Merge tag 'for-master' of https://github.com/rhdrjones/kvm-unit-tests into HEAD

arm/arm64 patches ready for master

arm/Makefile.common

@@ -9,10 +9,11 @@ ifeq ($(LOADADDR),)
 	LOADADDR = 0x40000000
 endif
 
-tests-common = \
-	$(TEST_DIR)/selftest.flat \
-	$(TEST_DIR)/spinlock-test.flat \
-	$(TEST_DIR)/pci-test.flat
+tests-common  = $(TEST_DIR)/selftest.flat
+tests-common += $(TEST_DIR)/spinlock-test.flat
+tests-common += $(TEST_DIR)/pci-test.flat
+tests-common += $(TEST_DIR)/pmu.flat
+tests-common += $(TEST_DIR)/gic.flat
 
 all: test_cases
 
@@ -21,6 +22,7 @@ phys_base = $(LOADADDR)
 
 CFLAGS += -std=gnu99
 CFLAGS += -ffreestanding
+CFLAGS += -fno-pic
 CFLAGS += -Wextra
 CFLAGS += -O2
 CFLAGS += -I lib -I lib/libfdt
@@ -46,6 +48,8 @@ cflatobjs += lib/arm/mmu.o
 cflatobjs += lib/arm/bitops.o
 cflatobjs += lib/arm/psci.o
 cflatobjs += lib/arm/smp.o
+cflatobjs += lib/arm/delay.o
+cflatobjs += lib/arm/gic.o lib/arm/gic-v2.o lib/arm/gic-v3.o
 
 libeabi = lib/arm/libeabi.a
 eabiobjs = lib/arm/eabi_compat.o

arm/cstart.S

@@ -9,7 +9,7 @@
 #include <asm/thread_info.h>
 #include <asm/asm-offsets.h>
 #include <asm/ptrace.h>
-#include <asm/cp15.h>
+#include <asm/sysreg.h>
 
 #define THREAD_START_SP ((THREAD_SIZE - S_FRAME_SIZE * 8) & ~7)
 

arm/gic.c

+/*
+ * GIC tests
+ *
+ * GICv2
+ *   + test sending/receiving IPIs
+ * GICv3
+ *   + test sending/receiving IPIs
+ *
+ * Copyright (C) 2016, Red Hat Inc, Andrew Jones <drjones@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2.
+ */
+#include <libcflat.h>
+#include <asm/setup.h>
+#include <asm/processor.h>
+#include <asm/delay.h>
+#include <asm/gic.h>
+#include <asm/smp.h>
+#include <asm/barrier.h>
+#include <asm/io.h>
+
+#define IPI_SENDER	1
+#define IPI_IRQ		1
+
+struct gic {
+	struct {
+		void (*send_self)(void);
+		void (*send_broadcast)(void);
+	} ipi;
+};
+
+static struct gic *gic;
+static int acked[NR_CPUS], spurious[NR_CPUS];
+static int bad_sender[NR_CPUS], bad_irq[NR_CPUS];
+static cpumask_t ready;
+
+static void nr_cpu_check(int nr)
+{
+	if (nr_cpus < nr)
+		report_abort("At least %d cpus required", nr);
+}
+
+static void wait_on_ready(void)
+{
+	cpumask_set_cpu(smp_processor_id(), &ready);
+	while (!cpumask_full(&ready))
+		cpu_relax();
+}
+
+static void stats_reset(void)
+{
+	int i;
+
+	for (i = 0; i < nr_cpus; ++i) {
+		acked[i] = 0;
+		bad_sender[i] = -1;
+		bad_irq[i] = -1;
+	}
+	smp_wmb();
+}
+
+static void check_acked(cpumask_t *mask)
+{
+	int missing = 0, extra = 0, unexpected = 0;
+	int nr_pass, cpu, i;
+	bool bad = false;
+
+	/* Wait up to 5s for all interrupts to be delivered */
+	for (i = 0; i < 50; ++i) {
+		mdelay(100);
+		nr_pass = 0;
+		for_each_present_cpu(cpu) {
+			smp_rmb();
+			nr_pass += cpumask_test_cpu(cpu, mask) ?
+				acked[cpu] == 1 : acked[cpu] == 0;
+
+			if (bad_sender[cpu] != -1) {
+				printf("cpu%d received IPI from wrong sender %d\n",
+					cpu, bad_sender[cpu]);
+				bad = true;
+			}
+
+			if (bad_irq[cpu] != -1) {
+				printf("cpu%d received wrong irq %d\n",
+					cpu, bad_irq[cpu]);
+				bad = true;
+			}
+		}
+		if (nr_pass == nr_cpus) {
+			report("Completed in %d ms", !bad, ++i * 100);
+			return;
+		}
+	}
+
+	for_each_present_cpu(cpu) {
+		if (cpumask_test_cpu(cpu, mask)) {
+			if (!acked[cpu])
+				++missing;
+			else if (acked[cpu] > 1)
+				++extra;
+		} else {
+			if (acked[cpu])
+				++unexpected;
+		}
+	}
+
+	report("Timed-out (5s). ACKS: missing=%d extra=%d unexpected=%d",
+	       false, missing, extra, unexpected);
+}
+
+static void check_spurious(void)
+{
+	int cpu;
+
+	smp_rmb();
+	for_each_present_cpu(cpu) {
+		if (spurious[cpu])
+			report_info("WARN: cpu%d got %d spurious interrupts",
+				cpu, spurious[cpu]);
+	}
+}
+
+static void check_ipi_sender(u32 irqstat)
+{
+	if (gic_version() == 2) {
+		int src = (irqstat >> 10) & 7;
+
+		if (src != IPI_SENDER)
+			bad_sender[smp_processor_id()] = src;
+	}
+}
+
+static void check_irqnr(u32 irqnr)
+{
+	if (irqnr != IPI_IRQ)
+		bad_irq[smp_processor_id()] = irqnr;
+}
+
+static void ipi_handler(struct pt_regs *regs __unused)
+{
+	u32 irqstat = gic_read_iar();
+	u32 irqnr = gic_iar_irqnr(irqstat);
+
+	if (irqnr != GICC_INT_SPURIOUS) {
+		gic_write_eoir(irqstat);
+		smp_rmb(); /* pairs with wmb in stats_reset */
+		++acked[smp_processor_id()];
+		check_ipi_sender(irqstat);
+		check_irqnr(irqnr);
+		smp_wmb(); /* pairs with rmb in check_acked */
+	} else {
+		++spurious[smp_processor_id()];
+		smp_wmb();
+	}
+}
+
+static void gicv2_ipi_send_self(void)
+{
+	writel(2 << 24 | IPI_IRQ, gicv2_dist_base() + GICD_SGIR);
+}
+
+static void gicv2_ipi_send_broadcast(void)
+{
+	writel(1 << 24 | IPI_IRQ, gicv2_dist_base() + GICD_SGIR);
+}
+
+static void gicv3_ipi_send_self(void)
+{
+	gic_ipi_send_single(IPI_IRQ, smp_processor_id());
+}
+
+static void gicv3_ipi_send_broadcast(void)
+{
+	gicv3_write_sgi1r(1ULL << 40 | IPI_IRQ << 24);
+	isb();
+}
+
+static void ipi_test_self(void)
+{
+	cpumask_t mask;
+
+	report_prefix_push("self");
+	stats_reset();
+	cpumask_clear(&mask);
+	cpumask_set_cpu(smp_processor_id(), &mask);
+	gic->ipi.send_self();
+	check_acked(&mask);
+	report_prefix_pop();
+}
+
+static void ipi_test_smp(void)
+{
+	cpumask_t mask;
+	int i;
+
+	report_prefix_push("target-list");
+	stats_reset();
+	cpumask_copy(&mask, &cpu_present_mask);
+	for (i = smp_processor_id() & 1; i < nr_cpus; i += 2)
+		cpumask_clear_cpu(i, &mask);
+	gic_ipi_send_mask(IPI_IRQ, &mask);
+	check_acked(&mask);
+	report_prefix_pop();
+
+	report_prefix_push("broadcast");
+	stats_reset();
+	cpumask_copy(&mask, &cpu_present_mask);
+	cpumask_clear_cpu(smp_processor_id(), &mask);
+	gic->ipi.send_broadcast();
+	check_acked(&mask);
+	report_prefix_pop();
+}
+
+static void ipi_enable(void)
+{
+	gic_enable_defaults();
+#ifdef __arm__
+	install_exception_handler(EXCPTN_IRQ, ipi_handler);
+#else
+	install_irq_handler(EL1H_IRQ, ipi_handler);
+#endif
+	local_irq_enable();
+}
+
+static void ipi_send(void)
+{
+	ipi_enable();
+	wait_on_ready();
+	ipi_test_self();
+	ipi_test_smp();
+	check_spurious();
+	exit(report_summary());
+}
+
+static void ipi_recv(void)
+{
+	ipi_enable();
+	cpumask_set_cpu(smp_processor_id(), &ready);
+	while (1)
+		wfi();
+}
+
+static struct gic gicv2 = {
+	.ipi = {
+		.send_self = gicv2_ipi_send_self,
+		.send_broadcast = gicv2_ipi_send_broadcast,
+	},
+};
+
+static struct gic gicv3 = {
+	.ipi = {
+		.send_self = gicv3_ipi_send_self,
+		.send_broadcast = gicv3_ipi_send_broadcast,
+	},
+};
+
+int main(int argc, char **argv)
+{
+	char pfx[8];
+	int cpu;
+
+	if (!gic_init()) {
+		printf("No supported gic present, skipping tests...\n");
+		return report_summary();
+	}
+
+	snprintf(pfx, sizeof(pfx), "gicv%d", gic_version());
+	report_prefix_push(pfx);
+
+	switch (gic_version()) {
+	case 2:
+		gic = &gicv2;
+		break;
+	case 3:
+		gic = &gicv3;
+		break;
+	}
+
+	if (argc < 2)
+		report_abort("no test specified");
+
+	if (strcmp(argv[1], "ipi") == 0) {
+		report_prefix_push(argv[1]);
+		nr_cpu_check(2);
+
+		for_each_present_cpu(cpu) {
+			if (cpu == 0)
+				continue;
+			smp_boot_secondary(cpu,
+				cpu == IPI_SENDER ? ipi_send : ipi_recv);
+		}
+		ipi_recv();
+	} else {
+		report_abort("Unknown subtest '%s'", argv[1]);
+	}
+
+	return report_summary();
+}

arm/pci-test.c

@@ -14,14 +14,19 @@ int main(void)
 {
 	int ret;
 
-	if (!pci_probe())
-		report_abort("PCI bus probing failed\n");
+	if (!pci_probe()) {
+		printf("PCI bus probing failed, skipping tests...\n");
+		return report_summary();
+	}
 
 	pci_print();
 
 	ret = pci_testdev();
-	report("PCI test device passed %d/%d tests",
-		ret >= NR_TESTS, ret > 0 ? ret : 0, NR_TESTS);
+	if (ret == -1)
+		report_skip("No PCI test device");
+	else
+		report("PCI test device passed %d/%d tests",
+			ret >= NR_TESTS, ret > 0 ? ret : 0, NR_TESTS);
 
 	return report_summary();
 }

arm/pmu.c

+/*
+ * Test the ARM Performance Monitors Unit (PMU).
+ *
+ * Copyright (c) 2015-2016, The Linux Foundation. All rights reserved.
+ * Copyright (C) 2016, Red Hat Inc, Wei Huang <wei@redhat.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU Lesser General Public License version 2.1 and
+ * only version 2.1 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU Lesser General Public License
+ * for more details.
+ */
+#include "libcflat.h"
+#include "asm/barrier.h"
+#include "asm/sysreg.h"
+#include "asm/processor.h"
+
+#define PMU_PMCR_E         (1 << 0)
+#define PMU_PMCR_C         (1 << 2)
+#define PMU_PMCR_LC        (1 << 6)
+#define PMU_PMCR_N_SHIFT   11
+#define PMU_PMCR_N_MASK    0x1f
+#define PMU_PMCR_ID_SHIFT  16
+#define PMU_PMCR_ID_MASK   0xff
+#define PMU_PMCR_IMP_SHIFT 24
+#define PMU_PMCR_IMP_MASK  0xff
+
+#define PMU_CYCLE_IDX      31
+
+#define NR_SAMPLES 10
+
+static unsigned int pmu_version;
+#if defined(__arm__)
+#define ID_DFR0_PERFMON_SHIFT 24
+#define ID_DFR0_PERFMON_MASK  0xf
+
+#define PMCR         __ACCESS_CP15(c9, 0, c12, 0)
+#define ID_DFR0      __ACCESS_CP15(c0, 0, c1, 2)
+#define PMSELR       __ACCESS_CP15(c9, 0, c12, 5)
+#define PMXEVTYPER   __ACCESS_CP15(c9, 0, c13, 1)
+#define PMCNTENSET   __ACCESS_CP15(c9, 0, c12, 1)
+#define PMCCNTR32    __ACCESS_CP15(c9, 0, c13, 0)
+#define PMCCNTR64    __ACCESS_CP15_64(0, c9)
+
+static inline uint32_t get_id_dfr0(void) { return read_sysreg(ID_DFR0); }
+static inline uint32_t get_pmcr(void) { return read_sysreg(PMCR); }
+static inline void set_pmcr(uint32_t v) { write_sysreg(v, PMCR); }
+static inline void set_pmcntenset(uint32_t v) { write_sysreg(v, PMCNTENSET); }
+
+static inline uint8_t get_pmu_version(void)
+{
+	return (get_id_dfr0() >> ID_DFR0_PERFMON_SHIFT) & ID_DFR0_PERFMON_MASK;
+}
+
+static inline uint64_t get_pmccntr(void)
+{
+	if (pmu_version == 0x3)
+		return read_sysreg(PMCCNTR64);
+	else
+		return read_sysreg(PMCCNTR32);
+}
+
+static inline void set_pmccntr(uint64_t value)
+{
+	if (pmu_version == 0x3)
+		write_sysreg(value, PMCCNTR64);
+	else
+		write_sysreg(value & 0xffffffff, PMCCNTR32);
+}
+
+/* PMCCFILTR is an obsolete name for PMXEVTYPER31 in ARMv7 */
+static inline void set_pmccfiltr(uint32_t value)
+{
+	write_sysreg(PMU_CYCLE_IDX, PMSELR);
+	write_sysreg(value, PMXEVTYPER);
+	isb();
+}
+
+/*
+ * Extra instructions inserted by the compiler would be difficult to compensate
+ * for, so hand assemble everything between, and including, the PMCR accesses
+ * to start and stop counting. isb instructions were inserted to make sure
+ * pmccntr read after this function returns the exact instructions executed in
+ * the controlled block. Total instrs = isb + mcr + 2*loop = 2 + 2*loop.
+ */
+static inline void precise_instrs_loop(int loop, uint32_t pmcr)
+{
+	asm volatile(
+	"	mcr	p15, 0, %[pmcr], c9, c12, 0\n"
+	"	isb\n"
+	"1:	subs	%[loop], %[loop], #1\n"
+	"	bgt	1b\n"
+	"	mcr	p15, 0, %[z], c9, c12, 0\n"
+	"	isb\n"
+	: [loop] "+r" (loop)
+	: [pmcr] "r" (pmcr), [z] "r" (0)
+	: "cc");
+}
+#elif defined(__aarch64__)
+#define ID_AA64DFR0_PERFMON_SHIFT 8
+#define ID_AA64DFR0_PERFMON_MASK  0xf
+
+static inline uint32_t get_id_aa64dfr0(void) { return read_sysreg(id_aa64dfr0_el1); }
+static inline uint32_t get_pmcr(void) { return read_sysreg(pmcr_el0); }
+static inline void set_pmcr(uint32_t v) { write_sysreg(v, pmcr_el0); }
+static inline uint64_t get_pmccntr(void) { return read_sysreg(pmccntr_el0); }
+static inline void set_pmccntr(uint64_t v) { write_sysreg(v, pmccntr_el0); }
+static inline void set_pmcntenset(uint32_t v) { write_sysreg(v, pmcntenset_el0); }
+static inline void set_pmccfiltr(uint32_t v) { write_sysreg(v, pmccfiltr_el0); }
+
+static inline uint8_t get_pmu_version(void)
+{
+	uint8_t ver = (get_id_aa64dfr0() >> ID_AA64DFR0_PERFMON_SHIFT) & ID_AA64DFR0_PERFMON_MASK;
+	return ver == 1 ? 3 : ver;
+}
+
+/*
+ * Extra instructions inserted by the compiler would be difficult to compensate
+ * for, so hand assemble everything between, and including, the PMCR accesses
+ * to start and stop counting. isb instructions are inserted to make sure
+ * pmccntr read after this function returns the exact instructions executed
+ * in the controlled block. Total instrs = isb + msr + 2*loop = 2 + 2*loop.
+ */
+static inline void precise_instrs_loop(int loop, uint32_t pmcr)
+{
+	asm volatile(
+	"	msr	pmcr_el0, %[pmcr]\n"
+	"	isb\n"
+	"1:	subs	%[loop], %[loop], #1\n"
+	"	b.gt	1b\n"
+	"	msr	pmcr_el0, xzr\n"
+	"	isb\n"
+	: [loop] "+r" (loop)
+	: [pmcr] "r" (pmcr)
+	: "cc");
+}
+#endif
+
+/*
+ * As a simple sanity check on the PMCR_EL0, ensure the implementer field isn't
+ * null. Also print out a couple other interesting fields for diagnostic
+ * purposes. For example, as of fall 2016, QEMU TCG mode doesn't implement
+ * event counters and therefore reports zero event counters, but hopefully
+ * support for at least the instructions event will be added in the future and
+ * the reported number of event counters will become nonzero.
+ */
+static bool check_pmcr(void)
+{
+	uint32_t pmcr;
+
+	pmcr = get_pmcr();
+
+	report_info("PMU implementer/ID code/counters: 0x%x(\"%c\")/0x%x/%d",
+		    (pmcr >> PMU_PMCR_IMP_SHIFT) & PMU_PMCR_IMP_MASK,
+		    ((pmcr >> PMU_PMCR_IMP_SHIFT) & PMU_PMCR_IMP_MASK) ? : ' ',
+		    (pmcr >> PMU_PMCR_ID_SHIFT) & PMU_PMCR_ID_MASK,
+		    (pmcr >> PMU_PMCR_N_SHIFT) & PMU_PMCR_N_MASK);
+
+	return ((pmcr >> PMU_PMCR_IMP_SHIFT) & PMU_PMCR_IMP_MASK) != 0;
+}
+
+/*
+ * Ensure that the cycle counter progresses between back-to-back reads.
+ */
+static bool check_cycles_increase(void)
+{
+	bool success = true;
+
+	/* init before event access, this test only cares about cycle count */
+	set_pmcntenset(1 << PMU_CYCLE_IDX);
+	set_pmccfiltr(0); /* count cycles in EL0, EL1, but not EL2 */
+
+	set_pmcr(get_pmcr() | PMU_PMCR_LC | PMU_PMCR_C | PMU_PMCR_E);
+
+	for (int i = 0; i < NR_SAMPLES; i++) {
+		uint64_t a, b;
+
+		a = get_pmccntr();
+		b = get_pmccntr();
+
+		if (a >= b) {
+			printf("Read %"PRId64" then %"PRId64".\n", a, b);
+			success = false;
+			break;
+		}
+	}
+
+	set_pmcr(get_pmcr() & ~PMU_PMCR_E);
+
+	return success;
+}
+
+/*
+ * Execute a known number of guest instructions. Only even instruction counts
+ * greater than or equal to 4 are supported by the in-line assembly code. The
+ * control register (PMCR_EL0) is initialized with the provided value (allowing
+ * for example for the cycle counter or event counters to be reset). At the end
+ * of the exact instruction loop, zero is written to PMCR_EL0 to disable
+ * counting, allowing the cycle counter or event counters to be read at the
+ * leisure of the calling code.
+ */
+static void measure_instrs(int num, uint32_t pmcr)
+{
+	int loop = (num - 2) / 2;
+
+	assert(num >= 4 && ((num - 2) % 2 == 0));
+	precise_instrs_loop(loop, pmcr);
+}
+
+/*
+ * Measure cycle counts for various known instruction counts. Ensure that the
+ * cycle counter progresses (similar to check_cycles_increase() but with more
+ * instructions and using reset and stop controls). If supplied a positive,
+ * nonzero CPI parameter, it also strictly checks that every measurement matches
+ * it. Strict CPI checking is used to test -icount mode.
+ */
+static bool check_cpi(int cpi)
+{
+	uint32_t pmcr = get_pmcr() | PMU_PMCR_LC | PMU_PMCR_C | PMU_PMCR_E;
+
+	/* init before event access, this test only cares about cycle count */
+	set_pmcntenset(1 << PMU_CYCLE_IDX);
+	set_pmccfiltr(0); /* count cycles in EL0, EL1, but not EL2 */
+
+	if (cpi > 0)
+		printf("Checking for CPI=%d.\n", cpi);
+	printf("instrs : cycles0 cycles1 ...\n");
+
+	for (unsigned int i = 4; i < 300; i += 32) {
+		uint64_t avg, sum = 0;
+
+		printf("%4d:", i);
+		for (int j = 0; j < NR_SAMPLES; j++) {
+			uint64_t cycles;
+
+			set_pmccntr(0);
+			measure_instrs(i, pmcr);
+			cycles = get_pmccntr();
+			printf(" %4"PRId64"", cycles);
+
+			if (!cycles) {
+				printf("\ncycles not incrementing!\n");
+				return false;
+			} else if (cpi > 0 && cycles != i * cpi) {
+				printf("\nunexpected cycle count received!\n");
+				return false;
+			} else if ((cycles >> 32) != 0) {
+				/* The cycles taken by the loop above should
+				 * fit in 32 bits easily. We check the upper
+				 * 32 bits of the cycle counter to make sure
+				 * there is no supprise. */
+				printf("\ncycle count bigger than 32bit!\n");
+				return false;
+			}
+
+			sum += cycles;
+		}
+		avg = sum / NR_SAMPLES;
+		printf(" avg=%-4"PRId64" %s=%-3"PRId64"\n", avg,
+		       (avg >= i) ? "cpi" : "ipc",
+		       (avg >= i) ? avg / i : i / avg);
+	}
+
+	return true;
+}