Merge https://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Signed-off-by: Jakub Kicinski <kuba@kernel.org>

70 files changed, 3105 insertions, 489 deletions

diff --git a/tools/bpf/bpftool/feature.c b/tools/bpf/bpftool/feature.c
index a43a6f10b564..359960a8f1de 100644
--- a/tools/bpf/bpftool/feature.c
+++ b/tools/bpf/bpftool/feature.c
@@ -843,9 +843,14 @@ static int handle_perms(void)
 		else
 			p_err("missing %s%s%s%s%s%s%s%srequired for full feature probing; run as root or use 'unprivileged'",
 			      capability_msg(bpf_caps, 0),
+#ifdef CAP_BPF
 			      capability_msg(bpf_caps, 1),
 			      capability_msg(bpf_caps, 2),
-			      capability_msg(bpf_caps, 3));
+			      capability_msg(bpf_caps, 3)
+#else
+				"", "", "", "", "", ""
+#endif /* CAP_BPF */
+				);
 		goto exit_free;
 	}
 
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index d942c1e3372c..acdb2c245f0a 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -940,7 +940,7 @@ static int parse_attach_detach_args(int argc, char **argv, int *progfd,
 	}
 
 	if (*attach_type == BPF_FLOW_DISSECTOR) {
-		*mapfd = -1;
+		*mapfd = 0;
 		return 0;
 	}
 
diff --git a/tools/bpf/bpftool/skeleton/profiler.bpf.c b/tools/bpf/bpftool/skeleton/profiler.bpf.c
index 4e3512f700c0..ce5b65e07ab1 100644
--- a/tools/bpf/bpftool/skeleton/profiler.bpf.c
+++ b/tools/bpf/bpftool/skeleton/profiler.bpf.c
@@ -70,7 +70,7 @@ int BPF_PROG(fentry_XXX)
 static inline void
 fexit_update_maps(u32 id, struct bpf_perf_event_value *after)
 {
-	struct bpf_perf_event_value *before, diff, *accum;
+	struct bpf_perf_event_value *before, diff;
 
 	before = bpf_map_lookup_elem(&fentry_readings, &id);
 	/* only account samples with a valid fentry_reading */
@@ -95,7 +95,7 @@ int BPF_PROG(fexit_XXX)
 {
 	struct bpf_perf_event_value readings[MAX_NUM_MATRICS];
 	u32 cpu = bpf_get_smp_processor_id();
-	u32 i, one = 1, zero = 0;
+	u32 i, zero = 0;
 	int err;
 	u64 *count;
 
diff --git a/tools/lib/bpf/hashmap.h b/tools/lib/bpf/hashmap.h
index d9b385fe808c..10a4c4cd13cf 100644
--- a/tools/lib/bpf/hashmap.h
+++ b/tools/lib/bpf/hashmap.h
@@ -15,6 +15,9 @@
 static inline size_t hash_bits(size_t h, int bits)
 {
 	/* shuffle bits and return requested number of upper bits */
+	if (bits == 0)
+		return 0;
+
 #if (__SIZEOF_SIZE_T__ == __SIZEOF_LONG_LONG__)
 	/* LP64 case */
 	return (h * 11400714819323198485llu) >> (__SIZEOF_LONG_LONG__ * 8 - bits);
@@ -174,17 +177,17 @@ bool hashmap__find(const struct hashmap *map, const void *key, void **value);
  * @key: key to iterate entries for
  */
 #define hashmap__for_each_key_entry(map, cur, _key)			    \
-	for (cur = ({ size_t bkt = hash_bits(map->hash_fn((_key), map->ctx),\
-					     map->cap_bits);		    \
-		     map->buckets ? map->buckets[bkt] : NULL; });	    \
+	for (cur = map->buckets						    \
+		     ? map->buckets[hash_bits(map->hash_fn((_key), map->ctx), map->cap_bits)] \
+		     : NULL;						    \
 	     cur;							    \
 	     cur = cur->next)						    \
 		if (map->equal_fn(cur->key, (_key), map->ctx))
 
 #define hashmap__for_each_key_entry_safe(map, cur, tmp, _key)		    \
-	for (cur = ({ size_t bkt = hash_bits(map->hash_fn((_key), map->ctx),\
-					     map->cap_bits);		    \
-		     cur = map->buckets ? map->buckets[bkt] : NULL; });	    \
+	for (cur = map->buckets						    \
+		     ? map->buckets[hash_bits(map->hash_fn((_key), map->ctx), map->cap_bits)] \
+		     : NULL;						    \
 	     cur && ({ tmp = cur->next; true; });			    \
 	     cur = tmp)							    \
 		if (map->equal_fn(cur->key, (_key), map->ctx))
diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c
index e3c98c007825..9bc537d0b92d 100644
--- a/tools/lib/bpf/xsk.c
+++ b/tools/lib/bpf/xsk.c
@@ -891,13 +891,16 @@ int xsk_umem__delete(struct xsk_umem *umem)
 void xsk_socket__delete(struct xsk_socket *xsk)
 {
 	size_t desc_sz = sizeof(struct xdp_desc);
-	struct xsk_ctx *ctx = xsk->ctx;
 	struct xdp_mmap_offsets off;
+	struct xsk_umem *umem;
+	struct xsk_ctx *ctx;
 	int err;
 
 	if (!xsk)
 		return;
 
+	ctx = xsk->ctx;
+	umem = ctx->umem;
 	if (ctx->prog_fd != -1) {
 		xsk_delete_bpf_maps(xsk);
 		close(ctx->prog_fd);
@@ -917,11 +920,11 @@ void xsk_socket__delete(struct xsk_socket *xsk)
 
 	xsk_put_ctx(ctx);
 
-	ctx->umem->refcount--;
+	umem->refcount--;
 	/* Do not close an fd that also has an associated umem connected
 	 * to it.
 	 */
-	if (xsk->fd != ctx->umem->fd)
+	if (xsk->fd != umem->fd)
 		close(xsk->fd);
 	free(xsk);
 }
diff --git a/tools/power/x86/turbostat/Makefile b/tools/power/x86/turbostat/Makefile
index 2b6551269e43..f3e3c94ab9bd 100644
--- a/tools/power/x86/turbostat/Makefile
+++ b/tools/power/x86/turbostat/Makefile
@@ -12,11 +12,12 @@ turbostat : turbostat.c
 override CFLAGS +=	-O2 -Wall -I../../../include
 override CFLAGS +=	-DMSRHEADER='"../../../../arch/x86/include/asm/msr-index.h"'
 override CFLAGS +=	-DINTEL_FAMILY_HEADER='"../../../../arch/x86/include/asm/intel-family.h"'
+override CFLAGS +=	-D_FILE_OFFSET_BITS=64
 override CFLAGS +=	-D_FORTIFY_SOURCE=2
 
 %: %.c
 	@mkdir -p $(BUILD_OUTPUT)
-	$(CC) $(CFLAGS) $< -o $(BUILD_OUTPUT)/$@ $(LDFLAGS) -lcap
+	$(CC) $(CFLAGS) $< -o $(BUILD_OUTPUT)/$@ $(LDFLAGS) -lcap -lrt
 
 .PHONY : clean
 clean :
diff --git a/tools/power/x86/turbostat/turbostat.8 b/tools/power/x86/turbostat/turbostat.8
index a6db83a88e85..f6b7e85b121c 100644
--- a/tools/power/x86/turbostat/turbostat.8
+++ b/tools/power/x86/turbostat/turbostat.8
@@ -335,7 +335,7 @@ that they count at TSC rate, which is true on all processors tested to date.
 
 .SH REFERENCES
 Volume 3B: System Programming Guide"
-http://www.intel.com/products/processor/manuals/
+https://www.intel.com/products/processor/manuals/
 
 .SH FILES
 .ta
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 33b370865d16..f3a1746f7f45 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -79,6 +79,7 @@ unsigned long long  gfx_cur_rc6_ms;
 unsigned long long cpuidle_cur_cpu_lpi_us;
 unsigned long long cpuidle_cur_sys_lpi_us;
 unsigned int gfx_cur_mhz;
+unsigned int gfx_act_mhz;
 unsigned int tcc_activation_temp;
 unsigned int tcc_activation_temp_override;
 double rapl_power_units, rapl_time_units;
@@ -210,13 +211,14 @@ struct pkg_data {
 	unsigned long long pkg_both_core_gfxe_c0;
 	long long gfx_rc6_ms;
 	unsigned int gfx_mhz;
+	unsigned int gfx_act_mhz;
 	unsigned int package_id;
-	unsigned int energy_pkg;	/* MSR_PKG_ENERGY_STATUS */
-	unsigned int energy_dram;	/* MSR_DRAM_ENERGY_STATUS */
-	unsigned int energy_cores;	/* MSR_PP0_ENERGY_STATUS */
-	unsigned int energy_gfx;	/* MSR_PP1_ENERGY_STATUS */
-	unsigned int rapl_pkg_perf_status;	/* MSR_PKG_PERF_STATUS */
-	unsigned int rapl_dram_perf_status;	/* MSR_DRAM_PERF_STATUS */
+	unsigned long long energy_pkg;	/* MSR_PKG_ENERGY_STATUS */
+	unsigned long long energy_dram;	/* MSR_DRAM_ENERGY_STATUS */
+	unsigned long long energy_cores;	/* MSR_PP0_ENERGY_STATUS */
+	unsigned long long energy_gfx;	/* MSR_PP1_ENERGY_STATUS */
+	unsigned long long rapl_pkg_perf_status;	/* MSR_PKG_PERF_STATUS */
+	unsigned long long rapl_dram_perf_status;	/* MSR_DRAM_PERF_STATUS */
 	unsigned int pkg_temp_c;
 	unsigned long long counter[MAX_ADDED_COUNTERS];
 } *package_even, *package_odd;
@@ -259,6 +261,113 @@ struct msr_counter {
 #define	SYSFS_PERCPU	(1 << 1)
 };
 
+/*
+ * The accumulated sum of MSR is defined as a monotonic
+ * increasing MSR, it will be accumulated periodically,
+ * despite its register's bit width.
+ */
+enum {
+	IDX_PKG_ENERGY,
+	IDX_DRAM_ENERGY,
+	IDX_PP0_ENERGY,
+	IDX_PP1_ENERGY,
+	IDX_PKG_PERF,
+	IDX_DRAM_PERF,
+	IDX_COUNT,
+};
+
+int get_msr_sum(int cpu, off_t offset, unsigned long long *msr);
+
+struct msr_sum_array {
+	/* get_msr_sum() = sum + (get_msr() - last) */
+	struct {
+		/*The accumulated MSR value is updated by the timer*/
+		unsigned long long sum;
+		/*The MSR footprint recorded in last timer*/
+		unsigned long long last;
+	} entries[IDX_COUNT];
+};
+
+/* The percpu MSR sum array.*/
+struct msr_sum_array *per_cpu_msr_sum;
+
+int idx_to_offset(int idx)
+{
+	int offset;
+
+	switch (idx) {
+	case IDX_PKG_ENERGY:
+		offset = MSR_PKG_ENERGY_STATUS;
+		break;
+	case IDX_DRAM_ENERGY:
+		offset = MSR_DRAM_ENERGY_STATUS;
+		break;
+	case IDX_PP0_ENERGY:
+		offset = MSR_PP0_ENERGY_STATUS;
+		break;
+	case IDX_PP1_ENERGY:
+		offset = MSR_PP1_ENERGY_STATUS;
+		break;
+	case IDX_PKG_PERF:
+		offset = MSR_PKG_PERF_STATUS;
+		break;
+	case IDX_DRAM_PERF:
+		offset = MSR_DRAM_PERF_STATUS;
+		break;
+	default:
+		offset = -1;
+	}
+	return offset;
+}
+
+int offset_to_idx(int offset)
+{
+	int idx;
+
+	switch (offset) {
+	case MSR_PKG_ENERGY_STATUS:
+		idx = IDX_PKG_ENERGY;
+		break;
+	case MSR_DRAM_ENERGY_STATUS:
+		idx = IDX_DRAM_ENERGY;
+		break;
+	case MSR_PP0_ENERGY_STATUS:
+		idx = IDX_PP0_ENERGY;
+		break;
+	case MSR_PP1_ENERGY_STATUS:
+		idx = IDX_PP1_ENERGY;
+		break;
+	case MSR_PKG_PERF_STATUS:
+		idx = IDX_PKG_PERF;
+		break;
+	case MSR_DRAM_PERF_STATUS:
+		idx = IDX_DRAM_PERF;
+		break;
+	default:
+		idx = -1;
+	}
+	return idx;
+}
+
+int idx_valid(int idx)
+{
+	switch (idx) {
+	case IDX_PKG_ENERGY:
+		return do_rapl & RAPL_PKG;
+	case IDX_DRAM_ENERGY:
+		return do_rapl & RAPL_DRAM;
+	case IDX_PP0_ENERGY:
+		return do_rapl & RAPL_CORES_ENERGY_STATUS;
+	case IDX_PP1_ENERGY:
+		return do_rapl & RAPL_GFX;
+	case IDX_PKG_PERF:
+		return do_rapl & RAPL_PKG_PERF_STATUS;
+	case IDX_DRAM_PERF:
+		return do_rapl & RAPL_DRAM_PERF_STATUS;
+	default:
+		return 0;
+	}
+}
 struct sys_counters {
 	unsigned int added_thread_counters;
 	unsigned int added_core_counters;
@@ -451,6 +560,7 @@ struct msr_counter bic[] = {
 	{ 0x0, "APIC" },
 	{ 0x0, "X2APIC" },
 	{ 0x0, "Die" },
+	{ 0x0, "GFXAMHz" },
 };
 
 #define MAX_BIC (sizeof(bic) / sizeof(struct msr_counter))
@@ -505,6 +615,7 @@ struct msr_counter bic[] = {
 #define	BIC_APIC	(1ULL << 48)
 #define	BIC_X2APIC	(1ULL << 49)
 #define	BIC_Die		(1ULL << 50)
+#define	BIC_GFXACTMHz	(1ULL << 51)
 
 #define BIC_DISABLED_BY_DEFAULT	(BIC_USEC | BIC_TOD | BIC_APIC | BIC_X2APIC)
 
@@ -724,6 +835,9 @@ void print_header(char *delim)
 	if (DO_BIC(BIC_GFXMHz))
 		outp += sprintf(outp, "%sGFXMHz", (printed++ ? delim : ""));
 
+	if (DO_BIC(BIC_GFXACTMHz))
+		outp += sprintf(outp, "%sGFXAMHz", (printed++ ? delim : ""));
+
 	if (DO_BIC(BIC_Totl_c0))
 		outp += sprintf(outp, "%sTotl%%C0", (printed++ ? delim : ""));
 	if (DO_BIC(BIC_Any_c0))
@@ -858,13 +972,13 @@ int dump_counters(struct thread_data *t, struct core_data *c,
 		outp += sprintf(outp, "pc10: %016llX\n", p->pc10);
 		outp += sprintf(outp, "cpu_lpi: %016llX\n", p->cpu_lpi);
 		outp += sprintf(outp, "sys_lpi: %016llX\n", p->sys_lpi);
-		outp += sprintf(outp, "Joules PKG: %0X\n", p->energy_pkg);
-		outp += sprintf(outp, "Joules COR: %0X\n", p->energy_cores);
-		outp += sprintf(outp, "Joules GFX: %0X\n", p->energy_gfx);
-		outp += sprintf(outp, "Joules RAM: %0X\n", p->energy_dram);
-		outp += sprintf(outp, "Throttle PKG: %0X\n",
+		outp += sprintf(outp, "Joules PKG: %0llX\n", p->energy_pkg);
+		outp += sprintf(outp, "Joules COR: %0llX\n", p->energy_cores);
+		outp += sprintf(outp, "Joules GFX: %0llX\n", p->energy_gfx);
+		outp += sprintf(outp, "Joules RAM: %0llX\n", p->energy_dram);
+		outp += sprintf(outp, "Throttle PKG: %0llX\n",
 			p->rapl_pkg_perf_status);
-		outp += sprintf(outp, "Throttle RAM: %0X\n",
+		outp += sprintf(outp, "Throttle RAM: %0llX\n",
 			p->rapl_dram_perf_status);
 		outp += sprintf(outp, "PTM: %dC\n", p->pkg_temp_c);
 
@@ -1062,14 +1176,7 @@ int format_counters(struct thread_data *t, struct core_data *c,
 		}
 	}
 
-	/*
-	 * If measurement interval exceeds minimum RAPL Joule Counter range,
-	 * indicate that results are suspect by printing "**" in fraction place.
-	 */
-	if (interval_float < rapl_joule_counter_range)
-		fmt8 = "%s%.2f";
-	else
-		fmt8 = "%6.0f**";
+	fmt8 = "%s%.2f";
 
 	if (DO_BIC(BIC_CorWatt) && (do_rapl & RAPL_PER_CORE_ENERGY))
 		outp += sprintf(outp, fmt8, (printed++ ? delim : ""), c->core_energy * rapl_energy_units / interval_float);
@@ -1098,6 +1205,10 @@ int format_counters(struct thread_data *t, struct core_data *c,
 	if (DO_BIC(BIC_GFXMHz))
 		outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), p->gfx_mhz);
 
+	/* GFXACTMHz */
+	if (DO_BIC(BIC_GFXACTMHz))
+		outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), p->gfx_act_mhz);
+
 	/* Totl%C0, Any%C0 GFX%C0 CPUGFX% */
 	if (DO_BIC(BIC_Totl_c0))
 		outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->pkg_wtd_core_c0/tsc);
@@ -1210,11 +1321,7 @@ void format_all_counters(struct thread_data *t, struct core_data *c, struct pkg_
 }
 
 #define DELTA_WRAP32(new, old)			\
-	if (new > old) {			\
-		old = new - old;		\
-	} else {				\
-		old = 0x100000000 + new - old;	\
-	}
+	old = ((((unsigned long long)new << 32) - ((unsigned long long)old << 32)) >> 32);
 
 int
 delta_package(struct pkg_data *new, struct pkg_data *old)
@@ -1253,13 +1360,14 @@ delta_package(struct pkg_data *new, struct pkg_data *old)
 		old->gfx_rc6_ms = new->gfx_rc6_ms - old->gfx_rc6_ms;
 
 	old->gfx_mhz = new->gfx_mhz;
+	old->gfx_act_mhz = new->gfx_act_mhz;
 
-	DELTA_WRAP32(new->energy_pkg, old->energy_pkg);
-	DELTA_WRAP32(new->energy_cores, old->energy_cores);
-	DELTA_WRAP32(new->energy_gfx, old->energy_gfx);
-	DELTA_WRAP32(new->energy_dram, old->energy_dram);
-	DELTA_WRAP32(new->rapl_pkg_perf_status, old->rapl_pkg_perf_status);
-	DELTA_WRAP32(new->rapl_dram_perf_status, old->rapl_dram_perf_status);
+	old->energy_pkg = new->energy_pkg - old->energy_pkg;
+	old->energy_cores = new->energy_cores - old->energy_cores;
+	old->energy_gfx = new->energy_gfx - old->energy_gfx;
+	old->energy_dram = new->energy_dram - old->energy_dram;
+	old->rapl_pkg_perf_status = new->rapl_pkg_perf_status - old->rapl_pkg_perf_status;
+	old->rapl_dram_perf_status = new->rapl_dram_perf_status - old->rapl_dram_perf_status;
 
 	for (i = 0, mp = sys.pp; mp; i++, mp = mp->next) {
 		if (mp->format == FORMAT_RAW)
@@ -1469,6 +1577,7 @@ void clear_counters(struct thread_data *t, struct core_data *c, struct pkg_data
 
 	p->gfx_rc6_ms = 0;
 	p->gfx_mhz = 0;
+	p->gfx_act_mhz = 0;
 	for (i = 0, mp = sys.tp; mp; i++, mp = mp->next)
 		t->counter[i] = 0;
 
@@ -1564,6 +1673,7 @@ int sum_counters(struct thread_data *t, struct core_data *c,
 
 	average.packages.gfx_rc6_ms = p->gfx_rc6_ms;
 	average.packages.gfx_mhz =