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

Pull perf tooling fixes from Thomas Gleixner:

 - Synchronization of tools and kernel headers

 - A series of fixes for perf report addressing various failures:
    * Handle invalid maps proper
    * Plug a memory leak
    * Handle frames and callchain order correctly

 - Fixes for handling inlines and children mode

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  tools/include: Sync kernel ABI headers with tooling headers
  perf tools: Put caller above callee in --children mode
  perf report: Do not drop last inlined frame
  perf report: Always honor callchain order for inlined nodes
  perf script: Add --inline option for debugging
  perf report: Fix off-by-one for non-activation frames
  perf report: Fix memory leak in addr2line when called by addr2inlines
  perf report: Don't crash on invalid maps in `-g srcline` mode

18 files changed, 176 insertions, 47 deletions

diff --git a/tools/arch/arm/include/uapi/asm/kvm.h b/tools/arch/arm/include/uapi/asm/kvm.h
index 6ebd3e6a1fd1..5e3c673fa3f4 100644
--- a/tools/arch/arm/include/uapi/asm/kvm.h
+++ b/tools/arch/arm/include/uapi/asm/kvm.h
@@ -27,6 +27,8 @@
 #define __KVM_HAVE_IRQ_LINE
 #define __KVM_HAVE_READONLY_MEM
 
+#define KVM_COALESCED_MMIO_PAGE_OFFSET 1
+
 #define KVM_REG_SIZE(id)						\
 	(1U << (((id) & KVM_REG_SIZE_MASK) >> KVM_REG_SIZE_SHIFT))
 
@@ -114,6 +116,8 @@ struct kvm_debug_exit_arch {
 };
 
 struct kvm_sync_regs {
+	/* Used with KVM_CAP_ARM_USER_IRQ */
+	__u64 device_irq_level;
 };
 
 struct kvm_arch_memory_slot {
@@ -192,13 +196,17 @@ struct kvm_arch_memory_slot {
 #define KVM_DEV_ARM_VGIC_GRP_REDIST_REGS 5
 #define KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS 6
 #define KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO  7
+#define KVM_DEV_ARM_VGIC_GRP_ITS_REGS	8
 #define KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_SHIFT	10
 #define KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_MASK \
 			(0x3fffffULL << KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_SHIFT)
 #define KVM_DEV_ARM_VGIC_LINE_LEVEL_INTID_MASK 0x3ff
 #define VGIC_LEVEL_INFO_LINE_LEVEL	0
 
-#define   KVM_DEV_ARM_VGIC_CTRL_INIT    0
+#define   KVM_DEV_ARM_VGIC_CTRL_INIT		0
+#define   KVM_DEV_ARM_ITS_SAVE_TABLES		1
+#define   KVM_DEV_ARM_ITS_RESTORE_TABLES	2
+#define   KVM_DEV_ARM_VGIC_SAVE_PENDING_TABLES	3
 
 /* KVM_IRQ_LINE irq field index values */
 #define KVM_ARM_IRQ_TYPE_SHIFT		24
diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h
index c2860358ae3e..70eea2ecc663 100644
--- a/tools/arch/arm64/include/uapi/asm/kvm.h
+++ b/tools/arch/arm64/include/uapi/asm/kvm.h
@@ -39,6 +39,8 @@
 #define __KVM_HAVE_IRQ_LINE
 #define __KVM_HAVE_READONLY_MEM
 
+#define KVM_COALESCED_MMIO_PAGE_OFFSET 1
+
 #define KVM_REG_SIZE(id)						\
 	(1U << (((id) & KVM_REG_SIZE_MASK) >> KVM_REG_SIZE_SHIFT))
 
@@ -143,6 +145,8 @@ struct kvm_debug_exit_arch {
 #define KVM_GUESTDBG_USE_HW		(1 << 17)
 
 struct kvm_sync_regs {
+	/* Used with KVM_CAP_ARM_USER_IRQ */
+	__u64 device_irq_level;
 };
 
 struct kvm_arch_memory_slot {
@@ -212,13 +216,17 @@ struct kvm_arch_memory_slot {
 #define KVM_DEV_ARM_VGIC_GRP_REDIST_REGS 5
 #define KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS 6
 #define KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO  7
+#define KVM_DEV_ARM_VGIC_GRP_ITS_REGS 8
 #define KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_SHIFT	10
 #define KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_MASK \
 			(0x3fffffULL << KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_SHIFT)
 #define KVM_DEV_ARM_VGIC_LINE_LEVEL_INTID_MASK	0x3ff
 #define VGIC_LEVEL_INFO_LINE_LEVEL	0
 
-#define   KVM_DEV_ARM_VGIC_CTRL_INIT	0
+#define   KVM_DEV_ARM_VGIC_CTRL_INIT		0
+#define   KVM_DEV_ARM_ITS_SAVE_TABLES           1
+#define   KVM_DEV_ARM_ITS_RESTORE_TABLES        2
+#define   KVM_DEV_ARM_VGIC_SAVE_PENDING_TABLES	3
 
 /* Device Control API on vcpu fd */
 #define KVM_ARM_VCPU_PMU_V3_CTRL	0
diff --git a/tools/arch/powerpc/include/uapi/asm/kvm.h b/tools/arch/powerpc/include/uapi/asm/kvm.h
index 4edbe4bb0e8b..07fbeb927834 100644
--- a/tools/arch/powerpc/include/uapi/asm/kvm.h
+++ b/tools/arch/powerpc/include/uapi/asm/kvm.h
@@ -29,6 +29,9 @@
 #define __KVM_HAVE_IRQ_LINE
 #define __KVM_HAVE_GUEST_DEBUG
 
+/* Not always available, but if it is, this is the correct offset.  */
+#define KVM_COALESCED_MMIO_PAGE_OFFSET 1
+
 struct kvm_regs {
 	__u64 pc;
 	__u64 cr;
diff --git a/tools/arch/s390/include/uapi/asm/kvm.h b/tools/arch/s390/include/uapi/asm/kvm.h
index 7f4fd65e9208..3dd2a1d308dd 100644
--- a/tools/arch/s390/include/uapi/asm/kvm.h
+++ b/tools/arch/s390/include/uapi/asm/kvm.h
@@ -26,6 +26,8 @@
 #define KVM_DEV_FLIC_ADAPTER_REGISTER	6
 #define KVM_DEV_FLIC_ADAPTER_MODIFY	7
 #define KVM_DEV_FLIC_CLEAR_IO_IRQ	8
+#define KVM_DEV_FLIC_AISM		9
+#define KVM_DEV_FLIC_AIRQ_INJECT	10
 /*
  * We can have up to 4*64k pending subchannels + 8 adapter interrupts,
  * as well as up  to ASYNC_PF_PER_VCPU*KVM_MAX_VCPUS pfault done interrupts.
@@ -41,7 +43,14 @@ struct kvm_s390_io_adapter {
 	__u8 isc;
 	__u8 maskable;
 	__u8 swap;
-	__u8 pad;
+	__u8 flags;
+};
+
+#define KVM_S390_ADAPTER_SUPPRESSIBLE 0x01
+
+struct kvm_s390_ais_req {
+	__u8 isc;
+	__u16 mode;
 };
 
 #define KVM_S390_IO_ADAPTER_MASK 1
@@ -110,6 +119,7 @@ struct kvm_s390_vm_cpu_machine {
 #define KVM_S390_VM_CPU_FEAT_CMMA	10
 #define KVM_S390_VM_CPU_FEAT_PFMFI	11
 #define KVM_S390_VM_CPU_FEAT_SIGPIF	12
+#define KVM_S390_VM_CPU_FEAT_KSS	13
 struct kvm_s390_vm_cpu_feat {
 	__u64 feat[16];
 };
@@ -198,6 +208,10 @@ struct kvm_guest_debug_arch {
 #define KVM_SYNC_VRS    (1UL << 6)
 #define KVM_SYNC_RICCB  (1UL << 7)
 #define KVM_SYNC_FPRS   (1UL << 8)
+#define KVM_SYNC_GSCB   (1UL << 9)
+/* length and alignment of the sdnx as a power of two */
+#define SDNXC 8
+#define SDNXL (1UL << SDNXC)
 /* definition of registers in kvm_run */
 struct kvm_sync_regs {
 	__u64 prefix;	/* prefix register */
@@ -218,8 +232,16 @@ struct kvm_sync_regs {
 	};
 	__u8  reserved[512];	/* for future vector expansion */
 	__u32 fpc;		/* valid on KVM_SYNC_VRS or KVM_SYNC_FPRS */
-	__u8 padding[52];	/* riccb needs to be 64byte aligned */
+	__u8 padding1[52];	/* riccb needs to be 64byte aligned */
 	__u8 riccb[64];		/* runtime instrumentation controls block */
+	__u8 padding2[192];	/* sdnx needs to be 256byte aligned */
+	union {
+		__u8 sdnx[SDNXL];  /* state description annex */
+		struct {
+			__u64 reserved1[2];
+			__u64 gscb[4];
+		};
+	};
 };
 
 #define KVM_REG_S390_TODPR	(KVM_REG_S390 | KVM_REG_SIZE_U32 | 0x1)
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index 0fe00446f9ca..2701e5f8145b 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -202,6 +202,8 @@
 #define X86_FEATURE_AVX512_4VNNIW (7*32+16) /* AVX-512 Neural Network Instructions */
 #define X86_FEATURE_AVX512_4FMAPS (7*32+17) /* AVX-512 Multiply Accumulation Single precision */
 
+#define X86_FEATURE_MBA         ( 7*32+18) /* Memory Bandwidth Allocation */
+
 /* Virtualization flags: Linux defined, word 8 */
 #define X86_FEATURE_TPR_SHADOW  ( 8*32+ 0) /* Intel TPR Shadow */
 #define X86_FEATURE_VNMI        ( 8*32+ 1) /* Intel Virtual NMI */
diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h
index 85599ad4d024..5dff775af7cd 100644
--- a/tools/arch/x86/include/asm/disabled-features.h
+++ b/tools/arch/x86/include/asm/disabled-features.h
@@ -36,6 +36,12 @@
 # define DISABLE_OSPKE		(1<<(X86_FEATURE_OSPKE & 31))
 #endif /* CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS */
 
+#ifdef CONFIG_X86_5LEVEL
+# define DISABLE_LA57	0
+#else
+# define DISABLE_LA57	(1<<(X86_FEATURE_LA57 & 31))
+#endif
+
 /*
  * Make sure to add features to the correct mask
  */
@@ -55,7 +61,7 @@
 #define DISABLED_MASK13	0
 #define DISABLED_MASK14	0
 #define DISABLED_MASK15	0
-#define DISABLED_MASK16	(DISABLE_PKU|DISABLE_OSPKE)
+#define DISABLED_MASK16	(DISABLE_PKU|DISABLE_OSPKE|DISABLE_LA57)
 #define DISABLED_MASK17	0
 #define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 18)
 
diff --git a/tools/arch/x86/include/asm/required-features.h b/tools/arch/x86/include/asm/required-features.h
index fac9a5c0abe9..d91ba04dd007 100644
--- a/tools/arch/x86/include/asm/required-features.h
+++ b/tools/arch/x86/include/asm/required-features.h
@@ -53,6 +53,12 @@
 # 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 */
@@ -98,7 +104,7 @@
 #define REQUIRED_MASK13	0
 #define REQUIRED_MASK14	0
 #define REQUIRED_MASK15	0
-#define REQUIRED_MASK16	0
+#define REQUIRED_MASK16	(NEED_LA57)
 #define REQUIRED_MASK17	0
 #define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 18)
 
diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h
index 739c0c594022..c2824d02ba37 100644
--- a/tools/arch/x86/include/uapi/asm/kvm.h
+++ b/tools/arch/x86/include/uapi/asm/kvm.h
@@ -9,6 +9,9 @@
 #include <linux/types.h>
 #include <linux/ioctl.h>
 
+#define KVM_PIO_PAGE_OFFSET 1
+#define KVM_COALESCED_MMIO_PAGE_OFFSET 2
+
 #define DE_VECTOR 0
 #define DB_VECTOR 1
 #define BP_VECTOR 3
diff --git a/tools/arch/x86/include/uapi/asm/vmx.h b/tools/arch/x86/include/uapi/asm/vmx.h
index 14458658e988..690a2dcf4078 100644
--- a/tools/arch/x86/include/uapi/asm/vmx.h
+++ b/tools/arch/x86/include/uapi/asm/vmx.h
@@ -76,7 +76,11 @@
 #define EXIT_REASON_WBINVD              54
 #define EXIT_REASON_XSETBV              55
 #define EXIT_REASON_APIC_WRITE          56
+#define EXIT_REASON_RDRAND              57
 #define EXIT_REASON_INVPCID             58
+#define EXIT_REASON_VMFUNC              59
+#define EXIT_REASON_ENCLS               60
+#define EXIT_REASON_RDSEED              61
 #define EXIT_REASON_PML_FULL            62
 #define EXIT_REASON_XSAVES              63
 #define EXIT_REASON_XRSTORS             64
@@ -90,6 +94,7 @@
 	{ EXIT_REASON_TASK_SWITCH,           "TASK_SWITCH" }, \
 	{ EXIT_REASON_CPUID,                 "CPUID" }, \
 	{ EXIT_REASON_HLT,                   "HLT" }, \
+	{ EXIT_REASON_INVD,                  "INVD" }, \
 	{ EXIT_REASON_INVLPG,                "INVLPG" }, \
 	{ EXIT_REASON_RDPMC,                 "RDPMC" }, \
 	{ EXIT_REASON_RDTSC,                 "RDTSC" }, \
@@ -108,6 +113,8 @@
 	{ EXIT_REASON_IO_INSTRUCTION,        "IO_INSTRUCTION" }, \
 	{ EXIT_REASON_MSR_READ,              "MSR_READ" }, \
 	{ EXIT_REASON_MSR_WRITE,             "MSR_WRITE" }, \
+	{ EXIT_REASON_INVALID_STATE,         "INVALID_STATE" }, \
+	{ EXIT_REASON_MSR_LOAD_FAIL,         "MSR_LOAD_FAIL" }, \
 	{ EXIT_REASON_MWAIT_INSTRUCTION,     "MWAIT_INSTRUCTION" }, \
 	{ EXIT_REASON_MONITOR_TRAP_FLAG,     "MONITOR_TRAP_FLAG" }, \
 	{ EXIT_REASON_MONITOR_INSTRUCTION,   "MONITOR_INSTRUCTION" }, \
@@ -115,20 +122,24 @@
 	{ EXIT_REASON_MCE_DURING_VMENTRY,    "MCE_DURING_VMENTRY" }, \
 	{ EXIT_REASON_TPR_BELOW_THRESHOLD,   "TPR_BELOW_THRESHOLD" }, \
 	{ EXIT_REASON_APIC_ACCESS,           "APIC_ACCESS" }, \
-	{ EXIT_REASON_GDTR_IDTR,	     "GDTR_IDTR" }, \
-	{ EXIT_REASON_LDTR_TR,		     "LDTR_TR" }, \
+	{ EXIT_REASON_EOI_INDUCED,           "EOI_INDUCED" }, \
+	{ EXIT_REASON_GDTR_IDTR,             "GDTR_IDTR" }, \
+	{ EXIT_REASON_LDTR_TR,               "LDTR_TR" }, \
 	{ EXIT_REASON_EPT_VIOLATION,         "EPT_VIOLATION" }, \
 	{ EXIT_REASON_EPT_MISCONFIG,         "EPT_MISCONFIG" }, \
 	{ EXIT_REASON_INVEPT,                "INVEPT" }, \
+	{ EXIT_REASON_RDTSCP,                "RDTSCP" }, \
 	{ EXIT_REASON_PREEMPTION_TIMER,      "PREEMPTION_TIMER" }, \
+	{ EXIT_REASON_INVVPID,               "INVVPID" }, \
 	{ EXIT_REASON_WBINVD,                "WBINVD" }, \
+	{ EXIT_REASON_XSETBV,                "XSETBV" }, \
 	{ EXIT_REASON_APIC_WRITE,            "APIC_WRITE" }, \
-	{ EXIT_REASON_EOI_INDUCED,           "EOI_INDUCED" }, \
-	{ EXIT_REASON_INVALID_STATE,         "INVALID_STATE" }, \
-	{ EXIT_REASON_MSR_LOAD_FAIL,         "MSR_LOAD_FAIL" }, \
-	{ EXIT_REASON_INVD,                  "INVD" }, \
-	{ EXIT_REASON_INVVPID,               "INVVPID" }, \
+	{ EXIT_REASON_RDRAND,                "RDRAND" }, \
 	{ EXIT_REASON_INVPCID,               "INVPCID" }, \
+	{ EXIT_REASON_VMFUNC,                "VMFUNC" }, \
+	{ EXIT_REASON_ENCLS,                 "ENCLS" }, \
+	{ EXIT_REASON_RDSEED,                "RDSEED" }, \
+	{ EXIT_REASON_PML_FULL,              "PML_FULL" }, \
 	{ EXIT_REASON_XSAVES,                "XSAVES" }, \
 	{ EXIT_REASON_XRSTORS,               "XRSTORS" }
 
diff --git a/tools/include/uapi/linux/stat.h b/tools/include/uapi/linux/stat.h
index d538897b8e08..17b10304c393 100644
--- a/tools/include/uapi/linux/stat.h
+++ b/tools/include/uapi/linux/stat.h
@@ -48,17 +48,13 @@
  * tv_sec holds the number of seconds before (negative) or after (positive)
  * 00:00:00 1st January 1970 UTC.
  *
- * tv_nsec holds a number of nanoseconds before (0..-999,999,999 if tv_sec is
- * negative) or after (0..999,999,999 if tv_sec is positive) the tv_sec time.
- *
- * Note that if both tv_sec and tv_nsec are non-zero, then the two values must
- * either be both positive or both negative.
+ * tv_nsec holds a number of nanoseconds (0..999,999,999) after the tv_sec time.
  *
  * __reserved is held in case we need a yet finer resolution.
  */
 struct statx_timestamp {
 	__s64	tv_sec;
-	__s32	tv_nsec;
+	__u32	tv_nsec;
 	__s32	__reserved;
 };
 
diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index cb0eda3925e6..3517e204a2b3 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -311,6 +311,10 @@ include::itrace.txt[]
 	Set the maximum number of program blocks to print with brstackasm for
 	each sample.
 
+--inline::
+	If a callgraph address belongs to an inlined function, the inline stack
+	will be printed. Each entry has function name and file/line.
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-script-perl[1],
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index d05aec491cff..4761b0d7fcb5 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -2494,6 +2494,8 @@ int cmd_script(int argc, const char **argv)
 			"Enable kernel symbol demangling"),
 	OPT_STRING(0, "time", &script.time_str, "str",
 		   "Time span of interest (start,stop)"),
+	OPT_BOOLEAN(0, "inline", &symbol_conf.inline_name,
+		    "Show inline function"),
 	OPT_END()
 	};
 	const char * const script_subcommands[] = { "record", "report", NULL };
diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
index 59addd52d9cd..ddb2c6fbdf91 100644
--- a/tools/perf/ui/hist.c
+++ b/tools/perf/ui/hist.c
@@ -210,6 +210,8 @@ static int __hpp__sort_acc(struct hist_entry *a, struct hist_entry *b,
 			return 0;
 
 		ret = b->callchain->max_depth - a->callchain->max_depth;
+		if (callchain_param.order == ORDER_CALLER)
+			ret = -ret;
 	}
 	return ret;
 }
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 81fc29ac798f..b4204b43ed58 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -621,14 +621,19 @@ enum match_result {
 static enum match_result match_chain_srcline(struct callchain_cursor_node *node,
 					     struct callchain_list *cnode)
 {
-	char *left = get_srcline(cnode->ms.map->dso,
+	char *left = NULL;
+	char *right = NULL;
+	enum match_result ret = MATCH_EQ;
+	int cmp;
+
+	if (cnode->ms.map)
+		left = get_srcline(cnode->ms.map->dso,
 				 map__rip_2objdump(cnode->ms.map, cnode->ip),
 				 cnode->ms.sym, true, false);
-	char *right = get_srcline(node->map->dso,
+	if (node->map)
+		right = get_srcline(node->map->dso,
 				  map__rip_2objdump(node->map, node->ip),
 				  node->sym, true, false);
-	enum match_result ret = MATCH_EQ;
-	int cmp;
 
 	if (left && right)
 		cmp = strcmp(left, right);
diff --git a/tools/perf/util/evsel_fprintf.c b/tools/perf/util/evsel_fprintf.c
index e415aee6a245..583f3a602506 100644
--- a/tools/perf/util/evsel_fprintf.c
+++ b/tools/perf/util/evsel_fprintf.c
@@ -7,6 +7,7 @@
 #include "map.h"
 #include "strlist.h"
 #include "symbol.h"
+#include "srcline.h"
 
 static int comma_fprintf(FILE *fp, bool *first, const char *fmt, ...)
 {
@@ -168,6 +169,38 @@ int sample__fprintf_callchain(struct perf_sample *sample, int left_alignment,
 			if (!print_oneline)
 				printed += fprintf(fp, "\n");
 
+			if (symbol_conf.inline_name && node->map) {
+				struct inline_node *inode;
+
+				addr = map__rip_2objdump(node->map, node->ip),
+				inode = dso__parse_addr_inlines(node->map->dso, addr);
+
+				if (inode) {
+					struct inline_list *ilist;
+
+					list_for_each_entry(ilist, &inode->val, list) {
+						if (print_arrow)
+							printed += fprintf(fp, " <-");
+
+						/* IP is same, just skip it */
+						if (print_ip)
+							printed += fprintf(fp, "%c%16s",
+									   s, "");
+						if (print_sym)
+							printed += fprintf(fp, " %s",
+									   ilist->funcname);
+						if (print_srcline)
+							printed += fprintf(fp, "\n  %s:%d",
+									   ilist->filename,
+									   ilist->line_nr);
+						if (!print_oneline)
+							printed += fprintf(fp, "\n");
+					}
+
+					inline_node__delete(inode);
+				}
+			}
+
 			if (symbol_conf.bt_stop_list &&
 			    node->sym &&
 			    strlist__has_entry(symbol_conf.bt_stop_list,
diff --git a/tools/perf/util/srcline.c b/tools/perf/util/srcline.c
index df051a52393c..ebc88a74e67b 100644
--- a/tools/perf/util/srcline.c
+++ b/tools/perf/util/srcline.c
@@ -56,7 +56,10 @@ static int inline_list__append(char *filename, char *funcname, int line_nr,
 		}
 	}
 
-	list_add_tail(&ilist->list, &node->val);
+	if (callchain_param.order == ORDER_CALLEE)
+		list_add_tail(&ilist->list, &node->val);
+	else
+		list_add(&ilist->list, &node->val);
 
 	return 0;
 }
@@ -200,12 +203,14 @@ static void addr2line_cleanup(struct a2l_data *a2l)
 
 #define MAX_INLINE_NEST 1024
 
-static void inline_list__reverse(struct inline_node *node)
+static int inline_list__append_dso_a2l(struct dso *dso,
+				       struct inline_node *node)
 {
-	struct inline_list *ilist, *n;
+	struct a2l_data *a2l = dso->a2l;
+	char *funcname = a2l->funcname ? strdup(a2l->funcname) : NULL;
+	char *filename = a2l->filename ? strdup(a2l->filename) : NULL;
 
-	list_for_each_entry_safe_reverse(ilist, n, &node->val, list)
-		list_move_tail(&ilist->list, &node->val);
+	return inline_list__append(filename, funcname, a2l->line, node, dso);
 }
 
 static int addr2line(const char *dso_name, u64 addr,
@@ -230,36 +235,36 @@ static int addr2line(const char *dso_name, u64 addr,
 
 	bfd_map_over_sections(a2l->abfd, find_address_in_section, a2l);
 
-	if (a2l->found && unwind_inlines) {
+	if (!a2l->found)
+		return 0;
+
+	if (unwind_inlines) {
 		int cnt = 0;
 
+		if (node && inline_list__append_dso_a2l(dso, node))
+			return 0;
+
 		while (bfd_find_inliner_info(a2l->abfd, &a2l->filename,
 					     &a2l->funcname, &a2l->line) &&
 		       cnt++ < MAX_INLINE_NEST) {
 
 			if (node != NULL) {
-				if (inline_list__append(strdup(a2l->filename),
-							strdup(a2l->funcname),
-							a2l->line, node,
-							dso) != 0)
+				if (inline_list__append_dso_a2l(dso, node))
 					return 0;
+				// found at least one inline frame
+				ret = 1;
 			}
 		}
+	}
 
-		if ((node != NULL) &&
-		    (callchain_param.order != ORDER_CALLEE)) {
-			inline_list__reverse(node);
-		}
+	if (file) {
+		*file = a2l->filename ? strdup(a2l->filename) : NULL;
+		ret = *file ? 1 : 0;
 	}
 
-	if (a2l->found && a2l->filename) {
-		*file = strdup(a2l->filename);
+	if (line)
 		*line = a2l->line;
 
-		if (*file)
-			ret = 1;
-	}
-
 	return ret;
 }
 
@@ -278,8 +283,6 @@ void dso__free_a2l(struct dso *dso)
 static struct inline_node *addr2inlines(const char *dso_name, u64 addr,
 	struct dso *dso)
 {
-	char *file = NULL;
-	unsigned int line = 0;
 	struct inline_node *node;
 
 	node = zalloc(sizeof(*node));
@@ -291,7 +294,7 @@ static struct inline_node *addr2inlines(const char *dso_name, u64 addr,
 	INIT_LIST_HEAD(&node->val);
 	node->addr = addr;
 
-	if (!addr2line(dso_name, addr, &file, &line, dso, TRUE, node))
+	if (!addr2line(dso_name, addr, NULL, NULL, dso, TRUE, node))
 		goto out_free_inline_node;
 
 	if (list_empty(&node->val))
diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c
index f90e11a555b2..943a06291587 100644
--- a/tools/perf/util/unwind-libdw.c
+++ b/tools/perf/util/unwind-libdw.c
@@ -168,12 +168,16 @@ frame_callback(Dwfl_Frame *state, void *arg)
 {
 	struct unwind_info *ui = arg;
 	Dwarf_Addr pc;
+	bool isactivation;
 
-	if (!dwfl_frame_pc(state, &pc, NULL)) {
+	if (!dwfl_frame_pc(state, &pc, &isactivation)) {
 		pr_err("%s", dwfl_errmsg(-1));
 		return DWARF_CB_ABORT;
 	}
 
+	if (!isactivation)
+		--pc;
+
 	return entry(pc, ui) || !(--ui->max_stack) ?
 	       DWARF_CB_ABORT : DWARF_CB_OK;
 }
diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c
index f8455bed6e65..672c2ada9357 100644
--- a/tools/perf/util/unwind-libunwind-local.c
+++ b/tools/perf/util/unwind-libunwind-local.c
@@ -692,6 +692,17 @@ static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb,
 
 		while (!ret && (unw_step(&c) > 0) && i < max_stack) {
 			unw_get_reg(&c, UNW_REG_IP, &ips[i]);
+
+			/*
+			 * Decrement the IP for any non-activation frames.
+			 * this is required to properly find the srcline
+			 * for caller frames.
+			 * See also the documentation for dwfl_frame_pc(),
+			 * which this code tries to replicate.
+			 */
+			if (unw_is_signal_frame(&c) <= 0)
+				--ips[i];
+
 			++i;
 		}