%s` (with two dashes ?)\n", arg);
 			exit(129);
 		}
 	}

tools/perf/Documentation/perf-config.txt

@@ -334,6 +334,11 @@ annotate.*::
 
 		99.93 │      mov    %eax,%eax
 
+	annotate.offset_level::
+		Default is '1', meaning just jump targets will have offsets show right beside
+		the instruction. When set to '2' 'call' instructions will also have its offsets
+		shown, 3 or higher will show offsets for all instructions.
+
 hist.*::
 	hist.percentage::
 		This option control the way to calculate overhead of filtered entries -

tools/perf/Documentation/perf-mem.txt

@@ -67,6 +67,9 @@ OPTIONS
 --phys-data::
 	Record/Report sample physical addresses
 
+In addition, for report all perf report options are valid, and for record
+all perf record options.
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-report[1]

tools/perf/Documentation/perf-sched.txt

@@ -104,8 +104,8 @@ OPTIONS for 'perf sched timehist'
     kallsyms pathname
 
 -g::
---no-call-graph::
-	Do not display call chains if present.
+--call-graph::
+	Display call chains if present (default on).
 
 --max-stack::
 	Maximum number of functions to display in backtrace, default 5.

tools/perf/Documentation/perf-script.txt

@@ -228,14 +228,15 @@ OPTIONS
 	For sample events it's possible to display misc field with -F +misc option,
 	following letters are displayed for each bit:
 
-	  PERF_RECORD_MISC_KERNEL        K
-	  PERF_RECORD_MISC_USER          U
-	  PERF_RECORD_MISC_HYPERVISOR    H
-	  PERF_RECORD_MISC_GUEST_KERNEL  G
-	  PERF_RECORD_MISC_GUEST_USER    g
-	  PERF_RECORD_MISC_MMAP_DATA*    M
-	  PERF_RECORD_MISC_COMM_EXEC     E
-	  PERF_RECORD_MISC_SWITCH_OUT    S
+	  PERF_RECORD_MISC_KERNEL               K
+	  PERF_RECORD_MISC_USER                 U
+	  PERF_RECORD_MISC_HYPERVISOR           H
+	  PERF_RECORD_MISC_GUEST_KERNEL         G
+	  PERF_RECORD_MISC_GUEST_USER           g
+	  PERF_RECORD_MISC_MMAP_DATA*           M
+	  PERF_RECORD_MISC_COMM_EXEC            E
+	  PERF_RECORD_MISC_SWITCH_OUT           S
+	  PERF_RECORD_MISC_SWITCH_OUT_PREEMPT   Sp
 
 	  $ perf script -F +misc ...
 	   sched-messaging  1414 K     28690.636582:       4590 cycles ...

tools/perf/Documentation/perf-stat.txt

@@ -153,7 +153,7 @@ perf stat --repeat 10 --null --sync --pre 'make -s O=defconfig-build/clean' -- m
 
 -I msecs::
 --interval-print msecs::
-Print count deltas every N milliseconds (minimum: 10ms)
+Print count deltas every N milliseconds (minimum: 1ms)
 The overhead percentage could be high in some cases, for instance with small, sub 100ms intervals.  Use with caution.
 	example: 'perf stat -I 1000 -e cycles -a sleep 5'
 

tools/perf/Makefile.config

@@ -68,7 +68,7 @@ ifeq ($(NO_PERF_REGS),0)
 endif
 
 ifneq ($(NO_SYSCALL_TABLE),1)
-  CFLAGS += -DHAVE_SYSCALL_TABLE
+  CFLAGS += -DHAVE_SYSCALL_TABLE_SUPPORT
 endif
 
 # So far there's only x86 and arm libdw unwind support merged in perf.
@@ -847,7 +847,7 @@ ifndef NO_JVMTI
   ifeq ($(feature-jvmti), 1)
     $(call detected_var,JDIR)
   else
-    $(warning No openjdk development package found, please install JDK package)
+    $(warning No openjdk development package found, please install JDK package, e.g. openjdk-8-jdk, java-1.8.0-openjdk-devel)
     NO_JVMTI := 1
   endif
 endif

tools/perf/arch/arm/include/arch-tests.h

+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef ARCH_TESTS_H
+#define ARCH_TESTS_H
+
+#ifdef HAVE_DWARF_UNWIND_SUPPORT
+struct thread;
+struct perf_sample;
+#endif
+
+extern struct test arch_tests[];
+
+#endif

tools/perf/arch/arm/tests/Build

 libperf-y += regs_load.o
 libperf-y += dwarf-unwind.o
+
+libperf-y += arch-tests.o

tools/perf/arch/arm/tests/arch-tests.c

+// SPDX-License-Identifier: GPL-2.0
+#include <string.h>
+#include "tests/tests.h"
+#include "arch-tests.h"
+
+struct test arch_tests[] = {
+#ifdef HAVE_DWARF_UNWIND_SUPPORT
+	{
+		.desc = "DWARF unwind",
+		.func = test__dwarf_unwind,
+	},
+#endif
+	{
+		.func = NULL,
+	},
+};

tools/perf/arch/arm/util/auxtrace.c

+// SPDX-License-Identifier: GPL-2.0
 /*
  * Copyright(C) 2015 Linaro Limited. All rights reserved.
  * Author: Mathieu Poirier <mathieu.poirier@linaro.org>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published by
- * the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #include <stdbool.h>

tools/perf/arch/arm/util/cs-etm.c

+// SPDX-License-Identifier: GPL-2.0
 /*
  * Copyright(C) 2015 Linaro Limited. All rights reserved.
  * Author: Mathieu Poirier <mathieu.poirier@linaro.org>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published by
- * the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #include <api/fs/fs.h>

tools/perf/arch/arm/util/cs-etm.h

+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Copyright(C) 2015 Linaro Limited. All rights reserved.
  * Author: Mathieu Poirier <mathieu.poirier@linaro.org>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published by
- * the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef INCLUDE__PERF_CS_ETM_H__

tools/perf/arch/arm/util/pmu.c

+// SPDX-License-Identifier: GPL-2.0
 /*
  * Copyright(C) 2015 Linaro Limited. All rights reserved.
  * Author: Mathieu Poirier <mathieu.poirier@linaro.org>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published by
- * the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #include <string.h>

tools/perf/arch/x86/Makefile

@@ -21,7 +21,7 @@ _dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)')
 $(header): $(sys)/syscall_64.tbl $(systbl)
 	@(test -d ../../kernel -a -d ../../tools -a -d ../perf && ( \
         (diff -B arch/x86/entry/syscalls/syscall_64.tbl ../../arch/x86/entry/syscalls/syscall_64.tbl >/dev/null) \
-        || echo "Warning: Kernel ABI header at 'tools/arch/x86/entry/syscalls/syscall_64.tbl' differs from latest version at 'arch/x86/entry/syscalls/syscall_64.tbl'" >&2 )) || true
+        || echo "Warning: Kernel ABI header at 'tools/perf/arch/x86/entry/syscalls/syscall_64.tbl' differs from latest version at 'arch/x86/entry/syscalls/syscall_64.tbl'" >&2 )) || true
 	$(Q)$(SHELL) '$(systbl)' $(sys)/syscall_64.tbl 'x86_64' > $@
 
 clean::

tools/perf/arch/x86/annotate/instructions.c

 // SPDX-License-Identifier: GPL-2.0
 static struct ins x86__instructions[] = {
+	{ .name = "adc",	.ops = &mov_ops,  },
+	{ .name = "adcb",	.ops = &mov_ops,  },
+	{ .name = "adcl",	.ops = &mov_ops,  },
 	{ .name = "add",	.ops = &mov_ops,  },
 	{ .name = "addl",	.ops = &mov_ops,  },
 	{ .name = "addq",	.ops = &mov_ops,  },
+	{ .name = "addsd",	.ops = &mov_ops,  },
 	{ .name = "addw",	.ops = &mov_ops,  },
 	{ .name = "and",	.ops = &mov_ops,  },
+	{ .name = "andb",	.ops = &mov_ops,  },
+	{ .name = "andl",	.ops = &mov_ops,  },
+	{ .name = "andpd",	.ops = &mov_ops,  },
+	{ .name = "andps",	.ops = &mov_ops,  },
+	{ .name = "andq",	.ops = &mov_ops,  },
+	{ .name = "andw",	.ops = &mov_ops,  },
+	{ .name = "bsr",	.ops = &mov_ops,  },
+	{ .name = "bt",		.ops = &mov_ops,  },
+	{ .name = "btr",	.ops = &mov_ops,  },
 	{ .name = "bts",	.ops = &mov_ops,  },
+	{ .name = "btsq",	.ops = &mov_ops,  },
 	{ .name = "call",	.ops = &call_ops, },
 	{ .name = "callq",	.ops = &call_ops, },
+	{ .name = "cmovbe",	.ops = &mov_ops,  },
+	{ .name = "cmove",	.ops = &mov_ops,  },
+	{ .name = "cmovae",	.ops = &mov_ops,  },
 	{ .name = "cmp",	.ops = &mov_ops,  },
 	{ .name = "cmpb",	.ops = &mov_ops,  },
 	{ .name = "cmpl",	.ops = &mov_ops,  },
 	{ .name = "cmpq",	.ops = &mov_ops,  },
 	{ .name = "cmpw",	.ops = &mov_ops,  },
 	{ .name = "cmpxch",	.ops = &mov_ops,  },
+	{ .name = "cmpxchg",	.ops = &mov_ops,  },
+	{ .name = "cs",		.ops = &mov_ops,  },
 	{ .name = "dec",	.ops = &dec_ops,  },
 	{ .name = "decl",	.ops = &dec_ops,  },
+	{ .name = "divsd",	.ops = &mov_ops,  },
+	{ .name = "divss",	.ops = &mov_ops,  },
+	{ .name = "gs",		.ops = &mov_ops,  },
 	{ .name = "imul",	.ops = &mov_ops,  },
 	{ .name = "inc",	.ops = &dec_ops,  },
 	{ .name = "incl",	.ops = &dec_ops,  },
@@ -57,25 +79,68 @@ static struct ins x86__instructions[] = {
 	{ .name = "lea",	.ops = &mov_ops,  },
 	{ .name = "lock",	.ops = &lock_ops, },
 	{ .name = "mov",	.ops = &mov_ops,  },
+	{ .name = "movapd",	.ops = &mov_ops,  },
+	{ .name = "movaps",	.ops = &mov_ops,  },
 	{ .name = "movb",	.ops = &mov_ops,  },
 	{ .name = "movdqa",	.ops = &mov_ops,  },
+	{ .name = "movdqu",	.ops = &mov_ops,  },
 	{ .name = "movl",	.ops = &mov_ops,  },
 	{ .name = "movq",	.ops = &mov_ops,  },
+	{ .name = "movsd",	.ops = &mov_ops,  },
 	{ .name = "movslq",	.ops = &mov_ops,  },
+	{ .name = "movss",	.ops = &mov_ops,  },
+	{ .name = "movupd",	.ops = &mov_ops,  },
+	{ .name = "movups",	.ops = &mov_ops,  },
+	{ .name = "movw",	.ops = &mov_ops,  },
 	{ .name = "movzbl",	.ops = &mov_ops,  },
 	{ .name = "movzwl",	.ops = &mov_ops,  },
+	{ .name = "mulsd",	.ops = &mov_ops,  },
+	{ .name = "mulss",	.ops = &mov_ops,  },
 	{ .name = "nop",	.ops = &nop_ops,  },
 	{ .name = "nopl",	.ops = &nop_ops,  },
 	{ .name = "nopw",	.ops = &nop_ops,  },
 	{ .name = "or",		.ops = &mov_ops,  },
+	{ .name = "orb",	.ops = &mov_ops,  },
 	{ .name = "orl",	.ops = &mov_ops,  },
+	{ .name = "orps",	.ops = &mov_ops,  },
+	{ .name = "orq",	.ops = &mov_ops,  },
+	{ .name = "pand",	.ops = &mov_ops,  },
+	{ .name = "paddq",	.ops = &mov_ops,  },
+	{ .name = "pcmpeqb",	.ops = &mov_ops,  },
+	{ .name = "por",	.ops = &mov_ops,  },
+	{ .name = "rclb",	.ops = &mov_ops,  },
+	{ .name = "rcll",	.ops = &mov_ops,  },
+	{ .name = "retq",	.ops = &ret_ops,  },
+	{ .name = "sbb",	.ops = &mov_ops,  },
+	{ .name = "sbbl",	.ops = &mov_ops,  },
+	{ .name = "sete",	.ops = &mov_ops,  },
+	{ .name = "sub",	.ops = &mov_ops,  },
+	{ .name = "subl",	.ops = &mov_ops,  },
+	{ .name = "subq",	.ops = &mov_ops,  },
+	{ .name = "subsd",	.ops = &mov_ops,  },
+	{ .name = "subw",	.ops = &mov_ops,  },
 	{ .name = "test",	.ops = &mov_ops,  },
 	{ .name = "testb",	.ops = &mov_ops,  },
 	{ .name = "testl",	.ops = &mov_ops,  },
+	{ .name = "ucomisd",	.ops = &mov_ops,  },
+	{ .name = "ucomiss",	.ops = &mov_ops,  },
+	{ .name = "vaddsd",	.ops = &mov_ops,  },
+	{ .name = "vandpd",	.ops = &mov_ops,  },
+	{ .name = "vmovdqa",	.ops = &mov_ops,  },
+	{ .name = "vmovq",	.ops = &mov_ops,  },
+	{ .name = "vmovsd",	.ops = &mov_ops,  },
+	{ .name = "vmulsd",	.ops = &mov_ops,  },
+	{ .name = "vorpd",	.ops = &mov_ops,  },
+	{ .name = "vsubsd",	.ops = &mov_ops,  },
+	{ .name = "vucomisd",	.ops = &mov_ops,  },
 	{ .name = "xadd",	.ops = &mov_ops,  },
 	{ .name = "xbeginl",	.ops = &jump_ops, },
 	{ .name = "xbeginq",	.ops = &jump_ops, },
-	{ .name = "retq",	.ops = &ret_ops,  },
+	{ .name = "xchg",	.ops = &mov_ops,  },
+	{ .name = "xor",	.ops = &mov_ops, },
+	{ .name = "xorb",	.ops = &mov_ops, },
+	{ .name = "xorpd",	.ops = &mov_ops, },
+	{ .name = "xorps",	.ops = &mov_ops, },
 };
 
 static bool x86__ins_is_fused(struct arch *arch, const char *ins1,

tools/perf/builtin-help.c

@@ -439,7 +439,7 @@ int cmd_help(int argc, const char **argv)
 #ifdef HAVE_LIBELF_SUPPORT
 		"probe",
 #endif
-#if defined(HAVE_LIBAUDIT_SUPPORT) || defined(HAVE_SYSCALL_TABLE)
+#if defined(HAVE_LIBAUDIT_SUPPORT) || defined(HAVE_SYSCALL_TABLE_SUPPORT)
 		"trace",
 #endif
 	NULL };

tools/perf/builtin-mem.c

@@ -83,7 +83,7 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem)
 	};
 
 	argc = parse_options(argc, argv, options, record_mem_usage,
-			     PARSE_OPT_STOP_AT_NON_OPTION);
+			     PARSE_OPT_KEEP_UNKNOWN);
 
 	rec_argc = argc + 9; /* max number of arguments */
 	rec_argv = calloc(rec_argc + 1, sizeof(char *));
@@ -436,7 +436,7 @@ int cmd_mem(int argc, const char **argv)
 	}
 
 	argc = parse_options_subcommand(argc, argv, mem_options, mem_subcommands,
-					mem_usage, PARSE_OPT_STOP_AT_NON_OPTION);
+					mem_usage, PARSE_OPT_KEEP_UNKNOWN);
 
 	if (!argc || !(strncmp(argv[0], "rec", 3) || mem.operation))
 		usage_with_options(mem_usage, mem_options);

tools/perf/builtin-script.c

@@ -657,8 +657,11 @@ static int perf_sample__fprintf_start(struct perf_sample *sample,
 			break;
 		case PERF_RECORD_SWITCH:
 		case PERF_RECORD_SWITCH_CPU_WIDE:
-			if (has(SWITCH_OUT))
+			if (has(SWITCH_OUT)) {
 				ret += fprintf(fp, "S");
+				if (sample->misc & PERF_RECORD_MISC_SWITCH_OUT_PREEMPT)
+					ret += fprintf(fp, "p");
+			}
 		default:
 			break;
 		}
@@ -2801,11 +2804,11 @@ int find_scripts(char **scripts_array, char **scripts_path_array)
 	for_each_lang(scripts_path, scripts_dir, lang_dirent) {
 		scnprintf(lang_path, MAXPATHLEN, "%s/%s", scripts_path,
 			  lang_dirent->d_name);
-#ifdef NO_LIBPERL
+#ifndef HAVE_LIBPERL_SUPPORT
 		if (strstr(lang_path, "perl"))
 			continue;
 #endif
-#ifdef NO_LIBPYTHON
+#ifndef HAVE_LIBPYTHON_SUPPORT
 		if (strstr(lang_path, "python"))
 			continue;
 #endif

tools/perf/builtin-stat.c

@@ -1943,7 +1943,8 @@ static const struct option stat_options[] = {
 	OPT_STRING(0, "post", &post_cmd, "command",
 			"command to run after to the measured command"),
 	OPT_UINTEGER('I', "interval-print", &stat_config.interval,
-		    "print counts at regular interval in ms (>= 10)"),
+		    "print counts at regular interval in ms "
+		    "(overhead is possible for values <= 100ms)"),
 	OPT_INTEGER(0, "interval-count", &stat_config.times,
 		    "print counts for fixed number of times"),
 	OPT_UINTEGER(0, "timeout", &stat_config.timeout,
@@ -2923,17 +2924,6 @@ int cmd_stat(int argc, const char **argv)
 		}
 	}
 
-	if (interval && interval < 100) {
-		if (interval < 10) {
-			pr_err("print interval must be >= 10ms\n");
-			parse_options_usage(stat_usage, stat_options, "I", 1);
-			goto out;
-		} else
-			pr_warning("print interval < 100ms. "
-				   "The overhead percentage could be high in some cases. "
-				   "Please proceed with caution.\n");
-	}
-
 	if (stat_config.times && interval)
 		interval_count = true;
 	else if (stat_config.times && !interval) {

tools/perf/builtin-version.c

@@ -60,7 +60,10 @@ static void library_status(void)
 	STATUS(HAVE_DWARF_GETLOCATIONS_SUPPORT, dwarf_getlocations);
 	STATUS(HAVE_GLIBC_SUPPORT, glibc);
 	STATUS(HAVE_GTK2_SUPPORT, gtk2);
+#ifndef HAVE_SYSCALL_TABLE_SUPPORT
 	STATUS(HAVE_LIBAUDIT_SUPPORT, libaudit);
+#endif
+	STATUS(HAVE_SYSCALL_TABLE_SUPPORT, syscall_table);
 	STATUS(HAVE_LIBBFD_SUPPORT, libbfd);
 	STATUS(HAVE_LIBELF_SUPPORT, libelf);
 	STATUS(HAVE_LIBNUMA_SUPPORT, libnuma);

tools/perf/perf.c

@@ -73,7 +73,7 @@ static struct cmd_struct commands[] = {
 	{ "lock",	cmd_lock,	0 },
 	{ "kvm",	cmd_kvm,	0 },
 	{ "test",	cmd_test,	0 },
-#if defined(HAVE_LIBAUDIT_SUPPORT) || defined(HAVE_SYSCALL_TABLE)
+#if defined(HAVE_LIBAUDIT_SUPPORT) || defined(HAVE_SYSCALL_TABLE_SUPPORT)
 	{ "trace",	cmd_trace,	0 },
 #endif
 	{ "inject",	cmd_inject,	0 },
@@ -491,7 +491,7 @@ int main(int argc, const char **argv)
 		argv[0] = cmd;
 	}
 	if (strstarts(cmd, "trace")) {
-#if defined(HAVE_LIBAUDIT_SUPPORT) || defined(HAVE_SYSCALL_TABLE)
+#if defined(HAVE_LIBAUDIT_SUPPORT) || defined(HAVE_SYSCALL_TABLE_SUPPORT)
 		setup_path();
 		argv[0] = "trace";
 		return cmd_trace(argc, argv);

tools/perf/tests/bpf-script-example.c

@@ -31,7 +31,7 @@ struct bpf_map_def SEC("maps") flip_table = {
 	.max_entries = 1,
 };
 
-SEC("func=SyS_epoll_pwait")
+SEC("func=do_epoll_wait")
 int bpf_func__SyS_epoll_pwait(void *ctx)
 {
 	int ind =0;

tools/perf/tests/bpf-script-test-kbuild.c

@@ -9,7 +9,6 @@
 #define SEC(NAME) __attribute__((section(NAME), used))
 
 #include <uapi/linux/fs.h>
-#include <uapi/asm/ptrace.h>
 
 SEC("func=vfs_llseek")
 int bpf_func__vfs_llseek(void *ctx)

tools/perf/tests/builtin-test.c

@@ -118,6 +118,7 @@ static struct test generic_tests[] = {
 	{
 		.desc = "Breakpoint accounting",
 		.func = test__bp_accounting,
+		.is_supported = test__bp_signal_is_supported,
 	},
 	{
 		.desc = "Number of exit events of a simple workload",

tools/perf/tests/mmap-basic.c

@@ -75,7 +75,7 @@ int test__basic_mmap(struct test *test __maybe_unused, int subtest __maybe_unuse
 		snprintf(name, sizeof(name), "sys_enter_%s", syscall_names[i]);
 		evsels[i] = perf_evsel__newtp("syscalls", name);
 		if (IS_ERR(evsels[i])) {
-			pr_debug("perf_evsel__new\n");
+			pr_debug("perf_evsel__new(%s)\n", name);
 			goto out_delete_evlist;
 		}
 

tools/perf/trace/beauty/mmap.c

@@ -54,6 +54,9 @@ static size_t syscall_arg__scnprintf_mmap_flags(char *bf, size_t size,
 	P_MMAP_FLAG(EXECUTABLE);
 	P_MMAP_FLAG(FILE);
 	P_MMAP_FLAG(FIXED);
+#ifdef MAP_FIXED_NOREPLACE
+	P_MMAP_FLAG(FIXED_NOREPLACE);
+#endif
 	P_MMAP_FLAG(GROWSDOWN);
 	P_MMAP_FLAG(HUGETLB);
 	P_MMAP_FLAG(LOCKED);

tools/perf/ui/browsers/annotate.c

@@ -692,6 +692,7 @@ static int annotate_browser__run(struct annotate_browser *browser,
 		"J             Toggle showing number of jump sources on targets\n"
 		"n             Search next string\n"
 		"o             Toggle disassembler output/simplified view\n"
+		"O             Bump offset level (jump targets -> +call -> all -> cycle thru)\n"
 		"s             Toggle source code view\n"
 		"t             Circulate percent, total period, samples view\n"
 		"/             Search string\n"
@@ -719,6 +720,10 @@ static int annotate_browser__run(struct annotate_browser *browser,
 			notes->options->use_offset = !notes->options->use_offset;
 			annotation__update_column_widths(notes);
 			continue;
+		case 'O':
+			if (++notes->options->offset_level > ANNOTATION__MAX_OFFSET_LEVEL)
+				notes->options->offset_level = ANNOTATION__MIN_OFFSET_LEVEL;
+			continue;
 		case 'j':
 			notes->options->jump_arrows = !notes->options->jump_arrows;
 			continue;

tools/perf/ui/browsers/hists.c

@@ -2714,7 +2714,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 	"h/?/F1        Show this window\n"				\
 	"UP/DOWN/PGUP\n"						\
 	"PGDN/SPACE    Navigate\n"					\
-	"q/ESC/CTRL+C  Exit browser\n\n"				\
+	"q/ESC/CTRL+C  Exit browser or go back to previous screen\n\n"	\
 	"For multiple event sessions:\n\n"				\
 	"TAB/UNTAB     Switch events\n\n"				\
 	"For symbolic views (--sort has sym):\n\n"			\

tools/perf/util/annotate.c

@@ -46,6 +46,7 @@
 struct annotation_options annotation__default_options = {
 	.use_offset     = true,
 	.jump_arrows    = true,
+	.offset_level	= ANNOTATION__OFFSET_JUMP_TARGETS,
 };
 
 const char 	*disassembler_style;
@@ -2512,7 +2513,8 @@ static void __annotation_line__write(struct annotation_line *al, struct annotati
 		if (!notes->options->use_offset) {
 			printed = scnprintf(bf, sizeof(bf), "%" PRIx64 ": ", addr);
 		} else {
-			if (al->jump_sources) {
+			if (al->jump_sources &&
+			    notes->options->offset_level >= ANNOTATION__OFFSET_JUMP_TARGETS) {
 				if (notes->options->show_nr_jumps) {
 					int prev;
 					printed = scnprintf(bf, sizeof(bf), "%*d ",
@@ -2523,9 +2525,14 @@ static void __annotation_line__write(struct annotation_line *al, struct annotati
 					obj__printf(obj, bf);
 					obj__set_color(obj, prev);
 				}
-
+print_addr:
 				printed = scnprintf(bf, sizeof(bf), "%*" PRIx64 ": ",
 						    notes->widths.target, addr);
+			} else if (ins__is_call(&disasm_line(al)->ins) &&
+				   notes->options->offset_level >= ANNOTATION__OFFSET_CALL) {
+				goto print_addr;
+			} else if (notes->options->offset_level == ANNOTATION__MAX_OFFSET_LEVEL) {
+				goto print_addr;
 			} else {
 				printed = scnprintf(bf, sizeof(bf), "%-*s  ",
 						    notes->widths.addr, " ");
@@ -2642,10 +2649,11 @@ int __annotation__scnprintf_samples_period(struct annotation *notes,
  */
 static struct annotation_config {
 	const char *name;
-	bool *value;
+	void *value;
 } annotation__configs[] = {
 	ANNOTATION__CFG(hide_src_code),
 	ANNOTATION__CFG(jump_arrows),
+	ANNOTATION__CFG(offset_level),
 	ANNOTATION__CFG(show_linenr),
 	ANNOTATION__CFG(show_nr_jumps),
 	ANNOTATION__CFG(show_nr_samples),
@@ -2677,8 +2685,16 @@ static int annotation__config(const char *var, const char *value,
 
 	if (cfg == NULL)
 		pr_debug("%s variable unknown, ignoring...", var);
-	else
-		*cfg->value = perf_config_bool(name, value);
+	else if (strcmp(var, "annotate.offset_level") == 0) {
+		perf_config_int(cfg->value, name, value);
+
+		if (*(int *)cfg->value > ANNOTATION__MAX_OFFSET_LEVEL)
+			*(int *)cfg->value = ANNOTATION__MAX_OFFSET_LEVEL;
+		else if (*(int *)cfg->value < ANNOTATION__MIN_OFFSET_LEVEL)
+			*(int *)cfg->value = ANNOTATION__MIN_OFFSET_LEVEL;
+	} else {
+		*(bool *)cfg->value = perf_config_bool(name, value);
+	}
 	return 0;
 }
 

tools/perf/util/annotate.h

@@ -70,8 +70,17 @@ struct annotation_options {
 	     show_nr_jumps,
 	     show_nr_samples,
 	     show_total_period;
+	u8   offset_level;
 };
 
+enum {
+	ANNOTATION__OFFSET_JUMP_TARGETS = 1,
+	ANNOTATION__OFFSET_CALL,
+	ANNOTATION__MAX_OFFSET_LEVEL,
+};
+
+#define ANNOTATION__MIN_OFFSET_LEVEL ANNOTATION__OFFSET_JUMP_TARGETS
+
 extern struct annotation_options annotation__default_options;
 
 struct annotation;

tools/perf/util/cs-etm-decoder/cs-etm-decoder.c

+// SPDX-License-Identifier: GPL-2.0
 /*
- * SPDX-License-Identifier: GPL-2.0
- *
  * Copyright(C) 2015-2018 Linaro Limited.
  *
  * Author: Tor Jeremiassen <tor@ti.com>

tools/perf/util/cs-etm.c

+// SPDX-License-Identifier: GPL-2.0
 /*
- * SPDX-License-Identifier: GPL-2.0
- *
  * Copyright(C) 2015-2018 Linaro Limited.
  *
  * Author: Tor Jeremiassen <tor@ti.com>

tools/perf/util/cs-etm.h

+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Copyright(C) 2015 Linaro Limited. All rights reserved.
  * Author: Mathieu Poirier <mathieu.poirier@linaro.org>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published by
- * the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef INCLUDE__UTIL_PERF_CS_ETM_H__

tools/perf/util/event.c

@@ -1421,7 +1421,9 @@ size_t perf_event__fprintf_itrace_start(union perf_event *event, FILE *fp)
 size_t perf_event__fprintf_switch(union perf_event *event, FILE *fp)
 {
 	bool out = event->header.misc & PERF_RECORD_MISC_SWITCH_OUT;
-	const char *in_out = out ? "OUT" : "IN ";
+	const char *in_out = !out ? "IN         " :
+		!(event->header.misc & PERF_RECORD_MISC_SWITCH_OUT_PREEMPT) ?
+				    "OUT        " : "OUT preempt";
 
 	if (event->header.type == PERF_RECORD_SWITCH)
 		return fprintf(fp, " %s\n", in_out);

tools/perf/util/evsel.c

@@ -2870,8 +2870,7 @@ int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target,
 #if defined(__i386__) || defined(__x86_64__)
 		if (evsel->attr.type == PERF_TYPE_HARDWARE)
 			return scnprintf(msg, size, "%s",
-	"No hardware sampling interrupt available.\n"
-	"No APIC? If so then you can boot the kernel with the \"lapic\" boot parameter to force-enable it.");
+	"No hardware sampling interrupt available.\n");
 #endif
 		break;
 	case EBUSY:
@@ -2894,8 +2893,7 @@ int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target,
 
 	return scnprintf(msg, size,
 	"The sys_perf_event_open() syscall returned with %d (%s) for event (%s).\n"
-	"/bin/dmesg may provide additional information.\n"
-	"No CONFIG_PERF_EVENTS=y kernel support configured?",
+	"/bin/dmesg | grep -i perf may provide additional information.\n",
 			 err, str_error_r(err, sbuf, sizeof(sbuf)),
 			 perf_evsel__name(evsel));
 }

tools/perf/util/generate-cmdlist.sh

@@ -38,7 +38,7 @@ do
 done
 echo "#endif /* HAVE_LIBELF_SUPPORT */"
 
-echo "#if defined(HAVE_LIBAUDIT_SUPPORT) || defined(HAVE_SYSCALL_TABLE)"
+echo "#if defined(HAVE_LIBAUDIT_SUPPORT) || defined(HAVE_SYSCALL_TABLE_SUPPORT)"
 sed -n -e 's/^perf-\([^ 	]*\)[ 	].* audit*/\1/p' command-list.txt |
 sort |
 while read cmd

tools/perf/util/header.c

@@ -1320,7 +1320,8 @@ static int build_mem_topology(struct memory_node *nodes, u64 size, u64 *cntp)
 
 	dir = opendir(path);
 	if (!dir) {
-		pr_warning("failed: can't open node sysfs data\n");
+		pr_debug2("%s: could't read %s, does this arch have topology information?\n",
+			  __func__, path);
 		return -1;
 	}
 

tools/perf/util/pmu.c

@@ -562,6 +562,12 @@ static int is_pmu_core(const char *name)
 	if (stat(path, &st) == 0)
 		return 1;
 
+	/* Look for cpu sysfs (specific to s390) */
+	scnprintf(path, PATH_MAX, "%s/bus/event_source/devices/%s",
+		  sysfs, name);
+	if (stat(path, &st) == 0 && !strncmp(name, "cpum_", 5))
+		return 1;
+
 	return 0;
 }
 

tools/perf/util/symbol.c

@@ -2091,16 +2091,14 @@ static bool symbol__read_kptr_restrict(void)
 
 int symbol__annotation_init(void)
 {
+	if (symbol_conf.init_annotation)
+		return 0;
+
 	if (symbol_conf.initialized) {
 		pr_err("Annotation needs to be init before symbol__init()\n");
 		return -1;
 	}
 
-	if (symbol_conf.init_annotation) {
-		pr_warning("Annotation being initialized multiple times\n");
-		return 0;
-	}
-
 	symbol_conf.priv_size += sizeof(struct annotation);
 	symbol_conf.init_annotation = true;
 	return 0;

tools/perf/util/syscalltbl.c

@@ -17,7 +17,7 @@
 #include <stdlib.h>
 #include <linux/compiler.h>
 
-#ifdef HAVE_SYSCALL_TABLE
+#ifdef HAVE_SYSCALL_TABLE_SUPPORT
 #include <string.h>
 #include "string2.h"
 #include "util.h"
@@ -139,7 +139,7 @@ int syscalltbl__strglobmatch_first(struct syscalltbl *tbl, const char *syscall_g
 	return syscalltbl__strglobmatch_next(tbl, syscall_glob, idx);
 }
 
-#else /* HAVE_SYSCALL_TABLE */
+#else /* HAVE_SYSCALL_TABLE_SUPPORT */
 
 #include <libaudit.h>
 
@@ -176,4 +176,4 @@ int syscalltbl__strglobmatch_first(struct syscalltbl *tbl, const char *syscall_g
 {
 	return syscalltbl__strglobmatch_next(tbl, syscall_glob, idx);
 }
-#endif /* HAVE_SYSCALL_TABLE */
+#endif /* HAVE_SYSCALL_TABLE_SUPPORT */

tools/perf/util/trace-event-scripting.c

@@ -98,7 +98,7 @@ static void register_python_scripting(struct scripting_ops *scripting_ops)
 	}
 }
 
-#ifdef NO_LIBPYTHON
+#ifndef HAVE_LIBPYTHON_SUPPORT
 void setup_python_scripting(void)
 {
 	register_python_scripting(&python_scripting_unsupported_ops);
@@ -161,7 +161,7 @@ static void register_perl_scripting(struct scripting_ops *scripting_ops)
 	}
 }
 
-#ifdef NO_LIBPERL
+#ifndef HAVE_LIBPERL_SUPPORT
 void setup_perl_scripting(void)
 {
 	register_perl_scripting(&perl_scripting_unsupported_ops);