Merge v4.18-rc3 into drm-next

Two requests have come in for a backmerge,
and I've got some pull reqs on rc2, so this
just makes sense.

Signed-off-by: Dave Airlie <airlied@redhat.com>

59 files changed, 1345 insertions, 214 deletions

diff --git a/tools/arch/arm/include/uapi/asm/kvm.h b/tools/arch/arm/include/uapi/asm/kvm.h
index caae4843cb70..16e006f708ca 100644
--- a/tools/arch/arm/include/uapi/asm/kvm.h
+++ b/tools/arch/arm/include/uapi/asm/kvm.h
@@ -91,6 +91,7 @@ struct kvm_regs {
 #define KVM_VGIC_V3_ADDR_TYPE_DIST	2
 #define KVM_VGIC_V3_ADDR_TYPE_REDIST	3
 #define KVM_VGIC_ITS_ADDR_TYPE		4
+#define KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION	5
 
 #define KVM_VGIC_V3_DIST_SIZE		SZ_64K
 #define KVM_VGIC_V3_REDIST_SIZE		(2 * SZ_64K)
diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h
index 04b3256f8e6d..4e76630dd655 100644
--- a/tools/arch/arm64/include/uapi/asm/kvm.h
+++ b/tools/arch/arm64/include/uapi/asm/kvm.h
@@ -91,6 +91,7 @@ struct kvm_regs {
 #define KVM_VGIC_V3_ADDR_TYPE_DIST	2
 #define KVM_VGIC_V3_ADDR_TYPE_REDIST	3
 #define KVM_VGIC_ITS_ADDR_TYPE		4
+#define KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION	5
 
 #define KVM_VGIC_V3_DIST_SIZE		SZ_64K
 #define KVM_VGIC_V3_REDIST_SIZE		(2 * SZ_64K)
diff --git a/tools/arch/powerpc/include/uapi/asm/kvm.h b/tools/arch/powerpc/include/uapi/asm/kvm.h
index 833ed9a16adf..1b32b56a03d3 100644
--- a/tools/arch/powerpc/include/uapi/asm/kvm.h
+++ b/tools/arch/powerpc/include/uapi/asm/kvm.h
@@ -633,6 +633,7 @@ struct kvm_ppc_cpu_char {
 #define KVM_REG_PPC_PSSCR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xbd)
 
 #define KVM_REG_PPC_DEC_EXPIRY	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xbe)
+#define KVM_REG_PPC_ONLINE	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xbf)
 
 /* Transactional Memory checkpointed state:
  * This is all GPRs, all VSX regs and a subset of SPRs
diff --git a/tools/arch/powerpc/include/uapi/asm/unistd.h b/tools/arch/powerpc/include/uapi/asm/unistd.h
index 389c36fd8299..ac5ba55066dd 100644
--- a/tools/arch/powerpc/include/uapi/asm/unistd.h
+++ b/tools/arch/powerpc/include/uapi/asm/unistd.h
@@ -398,5 +398,6 @@
 #define __NR_pkey_alloc		384
 #define __NR_pkey_free		385
 #define __NR_pkey_mprotect	386
+#define __NR_rseq		387
 
 #endif /* _UAPI_ASM_POWERPC_UNISTD_H_ */
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index fb00a2fca990..5701f5cecd31 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -282,7 +282,9 @@
 #define X86_FEATURE_AMD_IBPB		(13*32+12) /* "" Indirect Branch Prediction Barrier */
 #define X86_FEATURE_AMD_IBRS		(13*32+14) /* "" Indirect Branch Restricted Speculation */
 #define X86_FEATURE_AMD_STIBP		(13*32+15) /* "" Single Thread Indirect Branch Predictors */
+#define X86_FEATURE_AMD_SSBD		(13*32+24) /* "" Speculative Store Bypass Disable */
 #define X86_FEATURE_VIRT_SSBD		(13*32+25) /* Virtualized Speculative Store Bypass Disable */
+#define X86_FEATURE_AMD_SSB_NO		(13*32+26) /* "" Speculative Store Bypass is fixed in hardware. */
 
 /* Thermal and Power Management Leaf, CPUID level 0x00000006 (EAX), word 14 */
 #define X86_FEATURE_DTHERM		(14*32+ 0) /* Digital Thermal Sensor */
diff --git a/tools/bpf/bpftool/perf.c b/tools/bpf/bpftool/perf.c
index ac6b1a12c9b7..b76b77dcfd1f 100644
--- a/tools/bpf/bpftool/perf.c
+++ b/tools/bpf/bpftool/perf.c
@@ -29,9 +29,10 @@ static bool has_perf_query_support(void)
 	if (perf_query_supported)
 		goto out;
 
-	fd = open(bin_name, O_RDONLY);
+	fd = open("/", O_RDONLY);
 	if (fd < 0) {
-		p_err("perf_query_support: %s", strerror(errno));
+		p_err("perf_query_support: cannot open directory \"/\" (%s)",
+		      strerror(errno));
 		goto out;
 	}
 
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index a4f435203fef..05f42a46d6ed 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -90,7 +90,9 @@ static void print_boot_time(__u64 nsecs, char *buf, unsigned int size)
 	}
 
 	wallclock_secs = (real_time_ts.tv_sec - boot_time_ts.tv_sec) +
-		nsecs / 1000000000;
+		(real_time_ts.tv_nsec - boot_time_ts.tv_nsec + nsecs) /
+		1000000000;
+
 
 	if (!localtime_r(&wallclock_secs, &load_tm)) {
 		snprintf(buf, size, "%llu", nsecs / 1000000000);
diff --git a/tools/include/uapi/drm/drm.h b/tools/include/uapi/drm/drm.h
index 6fdff5945c8a..9c660e1688ab 100644
--- a/tools/include/uapi/drm/drm.h
+++ b/tools/include/uapi/drm/drm.h
@@ -680,6 +680,13 @@ struct drm_get_cap {
  */
 #define DRM_CLIENT_CAP_ATOMIC	3
 
+/**
+ * DRM_CLIENT_CAP_ASPECT_RATIO
+ *
+ * If set to 1, the DRM core will provide aspect ratio information in modes.
+ */
+#define DRM_CLIENT_CAP_ASPECT_RATIO    4
+
 /** DRM_IOCTL_SET_CLIENT_CAP ioctl argument type */
 struct drm_set_client_cap {
 	__u64 capability;
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index e0b06784f227..59b19b6a40d7 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -2630,7 +2630,7 @@ struct bpf_fib_lookup {
 	union {
 		/* inputs to lookup */
 		__u8	tos;		/* AF_INET  */
-		__be32	flowlabel;	/* AF_INET6 */
+		__be32	flowinfo;	/* AF_INET6, flow_label + priority */
 
 		/* output: metric of fib result (IPv4/IPv6 only) */
 		__u32	rt_metric;
diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h
index 68699f654118..cf01b6824244 100644
--- a/tools/include/uapi/linux/if_link.h
+++ b/tools/include/uapi/linux/if_link.h
@@ -333,6 +333,7 @@ enum {
 	IFLA_BRPORT_BCAST_FLOOD,
 	IFLA_BRPORT_GROUP_FWD_MASK,
 	IFLA_BRPORT_NEIGH_SUPPRESS,
+	IFLA_BRPORT_ISOLATED,
 	__IFLA_BRPORT_MAX
 };
 #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1)
@@ -516,6 +517,7 @@ enum {
 	IFLA_VXLAN_COLLECT_METADATA,
 	IFLA_VXLAN_LABEL,
 	IFLA_VXLAN_GPE,
+	IFLA_VXLAN_TTL_INHERIT,
 	__IFLA_VXLAN_MAX
 };
 #define IFLA_VXLAN_MAX	(__IFLA_VXLAN_MAX - 1)
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index 39e364c70caf..b6270a3b38e9 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -948,6 +948,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_S390_BPB 152
 #define KVM_CAP_GET_MSR_FEATURES 153
 #define KVM_CAP_HYPERV_EVENTFD 154
+#define KVM_CAP_HYPERV_TLBFLUSH 155
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index 38047c6aa575..f4a25bd1871f 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -164,6 +164,7 @@ static int __dead_end_function(struct objtool_file *file, struct symbol *func,
 		"lbug_with_loc",
 		"fortify_panic",
 		"usercopy_abort",
+		"machine_real_restart",
 	};
 
 	if (func->bind == STB_WEAK)
diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 5dfe102fb5b5..b10a90b6a718 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -178,6 +178,9 @@ Print count deltas for fixed number of times.
 This option should be used together with "-I" option.
 	example: 'perf stat -I 1000 --interval-count 2 -e cycles -a'
 
+--interval-clear::
+Clear the screen before next interval.
+
 --timeout msecs::
 Stop the 'perf stat' session and print count deltas after N milliseconds (minimum: 10 ms).
 This option is not supported with the "-I" option.
diff --git a/tools/perf/arch/powerpc/util/skip-callchain-idx.c b/tools/perf/arch/powerpc/util/skip-callchain-idx.c
index 3598b8b75d27..ef5d59a5742e 100644
--- a/tools/perf/arch/powerpc/util/skip-callchain-idx.c
+++ b/tools/perf/arch/powerpc/util/skip-callchain-idx.c
@@ -243,7 +243,7 @@ int arch_skip_callchain_idx(struct thread *thread, struct ip_callchain *chain)
 	u64 ip;
 	u64 skip_slot = -1;
 
-	if (chain->nr < 3)
+	if (!chain || chain->nr < 3)
 		return skip_slot;
 
 	ip = chain->ips[2];
diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
index 4dfe42666d0c..f0b1709a5ffb 100644
--- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
@@ -341,6 +341,8 @@
 330	common	pkey_alloc		__x64_sys_pkey_alloc
 331	common	pkey_free		__x64_sys_pkey_free
 332	common	statx			__x64_sys_statx
+333	common	io_pgetevents		__x64_sys_io_pgetevents
+334	common	rseq			__x64_sys_rseq
 
 #
 # x32-specific system call numbers start at 512 to avoid cache impact
diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
index 63eb49082774..44195514b19e 100644
--- a/tools/perf/bench/numa.c
+++ b/tools/perf/bench/numa.c
@@ -1098,7 +1098,7 @@ static void *worker_thread(void *__tdata)
 	u8 *global_data;
 	u8 *process_data;
 	u8 *thread_data;
-	u64 bytes_done;
+	u64 bytes_done, secs;
 	long work_done;
 	u32 l;
 	struct rusage rusage;
@@ -1254,7 +1254,8 @@ static void *worker_thread(void *__tdata)
 	timersub(&stop, &start0, &diff);
 	td->runtime_ns = diff.tv_sec * NSEC_PER_SEC;
 	td->runtime_ns += diff.tv_usec * NSEC_PER_USEC;
-	td->speed_gbs = bytes_done / (td->runtime_ns / NSEC_PER_SEC) / 1e9;
+	secs = td->runtime_ns / NSEC_PER_SEC;
+	td->speed_gbs = secs ? bytes_done / secs / 1e9 : 0;
 
 	getrusage(RUSAGE_THREAD, &rusage);
 	td->system_time_ns = rusage.ru_stime.tv_sec * NSEC_PER_SEC;
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 5eb22cc56363..8180319285af 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -283,6 +283,15 @@ out_put:
 	return ret;
 }
 
+static int process_feature_event(struct perf_tool *tool,
+				 union perf_event *event,
+				 struct perf_session *session)
+{
+	if (event->feat.feat_id < HEADER_LAST_FEATURE)
+		return perf_event__process_feature(tool, event, session);
+	return 0;
+}
+
 static int hist_entry__tty_annotate(struct hist_entry *he,
 				    struct perf_evsel *evsel,
 				    struct perf_annotate *ann)
@@ -471,7 +480,7 @@ int cmd_annotate(int argc, const char **argv)
 			.attr	= perf_event__process_attr,
 			.build_id = perf_event__process_build_id,
 			.tracing_data   = perf_event__process_tracing_data,
-			.feature	= perf_event__process_feature,
+			.feature	= process_feature_event,
 			.ordered_events = true,
 			.ordering_requires_timestamps = true,
 		},
diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c
index 307b3594525f..6a8738f7ead3 100644
--- a/tools/perf/builtin-c2c.c
+++ b/tools/perf/builtin-c2c.c
@@ -56,16 +56,16 @@ struct c2c_hist_entry {
 
 	struct compute_stats	 cstats;
 
+	unsigned long		 paddr;
+	unsigned long		 paddr_cnt;
+	bool			 paddr_zero;
+	char			*nodestr;
+
 	/*
 	 * must be at the end,
 	 * because of its callchain dynamic entry
 	 */
 	struct hist_entry	he;
-
-	unsigned long		 paddr;
-	unsigned long		 paddr_cnt;
-	bool			 paddr_zero;
-	char			*nodestr;
 };
 
 static char const *coalesce_default = "pid,iaddr";
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index cdb5b6949832..c04dc7b53797 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -217,7 +217,8 @@ static int process_feature_event(struct perf_tool *tool,
 	}
 
 	/*
-	 * All features are received, we can force the
+	 * (feat_id = HEADER_LAST_FEATURE) is the end marker which
+	 * means all features are received, now we can force the
 	 * group if needed.
 	 */
 	setup_forced_leader(rep, session->evlist);
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index b3bf35512d21..568ddfac3213 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -180,6 +180,18 @@ static struct {
 				  PERF_OUTPUT_EVNAME | PERF_OUTPUT_TRACE
 	},
 
+	[PERF_TYPE_HW_CACHE] = {
+		.user_set = false,
+
+		.fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID |
+			      PERF_OUTPUT_CPU | PERF_OUTPUT_TIME |
+			      PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP |
+			      PERF_OUTPUT_SYM | PERF_OUTPUT_SYMOFFSET |
+			      PERF_OUTPUT_DSO | PERF_OUTPUT_PERIOD,
+
+		.invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT,
+	},
+
 	[PERF_TYPE_RAW] = {
 		.user_set = false,
 
@@ -1822,6 +1834,7 @@ static int process_attr(struct perf_tool *tool, union perf_event *event,
 	struct perf_evlist *evlist;
 	struct perf_evsel *evsel, *pos;
 	int err;
+	static struct perf_evsel_script *es;
 
 	err = perf_event__process_attr(tool, event, pevlist);
 	if (err)
@@ -1830,6 +1843,19 @@ static int process_attr(struct perf_tool *tool, union perf_event *event,
 	evlist = *pevlist;
 	evsel = perf_evlist__last(*pevlist);
 
+	if (!evsel->priv) {
+		if (scr->per_event_dump) {
+			evsel->priv = perf_evsel_script__new(evsel,
+						scr->session->data);
+		} else {
+			es = zalloc(sizeof(*es));
+			if (!es)
+				return -ENOMEM;
+			es->fp = stdout;
+			evsel->priv = es;
+		}
+	}
+
 	if (evsel->attr.type >= PERF_TYPE_MAX &&
 	    evsel->attr.type != PERF_TYPE_SYNTH)
 		return 0;
@@ -3018,6 +3044,15 @@ int process_cpu_map_event(struct perf_tool *tool __maybe_unused,
 	return set_maps(script);
 }
 
+static int process_feature_event(struct perf_tool *tool,
+				 union perf_event *event,
+				 struct perf_session *session)
+{
+	if (event->feat.feat_id < HEADER_LAST_FEATURE)
+		return perf_event__process_feature(tool, event, session);
+	return 0;
+}
+
 #ifdef HAVE_AUXTRACE_SUPPORT
 static int perf_script__process_auxtrace_info(struct perf_tool *tool,
 					      union perf_event *event,
@@ -3062,7 +3097,7 @@ int cmd_script(int argc, const char **argv)
 			.attr		 = process_attr,
 			.event_update   = perf_event__process_event_update,
 			.tracing_data	 = perf_event__process_tracing_data,
-			.feature	 = perf_event__process_feature,
+			.feature	 = process_feature_event,
 			.build_id	 = perf_event__process_build_id,
 			.id_index	 = perf_event__process_id_index,
 			.auxtrace_info	 = perf_script__process_auxtrace_info,
@@ -3113,8 +3148,9 @@ int cmd_script(int argc, const char **argv)
 		     "+field to add and -field to remove."
 		     "Valid types: hw,sw,trace,raw,synth. "
 		     "Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso,"
-		     "addr,symoff,period,iregs,uregs,brstack,brstacksym,flags,"
-		     "bpf-output,callindent,insn,insnlen,brstackinsn,synth,phys_addr",
+		     "addr,symoff,srcline,period,iregs,uregs,brstack,"
+		     "brstacksym,flags,bpf-output,brstackinsn,brstackoff,"
+		     "callindent,insn,insnlen,synth,phys_addr,metric,misc",
 		     parse_output_fields),
 	OPT_BOOLEAN('a', "all-cpus", &system_wide,
 		    "system-wide collection from all CPUs"),
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 096ccb25c11f..22547a490e1f 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -65,6 +65,7 @@
 #include "util/tool.h"
 #include "util/string2.h"
 #include "util/metricgroup.h"
+#include "util/top.h"
 #include "asm/bug.h"
 
 #include <linux/time64.h>
@@ -144,6 +145,8 @@ static struct target target = {
 
 typedef int (*aggr_get_id_t)(struct cpu_map *m, int cpu);
 
+#define METRIC_ONLY_LEN 20
+
 static int			run_count			=  1;
 static bool			no_inherit			= false;
 static volatile pid_t		child_pid			= -1;
@@ -173,6 +176,7 @@ static struct cpu_map		*aggr_map;
 static aggr_get_id_t		aggr_get_id;
 static bool			append_file;
 static bool			interval_count;
+static bool			interval_clear;
 static const char		*output_name;
 static int			output_fd;
 static int			print_free_counters_hint;
@@ -180,6 +184,7 @@ static int			print_mixed_hw_group_error;
 static u64			*walltime_run;
 static bool			ru_display			= false;
 static struct rusage		ru_data;
+static unsigned int		metric_only_len			= METRIC_ONLY_LEN;
 
 struct perf_stat {
 	bool			 record;
@@ -967,8 +972,6 @@ static void print_metric_csv(void *ctx,
 	fprintf(out, "%s%s%s%s", csv_sep, vals, csv_sep, unit);
 }
 
-#define METRIC_ONLY_LEN 20
-
 /* Filter out some columns that don't work well in metrics only mode */
 
 static bool valid_only_metric(const char *unit)
@@ -999,22 +1002,20 @@ static void print_metric_only(void *ctx, const char *color, const char *fmt,
 {
 	struct outstate *os = ctx;
 	FILE *out = os->fh;
-	int n;
-	char buf[1024];
-	unsigned mlen = METRIC_ONLY_LEN;
+	char buf[1024], str[1024];
+	unsigned mlen = metric_only_len;
 
 	if (!valid_only_metric(unit))
 		return;
 	unit = fixunit(buf, os->evsel, unit);
-	if (color)
-		n = color_fprintf(out, color, fmt, val);
-	else
-		n = fprintf(out, fmt, val);
-	if (n > METRIC_ONLY_LEN)
-		n = METRIC_ONLY_LEN;
 	if (mlen < strlen(unit))
 		mlen = strlen(unit) + 1;
-	fprintf(out, "%*s", mlen - n, "");
+
+	if (color)
+		mlen += strlen(color) + sizeof(PERF_COLOR_RESET) - 1;
+
+	color_snprintf(str, sizeof(str), color ?: "", fmt, val);
+	fprintf(out, "%*s ", mlen, str);
 }
 
 static void print_metric_only_csv(void *ctx, const char *color __maybe_unused,
@@ -1054,7 +1055,7 @@ static void print_metric_header(void *ctx, const char *color __maybe_unused,
 	if (csv_output)
 		fprintf(os->fh, "%s%s", unit, csv_sep);
 	else
-		fprintf(os->fh, "%-*s ", METRIC_ONLY_LEN, unit);
+		fprintf(os->fh, "%*s ", metric_only_len, unit);
 }
 
 static void nsec_printout(int id, int nr, struct perf_evsel *evsel, double avg)
@@ -1704,9 +1705,12 @@ static void print_interval(char *prefix, struct timespec *ts)
 	FILE *output = stat_config.output;
 	static int num_print_interval;
 
+	if (interval_clear)
+		puts(CONSOLE_CLEAR);
+
 	sprintf(prefix, "%6lu.%09lu%s", ts->tv_sec, ts->tv_nsec, csv_sep);
 
-	if (num_print_interval == 0 && !csv_output) {
+	if ((num_print_interval == 0 && !csv_output) || interval_clear) {
 		switch (stat_config.aggr_mode) {
 		case AGGR_SOCKET:
 			fprintf(o