Merge tag 'v4.12-rc5' into for-4.13/block

We've already got a few conflicts and upcoming work depends on some of the
changes that have gone into mainline as regression fixes for this series.

Pull in 4.12-rc5 to resolve these conflicts and make it easier on down stream
trees to continue working on 4.13 changes.

Signed-off-by: Jens Axboe <axboe@kernel.dk>

42 files changed, 681 insertions, 208 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/linux/filter.h b/tools/include/linux/filter.h
index 390d7c9685fd..4ce25d43e8e3 100644
--- a/tools/include/linux/filter.h
+++ b/tools/include/linux/filter.h
@@ -208,6 +208,16 @@
 		.off   = OFF,					\
 		.imm   = IMM })
 
+/* Unconditional jumps, goto pc + off16 */
+
+#define BPF_JMP_A(OFF)						\
+	((struct bpf_insn) {					\
+		.code  = BPF_JMP | BPF_JA,			\
+		.dst_reg = 0,					\
+		.src_reg = 0,					\
+		.off   = OFF,					\
+		.imm   = 0 })
+
 /* Function call */
 
 #define BPF_EMIT_CALL(FUNC)					\
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-probe.txt b/tools/perf/Documentation/perf-probe.txt
index e6c9902c6d82..165c2b1d4317 100644
--- a/tools/perf/Documentation/perf-probe.txt
+++ b/tools/perf/Documentation/perf-probe.txt
@@ -240,9 +240,13 @@ Add a probe on schedule() function 12th line with recording cpu local variable:
  or
  ./perf probe --add='schedule:12 cpu'
 
- this will add one or more probes which has the name start with "schedule".
+Add one or more probes which has the name start with "schedule".
 
- Add probes on lines in schedule() function which calls update_rq_clock().
+ ./perf probe schedule*
+ or
+ ./perf probe --add='schedule*'
+
+Add probes on lines in schedule() function which calls update_rq_clock().
 
  ./perf probe 'schedule;update_rq_clock*'
  or
diff --git a/tools/perf/Documentation/perf-script-perl.txt b/tools/perf/Documentation/perf-script-perl.txt
index dfbb506d2c34..142606c0ec9c 100644
--- a/tools/perf/Documentation/perf-script-perl.txt
+++ b/tools/perf/Documentation/perf-script-perl.txt
@@ -39,7 +39,7 @@ EVENT HANDLERS
 When perf script is invoked using a trace script, a user-defined
 'handler function' is called for each event in the trace.  If there's
 no handler function defined for a given event type, the event is
-ignored (or passed to a 'trace_handled' function, see below) and the
+ignored (or passed to a 'trace_unhandled' function, see below) and the
 next event is processed.
 
 Most of the event's field values are passed as arguments to the
diff --git a/tools/perf/Documentation/perf-script-python.txt b/tools/perf/Documentation/perf-script-python.txt
index 54acba221558..51ec2d20068a 100644
--- a/tools/perf/Documentation/perf-script-python.txt
+++ b/tools/perf/Documentation/perf-script-python.txt
@@ -149,10 +149,8 @@ def raw_syscalls__sys_enter(event_name, context, common_cpu,
 		print "id=%d, args=%s\n" % \
 		(id, args),
 
-def trace_unhandled(event_name, context, common_cpu, common_secs, common_nsecs,
-		common_pid, common_comm):
-		print_header(event_name, common_cpu, common_secs, common_nsecs,
-		common_pid, common_comm)
+def trace_unhandled(event_name, context, event_fields_dict):
+		print ' '.join(['%s=%s'%(k,str(v))for k,v in sorted(event_fields_dict.items())])
 
 def print_header(event_name, cpu, secs, nsecs, pid, comm):
 	print "%-20s %5u %05u.%09u %8u %-20s " % \
@@ -321,7 +319,7 @@ So those are the essential steps in writing and running a script.  The
 process can be generalized to any tracepoint or set of tracepoints
 you're interested in - basically find the tracepoint(s) you're
 interested in by looking at the list of available events shown by
-'perf list' and/or look in /sys/kernel/debug/tracing events for
+'perf list' and/or look in /sys/kernel/debug/tracing/events/ for
 detailed event and field info, record the corresponding trace data
 using 'perf record', passing it the list of interesting events,
 generate a skeleton script using 'perf script -g python' and modify the
@@ -334,7 +332,7 @@ right place, you can have your script listed alongside the other
 scripts listed by the 'perf script -l' command e.g.:
 
 ----
-root@tropicana:~# perf script -l
+# perf script -l
 List of available trace scripts:
   wakeup-latency                       system-wide min/max/avg wakeup latency
   rw-by-file <comm>                    r/w activity for a program, by file
@@ -383,8 +381,6 @@ source tree:
 
 ----
 # ls -al kernel-source/tools/perf/scripts/python
-
-root@tropicana:/home/trz/src/tip# ls -al tools/perf/scripts/python
 total 32
 drwxr-xr-x 4 trz trz 4096 2010-01-26 22:30 .
 drwxr-xr-x 4 trz trz 4096 2010-01-26 22:29 ..
@@ -399,7 +395,7 @@ otherwise your script won't show up at run-time), 'perf script -l'
 should show a new entry for your script:
 
 ----
-root@tropicana:~# perf script -l
+# perf script -l
 List of available trace scripts:
   wakeup-latency                       system-wide min/max/avg wakeup latency
   rw-by-file <comm>                    r/w activity for a program, by file
@@ -437,7 +433,7 @@ EVENT HANDLERS
 When perf script is invoked using a trace script, a user-defined
 'handler function' is called for each event in the trace.  If there's
 no handler function defined for a given event type, the event is
-ignored (or passed to a 'trace_handled' function, see below) and the
+ignored (or passed to a 'trace_unhandled' function, see below) and the
 next event is processed.
 
 Most of the event's field values are passed as arguments to the
@@ -532,7 +528,7 @@ can implement a set of optional functions:
 gives scripts a chance to do setup tasks:
 
 ----
-def trace_begin:
+def trace_begin():
     pass
 ----
 
@@ -541,7 +537,7 @@ def trace_begin:
  as display results:
 
 ----
-def trace_end:
+def trace_end():
     pass
 ----
 
@@ -550,8 +546,7 @@ def trace_end:
  of common arguments are passed into it:
 
 ----
-def trace_unhandled(event_name, context, common_cpu, common_secs,
-        common_nsecs, common_pid, common_comm):
+def trace_unhandled(event_name, context, event_fields_dict):
     pass
 ----
 
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/arch/common.c b/tools/perf/arch/common.c
index 837067f48a4c..6b40e9f01740 100644
--- a/tools/perf/arch/common.c
+++ b/tools/perf/arch/common.c
@@ -26,6 +26,7 @@ const char *const arm64_triplets[] = {
 
 const char *const powerpc_triplets[] = {
 	"powerpc-unknown-linux-gnu-",
+	"powerpc-linux-gnu-",
 	"powerpc64-unknown-linux-gnu-",
 	"powerpc64-linux-gnu-",
 	"powerpc64le-linux-gnu-",
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/builtin-stat.c b/tools/perf/builtin-stat.c
index a935b5023732..ad9324d1daf9 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -1578,6 +1578,7 @@ static void print_header(int argc, const char **argv)
 static void print_footer(void)
 {
 	FILE *output = stat_config.output;
+	int n;
 
 	if (!null_run)
 		fprintf(output, "\n");
@@ -1590,7 +1591,9 @@ static void print_footer(void)
 	}
 	fprintf(output, "\n\n");
 
-	if (print_free_counters_hint)
+	if (print_free_counters_hint &&
+	    sysctl__read_int("kernel/nmi_watchdog", &n) >= 0 &&
+	    n > 0)
 		fprintf(output,
 "Some events weren't counted. Try disabling the NMI watchdog:\n"
 "	echo 0 > /proc/sys/kernel/nmi_watchdog\n"
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index d014350adc52..4b2a5d298197 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -681,6 +681,10 @@ static struct syscall_fmt {
 	{ .name	    = "mlockall",   .errmsg = true,
 	  .arg_scnprintf = { [0] = SCA_HEX, /* addr */ }, },
 	{ .name	    = "mmap",	    .hexret = true,
+/* The standard mmap maps to old_mmap on s390x */
+#if defined(__s390x__)
+	.alias = "old_mmap",
+#endif
 	  .arg_scnprintf = { [0] = SCA_HEX,	  /* addr */
 			     [2] = SCA_MMAP_PROT, /* prot */
 			     [3] = SCA_MMAP_FLAGS, /* flags */ }, },
diff --git a/tools/perf/tests/bp_signal.c b/tools/perf/tests/bp_signal.c
index e7664fe3bd33..8ba2c4618fe9 100644
--- a/tools/perf/tests/bp_signal.c
+++ b/tools/perf/tests/bp_signal.c
@@ -288,3 +288,17 @@ int test__bp_signal(int subtest __maybe_unused)
 	return count1 == 1 && overflows == 3 && count2 == 3 && overflows_2 == 3 && count3 == 2 ?
 		TEST_OK : TEST_FAIL;
 }
+
+bool test__bp_signal_is_supported(void)
+{
+/*
+ * The powerpc so far does not have support to even create
+ * instruction breakpoint using the perf event interface.
+ * Once it's there we can release this.
+ */
+#ifdef __powerpc__
+	return false;
+#else
+	return true;
+#endif
+}
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 9e08d297f1a9..3ccfd58a8c3c 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -97,10 +97,12 @@ static struct test generic_tests[] = {
 	{
 		.desc = "Breakpoint overflow signal handler",
 		.func = test__bp_signal,
+		.is_supported = test__bp_signal_is_supported,
 	},
 	{
 		.desc = "Breakpoint overflow sampling",
 		.func = test__bp_signal_overflow,
+		.is_supported = test__bp_signal_is_supported,
 	},
 	{
 		.desc = "Number of exit events of a simple workload",
@@ -401,6 +403,11 @@ static int __cmd_test(int argc, const char *argv[], struct intlist *skiplist)
 		if (!perf_test__matches(t, curr, argc, argv))
 			continue;
 
+		if (t->is_supported && !t->is_supported()) {
+			pr_debug("%2d: %-*s: Disabled\n", i, width, t->desc);
+			continue;
+		}
+
 		pr_info("%2d: %-*s:", i, width, t->desc);
 
 		if (intlist__find(skiplist, i)) {
diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index 1f14e7612cbb..94b7c7b02bde 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -229,6 +229,8 @@ static int read_object_code(u64 addr, size_t len, u8 cpumode,
 	unsigned char buf2[BUFSZ];
 	size_t ret_len;
 	u64 objdump_addr;
+	const char *objdump_name;
+	char decomp_name[KMOD_DECOMP_LEN];
 	int ret;
 
 	pr_debug("Reading object code for memory address: %#"PRIx64"\n", addr);
@@ -289,9 +291,25 @@ static int read_object_code(u64 addr, size_t len, u8 cpumode,
 		state->done[state->done_cnt++] = al.map->start;
 	}
 
+	objdump_name = al.map->dso->long_name;
+	if (dso__needs_decompress(al.map->dso)) {
+		if (dso__decompress_kmodule_path(al.map->dso, objdump_name,
+						 decomp_name,
+						 sizeof(decomp_name)) < 0) {
+			pr_debug("decompression failed\n");
+			return -1;
+		}
+
+		objdump_name = decomp_name;
+	}
+
 	/* Read the object code using objdump */
 	objdump_addr = map__rip_2objdump(al.map, al.addr);
-	ret = read_via_objdump(al.map->dso->long_name, objdump_addr, buf2, len);
+	ret = read_via_objdump(objdump_name, objdump_addr, buf2, len);
+
+	if (dso__needs_decompress(al.map->dso))
+		unlink(objdump_name);
+
 	if (ret > 0) {
 		/*
 		 * The kernel maps are inaccurate - assume objdump is right in
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index 631859629403..577363809c9b 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -34,6 +34,7 @@ struct test {
 		int (*get_nr)(void);
 		const char *(*get_desc)(int subtest);
 	} subtest;
+	bool (*is_supported)(void);
 };
 
 /* Tests */
@@ -99,6 +100,8 @@ const char *test__clang_subtest_get_desc(int subtest);
 int test__clang_subtest_get_nr(void);
 int test__unit_number__scnprint(int subtest);
 
+bool test__bp_signal_is_supported(void);
+
 #if defined(__arm__) || defined(__aarch64__)
 #ifdef HAVE_DWARF_UNWIND_SUPPORT
 struct thread;
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/annotate.c b/tools/perf/util/annotate.c
index 683f8340460c..ddbd56df9187 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -239,10 +239,20 @@ static int jump__parse(struct arch *arch __maybe_unused, struct ins_operands *op
 	const char *s = strchr(ops->raw, '+');
 	const char *c = strchr(ops->raw, ',');
 
-	if (c++ != NULL)
+	/*
+	 * skip over possible up to 2 operands to get to address, e.g.:
+	 * tbnz	 w0, #26, ffff0000083cd190 <security_file_permission+0xd0>
+	 */
+	if (c++ != NULL) {
 		ops->target.addr = strtoull(c, NULL, 16);
-	else
+		if (!ops->target.addr) {
+			c = strchr(c, ',');
+			if (c++ != NULL)
+				ops->target.addr = strtoull(c, NULL, 16);
+		}
+	} else {
 		ops->target.addr = strtoull(ops->raw, NULL, 16);
+	}
 
 	if (s++ != NULL) {
 		ops->target.offset = strtoull(s, NULL, 16);
@@ -257,10 +267,27 @@ static int jump__parse(struct arch *arch __maybe_unused, struct ins_operands *op
 static int jump__scnprintf(struct ins *ins, char *bf, size_t size,
 			   struct ins_operands *ops)
 {
+	const char *c = strchr(ops->raw, ',');
+
 	if (!ops->target.addr || ops->target.offset < 0)
 		return ins__raw_scnprintf(ins, bf, size, ops);
 
-	return scnprintf(bf, size, "%-6.6s %" PRIx64, ins->name, ops->target.offset);
+	if (c != NULL) {
+		const char *c2 = strchr(c + 1, ',');
+
+		/* check for 3-op insn */
+		if (c2 != NULL)
+			c = c2;
+		c++;
+
+		/* mirror arch objdump's space-after-comma style */
+		if (*c == ' ')
+			c++;
+	}
+
+	return scnprintf(bf, size, "%-6.6s %.*s%" PRIx64,
+			 ins->name, c ? c - ops->raw : 0, ops->raw,
+			 ops->target.offset);
 }
 
 static struct ins_ops jump_ops = {
@@ -1294,6 +1321,7 @@ static int dso__disassemble_filename(struct dso *dso, char *filename, size_t fil
 	char linkname[PATH_MAX];
 	char *build_id_filename;
 	char *build_id_path = NULL;
+	char *pos;
 
 	if (dso->symtab_type == DSO_BINARY_TYPE__KALLSYMS &&
 	    !dso__is_kcore(dso))
@@ -1313,7 +1341,14 @@ static int dso__disassemble_filename(struct dso *dso, char *filename, size_t fil
 	if (!build_id_path)
 		return -1;
 
-	dirname(build_id_path);
+	/*
+	 * old style build-id cache has name of XX/XXXXXXX.. while
+	 * new style has XX/XXXXXXX../{elf,kallsyms,vdso}.
+	 * extract the build-id part of dirname in the new style only.
+	 */
+	pos = strrchr(build_id_path, '/');
+	if (pos && strlen(pos) < SBUILD_ID_SIZE - 2)
+		dirname(build_id_path);
 
 	if (dso__is_kcore(dso) ||
 	    readlink(build_id_path, linkname, sizeof(linkname)) < 0 ||
@@ -1396,31 +1431,10 @@ int symbol__disassemble(struct symbol *sym, struct map *map, const char *arch_na
 				sizeof(symfs_filename));
 		}
 	} else if (dso__needs_decompress(dso)) {
-		char tmp[PATH_MAX];
-		struct kmod_path m;
-		int fd;
-		bool ret;
-
-		if (kmod_path__parse_ext(&m, symfs_filename))
-			goto out;
-
-		snprintf(tmp, PATH_MAX, "/tmp/perf-kmod-XXXXXX");
-
-		fd = mkstemp(tmp);
-		if (fd < 0) {
-			free(m.ext);
-			goto out;
-		}
-
-		ret = decompress_to_file(m.ext, symfs_filename, fd);
-
-		if (ret)
-			pr_err("Cannot decompress %s %s\n", m.ext, symfs_filename);
-
-		free(m.ext);
-		close(fd);
+		char tmp[KMOD_DECOMP_LEN];
 
-		if (!ret)
+		if (dso__decompress_kmodule_path(dso, symfs_filename,
+						 tmp, sizeof(tmp)) < 0)
 			goto out;
 
 		strcpy(symfs_filename, tmp);
@@ -1429,7 +1443,7 @@ int symbol__disassemble(struct symbol *sym, struct map *map, const char *arch_na
 	snprintf(command, sizeof(command),
 		 "%s %s%s --start-address=0x%016" PRIx64
 		 " --stop-address=0x%016" PRIx64
-		 " -l -d %s %s -C %s 2>/dev/null|grep -v %s:|expand",
+		 " -l -d %s %s -C \"%s\" 2>/dev/null|grep -v \"%s:\"|expand",
 		 objdump_path ? objdump_path : "objdump",
 		 disassembler_style ? "-M " : "",
 		 disassembler_style ? disassembler_style : "",
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index 168cc49654e7..e0148b081bdf 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -278,51 +278,6 @@ char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size)
 	return bf;
 }
 
-bool dso__build_id_is_kmod(const struct dso *dso, char *bf, size_t size)
-{
-	char *id_name = NULL, *ch;
-	struct stat sb;
-	char sbuild_id[SBUILD_ID_SIZE];
-
-	if (!dso->has_build_id)
-		goto err;
-
-	build_id__sprintf(dso->build_id, sizeof(dso->build_id), sbuild_id);
-	id_name = build_id_cache__linkname(sbuild_id, NULL, 0);
-	if (!id_name)
-		goto err;
-	if (access(id_name, F_OK))
-		goto err;
-	if (lstat(id_name, &sb) == -1)
-		goto err;
-	if ((size_t)sb.st_size > size - 1)
-		goto err;
-	if (readlink(id_name, bf, size - 1) < 0)
-		goto err;
-
-	bf[sb.st_size] = '\0';
-
-	/*
-	 * link should be:
-	 * ../../lib/modules/4.4.0-rc4/kernel/net/ipv4/netfilter/nf_nat_ipv4.ko/a09fe3eb3147dafa4e3b31dbd6257e4d696bdc92
-	 */
-	ch = strrchr(bf, '/');
-	if (!ch)
-		goto err;
-	if (ch - 3 < bf)
-		goto err;
-
-	free(id_name);
-	return strncmp(".ko", ch - 3, 3) == 0;
-err:
-	pr_err("Invalid build id: %s\n", id_name ? :
-					 dso->long_name ? :
-					 dso->short_name ? :
-					 "[unknown]");
-	free(id_name);
-	return false;
-}
-
 #define dsos__for_each_with_build_id(pos, head)	\
 	list_for_each_entry(pos, head, node)	\
 		if (!pos->has_build_id)		\
diff --git a/tools/perf/util/build-id.h b/tools/perf/util/build-id.h
index 8a89b195c1fc..96690a55c62c 100644
--- a/tools/perf/util/build-id.h
+++ b/tools/perf/util/build-id.h
@@ -17,7 +17,6 @@ char *build_id_cache__kallsyms_path(const char *sbuild_id, char *bf,
 				    size_t size);
 
 char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size);
-bool dso__build_id_is_kmod(const struct dso *dso, char *bf, size_t size);
 
 int build_id__mark_dso_hit(struct perf_tool *tool, union perf_event *event,
 			   struct perf_sample *sample, struct perf_evsel *evsel,
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/dso.c b/tools/perf/util/dso.c
index a96a99d2369f..4e7ab611377a 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -248,6 +248,64 @@ bool dso__needs_decompress(struct dso *dso)
 		dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE_COMP;
 }
 
+static int decompress_kmodule(struct dso *dso, const char *name, char *tmpbuf)
+{
+	int fd = -1;
+	struct kmod_path m;
+
+	if (!dso__needs_decompress(dso))
+		return -1;
+
+	if (kmod_path__parse_ext(&m, dso->long_name))
+		return -1;
+
+	if (!m.comp)
+		goto out;
+
+	fd = mkstemp(tmpbuf);
+	if (fd < 0) {
+		dso->load_errno = errno;
+		goto out;
+	}
+
+	if (!decompress_to_file(m.ext, name, fd)) {
+		dso->load_errno = DSO_LOAD_ERRNO__DECOMPRESSION_FAILURE;
+		close(fd);
+		fd = -1;
+	}
+
+out:
+	free(m.ext);
+	return fd;
+}
+
+int dso__decompress_kmodule_fd(struct dso *dso, const char *name)
+{
+	char tmpbuf[] = KMOD_DECOMP_NAME;
+	int fd;
+
+	fd = decompress_kmodule(dso, name, tmpbuf);
+	unlink(tmpbuf);
+	return fd;
+}
+
+int dso__decompress_kmodule_path(struct dso *dso, const char *name,
+				 char *pathname, size_t len)
+{
+	char tmpbuf[] = KMOD_DECOMP_NAME;
+	int fd;
+
+	fd = decompress_kmodule(dso, name, tmpbuf);
+	if (fd < 0) {
+		unlink(tmpbuf);
+		return -1;
+	}
+
+	strncpy(pathname, tmpbuf, len);
+	close(fd);
+	return 0;
+}
+
 /*
  * Parses kernel module specified in @path and updates
  * @m argument like:
@@ -335,6 +393,21 @@ int __kmod_path__parse(struct kmod_path *m, const char *path,
 	return 0;
 }
 
+void dso__set_module_info(struct dso *dso, struct kmod_path *m,
+			  struct machine *machine)
+{
+	if (machine__is_host(machine))
+		dso->symtab_type = DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE;
+	else
+		dso->symtab_type = DSO_BINARY_TYPE__GUEST_KMODULE;
+
+	/* _KMODULE_COMP should be next to _KMODULE */
+	if (m->kmod && m->comp)
+		dso->symtab_type++;
+
+	dso__set_short_name(dso, strdup(m->name), true);
+}
+
 /*
  * Global list of open DSOs and the counter.
  */
@@ -381,7 +454,7 @@ static int do_open(char *name)
 
 static int __open_dso(struct dso *dso, struct machine *machine)
 {
-	int fd;
+	int fd = -EINVAL;
 	char *root_dir = (char *)"";
 	char *name = malloc(PATH_MAX);
 
@@ -392,15 +465,30 @@ static int __open_dso(struct dso *dso, struct machine *machine)
 		root_dir = machine->root_dir;
 
 	if (dso__read_binary_type_filename(dso, dso->binary_type,
-					    root_dir, name, PATH_MAX)) {
-		free(name);
-		return -EINVAL;
-	}
+					    root_dir, name, PATH_MAX))
+		goto out;
 
 	if (!is_regular_file(name))
-		return -EINVAL;
+		goto out;
+
+	if (dso__needs_decompress(dso)) {
+		char newpath[KMOD_DECOMP_LEN];
+		size_t len = sizeof(newpath);
+
+		if (dso__decompress_kmodule_path(dso, name, newpath, len) < 0) {
+			fd = -dso->load_errno;
+			goto out;
+		}
+
+		strcpy(name, newpath);
+	}
 
 	fd = do_open(name);
+
+	if (dso__needs_decompress(dso))
+		unlink(name);
+
+out:
 	free(name);
 	return fd;
 }
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index 12350b171727..bd061ba7b47c 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -244,6 +244,12 @@ bool is_supported_compression(const char *ext);
 bool is_kernel_module(const char *pathname, int cpumode);
 bool decompress_to_file(const char *ext, const char *filename, int output_fd);
 bool dso__needs_decompress(struct dso *dso);
+int dso__decompress_kmodule_fd(struct dso *dso, const char *name);
+int dso__decompress_kmodule_path(struct dso *dso, const char *name,
+				 char *pathname, size_t len);
+
+#define KMOD_DECOMP_NAME  "/tmp/perf-kmod-XXXXXX"
+#define KMOD_DECOMP_LEN   sizeof(KMOD_DECOMP_NAME)
 
 struct kmod_path {
 	char *name;
@@ -259,6 +265,9 @@ int __kmod_path__parse(struct kmod_path *m, const char *path,
 #define kmod_path__parse_name(__m, __p) __kmod_path__parse(__m, __p, true , false)
 #define kmod_path__parse_ext(__m, __p)  __kmod_path__parse(__m, __p, false, true)
 
+void dso__set_module_info(struct dso *dso, struct kmod_path *m,
+			  struct machine *machine);
+
 /*
  * The dso__data_* external interface provides following functions:
  *   dso__data_get_fd
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/header.c b/tools/perf/util/header.c
index 314a07151fb7..5cac8d5e009a 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -1469,8 +1469,16 @@ static int __event_process_build_id(struct build_id_event *bev,
 
 		dso__set_build_id(dso, &bev->build_id);
 
-		if (!is_kernel_module(filename, cpumode))
-			dso->kernel = dso_type;
+		if (dso_type != DSO_TYPE_USER) {
+			struct kmod_path m = { .name = NULL, };
+
+			if (!kmod_path__parse_name(&m, filename) && m.kmod)
+				dso__set_module_info(dso, &m, machine);
+			else
+				dso->kernel = dso_type;
+
+			free(m.name);
+		}
 
 		build_id__sprintf(dso->build_id, sizeof(dso->build_id),
 				  sbuild_id);
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index d97e014c3df3..d7f31cb0a4cb 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -572,16 +572,7 @@ static struct dso *machine__findnew_module_dso(struct machine *machine,
 		if (dso == NULL)
 			goto out_unlock;
 
-		if (machine__is_host(machine))
-			dso->symtab_type = DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE;
-		else
-			dso->symtab_type = DSO_BINARY_TYPE__GUEST_KMODULE;
-
-		/* _KMODULE_COMP should be next to _KMODULE */
-		if (m->kmod && m->comp)
-			dso->symtab_type++;
-
-		dso__set_short_name(dso, strdup(m->name), true);
+		dso__set_module_info(dso, m, machine);
 		dso__set_long_name(dso, strdup(filename), true);
 	}
 
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 9d92af7d0718..40de3cb40d21 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -1219,7 +1219,7 @@ static int python_generate_script(struct pevent *pevent, const char *outfile)
 	fprintf(ofp, "# be retrieved using Python functions of the form "
 		"common_*(context).\n");
 
-	fprintf(ofp, "# See the perf-trace-python Documentation for the list "
+	fprintf(ofp, "# See the perf-script-python Documentation for the list "
 		"of available functions.\n\n");
 
 	fprintf(ofp, "import os\n");
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/symbol-elf.c b/tools/perf/util/symbol-elf.c
index e7ee47f7377a..502505cf236a 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -637,43 +637,6 @@ static int dso__swap_init(struct dso *dso, unsigned char eidata)
 	return 0;
 }
 
-static int decompress_kmodule(struct dso *dso, const char *name,
-			      enum dso_binary_type type)
-{
-	int fd = -1;
-	char tmpbuf[] = "/tmp/perf-kmod-XXXXXX";
-	struct kmod_path m;
-
-	if (type != DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP &&
-	    type != DSO_BINARY_TYPE__GUEST_KMODULE_COMP &&
-	    type != DSO_BINARY_TYPE__BUILD_ID_CACHE)
-		return -1;
-
-	if (type == DSO_BINARY_TYPE__BUILD_ID_CACHE)
-		name = dso->long_name;
-
-	if (kmod_path__parse_ext(&m, name) || !m.comp)
-		return -1;
-
-	fd = mkstemp(tmpbuf);
-	if (fd < 0) {
-		dso->load_errno = errno;
-		goto out;
-	}
-
-	if (!decompress_to_file(m.ext, name, fd)) {
-		dso->load_errno = DSO_LOAD_ERRNO__DECOMPRESSION_FAILURE;
-		close(fd);
-		fd = -1;
-	}
-
-	unlink(tmpbuf);
-
-out:
-	free(m.ext);
-	return fd;
-}
-
 bool symsrc__possibly_runtime(struct symsrc *ss)
 {
 	return ss->dynsym || ss->opdsec;
@@ -705,9 +668,11 @@ int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name,
 	int fd;
 
 	if (dso__needs_decompress(dso)) {
-		fd = decompress_kmodule(dso, name, type);
+		fd = dso__decompress_kmodule_fd(dso, name);
 		if (fd < 0)
 			return -1;
+
+		type = dso->symtab_type;
 	} else {
 		fd = open(name, O_RDONLY);
 		if (fd < 0) {
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 8f2b068ff756..e7a98dbd2aed 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1562,10 +1562,6 @@ int dso__load(struct dso *dso, struct map *map)
 	if (!runtime_ss && syms_ss)
 		runtime_ss = syms_ss;
 
-	if (syms_ss && syms_ss->type == DSO_BINARY_TYPE__BUILD_ID_CACHE)
-		if (dso__build_id_is_kmod(dso, name, PATH_MAX))
-			kmod = true;
-
 	if (syms_ss)
 		ret = dso__load_sym(dso, map, syms_ss, runtime_ss, kmod);
 	else
diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c
index f90e11a555b2..da45c4be5fb3 100644
--- a/tools/perf/util/unwind-libdw.c
+++ b/tools/perf/util/unwind-libdw.c
@@ -39,6 +39,14 @@ static int __report_module(struct addr_location *al, u64 ip,
 		return 0;
 
 	mod = dwfl_addrmodule(ui->dwfl, ip);
+	if (mod) {
+		Dwarf_Addr s;
+
+		dwfl_module_info(mod, NULL, &s, NULL, NULL, NULL, NULL, NULL);
+		if (s != al->map->start)
+			mod = 0;
+	}
+
 	if (!mod)
 		mod = dwfl_report_elf(ui->dwfl, dso->short_name,
 				      dso->long_name, -1, al->map->start,
@@ -168,12 +176,16 @@ 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;
 }
@@ -220,7 +232,7 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
 
 	err = dwfl_getthread_frames(ui->dwfl, thread->tid, frame_callback, ui);
 
-	if (err && !ui->max_stack)
+	if (err && ui->max_stack != max_stack)
 		err = 0;
 
 	/*
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;
 		}
 
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 3773562056da..cabb19b1e371 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -49,6 +49,7 @@
 #define MAX_NR_MAPS	4
 
 #define F_NEEDS_EFFICIENT_UNALIGNED_ACCESS	(1 << 0)
+#define F_LOAD_WITH_STRICT_ALIGNMENT		(1 << 1)
 
 struct bpf_test {
 	const char *descr;
@@ -2615,6 +2616,30 @@ static struct bpf_test tests[] = {
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 	},
 	{
+		"direct packet access: test17 (pruning, alignment)",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct __sk_buff, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct __sk_buff, data_end)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_1,
+				    offsetof(struct __sk_buff, mark)),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 14),
+			BPF_JMP_IMM(BPF_JGT, BPF_REG_7, 1, 4),
+			BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1),
+			BPF_STX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, -4),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 1),
+			BPF_JMP_A(-6),
+		},
+		.errstr = "misaligned packet access off 2+15+-4 size 4",
+		.result = REJECT,
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.flags = F_LOAD_WITH_STRICT_ALIGNMENT,
+	},
+	{
 		"helper access to packet: test1, valid packet_ptr range",
 		.insns = {
 			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
@@ -3341,6 +3366,70 @@ static struct bpf_test tests[] = {
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS
 	},
 	{
+		"alu ops on ptr_to_map_value_or_null, 1",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_1, 10),
+			BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_1, -8),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_map_lookup_elem),
+			BPF_MOV64_REG(BPF_REG_4, BPF_REG_0),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, -2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 2),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
+			BPF_ST_MEM(BPF_DW, BPF_REG_4, 0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_map1 = { 4 },
+		.errstr = "R4 invalid mem access",
+		.result = REJECT,
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS
+	},
+	{
+		"alu ops on ptr_to_map_value_or_null, 2",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_1, 10),
+			BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_1, -8),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_map_lookup_elem),
+			BPF_MOV64_REG(BPF_REG_4, BPF_REG_0),
+			BPF_ALU64_IMM(BPF_AND, BPF_REG_4, -1),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
+			BPF_ST_MEM(BPF_DW, BPF_REG_4, 0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_map1 = { 4 },
+		.errstr = "R4 invalid mem access",
+		.result = REJECT,
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS
+	},
+	{
+		"alu ops on ptr_to_map_value_or_null, 3",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_1, 10),
+			BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_1, -8),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_map_lookup_elem),
+			BPF_MOV64_REG(BPF_REG_4, BPF_REG_0),
+			BPF_ALU64_IMM(BPF_LSH, BPF_REG_4, 1),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
+			BPF_ST_MEM(BPF_DW, BPF_REG_4, 0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_map1 = { 4 },
+		.errstr = "R4 invalid mem access",
+		.result = REJECT,
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS
+	},
+	{
 		"invalid memory access with multiple map_lookup_elem calls",
 		.insns = {
 			BPF_MOV64_IMM(BPF_REG_1, 10),
@@ -4937,7 +5026,149 @@ static struct bpf_test tests[] = {
 		.fixup_map_in_map = { 3 },
 		.errstr = "R1 type=map_value_or_null expected=map_ptr",
 		.result = REJECT,
-	}
+	},
+	{
+		"ld_abs: check calling conv, r1",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+			BPF_MOV64_IMM(BPF_REG_1, 0),
+			BPF_LD_ABS(BPF_W, -0x200000),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "R1 !read_ok",
+		.result = REJECT,
+	},
+	{
+		"ld_abs: check calling conv, r2",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+			BPF_MOV64_IMM(BPF_REG_2, 0),
+			BPF_LD_ABS(BPF_W, -0x200000),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "R2 !read_ok",
+		.result = REJECT,
+	},
+	{
+		"ld_abs: check calling conv, r3",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+			BPF_MOV64_IMM(BPF_REG_3, 0),
+			BPF_LD_ABS(BPF_W, -0x200000),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_3),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "R3 !read_ok",
+		.result = REJECT,
+	},
+	{
+		"ld_abs: check calling conv, r4",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+			BPF_MOV64_IMM(BPF_REG_4, 0),
+			BPF_LD_ABS(BPF_W, -0x200000),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_4),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "R4 !read_ok",
+		.result = REJECT,
+	},
+	{
+		"ld_abs: check calling conv, r5",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+			BPF_MOV64_IMM(BPF_REG_5, 0),
+			BPF_LD_ABS(BPF_W, -0x200000),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_5),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "R5 !read_ok",
+		.result = REJECT,
+	},
+	{
+		"ld_abs: check calling conv, r7",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+			BPF_MOV64_IMM(BPF_REG_7, 0),
+			BPF_LD_ABS(BPF_W, -0x200000),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_7),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+	},
+	{
+		"ld_ind: check calling conv, r1",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+			BPF_MOV64_IMM(BPF_REG_1, 1),
+			BPF_LD_IND(BPF_W, BPF_REG_1, -0x200000),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "R1 !read_ok",
+		.result = REJECT,
+	},
+	{
+		"ld_ind: check calling conv, r2",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+			BPF_MOV64_IMM(BPF_REG_2, 1),
+			BPF_LD_IND(BPF_W, BPF_REG_2, -0x200000),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "R2 !read_ok",
+		.result = REJECT,
+	},
+	{
+		"ld_ind: check calling conv, r3",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+			BPF_MOV64_IMM(BPF_REG_3, 1),
+			BPF_LD_IND(BPF_W, BPF_REG_3, -0x200000),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_3),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "R3 !read_ok",
+		.result = REJECT,
+	},
+	{
+		"ld_ind: check calling conv, r4",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+			BPF_MOV64_IMM(BPF_REG_4, 1),
+			BPF_LD_IND(BPF_W, BPF_REG_4, -0x200000),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_4),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "R4 !read_ok",
+		.result = REJECT,
+	},
+	{
+		"ld_ind: check calling conv, r5",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+			BPF_MOV64_IMM(BPF_REG_5, 1),
+			BPF_LD_IND(BPF_W, BPF_REG_5, -0x200000),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_5),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "R5 !read_ok",
+		.result = REJECT,
+	},
+	{
+		"ld_ind: check calling conv, r7",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+			BPF_MOV64_IMM(BPF_REG_7, 1),
+			BPF_LD_IND(BPF_W, BPF_REG_7, -0x200000),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_7),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+	},
 };
 
 static int probe_filter_length(const struct bpf_insn *fp)
@@ -5059,9 +5290,9 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
 
 	do_test_fixup(test, prog, map_fds);
 
-	fd_prog = bpf_load_program(prog_type ? : BPF_PROG_TYPE_SOCKET_FILTER,
-				   prog, prog_len, "GPL", 0, bpf_vlog,
-				   sizeof(bpf_vlog));
+	fd_prog = bpf_verify_program(prog_type ? : BPF_PROG_TYPE_SOCKET_FILTER,
+				     prog, prog_len, test->flags & F_LOAD_WITH_STRICT_ALIGNMENT,
+				     "GPL", 0, bpf_vlog, sizeof(bpf_vlog));
 
 	expected_ret = unpriv && test->result_unpriv != UNDEF ?
 		       test->result_unpriv : test->result;
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/multiple_kprobes.tc b/tools/testing/selftests/ftrace/test.d/kprobe/multiple_kprobes.tc
new file mode 100644
index 000000000000..f4d1ff785d67
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/multiple_kprobes.tc
@@ -0,0 +1,21 @@
+#!/bin/sh
+# description: Register/unregister many kprobe events
+
+# ftrace fentry skip size depends on the machine architecture.
+# Currently HAVE_KPROBES_ON_FTRACE defined on x86 and powerpc
+case `uname -m` in
+  x86_64|i[3456]86) OFFS=5;;
+  ppc*) OFFS=4;;
+  *) OFFS=0;;
+esac
+
+echo "Setup up to 256 kprobes"
+grep t /proc/kallsyms | cut -f3 -d" " | grep -v .*\\..* | \
+head -n 256 | while read i; do echo p ${i}+${OFFS} ; done > kprobe_events ||:
+
+echo 1 > events/kprobes/enable
+echo 0 > events/kprobes/enable
+echo > kprobe_events
+echo "Waiting for unoptimizing & freeing"
+sleep 5
+echo "Done"
diff --git a/tools/testing/selftests/powerpc/tm/tm-resched-dscr.c b/tools/testing/selftests/powerpc/tm/tm-resched-dscr.c
index d9c49f41515e..e79ccd6aada1 100644
--- a/tools/testing/selftests/powerpc/tm/tm-resched-dscr.c
+++ b/tools/testing/selftests/powerpc/tm/tm-resched-dscr.c
@@ -42,12 +42,12 @@ int test_body(void)
 	printf("Check DSCR TM context switch: ");
 	fflush(stdout);
 	for (;;) {
-		rv = 1;
 		asm __volatile__ (
 			/* set a known value into the DSCR */
 			"ld      3, %[dscr1];"
 			"mtspr   %[sprn_dscr], 3;"
 
+			"li      %[rv], 1;"
 			/* start and suspend a transaction */
 			"tbegin.;"
 			"beq     1f;"