21 files changed, 1359 insertions, 32 deletions

diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 0a22407e1d7d..5d34815c7ccb 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -77,6 +77,9 @@ include config/utilities.mak
 # Define NO_AUXTRACE if you do not want AUX area tracing support
 #
 # Define NO_LIBBPF if you do not want BPF support
+#
+# Define FEATURES_DUMP to provide features detection dump file
+# and bypass the feature detection
 
 # As per kernel Makefile, avoid funny character set dependencies
 unexport LC_ALL
@@ -166,6 +169,15 @@ ifeq ($(config),1)
 include config/Makefile
 endif
 
+# The FEATURE_DUMP_EXPORT holds location of the actual
+# FEATURE_DUMP file to be used to bypass feature detection
+# (for bpf or any other subproject)
+ifeq ($(FEATURES_DUMP),)
+FEATURE_DUMP_EXPORT := $(realpath $(OUTPUT)FEATURE-DUMP)
+else
+FEATURE_DUMP_EXPORT := $(FEATURES_DUMP)
+endif
+
 export prefix bindir sharedir sysconfdir DESTDIR
 
 # sparse is architecture-neutral, which means that we need to tell it
@@ -436,7 +448,7 @@ $(LIBAPI)-clean:
 	$(Q)$(MAKE) -C $(LIB_DIR) O=$(OUTPUT) clean >/dev/null
 
 $(LIBBPF): fixdep FORCE
-	$(Q)$(MAKE) -C $(BPF_DIR) O=$(OUTPUT) $(OUTPUT)libbpf.a FEATURES_DUMP=$(realpath $(OUTPUT)FEATURE-DUMP)
+	$(Q)$(MAKE) -C $(BPF_DIR) O=$(OUTPUT) $(OUTPUT)libbpf.a FEATURES_DUMP=$(FEATURE_DUMP_EXPORT)
 
 $(LIBBPF)-clean:
 	$(call QUIET_CLEAN, libbpf)
@@ -611,6 +623,17 @@ clean: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clean
 	$(python-clean)
 
 #
+# To provide FEATURE-DUMP into $(FEATURE_DUMP_COPY)
+# file if defined, with no further action.
+feature-dump:
+ifdef FEATURE_DUMP_COPY
+	@cp $(OUTPUT)FEATURE-DUMP $(FEATURE_DUMP_COPY)
+	@echo "FEATURE-DUMP file copied into $(FEATURE_DUMP_COPY)"
+else
+	@echo "FEATURE-DUMP file available in $(OUTPUT)FEATURE-DUMP"
+endif
+
+#
 # Trick: if ../../.git does not exist - we are building out of tree for example,
 # then force version regeneration:
 #
diff --git a/tools/perf/arch/x86/tests/intel-cqm.c b/tools/perf/arch/x86/tests/intel-cqm.c
index 3e89ba825f6b..7f064eb37158 100644
--- a/tools/perf/arch/x86/tests/intel-cqm.c
+++ b/tools/perf/arch/x86/tests/intel-cqm.c
@@ -17,7 +17,7 @@ static pid_t spawn(void)
 	if (pid)
 		return pid;
 
-	while(1);
+	while(1)
 		sleep(5);
 	return 0;
 }
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index e5959c136a19..511141b102e8 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -181,7 +181,11 @@ LDFLAGS += -Wl,-z,noexecstack
 
 EXTLIBS = -lpthread -lrt -lm -ldl
 
+ifeq ($(FEATURES_DUMP),)
 include $(srctree)/tools/build/Makefile.feature
+else
+include $(FEATURES_DUMP)
+endif
 
 ifeq ($(feature-stackprotector-all), 1)
   CFLAGS += -fstack-protector-all
diff --git a/tools/perf/tests/make b/tools/perf/tests/make
index df38decc48c3..f918015512af 100644
--- a/tools/perf/tests/make
+++ b/tools/perf/tests/make
@@ -5,7 +5,7 @@ ifeq ($(MAKECMDGOALS),)
 # no target specified, trigger the whole suite
 all:
 	@echo "Testing Makefile";      $(MAKE) -sf tests/make MK=Makefile
-	@echo "Testing Makefile.perf"; $(MAKE) -sf tests/make MK=Makefile.perf
+	@echo "Testing Makefile.perf"; $(MAKE) -sf tests/make MK=Makefile.perf SET_PARALLEL=1 SET_O=1
 else
 # run only specific test over 'Makefile'
 %:
@@ -13,6 +13,26 @@ else
 endif
 else
 PERF := .
+PERF_O := $(PERF)
+O_OPT :=
+
+ifneq ($(O),)
+  FULL_O := $(shell readlink -f $(O) || echo $(O))
+  PERF_O := $(FULL_O)
+  ifeq ($(SET_O),1)
+    O_OPT := 'O=$(FULL_O)'
+  endif
+  K_O_OPT := 'O=$(FULL_O)'
+endif
+
+PARALLEL_OPT=
+ifeq ($(SET_PARALLEL),1)
+  cores := $(shell (getconf _NPROCESSORS_ONLN || egrep -c '^processor|^CPU[0-9]' /proc/cpuinfo) 2>/dev/null)
+  ifeq ($(cores),0)
+    cores := 1
+  endif
+  PARALLEL_OPT="-j$(cores)"
+endif
 
 # As per kernel Makefile, avoid funny character set dependencies
 unexport LC_ALL
@@ -156,11 +176,11 @@ test_make_doc    := $(test_ok)
 test_make_help_O := $(test_ok)
 test_make_doc_O  := $(test_ok)
 
-test_make_python_perf_so := test -f $(PERF)/python/perf.so
+test_make_python_perf_so := test -f $(PERF_O)/python/perf.so
 
-test_make_perf_o           := test -f $(PERF)/perf.o
-test_make_util_map_o       := test -f $(PERF)/util/map.o
-test_make_util_pmu_bison_o := test -f $(PERF)/util/pmu-bison.o
+test_make_perf_o           := test -f $(PERF_O)/perf.o
+test_make_util_map_o       := test -f $(PERF_O)/util/map.o
+test_make_util_pmu_bison_o := test -f $(PERF_O)/util/pmu-bison.o
 
 define test_dest_files
   for file in $(1); do				\
@@ -227,7 +247,7 @@ test_make_perf_o_O            := test -f $$TMP_O/perf.o
 test_make_util_map_o_O        := test -f $$TMP_O/util/map.o
 test_make_util_pmu_bison_o_O := test -f $$TMP_O/util/pmu-bison.o
 
-test_default = test -x $(PERF)/perf
+test_default = test -x $(PERF_O)/perf
 test = $(if $(test_$1),$(test_$1),$(test_default))
 
 test_default_O = test -x $$TMP_O/perf
@@ -247,12 +267,12 @@ endif
 
 MAKEFLAGS := --no-print-directory
 
-clean := @(cd $(PERF); make -s -f $(MK) clean >/dev/null)
+clean := @(cd $(PERF); make -s -f $(MK) $(O_OPT) clean >/dev/null)
 
 $(run):
 	$(call clean)
 	@TMP_DEST=$$(mktemp -d); \
-	cmd="cd $(PERF) && make -f $(MK) DESTDIR=$$TMP_DEST $($@)"; \
+	cmd="cd $(PERF) && make -f $(MK) $(PARALLEL_OPT) $(O_OPT) DESTDIR=$$TMP_DEST $($@)"; \
 	echo "- $@: $$cmd" && echo $$cmd > $@ && \
 	( eval $$cmd ) >> $@ 2>&1; \
 	echo "  test: $(call test,$@)" >> $@ 2>&1; \
@@ -263,7 +283,7 @@ $(run_O):
 	$(call clean)
 	@TMP_O=$$(mktemp -d); \
 	TMP_DEST=$$(mktemp -d); \
-	cmd="cd $(PERF) && make -f $(MK) O=$$TMP_O DESTDIR=$$TMP_DEST $($(patsubst %_O,%,$@))"; \
+	cmd="cd $(PERF) && make -f $(MK) $(PARALLEL_OPT) O=$$TMP_O DESTDIR=$$TMP_DEST $($(patsubst %_O,%,$@))"; \
 	echo "- $@: $$cmd" && echo $$cmd > $@ && \
 	( eval $$cmd ) >> $@ 2>&1 && \
 	echo "  test: $(call test_O,$@)" >> $@ 2>&1; \
@@ -276,17 +296,22 @@ tarpkg:
 	( eval $$cmd ) >> $@ 2>&1 && \
 	rm -f $@
 
+KERNEL_O := ../..
+ifneq ($(O),)
+  KERNEL_O := $(O)
+endif
+
 make_kernelsrc:
-	@echo "- make -C <kernelsrc> tools/perf"
+	@echo "- make -C <kernelsrc> $(PARALLEL_OPT) $(K_O_OPT) tools/perf"
 	$(call clean); \
-	(make -C ../.. tools/perf) > $@ 2>&1 && \
-	test -x perf && rm -f $@ || (cat $@ ; false)
+	(make -C ../.. $(PARALLEL_OPT) $(K_O_OPT) tools/perf) > $@ 2>&1 && \
+	test -x $(KERNEL_O)/tools/perf/perf && rm -f $@ || (cat $@ ; false)
 
 make_kernelsrc_tools:
-	@echo "- make -C <kernelsrc>/tools perf"
+	@echo "- make -C <kernelsrc>/tools $(PARALLEL_OPT) $(K_O_OPT) perf"
 	$(call clean); \
-	(make -C ../../tools perf) > $@ 2>&1 && \
-	test -x perf && rm -f $@ || (cat $@ ; false)
+	(make -C ../../tools $(PARALLEL_OPT) $(K_O_OPT) perf) > $@ 2>&1 && \
+	test -x $(KERNEL_O)/tools/perf/perf && rm -f $@ || (cat $@ ; false)
 
 all: $(run) $(run_O) tarpkg make_kernelsrc make_kernelsrc_tools
 	@echo OK
diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index d4d7cc27252f..718bd46d47fa 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -755,11 +755,11 @@ static int annotate_browser__run(struct annotate_browser *browser,
 				nd = browser->curr_hot;
 			break;
 		case K_UNTAB:
-			if (nd != NULL)
+			if (nd != NULL) {
 				nd = rb_next(nd);
 				if (nd == NULL)
 					nd = rb_first(&browser->entries);
-			else
+			} else
 				nd = browser->curr_hot;
 			break;
 		case K_F1:
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index c226303e3da0..68a7612019dc 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -131,6 +131,8 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
 			symlen = unresolved_col_width + 4 + 2;
 			hists__new_col_len(hists, HISTC_MEM_DADDR_SYMBOL,
 					   symlen);
+			hists__new_col_len(hists, HISTC_MEM_DCACHELINE,
+					   symlen);
 		}
 
 		if (h->mem_info->iaddr.sym) {
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index d5636ba94b20..40b7a0d0905b 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1149,7 +1149,7 @@ static struct machine *machines__find_for_cpumode(struct machines *machines,
 
 		machine = machines__find(machines, pid);
 		if (!machine)
-			machine = machines__find(machines, DEFAULT_GUEST_KERNEL_ID);
+			machine = machines__findnew(machines, DEFAULT_GUEST_KERNEL_ID);
 		return machine;
 	}
 
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index 2f901d15e063..2b58edccd56f 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -310,7 +310,6 @@ int perf_stat_process_counter(struct perf_stat_config *config,
 	int i, ret;
 
 	aggr->val = aggr->ena = aggr->run = 0;
-	init_stats(ps->res_stats);
 
 	if (counter->per_pkg)
 		zero_per_pkg(counter);
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 3b2de6eb3376..ab02209a7cf3 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1466,7 +1466,7 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter)
 	 * Read the build id if possible. This is required for
 	 * DSO_BINARY_TYPE__BUILDID_DEBUGINFO to work
 	 */
-	if (filename__read_build_id(dso->name, build_id, BUILD_ID_SIZE) > 0)
+	if (filename__read_build_id(dso->long_name, build_id, BUILD_ID_SIZE) > 0)
 		dso__set_build_id(dso, build_id);
 
 	/*
diff --git a/tools/testing/selftests/timers/valid-adjtimex.c b/tools/testing/selftests/timers/valid-adjtimex.c
index e86d937cc22c..60fe3c569bd9 100644
--- a/tools/testing/selftests/timers/valid-adjtimex.c
+++ b/tools/testing/selftests/timers/valid-adjtimex.c
@@ -45,7 +45,17 @@ static inline int ksft_exit_fail(void)
 }
 #endif
 
-#define NSEC_PER_SEC 1000000000L
+#define NSEC_PER_SEC 1000000000LL
+#define USEC_PER_SEC 1000000LL
+
+#define ADJ_SETOFFSET 0x0100
+
+#include <sys/syscall.h>
+static int clock_adjtime(clockid_t id, struct timex *tx)
+{
+	return syscall(__NR_clock_adjtime, id, tx);
+}
+
 
 /* clear NTP time_status & time_state */
 int clear_time_state(void)
@@ -193,10 +203,137 @@ out:
 }
 
 
+int set_offset(long long offset, int use_nano)
+{
+	struct timex tmx = {};
+	int ret;
+
+	tmx.modes = ADJ_SETOFFSET;
+	if (use_nano) {
+		tmx.modes |= ADJ_NANO;
+
+		tmx.time.tv_sec = offset / NSEC_PER_SEC;
+		tmx.time.tv_usec = offset % NSEC_PER_SEC;
+
+		if (offset < 0 && tmx.time.tv_usec) {
+			tmx.time.tv_sec -= 1;
+			tmx.time.tv_usec += NSEC_PER_SEC;
+		}
+	} else {
+		tmx.time.tv_sec = offset / USEC_PER_SEC;
+		tmx.time.tv_usec = offset % USEC_PER_SEC;
+
+		if (offset < 0 && tmx.time.tv_usec) {
+			tmx.time.tv_sec -= 1;
+			tmx.time.tv_usec += USEC_PER_SEC;
+		}
+	}
+
+	ret = clock_adjtime(CLOCK_REALTIME, &tmx);
+	if (ret < 0) {
+		printf("(sec: %ld  usec: %ld) ", tmx.time.tv_sec, tmx.time.tv_usec);
+		printf("[FAIL]\n");
+		return -1;
+	}
+	return 0;
+}
+
+int set_bad_offset(long sec, long usec, int use_nano)
+{
+	struct timex tmx = {};
+	int ret;
+
+	tmx.modes = ADJ_SETOFFSET;
+	if (use_nano)
+		tmx.modes |= ADJ_NANO;
+
+	tmx.time.tv_sec = sec;
+	tmx.time.tv_usec = usec;
+	ret = clock_adjtime(CLOCK_REALTIME, &tmx);
+	if (ret >= 0) {
+		printf("Invalid (sec: %ld  usec: %ld) did not fail! ", tmx.time.tv_sec, tmx.time.tv_usec);
+		printf("[FAIL]\n");
+		return -1;
+	}
+	return 0;
+}
+
+int validate_set_offset(void)
+{
+	printf("Testing ADJ_SETOFFSET... ");
+
+	/* Test valid values */
+	if (set_offset(NSEC_PER_SEC - 1, 1))
+		return -1;
+
+	if (set_offset(-NSEC_PER_SEC + 1, 1))
+		return -1;
+
+	if (set_offset(-NSEC_PER_SEC - 1, 1))
+		return -1;
+
+	if (set_offset(5 * NSEC_PER_SEC, 1))
+		return -1;
+
+	if (set_offset(-5 * NSEC_PER_SEC, 1))
+		return -1;
+
+	if (set_offset(5 * NSEC_PER_SEC + NSEC_PER_SEC / 2, 1))
+		return -1;
+
+	if (set_offset(-5 * NSEC_PER_SEC - NSEC_PER_SEC / 2, 1))
+		return -1;
+
+	if (set_offset(USEC_PER_SEC - 1, 0))
+		return -1;
+
+	if (set_offset(-USEC_PER_SEC + 1, 0))
+		return -1;
+
+	if (set_offset(-USEC_PER_SEC - 1, 0))
+		return -1;
+
+	if (set_offset(5 * USEC_PER_SEC, 0))
+		return -1;
+
+	if (set_offset(-5 * USEC_PER_SEC, 0))
+		return -1;
+
+	if (set_offset(5 * USEC_PER_SEC + USEC_PER_SEC / 2, 0))
+		return -1;
+
+	if (set_offset(-5 * USEC_PER_SEC - USEC_PER_SEC / 2, 0))
+		return -1;
+
+	/* Test invalid values */
+	if (set_bad_offset(0, -1, 1))
+		return -1;
+	if (set_bad_offset(0, -1, 0))
+		return -1;
+	if (set_bad_offset(0, 2 * NSEC_PER_SEC, 1))
+		return -1;
+	if (set_bad_offset(0, 2 * USEC_PER_SEC, 0))
+		return -1;
+	if (set_bad_offset(0, NSEC_PER_SEC, 1))
+		return -1;
+	if (set_bad_offset(0, USEC_PER_SEC, 0))
+		return -1;
+	if (set_bad_offset(0, -NSEC_PER_SEC, 1))
+		return -1;
+	if (set_bad_offset(0, -USEC_PER_SEC, 0))
+		return -1;
+
+	printf("[OK]\n");
+	return 0;
+}
+
 int main(int argc, char **argv)
 {
 	if (validate_freq())
 		return ksft_exit_fail();
 
+	if (validate_set_offset())
+		return ksft_exit_fail();
+
 	return ksft_exit_pass();
 }
diff --git a/tools/virtio/asm/barrier.h b/tools/virtio/asm/barrier.h
index 26b7926bda88..ba34f9e96efd 100644
--- a/tools/virtio/asm/barrier.h
+++ b/tools/virtio/asm/barrier.h
@@ -1,15 +1,19 @@
 #if defined(__i386__) || defined(__x86_64__)
 #define barrier() asm volatile("" ::: "memory")
-#define mb() __sync_synchronize()
-
-#define smp_mb()	mb()
-# define dma_rmb()	barrier()
-# define dma_wmb()	barrier()
-# define smp_rmb()	barrier()
-# define smp_wmb()	barrier()
+#define virt_mb() __sync_synchronize()
+#define virt_rmb() barrier()
+#define virt_wmb() barrier()
+/* Atomic store should be enough, but gcc generates worse code in that case. */
+#define virt_store_mb(var, value)  do { \
+	typeof(var) virt_store_mb_value = (value); \
+	__atomic_exchange(&(var), &virt_store_mb_value, &virt_store_mb_value, \
+			  __ATOMIC_SEQ_CST); \
+	barrier(); \
+} while (0);
 /* Weak barriers should be used. If not - it's a bug */
-# define rmb()	abort()
-# define wmb()	abort()
+# define mb() abort()
+# define rmb() abort()
+# define wmb() abort()
 #else
 #error Please fill in barrier macros
 #endif
diff --git a/tools/virtio/linux/compiler.h b/tools/virtio/linux/compiler.h
new file mode 100644
index 000000000000..845960e1cbf2
--- /dev/null
+++ b/tools/virtio/linux/compiler.h
@@ -0,0 +1,9 @@
+#ifndef LINUX_COMPILER_H
+#define LINUX_COMPILER_H
+
+#define WRITE_ONCE(var, val) \
+	(*((volatile typeof(val) *)(&(var))) = (val))
+
+#define READ_ONCE(var) (*((volatile typeof(val) *)(&(var))))
+
+#endif
diff --git a/tools/virtio/linux/kernel.h b/tools/virtio/linux/kernel.h
index 4db7d5691ba7..033849948215 100644
--- a/tools/virtio/linux/kernel.h
+++ b/tools/virtio/linux/kernel.h
@@ -8,6 +8,7 @@
 #include <assert.h>
 #include <stdarg.h>
 
+#include <linux/compiler.h>
 #include <linux/types.h>
 #include <linux/printk.h>
 #include <linux/bug.h>
diff --git a/tools/virtio/ringtest/Makefile b/tools/virtio/ringtest/Makefile
new file mode 100644
index 000000000000..feaa64ac4630
--- /dev/null
+++ b/tools/virtio/ringtest/Makefile
@@ -0,0 +1,22 @@
+all:
+
+all: ring virtio_ring_0_9 virtio_ring_poll
+
+CFLAGS += -Wall
+CFLAGS += -pthread -O2 -ggdb
+LDFLAGS += -pthread -O2 -ggdb
+
+main.o: main.c main.h
+ring.o: ring.c main.h
+virtio_ring_0_9.o: virtio_ring_0_9.c main.h
+virtio_ring_poll.o: virtio_ring_poll.c virtio_ring_0_9.c main.h
+ring: ring.o main.o
+virtio_ring_0_9: virtio_ring_0_9.o main.o
+virtio_ring_poll: virtio_ring_poll.o main.o
+clean:
+	-rm main.o
+	-rm ring.o ring
+	-rm virtio_ring_0_9.o virtio_ring_0_9
+	-rm virtio_ring_poll.o virtio_ring_poll
+
+.PHONY: all clean
diff --git a/tools/virtio/ringtest/README b/tools/virtio/ringtest/README
new file mode 100644
index 000000000000..34e94c46104f
--- /dev/null
+++ b/tools/virtio/ringtest/README
@@ -0,0 +1,2 @@
+Partial implementation of various ring layouts, useful to tune virtio design.
+Uses shared memory heavily.
diff --git a/tools/virtio/ringtest/main.c b/tools/virtio/ringtest/main.c
new file mode 100644
index 000000000000..3a5ff438bd62
--- /dev/null
+++ b/tools/virtio/ringtest/main.c
@@ -0,0 +1,366 @@
+/*
+ * Copyright (C) 2016 Red Hat, Inc.
+ * Author: Michael S. Tsirkin <mst@redhat.com>
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ *
+ * Command line processing and common functions for ring benchmarking.
+ */
+#define _GNU_SOURCE
+#include <getopt.h>
+#include <pthread.h>
+#include <assert.h>
+#include <sched.h>
+#include "main.h"
+#include <sys/eventfd.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <unistd.h>
+#include <limits.h>
+
+int runcycles = 10000000;
+int max_outstanding = INT_MAX;
+int batch = 1;
+
+bool do_sleep = false;
+bool do_relax = false;
+bool do_exit = true;
+
+unsigned ring_size = 256;
+
+static int kickfd = -1;
+static int callfd = -1;
+
+void notify(int fd)
+{
+	unsigned long long v = 1;
+	int r;
+
+	vmexit();
+	r = write(fd, &v, sizeof v);
+	assert(r == sizeof v);
+	vmentry();
+}
+
+void wait_for_notify(int fd)
+{
+	unsigned long long v = 1;
+	int r;
+
+	vmexit();
+	r = read(fd, &v, sizeof v);
+	assert(r == sizeof v);
+	vmentry();
+}
+
+void kick(void)
+{
+	notify(kickfd);
+}
+
+void wait_for_kick(void)
+{
+	wait_for_notify(kickfd);
+}
+
+void call(void)
+{
+	notify(callfd);
+}
+
+void wait_for_call(void)
+{
+	wait_for_notify(callfd);
+}
+
+void set_affinity(const char *arg)
+{
+	cpu_set_t cpuset;
+	int ret;
+	pthread_t self;
+	long int cpu;
+	char *endptr;
+
+	if (!arg)
+		return;
+
+	cpu = strtol(arg, &endptr, 0);
+	assert(!*endptr);
+
+	assert(cpu >= 0 || cpu < CPU_SETSIZE);
+
+	self = pthread_self();
+	CPU_ZERO(&cpuset);
+	CPU_SET(cpu, &cpuset);
+
+	ret = pthread_setaffinity_np(self, sizeof(cpu_set_t), &cpuset);
+	assert(!ret);
+}
+
+static void run_guest(void)
+{
+	int completed_before;
+	int completed = 0;
+	int started = 0;
+	int bufs = runcycles;
+	int spurious = 0;
+	int r;
+	unsigned len;
+	void *buf;
+	int tokick = batch;
+
+	for (;;) {
+		if (do_sleep)
+			disable_call();
+		completed_before = completed;
+		do {
+			if (started < bufs &&
+			    started - completed < max_outstanding) {
+				r = add_inbuf(0, NULL, "Hello, world!");
+				if (__builtin_expect(r == 0, true)) {
+					++started;
+					if (!--tokick) {
+						tokick = batch;
+						if (do_sleep)
+							kick_available();
+					}
+
+				}
+			} else
+				r = -1;
+
+			/* Flush out completed bufs if any */
+			if (get_buf(&len, &buf)) {
+				++completed;
+				if (__builtin_expect(completed == bufs, false))
+					return;
+				r = 0;
+			}
+		} while (r == 0);
+		if (completed == completed_before)
+			++spurious;
+		assert(completed <= bufs);
+		assert(started <= bufs);
+		if (do_sleep) {
+			if (enable_call())
+				wait_for_call();
+		} else {
+			poll_used();
+		}
+	}
+}
+
+static void run_host(void)
+{
+	int completed_before;
+	int completed = 0;
+	int spurious = 0;
+	int bufs = runcycles;
+	unsigned len;
+	void *buf;
+
+	for (;;) {
+		if (do_sleep) {
+			if (enable_kick())
+				wait_for_kick();
+		} else {
+			poll_avail();
+		}
+		if (do_sleep)
+			disable_kick();
+		completed_before = completed;
+		while (__builtin_expect(use_buf(&len, &buf), true)) {
+			if (do_sleep)
+				call_used();
+			++completed;
+			if (__builtin_expect(completed == bufs, false))
+				return;
+		}
+		if (completed == completed_before)
+			++spurious;
+		assert(completed <= bufs);
+		if (completed == bufs)
+			break;
+	}
+}
+
+void *start_guest(void *arg)
+{
+	set_affinity(arg);
+	run_guest();
+	pthread_exit(NULL);
+}
+
+void *start_host(void *arg)
+{
+	set_affinity(arg);
+	run_host();
+	pthread_exit(NULL);
+}
+
+static const char optstring[] = "";
+static const struct option longopts[] = {
+	{
+		.name = "help",
+		.has_arg = no_argument,
+		.val = 'h',
+	},
+	{
+		.name = "host-affinity",
+		.has_arg = required_argument,
+		.val = 'H',
+	},
+	{
+		.name = "guest-affinity",
+		.has_arg = required_argument,
+		.val = 'G',
+	},
+	{
+		.name = "ring-size",
+		.has_arg = required_argument,
+		.val = 'R',
+	},
+	{
+		.name = "run-cycles",
+		.has_arg = required_argument,
+		.val = 'C',
+	},
+	{
+		.name = "outstanding",
+		.has_arg = required_argument,
+		.val = 'o',
+	},
+	{
+		.name = "batch",
+		.has_arg = required_argument,
+		.val = 'b',
+	},
+	{
+		.name = "sleep",
+		.has_arg = no_argument,
+		.val = 's',
+	},
+	{
+		.name = "relax",
+		.has_arg = no_argument,
+		.val = 'x',
+	},
+	{
+		.name = "exit",
+		.has_arg = no_argument,
+		.val = 'e',
+	},
+	{
+	}
+};
+
+static void help(void)
+{
+	fprintf(stderr, "Usage: <test> [--help]"
+		" [--host-affinity H]"
+		" [--guest-affinity G]"
+		" [--ring-size R (default: %d)]"
+		" [--run-cycles C (default: %d)]"
+		" [--batch b]"
+		" [--outstanding o]"
+		" [--sleep]"
+		" [--relax]"
+		" [--exit]"
+		"\n",
+		ring_size,
+		runcycles);
+}
+
+int main(int argc, char **argv)
+{
+	int ret;
+	pthread_t host, guest;
+	void *tret;
+	char *host_arg = NULL;
+	char *guest_arg = NULL;
+	char *endptr;
+	long int c;
+
+	kickfd = eventfd(0, 0);
+	assert(kickfd >= 0);
+	callfd = eventfd(0, 0);
+	assert(callfd >= 0);
+
+	for (;;) {
+		int o = getopt_long(argc, argv, optstring, longopts, NULL);
+		switch (o) {
+		case -1:
+			goto done;
+		case '?':
+			help();
+			exit(2);
+		case 'H':
+			host_arg = optarg;
+			break;
+		case 'G':
+			guest_arg = optarg;
+			break;
+		case 'R':
+			ring_size = strtol(optarg, &endptr, 0);
+			assert(ring_size && !(ring_size & (ring_size - 1)));
+			assert(!*endptr);
+			break;
+		case 'C':
+			c = strtol(optarg, &endptr, 0);
+			assert(!*endptr);
+			assert(c > 0 && c < INT_MAX);
+			runcycles = c;
+			break;
+		case 'o':
+			c = strtol(optarg, &endptr, 0);
+			assert(!*endptr);
+			assert(c > 0 && c < INT_MAX);
+			max_outstanding = c;
+			break;
+		case 'b':
+			c = strtol(optarg, &endptr, 0);
+			assert(!*endptr);
+			assert(c > 0 && c < INT_MAX);
+			batch = c;
+			break;
+		case 's':
+			do_sleep = true;
+			break;
+		case 'x':
+			do_relax = true;
+			break;
+		case 'e':
+			do_exit = true;
+			break;
+		default:
+			help();
+			exit(4);
+			break;
+		}
+	}
+
+	/* does nothing here, used to make sure all smp APIs compile */
+	smp_acquire();
+	smp_release();
+	smp_mb();
+done:
+
+	if (batch > max_outstanding)
+		batch = max_outstanding;
+
+	if (optind < argc) {
+		help();
+		exit(4);
+	}
+	alloc_ring();
+
+	ret = pthread_create(&host, NULL, start_host, host_arg);
+	assert(!ret);
+	ret = pthread_create(&guest, NULL, start_guest, guest_arg);
+	assert(!ret);
+
+	ret = pthread_join(guest, &tret);
+	assert(!ret);
+	ret = pthread_join(host, &tret);
+	assert(!ret);
+	return 0;
+}
diff --git a/tools/virtio/ringtest/main.h b/tools/virtio/ringtest/main.h
new file mode 100644
index 000000000000..16917acb0ade
--- /dev/null
+++ b/tools/virtio/ringtest/main.h
@@ -0,0 +1,119 @@
+/*
+ * Copyright (C) 2016 Red Hat, Inc.
+ * Author: Michael S. Tsirkin <mst@redhat.com>
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ *
+ * Common macros and functions for ring benchmarking.
+ */
+#ifndef MAIN_H
+#define MAIN_H
+
+#include <stdbool.h>
+
+extern bool do_exit;
+
+#if defined(__x86_64__) || defined(__i386__)
+#include "x86intrin.h"
+
+static inline void wait_cycles(unsigned long long cycles)
+{
+	unsigned long long t;
+
+	t = __rdtsc();
+	while (__rdtsc() - t < cycles) {}
+}
+
+#define VMEXIT_CYCLES 500
+#define VMENTRY_CYCLES 500
+
+#else
+static inline void wait_cycles(unsigned long long cycles)
+{
+	_Exit(5);
+}
+#define VMEXIT_CYCLES 0
+#define VMENTRY_CYCLES 0
+#endif
+
+static inline void vmexit(void)
+{
+	if (!do_exit)
+		return;
+	
+	wait_cycles(VMEXIT_CYCLES);
+}
+static inline void vmentry(void)
+{
+	if (!do_exit)
+		return;
+	
+	wait_cycles(VMENTRY_CYCLES);
+}
+
+/* implemented by ring */
+void alloc_ring(void);
+/* guest side */
+int add_inbuf(unsigned, void *, void *);
+void *get_buf(unsigned *, void **);
+void disable_call();
+bool enable_call();
+void kick_available();
+void poll_used();
+/* host side */
+void disable_kick();
+bool enable_kick();
+bool use_buf(unsigned *, void **);
+void call_used();
+void poll_avail();
+
+/* implemented by main */
+extern bool do_sleep;
+void kick(void);
+void wait_for_kick(void);
+void call(void);
+void wait_for_call(void);
+
+extern unsigned ring_size;
+
+/* Compiler barrier - similar to what Linux uses */
+#define barrier() asm volatile("" ::: "memory")
+
+/* Is there a portable way to do this? */
+#if defined(__x86_64__) || defined(__i386__)
+#define cpu_relax() asm ("rep; nop" ::: "memory")
+#else
+#define cpu_relax() assert(0)
+#endif
+
+extern bool do_relax;
+
+static inline void busy_wait(void)
+{
+	if (do_relax)
+		cpu_relax();
+	else
+		/* prevent compiler from removing busy loops */
+		barrier();
+} 
+
+/*
+ * Not using __ATOMIC_SEQ_CST since gcc docs say they are only synchronized
+ * with other __ATOMIC_SEQ_CST calls.
+ */
+#define smp_mb() __sync_synchronize()
+
+/*
+ * This abuses the atomic builtins for thread fences, and
+ * adds a compiler barrier.
+ */
+#define smp_release() do { \
+    barrier(); \
+    __atomic_thread_fence(__ATOMIC_RELEASE); \
+} while (0)
+
+#define smp_acquire() do { \
+    __atomic_thread_fence(__ATOMIC_ACQUIRE); \
+    barrier(); \
+} while (0)
+
+#endif
diff --git a/tools/virtio/ringtest/ring.c b/tools/virtio/ringtest/ring.c
new file mode 100644
index 000000000000..c25c8d248b6b
--- /dev/null
+++ b/tools/virtio/ringtest/ring.c
@@ -0,0 +1,272 @@
+/*
+ * Copyright (C) 2016 Red Hat, Inc.
+ * Author: Michael S. Tsirkin <mst@redhat.com>
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ *
+ * Simple descriptor-based ring. virtio 0.9 compatible event index is used for
+ * signalling, unconditionally.
+ */
+#define _GNU_SOURCE
+#include "main.h"
+#include <stdlib.h>
+#include <stdio.h>
+#include <string.h>
+
+/* Next - Where next entry will be written.
+ * Prev - "Next" value when event triggered previously.
+ * Event - Peer requested event after writing this entry.
+ */
+static inline bool need_event(unsigned short event,
+			      unsigned short next,
+			      unsigned short prev)
+{
+	return (unsigned short)(next - event - 1) < (unsigned short)(next - prev);
+}
+
+/* Design:
+ * Guest adds descriptors with unique index values and DESC_HW in flags.
+ * Host overwrites used descriptors with correct len, index, and DESC_HW clear.
+ * Flags are always set last.
+ */
+#define DESC_HW 0x1
+
+struct desc {
+	unsigned short flags;
+	unsigned short index;
+	unsigned len;
+	unsigned long long addr;
+};
+
+/* how much padding is needed to avoid false cache sharing */
+#define HOST_GUEST_PADDING 0x80
+
+/* Mostly read */
+struct event {
+	unsigned short kick_index;
+	unsigned char reserved0[HOST_GUEST_PADDING - 2];
+	unsigned short call_index;
+	unsigned char reserved1[HOST_GUEST_PADDING - 2];
+};
+
+struct data {
+	void *buf; /* descriptor is writeable, we can't get buf from there */
+	void *data;
+} *data;
+
+struct desc *ring;
+struct event *event;
+
+struct guest {
+	unsigned avail_idx;
+	unsigned last_used_idx;
+	unsigned num_free;
+	unsigned kicked_avail_idx;
+	unsigned char reserved[HOST_GUEST_PADDING - 12];
+} guest;
+
+struct host {
+	/* we do not need to track last avail index
+	 * unless we have more than one in flight.
+	 */
+	unsigned used_idx;
+	unsigned called_used_idx;
+	unsigned char reserved[HOST_GUEST_PADDING - 4];
+} host;
+
+/* implemented by ring */
+void alloc_ring(void)
+{
+	int ret;
+	int i;
+
+	ret = posix_memalign((void **)&ring, 0x1000, ring_size * sizeof *ring);
+	if (ret) {
+		perror("Unable to allocate ring buffer.\n");
+		exit(3);
+	}
+	event = malloc(sizeof *event);
+	if (!event) {
+		perror("Unable to allocate event buffer.\n");
+		exit(3);
+	}
+	memset(event, 0, sizeof *event);
+	guest.avail_idx = 0;
+	guest.kicked_avail_idx = -1;
+	guest.last_used_idx = 0;
+	host.used_idx = 0;
+	host.called_used_idx = -1;
+	for (i = 0; i < ring_size; ++i) {
+		struct desc desc = {
+			.index = i,
+		};
+		ring[i] = desc;
+	}
+	guest.num_free = ring_size;
+	data = malloc(ring_size * sizeof *data);
+	if (!data) {
+		perror("Unable to allocate data buffer.\n");
+		exit(3);
+	}
+	memset(data, 0, ring_size * sizeof *data);
+}
+
+/* guest side */
+int add_inbuf(unsigned len, void *buf, void *datap)
+{
+	unsigned head, index;
+
+	if (!guest.num_free)
+		return -1;
+
+	guest.num_free--;
+	head = (ring_size - 1) & (guest.avail_idx++);
+
+	/* Start with a write. On MESI architectures this helps
+	 * avoid a shared state with consumer that is polling this descriptor.
+	 */
+	ring[head].addr = (unsigned long)(void*)buf;
+	ring[head].len = len;
+	/* read below might bypass write above. That is OK because it's just an
+	 * optimization. If this happens, we will get the cache line in a
+	 * shared state which is unfortunate, but probably not worth it to
+	 * add an explicit full barrier to avoid this.
+	 */
+	barrier();
+	index = ring[head].index;
+	data[index].buf = buf;
+	data[index].data = datap;
+	/* Barrier A (for pairing) */
+	smp_release();
+	ring[head].flags = DESC_HW;
+
+	return 0;
+}
+
+void *get_buf(unsigned *lenp, void **bufp)
+{
+	unsigned head = (ring_size - 1) & guest.last_used_idx;
+	unsigned index;
+	void *datap;
+
+	if (ring[head].flags & DESC_HW)
+		return NULL;
+	/* Barrier B (for pairing) */
+	smp_acquire();
+	*lenp = ring[head].len;
+	index = ring[head].index & (ring_size - 1);
+	datap = data[index].data;
+	*bufp = data[index].buf;
+	data[index].buf = NULL;
+	data[index].data = NULL;
+	guest.num_free++;
+	guest.last_used_idx++;
+	return datap;
+}
+
+void poll_used(void)
+{
+	unsigned head = (ring_size - 1) & guest.last_used_idx;
+
+	while (ring[head].flags & DESC_HW)
+		busy_wait();
+}
+
+void disable_call()
+{
+	/* Doing nothing to disable calls might cause
+	 * extra interrupts, but reduces the number of cache misses.
+	 */
+}
+
+bool enable_call()
+{
+	unsigned head = (ring_size - 1) & guest.last_used_idx;
+
+	event->call_index = guest.last_used_idx;
+	/* Flush call index write */
+	/* Barrier D (for pairing) */
+	smp_mb();
+	return ring[head].flags & DESC_HW;
+}
+
+void kick_available(void)
+{
+	/* Flush in previous flags write */
+	/* Barrier C (for pairing) */
+	smp_mb();
+	if (!need_event(event->kick_index,
+			guest.avail_idx,
+			guest.kicked_avail_idx))
+		return;
+
+	guest.kicked_avail_idx = guest.avail_idx;
+	kick();
+}
+
+/* host side */
+void disable_kick()
+{
+	/* Doing nothing to disable kicks might cause
+	 * extra interrupts, but reduces the number of cache misses.
+	 */
+}
+
+bool enable_kick()
+{
+	unsigned head = (ring_size - 1) & host.used_idx;
+
+	event->kick_index = host.used_idx;
+	/* Barrier C (for pairing) */
+	smp_mb();
+	return !(ring[head].flags & DESC_HW);
+}
+
+void poll_avail(void)
+{
+	unsigned head = (ring_size - 1) & host.used_idx;
+
+	while (!(ring[head].flags & DESC_HW))
+		busy_wait();
+}
+
+bool use_buf(unsigned *lenp, void **bufp)
+{
+	unsigned head = (ring_size - 1) & host.used_idx;
+
+	if (!(ring[head].flags & DESC_HW))
+		return false;
+
+	/* make sure length read below is not speculated */
+	/* Barrier A (for pairing) */
+	smp_acquire();
+
+	/* simple in-order completion: we don't need
+	 * to touch index at all. This also means we
+	 * can just modify the descriptor in-place.
+	 */
+	ring[head].len--;
+	/* Make sure len is valid before flags.
+	 * Note: alternative is to write len and flags in one access -
+	 * possible on 64 bit architectures but wmb is free on Intel anyway
+	 * so I have no way to test whether it's a gain.
+	 */
+	/* Barrier B (for pairing) */
+	smp_release();
+	ring[head].flags = 0;
+	host.used_idx++;
+	return true;
+}
+
+void call_used(void)
+{
+	/* Flush in previous flags write */
+	/* Barrier D (for pairing) */
+	smp_mb();
+	if (!need_event(event->call_index,
+			host.used_idx,
+			host.called_used_idx))
+		return;
+
+	host.called_used_idx = host.used_idx;
+	call();
+}
diff --git a/tools/virtio/ringtest/run-on-all.sh b/tools/virtio/ringtest/run-on-all.sh
new file mode 100755
index 000000000000..52b0f71ffa8d
--- /dev/null
+++ b/tools/virtio/ringtest/run-on-all.sh
@@ -0,0 +1,24 @@
+#!/bin/sh
+
+#use last CPU for host. Why not the first?
+#many devices tend to use cpu0 by default so
+#it tends to be busier
+HOST_AFFINITY=$(cd /dev/cpu; ls|grep -v '[a-z]'|sort -n|tail -1)
+
+#run command on all cpus
+for cpu in $(cd /dev/cpu; ls|grep -v '[a-z]'|sort -n);
+do
+	#Don't run guest and host on same CPU
+	#It actually works ok if using signalling
+	if
+		(echo "$@" | grep -e "--sleep" > /dev/null) || \
+			test $HOST_AFFINITY '!=' $cpu
+	then
+		echo "GUEST AFFINITY $cpu"
+		"$@" --host-affinity $HOST_AFFINITY --guest-affinity $cpu
+	fi
+done
+echo "NO GUEST AFFINITY"
+"$@" --host-affinity $HOST_AFFINITY
+echo "NO AFFINITY"
+"$@"
diff --git a/tools/virtio/ringtest/virtio_ring_0_9.c b/tools/virtio/ringtest/virtio_ring_0_9.c
new file mode 100644
index 000000000000..47c9a1a18d36
--- /dev/null
+++ b/tools/virtio/ringtest/virtio_ring_0_9.c
@@ -0,0 +1,316 @@
+/*
+ * Copyright (C) 2016 Red Hat, Inc.
+ * Author: Michael S. Tsirkin <mst@redhat.com>
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ *
+ * Partial implementation of virtio 0.9. event index is used for signalling,
+ * unconditionally. Design roughly follows linux kernel implementation in order
+ * to be able to judge its performance.
+ */
+#define _GNU_SOURCE
+#include "main.h"
+#include <stdlib.h>
+#include <stdio.h>
+#include <assert.h>
+#include <string.h>
+#include <linux/virtio_ring.h>
+
+struct data {
+	void *data;
+} *data;
+
+struct vring ring;
+
+/* enabling the below activates experimental ring polling code
+ * (which skips index reads on consumer in favor of looking at
+ * high bits of ring id ^ 0x8000).
+ */
+/* #ifdef RING_POLL */
+
+/* how much padding is needed to avoid false cache sharing */
+#define HOST_GUEST_PADDING 0x80
+
+struct guest {
+	unsigned short avail_idx;
+	unsigned short last_used_idx;
+	unsigned short num_free;
+	unsigned short kicked_avail_idx;
+	unsigned short free_head;
+	unsigned char reserved[HOST_GUEST_PADDING - 10];
+} guest;
+
+struct host {
+	/* we do not need to track last avail index
+	 * unless we have more than one in flight.
+	 */
+	unsigned short used_idx;
+	unsigned short called_used_idx;
+	unsigned char reserved[HOST_GUEST_PADDING - 4];
+} host;
+
+/* implemented by ring */
+void alloc_ring(void)
+{
+	int ret;
+	int i;
+	void *p;
+
+	ret = posix_memalign(&p, 0x1000, vring_size(ring_size, 0x1000));
+	if (ret) {
+		perror("Unable to allocate ring buffer.\n");
+		exit(3);
+	}
+	memset(p, 0, vring_size(ring_size, 0x1000));
+	vring_init(&ring, ring_size, p, 0x1000);
+
+	guest.avail_idx = 0;
+	guest.kicked_avail_idx = -1;
+	guest.last_used_idx = 0;
+	/* Put everything in free lists. */
+	guest.free_head = 0;
+	for (i = 0; i < ring_size - 1; i++)
+		ring.desc[i].next = i + 1;
+	host.used_idx = 0;
+	host.called_used_idx = -1;
+	guest.num_free = ring_size;
+	data = malloc(ring_size * sizeof *data);
+	if (!data) {
+		perror("Unable to allocate data buffer.\n");
+		exit(3);
+	}
+	memset(data, 0, ring_size * sizeof *data);
+}
+
+/* guest side */
+int add_inbuf(unsigned len, void *buf, void *datap)
+{
+	unsigned head, avail;
+	struct vring_desc *desc;
+
+	if (!guest.num_free)
+		return -1;
+
+	head = guest.free_head;
+	guest.num_free--;
+
+	desc = ring.desc;
+	desc[head].flags = VRING_DESC_F_NEXT;
+	desc[head].addr = (unsigned long)(void *)buf;
+	desc[head].len = len;
+	/* We do it like this to simulate the way
+	 * we'd have to flip it if we had multiple
+	 * descriptors.
+	 */
+	desc[head].flags &= ~VRING_DESC_F_NEXT;
+	guest.free_head = desc[head].next;
+
+	data[head].data = datap;
+
+#ifdef RING_POLL
+	/* Barrier A (for pairing) */
+	smp_release();
+	avail = guest.avail_idx++;
+	ring.avail->ring[avail & (ring_size - 1)] =
+		(head | (avail & ~(ring_size - 1))) ^ 0x8000;
+#else
+	avail = (ring_size - 1) & (guest.avail_idx++);
+	ring.avail->ring[avail] = head;
+	/* Barrier A (for pairing) */
+	smp_release();
+#endif
+	ring.avail->idx = guest.avail_idx;
+	return 0;
+}
+
+void *get_buf(unsigned *lenp, void **bufp)
+{
+	unsigned head;
+	unsigned index;
+	void *datap;
+
+#ifdef RING_POLL
+	head = (ring_size - 1) & guest.last_used_idx;
+	index = ring.used->ring[head].id;
+	if ((index ^ guest.last_used_idx ^ 0x8000) & ~(ring_size - 1))
+		return NULL;
+	/* Barrier B (for pairing) */
+	smp_acquire();
+	index &= ring_size - 1;
+#else
+	if (ring.used->idx == guest.last_used_idx)
+		return NULL;
+	/* Barrier B (for pairing) */
+	smp_acquire();
+	head = (ring_size - 1) & guest.last_used_idx;
+	index = ring.used->ring[head].id;
+#endif
+	*lenp = ring.used->ring[head].len;
+	datap = data[index].data;
+	*bufp = (void*)(unsigned long)ring.desc[index].addr;
+	data[index].data = NULL;
+	ring.desc[index].next = guest.free_head;
+	guest.free_head = index;
+	guest.num_free++;
+	guest.last_used_idx++;
+	return datap;
+}
+
+void poll_used(void)
+{
+#ifdef RING_POLL
+	unsigned head = (ring_size - 1) & guest.last_used_idx;
+
+	for (;;) {
+		unsigned index = ring.used->ring[head].id;
+
+		if ((index ^ guest.last_used_idx ^ 0x8000) & ~(ring_size - 1))
+			busy_wait();
+		else
+			break;
+	}
+#else
+	unsigned head = guest.last_used_idx;
+
+	while (ring.used->idx == head)
+		busy_wait();
+#endif
+}
+
+void disable_call()
+{
+	/* Doing nothing to disable calls might cause
+	 * extra interrupts, but reduces the number of cache misses.
+	 */
+}
+
+bool enable_call()
+{
+	unsigned short last_used_idx;
+
+	vring_used_event(&ring) = (last_used_idx = guest.last_used_idx);
+	/* Flush call index write */
+	/* Barrier D (for pairing) */
+	smp_mb();
+#ifdef RING_POLL
+	{
+		unsigned short head = last_used_idx & (ring_size - 1);
+		unsigned index = ring.used->ring[head].id;
+
+		return (index ^ last_used_idx ^ 0x8000) & ~(ring_size - 1);
+	}
+#else
+	return ring.used->idx == last_used_idx;
+#endif
+}
+
+void kick_available(void)
+{
+	/* Flush in previous flags write */
+	/* Barrier C (for pairing) */
+	smp_mb();
+	if (!vring_need_event(vring_avail_event(&ring),
+			      guest.avail_idx,
+			      guest.kicked_avail_idx))
+		return;
+
+	guest.kicked_avail_idx = guest.avail_idx;
+	kick();
+}
+
+/* host side */
+void disable_kick()
+{
+	/* Doing nothing to disable kicks might cause
+	 * extra interrupts, but reduces the number of cache misses.
+	 */
+}
+
+bool enable_kick()
+{
+	unsigned head = host.used_idx;
+
+	vring_avail_event(&ring) = head;
+	/* Barrier C (for pairing) */
+	smp_mb();
+#ifdef RING_POLL
+	{
+		unsigned index = ring.avail->ring[head & (ring_size - 1)];
+
+		return (index ^ head ^ 0x8000) & ~(ring_size - 1);
+	}
+#else
+	return head == ring.avail->idx;
+#endif
+}
+
+void poll_avail(void)
+{
+	unsigned head = host.used_idx;
+#ifdef RING_POLL
+	for (;;) {
+		unsigned index = ring.avail->ring[head & (ring_size - 1)];
+		if ((index ^ head ^ 0x8000) & ~(ring_size - 1))
+			busy_wait();
+		else
+			break;
+	}
+#else
+	while (ring.avail->idx == head)
+		busy_wait();
+#endif
+}
+
+bool use_buf(unsigned *lenp, void **bufp)
+{
+	unsigned used_idx = host.used_idx;
+	struct vring_desc *desc;
+	unsigned head;
+
+#ifdef RING_POLL
+	head = ring.avail->ring[used_idx & (ring_size - 1)];
+	if ((used_idx ^ head ^ 0x8000) & ~(ring_size - 1))
+		return false;
+	/* Barrier A (for pairing) */
+	smp_acquire();
+
+	used_idx &= ring_size - 1;
+	desc = &ring.desc[head & (ring_size - 1)];
+#else
+	if (used_idx == ring.avail->idx)
+		return false;
+
+	/* Barrier A (for pairing) */
+	smp_acquire();
+
+	used_idx &= ring_size - 1;
+	head = ring.avail->ring[used_idx];
+	desc = &ring.desc[head];
+#endif
+
+	*lenp = desc->len;
+	*bufp = (void *)(unsigned long)desc->addr;
+
+	/* now update used ring */
+	ring.used->ring[used_idx].id = head;
+	ring.used->ring[used_idx].len = desc->len - 1;
+	/* Barrier B (for pairing) */
+	smp_release();
+	host.used_idx++;
+	ring.used->idx = host.used_idx;
+	
+	return true;
+}
+
+void call_used(void)
+{
+	/* Flush in previous flags write */
+	/* Barrier D (for pairing) */
+	smp_mb();
+	if (!vring_need_event(vring_used_event(&ring),
+			      host.used_idx,
+			      host.called_used_idx))
+		return;
+
+	host.called_used_idx = host.used_idx;
+	call();
+}
diff --git a/tools/virtio/ringtest/virtio_ring_poll.c b/tools/virtio/ringtest/virtio_ring_poll.c
new file mode 100644
index 000000000000..84fc2c557aaa
--- /dev/null
+++ b/tools/virtio/ringtest/virtio_ring_poll.c
@@ -0,0 +1,2 @@
+#define RING_POLL 1
+#include "virtio_ring_0_9.c"