diff options
Diffstat (limited to 'tools/testing')
117 files changed, 6007 insertions, 1108 deletions
diff --git a/tools/testing/cxl/Kbuild b/tools/testing/cxl/Kbuild index d07f14cb7aa4..0d5ce4b74b9f 100644 --- a/tools/testing/cxl/Kbuild +++ b/tools/testing/cxl/Kbuild @@ -5,22 +5,19 @@ ldflags-y += --wrap=acpi_evaluate_integer ldflags-y += --wrap=acpi_pci_find_root ldflags-y += --wrap=nvdimm_bus_register ldflags-y += --wrap=devm_cxl_port_enumerate_dports -ldflags-y += --wrap=devm_cxl_setup_hdm -ldflags-y += --wrap=devm_cxl_add_passthrough_decoder -ldflags-y += --wrap=devm_cxl_enumerate_decoders ldflags-y += --wrap=cxl_await_media_ready -ldflags-y += --wrap=cxl_hdm_decode_init -ldflags-y += --wrap=cxl_dvsec_rr_decode ldflags-y += --wrap=devm_cxl_add_rch_dport ldflags-y += --wrap=cxl_rcd_component_reg_phys ldflags-y += --wrap=cxl_endpoint_parse_cdat ldflags-y += --wrap=cxl_dport_init_ras_reporting +ldflags-y += --wrap=devm_cxl_endpoint_decoders_setup DRIVERS := ../../../drivers CXL_SRC := $(DRIVERS)/cxl CXL_CORE_SRC := $(DRIVERS)/cxl/core ccflags-y := -I$(srctree)/drivers/cxl/ ccflags-y += -D__mock=__weak +ccflags-y += -DCXL_TEST_ENABLE=1 ccflags-y += -DTRACE_INCLUDE_PATH=$(CXL_CORE_SRC) -I$(srctree)/drivers/cxl/core/ obj-m += cxl_acpi.o diff --git a/tools/testing/cxl/cxl_core_exports.c b/tools/testing/cxl/cxl_core_exports.c index f088792a8925..6754de35598d 100644 --- a/tools/testing/cxl/cxl_core_exports.c +++ b/tools/testing/cxl/cxl_core_exports.c @@ -2,6 +2,28 @@ /* Copyright(c) 2022 Intel Corporation. All rights reserved. */ #include "cxl.h" +#include "exports.h" /* Exporting of cxl_core symbols that are only used by cxl_test */ EXPORT_SYMBOL_NS_GPL(cxl_num_decoders_committed, "CXL"); + +cxl_add_dport_by_dev_fn _devm_cxl_add_dport_by_dev = + __devm_cxl_add_dport_by_dev; +EXPORT_SYMBOL_NS_GPL(_devm_cxl_add_dport_by_dev, "CXL"); + +struct cxl_dport *devm_cxl_add_dport_by_dev(struct cxl_port *port, + struct device *dport_dev) +{ + return _devm_cxl_add_dport_by_dev(port, dport_dev); +} +EXPORT_SYMBOL_NS_GPL(devm_cxl_add_dport_by_dev, "CXL"); + +cxl_switch_decoders_setup_fn _devm_cxl_switch_port_decoders_setup = + __devm_cxl_switch_port_decoders_setup; +EXPORT_SYMBOL_NS_GPL(_devm_cxl_switch_port_decoders_setup, "CXL"); + +int devm_cxl_switch_port_decoders_setup(struct cxl_port *port) +{ + return _devm_cxl_switch_port_decoders_setup(port); +} +EXPORT_SYMBOL_NS_GPL(devm_cxl_switch_port_decoders_setup, "CXL"); diff --git a/tools/testing/cxl/exports.h b/tools/testing/cxl/exports.h new file mode 100644 index 000000000000..7ebee7c0bd67 --- /dev/null +++ b/tools/testing/cxl/exports.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2025 Intel Corporation */ +#ifndef __MOCK_CXL_EXPORTS_H_ +#define __MOCK_CXL_EXPORTS_H_ + +typedef struct cxl_dport *(*cxl_add_dport_by_dev_fn)(struct cxl_port *port, + struct device *dport_dev); +extern cxl_add_dport_by_dev_fn _devm_cxl_add_dport_by_dev; + +typedef int(*cxl_switch_decoders_setup_fn)(struct cxl_port *port); +extern cxl_switch_decoders_setup_fn _devm_cxl_switch_port_decoders_setup; + +#endif diff --git a/tools/testing/cxl/test/cxl.c b/tools/testing/cxl/test/cxl.c index 6a25cca5636f..2d135ca533d0 100644 --- a/tools/testing/cxl/test/cxl.c +++ b/tools/testing/cxl/test/cxl.c @@ -210,7 +210,7 @@ static struct { }, .interleave_ways = 0, .granularity = 4, - .restrictions = ACPI_CEDT_CFMWS_RESTRICT_TYPE3 | + .restrictions = ACPI_CEDT_CFMWS_RESTRICT_HOSTONLYMEM | ACPI_CEDT_CFMWS_RESTRICT_VOLATILE, .qtg_id = FAKE_QTG_ID, .window_size = SZ_256M * 4UL, @@ -225,7 +225,7 @@ static struct { }, .interleave_ways = 1, .granularity = 4, - .restrictions = ACPI_CEDT_CFMWS_RESTRICT_TYPE3 | + .restrictions = ACPI_CEDT_CFMWS_RESTRICT_HOSTONLYMEM | ACPI_CEDT_CFMWS_RESTRICT_VOLATILE, .qtg_id = FAKE_QTG_ID, .window_size = SZ_256M * 8UL, @@ -240,7 +240,7 @@ static struct { }, .interleave_ways = 0, .granularity = 4, - .restrictions = ACPI_CEDT_CFMWS_RESTRICT_TYPE3 | + .restrictions = ACPI_CEDT_CFMWS_RESTRICT_HOSTONLYMEM | ACPI_CEDT_CFMWS_RESTRICT_PMEM, .qtg_id = FAKE_QTG_ID, .window_size = SZ_256M * 4UL, @@ -255,7 +255,7 @@ static struct { }, .interleave_ways = 1, .granularity = 4, - .restrictions = ACPI_CEDT_CFMWS_RESTRICT_TYPE3 | + .restrictions = ACPI_CEDT_CFMWS_RESTRICT_HOSTONLYMEM | ACPI_CEDT_CFMWS_RESTRICT_PMEM, .qtg_id = FAKE_QTG_ID, .window_size = SZ_256M * 8UL, @@ -270,7 +270,7 @@ static struct { }, .interleave_ways = 0, .granularity = 4, - .restrictions = ACPI_CEDT_CFMWS_RESTRICT_TYPE3 | + .restrictions = ACPI_CEDT_CFMWS_RESTRICT_HOSTONLYMEM | ACPI_CEDT_CFMWS_RESTRICT_PMEM, .qtg_id = FAKE_QTG_ID, .window_size = SZ_256M * 4UL, @@ -285,7 +285,7 @@ static struct { }, .interleave_ways = 0, .granularity = 4, - .restrictions = ACPI_CEDT_CFMWS_RESTRICT_TYPE3 | + .restrictions = ACPI_CEDT_CFMWS_RESTRICT_HOSTONLYMEM | ACPI_CEDT_CFMWS_RESTRICT_VOLATILE, .qtg_id = FAKE_QTG_ID, .window_size = SZ_256M, @@ -302,7 +302,7 @@ static struct { .interleave_arithmetic = ACPI_CEDT_CFMWS_ARITHMETIC_XOR, .interleave_ways = 0, .granularity = 4, - .restrictions = ACPI_CEDT_CFMWS_RESTRICT_TYPE3 | + .restrictions = ACPI_CEDT_CFMWS_RESTRICT_HOSTONLYMEM | ACPI_CEDT_CFMWS_RESTRICT_PMEM, .qtg_id = FAKE_QTG_ID, .window_size = SZ_256M * 8UL, @@ -318,7 +318,7 @@ static struct { .interleave_arithmetic = ACPI_CEDT_CFMWS_ARITHMETIC_XOR, .interleave_ways = 1, .granularity = 0, - .restrictions = ACPI_CEDT_CFMWS_RESTRICT_TYPE3 | + .restrictions = ACPI_CEDT_CFMWS_RESTRICT_HOSTONLYMEM | ACPI_CEDT_CFMWS_RESTRICT_PMEM, .qtg_id = FAKE_QTG_ID, .window_size = SZ_256M * 8UL, @@ -334,7 +334,7 @@ static struct { .interleave_arithmetic = ACPI_CEDT_CFMWS_ARITHMETIC_XOR, .interleave_ways = 8, .granularity = 1, - .restrictions = ACPI_CEDT_CFMWS_RESTRICT_TYPE3 | + .restrictions = ACPI_CEDT_CFMWS_RESTRICT_HOSTONLYMEM | ACPI_CEDT_CFMWS_RESTRICT_PMEM, .qtg_id = FAKE_QTG_ID, .window_size = SZ_512M * 6UL, @@ -643,15 +643,8 @@ static struct cxl_hdm *mock_cxl_setup_hdm(struct cxl_port *port, return cxlhdm; } -static int mock_cxl_add_passthrough_decoder(struct cxl_port *port) -{ - dev_err(&port->dev, "unexpected passthrough decoder for cxl_test\n"); - return -EOPNOTSUPP; -} - - struct target_map_ctx { - int *target_map; + u32 *target_map; int index; int target_count; }; @@ -818,15 +811,21 @@ static void mock_init_hdm_decoder(struct cxl_decoder *cxld) */ if (WARN_ON(!dev)) continue; + cxlsd = to_cxl_switch_decoder(dev); if (i == 0) { /* put cxl_mem.4 second in the decode order */ - if (pdev->id == 4) + if (pdev->id == 4) { cxlsd->target[1] = dport; - else + cxld->target_map[1] = dport->port_id; + } else { cxlsd->target[0] = dport; - } else + cxld->target_map[0] = dport->port_id; + } + } else { cxlsd->target[0] = dport; + cxld->target_map[0] = dport->port_id; + } cxld = &cxlsd->cxld; cxld->target_type = CXL_DECODER_HOSTONLYMEM; cxld->flags = CXL_DECODER_F_ENABLE; @@ -863,9 +862,7 @@ static int mock_cxl_enumerate_decoders(struct cxl_hdm *cxlhdm, target_count = NR_CXL_SWITCH_PORTS; for (i = 0; i < NR_CXL_PORT_DECODERS; i++) { - int target_map[CXL_DECODER_MAX_INTERLEAVE] = { 0 }; struct target_map_ctx ctx = { - .target_map = target_map, .target_count = target_count, }; struct cxl_decoder *cxld; @@ -894,6 +891,8 @@ static int mock_cxl_enumerate_decoders(struct cxl_hdm *cxlhdm, cxld = &cxled->cxld; } + ctx.target_map = cxld->target_map; + mock_init_hdm_decoder(cxld); if (target_count) { @@ -905,7 +904,7 @@ static int mock_cxl_enumerate_decoders(struct cxl_hdm *cxlhdm, } } - rc = cxl_decoder_add_locked(cxld, target_map); + rc = cxl_decoder_add_locked(cxld); if (rc) { put_device(&cxld->dev); dev_err(&port->dev, "Failed to add decoder\n"); @@ -921,10 +920,42 @@ static int mock_cxl_enumerate_decoders(struct cxl_hdm *cxlhdm, return 0; } -static int mock_cxl_port_enumerate_dports(struct cxl_port *port) +static int __mock_cxl_decoders_setup(struct cxl_port *port) +{ + struct cxl_hdm *cxlhdm; + + cxlhdm = mock_cxl_setup_hdm(port, NULL); + if (IS_ERR(cxlhdm)) { + if (PTR_ERR(cxlhdm) != -ENODEV) + dev_err(&port->dev, "Failed to map HDM decoder capability\n"); + return PTR_ERR(cxlhdm); + } + + return mock_cxl_enumerate_decoders(cxlhdm, NULL); +} + +static int mock_cxl_switch_port_decoders_setup(struct cxl_port *port) +{ + if (is_cxl_root(port) || is_cxl_endpoint(port)) + return -EOPNOTSUPP; + + return __mock_cxl_decoders_setup(port); +} + +static int mock_cxl_endpoint_decoders_setup(struct cxl_port *port) +{ + if (!is_cxl_endpoint(port)) + return -EOPNOTSUPP; + + return __mock_cxl_decoders_setup(port); +} + +static int get_port_array(struct cxl_port *port, + struct platform_device ***port_array, + int *port_array_size) { struct platform_device **array; - int i, array_size; + int array_size; if (port->depth == 1) { if (is_multi_bridge(port->uport_dev)) { @@ -958,6 +989,22 @@ static int mock_cxl_port_enumerate_dports(struct cxl_port *port) return -ENXIO; } + *port_array = array; + *port_array_size = array_size; + + return 0; +} + +static int mock_cxl_port_enumerate_dports(struct cxl_port *port) +{ + struct platform_device **array; + int i, array_size; + int rc; + + rc = get_port_array(port, &array, &array_size); + if (rc) + return rc; + for (i = 0; i < array_size; i++) { struct platform_device *pdev = array[i]; struct cxl_dport *dport; @@ -979,6 +1026,36 @@ static int mock_cxl_port_enumerate_dports(struct cxl_port *port) return 0; } +static struct cxl_dport *mock_cxl_add_dport_by_dev(struct cxl_port *port, + struct device *dport_dev) +{ + struct platform_device **array; + int rc, i, array_size; + + rc = get_port_array(port, &array, &array_size); + if (rc) + return ERR_PTR(rc); + + for (i = 0; i < array_size; i++) { + struct platform_device *pdev = array[i]; + + if (pdev->dev.parent != port->uport_dev) { + dev_dbg(&port->dev, "%s: mismatch parent %s\n", + dev_name(port->uport_dev), + dev_name(pdev->dev.parent)); + continue; + } + + if (&pdev->dev != dport_dev) + continue; + + return devm_cxl_add_dport(port, &pdev->dev, pdev->id, + CXL_RESOURCE_NONE); + } + + return ERR_PTR(-ENODEV); +} + /* * Faking the cxl_dpa_perf for the memdev when appropriate. */ @@ -1035,11 +1112,11 @@ static struct cxl_mock_ops cxl_mock_ops = { .acpi_table_parse_cedt = mock_acpi_table_parse_cedt, .acpi_evaluate_integer = mock_acpi_evaluate_integer, .acpi_pci_find_root = mock_acpi_pci_find_root, + .devm_cxl_switch_port_decoders_setup = mock_cxl_switch_port_decoders_setup, + .devm_cxl_endpoint_decoders_setup = mock_cxl_endpoint_decoders_setup, .devm_cxl_port_enumerate_dports = mock_cxl_port_enumerate_dports, - .devm_cxl_setup_hdm = mock_cxl_setup_hdm, - .devm_cxl_add_passthrough_decoder = mock_cxl_add_passthrough_decoder, - .devm_cxl_enumerate_decoders = mock_cxl_enumerate_decoders, .cxl_endpoint_parse_cdat = mock_cxl_endpoint_parse_cdat, + .devm_cxl_add_dport_by_dev = mock_cxl_add_dport_by_dev, .list = LIST_HEAD_INIT(cxl_mock_ops.list), }; diff --git a/tools/testing/cxl/test/mock.c b/tools/testing/cxl/test/mock.c index 1989ae020df3..995269a75cbd 100644 --- a/tools/testing/cxl/test/mock.c +++ b/tools/testing/cxl/test/mock.c @@ -10,12 +10,21 @@ #include <cxlmem.h> #include <cxlpci.h> #include "mock.h" +#include "../exports.h" static LIST_HEAD(mock); +static struct cxl_dport * +redirect_devm_cxl_add_dport_by_dev(struct cxl_port *port, + struct device *dport_dev); +static int redirect_devm_cxl_switch_port_decoders_setup(struct cxl_port *port); + void register_cxl_mock_ops(struct cxl_mock_ops *ops) { list_add_rcu(&ops->list, &mock); + _devm_cxl_add_dport_by_dev = redirect_devm_cxl_add_dport_by_dev; + _devm_cxl_switch_port_decoders_setup = + redirect_devm_cxl_switch_port_decoders_setup; } EXPORT_SYMBOL_GPL(register_cxl_mock_ops); @@ -23,6 +32,9 @@ DEFINE_STATIC_SRCU(cxl_mock_srcu); void unregister_cxl_mock_ops(struct cxl_mock_ops *ops) { + _devm_cxl_switch_port_decoders_setup = + __devm_cxl_switch_port_decoders_setup; + _devm_cxl_add_dport_by_dev = __devm_cxl_add_dport_by_dev; list_del_rcu(&ops->list); synchronize_srcu(&cxl_mock_srcu); } @@ -131,55 +143,34 @@ __wrap_nvdimm_bus_register(struct device *dev, } EXPORT_SYMBOL_GPL(__wrap_nvdimm_bus_register); -struct cxl_hdm *__wrap_devm_cxl_setup_hdm(struct cxl_port *port, - struct cxl_endpoint_dvsec_info *info) - -{ - int index; - struct cxl_hdm *cxlhdm; - struct cxl_mock_ops *ops = get_cxl_mock_ops(&index); - - if (ops && ops->is_mock_port(port->uport_dev)) - cxlhdm = ops->devm_cxl_setup_hdm(port, info); - else - cxlhdm = devm_cxl_setup_hdm(port, info); - put_cxl_mock_ops(index); - - return cxlhdm; -} -EXPORT_SYMBOL_NS_GPL(__wrap_devm_cxl_setup_hdm, "CXL"); - -int __wrap_devm_cxl_add_passthrough_decoder(struct cxl_port *port) +int redirect_devm_cxl_switch_port_decoders_setup(struct cxl_port *port) { int rc, index; struct cxl_mock_ops *ops = get_cxl_mock_ops(&index); if (ops && ops->is_mock_port(port->uport_dev)) - rc = ops->devm_cxl_add_passthrough_decoder(port); + rc = ops->devm_cxl_switch_port_decoders_setup(port); else - rc = devm_cxl_add_passthrough_decoder(port); + rc = __devm_cxl_switch_port_decoders_setup(port); put_cxl_mock_ops(index); return rc; } -EXPORT_SYMBOL_NS_GPL(__wrap_devm_cxl_add_passthrough_decoder, "CXL"); -int __wrap_devm_cxl_enumerate_decoders(struct cxl_hdm *cxlhdm, - struct cxl_endpoint_dvsec_info *info) +int __wrap_devm_cxl_endpoint_decoders_setup(struct cxl_port *port) { int rc, index; - struct cxl_port *port = cxlhdm->port; struct cxl_mock_ops *ops = get_cxl_mock_ops(&index); if (ops && ops->is_mock_port(port->uport_dev)) - rc = ops->devm_cxl_enumerate_decoders(cxlhdm, info); + rc = ops->devm_cxl_endpoint_decoders_setup(port); else - rc = devm_cxl_enumerate_decoders(cxlhdm, info); + rc = devm_cxl_endpoint_decoders_setup(port); put_cxl_mock_ops(index); return rc; } -EXPORT_SYMBOL_NS_GPL(__wrap_devm_cxl_enumerate_decoders, "CXL"); +EXPORT_SYMBOL_NS_GPL(__wrap_devm_cxl_endpoint_decoders_setup, "CXL"); int __wrap_devm_cxl_port_enumerate_dports(struct cxl_port *port) { @@ -211,39 +202,6 @@ int __wrap_cxl_await_media_ready(struct cxl_dev_state *cxlds) } EXPORT_SYMBOL_NS_GPL(__wrap_cxl_await_media_ready, "CXL"); -int __wrap_cxl_hdm_decode_init(struct cxl_dev_state *cxlds, - struct cxl_hdm *cxlhdm, - struct cxl_endpoint_dvsec_info *info) -{ - int rc = 0, index; - struct cxl_mock_ops *ops = get_cxl_mock_ops(&index); - - if (ops && ops->is_mock_dev(cxlds->dev)) - rc = 0; - else - rc = cxl_hdm_decode_init(cxlds, cxlhdm, info); - put_cxl_mock_ops(index); - - return rc; -} -EXPORT_SYMBOL_NS_GPL(__wrap_cxl_hdm_decode_init, "CXL"); - -int __wrap_cxl_dvsec_rr_decode(struct cxl_dev_state *cxlds, - struct cxl_endpoint_dvsec_info *info) -{ - int rc = 0, index; - struct cxl_mock_ops *ops = get_cxl_mock_ops(&index); - - if (ops && ops->is_mock_dev(cxlds->dev)) - rc = 0; - else - rc = cxl_dvsec_rr_decode(cxlds, info); - put_cxl_mock_ops(index); - - return rc; -} -EXPORT_SYMBOL_NS_GPL(__wrap_cxl_dvsec_rr_decode, "CXL"); - struct cxl_dport *__wrap_devm_cxl_add_rch_dport(struct cxl_port *port, struct device *dport_dev, int port_id, @@ -311,6 +269,22 @@ void __wrap_cxl_dport_init_ras_reporting(struct cxl_dport *dport, struct device } EXPORT_SYMBOL_NS_GPL(__wrap_cxl_dport_init_ras_reporting, "CXL"); +struct cxl_dport *redirect_devm_cxl_add_dport_by_dev(struct cxl_port *port, + struct device *dport_dev) +{ + int index; + struct cxl_mock_ops *ops = get_cxl_mock_ops(&index); + struct cxl_dport *dport; + + if (ops && ops->is_mock_port(port->uport_dev)) + dport = ops->devm_cxl_add_dport_by_dev(port, dport_dev); + else + dport = __devm_cxl_add_dport_by_dev(port, dport_dev); + put_cxl_mock_ops(index); + + return dport; +} + MODULE_LICENSE("GPL v2"); MODULE_DESCRIPTION("cxl_test: emulation module"); MODULE_IMPORT_NS("ACPI"); diff --git a/tools/testing/cxl/test/mock.h b/tools/testing/cxl/test/mock.h index d1b0271d2822..4ed932e76aae 100644 --- a/tools/testing/cxl/test/mock.h +++ b/tools/testing/cxl/test/mock.h @@ -20,12 +20,11 @@ struct cxl_mock_ops { bool (*is_mock_port)(struct device *dev); bool (*is_mock_dev)(struct device *dev); int (*devm_cxl_port_enumerate_dports)(struct cxl_port *port); - struct cxl_hdm *(*devm_cxl_setup_hdm)( - struct cxl_port *port, struct cxl_endpoint_dvsec_info *info); - int (*devm_cxl_add_passthrough_decoder)(struct cxl_port *port); - int (*devm_cxl_enumerate_decoders)( - struct cxl_hdm *hdm, struct cxl_endpoint_dvsec_info *info); + int (*devm_cxl_switch_port_decoders_setup)(struct cxl_port *port); + int (*devm_cxl_endpoint_decoders_setup)(struct cxl_port *port); void (*cxl_endpoint_parse_cdat)(struct cxl_port *port); + struct cxl_dport *(*devm_cxl_add_dport_by_dev)(struct cxl_port *port, + struct device *dport_dev); }; void register_cxl_mock_ops(struct cxl_mock_ops *ops); diff --git a/tools/testing/nvdimm/test/ndtest.c b/tools/testing/nvdimm/test/ndtest.c index 68a064ce598c..8e3b6be53839 100644 --- a/tools/testing/nvdimm/test/ndtest.c +++ b/tools/testing/nvdimm/test/ndtest.c @@ -850,11 +850,22 @@ static int ndtest_probe(struct platform_device *pdev) p->dcr_dma = devm_kcalloc(&p->pdev.dev, NUM_DCR, sizeof(dma_addr_t), GFP_KERNEL); + if (!p->dcr_dma) { + rc = -ENOMEM; + goto err; + } p->label_dma = devm_kcalloc(&p->pdev.dev, NUM_DCR, sizeof(dma_addr_t), GFP_KERNEL); + if (!p->label_dma) { + rc = -ENOMEM; + goto err; + } p->dimm_dma = devm_kcalloc(&p->pdev.dev, NUM_DCR, sizeof(dma_addr_t), GFP_KERNEL); - + if (!p->dimm_dma) { + rc = -ENOMEM; + goto err; + } rc = ndtest_nvdimm_init(p); if (rc) goto err; diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index 36d03860d9d8..c46ebdb9b8ef 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -125,6 +125,7 @@ TARGETS += uevent TARGETS += user_events TARGETS += vDSO TARGETS += mm +TARGETS += vfio TARGETS += x86 TARGETS += x86/bugs TARGETS += zram diff --git a/tools/testing/selftests/drivers/net/Makefile b/tools/testing/selftests/drivers/net/Makefile index bd3af9a34e2f..6e41635bd55a 100644 --- a/tools/testing/selftests/drivers/net/Makefile +++ b/tools/testing/selftests/drivers/net/Makefile @@ -10,6 +10,7 @@ TEST_GEN_FILES := \ # end of TEST_GEN_FILES TEST_PROGS := \ + hds.py \ napi_id.py \ napi_threaded.py \ netcons_basic.sh \ @@ -21,9 +22,8 @@ TEST_PROGS := \ ping.py \ psp.py \ queues.py \ - stats.py \ shaper.py \ - hds.py \ + stats.py \ xdp.py \ # end of TEST_PROGS diff --git a/tools/testing/selftests/drivers/net/bonding/Makefile b/tools/testing/selftests/drivers/net/bonding/Makefile index 2f095cf67d9a..402d4ee84f2e 100644 --- a/tools/testing/selftests/drivers/net/bonding/Makefile +++ b/tools/testing/selftests/drivers/net/bonding/Makefile @@ -4,24 +4,27 @@ TEST_PROGS := \ bond-arp-interval-causes-panic.sh \ bond-break-lacpdu-tx.sh \ + bond-eth-type-change.sh \ bond-lladdr-target.sh \ + bond_ipsec_offload.sh \ + bond_lacp_prio.sh \ + bond_macvlan_ipvlan.sh \ + bond_options.sh \ + bond_passive_lacp.sh \ dev_addr_lists.sh \ mode-1-recovery-updelay.sh \ mode-2-recovery-updelay.sh \ - bond_options.sh \ - bond-eth-type-change.sh \ - bond_macvlan_ipvlan.sh \ - bond_passive_lacp.sh \ - bond_lacp_prio.sh - bond_ipsec_offload.sh +# end of TEST_PROGS TEST_FILES := \ - lag_lib.sh \ bond_topo_2d1c.sh \ - bond_topo_3d1c.sh + bond_topo_3d1c.sh \ + lag_lib.sh \ +# end of TEST_FILES TEST_INCLUDES := \ + ../../../net/lib.sh \ ../../../net/forwarding/lib.sh \ - ../../../net/lib.sh +# end of TEST_INCLUDES include ../../../lib.mk diff --git a/tools/testing/selftests/drivers/net/bonding/config b/tools/testing/selftests/drivers/net/bonding/config index e5b7a8db4dfa..6bb290abd48b 100644 --- a/tools/testing/selftests/drivers/net/bonding/config +++ b/tools/testing/selftests/drivers/net/bonding/config @@ -1,17 +1,17 @@ CONFIG_BONDING=y CONFIG_BRIDGE=y CONFIG_DUMMY=y +CONFIG_INET_ESP=y +CONFIG_INET_ESP_OFFLOAD=y CONFIG_IPV6=y -CONFIG_MACVLAN=y CONFIG_IPVLAN=y +CONFIG_MACVLAN=y CONFIG_NET_ACT_GACT=y CONFIG_NET_CLS_FLOWER=y CONFIG_NET_CLS_MATCHALL=m +CONFIG_NETDEVSIM=m CONFIG_NET_SCH_INGRESS=y CONFIG_NLMON=y CONFIG_VETH=y CONFIG_VLAN_8021Q=m -CONFIG_INET_ESP=y -CONFIG_INET_ESP_OFFLOAD=y CONFIG_XFRM_USER=m -CONFIG_NETDEVSIM=m diff --git a/tools/testing/selftests/drivers/net/config b/tools/testing/selftests/drivers/net/config index 601431248d5b..77ccf83d87e0 100644 --- a/tools/testing/selftests/drivers/net/config +++ b/tools/testing/selftests/drivers/net/config @@ -3,8 +3,8 @@ CONFIG_DEBUG_INFO_BTF=y CONFIG_DEBUG_INFO_BTF_MODULES=n CONFIG_INET_PSP=y CONFIG_IPV6=y -CONFIG_NETDEVSIM=m CONFIG_NETCONSOLE=m CONFIG_NETCONSOLE_DYNAMIC=y CONFIG_NETCONSOLE_EXTENDED_LOG=y +CONFIG_NETDEVSIM=m CONFIG_XDP_SOCKETS=y diff --git a/tools/testing/selftests/drivers/net/dsa/Makefile b/tools/testing/selftests/drivers/net/dsa/Makefile index cd6817fe5be6..7994bd0e5c44 100644 --- a/tools/testing/selftests/drivers/net/dsa/Makefile +++ b/tools/testing/selftests/drivers/net/dsa/Makefile @@ -1,6 +1,7 @@ # SPDX-License-Identifier: GPL-2.0+ OR MIT -TEST_PROGS = bridge_locked_port.sh \ +TEST_PROGS := \ + bridge_locked_port.sh \ bridge_mdb.sh \ bridge_mld.sh \ bridge_vlan_aware.sh \ @@ -9,11 +10,13 @@ TEST_PROGS = bridge_locked_port.sh \ local_termination.sh \ no_forwarding.sh \ tc_actions.sh \ - test_bridge_fdb_stress.sh + test_bridge_fdb_stress.sh \ +# end of TEST_PROGS TEST_FILES := \ + forwarding.config \ run_net_forwarding_test.sh \ - forwarding.config +# end of TEST_FILES TEST_INCLUDES := \ ../../../net/forwarding/bridge_locked_port.sh \ @@ -27,6 +30,7 @@ TEST_INCLUDES := \ ../../../net/forwarding/no_forwarding.sh \ ../../../net/forwarding/tc_actions.sh \ ../../../net/forwarding/tc_common.sh \ - ../../../net/lib.sh + ../../../net/lib.sh \ +# end of TEST_INCLUDES include ../../../lib.mk diff --git a/tools/testing/selftests/drivers/net/hds.py b/tools/testing/selftests/drivers/net/hds.py index a2011474e625..c4fe049e9baa 100755 --- a/tools/testing/selftests/drivers/net/hds.py +++ b/tools/testing/selftests/drivers/net/hds.py @@ -3,11 +3,12 @@ import errno import os +import random from typing import Union from lib.py import ksft_run, ksft_exit, ksft_eq, ksft_raises, KsftSkipEx from lib.py import CmdExitFailure, EthtoolFamily, NlError from lib.py import NetDrvEnv -from lib.py import defer, ethtool, ip, random +from lib.py import defer, ethtool, ip def _get_hds_mode(cfg, netnl) -> str: diff --git a/tools/testing/selftests/drivers/net/hw/Makefile b/tools/testing/selftests/drivers/net/hw/Makefile index ee09a40d532c..8133d1a0051c 100644 --- a/tools/testing/selftests/drivers/net/hw/Makefile +++ b/tools/testing/selftests/drivers/net/hw/Makefile @@ -32,8 +32,8 @@ TEST_FILES := \ TEST_INCLUDES := \ $(wildcard lib/py/*.py ../lib/py/*.py) \ ../../../net/lib.sh \ - ../../../net/forwarding/lib.sh \ ../../../net/forwarding/ipip_lib.sh \ + ../../../net/forwarding/lib.sh \ ../../../net/forwarding/tc_common.sh \ # @@ -45,7 +45,11 @@ TEST_GEN_FILES += $(patsubst %.c,%.o,$(wildcard *.bpf.c)) include ../../../lib.mk # YNL build -YNL_GENS := ethtool netdev +YNL_GENS := \ + ethtool \ + netdev \ +# end of YNL_GENS + include ../../../net/ynl.mk include ../../../net/bpf.mk diff --git a/tools/testing/selftests/drivers/net/hw/config b/tools/testing/selftests/drivers/net/hw/config index e8a06aa1471c..2307aa001be1 100644 --- a/tools/testing/selftests/drivers/net/hw/config +++ b/tools/testing/selftests/drivers/net/hw/config @@ -1,3 +1,7 @@ +CONFIG_FAIL_FUNCTION=y +CONFIG_FAULT_INJECTION=y +CONFIG_FAULT_INJECTION_DEBUG_FS=y +CONFIG_FUNCTION_ERROR_INJECTION=y CONFIG_IO_URING=y CONFIG_IPV6=y CONFIG_IPV6_GRE=y diff --git a/tools/testing/selftests/drivers/net/hw/pp_alloc_fail.py b/tools/testing/selftests/drivers/net/hw/pp_alloc_fail.py index ad192fef3117..2a51b60df8a1 100755 --- a/tools/testing/selftests/drivers/net/hw/pp_alloc_fail.py +++ b/tools/testing/selftests/drivers/net/hw/pp_alloc_fail.py @@ -1,8 +1,13 @@ #!/usr/bin/env python3 # SPDX-License-Identifier: GPL-2.0 +""" +Test driver resilience vs page pool allocation failures. +""" + import errno import time +import math import os from lib.py import ksft_run, ksft_exit, ksft_pr from lib.py import KsftSkipEx, KsftFailEx @@ -13,7 +18,8 @@ from lib.py import cmd, tool, GenerateTraffic def _write_fail_config(config): for key, value in config.items(): - with open("/sys/kernel/debug/fail_function/" + key, "w") as fp: + path = "/sys/kernel/debug/fail_function/" + with open(path + key, "w", encoding='ascii') as fp: fp.write(str(value) + "\n") @@ -22,8 +28,7 @@ def _enable_pp_allocation_fail(): raise KsftSkipEx("Kernel built without function error injection (or DebugFS)") if not os.path.exists("/sys/kernel/debug/fail_function/page_pool_alloc_netmems"): - with open("/sys/kernel/debug/fail_function/inject", "w") as fp: - fp.write("page_pool_alloc_netmems\n") + _write_fail_config({"inject": "page_pool_alloc_netmems"}) _write_fail_config({ "verbose": 0, @@ -38,8 +43,7 @@ def _disable_pp_allocation_fail(): return if os.path.exists("/sys/kernel/debug/fail_function/page_pool_alloc_netmems"): - with open("/sys/kernel/debug/fail_function/inject", "w") as fp: - fp.write("\n") + _write_fail_config({"inject": ""}) _write_fail_config({ "probability": 0, @@ -48,6 +52,10 @@ def _disable_pp_allocation_fail(): def test_pp_alloc(cfg, netdevnl): + """ + Configure page pool allocation fail injection while traffic is running. + """ + def get_stats(): return netdevnl.qstats_get({"ifindex": cfg.ifindex}, dump=True)[0] @@ -55,7 +63,7 @@ def test_pp_alloc(cfg, netdevnl): stat1 = get_stats() time.sleep(1) stat2 = get_stats() - if stat2['rx-packets'] - stat1['rx-packets'] < 15000: + if stat2['rx-packets'] - stat1['rx-packets'] < 4000: raise KsftFailEx("Traffic seems low:", stat2['rx-packets'] - stat1['rx-packets']) @@ -82,11 +90,16 @@ def test_pp_alloc(cfg, netdevnl): time.sleep(3) s2 = get_stats() - if s2['rx-alloc-fail'] - s1['rx-alloc-fail'] < 1: + seen_fails = s2['rx-alloc-fail'] - s1['rx-alloc-fail'] + if seen_fails < 1: raise KsftSkipEx("Allocation failures not increasing") - if s2['rx-alloc-fail'] - s1['rx-alloc-fail'] < 100: - raise KsftSkipEx("Allocation increasing too slowly", s2['rx-alloc-fail'] - s1['rx-alloc-fail'], - "packets:", s2['rx-packets'] - s1['rx-packets']) + pkts = s2['rx-packets'] - s1['rx-packets'] + # Expecting one failure per 512 buffers, 3.1x safety margin + want_fails = math.floor(pkts / 512 / 3.1) + if seen_fails < want_fails: + raise KsftSkipEx("Allocation increasing too slowly", seen_fails, + "packets:", pkts) + ksft_pr(f"Seen: pkts:{pkts} fails:{seen_fails} (pass thrs:{want_fails})") # Basic failures are fine, try to wobble some settings to catch extra failures check_traffic_flowing() @@ -105,7 +118,7 @@ def test_pp_alloc(cfg, netdevnl): else: ksft_pr("ethtool -G change retval: did not succeed", new_g) else: - ksft_pr("ethtool -G change retval: did not try") + ksft_pr("ethtool -G change retval: did not try") time.sleep(0.1) check_traffic_flowing() @@ -119,6 +132,7 @@ def test_pp_alloc(cfg, netdevnl): def main() -> None: + """ Ksft boiler plate main """ netdevnl = NetdevFamily() with NetDrvEpEnv(__file__, nsim_test=False) as cfg: diff --git a/tools/testing/selftests/drivers/net/lib/py/__init__.py b/tools/testing/selftests/drivers/net/lib/py/__init__.py index 2a645415c4ca..e6c070f32f51 100644 --- a/tools/testing/selftests/drivers/net/lib/py/__init__.py +++ b/tools/testing/selftests/drivers/net/lib/py/__init__.py @@ -1,5 +1,13 @@ # SPDX-License-Identifier: GPL-2.0 +""" +Driver test environment. +NetDrvEnv and NetDrvEpEnv are the main environment classes. +Former is for local host only tests, latter creates / connects +to a remote endpoint. See NIPA wiki for more information about +running and writing driver tests. +""" + import sys from pathlib import Path @@ -8,26 +16,39 @@ KSFT_DIR = (Path(__file__).parent / "../../../..").resolve() try: sys.path.append(KSFT_DIR.as_posix()) - from net.lib.py import * - # Import one by one to avoid pylint false positives + from net.lib.py import NetNS, NetNSEnter, NetdevSimDev from net.lib.py import EthtoolFamily, NetdevFamily, NetshaperFamily, \ NlError, RtnlFamily, DevlinkFamily, PSPFamily from net.lib.py import CmdExitFailure from net.lib.py import bkg, cmd, bpftool, bpftrace, defer, ethtool, \ fd_read_timeout, ip, rand_port, tool, wait_port_listen, wait_file - from net.lib.py import fd_read_timeout from net.lib.py import KsftSkipEx, KsftFailEx, KsftXfailEx from net.lib.py import ksft_disruptive, ksft_exit, ksft_pr, ksft_run, \ ksft_setup from net.lib.py import ksft_eq, ksft_ge, ksft_in, ksft_is, ksft_lt, \ ksft_ne, ksft_not_in, ksft_raises, ksft_true, ksft_gt, ksft_not_none + + __all__ = ["NetNS", "NetNSEnter", "NetdevSimDev", + "EthtoolFamily", "NetdevFamily", "NetshaperFamily", + "NlError", "RtnlFamily", "DevlinkFamily", "PSPFamily", + "CmdExitFailure", + "bkg", "cmd", "bpftool", "bpftrace", "defer", "ethtool", + "fd_read_timeout", "ip", "rand_port", "tool", + "wait_port_listen", "wait_file", + "KsftSkipEx", "KsftFailEx", "KsftXfailEx", + "ksft_disruptive", "ksft_exit", "ksft_pr", "ksft_run", + "ksft_setup", + "ksft_eq", "ksft_ge", "ksft_in", "ksft_is", "ksft_lt", + "ksft_ne", "ksft_not_in", "ksft_raises", "ksft_true", "ksft_gt", + "ksft_not_none", "ksft_not_none"] + + from .env import NetDrvEnv, NetDrvEpEnv + from .load import GenerateTraffic + from .remote import Remote + + __all__ += ["NetDrvEnv", "NetDrvEpEnv", "GenerateTraffic", "Remote"] except ModuleNotFoundError as e: - ksft_pr("Failed importing `net` library from kernel sources") - ksft_pr(str(e)) - ktap_result(True, comment="SKIP") + print("Failed importing `net` library from kernel sources") + print(str(e)) sys.exit(4) - -from .env import * -from .load import * -from .remote import Remote diff --git a/tools/testing/selftests/drivers/net/netdevsim/Makefile b/tools/testing/selftests/drivers/net/netdevsim/Makefile index 07b7c46d3311..daf51113c827 100644 --- a/tools/testing/selftests/drivers/net/netdevsim/Makefile +++ b/tools/testing/selftests/drivers/net/netdevsim/Makefile @@ -1,6 +1,7 @@ # SPDX-License-Identifier: GPL-2.0+ OR MIT -TEST_PROGS = devlink.sh \ +TEST_PROGS := \ + devlink.sh \ devlink_in_netns.sh \ devlink_trap.sh \ ethtool-coalesce.sh \ @@ -17,5 +18,6 @@ TEST_PROGS = devlink.sh \ psample.sh \ tc-mq-visibility.sh \ udp_tunnel_nic.sh \ +# end of TEST_PROGS include ../../../lib.mk diff --git a/tools/testing/selftests/drivers/net/team/Makefile b/tools/testing/selftests/drivers/net/team/Makefile index 89d854c7e674..1340b3df9c31 100644 --- a/tools/testing/selftests/drivers/net/team/Makefile +++ b/tools/testing/selftests/drivers/net/team/Makefile @@ -1,13 +1,18 @@ # SPDX-License-Identifier: GPL-2.0 # Makefile for net selftests -TEST_PROGS := dev_addr_lists.sh propagation.sh options.sh +TEST_PROGS := \ + dev_addr_lists.sh \ + options.sh \ + propagation.sh \ +# end of TEST_PROGS TEST_INCLUDES := \ ../bonding/lag_lib.sh \ ../../../net/forwarding/lib.sh \ - ../../../net/lib.sh \ ../../../net/in_netns.sh \ - ../../../net/lib/sh/defer.sh + ../../../net/lib.sh \ + ../../../net/lib/sh/defer.sh \ +# end of TEST_INCLUDES include ../../../lib.mk diff --git a/tools/testing/selftests/drivers/net/virtio_net/Makefile b/tools/testing/selftests/drivers/net/virtio_net/Makefile index 7ec7cd3ab2cc..868ece3fea1f 100644 --- a/tools/testing/selftests/drivers/net/virtio_net/Makefile +++ b/tools/testing/selftests/drivers/net/virtio_net/Makefile @@ -1,15 +1,12 @@ # SPDX-License-Identifier: GPL-2.0+ OR MIT -TEST_PROGS = basic_features.sh \ - # +TEST_PROGS = basic_features.sh -TEST_FILES = \ - virtio_net_common.sh \ - # +TEST_FILES = virtio_net_common.sh TEST_INCLUDES = \ - ../../../net/forwarding/lib.sh \ - ../../../net/lib.sh \ - # + ../../../net/forwarding/lib.sh \ + ../../../net/lib.sh \ +# end of TEST_INCLUDES include ../../../lib.mk diff --git a/tools/testing/selftests/drivers/net/xdp.py b/tools/testing/selftests/drivers/net/xdp.py index 08fea4230759..a148004e1c36 100755 --- a/tools/testing/selftests/drivers/net/xdp.py +++ b/tools/testing/selftests/drivers/net/xdp.py @@ -11,8 +11,9 @@ import string from dataclasses import dataclass from enum import Enum -from lib.py import ksft_run, ksft_exit, ksft_eq, ksft_ne, ksft_pr -from lib.py import KsftFailEx, NetDrvEpEnv, EthtoolFamily, NlError +from lib.py import ksft_run, ksft_exit, ksft_eq, ksft_ge, ksft_ne, ksft_pr +from lib.py import KsftFailEx, NetDrvEpEnv +from lib.py import EthtoolFamily, NetdevFamily, NlError from lib.py import bkg, cmd, rand_port, wait_port_listen from lib.py import ip, bpftool, defer @@ -541,11 +542,11 @@ def get_hds_thresh(cfg): The HDS threshold value. If the threshold is not supported or an error occurs, a default value of 1500 is returned. """ - netnl = cfg.netnl + ethnl = cfg.ethnl hds_thresh = 1500 try: - rings = netnl.rings_get({'header': {'dev-index': cfg.ifindex}}) + rings = ethnl.rings_get({'header': {'dev-index': cfg.ifindex}}) if 'hds-thresh' not in rings: ksft_pr(f'hds-thresh not supported. Using default: {hds_thresh}') return hds_thresh @@ -562,7 +563,7 @@ def _test_xdp_native_head_adjst(cfg, prog, pkt_sz_lst, offset_lst): Args: cfg: Configuration object containing network settings. - netnl: Network namespace or link object (not used in this function). + ethnl: Network namespace or link object (not used in this function). This function sets up the packet size and offset lists, then performs the head adjustment test by sending and receiving UDP packets. @@ -671,6 +672,88 @@ def test_xdp_native_adjst_head_shrnk_data(cfg): _validate_res(res, offset_lst, pkt_sz_lst) +def _test_xdp_native_ifc_stats(cfg, act): + cfg.require_cmd("socat") + + bpf_info = BPFProgInfo("xdp_prog", "xdp_native.bpf.o", "xdp", 1500) + prog_info = _load_xdp_prog(cfg, bpf_info) + port = rand_port() + + _set_xdp_map("map_xdp_setup", TestConfig.MODE.value, act.value) + _set_xdp_map("map_xdp_setup", TestConfig.PORT.value, port) + + # Discard the input, but we need a listener to avoid ICMP errors + rx_udp = f"socat -{cfg.addr_ipver} -T 2 -u UDP-RECV:{port},reuseport " + \ + "/dev/null" + # Listener runs on "remote" in case of XDP_TX + rx_host = cfg.remote if act == XDPAction.TX else None + # We want to spew 2000 packets quickly, bash seems to do a good enough job + tx_udp = f"exec 5<>/dev/udp/{cfg.addr}/{port}; " \ + "for i in `seq 2000`; do echo a >&5; done; exec 5>&-" + + cfg.wait_hw_stats_settle() + # Qstats have more clearly defined semantics than rtnetlink. + # XDP is the "first layer of the stack" so XDP packets should be counted + # as received and sent as if the decision was made in the routing layer. + before = cfg.netnl.qstats_get({"ifindex": cfg.ifindex}, dump=True)[0] + + with bkg(rx_udp, host=rx_host, exit_wait=True): + wait_port_listen(port, proto="udp", host=rx_host) + cmd(tx_udp, host=cfg.remote, shell=True) + + cfg.wait_hw_stats_settle() + after = cfg.netnl.qstats_get({"ifindex": cfg.ifindex}, dump=True)[0] + + ksft_ge(after['rx-packets'] - before['rx-packets'], 2000) + if act == XDPAction.TX: + ksft_ge(after['tx-packets'] - before['tx-packets'], 2000) + + expected_pkts = 2000 + stats = _get_stats(prog_info["maps"]["map_xdp_stats"]) + ksft_eq(stats[XDPStats.RX.value], expected_pkts, "XDP RX stats mismatch") + if act == XDPAction.TX: + ksft_eq(stats[XDPStats.TX.value], expected_pkts, "XDP TX stats mismatch") + + # Flip the ring count back and forth to make sure the stats from XDP rings + # don't get lost. + chans = cfg.ethnl.channels_get({'header': {'dev-index': cfg.ifindex}}) + if chans.get('combined-count', 0) > 1: + cfg.ethnl.channels_set({'header': {'dev-index': cfg.ifindex}, + 'combined-count': 1}) + cfg.ethnl.channels_set({'header': {'dev-index': cfg.ifindex}, + 'combined-count': chans['combined-count']}) + before = after + after = cfg.netnl.qstats_get({"ifindex": cfg.ifindex}, dump=True)[0] + + ksft_ge(after['rx-packets'], before['rx-packets']) + if act == XDPAction.TX: + ksft_ge(after['tx-packets'], before['tx-packets']) + + +def test_xdp_native_qstats_pass(cfg): + """ + Send 2000 messages, expect XDP_PASS, make sure the packets were counted + to interface level qstats (Rx). + """ + _test_xdp_native_ifc_stats(cfg, XDPAction.PASS) + + +def test_xdp_native_qstats_drop(cfg): + """ + Send 2000 messages, expect XDP_DROP, make sure the packets were counted + to interface level qstats (Rx). + """ + _test_xdp_native_ifc_stats(cfg, XDPAction.DROP) + + +def test_xdp_native_qstats_tx(cfg): + """ + Send 2000 messages, expect XDP_TX, make sure the packets were counted + to interface level qstats (Rx and Tx) + """ + _test_xdp_native_ifc_stats(cfg, XDPAction.TX) + + def main(): """ Main function to execute the XDP tests. @@ -681,7 +764,8 @@ def main(): function to execute the tests. """ with NetDrvEpEnv(__file__) as cfg: - cfg.netnl = EthtoolFamily() + cfg.ethnl = EthtoolFamily() + cfg.netnl = NetdevFamily() ksft_run( [ test_xdp_native_pass_sb, @@ -694,6 +778,9 @@ def main(): test_xdp_native_adjst_tail_shrnk_data, test_xdp_native_adjst_head_grow_data, test_xdp_native_adjst_head_shrnk_data, + test_xdp_native_qstats_pass, + test_xdp_native_qstats_drop, + test_xdp_native_qstats_tx, ], args=(cfg,)) ksft_exit() diff --git a/tools/testing/selftests/filesystems/binderfs/binderfs_test.c b/tools/testing/selftests/filesystems/binderfs/binderfs_test.c index 81db85a5cc16..39a68078a79b 100644 --- a/tools/testing/selftests/filesystems/binderfs/binderfs_test.c +++ b/tools/testing/selftests/filesystems/binderfs/binderfs_test.c @@ -65,6 +65,7 @@ static int __do_binderfs_test(struct __test_metadata *_metadata) "oneway_spam_detection", "extended_error", "freeze_notification", + "transaction_report", }; change_mountns(_metadata); diff --git a/tools/testing/selftests/hid/hid_common.h b/tools/testing/selftests/hid/hid_common.h index f77f69c6657d..8085519c47cb 100644 --- a/tools/testing/selftests/hid/hid_common.h +++ b/tools/testing/selftests/hid/hid_common.h @@ -230,6 +230,12 @@ static int uhid_event(struct __test_metadata *_metadata, int fd) break; case UHID_SET_REPORT: UHID_LOG("UHID_SET_REPORT from uhid-dev"); + + answer.type = UHID_SET_REPORT_REPLY; + answer.u.set_report_reply.id = ev.u.set_report.id; + answer.u.set_report_reply.err = 0; /* success */ + + uhid_write(_metadata, fd, &answer); break; default: TH_LOG("Invalid event from uhid-dev: %u", ev.type); diff --git a/tools/testing/selftests/hid/hidraw.c b/tools/testing/selftests/hid/hidraw.c index 821db37ba4bb..d625772f8b7c 100644 --- a/tools/testing/selftests/hid/hidraw.c +++ b/tools/testing/selftests/hid/hidraw.c @@ -2,6 +2,9 @@ /* Copyright (c) 2022-2024 Red Hat */ #include "hid_common.h" +#include <linux/input.h> +#include <string.h> +#include <sys/ioctl.h> /* for older kernels */ #ifndef HIDIOCREVOKE @@ -215,6 +218,476 @@ TEST_F(hidraw, write_event_revoked) pthread_mutex_unlock(&uhid_output_mtx); } +/* + * Test HIDIOCGRDESCSIZE ioctl to get report descriptor size + */ +TEST_F(hidraw, ioctl_rdescsize) +{ + int desc_size = 0; + int err; + + /* call HIDIOCGRDESCSIZE ioctl */ + err = ioctl(self->hidraw_fd, HIDIOCGRDESCSIZE, &desc_size); + ASSERT_EQ(err, 0) TH_LOG("HIDIOCGRDESCSIZE ioctl failed"); + + /* verify the size matches our test report descriptor */ + ASSERT_EQ(desc_size, sizeof(rdesc)) + TH_LOG("expected size %zu, got %d", sizeof(rdesc), desc_size); +} + +/* + * Test HIDIOCGRDESC ioctl to get report descriptor data + */ +TEST_F(hidraw, ioctl_rdesc) +{ + struct hidraw_report_descriptor desc; + int err; + + /* get the full report descriptor */ + desc.size = sizeof(rdesc); + err = ioctl(self->hidraw_fd, HIDIOCGRDESC, &desc); + ASSERT_EQ(err, 0) TH_LOG("HIDIOCGRDESC ioctl failed"); + + /* verify the descriptor data matches our test descriptor */ + ASSERT_EQ(memcmp(desc.value, rdesc, sizeof(rdesc)), 0) + TH_LOG("report descriptor data mismatch"); +} + +/* + * Test HIDIOCGRDESC ioctl with smaller buffer size + */ +TEST_F(hidraw, ioctl_rdesc_small_buffer) +{ + struct hidraw_report_descriptor desc; + int err; + size_t small_size = sizeof(rdesc) / 2; /* request half the descriptor size */ + + /* get partial report descriptor */ + desc.size = small_size; + err = ioctl(self->hidraw_fd, HIDIOCGRDESC, &desc); + ASSERT_EQ(err, 0) TH_LOG("HIDIOCGRDESC ioctl failed with small buffer"); + + /* verify we got the first part of the descriptor */ + ASSERT_EQ(memcmp(desc.value, rdesc, small_size), 0) + TH_LOG("partial report descriptor data mismatch"); +} + +/* + * Test HIDIOCGRAWINFO ioctl to get device information + */ +TEST_F(hidraw, ioctl_rawinfo) +{ + struct hidraw_devinfo devinfo; + int err; + + /* get device info */ + err = ioctl(self->hidraw_fd, HIDIOCGRAWINFO, &devinfo); + ASSERT_EQ(err, 0) TH_LOG("HIDIOCGRAWINFO ioctl failed"); + + /* verify device info matches our test setup */ + ASSERT_EQ(devinfo.bustype, BUS_USB) + TH_LOG("expected bustype 0x03, got 0x%x", devinfo.bustype); + ASSERT_EQ(devinfo.vendor, 0x0001) + TH_LOG("expected vendor 0x0001, got 0x%x", devinfo.vendor); + ASSERT_EQ(devinfo.product, 0x0a37) + TH_LOG("expected product 0x0a37, got 0x%x", devinfo.product); +} + +/* + * Test HIDIOCGFEATURE ioctl to get feature report + */ +TEST_F(hidraw, ioctl_gfeature) +{ + __u8 buf[10] = {0}; + int err; + + /* set report ID 1 in first byte */ + buf[0] = 1; + + /* get feature report */ + err = ioctl(self->hidraw_fd, HIDIOCGFEATURE(sizeof(buf)), buf); + ASSERT_EQ(err, sizeof(feature_data)) TH_LOG("HIDIOCGFEATURE ioctl failed, got %d", err); + + /* verify we got the expected feature data */ + ASSERT_EQ(buf[0], feature_data[0]) + TH_LOG("expected feature_data[0] = %d, got %d", feature_data[0], buf[0]); + ASSERT_EQ(buf[1], feature_data[1]) + TH_LOG("expected feature_data[1] = %d, got %d", feature_data[1], buf[1]); +} + +/* + * Test HIDIOCGFEATURE ioctl with invalid report ID + */ +TEST_F(hidraw, ioctl_gfeature_invalid) +{ + __u8 buf[10] = {0}; + int err; + + /* set invalid report ID (not 1) */ + buf[0] = 2; + + /* try to get feature report */ + err = ioctl(self->hidraw_fd, HIDIOCGFEATURE(sizeof(buf)), buf); + ASSERT_LT(err, 0) TH_LOG("HIDIOCGFEATURE should have failed with invalid report ID"); + ASSERT_EQ(errno, EIO) TH_LOG("expected EIO, got errno %d", errno); +} + +/* + * Test ioctl with incorrect nr bits + */ +TEST_F(hidraw, ioctl_invalid_nr) +{ + char buf[256] = {0}; + int err; + unsigned int bad_cmd; + + /* + * craft an ioctl command with wrong _IOC_NR bits + */ + bad_cmd = _IOC(_IOC_WRITE|_IOC_READ, 'H', 0x00, sizeof(buf)); /* 0 is not valid */ + + /* test the ioctl */ + err = ioctl(self->hidraw_fd, bad_cmd, buf); + ASSERT_LT(err, 0) TH_LOG("ioctl read-write with wrong _IOC_NR (0) should have failed"); + ASSERT_EQ(errno, ENOTTY) + TH_LOG("expected ENOTTY for wrong read-write _IOC_NR (0), got errno %d", errno); + + /* + * craft an ioctl command with wrong _IOC_NR bits + */ + bad_cmd = _IOC(_IOC_READ, 'H', 0x00, sizeof(buf)); /* 0 is not valid */ + + /* test the ioctl */ + err = ioctl(self->hidraw_fd, bad_cmd, buf); + ASSERT_LT(err, 0) TH_LOG("ioctl read-only with wrong _IOC_NR (0) should have failed"); + ASSERT_EQ(errno, ENOTTY) + TH_LOG("expected ENOTTY for wrong read-only _IOC_NR (0), got errno %d", errno); + + /* also test with bigger number */ + bad_cmd = _IOC(_IOC_READ, 'H', 0x42, sizeof(buf)); /* 0x42 is not valid as well */ + + err = ioctl(self->hidraw_fd, bad_cmd, buf); + ASSERT_LT(err, 0) TH_LOG("ioctl read-only with wrong _IOC_NR (0x42) should have failed"); + ASSERT_EQ(errno, ENOTTY) + TH_LOG("expected ENOTTY for wrong read-only _IOC_NR (0x42), got errno %d", errno); + + /* also test with bigger number: 0x42 is not valid as well */ + bad_cmd = _IOC(_IOC_WRITE|_IOC_READ, 'H', 0x42, sizeof(buf)); + + err = ioctl(self->hidraw_fd, bad_cmd, buf); + ASSERT_LT(err, 0) TH_LOG("ioctl read-write with wrong _IOC_NR (0x42) should have failed"); + ASSERT_EQ(errno, ENOTTY) + TH_LOG("expected ENOTTY for wrong read-write _IOC_NR (0x42), got errno %d", errno); +} + +/* + * Test ioctl with incorrect type bits + */ +TEST_F(hidraw, ioctl_invalid_type) +{ + char buf[256] = {0}; + int err; + unsigned int bad_cmd; + + /* + * craft an ioctl command with wrong _IOC_TYPE bits + */ + bad_cmd = _IOC(_IOC_WRITE|_IOC_READ, 'I', 0x01, sizeof(buf)); /* 'I' should be 'H' */ + + /* test the ioctl */ + err = ioctl(self->hidraw_fd, bad_cmd, buf); + ASSERT_LT(err, 0) TH_LOG("ioctl with wrong _IOC_TYPE (I) should have failed"); + ASSERT_EQ(errno, EINVAL) TH_LOG("expected EINVAL for wrong _IOC_NR, got errno %d", errno); +} + +/* + * Test HIDIOCGFEATURE ioctl with incorrect _IOC_DIR bits + */ +TEST_F(hidraw, ioctl_gfeature_invalid_dir) +{ + __u8 buf[10] = {0}; + int err; + unsigned int bad_cmd; + + /* set report ID 1 in first byte */ + buf[0] = 1; + + /* + * craft an ioctl command with wrong _IOC_DIR bits + * HIDIOCGFEATURE should have _IOC_WRITE|_IOC_READ, let's use only _IOC_WRITE + */ + bad_cmd = _IOC(_IOC_WRITE, 'H', 0x07, sizeof(buf)); /* should be _IOC_WRITE|_IOC_READ */ + + /* try to get feature report with wrong direction bits */ + err = ioctl(self->hidraw_fd, bad_cmd, buf); + ASSERT_LT(err, 0) TH_LOG("HIDIOCGFEATURE with wrong _IOC_DIR should have failed"); + ASSERT_EQ(errno, EINVAL) TH_LOG("expected EINVAL for wrong _IOC_DIR, got errno %d", errno); + + /* also test with only _IOC_READ */ + bad_cmd = _IOC(_IOC_READ, 'H', 0x07, sizeof(buf)); /* should be _IOC_WRITE|_IOC_READ */ + + err = ioctl(self->hidraw_fd, bad_cmd, buf); + ASSERT_LT(err, 0) TH_LOG("HIDIOCGFEATURE with wrong _IOC_DIR should have failed"); + ASSERT_EQ(errno, EINVAL) TH_LOG("expected EINVAL for wrong _IOC_DIR, got errno %d", errno); +} + +/* + * Test read-only ioctl with incorrect _IOC_DIR bits + */ +TEST_F(hidraw, ioctl_readonly_invalid_dir) +{ + char buf[256] = {0}; + int err; + unsigned int bad_cmd; + + /* + * craft an ioctl command with wrong _IOC_DIR bits + * HIDIOCGRAWNAME should have _IOC_READ, let's use _IOC_WRITE + */ + bad_cmd = _IOC(_IOC_WRITE, 'H', 0x04, sizeof(buf)); /* should be _IOC_READ */ + + /* try to get device name with wrong direction bits */ + err = ioctl(self->hidraw_fd, bad_cmd, buf); + ASSERT_LT(err, 0) TH_LOG("HIDIOCGRAWNAME with wrong _IOC_DIR should have failed"); + ASSERT_EQ(errno, EINVAL) TH_LOG("expected EINVAL for wrong _IOC_DIR, got errno %d", errno); + + /* also test with _IOC_WRITE|_IOC_READ */ + bad_cmd = _IOC(_IOC_WRITE|_IOC_READ, 'H', 0x04, sizeof(buf)); /* should be only _IOC_READ */ + + err = ioctl(self->hidraw_fd, bad_cmd, buf); + ASSERT_LT(err, 0) TH_LOG("HIDIOCGRAWNAME with wrong _IOC_DIR should have failed"); + ASSERT_EQ(errno, EINVAL) TH_LOG("expected EINVAL for wrong _IOC_DIR, got errno %d", errno); +} + +/* + * Test HIDIOCSFEATURE ioctl to set feature report + */ +TEST_F(hidraw, ioctl_sfeature) +{ + __u8 buf[10] = {0}; + int err; + + /* prepare feature report data */ + buf[0] = 1; /* report ID */ + buf[1] = 0x42; + buf[2] = 0x24; + + /* set feature report */ + err = ioctl(self->hidraw_fd, HIDIOCSFEATURE(3), buf); + ASSERT_EQ(err, 3) TH_LOG("HIDIOCSFEATURE ioctl failed, got %d", err); + + /* + * Note: The uhid mock doesn't validate the set report data, + * so we just verify the ioctl succeeds + */ +} + +/* + * Test HIDIOCGINPUT ioctl to get input report + */ +TEST_F(hidraw, ioctl_ginput) +{ + __u8 buf[10] = {0}; + int err; + + /* set report ID 1 in first byte */ + buf[0] = 1; + + /* get input report */ + err = ioctl(self->hidraw_fd, HIDIOCGINPUT(sizeof(buf)), buf); + ASSERT_EQ(err, sizeof(feature_data)) TH_LOG("HIDIOCGINPUT ioctl failed, got %d", err); + + /* verify we got the expected input data */ + ASSERT_EQ(buf[0], feature_data[0]) + TH_LOG("expected feature_data[0] = %d, got %d", feature_data[0], buf[0]); + ASSERT_EQ(buf[1], feature_data[1]) + TH_LOG("expected feature_data[1] = %d, got %d", feature_data[1], buf[1]); +} + +/* + * Test HIDIOCGINPUT ioctl with invalid report ID + */ +TEST_F(hidraw, ioctl_ginput_invalid) +{ + __u8 buf[10] = {0}; + int err; + + /* set invalid report ID (not 1) */ + buf[0] = 2; + + /* try to get input report */ + err = ioctl(self->hidraw_fd, HIDIOCGINPUT(sizeof(buf)), buf); + ASSERT_LT(err, 0) TH_LOG("HIDIOCGINPUT should have failed with invalid report ID"); + ASSERT_EQ(errno, EIO) TH_LOG("expected EIO, got errno %d", errno); +} + +/* + * Test HIDIOCSINPUT ioctl to set input report + */ +TEST_F(hidraw, ioctl_sinput) +{ + __u8 buf[10] = {0}; + int err; + + /* prepare input report data */ + buf[0] = 1; /* report ID */ + buf[1] = 0x55; + buf[2] = 0xAA; + + /* set input report */ + err = ioctl(self->hidraw_fd, HIDIOCSINPUT(3), buf); + ASSERT_EQ(err, 3) TH_LOG("HIDIOCSINPUT ioctl failed, got %d", err); + + /* + * Note: The uhid mock doesn't validate the set report data, + * so we just verify the ioctl succeeds + */ +} + +/* + * Test HIDIOCGOUTPUT ioctl to get output report + */ +TEST_F(hidraw, ioctl_goutput) +{ + __u8 buf[10] = {0}; + int err; + + /* set report ID 1 in first byte */ + buf[0] = 1; + + /* get output report */ + err = ioctl(self->hidraw_fd, HIDIOCGOUTPUT(sizeof(buf)), buf); + ASSERT_EQ(err, sizeof(feature_data)) TH_LOG("HIDIOCGOUTPUT ioctl failed, got %d", err); + + /* verify we got the expected output data */ + ASSERT_EQ(buf[0], feature_data[0]) + TH_LOG("expected feature_data[0] = %d, got %d", feature_data[0], buf[0]); + ASSERT_EQ(buf[1], feature_data[1]) + TH_LOG("expected feature_data[1] = %d, got %d", feature_data[1], buf[1]); +} + +/* + * Test HIDIOCGOUTPUT ioctl with invalid report ID + */ +TEST_F(hidraw, ioctl_goutput_invalid) +{ + __u8 buf[10] = {0}; + int err; + + /* set invalid report ID (not 1) */ + buf[0] = 2; + + /* try to get output report */ + err = ioctl(self->hidraw_fd, HIDIOCGOUTPUT(sizeof(buf)), buf); + ASSERT_LT(err, 0) TH_LOG("HIDIOCGOUTPUT should have failed with invalid report ID"); + ASSERT_EQ(errno, EIO) TH_LOG("expected EIO, got errno %d", errno); +} + +/* + * Test HIDIOCSOUTPUT ioctl to set output report + */ +TEST_F(hidraw, ioctl_soutput) +{ + __u8 buf[10] = {0}; + int err; + + /* prepare output report data */ + buf[0] = 1; /* report ID */ + buf[1] = 0x33; + buf[2] = 0xCC; + + /* set output report */ + err = ioctl(self->hidraw_fd, HIDIOCSOUTPUT(3), buf); + ASSERT_EQ(err, 3) TH_LOG("HIDIOCSOUTPUT ioctl failed, got %d", err); + + /* + * Note: The uhid mock doesn't validate the set report data, + * so we just verify the ioctl succeeds + */ +} + +/* + * Test HIDIOCGRAWNAME ioctl to get device name string + */ +TEST_F(hidraw, ioctl_rawname) +{ + char name[256] = {0}; + char expected_name[64]; + int err; + + /* get device name */ + err = ioctl(self->hidraw_fd, HIDIOCGRAWNAME(sizeof(name)), name); + ASSERT_GT(err, 0) TH_LOG("HIDIOCGRAWNAME ioctl failed, got %d", err); + + /* construct expected name based on device id */ + snprintf(expected_name, sizeof(expected_name), "test-uhid-device-%d", self->hid.dev_id); + + /* verify the name matches expected pattern */ + ASSERT_EQ(strcmp(name, expected_name), 0) + TH_LOG("expected name '%s', got '%s'", expected_name, name); +} + +/* + * Test HIDIOCGRAWPHYS ioctl to get device physical address string + */ +TEST_F(hidraw, ioctl_rawphys) +{ + char phys[256] = {0}; + char expected_phys[64]; + int err; + + /* get device physical address */ + err = ioctl(self->hidraw_fd, HIDIOCGRAWPHYS(sizeof(phys)), phys); + ASSERT_GT(err, 0) TH_LOG("HIDIOCGRAWPHYS ioctl failed, got %d", err); + + /* construct expected phys based on device id */ + snprintf(expected_phys, sizeof(expected_phys), "%d", self->hid.dev_id); + + /* verify the phys matches expected value */ + ASSERT_EQ(strcmp(phys, expected_phys), 0) + TH_LOG("expected phys '%s', got '%s'", expected_phys, phys); +} + +/* + * Test HIDIOCGRAWUNIQ ioctl to get device unique identifier string + */ +TEST_F(hidraw, ioctl_rawuniq) +{ + char uniq[256] = {0}; + int err; + + /* get device unique identifier */ + err = ioctl(self->hidraw_fd, HIDIOCGRAWUNIQ(sizeof(uniq)), uniq); + ASSERT_GE(err, 0) TH_LOG("HIDIOCGRAWUNIQ ioctl failed, got %d", err); + + /* uniq is typically empty in our test setup */ + ASSERT_EQ(strlen(uniq), 0) TH_LOG("expected empty uniq, got '%s'", uniq); +} + +/* + * Test device string ioctls with small buffer sizes + */ +TEST_F(hidraw, ioctl_strings_small_buffer) +{ + char small_buf[8] = {0}; + char expected_name[64]; + int err; + + /* test HIDIOCGRAWNAME with small buffer */ + err = ioctl(self->hidraw_fd, HIDIOCGRAWNAME(sizeof(small_buf)), small_buf); + ASSERT_EQ(err, sizeof(small_buf)) + TH_LOG("HIDIOCGRAWNAME with small buffer failed, got %d", err); + + /* construct expected truncated name */ + snprintf(expected_name, sizeof(expected_name), "test-uhid-device-%d", self->hid.dev_id); + + /* verify we got truncated name (first 8 chars, no null terminator guaranteed) */ + ASSERT_EQ(strncmp(small_buf, expected_name, sizeof(small_buf)), 0) + TH_LOG("expected truncated name to match first %zu chars", sizeof(small_buf)); + + /* Note: hidraw driver doesn't guarantee null termination when buffer is too small */ +} + int main(int argc, char **argv) { return test_harness_run(argc, argv); diff --git a/tools/testing/selftests/hid/vmtest.sh b/tools/testing/selftests/hid/vmtest.sh index db534e9099a8..ecbd57f775a0 100755 --- a/tools/testing/selftests/hid/vmtest.sh +++ b/tools/testing/selftests/hid/vmtest.sh @@ -1,296 +1,474 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +# +# Copyright (c) 2025 Red Hat +# Copyright (c) 2025 Meta Platforms, Inc. and affiliates +# +# Dependencies: +# * virtme-ng +# * busybox-static (used by virtme-ng) +# * qemu (used by virtme-ng) + +readonly SCRIPT_DIR="$(cd -P -- "$(dirname -- "${BASH_SOURCE[0]}")" && pwd -P)" +readonly KERNEL_CHECKOUT=$(realpath "${SCRIPT_DIR}"/../../../../) + +source "${SCRIPT_DIR}"/../kselftest/ktap_helpers.sh + +readonly HID_BPF_TEST="${SCRIPT_DIR}"/hid_bpf +readonly HIDRAW_TEST="${SCRIPT_DIR}"/hidraw +readonly HID_BPF_PROGS="${KERNEL_CHECKOUT}/drivers/hid/bpf/progs" +readonly SSH_GUEST_PORT=22 +readonly WAIT_PERIOD=3 +readonly WAIT_PERIOD_MAX=60 +readonly WAIT_TOTAL=$(( WAIT_PERIOD * WAIT_PERIOD_MAX )) +readonly QEMU_PIDFILE=$(mktemp /tmp/qemu_hid_vmtest_XXXX.pid) + +readonly QEMU_OPTS="\ + --pidfile ${QEMU_PIDFILE} \ +" +readonly KERNEL_CMDLINE="" +readonly LOG=$(mktemp /tmp/hid_vmtest_XXXX.log) +readonly TEST_NAMES=(vm_hid_bpf vm_hidraw vm_pytest) +readonly TEST_DESCS=( + "Run hid_bpf tests in the VM." + "Run hidraw tests in the VM." + "Run the hid-tools test-suite in the VM." +) + +VERBOSE=0 +SHELL_MODE=0 +BUILD_HOST="" +BUILD_HOST_PODMAN_CONTAINER_NAME="" + +usage() { + local name + local desc + local i + + echo + echo "$0 [OPTIONS] [TEST]... [-- tests-args]" + echo "If no TEST argument is given, all tests will be run." + echo + echo "Options" + echo " -b: build the kernel from the current source tree and use it for guest VMs" + echo " -H: hostname for remote build host (used with -b)" + echo " -p: podman container name for remote build host (used with -b)" + echo " Example: -H beefyserver -p vng" + echo " -q: set the path to or name of qemu binary" + echo " -s: start a shell in the VM instead of running tests" + echo " -v: more verbose output (can be repeated multiple times)" + echo + echo "Available tests" + + for ((i = 0; i < ${#TEST_NAMES[@]}; i++)); do + name=${TEST_NAMES[${i}]} + desc=${TEST_DESCS[${i}]} + printf "\t%-35s%-35s\n" "${name}" "${desc}" + done + echo -set -u -set -e - -# This script currently only works for x86_64 -ARCH="$(uname -m)" -case "${ARCH}" in -x86_64) - QEMU_BINARY=qemu-system-x86_64 - BZIMAGE="arch/x86/boot/bzImage" - ;; -*) - echo "Unsupported architecture" exit 1 - ;; -esac -SCRIPT_DIR="$(dirname $(realpath $0))" -OUTPUT_DIR="$SCRIPT_DIR/results" -KCONFIG_REL_PATHS=("${SCRIPT_DIR}/config" "${SCRIPT_DIR}/config.common" "${SCRIPT_DIR}/config.${ARCH}") -B2C_URL="https://gitlab.freedesktop.org/gfx-ci/boot2container/-/raw/main/vm2c.py" -NUM_COMPILE_JOBS="$(nproc)" -LOG_FILE_BASE="$(date +"hid_selftests.%Y-%m-%d_%H-%M-%S")" -LOG_FILE="${LOG_FILE_BASE}.log" -EXIT_STATUS_FILE="${LOG_FILE_BASE}.exit_status" -CONTAINER_IMAGE="registry.freedesktop.org/bentiss/hid/fedora/39:2023-11-22.1" - -TARGETS="${TARGETS:=$(basename ${SCRIPT_DIR})}" -DEFAULT_COMMAND="pip3 install hid-tools; make -C tools/testing/selftests TARGETS=${TARGETS} run_tests" - -usage() -{ - cat <<EOF -Usage: $0 [-j N] [-s] [-b] [-d <output_dir>] -- [<command>] - -<command> is the command you would normally run when you are in -the source kernel direcory. e.g: - - $0 -- ./tools/testing/selftests/hid/hid_bpf - -If no command is specified and a debug shell (-s) is not requested, -"${DEFAULT_COMMAND}" will be run by default. - -If you build your kernel using KBUILD_OUTPUT= or O= options, these -can be passed as environment variables to the script: - - O=<kernel_build_path> $0 -- ./tools/testing/selftests/hid/hid_bpf - -or - - KBUILD_OUTPUT=<kernel_build_path> $0 -- ./tools/testing/selftests/hid/hid_bpf - -Options: - - -u) Update the boot2container script to a newer version. - -d) Update the output directory (default: ${OUTPUT_DIR}) - -b) Run only the build steps for the kernel and the selftests - -j) Number of jobs for compilation, similar to -j in make - (default: ${NUM_COMPILE_JOBS}) - -s) Instead of powering off the VM, start an interactive - shell. If <command> is specified, the shell runs after - the command finishes executing -EOF } -download() -{ - local file="$1" +die() { + echo "$*" >&2 + exit "${KSFT_FAIL}" +} - echo "Downloading $file..." >&2 - curl -Lsf "$file" -o "${@:2}" +vm_ssh() { + # vng --ssh-client keeps shouting "Warning: Permanently added 'virtme-ng%22' + # (ED25519) to the list of known hosts.", + # So replace the command with what's actually called and add the "-q" option + stdbuf -oL ssh -q \ + -F ${HOME}/.cache/virtme-ng/.ssh/virtme-ng-ssh.conf \ + -l root virtme-ng%${SSH_GUEST_PORT} \ + "$@" + return $? } -recompile_kernel() -{ - local kernel_checkout="$1" - local make_command="$2" +cleanup() { + if [[ -s "${QEMU_PIDFILE}" ]]; then + pkill -SIGTERM -F "${QEMU_PIDFILE}" > /dev/null 2>&1 + fi - cd "${kernel_checkout}" + # If failure occurred during or before qemu start up, then we need + # to clean this up ourselves. + if [[ -e "${QEMU_PIDFILE}" ]]; then + rm "${QEMU_PIDFILE}" + fi +} + +check_args() { + local found - ${make_command} olddefconfig - ${make_command} headers - ${make_command} + for arg in "$@"; do + found=0 + for name in "${TEST_NAMES[@]}"; do + if [[ "${name}" = "${arg}" ]]; then + found=1 + break + fi + done + + if [[ "${found}" -eq 0 ]]; then + echo "${arg} is not an available test" >&2 + usage + fi + done + + for arg in "$@"; do + if ! command -v > /dev/null "test_${arg}"; then + echo "Test ${arg} not found" >&2 + usage + fi + done +} + +check_deps() { + for dep in vng ${QEMU} busybox pkill ssh pytest; do + if [[ ! -x $(command -v "${dep}") ]]; then + echo -e "skip: dependency ${dep} not found!\n" + exit "${KSFT_SKIP}" + fi + done + + if [[ ! -x $(command -v "${HID_BPF_TEST}") ]]; then + printf "skip: %s not found!" "${HID_BPF_TEST}" + printf " Please build the kselftest hid_bpf target.\n" + exit "${KSFT_SKIP}" + fi + + if [[ ! -x $(command -v "${HIDRAW_TEST}") ]]; then + printf "skip: %s not found!" "${HIDRAW_TEST}" + printf " Please build the kselftest hidraw target.\n" + exit "${KSFT_SKIP}" + fi } -update_selftests() -{ - local kernel_checkout="$1" - local selftests_dir="${kernel_checkout}/tools/testing/selftests/hid" +check_vng() { + local tested_versions + local version + local ok - cd "${selftests_dir}" - ${make_command} + tested_versions=("1.36" "1.37") + version="$(vng --version)" + + ok=0 + for tv in "${tested_versions[@]}"; do + if [[ "${version}" == *"${tv}"* ]]; then + ok=1 + break + fi + done + + if [[ ! "${ok}" -eq 1 ]]; then + printf "warning: vng version '%s' has not been tested and may " "${version}" >&2 + printf "not function properly.\n\tThe following versions have been tested: " >&2 + echo "${tested_versions[@]}" >&2 + fi } -run_vm() -{ - local run_dir="$1" - local b2c="$2" - local kernel_bzimage="$3" - local command="$4" - local post_command="" - - cd "${run_dir}" - - if ! which "${QEMU_BINARY}" &> /dev/null; then - cat <<EOF -Could not find ${QEMU_BINARY} -Please install qemu or set the QEMU_BINARY environment variable. -EOF +handle_build() { + if [[ ! "${BUILD}" -eq 1 ]]; then + return + fi + + if [[ ! -d "${KERNEL_CHECKOUT}" ]]; then + echo "-b requires vmtest.sh called from the kernel source tree" >&2 exit 1 fi - # alpine (used in post-container requires the PATH to have /bin - export PATH=$PATH:/bin + pushd "${KERNEL_CHECKOUT}" &>/dev/null - if [[ "${debug_shell}" != "yes" ]] - then - touch ${OUTPUT_DIR}/${LOG_FILE} - command="mount bpffs -t bpf /sys/fs/bpf/; set -o pipefail ; ${command} 2>&1 | tee ${OUTPUT_DIR}/${LOG_FILE}" - post_command="cat ${OUTPUT_DIR}/${LOG_FILE}" - else - command="mount bpffs -t bpf /sys/fs/bpf/; ${command}" + if ! vng --kconfig --config "${SCRIPT_DIR}"/config; then + die "failed to generate .config for kernel source tree (${KERNEL_CHECKOUT})" fi - set +e - $b2c --command "${command}" \ - --kernel ${kernel_bzimage} \ - --workdir ${OUTPUT_DIR} \ - --image ${CONTAINER_IMAGE} + local vng_args=("-v" "--config" "${SCRIPT_DIR}/config" "--build") - echo $? > ${OUTPUT_DIR}/${EXIT_STATUS_FILE} + if [[ -n "${BUILD_HOST}" ]]; then + vng_args+=("--build-host" "${BUILD_HOST}") + fi - set -e + if [[ -n "${BUILD_HOST_PODMAN_CONTAINER_NAME}" ]]; then + vng_args+=("--build-host-exec-prefix" \ + "podman exec -ti ${BUILD_HOST_PODMAN_CONTAINER_NAME}") + fi - ${post_command} -} + if ! vng "${vng_args[@]}"; then + die "failed to build kernel from source tree (${KERNEL_CHECKOUT})" + fi -is_rel_path() -{ - local path="$1" + if ! make -j$(nproc) -C "${HID_BPF_PROGS}"; then + die "failed to build HID bpf objects from source tree (${HID_BPF_PROGS})" + fi - [[ ${path:0:1} != "/" ]] + if ! make -j$(nproc) -C "${SCRIPT_DIR}"; then + die "failed to build HID selftests from source tree (${SCRIPT_DIR})" + fi + + popd &>/dev/null } -do_update_kconfig() -{ - local kernel_checkout="$1" - local kconfig_file="$2" +vm_start() { + local logfile=/dev/null + local verbose_opt="" + local kernel_opt="" + local qemu - rm -f "$kconfig_file" 2> /dev/null + qemu=$(command -v "${QEMU}") - for config in "${KCONFIG_REL_PATHS[@]}"; do - local kconfig_src="${config}" - cat "$kconfig_src" >> "$kconfig_file" - done -} + if [[ "${VERBOSE}" -eq 2 ]]; then + verbose_opt="--verbose" + logfile=/dev/stdout + fi -update_kconfig() -{ - local kernel_checkout="$1" - local kconfig_file="$2" - - if [[ -f "${kconfig_file}" ]]; then - local local_modified="$(stat -c %Y "${kconfig_file}")" - - for config in "${KCONFIG_REL_PATHS[@]}"; do - local kconfig_src="${config}" - local src_modified="$(stat -c %Y "${kconfig_src}")" - # Only update the config if it has been updated after the - # previously cached config was created. This avoids - # unnecessarily compiling the kernel and selftests. - if [[ "${src_modified}" -gt "${local_modified}" ]]; then - do_update_kconfig "$kernel_checkout" "$kconfig_file" - # Once we have found one outdated configuration - # there is no need to check other ones. - break - fi - done - else - do_update_kconfig "$kernel_checkout" "$kconfig_file" + # If we are running from within the kernel source tree, use the kernel source tree + # as the kernel to boot, otherwise use the currently running kernel. + if [[ "$(realpath "$(pwd)")" == "${KERNEL_CHECKOUT}"* ]]; then + kernel_opt="${KERNEL_CHECKOUT}" fi -} -main() -{ - local script_dir="$(cd -P -- "$(dirname -- "${BASH_SOURCE[0]}")" && pwd -P)" - local kernel_checkout=$(realpath "${script_dir}"/../../../../) - # By default the script searches for the kernel in the checkout directory but - # it also obeys environment variables O= and KBUILD_OUTPUT= - local kernel_bzimage="${kernel_checkout}/${BZIMAGE}" - local command="${DEFAULT_COMMAND}" - local update_b2c="no" - local debug_shell="no" - local build_only="no" - - while getopts ':hsud:j:b' opt; do - case ${opt} in - u) - update_b2c="yes" - ;; - d) - OUTPUT_DIR="$OPTARG" - ;; - j) - NUM_COMPILE_JOBS="$OPTARG" - ;; - s) - command="/bin/sh" - debug_shell="yes" - ;; - b) - build_only="yes" - ;; - h) - usage - exit 0 - ;; - \? ) - echo "Invalid Option: -$OPTARG" - usage - exit 1 - ;; - : ) - echo "Invalid Option: -$OPTARG requires an argument" - usage - exit 1 - ;; - esac - done - shift $((OPTIND -1)) - - # trap 'catch "$?"' EXIT - if [[ "${build_only}" == "no" && "${debug_shell}" == "no" ]]; then - if [[ $# -eq 0 ]]; then - echo "No command specified, will run ${DEFAULT_COMMAND} in the vm" - else - command="$@" - - if [[ "${command}" == "/bin/bash" || "${command}" == "bash" ]] - then - debug_shell="yes" - fi + vng \ + --run \ + ${kernel_opt} \ + ${verbose_opt} \ + --qemu-opts="${QEMU_OPTS}" \ + --qemu="${qemu}" \ + --user root \ + --append "${KERNEL_CMDLINE}" \ + --ssh "${SSH_GUEST_PORT}" \ + --rw &> ${logfile} & + + local vng_pid=$! + local elapsed=0 + + while [[ ! -s "${QEMU_PIDFILE}" ]]; do + if ! kill -0 "${vng_pid}" 2>/dev/null; then + echo "vng process (PID ${vng_pid}) exited early, check logs for details" >&2 + die "failed to boot VM" fi - fi - local kconfig_file="${OUTPUT_DIR}/latest.config" - local make_command="make -j ${NUM_COMPILE_JOBS} KCONFIG_CONFIG=${kconfig_file}" + if [[ ${elapsed} -ge ${WAIT_TOTAL} ]]; then + echo "Timed out after ${WAIT_TOTAL} seconds waiting for VM to boot" >&2 + die "failed to boot VM" + fi - # Figure out where the kernel is being built. - # O takes precedence over KBUILD_OUTPUT. - if [[ "${O:=""}" != "" ]]; then - if is_rel_path "${O}"; then - O="$(realpath "${PWD}/${O}")" + sleep 1 + elapsed=$((elapsed + 1)) + done +} + +vm_wait_for_ssh() { + local i + + i=0 + while true; do + if [[ ${i} -gt ${WAIT_PERIOD_MAX} ]]; then + die "Timed out waiting for guest ssh" fi - kernel_bzimage="${O}/${BZIMAGE}" - make_command="${make_command} O=${O}" - elif [[ "${KBUILD_OUTPUT:=""}" != "" ]]; then - if is_rel_path "${KBUILD_OUTPUT}"; then - KBUILD_OUTPUT="$(realpath "${PWD}/${KBUILD_OUTPUT}")" + if vm_ssh -- true; then + break fi - kernel_bzimage="${KBUILD_OUTPUT}/${BZIMAGE}" - make_command="${make_command} KBUILD_OUTPUT=${KBUILD_OUTPUT}" + i=$(( i + 1 )) + sleep ${WAIT_PERIOD} + done +} + +vm_mount_bpffs() { + vm_ssh -- mount bpffs -t bpf /sys/fs/bpf +} + +__log_stdin() { + stdbuf -oL awk '{ printf "%s:\t%s\n","'"${prefix}"'", $0; fflush() }' +} + +__log_args() { + echo "$*" | awk '{ printf "%s:\t%s\n","'"${prefix}"'", $0 }' +} + +log() { + local verbose="$1" + shift + + local prefix="$1" + + shift + local redirect= + if [[ ${verbose} -le 0 ]]; then + redirect=/dev/null + else + redirect=/dev/stdout + fi + + if [[ "$#" -eq 0 ]]; then + __log_stdin | tee -a "${LOG}" > ${redirect} + else + __log_args "$@" | tee -a "${LOG}" > ${redirect} fi +} - local b2c="${OUTPUT_DIR}/vm2c.py" +log_setup() { + log $((VERBOSE-1)) "setup" "$@" +} - echo "Output directory: ${OUTPUT_DIR}" +log_host() { + local testname=$1 - mkdir -p "${OUTPUT_DIR}" - update_kconfig "${kernel_checkout}" "${kconfig_file}" + shift + log $((VERBOSE-1)) "test:${testname}:host" "$@" +} - recompile_kernel "${kernel_checkout}" "${make_command}" - update_selftests "${kernel_checkout}" "${make_command}" +log_guest() { + local testname=$1 - if [[ "${build_only}" == "no" ]]; then - if [[ "${update_b2c}" == "no" && ! -f "${b2c}" ]]; then - echo "vm2c script not found in ${b2c}" - update_b2c="yes" - fi + shift + log ${VERBOSE} "# test:${testname}" "$@" +} - if [[ "${update_b2c}" == "yes" ]]; then - download $B2C_URL $b2c - chmod +x $b2c - fi +test_vm_hid_bpf() { + local testname="${FUNCNAME[0]#test_}" - run_vm "${kernel_checkout}" $b2c "${kernel_bzimage}" "${command}" - if [[ "${debug_shell}" != "yes" ]]; then - echo "Logs saved in ${OUTPUT_DIR}/${LOG_FILE}" - fi + vm_ssh -- "${HID_BPF_TEST}" \ + 2>&1 | log_guest "${testname}" + + return ${PIPESTATUS[0]} +} + +test_vm_hidraw() { + local testname="${FUNCNAME[0]#test_}" + + vm_ssh -- "${HIDRAW_TEST}" \ + 2>&1 | log_guest "${testname}" + + return ${PIPESTATUS[0]} +} + +test_vm_pytest() { + local testname="${FUNCNAME[0]#test_}" - exit $(cat ${OUTPUT_DIR}/${EXIT_STATUS_FILE}) + shift + + vm_ssh -- pytest ${SCRIPT_DIR}/tests --color=yes "$@" \ + 2>&1 | log_guest "${testname}" + + return ${PIPESTATUS[0]} +} + +run_test() { + local vm_oops_cnt_before + local vm_warn_cnt_before + local vm_oops_cnt_after + local vm_warn_cnt_after + local name + local rc + + vm_oops_cnt_before=$(vm_ssh -- dmesg | grep -c -i 'Oops') + vm_error_cnt_before=$(vm_ssh -- dmesg --level=err | wc -l) + + name=$(echo "${1}" | awk '{ print $1 }') + eval test_"${name}" "$@" + rc=$? + + vm_oops_cnt_after=$(vm_ssh -- dmesg | grep -i 'Oops' | wc -l) + if [[ ${vm_oops_cnt_after} -gt ${vm_oops_cnt_before} ]]; then + echo "FAIL: kernel oops detected on vm" | log_host "${name}" + rc=$KSFT_FAIL + fi + + vm_error_cnt_after=$(vm_ssh -- dmesg --level=err | wc -l) + if [[ ${vm_error_cnt_after} -gt ${vm_error_cnt_before} ]]; then + echo "FAIL: kernel error detected on vm" | log_host "${name}" + vm_ssh -- dmesg --level=err | log_host "${name}" + rc=$KSFT_FAIL fi + + return "${rc}" } -main "$@" +QEMU="qemu-system-$(uname -m)" + +while getopts :hvsbq:H:p: o +do + case $o in + v) VERBOSE=$((VERBOSE+1));; + s) SHELL_MODE=1;; + b) BUILD=1;; + q) QEMU=$OPTARG;; + H) BUILD_HOST=$OPTARG;; + p) BUILD_HOST_PODMAN_CONTAINER_NAME=$OPTARG;; + h|*) usage;; + esac +done +shift $((OPTIND-1)) + +trap cleanup EXIT + +PARAMS="" + +if [[ ${#} -eq 0 ]]; then + ARGS=("${TEST_NAMES[@]}") +else + ARGS=() + COUNT=0 + for arg in $@; do + COUNT=$((COUNT+1)) + if [[ x"$arg" == x"--" ]]; then + break + fi + ARGS+=($arg) + done + shift $COUNT + PARAMS="$@" +fi + +if [[ "${SHELL_MODE}" -eq 0 ]]; then + check_args "${ARGS[@]}" + echo "1..${#ARGS[@]}" +fi +check_deps +check_vng +handle_build + +log_setup "Booting up VM" +vm_start +vm_wait_for_ssh +vm_mount_bpffs +log_setup "VM booted up" + +if [[ "${SHELL_MODE}" -eq 1 ]]; then + log_setup "Starting interactive shell in VM" + echo "Starting shell in VM. Use 'exit' to quit and shutdown the VM." + CURRENT_DIR="$(pwd)" + vm_ssh -t -- "cd '${CURRENT_DIR}' && exec bash -l" + exit "$KSFT_PASS" +fi + +cnt_pass=0 +cnt_fail=0 +cnt_skip=0 +cnt_total=0 +for arg in "${ARGS[@]}"; do + run_test "${arg}" "${PARAMS}" + rc=$? + if [[ ${rc} -eq $KSFT_PASS ]]; then + cnt_pass=$(( cnt_pass + 1 )) + echo "ok ${cnt_total} ${arg}" + elif [[ ${rc} -eq $KSFT_SKIP ]]; then + cnt_skip=$(( cnt_skip + 1 )) + echo "ok ${cnt_total} ${arg} # SKIP" + elif [[ ${rc} -eq $KSFT_FAIL ]]; then + cnt_fail=$(( cnt_fail + 1 )) + echo "not ok ${cnt_total} ${arg} # exit=$rc" + fi + cnt_total=$(( cnt_total + 1 )) +done + +echo "SUMMARY: PASS=${cnt_pass} SKIP=${cnt_skip} FAIL=${cnt_fail}" +echo "Log: ${LOG}" + +if [ $((cnt_pass + cnt_skip)) -eq ${cnt_total} ]; then + exit "$KSFT_PASS" +else + exit "$KSFT_FAIL" +fi diff --git a/tools/testing/selftests/kvm/Makefile.kvm b/tools/testing/selftests/kvm/Makefile.kvm index 41b40c676d7f..148d427ff24b 100644 --- a/tools/testing/selftests/kvm/Makefile.kvm +++ b/tools/testing/selftests/kvm/Makefile.kvm @@ -87,6 +87,7 @@ TEST_GEN_PROGS_x86 += x86/kvm_clock_test TEST_GEN_PROGS_x86 += x86/kvm_pv_test TEST_GEN_PROGS_x86 += x86/kvm_buslock_test TEST_GEN_PROGS_x86 += x86/monitor_mwait_test +TEST_GEN_PROGS_x86 += x86/msrs_test TEST_GEN_PROGS_x86 += x86/nested_emulation_test TEST_GEN_PROGS_x86 += x86/nested_exceptions_test TEST_GEN_PROGS_x86 += x86/platform_info_test @@ -156,6 +157,7 @@ TEST_GEN_PROGS_arm64 = $(TEST_GEN_PROGS_COMMON) TEST_GEN_PROGS_arm64 += arm64/aarch32_id_regs TEST_GEN_PROGS_arm64 += arm64/arch_timer_edge_cases TEST_GEN_PROGS_arm64 += arm64/debug-exceptions +TEST_GEN_PROGS_arm64 += arm64/hello_el2 TEST_GEN_PROGS_arm64 += arm64/host_sve TEST_GEN_PROGS_arm64 += arm64/hypercalls TEST_GEN_PROGS_arm64 += arm64/external_aborts @@ -175,6 +177,7 @@ TEST_GEN_PROGS_arm64 += arch_timer TEST_GEN_PROGS_arm64 += coalesced_io_test TEST_GEN_PROGS_arm64 += dirty_log_perf_test TEST_GEN_PROGS_arm64 += get-reg-list +TEST_GEN_PROGS_arm64 += guest_memfd_test TEST_GEN_PROGS_arm64 += memslot_modification_stress_test TEST_GEN_PROGS_arm64 += memslot_perf_test TEST_GEN_PROGS_arm64 += mmu_stress_test @@ -196,9 +199,15 @@ TEST_GEN_PROGS_s390 += rseq_test TEST_GEN_PROGS_riscv = $(TEST_GEN_PROGS_COMMON) TEST_GEN_PROGS_riscv += riscv/sbi_pmu_test TEST_GEN_PROGS_riscv += riscv/ebreak_test +TEST_GEN_PROGS_riscv += access_tracking_perf_test TEST_GEN_PROGS_riscv += arch_timer TEST_GEN_PROGS_riscv += coalesced_io_test +TEST_GEN_PROGS_riscv += dirty_log_perf_test TEST_GEN_PROGS_riscv += get-reg-list +TEST_GEN_PROGS_riscv += memslot_modification_stress_test +TEST_GEN_PROGS_riscv += memslot_perf_test +TEST_GEN_PROGS_riscv += mmu_stress_test +TEST_GEN_PROGS_riscv += rseq_test TEST_GEN_PROGS_riscv += steal_time TEST_GEN_PROGS_loongarch += coalesced_io_test diff --git a/tools/testing/selftests/kvm/access_tracking_perf_test.c b/tools/testing/selftests/kvm/access_tracking_perf_test.c index c9de66537ec3..b058f27b2141 100644 --- a/tools/testing/selftests/kvm/access_tracking_perf_test.c +++ b/tools/testing/selftests/kvm/access_tracking_perf_test.c @@ -50,6 +50,7 @@ #include "memstress.h" #include "guest_modes.h" #include "processor.h" +#include "ucall_common.h" #include "cgroup_util.h" #include "lru_gen_util.h" diff --git a/tools/testing/selftests/kvm/arm64/arch_timer.c b/tools/testing/selftests/kvm/arm64/arch_timer.c index eeba1cc87ff8..d592a4515399 100644 --- a/tools/testing/selftests/kvm/arm64/arch_timer.c +++ b/tools/testing/selftests/kvm/arm64/arch_timer.c @@ -165,10 +165,8 @@ static void guest_code(void) static void test_init_timer_irq(struct kvm_vm *vm) { /* Timer initid should be same for all the vCPUs, so query only vCPU-0 */ - vcpu_device_attr_get(vcpus[0], KVM_ARM_VCPU_TIMER_CTRL, - KVM_ARM_VCPU_TIMER_IRQ_PTIMER, &ptimer_irq); - vcpu_device_attr_get(vcpus[0], KVM_ARM_VCPU_TIMER_CTRL, - KVM_ARM_VCPU_TIMER_IRQ_VTIMER, &vtimer_irq); + ptimer_irq = vcpu_get_ptimer_irq(vcpus[0]); + vtimer_irq = vcpu_get_vtimer_irq(vcpus[0]); sync_global_to_guest(vm, ptimer_irq); sync_global_to_guest(vm, vtimer_irq); @@ -176,14 +174,14 @@ static void test_init_timer_irq(struct kvm_vm *vm) pr_debug("ptimer_irq: %d; vtimer_irq: %d\n", ptimer_irq, vtimer_irq); } -static int gic_fd; - struct kvm_vm *test_vm_create(void) { struct kvm_vm *vm; unsigned int i; int nr_vcpus = test_args.nr_vcpus; + TEST_REQUIRE(kvm_supports_vgic_v3()); + vm = vm_create_with_vcpus(nr_vcpus, guest_code, vcpus); vm_init_descriptor_tables(vm); @@ -204,8 +202,6 @@ struct kvm_vm *test_vm_create(void) vcpu_init_descriptor_tables(vcpus[i]); test_init_timer_irq(vm); - gic_fd = vgic_v3_setup(vm, nr_vcpus, 64); - __TEST_REQUIRE(gic_fd >= 0, "Failed to create vgic-v3"); /* Make all the test's cmdline args visible to the guest */ sync_global_to_guest(vm, test_args); @@ -215,6 +211,5 @@ struct kvm_vm *test_vm_create(void) void test_vm_cleanup(struct kvm_vm *vm) { - close(gic_fd); kvm_vm_free(vm); } diff --git a/tools/testing/selftests/kvm/arm64/arch_timer_edge_cases.c b/tools/testing/selftests/kvm/arm64/arch_timer_edge_cases.c index ce74d069cb7b..91906414a474 100644 --- a/tools/testing/selftests/kvm/arm64/arch_timer_edge_cases.c +++ b/tools/testing/selftests/kvm/arm64/arch_timer_edge_cases.c @@ -924,10 +924,8 @@ static void test_run(struct kvm_vm *vm, struct kvm_vcpu *vcpu) static void test_init_timer_irq(struct kvm_vm *vm, struct kvm_vcpu *vcpu) { - vcpu_device_attr_get(vcpu, KVM_ARM_VCPU_TIMER_CTRL, - KVM_ARM_VCPU_TIMER_IRQ_PTIMER, &ptimer_irq); - vcpu_device_attr_get(vcpu, KVM_ARM_VCPU_TIMER_CTRL, - KVM_ARM_VCPU_TIMER_IRQ_VTIMER, &vtimer_irq); + ptimer_irq = vcpu_get_ptimer_irq(vcpu); + vtimer_irq = vcpu_get_vtimer_irq(vcpu); sync_global_to_guest(vm, ptimer_irq); sync_global_to_guest(vm, vtimer_irq); @@ -935,8 +933,6 @@ static void test_init_timer_irq(struct kvm_vm *vm, struct kvm_vcpu *vcpu) pr_debug("ptimer_irq: %d; vtimer_irq: %d\n", ptimer_irq, vtimer_irq); } -static int gic_fd; - static void test_vm_create(struct kvm_vm **vm, struct kvm_vcpu **vcpu, enum arch_timer timer) { @@ -951,8 +947,6 @@ static void test_vm_create(struct kvm_vm **vm, struct kvm_vcpu **vcpu, vcpu_args_set(*vcpu, 1, timer); test_init_timer_irq(*vm, *vcpu); - gic_fd = vgic_v3_setup(*vm, 1, 64); - __TEST_REQUIRE(gic_fd >= 0, "Failed to create vgic-v3"); sync_global_to_guest(*vm, test_args); sync_global_to_guest(*vm, CVAL_MAX); @@ -961,7 +955,6 @@ static void test_vm_create(struct kvm_vm **vm, struct kvm_vcpu **vcpu, static void test_vm_cleanup(struct kvm_vm *vm) { - close(gic_fd); kvm_vm_free(vm); } @@ -1042,6 +1035,8 @@ int main(int argc, char *argv[]) /* Tell stdout not to buffer its content */ setbuf(stdout, NULL); + TEST_REQUIRE(kvm_supports_vgic_v3()); + if (!parse_args(argc, argv)) exit(KSFT_SKIP); diff --git a/tools/testing/selftests/kvm/arm64/external_aborts.c b/tools/testing/selftests/kvm/arm64/external_aborts.c index 062bf84cced1..592b26ded779 100644 --- a/tools/testing/selftests/kvm/arm64/external_aborts.c +++ b/tools/testing/selftests/kvm/arm64/external_aborts.c @@ -250,6 +250,47 @@ static void test_serror(void) kvm_vm_free(vm); } +static void expect_sea_s1ptw_handler(struct ex_regs *regs) +{ + u64 esr = read_sysreg(esr_el1); + + GUEST_ASSERT_EQ(regs->pc, expected_abort_pc); + GUEST_ASSERT_EQ(ESR_ELx_EC(esr), ESR_ELx_EC_DABT_CUR); + GUEST_ASSERT_EQ((esr & ESR_ELx_FSC), ESR_ELx_FSC_SEA_TTW(3)); + + GUEST_DONE(); +} + +static noinline void test_s1ptw_abort_guest(void) +{ + extern char test_s1ptw_abort_insn; + + WRITE_ONCE(expected_abort_pc, (u64)&test_s1ptw_abort_insn); + + asm volatile("test_s1ptw_abort_insn:\n\t" + "ldr x0, [%0]\n\t" + : : "r" (MMIO_ADDR) : "x0", "memory"); + + GUEST_FAIL("Load on S1PTW abort should not retire"); +} + +static void test_s1ptw_abort(void) +{ + struct kvm_vcpu *vcpu; + u64 *ptep, bad_pa; + struct kvm_vm *vm = vm_create_with_dabt_handler(&vcpu, test_s1ptw_abort_guest, + expect_sea_s1ptw_handler); + + ptep = virt_get_pte_hva_at_level(vm, MMIO_ADDR, 2); + bad_pa = BIT(vm->pa_bits) - vm->page_size; + + *ptep &= ~GENMASK(47, 12); + *ptep |= bad_pa; + + vcpu_run_expect_done(vcpu); + kvm_vm_free(vm); +} + static void test_serror_emulated_guest(void) { GUEST_ASSERT(!(read_sysreg(isr_el1) & ISR_EL1_A)); @@ -327,4 +368,5 @@ int main(void) test_serror_masked(); test_serror_emulated(); test_mmio_ease(); + test_s1ptw_abort(); } diff --git a/tools/testing/selftests/kvm/arm64/hello_el2.c b/tools/testing/selftests/kvm/arm64/hello_el2.c new file mode 100644 index 000000000000..bbe6862c6ab1 --- /dev/null +++ b/tools/testing/selftests/kvm/arm64/hello_el2.c @@ -0,0 +1,71 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * hello_el2 - Basic KVM selftest for VM running at EL2 with E2H=RES1 + * + * Copyright 2025 Google LLC + */ +#include "kvm_util.h" +#include "processor.h" +#include "test_util.h" +#include "ucall.h" + +#include <asm/sysreg.h> + +static void guest_code(void) +{ + u64 mmfr0 = read_sysreg_s(SYS_ID_AA64MMFR0_EL1); + u64 mmfr1 = read_sysreg_s(SYS_ID_AA64MMFR1_EL1); + u64 mmfr4 = read_sysreg_s(SYS_ID_AA64MMFR4_EL1); + u8 e2h0 = SYS_FIELD_GET(ID_AA64MMFR4_EL1, E2H0, mmfr4); + + GUEST_ASSERT_EQ(get_current_el(), 2); + GUEST_ASSERT(read_sysreg(hcr_el2) & HCR_EL2_E2H); + GUEST_ASSERT_EQ(SYS_FIELD_GET(ID_AA64MMFR1_EL1, VH, mmfr1), + ID_AA64MMFR1_EL1_VH_IMP); + + /* + * Traps of the complete ID register space are IMPDEF without FEAT_FGT, + * which is really annoying to deal with in KVM describing E2H as RES1. + * + * If the implementation doesn't honor the trap then expect the register + * to return all zeros. + */ + if (e2h0 == ID_AA64MMFR4_EL1_E2H0_IMP) + GUEST_ASSERT_EQ(SYS_FIELD_GET(ID_AA64MMFR0_EL1, FGT, mmfr0), + ID_AA64MMFR0_EL1_FGT_NI); + else + GUEST_ASSERT_EQ(e2h0, ID_AA64MMFR4_EL1_E2H0_NI_NV1); + + GUEST_DONE(); +} + +int main(void) +{ + struct kvm_vcpu_init init; + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + struct ucall uc; + + TEST_REQUIRE(kvm_check_cap(KVM_CAP_ARM_EL2)); + + vm = vm_create(1); + + kvm_get_default_vcpu_target(vm, &init); + init.features[0] |= BIT(KVM_ARM_VCPU_HAS_EL2); + vcpu = aarch64_vcpu_add(vm, 0, &init, guest_code); + kvm_arch_vm_finalize_vcpus(vm); + + vcpu_run(vcpu); + switch (get_ucall(vcpu, &uc)) { + case UCALL_DONE: + break; + case UCALL_ABORT: + REPORT_GUEST_ASSERT(uc); + break; + default: + TEST_FAIL("Unhandled ucall: %ld\n", uc.cmd); + } + + kvm_vm_free(vm); + return 0; +} diff --git a/tools/testing/selftests/kvm/arm64/hypercalls.c b/tools/testing/selftests/kvm/arm64/hypercalls.c index 44cfcf8a7f46..bf038a0371f4 100644 --- a/tools/testing/selftests/kvm/arm64/hypercalls.c +++ b/tools/testing/selftests/kvm/arm64/hypercalls.c @@ -108,7 +108,7 @@ static void guest_test_hvc(const struct test_hvc_info *hc_info) for (i = 0; i < hvc_info_arr_sz; i++, hc_info++) { memset(&res, 0, sizeof(res)); - smccc_hvc(hc_info->func_id, hc_info->arg1, 0, 0, 0, 0, 0, 0, &res); + do_smccc(hc_info->func_id, hc_info->arg1, 0, 0, 0, 0, 0, 0, &res); switch (stage) { case TEST_STAGE_HVC_IFACE_FEAT_DISABLED: diff --git a/tools/testing/selftests/kvm/arm64/kvm-uuid.c b/tools/testing/selftests/kvm/arm64/kvm-uuid.c index af9581b860f1..b5be9133535a 100644 --- a/tools/testing/selftests/kvm/arm64/kvm-uuid.c +++ b/tools/testing/selftests/kvm/arm64/kvm-uuid.c @@ -25,7 +25,7 @@ static void guest_code(void) { struct arm_smccc_res res = {}; - smccc_hvc(ARM_SMCCC_VENDOR_HYP_CALL_UID_FUNC_ID, 0, 0, 0, 0, 0, 0, 0, &res); + do_smccc(ARM_SMCCC_VENDOR_HYP_CALL_UID_FUNC_ID, 0, 0, 0, 0, 0, 0, 0, &res); __GUEST_ASSERT(res.a0 == ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_0 && res.a1 == ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_1 && diff --git a/tools/testing/selftests/kvm/arm64/no-vgic-v3.c b/tools/testing/selftests/kvm/arm64/no-vgic-v3.c index f222538e6084..152c34776981 100644 --- a/tools/testing/selftests/kvm/arm64/no-vgic-v3.c +++ b/tools/testing/selftests/kvm/arm64/no-vgic-v3.c @@ -163,6 +163,8 @@ int main(int argc, char *argv[]) struct kvm_vm *vm; uint64_t pfr0; + test_disable_default_vgic(); + vm = vm_create_with_one_vcpu(&vcpu, NULL); pfr0 = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64PFR0_EL1)); __TEST_REQUIRE(FIELD_GET(ID_AA64PFR0_EL1_GIC, pfr0), diff --git a/tools/testing/selftests/kvm/arm64/psci_test.c b/tools/testing/selftests/kvm/arm64/psci_test.c index ab491ee9e5f7..98e49f710aef 100644 --- a/tools/testing/selftests/kvm/arm64/psci_test.c +++ b/tools/testing/selftests/kvm/arm64/psci_test.c @@ -27,7 +27,7 @@ static uint64_t psci_cpu_on(uint64_t target_cpu, uint64_t entry_addr, { struct arm_smccc_res res; - smccc_hvc(PSCI_0_2_FN64_CPU_ON, target_cpu, entry_addr, context_id, + do_smccc(PSCI_0_2_FN64_CPU_ON, target_cpu, entry_addr, context_id, 0, 0, 0, 0, &res); return res.a0; @@ -38,7 +38,7 @@ static uint64_t psci_affinity_info(uint64_t target_affinity, { struct arm_smccc_res res; - smccc_hvc(PSCI_0_2_FN64_AFFINITY_INFO, target_affinity, lowest_affinity_level, + do_smccc(PSCI_0_2_FN64_AFFINITY_INFO, target_affinity, lowest_affinity_level, 0, 0, 0, 0, 0, &res); return res.a0; @@ -48,7 +48,7 @@ static uint64_t psci_system_suspend(uint64_t entry_addr, uint64_t context_id) { struct arm_smccc_res res; - smccc_hvc(PSCI_1_0_FN64_SYSTEM_SUSPEND, entry_addr, context_id, + do_smccc(PSCI_1_0_FN64_SYSTEM_SUSPEND, entry_addr, context_id, 0, 0, 0, 0, 0, &res); return res.a0; @@ -58,7 +58,7 @@ static uint64_t psci_system_off2(uint64_t type, uint64_t cookie) { struct arm_smccc_res res; - smccc_hvc(PSCI_1_3_FN64_SYSTEM_OFF2, type, cookie, 0, 0, 0, 0, 0, &res); + do_smccc(PSCI_1_3_FN64_SYSTEM_OFF2, type, cookie, 0, 0, 0, 0, 0, &res); return res.a0; } @@ -67,7 +67,7 @@ static uint64_t psci_features(uint32_t func_id) { struct arm_smccc_res res; - smccc_hvc(PSCI_1_0_FN_PSCI_FEATURES, func_id, 0, 0, 0, 0, 0, 0, &res); + do_smccc(PSCI_1_0_FN_PSCI_FEATURES, func_id, 0, 0, 0, 0, 0, 0, &res); return res.a0; } @@ -89,12 +89,13 @@ static struct kvm_vm *setup_vm(void *guest_code, struct kvm_vcpu **source, vm = vm_create(2); - vm_ioctl(vm, KVM_ARM_PREFERRED_TARGET, &init); + kvm_get_default_vcpu_target(vm, &init); init.features[0] |= (1 << KVM_ARM_VCPU_PSCI_0_2); *source = aarch64_vcpu_add(vm, 0, &init, guest_code); *target = aarch64_vcpu_add(vm, 1, &init, guest_code); + kvm_arch_vm_finalize_vcpus(vm); return vm; } diff --git a/tools/testing/selftests/kvm/arm64/set_id_regs.c b/tools/testing/selftests/kvm/arm64/set_id_regs.c index 189321e96925..8ff1e853f7f8 100644 --- a/tools/testing/selftests/kvm/arm64/set_id_regs.c +++ b/tools/testing/selftests/kvm/arm64/set_id_regs.c @@ -15,8 +15,6 @@ #include "test_util.h" #include <linux/bitfield.h> -bool have_cap_arm_mte; - enum ftr_type { FTR_EXACT, /* Use a predefined safe value */ FTR_LOWER_SAFE, /* Smaller value is safe */ @@ -125,6 +123,13 @@ static const struct reg_ftr_bits ftr_id_aa64isar2_el1[] = { REG_FTR_END, }; +static const struct reg_ftr_bits ftr_id_aa64isar3_el1[] = { + REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64ISAR3_EL1, FPRCVT, 0), + REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64ISAR3_EL1, LSFE, 0), + REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64ISAR3_EL1, FAMINMAX, 0), + REG_FTR_END, +}; + static const struct reg_ftr_bits ftr_id_aa64pfr0_el1[] = { REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR0_EL1, CSV3, 0), REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR0_EL1, CSV2, 0), @@ -165,7 +170,9 @@ static const struct reg_ftr_bits ftr_id_aa64mmfr0_el1[] = { static const struct reg_ftr_bits ftr_id_aa64mmfr1_el1[] = { REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64MMFR1_EL1, TIDCP1, 0), REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64MMFR1_EL1, AFP, 0), + REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64MMFR1_EL1, HCX, 0), REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64MMFR1_EL1, ETS, 0), + REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64MMFR1_EL1, TWED, 0), REG_FTR_BITS(FTR_HIGHER_SAFE, ID_AA64MMFR1_EL1, SpecSEI, 0), REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64MMFR1_EL1, PAN, 0), REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64MMFR1_EL1, LO, 0), @@ -221,6 +228,7 @@ static struct test_feature_reg test_regs[] = { TEST_REG(SYS_ID_AA64ISAR0_EL1, ftr_id_aa64isar0_el1), TEST_REG(SYS_ID_AA64ISAR1_EL1, ftr_id_aa64isar1_el1), TEST_REG(SYS_ID_AA64ISAR2_EL1, ftr_id_aa64isar2_el1), + TEST_REG(SYS_ID_AA64ISAR3_EL1, ftr_id_aa64isar3_el1), TEST_REG(SYS_ID_AA64PFR0_EL1, ftr_id_aa64pfr0_el1), TEST_REG(SYS_ID_AA64PFR1_EL1, ftr_id_aa64pfr1_el1), TEST_REG(SYS_ID_AA64MMFR0_EL1, ftr_id_aa64mmfr0_el1), @@ -239,6 +247,7 @@ static void guest_code(void) GUEST_REG_SYNC(SYS_ID_AA64ISAR0_EL1); GUEST_REG_SYNC(SYS_ID_AA64ISAR1_EL1); GUEST_REG_SYNC(SYS_ID_AA64ISAR2_EL1); + GUEST_REG_SYNC(SYS_ID_AA64ISAR3_EL1); GUEST_REG_SYNC(SYS_ID_AA64PFR0_EL1); GUEST_REG_SYNC(SYS_ID_AA64MMFR0_EL1); GUEST_REG_SYNC(SYS_ID_AA64MMFR1_EL1); @@ -568,7 +577,9 @@ static void test_user_set_mte_reg(struct kvm_vcpu *vcpu) uint64_t mte_frac; int idx, err; - if (!have_cap_arm_mte) { + val = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64PFR1_EL1)); + mte = FIELD_GET(ID_AA64PFR1_EL1_MTE, val); + if (!mte) { ksft_test_result_skip("MTE capability not supported, nothing to test\n"); return; } @@ -593,9 +604,6 @@ static void test_user_set_mte_reg(struct kvm_vcpu *vcpu) * from unsupported (0xF) to supported (0). * */ - val = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64PFR1_EL1)); - - mte = FIELD_GET(ID_AA64PFR1_EL1_MTE, val); mte_frac = FIELD_GET(ID_AA64PFR1_EL1_MTE_frac, val); if (mte != ID_AA64PFR1_EL1_MTE_MTE2 || mte_frac != ID_AA64PFR1_EL1_MTE_frac_NI) { @@ -750,28 +758,23 @@ static void test_reset_preserves_id_regs(struct kvm_vcpu *vcpu) ksft_test_result_pass("%s\n", __func__); } -void kvm_arch_vm_post_create(struct kvm_vm *vm) -{ - if (vm_check_cap(vm, KVM_CAP_ARM_MTE)) { - vm_enable_cap(vm, KVM_CAP_ARM_MTE, 0); - have_cap_arm_mte = true; - } -} - int main(void) { struct kvm_vcpu *vcpu; struct kvm_vm *vm; bool aarch64_only; uint64_t val, el0; - int test_cnt; + int test_cnt, i, j; TEST_REQUIRE(kvm_has_cap(KVM_CAP_ARM_SUPPORTED_REG_MASK_RANGES)); TEST_REQUIRE(kvm_has_cap(KVM_CAP_ARM_WRITABLE_IMP_ID_REGS)); + test_wants_mte(); + vm = vm_create(1); vm_enable_cap(vm, KVM_CAP_ARM_WRITABLE_IMP_ID_REGS, 0); vcpu = vm_vcpu_add(vm, 0, guest_code); + kvm_arch_vm_finalize_vcpus(vm); /* Check for AARCH64 only system */ val = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64PFR0_EL1)); @@ -780,13 +783,10 @@ int main(void) ksft_print_header(); - test_cnt = ARRAY_SIZE(ftr_id_aa64dfr0_el1) + ARRAY_SIZE(ftr_id_dfr0_el1) + - ARRAY_SIZE(ftr_id_aa64isar0_el1) + ARRAY_SIZE(ftr_id_aa64isar1_el1) + - ARRAY_SIZE(ftr_id_aa64isar2_el1) + ARRAY_SIZE(ftr_id_aa64pfr0_el1) + - ARRAY_SIZE(ftr_id_aa64pfr1_el1) + ARRAY_SIZE(ftr_id_aa64mmfr0_el1) + - ARRAY_SIZE(ftr_id_aa64mmfr1_el1) + ARRAY_SIZE(ftr_id_aa64mmfr2_el1) + - ARRAY_SIZE(ftr_id_aa64mmfr3_el1) + ARRAY_SIZE(ftr_id_aa64zfr0_el1) - - ARRAY_SIZE(test_regs) + 3 + MPAM_IDREG_TEST + MTE_IDREG_TEST; + test_cnt = 3 + MPAM_IDREG_TEST + MTE_IDREG_TEST; + for (i = 0; i < ARRAY_SIZE(test_regs); i++) + for (j = 0; test_regs[i].ftr_bits[j].type != FTR_END; j++) + test_cnt++; ksft_set_plan(test_cnt); diff --git a/tools/testing/selftests/kvm/arm64/smccc_filter.c b/tools/testing/selftests/kvm/arm64/smccc_filter.c index 2d189f3da228..1763b9d45400 100644 --- a/tools/testing/selftests/kvm/arm64/smccc_filter.c +++ b/tools/testing/selftests/kvm/arm64/smccc_filter.c @@ -22,8 +22,20 @@ enum smccc_conduit { SMC_INSN, }; +static bool test_runs_at_el2(void) +{ + struct kvm_vm *vm = vm_create(1); + struct kvm_vcpu_init init; + + kvm_get_default_vcpu_target(vm, &init); + kvm_vm_free(vm); + + return init.features[0] & BIT(KVM_ARM_VCPU_HAS_EL2); +} + #define for_each_conduit(conduit) \ - for (conduit = HVC_INSN; conduit <= SMC_INSN; conduit++) + for (conduit = test_runs_at_el2() ? SMC_INSN : HVC_INSN; \ + conduit <= SMC_INSN; conduit++) static void guest_main(uint32_t func_id, enum smccc_conduit conduit) { @@ -64,7 +76,7 @@ static struct kvm_vm *setup_vm(struct kvm_vcpu **vcpu) struct kvm_vm *vm; vm = vm_create(1); - vm_ioctl(vm, KVM_ARM_PREFERRED_TARGET, &init); + kvm_get_default_vcpu_target(vm, &init); /* * Enable in-kernel emulation of PSCI to ensure that calls are denied @@ -73,6 +85,7 @@ static struct kvm_vm *setup_vm(struct kvm_vcpu **vcpu) init.features[0] |= (1 << KVM_ARM_VCPU_PSCI_0_2); *vcpu = aarch64_vcpu_add(vm, 0, &init, guest_main); + kvm_arch_vm_finalize_vcpus(vm); return vm; } diff --git a/tools/testing/selftests/kvm/arm64/vgic_init.c b/tools/testing/selftests/kvm/arm64/vgic_init.c index a8e0f46bc0ab..8d6d3a4ae4db 100644 --- a/tools/testing/selftests/kvm/arm64/vgic_init.c +++ b/tools/testing/selftests/kvm/arm64/vgic_init.c @@ -994,6 +994,8 @@ int main(int ac, char **av) int pa_bits; int cnt_impl = 0; + test_disable_default_vgic(); + pa_bits = vm_guest_mode_params[VM_MODE_DEFAULT].pa_bits; max_phys_size = 1ULL << pa_bits; diff --git a/tools/testing/selftests/kvm/arm64/vgic_irq.c b/tools/testing/selftests/kvm/arm64/vgic_irq.c index a09dd423c2d7..6338f5bbdb70 100644 --- a/tools/testing/selftests/kvm/arm64/vgic_irq.c +++ b/tools/testing/selftests/kvm/arm64/vgic_irq.c @@ -752,7 +752,6 @@ static void test_vgic(uint32_t nr_irqs, bool level_sensitive, bool eoi_split) vcpu_args_set(vcpu, 1, args_gva); gic_fd = vgic_v3_setup(vm, 1, nr_irqs); - __TEST_REQUIRE(gic_fd >= 0, "Failed to create vgic-v3, skipping"); vm_install_exception_handler(vm, VECTOR_IRQ_CURRENT, guest_irq_handlers[args.eoi_split][args.level_sensitive]); @@ -802,6 +801,9 @@ int main(int argc, char **argv) int opt; bool eoi_split = false; + TEST_REQUIRE(kvm_supports_vgic_v3()); + test_disable_default_vgic(); + while ((opt = getopt(argc, argv, "hn:e:l:")) != -1) { switch (opt) { case 'n': diff --git a/tools/testing/selftests/kvm/arm64/vgic_lpi_stress.c b/tools/testing/selftests/kvm/arm64/vgic_lpi_stress.c index fc4fe52fb6f8..87922a89b134 100644 --- a/tools/testing/selftests/kvm/arm64/vgic_lpi_stress.c +++ b/tools/testing/selftests/kvm/arm64/vgic_lpi_stress.c @@ -27,7 +27,7 @@ static vm_paddr_t gpa_base; static struct kvm_vm *vm; static struct kvm_vcpu **vcpus; -static int gic_fd, its_fd; +static int its_fd; static struct test_data { bool request_vcpus_stop; @@ -214,9 +214,6 @@ static void setup_test_data(void) static void setup_gic(void) { - gic_fd = vgic_v3_setup(vm, test_data.nr_cpus, 64); - __TEST_REQUIRE(gic_fd >= 0, "Failed to create GICv3"); - its_fd = vgic_its_setup(vm); } @@ -355,7 +352,6 @@ static void setup_vm(void) static void destroy_vm(void) { close(its_fd); - close(gic_fd); kvm_vm_free(vm); free(vcpus); } @@ -374,6 +370,8 @@ int main(int argc, char **argv) u32 nr_threads; int c; + TEST_REQUIRE(kvm_supports_vgic_v3()); + while ((c = getopt(argc, argv, "hv:d:e:i:")) != -1) { switch (c) { case 'v': diff --git a/tools/testing/selftests/kvm/arm64/vpmu_counter_access.c b/tools/testing/selftests/kvm/arm64/vpmu_counter_access.c index a0c4ab839155..ae36325c022f 100644 --- a/tools/testing/selftests/kvm/arm64/vpmu_counter_access.c +++ b/tools/testing/selftests/kvm/arm64/vpmu_counter_access.c @@ -28,7 +28,6 @@ struct vpmu_vm { struct kvm_vm *vm; struct kvm_vcpu *vcpu; - int gic_fd; }; static struct vpmu_vm vpmu_vm; @@ -45,11 +44,6 @@ static uint64_t get_pmcr_n(uint64_t pmcr) return FIELD_GET(ARMV8_PMU_PMCR_N, pmcr); } -static void set_pmcr_n(uint64_t *pmcr, uint64_t pmcr_n) -{ - u64p_replace_bits((__u64 *) pmcr, pmcr_n, ARMV8_PMU_PMCR_N); -} - static uint64_t get_counters_mask(uint64_t n) { uint64_t mask = BIT(ARMV8_PMU_CYCLE_IDX); @@ -415,10 +409,6 @@ static void create_vpmu_vm(void *guest_code) .attr = KVM_ARM_VCPU_PMU_V3_IRQ, .addr = (uint64_t)&irq, }; - struct kvm_device_attr init_attr = { - .group = KVM_ARM_VCPU_PMU_V3_CTRL, - .attr = KVM_ARM_VCPU_PMU_V3_INIT, - }; /* The test creates the vpmu_vm multiple times. Ensure a clean state */ memset(&vpmu_vm, 0, sizeof(vpmu_vm)); @@ -431,13 +421,12 @@ static void create_vpmu_vm(void *guest_code) } /* Create vCPU with PMUv3 */ - vm_ioctl(vpmu_vm.vm, KVM_ARM_PREFERRED_TARGET, &init); + kvm_get_default_vcpu_target(vpmu_vm.vm, &init); init.features[0] |= (1 << KVM_ARM_VCPU_PMU_V3); vpmu_vm.vcpu = aarch64_vcpu_add(vpmu_vm.vm, 0, &init, guest_code); vcpu_init_descriptor_tables(vpmu_vm.vcpu); - vpmu_vm.gic_fd = vgic_v3_setup(vpmu_vm.vm, 1, 64); - __TEST_REQUIRE(vpmu_vm.gic_fd >= 0, - "Failed to create vgic-v3, skipping"); + + kvm_arch_vm_finalize_vcpus(vpmu_vm.vm); /* Make sure that PMUv3 support is indicated in the ID register */ dfr0 = vcpu_get_reg(vpmu_vm.vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64DFR0_EL1)); @@ -446,14 +435,11 @@ static void create_vpmu_vm(void *guest_code) pmuver >= ID_AA64DFR0_EL1_PMUVer_IMP, "Unexpected PMUVER (0x%x) on the vCPU with PMUv3", pmuver); - /* Initialize vPMU */ vcpu_ioctl(vpmu_vm.vcpu, KVM_SET_DEVICE_ATTR, &irq_attr); - vcpu_ioctl(vpmu_vm.vcpu, KVM_SET_DEVICE_ATTR, &init_attr); } static void destroy_vpmu_vm(void) { - close(vpmu_vm.gic_fd); kvm_vm_free(vpmu_vm.vm); } @@ -475,33 +461,28 @@ static void run_vcpu(struct kvm_vcpu *vcpu, uint64_t pmcr_n) } } -static void test_create_vpmu_vm_with_pmcr_n(uint64_t pmcr_n, bool expect_fail) +static void test_create_vpmu_vm_with_nr_counters(unsigned int nr_counters, bool expect_fail) { struct kvm_vcpu *vcpu; - uint64_t pmcr, pmcr_orig; + unsigned int prev; + int ret; create_vpmu_vm(guest_code); vcpu = vpmu_vm.vcpu; - pmcr_orig = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_PMCR_EL0)); - pmcr = pmcr_orig; + prev = get_pmcr_n(vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_PMCR_EL0))); - /* - * Setting a larger value of PMCR.N should not modify the field, and - * return a success. - */ - set_pmcr_n(&pmcr, pmcr_n); - vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(SYS_PMCR_EL0), pmcr); - pmcr = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_PMCR_EL0)); + ret = __vcpu_device_attr_set(vcpu, KVM_ARM_VCPU_PMU_V3_CTRL, + KVM_ARM_VCPU_PMU_V3_SET_NR_COUNTERS, &nr_counters); if (expect_fail) - TEST_ASSERT(pmcr_orig == pmcr, - "PMCR.N modified by KVM to a larger value (PMCR: 0x%lx) for pmcr_n: 0x%lx", - pmcr, pmcr_n); + TEST_ASSERT(ret && errno == EINVAL, + "Setting more PMU counters (%u) than available (%u) unexpectedly succeeded", + nr_counters, prev); else - TEST_ASSERT(pmcr_n == get_pmcr_n(pmcr), - "Failed to update PMCR.N to %lu (received: %lu)", - pmcr_n, get_pmcr_n(pmcr)); + TEST_ASSERT(!ret, KVM_IOCTL_ERROR(KVM_SET_DEVICE_ATTR, ret)); + + vcpu_device_attr_set(vcpu, KVM_ARM_VCPU_PMU_V3_CTRL, KVM_ARM_VCPU_PMU_V3_INIT, NULL); } /* @@ -516,11 +497,11 @@ static void run_access_test(uint64_t pmcr_n) pr_debug("Test with pmcr_n %lu\n", pmcr_n); - test_create_vpmu_vm_with_pmcr_n(pmcr_n, false); + test_create_vpmu_vm_with_nr_counters(pmcr_n, false); vcpu = vpmu_vm.vcpu; /* Save the initial sp to restore them later to run the guest again */ - sp = vcpu_get_reg(vcpu, ARM64_CORE_REG(sp_el1)); + sp = vcpu_get_reg(vcpu, ctxt_reg_alias(vcpu, SYS_SP_EL1)); run_vcpu(vcpu, pmcr_n); @@ -528,11 +509,11 @@ static void run_access_test(uint64_t pmcr_n) * Reset and re-initialize the vCPU, and run the guest code again to * check if PMCR_EL0.N is preserved. */ - vm_ioctl(vpmu_vm.vm, KVM_ARM_PREFERRED_TARGET, &init); + kvm_get_default_vcpu_target(vpmu_vm.vm, &init); init.features[0] |= (1 << KVM_ARM_VCPU_PMU_V3); aarch64_vcpu_setup(vcpu, &init); vcpu_init_descriptor_tables(vcpu); - vcpu_set_reg(vcpu, ARM64_CORE_REG(sp_el1), sp); + vcpu_set_reg(vcpu, ctxt_reg_alias(vcpu, SYS_SP_EL1), sp); vcpu_set_reg(vcpu, ARM64_CORE_REG(regs.pc), (uint64_t)guest_code); run_vcpu(vcpu, pmcr_n); @@ -557,7 +538,7 @@ static void run_pmregs_validity_test(uint64_t pmcr_n) uint64_t set_reg_id, clr_reg_id, reg_val; uint64_t valid_counters_mask, max_counters_mask; - test_create_vpmu_vm_with_pmcr_n(pmcr_n, false); + test_create_vpmu_vm_with_nr_counters(pmcr_n, false); vcpu = vpmu_vm.vcpu; valid_counters_mask = get_counters_mask(pmcr_n); @@ -611,7 +592,7 @@ static void run_error_test(uint64_t pmcr_n) { pr_debug("Error test with pmcr_n %lu (larger than the host)\n", pmcr_n); - test_create_vpmu_vm_with_pmcr_n(pmcr_n, true); + test_create_vpmu_vm_with_nr_counters(pmcr_n, true); destroy_vpmu_vm(); } @@ -629,11 +610,25 @@ static uint64_t get_pmcr_n_limit(void) return get_pmcr_n(pmcr); } +static bool kvm_supports_nr_counters_attr(void) +{ + bool supported; + + create_vpmu_vm(NULL); + supported = !__vcpu_has_device_attr(vpmu_vm.vcpu, KVM_ARM_VCPU_PMU_V3_CTRL, + KVM_ARM_VCPU_PMU_V3_SET_NR_COUNTERS); + destroy_vpmu_vm(); + + return supported; +} + int main(void) { uint64_t i, pmcr_n; TEST_REQUIRE(kvm_has_cap(KVM_CAP_ARM_PMU_V3)); + TEST_REQUIRE(kvm_supports_vgic_v3()); + TEST_REQUIRE(kvm_supports_nr_counters_attr()); pmcr_n = get_pmcr_n_limit(); for (i = 0; i <= pmcr_n; i++) { diff --git a/tools/testing/selftests/kvm/dirty_log_perf_test.c b/tools/testing/selftests/kvm/dirty_log_perf_test.c index e79817bd0e29..0a1ea1d1e2d8 100644 --- a/tools/testing/selftests/kvm/dirty_log_perf_test.c +++ b/tools/testing/selftests/kvm/dirty_log_perf_test.c @@ -20,38 +20,6 @@ #include "guest_modes.h" #include "ucall_common.h" -#ifdef __aarch64__ -#include "arm64/vgic.h" - -static int gic_fd; - -static void arch_setup_vm(struct kvm_vm *vm, unsigned int nr_vcpus) -{ - /* - * The test can still run even if hardware does not support GICv3, as it - * is only an optimization to reduce guest exits. - */ - gic_fd = vgic_v3_setup(vm, nr_vcpus, 64); -} - -static void arch_cleanup_vm(struct kvm_vm *vm) -{ - if (gic_fd > 0) - close(gic_fd); -} - -#else /* __aarch64__ */ - -static void arch_setup_vm(struct kvm_vm *vm, unsigned int nr_vcpus) -{ -} - -static void arch_cleanup_vm(struct kvm_vm *vm) -{ -} - -#endif - /* How many host loops to run by default (one KVM_GET_DIRTY_LOG for each loop)*/ #define TEST_HOST_LOOP_N 2UL @@ -166,8 +134,6 @@ static void run_test(enum vm_guest_mode mode, void *arg) vm_enable_cap(vm, KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2, dirty_log_manual_caps); - arch_setup_vm(vm, nr_vcpus); - /* Start the iterations */ iteration = 0; host_quit = false; @@ -285,7 +251,6 @@ static void run_test(enum vm_guest_mode mode, void *arg) } memstress_free_bitmaps(bitmaps, p->slots); - arch_cleanup_vm(vm); memstress_destroy_vm(vm); } diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c index 23593d9eeba9..d58a641b0e6a 100644 --- a/tools/testing/selftests/kvm/dirty_log_test.c +++ b/tools/testing/selftests/kvm/dirty_log_test.c @@ -585,6 +585,7 @@ static struct kvm_vm *create_vm(enum vm_guest_mode mode, struct kvm_vcpu **vcpu, log_mode_create_vm_done(vm); *vcpu = vm_vcpu_add(vm, 0, guest_code); + kvm_arch_vm_finalize_vcpus(vm); return vm; } diff --git a/tools/testing/selftests/kvm/get-reg-list.c b/tools/testing/selftests/kvm/get-reg-list.c index 91f05f78e824..f4644c9d2d3b 100644 --- a/tools/testing/selftests/kvm/get-reg-list.c +++ b/tools/testing/selftests/kvm/get-reg-list.c @@ -116,10 +116,13 @@ void __weak finalize_vcpu(struct kvm_vcpu *vcpu, struct vcpu_reg_list *c) } #ifdef __aarch64__ -static void prepare_vcpu_init(struct vcpu_reg_list *c, struct kvm_vcpu_init *init) +static void prepare_vcpu_init(struct kvm_vm *vm, struct vcpu_reg_list *c, + struct kvm_vcpu_init *init) { struct vcpu_reg_sublist *s; + vm_ioctl(vm, KVM_ARM_PREFERRED_TARGET, init); + for_each_sublist(c, s) if (s->capability) init->features[s->feature / 32] |= 1 << (s->feature % 32); @@ -127,10 +130,10 @@ static void prepare_vcpu_init(struct vcpu_reg_list *c, struct kvm_vcpu_init *ini static struct kvm_vcpu *vcpu_config_get_vcpu(struct vcpu_reg_list *c, struct kvm_vm *vm) { - struct kvm_vcpu_init init = { .target = -1, }; + struct kvm_vcpu_init init; struct kvm_vcpu *vcpu; - prepare_vcpu_init(c, &init); + prepare_vcpu_init(vm, c, &init); vcpu = __vm_vcpu_add(vm, 0); aarch64_vcpu_setup(vcpu, &init); diff --git a/tools/testing/selftests/kvm/guest_memfd_test.c b/tools/testing/selftests/kvm/guest_memfd_test.c index ce687f8d248f..b3ca6737f304 100644 --- a/tools/testing/selftests/kvm/guest_memfd_test.c +++ b/tools/testing/selftests/kvm/guest_memfd_test.c @@ -13,12 +13,16 @@ #include <linux/bitmap.h> #include <linux/falloc.h> +#include <linux/sizes.h> +#include <setjmp.h> +#include <signal.h> #include <sys/mman.h> #include <sys/types.h> #include <sys/stat.h> #include "kvm_util.h" #include "test_util.h" +#include "ucall_common.h" static void test_file_read_write(int fd) { @@ -34,12 +38,83 @@ static void test_file_read_write(int fd) "pwrite on a guest_mem fd should fail"); } -static void test_mmap(int fd, size_t page_size) +static void test_mmap_supported(int fd, size_t page_size, size_t total_size) +{ + const char val = 0xaa; + char *mem; + size_t i; + int ret; + + mem = mmap(NULL, total_size, PROT_READ | PROT_WRITE, MAP_PRIVATE, fd, 0); + TEST_ASSERT(mem == MAP_FAILED, "Copy-on-write not allowed by guest_memfd."); + + mem = mmap(NULL, total_size, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0); + TEST_ASSERT(mem != MAP_FAILED, "mmap() for guest_memfd should succeed."); + + memset(mem, val, total_size); + for (i = 0; i < total_size; i++) + TEST_ASSERT_EQ(READ_ONCE(mem[i]), val); + + ret = fallocate(fd, FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE, 0, + page_size); + TEST_ASSERT(!ret, "fallocate the first page should succeed."); + + for (i = 0; i < page_size; i++) + TEST_ASSERT_EQ(READ_ONCE(mem[i]), 0x00); + for (; i < total_size; i++) + TEST_ASSERT_EQ(READ_ONCE(mem[i]), val); + + memset(mem, val, page_size); + for (i = 0; i < total_size; i++) + TEST_ASSERT_EQ(READ_ONCE(mem[i]), val); + + ret = munmap(mem, total_size); + TEST_ASSERT(!ret, "munmap() should succeed."); +} + +static sigjmp_buf jmpbuf; +void fault_sigbus_handler(int signum) +{ + siglongjmp(jmpbuf, 1); +} + +static void test_fault_overflow(int fd, size_t page_size, size_t total_size) +{ + struct sigaction sa_old, sa_new = { + .sa_handler = fault_sigbus_handler, + }; + size_t map_size = total_size * 4; + const char val = 0xaa; + char *mem; + size_t i; + int ret; + + mem = mmap(NULL, map_size, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0); + TEST_ASSERT(mem != MAP_FAILED, "mmap() for guest_memfd should succeed."); + + sigaction(SIGBUS, &sa_new, &sa_old); + if (sigsetjmp(jmpbuf, 1) == 0) { + memset(mem, 0xaa, map_size); + TEST_ASSERT(false, "memset() should have triggered SIGBUS."); + } + sigaction(SIGBUS, &sa_old, NULL); + + for (i = 0; i < total_size; i++) + TEST_ASSERT_EQ(READ_ONCE(mem[i]), val); + + ret = munmap(mem, map_size); + TEST_ASSERT(!ret, "munmap() should succeed."); +} + +static void test_mmap_not_supported(int fd, size_t page_size, size_t total_size) { char *mem; mem = mmap(NULL, page_size, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0); TEST_ASSERT_EQ(mem, MAP_FAILED); + + mem = mmap(NULL, total_size, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0); + TEST_ASSERT_EQ(mem, MAP_FAILED); } static void test_file_size(int fd, size_t page_size, size_t total_size) @@ -120,80 +195,187 @@ static void test_invalid_punch_hole(int fd, size_t page_size, size_t total_size) } } -static void test_create_guest_memfd_invalid(struct kvm_vm *vm) +static void test_create_guest_memfd_invalid_sizes(struct kvm_vm *vm, + uint64_t guest_memfd_flags, + size_t page_size) { - size_t page_size = getpagesize(); - uint64_t flag; size_t size; int fd; for (size = 1; size < page_size; size++) { - fd = __vm_create_guest_memfd(vm, size, 0); - TEST_ASSERT(fd == -1 && errno == EINVAL, + fd = __vm_create_guest_memfd(vm, size, guest_memfd_flags); + TEST_ASSERT(fd < 0 && errno == EINVAL, "guest_memfd() with non-page-aligned page size '0x%lx' should fail with EINVAL", size); } - - for (flag = BIT(0); flag; flag <<= 1) { - fd = __vm_create_guest_memfd(vm, page_size, flag); - TEST_ASSERT(fd == -1 && errno == EINVAL, - "guest_memfd() with flag '0x%lx' should fail with EINVAL", - flag); - } } static void test_create_guest_memfd_multiple(struct kvm_vm *vm) { int fd1, fd2, ret; struct stat st1, st2; + size_t page_size = getpagesize(); - fd1 = __vm_create_guest_memfd(vm, 4096, 0); + fd1 = __vm_create_guest_memfd(vm, page_size, 0); TEST_ASSERT(fd1 != -1, "memfd creation should succeed"); ret = fstat(fd1, &st1); TEST_ASSERT(ret != -1, "memfd fstat should succeed"); - TEST_ASSERT(st1.st_size == 4096, "memfd st_size should match requested size"); + TEST_ASSERT(st1.st_size == page_size, "memfd st_size should match requested size"); - fd2 = __vm_create_guest_memfd(vm, 8192, 0); + fd2 = __vm_create_guest_memfd(vm, page_size * 2, 0); TEST_ASSERT(fd2 != -1, "memfd creation should succeed"); ret = fstat(fd2, &st2); TEST_ASSERT(ret != -1, "memfd fstat should succeed"); - TEST_ASSERT(st2.st_size == 8192, "second memfd st_size should match requested size"); + TEST_ASSERT(st2.st_size == page_size * 2, "second memfd st_size should match requested size"); ret = fstat(fd1, &st1); TEST_ASSERT(ret != -1, "memfd fstat should succeed"); - TEST_ASSERT(st1.st_size == 4096, "first memfd st_size should still match requested size"); + TEST_ASSERT(st1.st_size == page_size, "first memfd st_size should still match requested size"); TEST_ASSERT(st1.st_ino != st2.st_ino, "different memfd should have different inode numbers"); close(fd2); close(fd1); } -int main(int argc, char *argv[]) +static void test_guest_memfd_flags(struct kvm_vm *vm, uint64_t valid_flags) { - size_t page_size; - size_t total_size; + size_t page_size = getpagesize(); + uint64_t flag; int fd; - struct kvm_vm *vm; - TEST_REQUIRE(kvm_has_cap(KVM_CAP_GUEST_MEMFD)); + for (flag = BIT(0); flag; flag <<= 1) { + fd = __vm_create_guest_memfd(vm, page_size, flag); + if (flag & valid_flags) { + TEST_ASSERT(fd >= 0, + "guest_memfd() with flag '0x%lx' should succeed", + flag); + close(fd); + } else { + TEST_ASSERT(fd < 0 && errno == EINVAL, + "guest_memfd() with flag '0x%lx' should fail with EINVAL", + flag); + } + } +} + +static void test_guest_memfd(unsigned long vm_type) +{ + uint64_t flags = 0; + struct kvm_vm *vm; + size_t total_size; + size_t page_size; + int fd; page_size = getpagesize(); total_size = page_size * 4; - vm = vm_create_barebones(); + vm = vm_create_barebones_type(vm_type); + + if (vm_check_cap(vm, KVM_CAP_GUEST_MEMFD_MMAP)) + flags |= GUEST_MEMFD_FLAG_MMAP; - test_create_guest_memfd_invalid(vm); test_create_guest_memfd_multiple(vm); + test_create_guest_memfd_invalid_sizes(vm, flags, page_size); - fd = vm_create_guest_memfd(vm, total_size, 0); + fd = vm_create_guest_memfd(vm, total_size, flags); test_file_read_write(fd); - test_mmap(fd, page_size); + + if (flags & GUEST_MEMFD_FLAG_MMAP) { + test_mmap_supported(fd, page_size, total_size); + test_fault_overflow(fd, page_size, total_size); + } else { + test_mmap_not_supported(fd, page_size, total_size); + } + test_file_size(fd, page_size, total_size); test_fallocate(fd, page_size, total_size); test_invalid_punch_hole(fd, page_size, total_size); + test_guest_memfd_flags(vm, flags); + close(fd); + kvm_vm_free(vm); +} + +static void guest_code(uint8_t *mem, uint64_t size) +{ + size_t i; + + for (i = 0; i < size; i++) + __GUEST_ASSERT(mem[i] == 0xaa, + "Guest expected 0xaa at offset %lu, got 0x%x", i, mem[i]); + + memset(mem, 0xff, size); + GUEST_DONE(); +} + +static void test_guest_memfd_guest(void) +{ + /* + * Skip the first 4gb and slot0. slot0 maps <1gb and is used to back + * the guest's code, stack, and page tables, and low memory contains + * the PCI hole and other MMIO regions that need to be avoided. + */ + const uint64_t gpa = SZ_4G; + const int slot = 1; + + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + uint8_t *mem; + size_t size; + int fd, i; + + if (!kvm_has_cap(KVM_CAP_GUEST_MEMFD_MMAP)) + return; + + vm = __vm_create_shape_with_one_vcpu(VM_SHAPE_DEFAULT, &vcpu, 1, guest_code); + + TEST_ASSERT(vm_check_cap(vm, KVM_CAP_GUEST_MEMFD_MMAP), + "Default VM type should always support guest_memfd mmap()"); + + size = vm->page_size; + fd = vm_create_guest_memfd(vm, size, GUEST_MEMFD_FLAG_MMAP); + vm_set_user_memory_region2(vm, slot, KVM_MEM_GUEST_MEMFD, gpa, size, NULL, fd, 0); + + mem = mmap(NULL, size, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0); + TEST_ASSERT(mem != MAP_FAILED, "mmap() on guest_memfd failed"); + memset(mem, 0xaa, size); + munmap(mem, size); + + virt_pg_map(vm, gpa, gpa); + vcpu_args_set(vcpu, 2, gpa, size); + vcpu_run(vcpu); + + TEST_ASSERT_EQ(get_ucall(vcpu, NULL), UCALL_DONE); + + mem = mmap(NULL, size, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0); + TEST_ASSERT(mem != MAP_FAILED, "mmap() on guest_memfd failed"); + for (i = 0; i < size; i++) + TEST_ASSERT_EQ(mem[i], 0xff); + + close(fd); + kvm_vm_free(vm); +} + +int main(int argc, char *argv[]) +{ + unsigned long vm_types, vm_type; + + TEST_REQUIRE(kvm_has_cap(KVM_CAP_GUEST_MEMFD)); + + /* + * Not all architectures support KVM_CAP_VM_TYPES. However, those that + * support guest_memfd have that support for the default VM type. + */ + vm_types = kvm_check_cap(KVM_CAP_VM_TYPES); + if (!vm_types) + vm_types = BIT(VM_TYPE_DEFAULT); + + for_each_set_bit(vm_type, &vm_types, BITS_PER_TYPE(vm_types)) + test_guest_memfd(vm_type); + + test_guest_memfd_guest(); } diff --git a/tools/testing/selftests/kvm/include/arm64/arch_timer.h b/tools/testing/selftests/kvm/include/arm64/arch_timer.h index bf461de34785..e2c4e9f0010f 100644 --- a/tools/testing/selftests/kvm/include/arm64/arch_timer.h +++ b/tools/testing/selftests/kvm/include/arm64/arch_timer.h @@ -155,4 +155,28 @@ static inline void timer_set_next_tval_ms(enum arch_timer timer, uint32_t msec) timer_set_tval(timer, msec_to_cycles(msec)); } +static inline u32 vcpu_get_vtimer_irq(struct kvm_vcpu *vcpu) +{ + u32 intid; + u64 attr; + + attr = vcpu_has_el2(vcpu) ? KVM_ARM_VCPU_TIMER_IRQ_HVTIMER : + KVM_ARM_VCPU_TIMER_IRQ_VTIMER; + vcpu_device_attr_get(vcpu, KVM_ARM_VCPU_TIMER_CTRL, attr, &intid); + + return intid; +} + +static inline u32 vcpu_get_ptimer_irq(struct kvm_vcpu *vcpu) +{ + u32 intid; + u64 attr; + + attr = vcpu_has_el2(vcpu) ? KVM_ARM_VCPU_TIMER_IRQ_HPTIMER : + KVM_ARM_VCPU_TIMER_IRQ_PTIMER; + vcpu_device_attr_get(vcpu, KVM_ARM_VCPU_TIMER_CTRL, attr, &intid); + + return intid; +} + #endif /* SELFTEST_KVM_ARCH_TIMER_H */ diff --git a/tools/testing/selftests/kvm/include/arm64/kvm_util_arch.h b/tools/testing/selftests/kvm/include/arm64/kvm_util_arch.h index e43a57d99b56..b973bb2c64a6 100644 --- a/tools/testing/selftests/kvm/include/arm64/kvm_util_arch.h +++ b/tools/testing/selftests/kvm/include/arm64/kvm_util_arch.h @@ -2,6 +2,9 @@ #ifndef SELFTEST_KVM_UTIL_ARCH_H #define SELFTEST_KVM_UTIL_ARCH_H -struct kvm_vm_arch {}; +struct kvm_vm_arch { + bool has_gic; + int gic_fd; +}; #endif // SELFTEST_KVM_UTIL_ARCH_H diff --git a/tools/testing/selftests/kvm/include/arm64/processor.h b/tools/testing/selftests/kvm/include/arm64/processor.h index 255fed769a8a..6f481475c135 100644 --- a/tools/testing/selftests/kvm/include/arm64/processor.h +++ b/tools/testing/selftests/kvm/include/arm64/processor.h @@ -175,6 +175,7 @@ void vm_install_exception_handler(struct kvm_vm *vm, void vm_install_sync_handler(struct kvm_vm *vm, int vector, int ec, handler_fn handler); +uint64_t *virt_get_pte_hva_at_level(struct kvm_vm *vm, vm_vaddr_t gva, int level); uint64_t *virt_get_pte_hva(struct kvm_vm *vm, vm_vaddr_t gva); static inline void cpu_relax(void) @@ -300,4 +301,77 @@ void smccc_smc(uint32_t function_id, uint64_t arg0, uint64_t arg1, /* Execute a Wait For Interrupt instruction. */ void wfi(void); +void test_wants_mte(void); +void test_disable_default_vgic(void); + +bool vm_supports_el2(struct kvm_vm *vm); +static bool vcpu_has_el2(struct kvm_vcpu *vcpu) +{ + return vcpu->init.features[0] & BIT(KVM_ARM_VCPU_HAS_EL2); +} + +#define MAPPED_EL2_SYSREG(el2, el1) \ + case SYS_##el1: \ + if (vcpu_has_el2(vcpu)) \ + alias = SYS_##el2; \ + break + + +static __always_inline u64 ctxt_reg_alias(struct kvm_vcpu *vcpu, u32 encoding) +{ + u32 alias = encoding; + + BUILD_BUG_ON(!__builtin_constant_p(encoding)); + + switch (encoding) { + MAPPED_EL2_SYSREG(SCTLR_EL2, SCTLR_EL1); + MAPPED_EL2_SYSREG(CPTR_EL2, CPACR_EL1); + MAPPED_EL2_SYSREG(TTBR0_EL2, TTBR0_EL1); + MAPPED_EL2_SYSREG(TTBR1_EL2, TTBR1_EL1); + MAPPED_EL2_SYSREG(TCR_EL2, TCR_EL1); + MAPPED_EL2_SYSREG(VBAR_EL2, VBAR_EL1); + MAPPED_EL2_SYSREG(AFSR0_EL2, AFSR0_EL1); + MAPPED_EL2_SYSREG(AFSR1_EL2, AFSR1_EL1); + MAPPED_EL2_SYSREG(ESR_EL2, ESR_EL1); + MAPPED_EL2_SYSREG(FAR_EL2, FAR_EL1); + MAPPED_EL2_SYSREG(MAIR_EL2, MAIR_EL1); + MAPPED_EL2_SYSREG(TCR2_EL2, TCR2_EL1); + MAPPED_EL2_SYSREG(PIR_EL2, PIR_EL1); + MAPPED_EL2_SYSREG(PIRE0_EL2, PIRE0_EL1); + MAPPED_EL2_SYSREG(POR_EL2, POR_EL1); + MAPPED_EL2_SYSREG(AMAIR_EL2, AMAIR_EL1); + MAPPED_EL2_SYSREG(ELR_EL2, ELR_EL1); + MAPPED_EL2_SYSREG(SPSR_EL2, SPSR_EL1); + MAPPED_EL2_SYSREG(ZCR_EL2, ZCR_EL1); + MAPPED_EL2_SYSREG(CONTEXTIDR_EL2, CONTEXTIDR_EL1); + MAPPED_EL2_SYSREG(SCTLR2_EL2, SCTLR2_EL1); + MAPPED_EL2_SYSREG(CNTHCTL_EL2, CNTKCTL_EL1); + case SYS_SP_EL1: + if (!vcpu_has_el2(vcpu)) + return ARM64_CORE_REG(sp_el1); + + alias = SYS_SP_EL2; + break; + default: + BUILD_BUG(); + } + + return KVM_ARM64_SYS_REG(alias); +} + +void kvm_get_default_vcpu_target(struct kvm_vm *vm, struct kvm_vcpu_init *init); + +static inline unsigned int get_current_el(void) +{ + return (read_sysreg(CurrentEL) >> 2) & 0x3; +} + +#define do_smccc(...) \ +do { \ + if (get_current_el() == 2) \ + smccc_smc(__VA_ARGS__); \ + else \ + smccc_hvc(__VA_ARGS__); \ +} while (0) + #endif /* SELFTEST_KVM_PROCESSOR_H */ diff --git a/tools/testing/selftests/kvm/include/arm64/vgic.h b/tools/testing/selftests/kvm/include/arm64/vgic.h index c481d0c00a5d..688beccc9436 100644 --- a/tools/testing/selftests/kvm/include/arm64/vgic.h +++ b/tools/testing/selftests/kvm/include/arm64/vgic.h @@ -16,6 +16,9 @@ ((uint64_t)(flags) << 12) | \ index) +bool kvm_supports_vgic_v3(void); +int __vgic_v3_setup(struct kvm_vm *vm, unsigned int nr_vcpus, uint32_t nr_irqs); +void __vgic_v3_init(int fd); int vgic_v3_setup(struct kvm_vm *vm, unsigned int nr_vcpus, uint32_t nr_irqs); #define VGIC_MAX_RESERVED 1023 diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h index 23a506d7eca3..26cc30290e76 100644 --- a/tools/testing/selftests/kvm/include/kvm_util.h +++ b/tools/testing/selftests/kvm/include/kvm_util.h @@ -64,6 +64,9 @@ struct kvm_vcpu { #ifdef __x86_64__ struct kvm_cpuid2 *cpuid; #endif +#ifdef __aarch64__ + struct kvm_vcpu_init init; +#endif struct kvm_binary_stats stats; struct kvm_dirty_gfn *dirty_gfns; uint32_t fetch_index; @@ -260,13 +263,18 @@ int __open_path_or_exit(const char *path, int flags, const char *enoent_help); int open_path_or_exit(const char *path, int flags); int open_kvm_dev_path_or_exit(void); -bool get_kvm_param_bool(const char *param); -bool get_kvm_intel_param_bool(const char *param); -bool get_kvm_amd_param_bool(const char *param); +int kvm_get_module_param_integer(const char *module_name, const char *param); +bool kvm_get_module_param_bool(const char *module_name, const char *param); + +static inline bool get_kvm_param_bool(const char *param) +{ + return kvm_get_module_param_bool("kvm", param); +} -int get_kvm_param_integer(const char *param); -int get_kvm_intel_param_integer(const char *param); -int get_kvm_amd_param_integer(const char *param); +static inline int get_kvm_param_integer(const char *param) +{ + return kvm_get_module_param_integer("kvm", param); +} unsigned int kvm_check_cap(long cap); @@ -1257,7 +1265,9 @@ static inline int __vm_disable_nx_huge_pages(struct kvm_vm *vm) */ void kvm_selftest_arch_init(void); -void kvm_arch_vm_post_create(struct kvm_vm *vm); +void kvm_arch_vm_post_create(struct kvm_vm *vm, unsigned int nr_vcpus); +void kvm_arch_vm_finalize_vcpus(struct kvm_vm *vm); +void kvm_arch_vm_release(struct kvm_vm *vm); bool vm_is_gpa_protected(struct kvm_vm *vm, vm_paddr_t paddr); diff --git a/tools/testing/selftests/kvm/include/riscv/processor.h b/tools/testing/selftests/kvm/include/riscv/processor.h index 162f303d9daa..e58282488beb 100644 --- a/tools/testing/selftests/kvm/include/riscv/processor.h +++ b/tools/testing/selftests/kvm/include/riscv/processor.h @@ -9,6 +9,7 @@ #include <linux/stringify.h> #include <asm/csr.h> +#include <asm/vdso/processor.h> #include "kvm_util.h" #define INSN_OPCODE_MASK 0x007c diff --git a/tools/testing/selftests/kvm/include/x86/pmu.h b/tools/testing/selftests/kvm/include/x86/pmu.h index 3c10c4dc0ae8..72575eadb63a 100644 --- a/tools/testing/selftests/kvm/include/x86/pmu.h +++ b/tools/testing/selftests/kvm/include/x86/pmu.h @@ -5,8 +5,11 @@ #ifndef SELFTEST_KVM_PMU_H #define SELFTEST_KVM_PMU_H +#include <stdbool.h> #include <stdint.h> +#include <linux/bits.h> + #define KVM_PMU_EVENT_FILTER_MAX_EVENTS 300 /* @@ -61,6 +64,11 @@ #define INTEL_ARCH_BRANCHES_RETIRED RAW_EVENT(0xc4, 0x00) #define INTEL_ARCH_BRANCHES_MISPREDICTED RAW_EVENT(0xc5, 0x00) #define INTEL_ARCH_TOPDOWN_SLOTS RAW_EVENT(0xa4, 0x01) +#define INTEL_ARCH_TOPDOWN_BE_BOUND RAW_EVENT(0xa4, 0x02) +#define INTEL_ARCH_TOPDOWN_BAD_SPEC RAW_EVENT(0x73, 0x00) +#define INTEL_ARCH_TOPDOWN_FE_BOUND RAW_EVENT(0x9c, 0x01) +#define INTEL_ARCH_TOPDOWN_RETIRING RAW_EVENT(0xc2, 0x02) +#define INTEL_ARCH_LBR_INSERTS RAW_EVENT(0xe4, 0x01) #define AMD_ZEN_CORE_CYCLES RAW_EVENT(0x76, 0x00) #define AMD_ZEN_INSTRUCTIONS_RETIRED RAW_EVENT(0xc0, 0x00) @@ -80,6 +88,11 @@ enum intel_pmu_architectural_events { INTEL_ARCH_BRANCHES_RETIRED_INDEX, INTEL_ARCH_BRANCHES_MISPREDICTED_INDEX, INTEL_ARCH_TOPDOWN_SLOTS_INDEX, + INTEL_ARCH_TOPDOWN_BE_BOUND_INDEX, + INTEL_ARCH_TOPDOWN_BAD_SPEC_INDEX, + INTEL_ARCH_TOPDOWN_FE_BOUND_INDEX, + INTEL_ARCH_TOPDOWN_RETIRING_INDEX, + INTEL_ARCH_LBR_INSERTS_INDEX, NR_INTEL_ARCH_EVENTS, }; @@ -94,4 +107,17 @@ enum amd_pmu_zen_events { extern const uint64_t intel_pmu_arch_events[]; extern const uint64_t amd_pmu_zen_events[]; +enum pmu_errata { + INSTRUCTIONS_RETIRED_OVERCOUNT, + BRANCHES_RETIRED_OVERCOUNT, +}; +extern uint64_t pmu_errata_mask; + +void kvm_init_pmu_errata(void); + +static inline bool this_pmu_has_errata(enum pmu_errata errata) +{ + return pmu_errata_mask & BIT_ULL(errata); +} + #endif /* SELFTEST_KVM_PMU_H */ diff --git a/tools/testing/selftests/kvm/include/x86/processor.h b/tools/testing/selftests/kvm/include/x86/processor.h index 2efb05c2f2fb..51cd84b9ca66 100644 --- a/tools/testing/selftests/kvm/include/x86/processor.h +++ b/tools/testing/selftests/kvm/include/x86/processor.h @@ -34,6 +34,8 @@ extern uint64_t guest_tsc_khz; #define NMI_VECTOR 0x02 +const char *ex_str(int vector); + #define X86_EFLAGS_FIXED (1u << 1) #define X86_CR4_VME (1ul << 0) @@ -265,7 +267,7 @@ struct kvm_x86_cpu_property { #define X86_PROPERTY_PMU_NR_GP_COUNTERS KVM_X86_CPU_PROPERTY(0xa, 0, EAX, 8, 15) #define X86_PROPERTY_PMU_GP_COUNTERS_BIT_WIDTH KVM_X86_CPU_PROPERTY(0xa, 0, EAX, 16, 23) #define X86_PROPERTY_PMU_EBX_BIT_VECTOR_LENGTH KVM_X86_CPU_PROPERTY(0xa, 0, EAX, 24, 31) -#define X86_PROPERTY_PMU_EVENTS_MASK KVM_X86_CPU_PROPERTY(0xa, 0, EBX, 0, 7) +#define X86_PROPERTY_PMU_EVENTS_MASK KVM_X86_CPU_PROPERTY(0xa, 0, EBX, 0, 12) #define X86_PROPERTY_PMU_FIXED_COUNTERS_BITMASK KVM_X86_CPU_PROPERTY(0xa, 0, ECX, 0, 31) #define X86_PROPERTY_PMU_NR_FIXED_COUNTERS KVM_X86_CPU_PROPERTY(0xa, 0, EDX, 0, 4) #define X86_PROPERTY_PMU_FIXED_COUNTERS_BIT_WIDTH KVM_X86_CPU_PROPERTY(0xa, 0, EDX, 5, 12) @@ -332,6 +334,11 @@ struct kvm_x86_pmu_feature { #define X86_PMU_FEATURE_BRANCH_INSNS_RETIRED KVM_X86_PMU_FEATURE(EBX, 5) #define X86_PMU_FEATURE_BRANCHES_MISPREDICTED KVM_X86_PMU_FEATURE(EBX, 6) #define X86_PMU_FEATURE_TOPDOWN_SLOTS KVM_X86_PMU_FEATURE(EBX, 7) +#define X86_PMU_FEATURE_TOPDOWN_BE_BOUND KVM_X86_PMU_FEATURE(EBX, 8) +#define X86_PMU_FEATURE_TOPDOWN_BAD_SPEC KVM_X86_PMU_FEATURE(EBX, 9) +#define X86_PMU_FEATURE_TOPDOWN_FE_BOUND KVM_X86_PMU_FEATURE(EBX, 10) +#define X86_PMU_FEATURE_TOPDOWN_RETIRING KVM_X86_PMU_FEATURE(EBX, 11) +#define X86_PMU_FEATURE_LBR_INSERTS KVM_X86_PMU_FEATURE(EBX, 12) #define X86_PMU_FEATURE_INSNS_RETIRED_FIXED KVM_X86_PMU_FEATURE(ECX, 0) #define X86_PMU_FEATURE_CPU_CYCLES_FIXED KVM_X86_PMU_FEATURE(ECX, 1) @@ -1179,6 +1186,12 @@ struct idt_entry { void vm_install_exception_handler(struct kvm_vm *vm, int vector, void (*handler)(struct ex_regs *)); +/* + * Exception fixup morphs #DE to an arbitrary magic vector so that '0' can be + * used to signal "no expcetion". + */ +#define KVM_MAGIC_DE_VECTOR 0xff + /* If a toddler were to say "abracadabra". */ #define KVM_EXCEPTION_MAGIC 0xabacadabaULL @@ -1314,6 +1327,26 @@ static inline uint8_t xsetbv_safe(uint32_t index, uint64_t value) bool kvm_is_tdp_enabled(void); +static inline bool get_kvm_intel_param_bool(const char *param) +{ + return kvm_get_module_param_bool("kvm_intel", param); +} + +static inline bool get_kvm_amd_param_bool(const char *param) +{ + return kvm_get_module_param_bool("kvm_amd", param); +} + +static inline int get_kvm_intel_param_integer(const char *param) +{ + return kvm_get_module_param_integer("kvm_intel", param); +} + +static inline int get_kvm_amd_param_integer(const char *param) +{ + return kvm_get_module_param_integer("kvm_amd", param); +} + static inline bool kvm_is_pmu_enabled(void) { return get_kvm_param_bool("enable_pmu"); @@ -1329,6 +1362,11 @@ static inline bool kvm_is_unrestricted_guest_enabled(void) return get_kvm_intel_param_bool("unrestricted_guest"); } +static inline bool kvm_is_ignore_msrs(void) +{ + return get_kvm_param_bool("ignore_msrs"); +} + uint64_t *__vm_get_page_table_entry(struct kvm_vm *vm, uint64_t vaddr, int *level); uint64_t *vm_get_page_table_entry(struct kvm_vm *vm, uint64_t vaddr); diff --git a/tools/testing/selftests/kvm/lib/arm64/processor.c b/tools/testing/selftests/kvm/lib/arm64/processor.c index eb115123d741..369a4c87dd8f 100644 --- a/tools/testing/selftests/kvm/lib/arm64/processor.c +++ b/tools/testing/selftests/kvm/lib/arm64/processor.c @@ -12,6 +12,7 @@ #include "kvm_util.h" #include "processor.h" #include "ucall_common.h" +#include "vgic.h" #include <linux/bitfield.h> #include <linux/sizes.h> @@ -185,7 +186,7 @@ void virt_arch_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr) _virt_pg_map(vm, vaddr, paddr, attr_idx); } -uint64_t *virt_get_pte_hva(struct kvm_vm *vm, vm_vaddr_t gva) +uint64_t *virt_get_pte_hva_at_level(struct kvm_vm *vm, vm_vaddr_t gva, int level) { uint64_t *ptep; @@ -195,17 +196,23 @@ uint64_t *virt_get_pte_hva(struct kvm_vm *vm, vm_vaddr_t gva) ptep = addr_gpa2hva(vm, vm->pgd) + pgd_index(vm, gva) * 8; if (!ptep) goto unmapped_gva; + if (level == 0) + return ptep; switch (vm->pgtable_levels) { case 4: ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) + pud_index(vm, gva) * 8; if (!ptep) goto unmapped_gva; + if (level == 1) + break; /* fall through */ case 3: ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) + pmd_index(vm, gva) * 8; if (!ptep) goto unmapped_gva; + if (level == 2) + break; /* fall through */ case 2: ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) + pte_index(vm, gva) * 8; @@ -223,6 +230,11 @@ unmapped_gva: exit(EXIT_FAILURE); } +uint64_t *virt_get_pte_hva(struct kvm_vm *vm, vm_vaddr_t gva) +{ + return virt_get_pte_hva_at_level(vm, gva, 3); +} + vm_paddr_t addr_arch_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva) { uint64_t *ptep = virt_get_pte_hva(vm, gva); @@ -266,31 +278,49 @@ void virt_arch_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) } } +bool vm_supports_el2(struct kvm_vm *vm) +{ + const char *value = getenv("NV"); + + if (value && *value == '0') + return false; + + return vm_check_cap(vm, KVM_CAP_ARM_EL2) && vm->arch.has_gic; +} + +void kvm_get_default_vcpu_target(struct kvm_vm *vm, struct kvm_vcpu_init *init) +{ + struct kvm_vcpu_init preferred = {}; + + vm_ioctl(vm, KVM_ARM_PREFERRED_TARGET, &preferred); + if (vm_supports_el2(vm)) + preferred.features[0] |= BIT(KVM_ARM_VCPU_HAS_EL2); + + *init = preferred; +} + void aarch64_vcpu_setup(struct kvm_vcpu *vcpu, struct kvm_vcpu_init *init) { struct kvm_vcpu_init default_init = { .target = -1, }; struct kvm_vm *vm = vcpu->vm; uint64_t sctlr_el1, tcr_el1, ttbr0_el1; - if (!init) + if (!init) { + kvm_get_default_vcpu_target(vm, &default_init); init = &default_init; - - if (init->target == -1) { - struct kvm_vcpu_init preferred; - vm_ioctl(vm, KVM_ARM_PREFERRED_TARGET, &preferred); - init->target = preferred.target; } vcpu_ioctl(vcpu, KVM_ARM_VCPU_INIT, init); + vcpu->init = *init; /* * Enable FP/ASIMD to avoid trapping when accessing Q0-Q15 * registers, which the variable argument list macros do. */ - vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(SYS_CPACR_EL1), 3 << 20); + vcpu_set_reg(vcpu, ctxt_reg_alias(vcpu, SYS_CPACR_EL1), 3 << 20); - sctlr_el1 = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_SCTLR_EL1)); - tcr_el1 = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_TCR_EL1)); + sctlr_el1 = vcpu_get_reg(vcpu, ctxt_reg_alias(vcpu, SYS_SCTLR_EL1)); + tcr_el1 = vcpu_get_reg(vcpu, ctxt_reg_alias(vcpu, SYS_TCR_EL1)); /* Configure base granule size */ switch (vm->mode) { @@ -357,11 +387,17 @@ void aarch64_vcpu_setup(struct kvm_vcpu *vcpu, struct kvm_vcpu_init *init) if (use_lpa2_pte_format(vm)) tcr_el1 |= TCR_DS; - vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(SYS_SCTLR_EL1), sctlr_el1); - vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(SYS_TCR_EL1), tcr_el1); - vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(SYS_MAIR_EL1), DEFAULT_MAIR_EL1); - vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(SYS_TTBR0_EL1), ttbr0_el1); + vcpu_set_reg(vcpu, ctxt_reg_alias(vcpu, SYS_SCTLR_EL1), sctlr_el1); + vcpu_set_reg(vcpu, ctxt_reg_alias(vcpu, SYS_TCR_EL1), tcr_el1); + vcpu_set_reg(vcpu, ctxt_reg_alias(vcpu, SYS_MAIR_EL1), DEFAULT_MAIR_EL1); + vcpu_set_reg(vcpu, ctxt_reg_alias(vcpu, SYS_TTBR0_EL1), ttbr0_el1); vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(SYS_TPIDR_EL1), vcpu->id); + + if (!vcpu_has_el2(vcpu)) + return; + + vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(SYS_HCR_EL2), + HCR_EL2_RW | HCR_EL2_TGE | HCR_EL2_E2H); } void vcpu_arch_dump(FILE *stream, struct kvm_vcpu *vcpu, uint8_t indent) @@ -395,7 +431,7 @@ static struct kvm_vcpu *__aarch64_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id, aarch64_vcpu_setup(vcpu, init); - vcpu_set_reg(vcpu, ARM64_CORE_REG(sp_el1), stack_vaddr + stack_size); + vcpu_set_reg(vcpu, ctxt_reg_alias(vcpu, SYS_SP_EL1), stack_vaddr + stack_size); return vcpu; } @@ -465,7 +501,7 @@ void vcpu_init_descriptor_tables(struct kvm_vcpu *vcpu) { extern char vectors; - vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(SYS_VBAR_EL1), (uint64_t)&vectors); + vcpu_set_reg(vcpu, ctxt_reg_alias(vcpu, SYS_VBAR_EL1), (uint64_t)&vectors); } void route_exception(struct ex_regs *regs, int vector) @@ -653,3 +689,39 @@ void wfi(void) { asm volatile("wfi"); } + +static bool request_mte; +static bool request_vgic = true; + +void test_wants_mte(void) +{ + request_mte = true; +} + +void test_disable_default_vgic(void) +{ + request_vgic = false; +} + +void kvm_arch_vm_post_create(struct kvm_vm *vm, unsigned int nr_vcpus) +{ + if (request_mte && vm_check_cap(vm, KVM_CAP_ARM_MTE)) + vm_enable_cap(vm, KVM_CAP_ARM_MTE, 0); + + if (request_vgic && kvm_supports_vgic_v3()) { + vm->arch.gic_fd = __vgic_v3_setup(vm, nr_vcpus, 64); + vm->arch.has_gic = true; + } +} + +void kvm_arch_vm_finalize_vcpus(struct kvm_vm *vm) +{ + if (vm->arch.has_gic) + __vgic_v3_init(vm->arch.gic_fd); +} + +void kvm_arch_vm_release(struct kvm_vm *vm) +{ + if (vm->arch.has_gic) + close(vm->arch.gic_fd); +} diff --git a/tools/testing/selftests/kvm/lib/arm64/vgic.c b/tools/testing/selftests/kvm/lib/arm64/vgic.c index 4427f43f73ea..d0f7bd0984b8 100644 --- a/tools/testing/selftests/kvm/lib/arm64/vgic.c +++ b/tools/testing/selftests/kvm/lib/arm64/vgic.c @@ -15,6 +15,17 @@ #include "gic.h" #include "gic_v3.h" +bool kvm_supports_vgic_v3(void) +{ + struct kvm_vm *vm = vm_create_barebones(); + int r; + + r = __kvm_test_create_device(vm, KVM_DEV_TYPE_ARM_VGIC_V3); + kvm_vm_free(vm); + + return !r; +} + /* * vGIC-v3 default host setup * @@ -30,24 +41,11 @@ * redistributor regions of the guest. Since it depends on the number of * vCPUs for the VM, it must be called after all the vCPUs have been created. */ -int vgic_v3_setup(struct kvm_vm *vm, unsigned int nr_vcpus, uint32_t nr_irqs) +int __vgic_v3_setup(struct kvm_vm *vm, unsigned int nr_vcpus, uint32_t nr_irqs) { int gic_fd; uint64_t attr; - struct list_head *iter; - unsigned int nr_gic_pages, nr_vcpus_created = 0; - - TEST_ASSERT(nr_vcpus, "Number of vCPUs cannot be empty"); - - /* - * Make sure that the caller is infact calling this - * function after all the vCPUs are added. - */ - list_for_each(iter, &vm->vcpus) - nr_vcpus_created++; - TEST_ASSERT(nr_vcpus == nr_vcpus_created, - "Number of vCPUs requested (%u) doesn't match with the ones created for the VM (%u)", - nr_vcpus, nr_vcpus_created); + unsigned int nr_gic_pages; /* Distributor setup */ gic_fd = __kvm_create_device(vm, KVM_DEV_TYPE_ARM_VGIC_V3); @@ -56,9 +54,6 @@ int vgic_v3_setup(struct kvm_vm *vm, unsigned int nr_vcpus, uint32_t nr_irqs) kvm_device_attr_set(gic_fd, KVM_DEV_ARM_VGIC_GRP_NR_IRQS, 0, &nr_irqs); - kvm_device_attr_set(gic_fd, KVM_DEV_ARM_VGIC_GRP_CTRL, - KVM_DEV_ARM_VGIC_CTRL_INIT, NULL); - attr = GICD_BASE_GPA; kvm_device_attr_set(gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, KVM_VGIC_V3_ADDR_TYPE_DIST, &attr); @@ -73,10 +68,39 @@ int vgic_v3_setup(struct kvm_vm *vm, unsigned int nr_vcpus, uint32_t nr_irqs) KVM_VGIC_V3_REDIST_SIZE * nr_vcpus); virt_map(vm, GICR_BASE_GPA, GICR_BASE_GPA, nr_gic_pages); - kvm_device_attr_set(gic_fd, KVM_DEV_ARM_VGIC_GRP_CTRL, + return gic_fd; +} + +void __vgic_v3_init(int fd) +{ + kvm_device_attr_set(fd, KVM_DEV_ARM_VGIC_GRP_CTRL, KVM_DEV_ARM_VGIC_CTRL_INIT, NULL); +} - return gic_fd; +int vgic_v3_setup(struct kvm_vm *vm, unsigned int nr_vcpus, uint32_t nr_irqs) +{ + unsigned int nr_vcpus_created = 0; + struct list_head *iter; + int fd; + + TEST_ASSERT(nr_vcpus, "Number of vCPUs cannot be empty"); + + /* + * Make sure that the caller is infact calling this + * function after all the vCPUs are added. + */ + list_for_each(iter, &vm->vcpus) + nr_vcpus_created++; + TEST_ASSERT(nr_vcpus == nr_vcpus_created, + "Number of vCPUs requested (%u) doesn't match with the ones created for the VM (%u)", + nr_vcpus, nr_vcpus_created); + + fd = __vgic_v3_setup(vm, nr_vcpus, nr_irqs); + if (fd < 0) + return fd; + + __vgic_v3_init(fd); + return fd; } /* should only work for level sensitive interrupts */ diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index c3f5142b0a54..6743fbd9bd67 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -24,7 +24,7 @@ uint32_t guest_random_seed; struct guest_random_state guest_rng; static uint32_t last_guest_seed; -static int vcpu_mmap_sz(void); +static size_t vcpu_mmap_sz(void); int __open_path_or_exit(const char *path, int flags, const char *enoent_help) { @@ -95,7 +95,7 @@ static ssize_t get_module_param(const char *module_name, const char *param, return bytes_read; } -static int get_module_param_integer(const char *module_name, const char *param) +int kvm_get_module_param_integer(const char *module_name, const char *param) { /* * 16 bytes to hold a 64-bit value (1 byte per char), 1 byte for the @@ -119,7 +119,7 @@ static int get_module_param_integer(const char *module_name, const char *param) return atoi_paranoid(value); } -static bool get_module_param_bool(const char *module_name, const char *param) +bool kvm_get_module_param_bool(const char *module_name, const char *param) { char value; ssize_t r; @@ -135,36 +135,6 @@ static bool get_module_param_bool(const char *module_name, const char *param) TEST_FAIL("Unrecognized value '%c' for boolean module param", value); } -bool get_kvm_param_bool(const char *param) -{ - return get_module_param_bool("kvm", param); -} - -bool get_kvm_intel_param_bool(const char *param) -{ - return get_module_param_bool("kvm_intel", param); -} - -bool get_kvm_amd_param_bool(const char *param) -{ - return get_module_param_bool("kvm_amd", param); -} - -int get_kvm_param_integer(const char *param) -{ - return get_module_param_integer("kvm", param); -} - -int get_kvm_intel_param_integer(const char *param) -{ - return get_module_param_integer("kvm_intel", param); -} - -int get_kvm_amd_param_integer(const char *param) -{ - return get_module_param_integer("kvm_amd", param); -} - /* * Capability * @@ -517,7 +487,7 @@ struct kvm_vm *__vm_create(struct vm_shape shape, uint32_t nr_runnable_vcpus, guest_rng = new_guest_random_state(guest_random_seed); sync_global_to_guest(vm, guest_rng); - kvm_arch_vm_post_create(vm); + kvm_arch_vm_post_create(vm, nr_runnable_vcpus); return vm; } @@ -555,6 +525,7 @@ struct kvm_vm *__vm_create_with_vcpus(struct vm_shape shape, uint32_t nr_vcpus, for (i = 0; i < nr_vcpus; ++i) vcpus[i] = vm_vcpu_add(vm, i, guest_code); + kvm_arch_vm_finalize_vcpus(vm); return vm; } @@ -805,6 +776,8 @@ void kvm_vm_release(struct kvm_vm *vmp) /* Free cached stats metadata and close FD */ kvm_stats_release(&vmp->stats); + + kvm_arch_vm_release(vmp); } static void __vm_mem_region_delete(struct kvm_vm *vm, @@ -1321,14 +1294,14 @@ void vm_guest_mem_fallocate(struct kvm_vm *vm, uint64_t base, uint64_t size, } /* Returns the size of a vCPU's kvm_run structure. */ -static int vcpu_mmap_sz(void) +static size_t vcpu_mmap_sz(void) { int dev_fd, ret; dev_fd = open_kvm_dev_path_or_exit(); ret = ioctl(dev_fd, KVM_GET_VCPU_MMAP_SIZE, NULL); - TEST_ASSERT(ret >= sizeof(struct kvm_run), + TEST_ASSERT(ret >= 0 && ret >= sizeof(struct kvm_run), KVM_IOCTL_ERROR(KVM_GET_VCPU_MMAP_SIZE, ret)); close(dev_fd); @@ -1369,7 +1342,7 @@ struct kvm_vcpu *__vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id) TEST_ASSERT_VM_VCPU_IOCTL(vcpu->fd >= 0, KVM_CREATE_VCPU, vcpu->fd, vm); TEST_ASSERT(vcpu_mmap_sz() >= sizeof(*vcpu->run), "vcpu mmap size " - "smaller than expected, vcpu_mmap_sz: %i expected_min: %zi", + "smaller than expected, vcpu_mmap_sz: %zi expected_min: %zi", vcpu_mmap_sz(), sizeof(*vcpu->run)); vcpu->run = (struct kvm_run *) mmap(NULL, vcpu_mmap_sz(), PROT_READ | PROT_WRITE, MAP_SHARED, vcpu->fd, 0); @@ -2330,7 +2303,15 @@ void kvm_get_stat(struct kvm_binary_stats *stats, const char *name, TEST_FAIL("Unable to find stat '%s'", name); } -__weak void kvm_arch_vm_post_create(struct kvm_vm *vm) +__weak void kvm_arch_vm_post_create(struct kvm_vm *vm, unsigned int nr_vcpus) +{ +} + +__weak void kvm_arch_vm_finalize_vcpus(struct kvm_vm *vm) +{ +} + +__weak void kvm_arch_vm_release(struct kvm_vm *vm) { } diff --git a/tools/testing/selftests/kvm/lib/x86/pmu.c b/tools/testing/selftests/kvm/lib/x86/pmu.c index f31f0427c17c..34cb57d1d671 100644 --- a/tools/testing/selftests/kvm/lib/x86/pmu.c +++ b/tools/testing/selftests/kvm/lib/x86/pmu.c @@ -8,6 +8,7 @@ #include <linux/kernel.h> #include "kvm_util.h" +#include "processor.h" #include "pmu.h" const uint64_t intel_pmu_arch_events[] = { @@ -19,6 +20,11 @@ const uint64_t intel_pmu_arch_events[] = { INTEL_ARCH_BRANCHES_RETIRED, INTEL_ARCH_BRANCHES_MISPREDICTED, INTEL_ARCH_TOPDOWN_SLOTS, + INTEL_ARCH_TOPDOWN_BE_BOUND, + INTEL_ARCH_TOPDOWN_BAD_SPEC, + INTEL_ARCH_TOPDOWN_FE_BOUND, + INTEL_ARCH_TOPDOWN_RETIRING, + INTEL_ARCH_LBR_INSERTS, }; kvm_static_assert(ARRAY_SIZE(intel_pmu_arch_events) == NR_INTEL_ARCH_EVENTS); @@ -29,3 +35,46 @@ const uint64_t amd_pmu_zen_events[] = { AMD_ZEN_BRANCHES_MISPREDICTED, }; kvm_static_assert(ARRAY_SIZE(amd_pmu_zen_events) == NR_AMD_ZEN_EVENTS); + +/* + * For Intel Atom CPUs, the PMU events "Instruction Retired" or + * "Branch Instruction Retired" may be overcounted for some certain + * instructions, like FAR CALL/JMP, RETF, IRET, VMENTRY/VMEXIT/VMPTRLD + * and complex SGX/SMX/CSTATE instructions/flows. + * + * The detailed information can be found in the errata (section SRF7): + * https://edc.intel.com/content/www/us/en/design/products-and-solutions/processors-and-chipsets/sierra-forest/xeon-6700-series-processor-with-e-cores-specification-update/errata-details/ + * + * For the Atom platforms before Sierra Forest (including Sierra Forest), + * Both 2 events "Instruction Retired" and "Branch Instruction Retired" would + * be overcounted on these certain instructions, but for Clearwater Forest + * only "Instruction Retired" event is overcounted on these instructions. + */ +static uint64_t get_pmu_errata(void) +{ + if (!this_cpu_is_intel()) + return 0; + + if (this_cpu_family() != 0x6) + return 0; + + switch (this_cpu_model()) { + case 0xDD: /* Clearwater Forest */ + return BIT_ULL(INSTRUCTIONS_RETIRED_OVERCOUNT); + case 0xAF: /* Sierra Forest */ + case 0x4D: /* Avaton, Rangely */ + case 0x5F: /* Denverton */ + case 0x86: /* Jacobsville */ + return BIT_ULL(INSTRUCTIONS_RETIRED_OVERCOUNT) | + BIT_ULL(BRANCHES_RETIRED_OVERCOUNT); + default: + return 0; + } +} + +uint64_t pmu_errata_mask; + +void kvm_init_pmu_errata(void) +{ + pmu_errata_mask = get_pmu_errata(); +} diff --git a/tools/testing/selftests/kvm/lib/x86/processor.c b/tools/testing/selftests/kvm/lib/x86/processor.c index d4c19ac885a9..c748cd9b2eef 100644 --- a/tools/testing/selftests/kvm/lib/x86/processor.c +++ b/tools/testing/selftests/kvm/lib/x86/processor.c @@ -6,6 +6,7 @@ #include "linux/bitmap.h" #include "test_util.h" #include "kvm_util.h" +#include "pmu.h" #include "processor.h" #include "sev.h" @@ -23,6 +24,39 @@ bool host_cpu_is_intel; bool is_forced_emulation_enabled; uint64_t guest_tsc_khz; +const char *ex_str(int vector) +{ + switch (vector) { +#define VEC_STR(v) case v##_VECTOR: return "#" #v + case DE_VECTOR: return "no exception"; + case KVM_MAGIC_DE_VECTOR: return "#DE"; + VEC_STR(DB); + VEC_STR(NMI); + VEC_STR(BP); + VEC_STR(OF); + VEC_STR(BR); + VEC_STR(UD); + VEC_STR(NM); + VEC_STR(DF); + VEC_STR(TS); + VEC_STR(NP); + VEC_STR(SS); + VEC_STR(GP); + VEC_STR(PF); + VEC_STR(MF); + VEC_STR(AC); + VEC_STR(MC); + VEC_STR(XM); + VEC_STR(VE); + VEC_STR(CP); + VEC_STR(HV); + VEC_STR(VC); + VEC_STR(SX); + default: return "#??"; +#undef VEC_STR + } +} + static void regs_dump(FILE *stream, struct kvm_regs *regs, uint8_t indent) { fprintf(stream, "%*srax: 0x%.16llx rbx: 0x%.16llx " @@ -557,7 +591,7 @@ static bool kvm_fixup_exception(struct ex_regs *regs) return false; if (regs->vector == DE_VECTOR) - return false; + regs->vector = KVM_MAGIC_DE_VECTOR; regs->rip = regs->r11; regs->r9 = regs->vector; @@ -625,7 +659,7 @@ void assert_on_unhandled_exception(struct kvm_vcpu *vcpu) REPORT_GUEST_ASSERT(uc); } -void kvm_arch_vm_post_create(struct kvm_vm *vm) +void kvm_arch_vm_post_create(struct kvm_vm *vm, unsigned int nr_vcpus) { int r; @@ -638,6 +672,7 @@ void kvm_arch_vm_post_create(struct kvm_vm *vm) sync_global_to_guest(vm, host_cpu_is_intel); sync_global_to_guest(vm, host_cpu_is_amd); sync_global_to_guest(vm, is_forced_emulation_enabled); + sync_global_to_guest(vm, pmu_errata_mask); if (is_sev_vm(vm)) { struct kvm_sev_init init = { 0 }; @@ -1269,6 +1304,8 @@ void kvm_selftest_arch_init(void) host_cpu_is_intel = this_cpu_is_intel(); host_cpu_is_amd = this_cpu_is_amd(); is_forced_emulation_enabled = kvm_is_forced_emulation_enabled(); + + kvm_init_pmu_errata(); } bool sys_clocksource_is_based_on_tsc(void) diff --git a/tools/testing/selftests/kvm/memslot_modification_stress_test.c b/tools/testing/selftests/kvm/memslot_modification_stress_test.c index c81a84990eab..3cdfa3b19b85 100644 --- a/tools/testing/selftests/kvm/memslot_modification_stress_test.c +++ b/tools/testing/selftests/kvm/memslot_modification_stress_test.c @@ -22,6 +22,7 @@ #include "processor.h" #include "test_util.h" #include "guest_modes.h" +#include "ucall_common.h" #define DUMMY_MEMSLOT_INDEX 7 diff --git a/tools/testing/selftests/kvm/memslot_perf_test.c b/tools/testing/selftests/kvm/memslot_perf_test.c index e3711beff7f3..5087d082c4b0 100644 --- a/tools/testing/selftests/kvm/memslot_perf_test.c +++ b/tools/testing/selftests/kvm/memslot_perf_test.c @@ -25,6 +25,7 @@ #include <test_util.h> #include <kvm_util.h> #include <processor.h> +#include <ucall_common.h> #define MEM_EXTRA_SIZE SZ_64K diff --git a/tools/testing/selftests/kvm/riscv/get-reg-list.c b/tools/testing/selftests/kvm/riscv/get-reg-list.c index a0b7dabb5040..705ab3d7778b 100644 --- a/tools/testing/selftests/kvm/riscv/get-reg-list.c +++ b/tools/testing/selftests/kvm/riscv/get-reg-list.c @@ -80,9 +80,11 @@ bool filter_reg(__u64 reg) case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZCF: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZCMOP: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZFA: + case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZFBFMIN: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZFH: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZFHMIN: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICBOM: + case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICBOP: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICBOZ: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICCRSE: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICNTR: @@ -103,6 +105,8 @@ bool filter_reg(__u64 reg) case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZTSO: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVBB: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVBC: + case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVFBFMIN: + case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVFBFWMA: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVFH: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVFHMIN: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVKB: @@ -128,6 +132,7 @@ bool filter_reg(__u64 reg) case KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_DBCN: case KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_SUSP: case KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_STA: + case KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_FWFT: case KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_EXPERIMENTAL: case KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_VENDOR: return true; @@ -255,6 +260,8 @@ static const char *config_id_to_str(const char *prefix, __u64 id) return "KVM_REG_RISCV_CONFIG_REG(zicbom_block_size)"; case KVM_REG_RISCV_CONFIG_REG(zicboz_block_size): return "KVM_REG_RISCV_CONFIG_REG(zicboz_block_size)"; + case KVM_REG_RISCV_CONFIG_REG(zicbop_block_size): + return "KVM_REG_RISCV_CONFIG_REG(zicbop_block_size)"; case KVM_REG_RISCV_CONFIG_REG(mvendorid): return "KVM_REG_RISCV_CONFIG_REG(mvendorid)"; case KVM_REG_RISCV_CONFIG_REG(marchid): @@ -532,9 +539,11 @@ static const char *isa_ext_single_id_to_str(__u64 reg_off) KVM_ISA_EXT_ARR(ZCF), KVM_ISA_EXT_ARR(ZCMOP), KVM_ISA_EXT_ARR(ZFA), + KVM_ISA_EXT_ARR(ZFBFMIN), KVM_ISA_EXT_ARR(ZFH), KVM_ISA_EXT_ARR(ZFHMIN), KVM_ISA_EXT_ARR(ZICBOM), + KVM_ISA_EXT_ARR(ZICBOP), KVM_ISA_EXT_ARR(ZICBOZ), KVM_ISA_EXT_ARR(ZICCRSE), KVM_ISA_EXT_ARR(ZICNTR), @@ -555,6 +564,8 @@ static const char *isa_ext_single_id_to_str(__u64 reg_off) KVM_ISA_EXT_ARR(ZTSO), KVM_ISA_EXT_ARR(ZVBB), KVM_ISA_EXT_ARR(ZVBC), + KVM_ISA_EXT_ARR(ZVFBFMIN), + KVM_ISA_EXT_ARR(ZVFBFWMA), KVM_ISA_EXT_ARR(ZVFH), KVM_ISA_EXT_ARR(ZVFHMIN), KVM_ISA_EXT_ARR(ZVKB), @@ -627,6 +638,7 @@ static const char *sbi_ext_single_id_to_str(__u64 reg_off) KVM_SBI_EXT_ARR(KVM_RISCV_SBI_EXT_DBCN), KVM_SBI_EXT_ARR(KVM_RISCV_SBI_EXT_SUSP), KVM_SBI_EXT_ARR(KVM_RISCV_SBI_EXT_STA), + KVM_SBI_EXT_ARR(KVM_RISCV_SBI_EXT_FWFT), KVM_SBI_EXT_ARR(KVM_RISCV_SBI_EXT_EXPERIMENTAL), KVM_SBI_EXT_ARR(KVM_RISCV_SBI_EXT_VENDOR), }; @@ -683,6 +695,19 @@ static const char *sbi_sta_id_to_str(__u64 reg_off) return strdup_printf("KVM_REG_RISCV_SBI_STA | %lld /* UNKNOWN */", reg_off); } +static const char *sbi_fwft_id_to_str(__u64 reg_off) +{ + switch (reg_off) { + case 0: return "KVM_REG_RISCV_SBI_FWFT | KVM_REG_RISCV_SBI_FWFT_REG(misaligned_deleg.enable)"; + case 1: return "KVM_REG_RISCV_SBI_FWFT | KVM_REG_RISCV_SBI_FWFT_REG(misaligned_deleg.flags)"; + case 2: return "KVM_REG_RISCV_SBI_FWFT | KVM_REG_RISCV_SBI_FWFT_REG(misaligned_deleg.value)"; + case 3: return "KVM_REG_RISCV_SBI_FWFT | KVM_REG_RISCV_SBI_FWFT_REG(pointer_masking.enable)"; + case 4: return "KVM_REG_RISCV_SBI_FWFT | KVM_REG_RISCV_SBI_FWFT_REG(pointer_masking.flags)"; + case 5: return "KVM_REG_RISCV_SBI_FWFT | KVM_REG_RISCV_SBI_FWFT_REG(pointer_masking.value)"; + } + return strdup_printf("KVM_REG_RISCV_SBI_FWFT | %lld /* UNKNOWN */", reg_off); +} + static const char *sbi_id_to_str(const char *prefix, __u64 id) { __u64 reg_off = id & ~(REG_MASK | KVM_REG_RISCV_SBI_STATE); @@ -695,6 +720,8 @@ static const char *sbi_id_to_str(const char *prefix, __u64 id) switch (reg_subtype) { case KVM_REG_RISCV_SBI_STA: return sbi_sta_id_to_str(reg_off); + case KVM_REG_RISCV_SBI_FWFT: + return sbi_fwft_id_to_str(reg_off); } return strdup_printf("%lld | %lld /* UNKNOWN */", reg_subtype, reg_off); @@ -780,10 +807,13 @@ void print_reg(const char *prefix, __u64 id) */ static __u64 base_regs[] = { KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CONFIG | KVM_REG_RISCV_CONFIG_REG(isa), + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CONFIG | KVM_REG_RISCV_CONFIG_REG(zicbom_block_size), KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CONFIG | KVM_REG_RISCV_CONFIG_REG(mvendorid), KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CONFIG | KVM_REG_RISCV_CONFIG_REG(marchid), KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CONFIG | KVM_REG_RISCV_CONFIG_REG(mimpid), + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CONFIG | KVM_REG_RISCV_CONFIG_REG(zicboz_block_size), KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CONFIG | KVM_REG_RISCV_CONFIG_REG(satp_mode), + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CONFIG | KVM_REG_RISCV_CONFIG_REG(zicbop_block_size), KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CORE | KVM_REG_RISCV_CORE_REG(regs.pc), KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CORE | KVM_REG_RISCV_CORE_REG(regs.ra), KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CORE | KVM_REG_RISCV_CORE_REG(regs.sp), @@ -859,11 +889,26 @@ static __u64 sbi_sta_regs[] = { KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_STATE | KVM_REG_RISCV_SBI_STA | KVM_REG_RISCV_SBI_STA_REG(shmem_hi), }; +static __u64 sbi_fwft_regs[] = { + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_FWFT, + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_STATE | KVM_REG_RISCV_SBI_FWFT | KVM_REG_RISCV_SBI_FWFT_REG(misaligned_deleg.enable), + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_STATE | KVM_REG_RISCV_SBI_FWFT | KVM_REG_RISCV_SBI_FWFT_REG(misaligned_deleg.flags), + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_STATE | KVM_REG_RISCV_SBI_FWFT | KVM_REG_RISCV_SBI_FWFT_REG(misaligned_deleg.value), + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_STATE | KVM_REG_RISCV_SBI_FWFT | KVM_REG_RISCV_SBI_FWFT_REG(pointer_masking.enable), + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_STATE | KVM_REG_RISCV_SBI_FWFT | KVM_REG_RISCV_SBI_FWFT_REG(pointer_masking.flags), + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_STATE | KVM_REG_RISCV_SBI_FWFT | KVM_REG_RISCV_SBI_FWFT_REG(pointer_masking.value), +}; + static __u64 zicbom_regs[] = { KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CONFIG | KVM_REG_RISCV_CONFIG_REG(zicbom_block_size), KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICBOM, }; +static __u64 zicbop_regs[] = { + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CONFIG | KVM_REG_RISCV_CONFIG_REG(zicbop_block_size), + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICBOP, +}; + static __u64 zicboz_regs[] = { KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CONFIG | KVM_REG_RISCV_CONFIG_REG(zicboz_block_size), KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICBOZ, @@ -1010,8 +1055,13 @@ static __u64 vector_regs[] = { #define SUBLIST_SBI_STA \ {"sbi-sta", .feature_type = VCPU_FEATURE_SBI_EXT, .feature = KVM_RISCV_SBI_EXT_STA, \ .regs = sbi_sta_regs, .regs_n = ARRAY_SIZE(sbi_sta_regs),} +#define SUBLIST_SBI_FWFT \ + {"sbi-fwft", .feature_type = VCPU_FEATURE_SBI_EXT, .feature = KVM_RISCV_SBI_EXT_FWFT, \ + .regs = sbi_fwft_regs, .regs_n = ARRAY_SIZE(sbi_fwft_regs),} #define SUBLIST_ZICBOM \ {"zicbom", .feature = KVM_RISCV_ISA_EXT_ZICBOM, .regs = zicbom_regs, .regs_n = ARRAY_SIZE(zicbom_regs),} +#define SUBLIST_ZICBOP \ + {"zicbop", .feature = KVM_RISCV_ISA_EXT_ZICBOP, .regs = zicbop_regs, .regs_n = ARRAY_SIZE(zicbop_regs),} #define SUBLIST_ZICBOZ \ {"zicboz", .feature = KVM_RISCV_ISA_EXT_ZICBOZ, .regs = zicboz_regs, .regs_n = ARRAY_SIZE(zicboz_regs),} #define SUBLIST_AIA \ @@ -1092,6 +1142,7 @@ KVM_SBI_EXT_SUBLIST_CONFIG(sta, STA); KVM_SBI_EXT_SIMPLE_CONFIG(pmu, PMU); KVM_SBI_EXT_SIMPLE_CONFIG(dbcn, DBCN); KVM_SBI_EXT_SIMPLE_CONFIG(susp, SUSP); +KVM_SBI_EXT_SUBLIST_CONFIG(fwft, FWFT); KVM_ISA_EXT_SUBLIST_CONFIG(aia, AIA); KVM_ISA_EXT_SUBLIST_CONFIG(fp_f, FP_F); @@ -1127,9 +1178,11 @@ KVM_ISA_EXT_SIMPLE_CONFIG(zcd, ZCD); KVM_ISA_EXT_SIMPLE_CONFIG(zcf, ZCF); KVM_ISA_EXT_SIMPLE_CONFIG(zcmop, ZCMOP); KVM_ISA_EXT_SIMPLE_CONFIG(zfa, ZFA); +KVM_ISA_EXT_SIMPLE_CONFIG(zfbfmin, ZFBFMIN); KVM_ISA_EXT_SIMPLE_CONFIG(zfh, ZFH); KVM_ISA_EXT_SIMPLE_CONFIG(zfhmin, ZFHMIN); KVM_ISA_EXT_SUBLIST_CONFIG(zicbom, ZICBOM); +KVM_ISA_EXT_SUBLIST_CONFIG(zicbop, ZICBOP); KVM_ISA_EXT_SUBLIST_CONFIG(zicboz, ZICBOZ); KVM_ISA_EXT_SIMPLE_CONFIG(ziccrse, ZICCRSE); KVM_ISA_EXT_SIMPLE_CONFIG(zicntr, ZICNTR); @@ -1150,6 +1203,8 @@ KVM_ISA_EXT_SIMPLE_CONFIG(zkt, ZKT); KVM_ISA_EXT_SIMPLE_CONFIG(ztso, ZTSO); KVM_ISA_EXT_SIMPLE_CONFIG(zvbb, ZVBB); KVM_ISA_EXT_SIMPLE_CONFIG(zvbc, ZVBC); +KVM_ISA_EXT_SIMPLE_CONFIG(zvfbfmin, ZVFBFMIN); +KVM_ISA_EXT_SIMPLE_CONFIG(zvfbfwma, ZVFBFWMA); KVM_ISA_EXT_SIMPLE_CONFIG(zvfh, ZVFH); KVM_ISA_EXT_SIMPLE_CONFIG(zvfhmin, ZVFHMIN); KVM_ISA_EXT_SIMPLE_CONFIG(zvkb, ZVKB); @@ -1167,6 +1222,7 @@ struct vcpu_reg_list *vcpu_configs[] = { &config_sbi_pmu, &config_sbi_dbcn, &config_sbi_susp, + &config_sbi_fwft, &config_aia, &config_fp_f, &config_fp_d, @@ -1201,9 +1257,11 @@ struct vcpu_reg_list *vcpu_configs[] = { &config_zcf, &config_zcmop, &config_zfa, + &config_zfbfmin, &config_zfh, &config_zfhmin, &config_zicbom, + &config_zicbop, &config_zicboz, &config_ziccrse, &config_zicntr, @@ -1224,6 +1282,8 @@ struct vcpu_reg_list *vcpu_configs[] = { &config_ztso, &config_zvbb, &config_zvbc, + &config_zvfbfmin, + &config_zvfbfwma, &config_zvfh, &config_zvfhmin, &config_zvkb, diff --git a/tools/testing/selftests/kvm/s390/cmma_test.c b/tools/testing/selftests/kvm/s390/cmma_test.c index 85cc8c18d6e7..e39a724fe860 100644 --- a/tools/testing/selftests/kvm/s390/cmma_test.c +++ b/tools/testing/selftests/kvm/s390/cmma_test.c @@ -145,7 +145,7 @@ static void finish_vm_setup(struct kvm_vm *vm) slot0 = memslot2region(vm, 0); ucall_init(vm, slot0->region.guest_phys_addr + slot0->region.memory_size); - kvm_arch_vm_post_create(vm); + kvm_arch_vm_post_create(vm, 0); } static struct kvm_vm *create_vm_two_memslots(void) diff --git a/tools/testing/selftests/kvm/s390/cpumodel_subfuncs_test.c b/tools/testing/selftests/kvm/s390/cpumodel_subfuncs_test.c index 27255880dabd..aded795d42be 100644 --- a/tools/testing/selftests/kvm/s390/cpumodel_subfuncs_test.c +++ b/tools/testing/selftests/kvm/s390/cpumodel_subfuncs_test.c @@ -291,7 +291,7 @@ int main(int argc, char *argv[]) ksft_test_result_pass("%s\n", testlist[idx].subfunc_name); free(array); } else { - ksft_test_result_skip("%s feature is not avaialable\n", + ksft_test_result_skip("%s feature is not available\n", testlist[idx].subfunc_name); } } diff --git a/tools/testing/selftests/kvm/steal_time.c b/tools/testing/selftests/kvm/steal_time.c index cce2520af720..8edc1fca345b 100644 --- a/tools/testing/selftests/kvm/steal_time.c +++ b/tools/testing/selftests/kvm/steal_time.c @@ -118,7 +118,7 @@ static int64_t smccc(uint32_t func, uint64_t arg) { struct arm_smccc_res res; - smccc_hvc(func, arg, 0, 0, 0, 0, 0, 0, &res); + do_smccc(func, arg, 0, 0, 0, 0, 0, 0, &res); return res.a0; } diff --git a/tools/testing/selftests/kvm/x86/fastops_test.c b/tools/testing/selftests/kvm/x86/fastops_test.c index 2ac89d6c1e46..8926cfe0e209 100644 --- a/tools/testing/selftests/kvm/x86/fastops_test.c +++ b/tools/testing/selftests/kvm/x86/fastops_test.c @@ -8,14 +8,21 @@ * to set RFLAGS.CF based on whether or not the input is even or odd, so that * instructions like ADC and SBB are deterministic. */ +#define fastop(__insn) \ + "bt $0, %[bt_val]\n\t" \ + __insn "\n\t" \ + "pushfq\n\t" \ + "pop %[flags]\n\t" + +#define flags_constraint(flags_val) [flags]"=r"(flags_val) +#define bt_constraint(__bt_val) [bt_val]"rm"((uint32_t)__bt_val) + #define guest_execute_fastop_1(FEP, insn, __val, __flags) \ ({ \ - __asm__ __volatile__("bt $0, %[val]\n\t" \ - FEP insn " %[val]\n\t" \ - "pushfq\n\t" \ - "pop %[flags]\n\t" \ - : [val]"+r"(__val), [flags]"=r"(__flags) \ - : : "cc", "memory"); \ + __asm__ __volatile__(fastop(FEP insn " %[val]") \ + : [val]"+r"(__val), flags_constraint(__flags) \ + : bt_constraint(__val) \ + : "cc", "memory"); \ }) #define guest_test_fastop_1(insn, type_t, __val) \ @@ -36,12 +43,10 @@ #define guest_execute_fastop_2(FEP, insn, __input, __output, __flags) \ ({ \ - __asm__ __volatile__("bt $0, %[output]\n\t" \ - FEP insn " %[input], %[output]\n\t" \ - "pushfq\n\t" \ - "pop %[flags]\n\t" \ - : [output]"+r"(__output), [flags]"=r"(__flags) \ - : [input]"r"(__input) : "cc", "memory"); \ + __asm__ __volatile__(fastop(FEP insn " %[input], %[output]") \ + : [output]"+r"(__output), flags_constraint(__flags) \ + : [input]"r"(__input), bt_constraint(__output) \ + : "cc", "memory"); \ }) #define guest_test_fastop_2(insn, type_t, __val1, __val2) \ @@ -63,12 +68,10 @@ #define guest_execute_fastop_cl(FEP, insn, __shift, __output, __flags) \ ({ \ - __asm__ __volatile__("bt $0, %[output]\n\t" \ - FEP insn " %%cl, %[output]\n\t" \ - "pushfq\n\t" \ - "pop %[flags]\n\t" \ - : [output]"+r"(__output), [flags]"=r"(__flags) \ - : "c"(__shift) : "cc", "memory"); \ + __asm__ __volatile__(fastop(FEP insn " %%cl, %[output]") \ + : [output]"+r"(__output), flags_constraint(__flags) \ + : "c"(__shift), bt_constraint(__output) \ + : "cc", "memory"); \ }) #define guest_test_fastop_cl(insn, type_t, __val1, __val2) \ @@ -89,6 +92,42 @@ ex_flags, insn, shift, (uint64_t)input, flags); \ }) +#define guest_execute_fastop_div(__KVM_ASM_SAFE, insn, __a, __d, __rm, __flags) \ +({ \ + uint64_t ign_error_code; \ + uint8_t vector; \ + \ + __asm__ __volatile__(fastop(__KVM_ASM_SAFE(insn " %[denom]")) \ + : "+a"(__a), "+d"(__d), flags_constraint(__flags), \ + KVM_ASM_SAFE_OUTPUTS(vector, ign_error_code) \ + : [denom]"rm"(__rm), bt_constraint(__rm) \ + : "cc", "memory", KVM_ASM_SAFE_CLOBBERS); \ + vector; \ +}) + +#define guest_test_fastop_div(insn, type_t, __val1, __val2) \ +({ \ + type_t _a = __val1, _d = __val1, rm = __val2; \ + type_t a = _a, d = _d, ex_a = _a, ex_d = _d; \ + uint64_t flags, ex_flags; \ + uint8_t v, ex_v; \ + \ + ex_v = guest_execute_fastop_div(KVM_ASM_SAFE, insn, ex_a, ex_d, rm, ex_flags); \ + v = guest_execute_fastop_div(KVM_ASM_SAFE_FEP, insn, a, d, rm, flags); \ + \ + GUEST_ASSERT_EQ(v, ex_v); \ + __GUEST_ASSERT(v == ex_v, \ + "Wanted vector 0x%x for '%s 0x%lx:0x%lx/0x%lx', got 0x%x", \ + ex_v, insn, (uint64_t)_a, (uint64_t)_d, (uint64_t)rm, v); \ + __GUEST_ASSERT(a == ex_a && d == ex_d, \ + "Wanted 0x%lx:0x%lx for '%s 0x%lx:0x%lx/0x%lx', got 0x%lx:0x%lx",\ + (uint64_t)ex_a, (uint64_t)ex_d, insn, (uint64_t)_a, \ + (uint64_t)_d, (uint64_t)rm, (uint64_t)a, (uint64_t)d); \ + __GUEST_ASSERT(v || ex_v || (flags == ex_flags), \ + "Wanted flags 0x%lx for '%s 0x%lx:0x%lx/0x%lx', got 0x%lx", \ + ex_flags, insn, (uint64_t)_a, (uint64_t)_d, (uint64_t)rm, flags);\ +}) + static const uint64_t vals[] = { 0, 1, @@ -115,14 +154,16 @@ do { \ guest_test_fastop_2("add" suffix, type_t, vals[i], vals[j]); \ guest_test_fastop_2("adc" suffix, type_t, vals[i], vals[j]); \ guest_test_fastop_2("and" suffix, type_t, vals[i], vals[j]); \ +if (sizeof(type_t) != 1) { \ guest_test_fastop_2("bsf" suffix, type_t, vals[i], vals[j]); \ guest_test_fastop_2("bsr" suffix, type_t, vals[i], vals[j]); \ guest_test_fastop_2("bt" suffix, type_t, vals[i], vals[j]); \ guest_test_fastop_2("btc" suffix, type_t, vals[i], vals[j]); \ guest_test_fastop_2("btr" suffix, type_t, vals[i], vals[j]); \ guest_test_fastop_2("bts" suffix, type_t, vals[i], vals[j]); \ - guest_test_fastop_2("cmp" suffix, type_t, vals[i], vals[j]); \ guest_test_fastop_2("imul" suffix, type_t, vals[i], vals[j]); \ +} \ + guest_test_fastop_2("cmp" suffix, type_t, vals[i], vals[j]); \ guest_test_fastop_2("or" suffix, type_t, vals[i], vals[j]); \ guest_test_fastop_2("sbb" suffix, type_t, vals[i], vals[j]); \ guest_test_fastop_2("sub" suffix, type_t, vals[i], vals[j]); \ @@ -136,12 +177,15 @@ do { \ guest_test_fastop_cl("sar" suffix, type_t, vals[i], vals[j]); \ guest_test_fastop_cl("shl" suffix, type_t, vals[i], vals[j]); \ guest_test_fastop_cl("shr" suffix, type_t, vals[i], vals[j]); \ + \ + guest_test_fastop_div("div" suffix, type_t, vals[i], vals[j]); \ } \ } \ } while (0) static void guest_code(void) { + guest_test_fastops(uint8_t, "b"); guest_test_fastops(uint16_t, "w"); guest_test_fastops(uint32_t, "l"); guest_test_fastops(uint64_t, "q"); diff --git a/tools/testing/selftests/kvm/x86/hyperv_cpuid.c b/tools/testing/selftests/kvm/x86/hyperv_cpuid.c index c863a689aa98..3c21af811d8f 100644 --- a/tools/testing/selftests/kvm/x86/hyperv_cpuid.c +++ b/tools/testing/selftests/kvm/x86/hyperv_cpuid.c @@ -45,7 +45,7 @@ static void test_hv_cpuid(struct kvm_vcpu *vcpu, bool evmcs_expected) TEST_ASSERT((entry->function >= 0x40000000) && (entry->function <= 0x40000082), - "function %x is our of supported range", + "function %x is out of supported range", entry->function); TEST_ASSERT(entry->index == 0, diff --git a/tools/testing/selftests/kvm/x86/hyperv_features.c b/tools/testing/selftests/kvm/x86/hyperv_features.c index 068e9c69710d..99d327084172 100644 --- a/tools/testing/selftests/kvm/x86/hyperv_features.c +++ b/tools/testing/selftests/kvm/x86/hyperv_features.c @@ -54,12 +54,12 @@ static void guest_msr(struct msr_data *msr) if (msr->fault_expected) __GUEST_ASSERT(vector == GP_VECTOR, - "Expected #GP on %sMSR(0x%x), got vector '0x%x'", - msr->write ? "WR" : "RD", msr->idx, vector); + "Expected #GP on %sMSR(0x%x), got %s", + msr->write ? "WR" : "RD", msr->idx, ex_str(vector)); else __GUEST_ASSERT(!vector, - "Expected success on %sMSR(0x%x), got vector '0x%x'", - msr->write ? "WR" : "RD", msr->idx, vector); + "Expected success on %sMSR(0x%x), got %s", + msr->write ? "WR" : "RD", msr->idx, ex_str(vector)); if (vector || is_write_only_msr(msr->idx)) goto done; @@ -102,12 +102,12 @@ static void guest_hcall(vm_vaddr_t pgs_gpa, struct hcall_data *hcall) vector = __hyperv_hypercall(hcall->control, input, output, &res); if (hcall->ud_expected) { __GUEST_ASSERT(vector == UD_VECTOR, - "Expected #UD for control '%lu', got vector '0x%x'", - hcall->control, vector); + "Expected #UD for control '%lu', got %s", + hcall->control, ex_str(vector)); } else { __GUEST_ASSERT(!vector, - "Expected no exception for control '%lu', got vector '0x%x'", - hcall->control, vector); + "Expected no exception for control '%lu', got %s", + hcall->control, ex_str(vector)); GUEST_ASSERT_EQ(res, hcall->expect); } diff --git a/tools/testing/selftests/kvm/x86/monitor_mwait_test.c b/tools/testing/selftests/kvm/x86/monitor_mwait_test.c index 0eb371c62ab8..e45c028d2a7e 100644 --- a/tools/testing/selftests/kvm/x86/monitor_mwait_test.c +++ b/tools/testing/selftests/kvm/x86/monitor_mwait_test.c @@ -30,12 +30,12 @@ do { \ \ if (fault_wanted) \ __GUEST_ASSERT((vector) == UD_VECTOR, \ - "Expected #UD on " insn " for testcase '0x%x', got '0x%x'", \ - testcase, vector); \ + "Expected #UD on " insn " for testcase '0x%x', got %s", \ + testcase, ex_str(vector)); \ else \ __GUEST_ASSERT(!(vector), \ - "Expected success on " insn " for testcase '0x%x', got '0x%x'", \ - testcase, vector); \ + "Expected success on " insn " for testcase '0x%x', got %s", \ + testcase, ex_str(vector)); \ } while (0) static void guest_monitor_wait(void *arg) diff --git a/tools/testing/selftests/kvm/x86/msrs_test.c b/tools/testing/selftests/kvm/x86/msrs_test.c new file mode 100644 index 000000000000..40d918aedce6 --- /dev/null +++ b/tools/testing/selftests/kvm/x86/msrs_test.c @@ -0,0 +1,489 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include <asm/msr-index.h> + +#include <stdint.h> + +#include "kvm_util.h" +#include "processor.h" + +/* Use HYPERVISOR for MSRs that are emulated unconditionally (as is HYPERVISOR). */ +#define X86_FEATURE_NONE X86_FEATURE_HYPERVISOR + +struct kvm_msr { + const struct kvm_x86_cpu_feature feature; + const struct kvm_x86_cpu_feature feature2; + const char *name; + const u64 reset_val; + const u64 write_val; + const u64 rsvd_val; + const u32 index; + const bool is_kvm_defined; +}; + +#define ____MSR_TEST(msr, str, val, rsvd, reset, feat, f2, is_kvm) \ +{ \ + .index = msr, \ + .name = str, \ + .write_val = val, \ + .rsvd_val = rsvd, \ + .reset_val = reset, \ + .feature = X86_FEATURE_ ##feat, \ + .feature2 = X86_FEATURE_ ##f2, \ + .is_kvm_defined = is_kvm, \ +} + +#define __MSR_TEST(msr, str, val, rsvd, reset, feat) \ + ____MSR_TEST(msr, str, val, rsvd, reset, feat, feat, false) + +#define MSR_TEST_NON_ZERO(msr, val, rsvd, reset, feat) \ + __MSR_TEST(msr, #msr, val, rsvd, reset, feat) + +#define MSR_TEST(msr, val, rsvd, feat) \ + __MSR_TEST(msr, #msr, val, rsvd, 0, feat) + +#define MSR_TEST2(msr, val, rsvd, feat, f2) \ + ____MSR_TEST(msr, #msr, val, rsvd, 0, feat, f2, false) + +/* + * Note, use a page aligned value for the canonical value so that the value + * is compatible with MSRs that use bits 11:0 for things other than addresses. + */ +static const u64 canonical_val = 0x123456789000ull; + +/* + * Arbitrary value with bits set in every byte, but not all bits set. This is + * also a non-canonical value, but that's coincidental (any 64-bit value with + * an alternating 0s/1s pattern will be non-canonical). + */ +static const u64 u64_val = 0xaaaa5555aaaa5555ull; + +#define MSR_TEST_CANONICAL(msr, feat) \ + __MSR_TEST(msr, #msr, canonical_val, NONCANONICAL, 0, feat) + +#define MSR_TEST_KVM(msr, val, rsvd, feat) \ + ____MSR_TEST(KVM_REG_ ##msr, #msr, val, rsvd, 0, feat, feat, true) + +/* + * The main struct must be scoped to a function due to the use of structures to + * define features. For the global structure, allocate enough space for the + * foreseeable future without getting too ridiculous, to minimize maintenance + * costs (bumping the array size every time an MSR is added is really annoying). + */ +static struct kvm_msr msrs[128]; +static int idx; + +static bool ignore_unsupported_msrs; + +static u64 fixup_rdmsr_val(u32 msr, u64 want) +{ + /* + * AMD CPUs drop bits 63:32 on some MSRs that Intel CPUs support. KVM + * is supposed to emulate that behavior based on guest vendor model + * (which is the same as the host vendor model for this test). + */ + if (!host_cpu_is_amd) + return want; + + switch (msr) { + case MSR_IA32_SYSENTER_ESP: + case MSR_IA32_SYSENTER_EIP: + case MSR_TSC_AUX: + return want & GENMASK_ULL(31, 0); + default: + return want; + } +} + +static void __rdmsr(u32 msr, u64 want) +{ + u64 val; + u8 vec; + + vec = rdmsr_safe(msr, &val); + __GUEST_ASSERT(!vec, "Unexpected %s on RDMSR(0x%x)", ex_str(vec), msr); + + __GUEST_ASSERT(val == want, "Wanted 0x%lx from RDMSR(0x%x), got 0x%lx", + want, msr, val); +} + +static void __wrmsr(u32 msr, u64 val) +{ + u8 vec; + + vec = wrmsr_safe(msr, val); + __GUEST_ASSERT(!vec, "Unexpected %s on WRMSR(0x%x, 0x%lx)", + ex_str(vec), msr, val); + __rdmsr(msr, fixup_rdmsr_val(msr, val)); +} + +static void guest_test_supported_msr(const struct kvm_msr *msr) +{ + __rdmsr(msr->index, msr->reset_val); + __wrmsr(msr->index, msr->write_val); + GUEST_SYNC(fixup_rdmsr_val(msr->index, msr->write_val)); + + __rdmsr(msr->index, msr->reset_val); +} + +static void guest_test_unsupported_msr(const struct kvm_msr *msr) +{ + u64 val; + u8 vec; + + /* + * KVM's ABI with respect to ignore_msrs is a mess and largely beyond + * repair, just skip the unsupported MSR tests. + */ + if (ignore_unsupported_msrs) + goto skip_wrmsr_gp; + + /* + * {S,U}_CET exist if IBT or SHSTK is supported, but with bits that are + * writable only if their associated feature is supported. Skip the + * RDMSR #GP test if the secondary feature is supported, but perform + * the WRMSR #GP test as the to-be-written value is tied to the primary + * feature. For all other MSRs, simply do nothing. + */ + if (this_cpu_has(msr->feature2)) { + if (msr->index != MSR_IA32_U_CET && + msr->index != MSR_IA32_S_CET) + goto skip_wrmsr_gp; + + goto skip_rdmsr_gp; + } + + vec = rdmsr_safe(msr->index, &val); + __GUEST_ASSERT(vec == GP_VECTOR, "Wanted #GP on RDMSR(0x%x), got %s", + msr->index, ex_str(vec)); + +skip_rdmsr_gp: + vec = wrmsr_safe(msr->index, msr->write_val); + __GUEST_ASSERT(vec == GP_VECTOR, "Wanted #GP on WRMSR(0x%x, 0x%lx), got %s", + msr->index, msr->write_val, ex_str(vec)); + +skip_wrmsr_gp: + GUEST_SYNC(0); +} + +void guest_test_reserved_val(const struct kvm_msr *msr) +{ + /* Skip reserved value checks as well, ignore_msrs is trully a mess. */ + if (ignore_unsupported_msrs) + return; + + /* + * If the CPU will truncate the written value (e.g. SYSENTER on AMD), + * expect success and a truncated value, not #GP. + */ + if (!this_cpu_has(msr->feature) || + msr->rsvd_val == fixup_rdmsr_val(msr->index, msr->rsvd_val)) { + u8 vec = wrmsr_safe(msr->index, msr->rsvd_val); + + __GUEST_ASSERT(vec == GP_VECTOR, + "Wanted #GP on WRMSR(0x%x, 0x%lx), got %s", + msr->index, msr->rsvd_val, ex_str(vec)); + } else { + __wrmsr(msr->index, msr->rsvd_val); + __wrmsr(msr->index, msr->reset_val); + } +} + +static void guest_main(void) +{ + for (;;) { + const struct kvm_msr *msr = &msrs[READ_ONCE(idx)]; + + if (this_cpu_has(msr->feature)) + guest_test_supported_msr(msr); + else + guest_test_unsupported_msr(msr); + + if (msr->rsvd_val) + guest_test_reserved_val(msr); + + GUEST_SYNC(msr->reset_val); + } +} + +static bool has_one_reg; +static bool use_one_reg; + +#define KVM_X86_MAX_NR_REGS 1 + +static bool vcpu_has_reg(struct kvm_vcpu *vcpu, u64 reg) +{ + struct { + struct kvm_reg_list list; + u64 regs[KVM_X86_MAX_NR_REGS]; + } regs = {}; + int r, i; + + /* + * If KVM_GET_REG_LIST succeeds with n=0, i.e. there are no supported + * regs, then the vCPU obviously doesn't support the reg. + */ + r = __vcpu_ioctl(vcpu, KVM_GET_REG_LIST, ®s.list); + if (!r) + return false; + + TEST_ASSERT_EQ(errno, E2BIG); + + /* + * KVM x86 is expected to support enumerating a relative small number + * of regs. The majority of registers supported by KVM_{G,S}ET_ONE_REG + * are enumerated via other ioctls, e.g. KVM_GET_MSR_INDEX_LIST. For + * simplicity, hardcode the maximum number of regs and manually update + * the test as necessary. + */ + TEST_ASSERT(regs.list.n <= KVM_X86_MAX_NR_REGS, + "KVM reports %llu regs, test expects at most %u regs, stale test?", + regs.list.n, KVM_X86_MAX_NR_REGS); + + vcpu_ioctl(vcpu, KVM_GET_REG_LIST, ®s.list); + for (i = 0; i < regs.list.n; i++) { + if (regs.regs[i] == reg) + return true; + } + + return false; +} + +static void host_test_kvm_reg(struct kvm_vcpu *vcpu) +{ + bool has_reg = vcpu_cpuid_has(vcpu, msrs[idx].feature); + u64 reset_val = msrs[idx].reset_val; + u64 write_val = msrs[idx].write_val; + u64 rsvd_val = msrs[idx].rsvd_val; + u32 reg = msrs[idx].index; + u64 val; + int r; + + if (!use_one_reg) + return; + + TEST_ASSERT_EQ(vcpu_has_reg(vcpu, KVM_X86_REG_KVM(reg)), has_reg); + + if (!has_reg) { + r = __vcpu_get_reg(vcpu, KVM_X86_REG_KVM(reg), &val); + TEST_ASSERT(r && errno == EINVAL, + "Expected failure on get_reg(0x%x)", reg); + rsvd_val = 0; + goto out; + } + + val = vcpu_get_reg(vcpu, KVM_X86_REG_KVM(reg)); + TEST_ASSERT(val == reset_val, "Wanted 0x%lx from get_reg(0x%x), got 0x%lx", + reset_val, reg, val); + + vcpu_set_reg(vcpu, KVM_X86_REG_KVM(reg), write_val); + val = vcpu_get_reg(vcpu, KVM_X86_REG_KVM(reg)); + TEST_ASSERT(val == write_val, "Wanted 0x%lx from get_reg(0x%x), got 0x%lx", + write_val, reg, val); + +out: + r = __vcpu_set_reg(vcpu, KVM_X86_REG_KVM(reg), rsvd_val); + TEST_ASSERT(r, "Expected failure on set_reg(0x%x, 0x%lx)", reg, rsvd_val); +} + +static void host_test_msr(struct kvm_vcpu *vcpu, u64 guest_val) +{ + u64 reset_val = msrs[idx].reset_val; + u32 msr = msrs[idx].index; + u64 val; + + if (!kvm_cpu_has(msrs[idx].feature)) + return; + + val = vcpu_get_msr(vcpu, msr); + TEST_ASSERT(val == guest_val, "Wanted 0x%lx from get_msr(0x%x), got 0x%lx", + guest_val, msr, val); + + if (use_one_reg) + vcpu_set_reg(vcpu, KVM_X86_REG_MSR(msr), reset_val); + else + vcpu_set_msr(vcpu, msr, reset_val); + + val = vcpu_get_msr(vcpu, msr); + TEST_ASSERT(val == reset_val, "Wanted 0x%lx from get_msr(0x%x), got 0x%lx", + reset_val, msr, val); + + if (!has_one_reg) + return; + + val = vcpu_get_reg(vcpu, KVM_X86_REG_MSR(msr)); + TEST_ASSERT(val == reset_val, "Wanted 0x%lx from get_reg(0x%x), got 0x%lx", + reset_val, msr, val); +} + +static void do_vcpu_run(struct kvm_vcpu *vcpu) +{ + struct ucall uc; + + for (;;) { + vcpu_run(vcpu); + + switch (get_ucall(vcpu, &uc)) { + case UCALL_SYNC: + host_test_msr(vcpu, uc.args[1]); + return; + case UCALL_PRINTF: + pr_info("%s", uc.buffer); + break; + case UCALL_ABORT: + REPORT_GUEST_ASSERT(uc); + case UCALL_DONE: + TEST_FAIL("Unexpected UCALL_DONE"); + default: + TEST_FAIL("Unexpected ucall: %lu", uc.cmd); + } + } +} + +static void vcpus_run(struct kvm_vcpu **vcpus, const int NR_VCPUS) +{ + int i; + + for (i = 0; i < NR_VCPUS; i++) + do_vcpu_run(vcpus[i]); +} + +#define MISC_ENABLES_RESET_VAL (MSR_IA32_MISC_ENABLE_PEBS_UNAVAIL | MSR_IA32_MISC_ENABLE_BTS_UNAVAIL) + +static void test_msrs(void) +{ + const struct kvm_msr __msrs[] = { + MSR_TEST_NON_ZERO(MSR_IA32_MISC_ENABLE, + MISC_ENABLES_RESET_VAL | MSR_IA32_MISC_ENABLE_FAST_STRING, + MSR_IA32_MISC_ENABLE_FAST_STRING, MISC_ENABLES_RESET_VAL, NONE), + MSR_TEST_NON_ZERO(MSR_IA32_CR_PAT, 0x07070707, 0, 0x7040600070406, NONE), + + /* + * TSC_AUX is supported if RDTSCP *or* RDPID is supported. Add + * entries for each features so that TSC_AUX doesn't exists for + * the "unsupported" vCPU, and obviously to test both cases. + */ + MSR_TEST2(MSR_TSC_AUX, 0x12345678, u64_val, RDTSCP, RDPID), + MSR_TEST2(MSR_TSC_AUX, 0x12345678, u64_val, RDPID, RDTSCP), + + MSR_TEST(MSR_IA32_SYSENTER_CS, 0x1234, 0, NONE), + /* + * SYSENTER_{ESP,EIP} are technically non-canonical on Intel, + * but KVM doesn't emulate that behavior on emulated writes, + * i.e. this test will observe different behavior if the MSR + * writes are handed by hardware vs. KVM. KVM's behavior is + * intended (though far from ideal), so don't bother testing + * non-canonical values. + */ + MSR_TEST(MSR_IA32_SYSENTER_ESP, canonical_val, 0, NONE), + MSR_TEST(MSR_IA32_SYSENTER_EIP, canonical_val, 0, NONE), + + MSR_TEST_CANONICAL(MSR_FS_BASE, LM), + MSR_TEST_CANONICAL(MSR_GS_BASE, LM), + MSR_TEST_CANONICAL(MSR_KERNEL_GS_BASE, LM), + MSR_TEST_CANONICAL(MSR_LSTAR, LM), + MSR_TEST_CANONICAL(MSR_CSTAR, LM), + MSR_TEST(MSR_SYSCALL_MASK, 0xffffffff, 0, LM), + + MSR_TEST2(MSR_IA32_S_CET, CET_SHSTK_EN, CET_RESERVED, SHSTK, IBT), + MSR_TEST2(MSR_IA32_S_CET, CET_ENDBR_EN, CET_RESERVED, IBT, SHSTK), + MSR_TEST2(MSR_IA32_U_CET, CET_SHSTK_EN, CET_RESERVED, SHSTK, IBT), + MSR_TEST2(MSR_IA32_U_CET, CET_ENDBR_EN, CET_RESERVED, IBT, SHSTK), + MSR_TEST_CANONICAL(MSR_IA32_PL0_SSP, SHSTK), + MSR_TEST(MSR_IA32_PL0_SSP, canonical_val, canonical_val | 1, SHSTK), + MSR_TEST_CANONICAL(MSR_IA32_PL1_SSP, SHSTK), + MSR_TEST(MSR_IA32_PL1_SSP, canonical_val, canonical_val | 1, SHSTK), + MSR_TEST_CANONICAL(MSR_IA32_PL2_SSP, SHSTK), + MSR_TEST(MSR_IA32_PL2_SSP, canonical_val, canonical_val | 1, SHSTK), + MSR_TEST_CANONICAL(MSR_IA32_PL3_SSP, SHSTK), + MSR_TEST(MSR_IA32_PL3_SSP, canonical_val, canonical_val | 1, SHSTK), + + MSR_TEST_KVM(GUEST_SSP, canonical_val, NONCANONICAL, SHSTK), + }; + + const struct kvm_x86_cpu_feature feat_none = X86_FEATURE_NONE; + const struct kvm_x86_cpu_feature feat_lm = X86_FEATURE_LM; + + /* + * Create three vCPUs, but run them on the same task, to validate KVM's + * context switching of MSR state. Don't pin the task to a pCPU to + * also validate KVM's handling of cross-pCPU migration. Use the full + * set of features for the first two vCPUs, but clear all features in + * third vCPU in order to test both positive and negative paths. + */ + const int NR_VCPUS = 3; + struct kvm_vcpu *vcpus[NR_VCPUS]; + struct kvm_vm *vm; + int i; + + kvm_static_assert(sizeof(__msrs) <= sizeof(msrs)); + kvm_static_assert(ARRAY_SIZE(__msrs) <= ARRAY_SIZE(msrs)); + memcpy(msrs, __msrs, sizeof(__msrs)); + + ignore_unsupported_msrs = kvm_is_ignore_msrs(); + + vm = vm_create_with_vcpus(NR_VCPUS, guest_main, vcpus); + + sync_global_to_guest(vm, msrs); + sync_global_to_guest(vm, ignore_unsupported_msrs); + + /* + * Clear features in the "unsupported features" vCPU. This needs to be + * done before the first vCPU run as KVM's ABI is that guest CPUID is + * immutable once the vCPU has been run. + */ + for (idx = 0; idx < ARRAY_SIZE(__msrs); idx++) { + /* + * Don't clear LM; selftests are 64-bit only, and KVM doesn't + * honor LM=0 for MSRs that are supposed to exist if and only + * if the vCPU is a 64-bit model. Ditto for NONE; clearing a + * fake feature flag will result in false failures. + */ + if (memcmp(&msrs[idx].feature, &feat_lm, sizeof(feat_lm)) && + memcmp(&msrs[idx].feature, &feat_none, sizeof(feat_none))) + vcpu_clear_cpuid_feature(vcpus[2], msrs[idx].feature); + } + + for (idx = 0; idx < ARRAY_SIZE(__msrs); idx++) { + struct kvm_msr *msr = &msrs[idx]; + + if (msr->is_kvm_defined) { + for (i = 0; i < NR_VCPUS; i++) + host_test_kvm_reg(vcpus[i]); + continue; + } + + /* + * Verify KVM_GET_SUPPORTED_CPUID and KVM_GET_MSR_INDEX_LIST + * are consistent with respect to MSRs whose existence is + * enumerated via CPUID. Skip the check for FS/GS.base MSRs, + * as they aren't reported in the save/restore list since their + * state is managed via SREGS. + */ + TEST_ASSERT(msr->index == MSR_FS_BASE || msr->index == MSR_GS_BASE || + kvm_msr_is_in_save_restore_list(msr->index) == + (kvm_cpu_has(msr->feature) || kvm_cpu_has(msr->feature2)), + "%s %s in save/restore list, but %s according to CPUID", msr->name, + kvm_msr_is_in_save_restore_list(msr->index) ? "is" : "isn't", + (kvm_cpu_has(msr->feature) || kvm_cpu_has(msr->feature2)) ? + "supported" : "unsupported"); + + sync_global_to_guest(vm, idx); + + vcpus_run(vcpus, NR_VCPUS); + vcpus_run(vcpus, NR_VCPUS); + } + + kvm_vm_free(vm); +} + +int main(void) +{ + has_one_reg = kvm_has_cap(KVM_CAP_ONE_REG); + + test_msrs(); + + if (has_one_reg) { + use_one_reg = true; + test_msrs(); + } +} diff --git a/tools/testing/selftests/kvm/x86/pmu_counters_test.c b/tools/testing/selftests/kvm/x86/pmu_counters_test.c index 8aaaf25b6111..3eaa216b96c0 100644 --- a/tools/testing/selftests/kvm/x86/pmu_counters_test.c +++ b/tools/testing/selftests/kvm/x86/pmu_counters_test.c @@ -14,10 +14,10 @@ #define NUM_BRANCH_INSNS_RETIRED (NUM_LOOPS) /* - * Number of instructions in each loop. 1 CLFLUSH/CLFLUSHOPT/NOP, 1 MFENCE, - * 1 LOOP. + * Number of instructions in each loop. 1 ENTER, 1 CLFLUSH/CLFLUSHOPT/NOP, + * 1 MFENCE, 1 MOV, 1 LEAVE, 1 LOOP. */ -#define NUM_INSNS_PER_LOOP 4 +#define NUM_INSNS_PER_LOOP 6 /* * Number of "extra" instructions that will be counted, i.e. the number of @@ -75,6 +75,11 @@ static struct kvm_intel_pmu_event intel_event_to_feature(uint8_t idx) [INTEL_ARCH_BRANCHES_RETIRED_INDEX] = { X86_PMU_FEATURE_BRANCH_INSNS_RETIRED, X86_PMU_FEATURE_NULL }, [INTEL_ARCH_BRANCHES_MISPREDICTED_INDEX] = { X86_PMU_FEATURE_BRANCHES_MISPREDICTED, X86_PMU_FEATURE_NULL }, [INTEL_ARCH_TOPDOWN_SLOTS_INDEX] = { X86_PMU_FEATURE_TOPDOWN_SLOTS, X86_PMU_FEATURE_TOPDOWN_SLOTS_FIXED }, + [INTEL_ARCH_TOPDOWN_BE_BOUND_INDEX] = { X86_PMU_FEATURE_TOPDOWN_BE_BOUND, X86_PMU_FEATURE_NULL }, + [INTEL_ARCH_TOPDOWN_BAD_SPEC_INDEX] = { X86_PMU_FEATURE_TOPDOWN_BAD_SPEC, X86_PMU_FEATURE_NULL }, + [INTEL_ARCH_TOPDOWN_FE_BOUND_INDEX] = { X86_PMU_FEATURE_TOPDOWN_FE_BOUND, X86_PMU_FEATURE_NULL }, + [INTEL_ARCH_TOPDOWN_RETIRING_INDEX] = { X86_PMU_FEATURE_TOPDOWN_RETIRING, X86_PMU_FEATURE_NULL }, + [INTEL_ARCH_LBR_INSERTS_INDEX] = { X86_PMU_FEATURE_LBR_INSERTS, X86_PMU_FEATURE_NULL }, }; kvm_static_assert(ARRAY_SIZE(__intel_event_to_feature) == NR_INTEL_ARCH_EVENTS); @@ -158,10 +163,18 @@ static void guest_assert_event_count(uint8_t idx, uint32_t pmc, uint32_t pmc_msr switch (idx) { case INTEL_ARCH_INSTRUCTIONS_RETIRED_INDEX: - GUEST_ASSERT_EQ(count, NUM_INSNS_RETIRED); + /* Relax precise count check due to VM-EXIT/VM-ENTRY overcount issue */ + if (this_pmu_has_errata(INSTRUCTIONS_RETIRED_OVERCOUNT)) + GUEST_ASSERT(count >= NUM_INSNS_RETIRED); + else + GUEST_ASSERT_EQ(count, NUM_INSNS_RETIRED); break; case INTEL_ARCH_BRANCHES_RETIRED_INDEX: - GUEST_ASSERT_EQ(count, NUM_BRANCH_INSNS_RETIRED); + /* Relax precise count check due to VM-EXIT/VM-ENTRY overcount issue */ + if (this_pmu_has_errata(BRANCHES_RETIRED_OVERCOUNT)) + GUEST_ASSERT(count >= NUM_BRANCH_INSNS_RETIRED); + else + GUEST_ASSERT_EQ(count, NUM_BRANCH_INSNS_RETIRED); break; case INTEL_ARCH_LLC_REFERENCES_INDEX: case INTEL_ARCH_LLC_MISSES_INDEX: @@ -171,9 +184,12 @@ static void guest_assert_event_count(uint8_t idx, uint32_t pmc, uint32_t pmc_msr fallthrough; case INTEL_ARCH_CPU_CYCLES_INDEX: case INTEL_ARCH_REFERENCE_CYCLES_INDEX: + case INTEL_ARCH_TOPDOWN_BE_BOUND_INDEX: + case INTEL_ARCH_TOPDOWN_FE_BOUND_INDEX: GUEST_ASSERT_NE(count, 0); break; case INTEL_ARCH_TOPDOWN_SLOTS_INDEX: + case INTEL_ARCH_TOPDOWN_RETIRING_INDEX: __GUEST_ASSERT(count >= NUM_INSNS_RETIRED, "Expected top-down slots >= %u, got count = %lu", NUM_INSNS_RETIRED, count); @@ -210,9 +226,11 @@ do { \ __asm__ __volatile__("wrmsr\n\t" \ " mov $" __stringify(NUM_LOOPS) ", %%ecx\n\t" \ "1:\n\t" \ + FEP "enter $0, $0\n\t" \ clflush "\n\t" \ "mfence\n\t" \ "mov %[m], %%eax\n\t" \ + FEP "leave\n\t" \ FEP "loop 1b\n\t" \ FEP "mov %%edi, %%ecx\n\t" \ FEP "xor %%eax, %%eax\n\t" \ @@ -311,7 +329,7 @@ static void guest_test_arch_events(void) } static void test_arch_events(uint8_t pmu_version, uint64_t perf_capabilities, - uint8_t length, uint8_t unavailable_mask) + uint8_t length, uint32_t unavailable_mask) { struct kvm_vcpu *vcpu; struct kvm_vm *vm; @@ -320,6 +338,9 @@ static void test_arch_events(uint8_t pmu_version, uint64_t perf_capabilities, if (!pmu_version) return; + unavailable_mask &= GENMASK(X86_PROPERTY_PMU_EVENTS_MASK.hi_bit, + X86_PROPERTY_PMU_EVENTS_MASK.lo_bit); + vm = pmu_vm_create_with_one_vcpu(&vcpu, guest_test_arch_events, pmu_version, perf_capabilities); @@ -344,8 +365,8 @@ static void test_arch_events(uint8_t pmu_version, uint64_t perf_capabilities, #define GUEST_ASSERT_PMC_MSR_ACCESS(insn, msr, expect_gp, vector) \ __GUEST_ASSERT(expect_gp ? vector == GP_VECTOR : !vector, \ - "Expected %s on " #insn "(0x%x), got vector %u", \ - expect_gp ? "#GP" : "no fault", msr, vector) \ + "Expected %s on " #insn "(0x%x), got %s", \ + expect_gp ? "#GP" : "no fault", msr, ex_str(vector)) \ #define GUEST_ASSERT_PMC_VALUE(insn, msr, val, expected) \ __GUEST_ASSERT(val == expected, \ @@ -575,6 +596,26 @@ static void test_intel_counters(void) }; /* + * To keep the total runtime reasonable, test only a handful of select, + * semi-arbitrary values for the mask of unavailable PMU events. Test + * 0 (all events available) and all ones (no events available) as well + * as alternating bit sequencues, e.g. to detect if KVM is checking the + * wrong bit(s). + */ + const uint32_t unavailable_masks[] = { + 0x0, + 0xffffffffu, + 0xaaaaaaaau, + 0x55555555u, + 0xf0f0f0f0u, + 0x0f0f0f0fu, + 0xa0a0a0a0u, + 0x0a0a0a0au, + 0x50505050u, + 0x05050505u, + }; + + /* * Test up to PMU v5, which is the current maximum version defined by * Intel, i.e. is the last version that is guaranteed to be backwards * compatible with KVM's existing behavior. @@ -611,16 +652,7 @@ static void test_intel_counters(void) pr_info("Testing arch events, PMU version %u, perf_caps = %lx\n", v, perf_caps[i]); - /* - * To keep the total runtime reasonable, test every - * possible non-zero, non-reserved bitmap combination - * only with the native PMU version and the full bit - * vector length. - */ - if (v == pmu_version) { - for (k = 1; k < (BIT(NR_INTEL_ARCH_EVENTS) - 1); k++) - test_arch_events(v, perf_caps[i], NR_INTEL_ARCH_EVENTS, k); - } + /* * Test single bits for all PMU version and lengths up * the number of events +1 (to verify KVM doesn't do @@ -629,11 +661,8 @@ static void test_intel_counters(void) * ones i.e. all events being available and unavailable. */ for (j = 0; j <= NR_INTEL_ARCH_EVENTS + 1; j++) { - test_arch_events(v, perf_caps[i], j, 0); - test_arch_events(v, perf_caps[i], j, 0xff); - - for (k = 0; k < NR_INTEL_ARCH_EVENTS; k++) - test_arch_events(v, perf_caps[i], j, BIT(k)); + for (k = 1; k < ARRAY_SIZE(unavailable_masks); k++) + test_arch_events(v, perf_caps[i], j, unavailable_masks[k]); } pr_info("Testing GP counters, PMU version %u, perf_caps = %lx\n", diff --git a/tools/testing/selftests/kvm/x86/pmu_event_filter_test.c b/tools/testing/selftests/kvm/x86/pmu_event_filter_test.c index c15513cd74d1..1c5b7611db24 100644 --- a/tools/testing/selftests/kvm/x86/pmu_event_filter_test.c +++ b/tools/testing/selftests/kvm/x86/pmu_event_filter_test.c @@ -214,8 +214,10 @@ static void remove_event(struct __kvm_pmu_event_filter *f, uint64_t event) do { \ uint64_t br = pmc_results.branches_retired; \ uint64_t ir = pmc_results.instructions_retired; \ + bool br_matched = this_pmu_has_errata(BRANCHES_RETIRED_OVERCOUNT) ? \ + br >= NUM_BRANCHES : br == NUM_BRANCHES; \ \ - if (br && br != NUM_BRANCHES) \ + if (br && !br_matched) \ pr_info("%s: Branch instructions retired = %lu (expected %u)\n", \ __func__, br, NUM_BRANCHES); \ TEST_ASSERT(br, "%s: Branch instructions retired = %lu (expected > 0)", \ diff --git a/tools/testing/selftests/kvm/x86/vmx_pmu_caps_test.c b/tools/testing/selftests/kvm/x86/vmx_pmu_caps_test.c index a1f5ff45d518..7ff6f62e20a3 100644 --- a/tools/testing/selftests/kvm/x86/vmx_pmu_caps_test.c +++ b/tools/testing/selftests/kvm/x86/vmx_pmu_caps_test.c @@ -29,7 +29,7 @@ static union perf_capabilities { u64 pebs_baseline:1; u64 perf_metrics:1; u64 pebs_output_pt_available:1; - u64 anythread_deprecated:1; + u64 pebs_timing_info:1; }; u64 capabilities; } host_cap; @@ -44,6 +44,7 @@ static const union perf_capabilities immutable_caps = { .pebs_arch_reg = 1, .pebs_format = -1, .pebs_baseline = 1, + .pebs_timing_info = 1, }; static const union perf_capabilities format_caps = { @@ -56,8 +57,8 @@ static void guest_test_perf_capabilities_gp(uint64_t val) uint8_t vector = wrmsr_safe(MSR_IA32_PERF_CAPABILITIES, val); __GUEST_ASSERT(vector == GP_VECTOR, - "Expected #GP for value '0x%lx', got vector '0x%x'", - val, vector); + "Expected #GP for value '0x%lx', got %s", + val, ex_str(vector)); } static void guest_code(uint64_t current_val) diff --git a/tools/testing/selftests/kvm/x86/xapic_state_test.c b/tools/testing/selftests/kvm/x86/xapic_state_test.c index fdebff1165c7..3b4814c55722 100644 --- a/tools/testing/selftests/kvm/x86/xapic_state_test.c +++ b/tools/testing/selftests/kvm/x86/xapic_state_test.c @@ -120,8 +120,8 @@ static void test_icr(struct xapic_vcpu *x) __test_icr(x, icr | i); /* - * Send all flavors of IPIs to non-existent vCPUs. TODO: use number of - * vCPUs, not vcpu.id + 1. Arbitrarily use vector 0xff. + * Send all flavors of IPIs to non-existent vCPUs. Arbitrarily use + * vector 0xff. */ icr = APIC_INT_ASSERT | 0xff; for (i = 0; i < 0xff; i++) { diff --git a/tools/testing/selftests/kvm/x86/xcr0_cpuid_test.c b/tools/testing/selftests/kvm/x86/xcr0_cpuid_test.c index c8a5c5e51661..d038c1571729 100644 --- a/tools/testing/selftests/kvm/x86/xcr0_cpuid_test.c +++ b/tools/testing/selftests/kvm/x86/xcr0_cpuid_test.c @@ -81,13 +81,13 @@ static void guest_code(void) vector = xsetbv_safe(0, XFEATURE_MASK_FP); __GUEST_ASSERT(!vector, - "Expected success on XSETBV(FP), got vector '0x%x'", - vector); + "Expected success on XSETBV(FP), got %s", + ex_str(vector)); vector = xsetbv_safe(0, supported_xcr0); __GUEST_ASSERT(!vector, - "Expected success on XSETBV(0x%lx), got vector '0x%x'", - supported_xcr0, vector); + "Expected success on XSETBV(0x%lx), got %s", + supported_xcr0, ex_str(vector)); for (i = 0; i < 64; i++) { if (supported_xcr0 & BIT_ULL(i)) @@ -95,8 +95,8 @@ static void guest_code(void) vector = xsetbv_safe(0, supported_xcr0 | BIT_ULL(i)); __GUEST_ASSERT(vector == GP_VECTOR, - "Expected #GP on XSETBV(0x%llx), supported XCR0 = %lx, got vector '0x%x'", - BIT_ULL(i), supported_xcr0, vector); + "Expected #GP on XSETBV(0x%llx), supported XCR0 = %lx, got %s", + BIT_ULL(i), supported_xcr0, ex_str(vector)); } GUEST_DONE(); diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 5d9d96515c4a..b5127e968108 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -1,128 +1,201 @@ # SPDX-License-Identifier: GPL-2.0 # Makefile for net selftests -CFLAGS += -Wall -Wl,--no-as-needed -O2 -g +CFLAGS += -Wall -Wl,--no-as-needed -O2 -g CFLAGS += -I../../../../usr/include/ $(KHDR_INCLUDES) # Additional include paths needed by kselftest.h CFLAGS += -I../ -TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh netdevice.sh \ - rtnetlink.sh xfrm_policy.sh -TEST_PROGS += fcnal-ipv4.sh fcnal-ipv6.sh fcnal-other.sh -TEST_PROGS += fib_tests.sh fib-onlink-tests.sh pmtu.sh udpgso.sh ip_defrag.sh -TEST_PROGS += udpgso_bench.sh fib_rule_tests.sh msg_zerocopy.sh psock_snd.sh -TEST_PROGS += udpgro_bench.sh udpgro.sh test_vxlan_under_vrf.sh reuseport_addr_any.sh -TEST_PROGS += test_vxlan_fdb_changelink.sh so_txtime.sh ipv6_flowlabel.sh -TEST_PROGS += tcp_fastopen_backup_key.sh l2tp.sh traceroute.sh -TEST_PROGS += fin_ack_lat.sh fib_nexthop_multiprefix.sh fib_nexthops.sh fib_nexthop_nongw.sh -TEST_PROGS += altnames.sh icmp.sh icmp_redirect.sh ip6_gre_headroom.sh -TEST_PROGS += route_localnet.sh -TEST_PROGS += reuseaddr_ports_exhausted.sh -TEST_PROGS += txtimestamp.sh -TEST_PROGS += vrf-xfrm-tests.sh -TEST_PROGS += rxtimestamp.sh -TEST_PROGS += drop_monitor_tests.sh -TEST_PROGS += vrf_route_leaking.sh -TEST_PROGS += bareudp.sh -TEST_PROGS += amt.sh -TEST_PROGS += unicast_extensions.sh -TEST_PROGS += udpgro_fwd.sh -TEST_PROGS += udpgro_frglist.sh -TEST_PROGS += nat6to4.sh -TEST_PROGS += veth.sh -TEST_PROGS += ioam6.sh -TEST_PROGS += gro.sh -TEST_PROGS += gre_gso.sh -TEST_PROGS += gre_ipv6_lladdr.sh -TEST_PROGS += cmsg_so_mark.sh -TEST_PROGS += cmsg_so_priority.sh -TEST_PROGS += test_so_rcv.sh -TEST_PROGS += cmsg_time.sh cmsg_ip.sh -TEST_PROGS += netns-name.sh -TEST_PROGS += link_netns.py -TEST_PROGS += nl_netdev.py -TEST_PROGS += rtnetlink.py -TEST_PROGS += rtnetlink_notification.sh -TEST_PROGS += srv6_end_dt46_l3vpn_test.sh -TEST_PROGS += srv6_end_dt4_l3vpn_test.sh -TEST_PROGS += srv6_end_dt6_l3vpn_test.sh -TEST_PROGS += srv6_hencap_red_l3vpn_test.sh -TEST_PROGS += srv6_hl2encap_red_l2vpn_test.sh -TEST_PROGS += srv6_end_next_csid_l3vpn_test.sh -TEST_PROGS += srv6_end_x_next_csid_l3vpn_test.sh -TEST_PROGS += srv6_end_flavors_test.sh -TEST_PROGS += srv6_end_dx4_netfilter_test.sh -TEST_PROGS += srv6_end_dx6_netfilter_test.sh -TEST_PROGS += vrf_strict_mode_test.sh -TEST_PROGS += arp_ndisc_evict_nocarrier.sh -TEST_PROGS += ndisc_unsolicited_na_test.sh -TEST_PROGS += arp_ndisc_untracked_subnets.sh -TEST_PROGS += stress_reuseport_listen.sh -TEST_PROGS += l2_tos_ttl_inherit.sh -TEST_PROGS += bind_bhash.sh -TEST_PROGS += ip_local_port_range.sh -TEST_PROGS += rps_default_mask.sh -TEST_PROGS += big_tcp.sh -TEST_PROGS += netns-sysctl.sh -TEST_PROGS += netdev-l2addr.sh -TEST_PROGS_EXTENDED := toeplitz_client.sh toeplitz.sh xfrm_policy_add_speed.sh -TEST_GEN_FILES = socket nettest -TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy reuseport_addr_any -TEST_GEN_FILES += tcp_mmap tcp_inq psock_snd txring_overwrite -TEST_GEN_FILES += udpgso udpgso_bench_tx udpgso_bench_rx ip_defrag -TEST_GEN_FILES += so_txtime ipv6_flowlabel ipv6_flowlabel_mgr so_netns_cookie -TEST_GEN_FILES += tcp_fastopen_backup_key -TEST_GEN_FILES += fin_ack_lat -TEST_GEN_FILES += reuseaddr_ports_exhausted -TEST_GEN_FILES += hwtstamp_config rxtimestamp timestamping txtimestamp -TEST_GEN_FILES += ipsec -TEST_GEN_FILES += ioam6_parser -TEST_GEN_FILES += gro -TEST_GEN_PROGS = reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa -TEST_GEN_PROGS += reuseport_dualstack reuseaddr_conflict tls tun tap epoll_busy_poll -TEST_GEN_FILES += toeplitz -TEST_GEN_FILES += cmsg_sender -TEST_GEN_FILES += stress_reuseport_listen -TEST_GEN_FILES += so_rcv_listener -TEST_PROGS += test_vxlan_vnifiltering.sh -TEST_GEN_FILES += io_uring_zerocopy_tx -TEST_PROGS += io_uring_zerocopy_tx.sh -TEST_GEN_FILES += bind_bhash -TEST_GEN_PROGS += sk_bind_sendto_listen -TEST_GEN_PROGS += sk_connect_zero_addr -TEST_GEN_PROGS += sk_so_peek_off -TEST_PROGS += test_ingress_egress_chaining.sh -TEST_GEN_PROGS += so_incoming_cpu -TEST_PROGS += sctp_vrf.sh -TEST_GEN_FILES += sctp_hello -TEST_GEN_FILES += ip_local_port_range -TEST_GEN_PROGS += bind_wildcard -TEST_GEN_PROGS += bind_timewait -TEST_PROGS += test_vxlan_mdb.sh -TEST_PROGS += test_bridge_neigh_suppress.sh -TEST_PROGS += test_vxlan_nh.sh -TEST_PROGS += test_vxlan_nolocalbypass.sh -TEST_PROGS += test_bridge_backup_port.sh -TEST_PROGS += test_neigh.sh -TEST_PROGS += fdb_flush.sh fdb_notify.sh -TEST_PROGS += fq_band_pktlimit.sh -TEST_PROGS += vlan_hw_filter.sh -TEST_PROGS += vlan_bridge_binding.sh -TEST_PROGS += bpf_offload.py -TEST_PROGS += ipv6_route_update_soft_lockup.sh -TEST_PROGS += busy_poll_test.sh -TEST_GEN_PROGS += proc_net_pktgen -TEST_PROGS += lwt_dst_cache_ref_loop.sh -TEST_PROGS += skf_net_off.sh -TEST_GEN_FILES += skf_net_off -TEST_GEN_FILES += tfo -TEST_PROGS += tfo_passive.sh -TEST_PROGS += broadcast_ether_dst.sh -TEST_PROGS += broadcast_pmtu.sh -TEST_PROGS += ipv6_force_forwarding.sh -TEST_GEN_PROGS += ipv6_fragmentation -TEST_PROGS += route_hint.sh -TEST_GEN_PROGS += tcp_port_share +TEST_PROGS := \ + altnames.sh \ + amt.sh \ + arp_ndisc_evict_nocarrier.sh \ + arp_ndisc_untracked_subnets.sh \ + bareudp.sh \ + big_tcp.sh \ + bind_bhash.sh \ + bpf_offload.py \ + broadcast_ether_dst.sh \ + broadcast_pmtu.sh \ + busy_poll_test.sh \ + cmsg_ip.sh \ + cmsg_so_mark.sh \ + cmsg_so_priority.sh \ + cmsg_time.sh \ + drop_monitor_tests.sh \ + fcnal-ipv4.sh \ + fcnal-ipv6.sh \ + fcnal-other.sh \ + fdb_flush.sh \ + fdb_notify.sh \ + fib-onlink-tests.sh \ + fib_nexthop_multiprefix.sh \ + fib_nexthop_nongw.sh \ + fib_nexthops.sh \ + fib_rule_tests.sh \ + fib_tests.sh \ + fin_ack_lat.sh \ + fq_band_pktlimit.sh \ + gre_gso.sh \ + gre_ipv6_lladdr.sh \ + gro.sh \ + icmp.sh \ + icmp_redirect.sh \ + io_uring_zerocopy_tx.sh \ + ioam6.sh \ + ip6_gre_headroom.sh \ + ip_defrag.sh \ + ip_local_port_range.sh \ + ipv6_flowlabel.sh \ + ipv6_force_forwarding.sh \ + ipv6_route_update_soft_lockup.sh \ + l2_tos_ttl_inherit.sh \ + l2tp.sh \ + link_netns.py \ + lwt_dst_cache_ref_loop.sh \ + msg_zerocopy.sh \ + nat6to4.sh \ + ndisc_unsolicited_na_test.sh \ + netdev-l2addr.sh \ + netdevice.sh \ + netns-name.sh \ + netns-sysctl.sh \ + nl_netdev.py \ + pmtu.sh \ + psock_snd.sh \ + reuseaddr_ports_exhausted.sh \ + reuseport_addr_any.sh \ + route_hint.sh \ + route_localnet.sh \ + rps_default_mask.sh \ + rtnetlink.py \ + rtnetlink.sh \ + rtnetlink_notification.sh \ + run_afpackettests \ + run_netsocktests \ + rxtimestamp.sh \ + sctp_vrf.sh \ + skf_net_off.sh \ + so_txtime.sh \ + srv6_end_dt46_l3vpn_test.sh \ + srv6_end_dt4_l3vpn_test.sh \ + srv6_end_dt6_l3vpn_test.sh \ + srv6_end_dx4_netfilter_test.sh \ + srv6_end_dx6_netfilter_test.sh \ + srv6_end_flavors_test.sh \ + srv6_end_next_csid_l3vpn_test.sh \ + srv6_end_x_next_csid_l3vpn_test.sh \ + srv6_hencap_red_l3vpn_test.sh \ + srv6_hl2encap_red_l2vpn_test.sh \ + stress_reuseport_listen.sh \ + tcp_fastopen_backup_key.sh \ + test_bpf.sh \ + test_bridge_backup_port.sh \ + test_bridge_neigh_suppress.sh \ + test_ingress_egress_chaining.sh \ + test_neigh.sh \ + test_so_rcv.sh \ + test_vxlan_fdb_changelink.sh \ + test_vxlan_mdb.sh \ + test_vxlan_nh.sh \ + test_vxlan_nolocalbypass.sh \ + test_vxlan_under_vrf.sh \ + test_vxlan_vnifiltering.sh \ + tfo_passive.sh \ + traceroute.sh \ + txtimestamp.sh \ + udpgro.sh \ + udpgro_bench.sh \ + udpgro_frglist.sh \ + udpgro_fwd.sh \ + udpgso.sh \ + udpgso_bench.sh \ + unicast_extensions.sh \ + veth.sh \ + vlan_bridge_binding.sh \ + vlan_hw_filter.sh \ + vrf-xfrm-tests.sh \ + vrf_route_leaking.sh \ + vrf_strict_mode_test.sh \ + xfrm_policy.sh \ +# end of TEST_PROGS + +TEST_PROGS_EXTENDED := \ + toeplitz.sh \ + toeplitz_client.sh \ + xfrm_policy_add_speed.sh \ +# end of TEST_PROGS_EXTENDED + +TEST_GEN_FILES := \ + bind_bhash \ + cmsg_sender \ + fin_ack_lat \ + gro \ + hwtstamp_config \ + io_uring_zerocopy_tx \ + ioam6_parser \ + ip_defrag \ + ip_local_port_range \ + ipsec \ + ipv6_flowlabel \ + ipv6_flowlabel_mgr \ + msg_zerocopy \ + nettest \ + psock_fanout \ + psock_snd \ + psock_tpacket \ + reuseaddr_ports_exhausted \ + reuseport_addr_any \ + rxtimestamp \ + sctp_hello \ + skf_net_off \ + so_netns_cookie \ + so_rcv_listener \ + so_txtime \ + socket \ + stress_reuseport_listen \ + tcp_fastopen_backup_key \ + tcp_inq \ + tcp_mmap \ + tfo \ + timestamping \ + toeplitz \ + txring_overwrite \ + txtimestamp \ + udpgso \ + udpgso_bench_rx \ + udpgso_bench_tx \ +# end of TEST_GEN_FILES + +TEST_GEN_PROGS := \ + bind_timewait \ + bind_wildcard \ + epoll_busy_poll \ + ipv6_fragmentation \ + proc_net_pktgen \ + reuseaddr_conflict \ + reuseport_bpf \ + reuseport_bpf_cpu \ + reuseport_bpf_numa \ + reuseport_dualstack \ + sk_bind_sendto_listen \ + sk_connect_zero_addr \ + sk_so_peek_off \ + so_incoming_cpu \ + tap \ + tcp_port_share \ + tls \ + tun \ +# end of TEST_GEN_PROGS + +TEST_FILES := \ + fcnal-test.sh \ + in_netns.sh \ + lib.sh \ + settings \ + setup_loopback.sh \ + setup_veth.sh \ +# end of TEST_FILES # YNL files, must be before "include ..lib.mk" YNL_GEN_FILES := busy_poller @@ -130,10 +203,6 @@ YNL_GEN_PROGS := netlink-dumps TEST_GEN_FILES += $(YNL_GEN_FILES) TEST_GEN_PROGS += $(YNL_GEN_PROGS) -TEST_FILES := settings -TEST_FILES += fcnal-test.sh -TEST_FILES += in_netns.sh lib.sh setup_loopback.sh setup_veth.sh - TEST_GEN_FILES += $(patsubst %.c,%.o,$(wildcard *.bpf.c)) TEST_INCLUDES := forwarding/lib.sh diff --git a/tools/testing/selftests/net/af_unix/Makefile b/tools/testing/selftests/net/af_unix/Makefile index 0a20c98bbcfd..de805cbbdf69 100644 --- a/tools/testing/selftests/net/af_unix/Makefile +++ b/tools/testing/selftests/net/af_unix/Makefile @@ -1,4 +1,12 @@ CFLAGS += $(KHDR_INCLUDES) -Wall -Wflex-array-member-not-at-end -TEST_GEN_PROGS := diag_uid msg_oob scm_inq scm_pidfd scm_rights unix_connect + +TEST_GEN_PROGS := \ + diag_uid \ + msg_oob \ + scm_inq \ + scm_pidfd \ + scm_rights \ + unix_connect \ +# end of TEST_GEN_PROGS include ../../lib.mk diff --git a/tools/testing/selftests/net/af_unix/config b/tools/testing/selftests/net/af_unix/config index 37368567768c..b5429c15a53c 100644 --- a/tools/testing/selftests/net/af_unix/config +++ b/tools/testing/selftests/net/af_unix/config @@ -1,3 +1,3 @@ -CONFIG_UNIX=y CONFIG_AF_UNIX_OOB=y +CONFIG_UNIX=y CONFIG_UNIX_DIAG=m diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config index d548611e2698..1e1f253118f5 100644 --- a/tools/testing/selftests/net/config +++ b/tools/testing/selftests/net/config @@ -1,130 +1,130 @@ -CONFIG_USER_NS=y -CONFIG_NET_NS=y +CONFIG_AMT=m +CONFIG_BAREUDP=m CONFIG_BONDING=m CONFIG_BPF_SYSCALL=y -CONFIG_TEST_BPF=m -CONFIG_NUMA=y -CONFIG_RPS=y -CONFIG_SYSFS=y -CONFIG_PROC_SYSCTL=y -CONFIG_NET_VRF=y -CONFIG_NET_L3_MASTER_DEV=y -CONFIG_IPV6=y -CONFIG_IPV6_MULTIPLE_TABLES=y -CONFIG_VETH=y -CONFIG_NET_IPVTI=y -CONFIG_IPV6_VTI=y -CONFIG_DUMMY=y -CONFIG_BRIDGE_VLAN_FILTERING=y CONFIG_BRIDGE=y +CONFIG_BRIDGE_VLAN_FILTERING=y +CONFIG_CAN=m +CONFIG_CAN_DEV=m +CONFIG_CAN_VXCAN=m +CONFIG_CRYPTO_ARIA=y CONFIG_CRYPTO_CHACHA20POLY1305=m +CONFIG_CRYPTO_SHA1=y +CONFIG_CRYPTO_SM4_GENERIC=y CONFIG_DEBUG_INFO_BTF=y CONFIG_DEBUG_INFO_BTF_MODULES=n -CONFIG_VLAN_8021Q=y +CONFIG_DUMMY=y CONFIG_GENEVE=m CONFIG_IFB=y CONFIG_INET_DIAG=y CONFIG_INET_ESP=y CONFIG_INET_ESP_OFFLOAD=y -CONFIG_CRYPTO_SHA1=y -CONFIG_NET_FOU=y -CONFIG_NET_FOU_IP_TUNNELS=y -CONFIG_NETFILTER=y -CONFIG_NETFILTER_ADVANCED=y -CONFIG_NETFILTER_XTABLES_LEGACY=y -CONFIG_NF_CONNTRACK=m -CONFIG_IPV6_MROUTE=y -CONFIG_IPV6_SIT=y -CONFIG_NF_NAT=m +CONFIG_IP6_NF_FILTER=m CONFIG_IP6_NF_IPTABLES=m CONFIG_IP6_NF_IPTABLES_LEGACY=m -CONFIG_IP_NF_IPTABLES=m -CONFIG_IP_NF_IPTABLES_LEGACY=m CONFIG_IP6_NF_MANGLE=m -CONFIG_IP6_NF_FILTER=m +CONFIG_IP6_NF_MATCH_RPFILTER=m CONFIG_IP6_NF_NAT=m CONFIG_IP6_NF_RAW=m -CONFIG_IP_NF_MANGLE=m +CONFIG_IP6_NF_TARGET_REJECT=m CONFIG_IP_NF_FILTER=m +CONFIG_IP_NF_IPTABLES=m +CONFIG_IP_NF_IPTABLES_LEGACY=m +CONFIG_IP_NF_MANGLE=m +CONFIG_IP_NF_MATCH_RPFILTER=m CONFIG_IP_NF_NAT=m CONFIG_IP_NF_RAW=m CONFIG_IP_NF_TARGET_REJECT=m -CONFIG_IP6_NF_TARGET_REJECT=m CONFIG_IP_NF_TARGET_TTL=m +CONFIG_IP_SCTP=m +CONFIG_IPV6=y CONFIG_IPV6_GRE=m +CONFIG_IPV6_ILA=m +CONFIG_IPV6_IOAM6_LWTUNNEL=y +CONFIG_IPV6_MROUTE=y +CONFIG_IPV6_MULTIPLE_TABLES=y +CONFIG_IPV6_RPL_LWTUNNEL=y CONFIG_IPV6_SEG6_LWTUNNEL=y +CONFIG_IPV6_SIT=y +CONFIG_IPV6_VTI=y +CONFIG_IPVLAN=m +CONFIG_KALLSYMS=y +CONFIG_L2TP=m CONFIG_L2TP_ETH=m CONFIG_L2TP_IP=m -CONFIG_L2TP=m CONFIG_L2TP_V3=y CONFIG_MACSEC=m CONFIG_MACVLAN=y CONFIG_MACVTAP=y CONFIG_MPLS=y +CONFIG_MPLS_IPTUNNEL=m +CONFIG_MPLS_ROUTING=m CONFIG_MPTCP=y -CONFIG_NF_TABLES=m -CONFIG_NF_TABLES_IPV6=y -CONFIG_NF_TABLES_IPV4=y -CONFIG_NFT_NAT=m -CONFIG_NETFILTER_XT_MATCH_LENGTH=m -CONFIG_NETFILTER_XT_TARGET_HL=m -CONFIG_NETFILTER_XT_NAT=m CONFIG_NET_ACT_CSUM=m CONFIG_NET_ACT_CT=m CONFIG_NET_ACT_GACT=m +CONFIG_NET_ACT_MIRRED=m CONFIG_NET_ACT_PEDIT=m +CONFIG_NET_ACT_TUNNEL_KEY=m CONFIG_NET_CLS_BASIC=m CONFIG_NET_CLS_BPF=m +CONFIG_NET_CLS_FLOWER=m CONFIG_NET_CLS_MATCHALL=m CONFIG_NET_CLS_U32=m -CONFIG_NET_IPGRE_DEMUX=m +CONFIG_NETDEVSIM=m +CONFIG_NET_DROP_MONITOR=m +CONFIG_NETFILTER=y +CONFIG_NETFILTER_ADVANCED=y +CONFIG_NETFILTER_XTABLES_LEGACY=y +CONFIG_NETFILTER_XT_MATCH_LENGTH=m +CONFIG_NETFILTER_XT_MATCH_POLICY=m +CONFIG_NETFILTER_XT_NAT=m +CONFIG_NETFILTER_XT_TARGET_HL=m +CONFIG_NET_FOU=y +CONFIG_NET_FOU_IP_TUNNELS=y CONFIG_NET_IPGRE=m +CONFIG_NET_IPGRE_DEMUX=m CONFIG_NET_IPIP=y +CONFIG_NET_IPVTI=y +CONFIG_NETKIT=y +CONFIG_NET_L3_MASTER_DEV=y +CONFIG_NET_NS=y +CONFIG_NET_PKTGEN=m +CONFIG_NET_SCH_ETF=m +CONFIG_NET_SCH_FQ=m CONFIG_NET_SCH_FQ_CODEL=m CONFIG_NET_SCH_HTB=m -CONFIG_NET_SCH_FQ=m -CONFIG_NET_SCH_ETF=m +CONFIG_NET_SCH_INGRESS=m CONFIG_NET_SCH_NETEM=y CONFIG_NET_SCH_PRIO=m -CONFIG_NFT_COMPAT=m +CONFIG_NET_VRF=y +CONFIG_NF_CONNTRACK=m CONFIG_NF_CONNTRACK_OVS=y CONFIG_NF_FLOW_TABLE=m +CONFIG_NF_NAT=m +CONFIG_NF_TABLES=m +CONFIG_NF_TABLES_IPV4=y +CONFIG_NF_TABLES_IPV6=y +CONFIG_NFT_COMPAT=m +CONFIG_NFT_NAT=m +CONFIG_NUMA=y CONFIG_OPENVSWITCH=m CONFIG_OPENVSWITCH_GENEVE=m CONFIG_OPENVSWITCH_GRE=m CONFIG_OPENVSWITCH_VXLAN=m +CONFIG_PROC_SYSCTL=y CONFIG_PSAMPLE=m +CONFIG_RPS=y +CONFIG_SYSFS=y CONFIG_TCP_MD5SIG=y CONFIG_TEST_BLACKHOLE_DEV=m -CONFIG_KALLSYMS=y +CONFIG_TEST_BPF=m CONFIG_TLS=m CONFIG_TRACEPOINTS=y -CONFIG_NET_DROP_MONITOR=m -CONFIG_NETDEVSIM=m -CONFIG_MPLS_ROUTING=m -CONFIG_MPLS_IPTUNNEL=m -CONFIG_NET_SCH_INGRESS=m -CONFIG_NET_CLS_FLOWER=m -CONFIG_NET_ACT_TUNNEL_KEY=m -CONFIG_NET_ACT_MIRRED=m -CONFIG_BAREUDP=m -CONFIG_IPV6_IOAM6_LWTUNNEL=y -CONFIG_CRYPTO_SM4_GENERIC=y -CONFIG_AMT=m CONFIG_TUN=y +CONFIG_USER_NS=y +CONFIG_VETH=y +CONFIG_VLAN_8021Q=y CONFIG_VXLAN=m -CONFIG_IP_SCTP=m -CONFIG_NETFILTER_XT_MATCH_POLICY=m -CONFIG_CRYPTO_ARIA=y CONFIG_XFRM_INTERFACE=m CONFIG_XFRM_USER=m -CONFIG_IP_NF_MATCH_RPFILTER=m -CONFIG_IP6_NF_MATCH_RPFILTER=m -CONFIG_IPVLAN=m -CONFIG_CAN=m -CONFIG_CAN_DEV=m -CONFIG_CAN_VXCAN=m -CONFIG_NETKIT=y -CONFIG_NET_PKTGEN=m -CONFIG_IPV6_ILA=m -CONFIG_IPV6_RPL_LWTUNNEL=y diff --git a/tools/testing/selftests/net/forwarding/Makefile b/tools/testing/selftests/net/forwarding/Makefile index e6f482a600da..ff4a00d91a26 100644 --- a/tools/testing/selftests/net/forwarding/Makefile +++ b/tools/testing/selftests/net/forwarding/Makefile @@ -1,11 +1,11 @@ # SPDX-License-Identifier: GPL-2.0+ OR MIT -TEST_PROGS = \ +TEST_PROGS := \ bridge_activity_notify.sh \ bridge_fdb_learning_limit.sh \ + bridge_fdb_local_vlan_0.sh \ bridge_igmp.sh \ bridge_locked_port.sh \ - bridge_fdb_local_vlan_0.sh \ bridge_mdb.sh \ bridge_mdb_host.sh \ bridge_mdb_max.sh \ @@ -21,64 +21,64 @@ TEST_PROGS = \ gre_custom_multipath_hash.sh \ gre_inner_v4_multipath.sh \ gre_inner_v6_multipath.sh \ - gre_multipath_nh_res.sh \ - gre_multipath_nh.sh \ gre_multipath.sh \ + gre_multipath_nh.sh \ + gre_multipath_nh_res.sh \ ip6_forward_instats_vrf.sh \ ip6gre_custom_multipath_hash.sh \ + ip6gre_flat.sh \ ip6gre_flat_key.sh \ ip6gre_flat_keys.sh \ - ip6gre_flat.sh \ + ip6gre_hier.sh \ ip6gre_hier_key.sh \ ip6gre_hier_keys.sh \ - ip6gre_hier.sh \ ip6gre_inner_v4_multipath.sh \ ip6gre_inner_v6_multipath.sh \ + ipip_flat_gre.sh \ ipip_flat_gre_key.sh \ ipip_flat_gre_keys.sh \ - ipip_flat_gre.sh \ + ipip_hier_gre.sh \ ipip_hier_gre_key.sh \ ipip_hier_gre_keys.sh \ - ipip_hier_gre.sh \ lib_sh_test.sh \ local_termination.sh \ min_max_mtu.sh \ + mirror_gre.sh \ mirror_gre_bound.sh \ mirror_gre_bridge_1d.sh \ mirror_gre_bridge_1d_vlan.sh \ - mirror_gre_bridge_1q_lag.sh \ mirror_gre_bridge_1q.sh \ + mirror_gre_bridge_1q_lag.sh \ mirror_gre_changes.sh \ mirror_gre_flower.sh \ mirror_gre_lag_lacp.sh \ mirror_gre_neigh.sh \ mirror_gre_nh.sh \ - mirror_gre.sh \ - mirror_gre_vlan_bridge_1q.sh \ mirror_gre_vlan.sh \ + mirror_gre_vlan_bridge_1q.sh \ mirror_vlan.sh \ no_forwarding.sh \ pedit_dsfield.sh \ pedit_ip.sh \ pedit_l4port.sh \ - q_in_vni_ipv6.sh \ q_in_vni.sh \ + q_in_vni_ipv6.sh \ + router.sh \ router_bridge.sh \ router_bridge_1d.sh \ router_bridge_1d_lag.sh \ router_bridge_lag.sh \ + router_bridge_pvid_vlan_upper.sh \ router_bridge_vlan.sh \ router_bridge_vlan_upper.sh \ - router_bridge_pvid_vlan_upper.sh \ router_bridge_vlan_upper_pvid.sh \ router_broadcast.sh \ - router_mpath_nh_res.sh \ router_mpath_nh.sh \ + router_mpath_nh_res.sh \ router_mpath_seed.sh \ router_multicast.sh \ router_multipath.sh \ router_nh.sh \ - router.sh \ router_vid_1.sh \ sch_ets.sh \ sch_red.sh \ @@ -88,32 +88,34 @@ TEST_PROGS = \ skbedit_priority.sh \ tc_actions.sh \ tc_chains.sh \ - tc_flower_router.sh \ tc_flower.sh \ - tc_flower_l2_miss.sh \ tc_flower_cfm.sh \ + tc_flower_l2_miss.sh \ tc_flower_port_range.sh \ + tc_flower_router.sh \ tc_mpls_l2vpn.sh \ tc_police.sh \ tc_shblocks.sh \ tc_tunnel_key.sh \ tc_vlan_modify.sh \ - vxlan_asymmetric_ipv6.sh \ vxlan_asymmetric.sh \ + vxlan_asymmetric_ipv6.sh \ + vxlan_bridge_1d.sh \ vxlan_bridge_1d_ipv6.sh \ - vxlan_bridge_1d_port_8472_ipv6.sh \ vxlan_bridge_1d_port_8472.sh \ - vxlan_bridge_1d.sh \ + vxlan_bridge_1d_port_8472_ipv6.sh \ + vxlan_bridge_1q.sh \ vxlan_bridge_1q_ipv6.sh \ vxlan_bridge_1q_mc_ul.sh \ - vxlan_bridge_1q_port_8472_ipv6.sh \ vxlan_bridge_1q_port_8472.sh \ - vxlan_bridge_1q.sh \ + vxlan_bridge_1q_port_8472_ipv6.sh \ vxlan_reserved.sh \ + vxlan_symmetric.sh \ vxlan_symmetric_ipv6.sh \ - vxlan_symmetric.sh +# end of TEST_PROGS -TEST_FILES := devlink_lib.sh \ +TEST_FILES := \ + devlink_lib.sh \ fib_offload_lib.sh \ forwarding.config.sample \ ip6gre_lib.sh \ @@ -128,10 +130,12 @@ TEST_FILES := devlink_lib.sh \ sch_ets_tests.sh \ sch_tbf_core.sh \ sch_tbf_etsprio.sh \ - tc_common.sh + tc_common.sh \ +# end of TEST_FILES TEST_INCLUDES := \ + $(wildcard ../lib/sh/*.sh) \ ../lib.sh \ - $(wildcard ../lib/sh/*.sh) +# end of TEST_INCLUDES include ../../lib.mk diff --git a/tools/testing/selftests/net/forwarding/config b/tools/testing/selftests/net/forwarding/config index 18fd69d8d937..ce64518aaa11 100644 --- a/tools/testing/selftests/net/forwarding/config +++ b/tools/testing/selftests/net/forwarding/config @@ -1,24 +1,23 @@ +CONFIG_BPF_SYSCALL=y CONFIG_BRIDGE=m -CONFIG_VLAN_8021Q=m -CONFIG_BRIDGE_VLAN_FILTERING=y CONFIG_BRIDGE_IGMP_SNOOPING=y -CONFIG_NET_L3_MASTER_DEV=y -CONFIG_IPV6_MULTIPLE_TABLES=y -CONFIG_NET_VRF=m -CONFIG_BPF_SYSCALL=y +CONFIG_BRIDGE_VLAN_FILTERING=y CONFIG_CGROUP_BPF=y CONFIG_DUMMY=m +CONFIG_IP_MROUTE=y +CONFIG_IP_MROUTE_MULTIPLE_TABLES=y +CONFIG_IP_PIMSM_V1=y +CONFIG_IP_PIMSM_V2=y CONFIG_IPV6=y CONFIG_IPV6_GRE=m CONFIG_IPV6_MROUTE=y CONFIG_IPV6_MROUTE_MULTIPLE_TABLES=y +CONFIG_IPV6_MULTIPLE_TABLES=y CONFIG_IPV6_PIMSM_V2=y -CONFIG_IP_MROUTE=y -CONFIG_IP_MROUTE_MULTIPLE_TABLES=y -CONFIG_IP_PIMSM_V1=y -CONFIG_IP_PIMSM_V2=y CONFIG_MACVLAN=m +CONFIG_NAMESPACES=y CONFIG_NET_ACT_CT=m +CONFIG_NET_ACT_GACT=m CONFIG_NET_ACT_MIRRED=m CONFIG_NET_ACT_MPLS=m CONFIG_NET_ACT_PEDIT=m @@ -27,29 +26,30 @@ CONFIG_NET_ACT_SAMPLE=m CONFIG_NET_ACT_SKBEDIT=m CONFIG_NET_ACT_TUNNEL_KEY=m CONFIG_NET_ACT_VLAN=m +CONFIG_NET_CLS_BASIC=m CONFIG_NET_CLS_FLOWER=m CONFIG_NET_CLS_MATCHALL=m -CONFIG_NET_CLS_BASIC=m CONFIG_NET_EMATCH=y CONFIG_NET_EMATCH_META=m +CONFIG_NETFILTER=y CONFIG_NET_IPGRE=m CONFIG_NET_IPGRE_DEMUX=m CONFIG_NET_IPIP=m +CONFIG_NET_L3_MASTER_DEV=y +CONFIG_NET_NS=y CONFIG_NET_SCH_ETS=m CONFIG_NET_SCH_INGRESS=m -CONFIG_NET_ACT_GACT=m CONFIG_NET_SCH_PRIO=m CONFIG_NET_SCH_RED=m CONFIG_NET_SCH_TBF=m CONFIG_NET_TC_SKB_EXT=y CONFIG_NET_TEAM=y CONFIG_NET_TEAM_MODE_LOADBALANCE=y -CONFIG_NETFILTER=y +CONFIG_NET_VRF=m CONFIG_NF_CONNTRACK=m CONFIG_NF_FLOW_TABLE=m CONFIG_NF_TABLES=m CONFIG_VETH=m -CONFIG_NAMESPACES=y -CONFIG_NET_NS=y +CONFIG_VLAN_8021Q=m CONFIG_VXLAN=m CONFIG_XFRM_USER=m diff --git a/tools/testing/selftests/net/hsr/Makefile b/tools/testing/selftests/net/hsr/Makefile index 884cd2cc0681..4b6afc0fe9f8 100644 --- a/tools/testing/selftests/net/hsr/Makefile +++ b/tools/testing/selftests/net/hsr/Makefile @@ -2,7 +2,11 @@ top_srcdir = ../../../../.. -TEST_PROGS := hsr_ping.sh hsr_redbox.sh +TEST_PROGS := \ + hsr_ping.sh \ + hsr_redbox.sh \ +# end of TEST_PROGS + TEST_FILES += hsr_common.sh include ../../lib.mk diff --git a/tools/testing/selftests/net/hsr/config b/tools/testing/selftests/net/hsr/config index 555a868743f0..205cc4d3d64b 100644 --- a/tools/testing/selftests/net/hsr/config +++ b/tools/testing/selftests/net/hsr/config @@ -1,6 +1,6 @@ +CONFIG_BRIDGE=y +CONFIG_HSR=y CONFIG_IPV6=y CONFIG_NET_SCH_NETEM=m -CONFIG_HSR=y CONFIG_VETH=y -CONFIG_BRIDGE=y CONFIG_VLAN_8021Q=m diff --git a/tools/testing/selftests/net/lib/Makefile b/tools/testing/selftests/net/lib/Makefile index 88c4bc461459..ce795bc0a1af 100644 --- a/tools/testing/selftests/net/lib/Makefile +++ b/tools/testing/selftests/net/lib/Makefile @@ -5,12 +5,16 @@ CFLAGS += -I../../../../../usr/include/ $(KHDR_INCLUDES) # Additional include paths needed by kselftest.h CFLAGS += -I../../ -TEST_FILES := ../../../../../Documentation/netlink/specs -TEST_FILES += ../../../../net/ynl +TEST_FILES := \ + ../../../../net/ynl \ + ../../../../../Documentation/netlink/specs \ +# end of TEST_FILES -TEST_GEN_FILES += csum -TEST_GEN_FILES += $(patsubst %.c,%.o,$(wildcard *.bpf.c)) -TEST_GEN_FILES += xdp_helper +TEST_GEN_FILES := \ + $(patsubst %.c,%.o,$(wildcard *.bpf.c)) \ + csum \ + xdp_helper \ +# end of TEST_GEN_FILES TEST_INCLUDES := $(wildcard py/*.py sh/*.sh) diff --git a/tools/testing/selftests/net/mptcp/Makefile b/tools/testing/selftests/net/mptcp/Makefile index 4c7e51336ab2..15d144a25d82 100644 --- a/tools/testing/selftests/net/mptcp/Makefile +++ b/tools/testing/selftests/net/mptcp/Makefile @@ -4,13 +4,31 @@ top_srcdir = ../../../../.. CFLAGS += -Wall -Wl,--no-as-needed -O2 -g -I$(top_srcdir)/usr/include $(KHDR_INCLUDES) -TEST_PROGS := mptcp_connect.sh mptcp_connect_mmap.sh mptcp_connect_sendfile.sh \ - mptcp_connect_checksum.sh pm_netlink.sh mptcp_join.sh diag.sh \ - simult_flows.sh mptcp_sockopt.sh userspace_pm.sh - -TEST_GEN_FILES = mptcp_connect pm_nl_ctl mptcp_sockopt mptcp_inq mptcp_diag - -TEST_FILES := mptcp_lib.sh settings +TEST_PROGS := \ + diag.sh \ + mptcp_connect.sh \ + mptcp_connect_checksum.sh \ + mptcp_connect_mmap.sh \ + mptcp_connect_sendfile.sh \ + mptcp_join.sh \ + mptcp_sockopt.sh \ + pm_netlink.sh \ + simult_flows.sh \ + userspace_pm.sh \ +# end of TEST_PROGS + +TEST_GEN_FILES := \ + mptcp_connect \ + mptcp_diag \ + mptcp_inq \ + mptcp_sockopt \ + pm_nl_ctl \ +# end of TEST_GEN_FILES + +TEST_FILES := \ + mptcp_lib.sh \ + settings \ +# end of TEST_FILES TEST_INCLUDES := ../lib.sh $(wildcard ../lib/sh/*.sh) diff --git a/tools/testing/selftests/net/mptcp/config b/tools/testing/selftests/net/mptcp/config index 968d440c03fe..59051ee2a986 100644 --- a/tools/testing/selftests/net/mptcp/config +++ b/tools/testing/selftests/net/mptcp/config @@ -1,36 +1,36 @@ +CONFIG_INET_DIAG=m +CONFIG_INET_MPTCP_DIAG=m +CONFIG_IP6_NF_FILTER=m +CONFIG_IP6_NF_TARGET_REJECT=m +CONFIG_IP_ADVANCED_ROUTER=y +CONFIG_IP_MULTIPLE_TABLES=y +CONFIG_IP_NF_FILTER=m +CONFIG_IP_NF_MANGLE=m +CONFIG_IP_NF_TARGET_REJECT=m +CONFIG_IPV6=y +CONFIG_IPV6_MULTIPLE_TABLES=y CONFIG_KALLSYMS=y CONFIG_MPTCP=y -CONFIG_IPV6=y CONFIG_MPTCP_IPV6=y -CONFIG_INET_DIAG=m -CONFIG_INET_MPTCP_DIAG=m -CONFIG_VETH=y -CONFIG_NET_SCH_NETEM=m -CONFIG_SYN_COOKIES=y +CONFIG_NET_ACT_CSUM=m +CONFIG_NET_ACT_PEDIT=m +CONFIG_NET_CLS_ACT=y +CONFIG_NET_CLS_FW=m CONFIG_NETFILTER=y CONFIG_NETFILTER_ADVANCED=y CONFIG_NETFILTER_NETLINK=m -CONFIG_NF_TABLES=m -CONFIG_NFT_COMPAT=m CONFIG_NETFILTER_XTABLES=m CONFIG_NETFILTER_XTABLES_LEGACY=y CONFIG_NETFILTER_XT_MATCH_BPF=m CONFIG_NETFILTER_XT_MATCH_LENGTH=m CONFIG_NETFILTER_XT_MATCH_STATISTIC=m CONFIG_NETFILTER_XT_TARGET_MARK=m +CONFIG_NET_SCH_INGRESS=m +CONFIG_NET_SCH_NETEM=m +CONFIG_NF_TABLES=m CONFIG_NF_TABLES_INET=y -CONFIG_NFT_TPROXY=m +CONFIG_NFT_COMPAT=m CONFIG_NFT_SOCKET=m -CONFIG_IP_ADVANCED_ROUTER=y -CONFIG_IP_MULTIPLE_TABLES=y -CONFIG_IP_NF_FILTER=m -CONFIG_IP_NF_MANGLE=m -CONFIG_IP_NF_TARGET_REJECT=m -CONFIG_IP6_NF_TARGET_REJECT=m -CONFIG_IPV6_MULTIPLE_TABLES=y -CONFIG_IP6_NF_FILTER=m -CONFIG_NET_ACT_CSUM=m -CONFIG_NET_ACT_PEDIT=m -CONFIG_NET_CLS_ACT=y -CONFIG_NET_CLS_FW=m -CONFIG_NET_SCH_INGRESS=m +CONFIG_NFT_TPROXY=m +CONFIG_SYN_COOKIES=y +CONFIG_VETH=y diff --git a/tools/testing/selftests/net/netfilter/Makefile b/tools/testing/selftests/net/netfilter/Makefile index a98ed892f55f..ee2d1a5254f8 100644 --- a/tools/testing/selftests/net/netfilter/Makefile +++ b/tools/testing/selftests/net/netfilter/Makefile @@ -6,46 +6,52 @@ HOSTPKG_CONFIG := pkg-config MNL_CFLAGS := $(shell $(HOSTPKG_CONFIG) --cflags libmnl 2>/dev/null) MNL_LDLIBS := $(shell $(HOSTPKG_CONFIG) --libs libmnl 2>/dev/null || echo -lmnl) -TEST_PROGS := br_netfilter.sh bridge_brouter.sh -TEST_PROGS += br_netfilter_queue.sh -TEST_PROGS += conntrack_dump_flush.sh -TEST_PROGS += conntrack_icmp_related.sh -TEST_PROGS += conntrack_ipip_mtu.sh -TEST_PROGS += conntrack_tcp_unreplied.sh -TEST_PROGS += conntrack_resize.sh -TEST_PROGS += conntrack_sctp_collision.sh -TEST_PROGS += conntrack_vrf.sh -TEST_PROGS += conntrack_clash.sh -TEST_PROGS += conntrack_reverse_clash.sh -TEST_PROGS += ipvs.sh -TEST_PROGS += nf_conntrack_packetdrill.sh -TEST_PROGS += nf_nat_edemux.sh -TEST_PROGS += nft_audit.sh -TEST_PROGS += nft_concat_range.sh -TEST_PROGS += nft_conntrack_helper.sh -TEST_PROGS += nft_fib.sh -TEST_PROGS += nft_flowtable.sh -TEST_PROGS += nft_interface_stress.sh -TEST_PROGS += nft_meta.sh -TEST_PROGS += nft_nat.sh -TEST_PROGS += nft_nat_zones.sh -TEST_PROGS += nft_queue.sh -TEST_PROGS += nft_synproxy.sh -TEST_PROGS += nft_tproxy_tcp.sh -TEST_PROGS += nft_tproxy_udp.sh -TEST_PROGS += nft_zones_many.sh -TEST_PROGS += rpath.sh -TEST_PROGS += vxlan_mtu_frag.sh -TEST_PROGS += xt_string.sh +TEST_PROGS := \ + br_netfilter.sh \ + br_netfilter_queue.sh \ + bridge_brouter.sh \ + conntrack_clash.sh \ + conntrack_dump_flush.sh \ + conntrack_icmp_related.sh \ + conntrack_ipip_mtu.sh \ + conntrack_resize.sh \ + conntrack_reverse_clash.sh \ + conntrack_sctp_collision.sh \ + conntrack_tcp_unreplied.sh \ + conntrack_vrf.sh \ + ipvs.sh \ + nf_conntrack_packetdrill.sh \ + nf_nat_edemux.sh \ + nft_audit.sh \ + nft_concat_range.sh \ + nft_conntrack_helper.sh \ + nft_fib.sh \ + nft_flowtable.sh \ + nft_interface_stress.sh \ + nft_meta.sh \ + nft_nat.sh \ + nft_nat_zones.sh \ + nft_queue.sh \ + nft_synproxy.sh \ + nft_tproxy_tcp.sh \ + nft_tproxy_udp.sh \ + nft_zones_many.sh \ + rpath.sh \ + vxlan_mtu_frag.sh \ + xt_string.sh \ +# end of TEST_PROGS TEST_PROGS_EXTENDED = nft_concat_range_perf.sh -TEST_GEN_FILES = audit_logread -TEST_GEN_FILES += connect_close nf_queue -TEST_GEN_FILES += conntrack_dump_flush -TEST_GEN_FILES += conntrack_reverse_clash -TEST_GEN_FILES += sctp_collision -TEST_GEN_FILES += udpclash +TEST_GEN_FILES = \ + audit_logread \ + connect_close \ + conntrack_dump_flush \ + conntrack_reverse_clash \ + nf_queue \ + sctp_collision \ + udpclash \ +# end of TEST_GEN_FILES include ../../lib.mk @@ -56,9 +62,12 @@ $(OUTPUT)/conntrack_dump_flush: CFLAGS += $(MNL_CFLAGS) $(OUTPUT)/conntrack_dump_flush: LDLIBS += $(MNL_LDLIBS) $(OUTPUT)/udpclash: LDLIBS += -lpthread -TEST_FILES := lib.sh -TEST_FILES += packetdrill +TEST_FILES := \ + lib.sh \ + packetdrill \ +# end of TEST_FILES TEST_INCLUDES := \ + $(wildcard ../lib/sh/*.sh) \ ../lib.sh \ - $(wildcard ../lib/sh/*.sh) +# end of TEST_INCLUDES diff --git a/tools/testing/selftests/net/netfilter/config b/tools/testing/selftests/net/netfilter/config index 305e46b819cb..12ce61fa15a8 100644 --- a/tools/testing/selftests/net/netfilter/config +++ b/tools/testing/selftests/net/netfilter/config @@ -1,77 +1,80 @@ CONFIG_AUDIT=y CONFIG_BPF_SYSCALL=y CONFIG_BRIDGE=m -CONFIG_NETFILTER_XTABLES_LEGACY=y -CONFIG_BRIDGE_NF_EBTABLES_LEGACY=m CONFIG_BRIDGE_EBT_BROUTE=m CONFIG_BRIDGE_EBT_IP=m CONFIG_BRIDGE_EBT_REDIRECT=m CONFIG_BRIDGE_EBT_T_FILTER=m CONFIG_BRIDGE_NETFILTER=m CONFIG_BRIDGE_NF_EBTABLES=m +CONFIG_BRIDGE_NF_EBTABLES_LEGACY=m CONFIG_BRIDGE_VLAN_FILTERING=y CONFIG_CGROUP_BPF=y +CONFIG_CRYPTO_SHA1=m CONFIG_DUMMY=m +CONFIG_INET_DIAG=m CONFIG_INET_ESP=m -CONFIG_CRYPTO_SHA1=m -CONFIG_IP_NF_MATCH_RPFILTER=m +CONFIG_INET_SCTP_DIAG=m +CONFIG_IP6_NF_FILTER=m +CONFIG_IP6_NF_IPTABLES=m +CONFIG_IP6_NF_IPTABLES_LEGACY=m CONFIG_IP6_NF_MATCH_RPFILTER=m +CONFIG_IP6_NF_RAW=m +CONFIG_IP_NF_FILTER=m CONFIG_IP_NF_IPTABLES=m CONFIG_IP_NF_IPTABLES_LEGACY=m -CONFIG_IP6_NF_IPTABLES=m -CONFIG_IP6_NF_IPTABLES_LEGACY=m +CONFIG_IP_NF_MATCH_RPFILTER=m CONFIG_IP_NF_NAT=m -CONFIG_IP_NF_FILTER=m -CONFIG_IP6_NF_FILTER=m CONFIG_IP_NF_RAW=m -CONFIG_IP6_NF_RAW=m CONFIG_IP_SCTP=m +CONFIG_IPV6=y +CONFIG_IPV6_MULTIPLE_TABLES=y CONFIG_IP_VS=m CONFIG_IP_VS_PROTO_TCP=y CONFIG_IP_VS_RR=m -CONFIG_IPV6=y -CONFIG_IPV6_MULTIPLE_TABLES=y CONFIG_MACVLAN=m CONFIG_NAMESPACES=y CONFIG_NET_CLS_U32=m -CONFIG_NET_L3_MASTER_DEV=y -CONFIG_NET_NS=y -CONFIG_NET_SCH_NETEM=m -CONFIG_NET_SCH_HTB=m -CONFIG_NET_IPIP=m -CONFIG_NET_VRF=y CONFIG_NETFILTER=y CONFIG_NETFILTER_ADVANCED=y CONFIG_NETFILTER_NETLINK=m CONFIG_NETFILTER_NETLINK_QUEUE=m CONFIG_NETFILTER_SYNPROXY=m CONFIG_NETFILTER_XTABLES=m -CONFIG_NETFILTER_XT_NAT=m +CONFIG_NETFILTER_XTABLES_LEGACY=y CONFIG_NETFILTER_XT_MATCH_CONNTRACK=m CONFIG_NETFILTER_XT_MATCH_STATE=m CONFIG_NETFILTER_XT_MATCH_STRING=m +CONFIG_NETFILTER_XT_NAT=m CONFIG_NETFILTER_XT_TARGET_REDIRECT=m +CONFIG_NET_IPIP=m +CONFIG_NET_L3_MASTER_DEV=y +CONFIG_NET_NS=y +CONFIG_NET_PKTGEN=m +CONFIG_NET_SCH_HTB=m +CONFIG_NET_SCH_NETEM=m +CONFIG_NET_VRF=y CONFIG_NF_CONNTRACK=m -CONFIG_NF_CONNTRACK_PROCFS=y CONFIG_NF_CONNTRACK_EVENTS=y CONFIG_NF_CONNTRACK_FTP=m CONFIG_NF_CONNTRACK_MARK=y +CONFIG_NF_CONNTRACK_PROCFS=y CONFIG_NF_CONNTRACK_ZONES=y CONFIG_NF_CT_NETLINK=m CONFIG_NF_CT_PROTO_SCTP=y CONFIG_NF_FLOW_TABLE=m +CONFIG_NF_FLOW_TABLE_INET=m CONFIG_NF_LOG_IPV4=m CONFIG_NF_LOG_IPV6=m CONFIG_NF_NAT=m -CONFIG_NF_NAT_REDIRECT=y CONFIG_NF_NAT_MASQUERADE=y +CONFIG_NF_NAT_REDIRECT=y CONFIG_NF_TABLES=m CONFIG_NF_TABLES_BRIDGE=m CONFIG_NF_TABLES_INET=y CONFIG_NF_TABLES_IPV4=y CONFIG_NF_TABLES_IPV6=y CONFIG_NF_TABLES_NETDEV=y -CONFIG_NF_FLOW_TABLE_INET=m CONFIG_NFT_BRIDGE_META=m CONFIG_NFT_COMPAT=m CONFIG_NFT_CT=m @@ -90,12 +93,9 @@ CONFIG_NFT_QUOTA=m CONFIG_NFT_REDIR=m CONFIG_NFT_SYNPROXY=m CONFIG_NFT_TPROXY=m +CONFIG_TUN=m CONFIG_VETH=m CONFIG_VLAN_8021Q=m CONFIG_VXLAN=m -CONFIG_XFRM_USER=m CONFIG_XFRM_STATISTICS=y -CONFIG_NET_PKTGEN=m -CONFIG_TUN=m -CONFIG_INET_DIAG=m -CONFIG_INET_SCTP_DIAG=m +CONFIG_XFRM_USER=m diff --git a/tools/testing/selftests/net/netfilter/nf_nat_edemux.sh b/tools/testing/selftests/net/netfilter/nf_nat_edemux.sh index 1014551dd769..6731fe1eaf2e 100755 --- a/tools/testing/selftests/net/netfilter/nf_nat_edemux.sh +++ b/tools/testing/selftests/net/netfilter/nf_nat_edemux.sh @@ -17,9 +17,31 @@ cleanup() checktool "socat -h" "run test without socat" checktool "iptables --version" "run test without iptables" +checktool "conntrack --version" "run test without conntrack" trap cleanup EXIT +connect_done() +{ + local ns="$1" + local port="$2" + + ip netns exec "$ns" ss -nt -o state established "dport = :$port" | grep -q "$port" +} + +check_ctstate() +{ + local ns="$1" + local dp="$2" + + if ! ip netns exec "$ns" conntrack --get -s 192.168.1.2 -d 192.168.1.1 -p tcp \ + --sport 10000 --dport "$dp" --state ESTABLISHED > /dev/null 2>&1;then + echo "FAIL: Did not find expected state for dport $2" + ip netns exec "$ns" bash -c 'conntrack -L; conntrack -S; ss -nt' + ret=1 + fi +} + setup_ns ns1 ns2 # Connect the namespaces using a veth pair @@ -44,15 +66,18 @@ socatpid=$! ip netns exec "$ns2" sysctl -q net.ipv4.ip_local_port_range="10000 10000" # add a virtual IP using DNAT -ip netns exec "$ns2" iptables -t nat -A OUTPUT -d 10.96.0.1/32 -p tcp --dport 443 -j DNAT --to-destination 192.168.1.1:5201 +ip netns exec "$ns2" iptables -t nat -A OUTPUT -d 10.96.0.1/32 -p tcp --dport 443 -j DNAT --to-destination 192.168.1.1:5201 || exit 1 # ... and route it to the other namespace ip netns exec "$ns2" ip route add 10.96.0.1 via 192.168.1.1 -# add a persistent connection from the other namespace -ip netns exec "$ns2" socat -t 10 - TCP:192.168.1.1:5201 > /dev/null & +# listener should be up by now, wait if it isn't yet. +wait_local_port_listen "$ns1" 5201 tcp -sleep 1 +# add a persistent connection from the other namespace +sleep 10 | ip netns exec "$ns2" socat -t 10 - TCP:192.168.1.1:5201 > /dev/null & +cpid0=$! +busywait "$BUSYWAIT_TIMEOUT" connect_done "$ns2" "5201" # ip daddr:dport will be rewritten to 192.168.1.1 5201 # NAT must reallocate source port 10000 because @@ -71,26 +96,25 @@ fi ip netns exec "$ns1" iptables -t nat -A PREROUTING -p tcp --dport 5202 -j REDIRECT --to-ports 5201 ip netns exec "$ns1" iptables -t nat -A PREROUTING -p tcp --dport 5203 -j REDIRECT --to-ports 5201 -sleep 5 | ip netns exec "$ns2" socat -t 5 -u STDIN TCP:192.168.1.1:5202,connect-timeout=5 >/dev/null & +sleep 5 | ip netns exec "$ns2" socat -T 5 -u STDIN TCP:192.168.1.1:5202,connect-timeout=5 >/dev/null & +cpid1=$! -# if connect succeeds, client closes instantly due to EOF on stdin. -# if connect hangs, it will time out after 5s. -echo | ip netns exec "$ns2" socat -t 3 -u STDIN TCP:192.168.1.1:5203,connect-timeout=5 >/dev/null & +sleep 5 | ip netns exec "$ns2" socat -T 5 -u STDIN TCP:192.168.1.1:5203,connect-timeout=5 >/dev/null & cpid2=$! -time_then=$(date +%s) -wait $cpid2 -rv=$? -time_now=$(date +%s) +busywait "$BUSYWAIT_TIMEOUT" connect_done "$ns2" 5202 +busywait "$BUSYWAIT_TIMEOUT" connect_done "$ns2" 5203 -# Check how much time has elapsed, expectation is for -# 'cpid2' to connect and then exit (and no connect delay). -delta=$((time_now - time_then)) +check_ctstate "$ns1" 5202 +check_ctstate "$ns1" 5203 -if [ $delta -lt 2 ] && [ $rv -eq 0 ]; then +kill $socatpid $cpid0 $cpid1 $cpid2 +socatpid=0 + +if [ $ret -eq 0 ]; then echo "PASS: could connect to service via redirected ports" else - echo "FAIL: socat cannot connect to service via redirect ($delta seconds elapsed, returned $rv)" + echo "FAIL: socat cannot connect to service via redirect" ret=1 fi diff --git a/tools/testing/selftests/net/netfilter/nft_fib.sh b/tools/testing/selftests/net/netfilter/nft_fib.sh index 9929a9ffef65..04544905c216 100755 --- a/tools/testing/selftests/net/netfilter/nft_fib.sh +++ b/tools/testing/selftests/net/netfilter/nft_fib.sh @@ -256,12 +256,12 @@ test_ping_unreachable() { local daddr4=$1 local daddr6=$2 - if ip netns exec "$ns1" ping -c 1 -w 1 -q "$daddr4" > /dev/null; then + if ip netns exec "$ns1" ping -c 1 -W 0.1 -q "$daddr4" > /dev/null; then echo "FAIL: ${ns1} could reach $daddr4" 1>&2 return 1 fi - if ip netns exec "$ns1" ping -c 1 -w 1 -q "$daddr6" > /dev/null; then + if ip netns exec "$ns1" ping -c 1 -W 0.1 -q "$daddr6" > /dev/null; then echo "FAIL: ${ns1} could reach $daddr6" 1>&2 return 1 fi @@ -437,14 +437,17 @@ check_type() local addr="$3" local type="$4" local count="$5" + local lret=0 [ -z "$count" ] && count=1 if ! ip netns exec "$nsrouter" nft get element inet t "$setname" { "$iifname" . "$addr" . "$type" } |grep -q "counter packets $count";then - echo "FAIL: did not find $iifname . $addr . $type in $setname" + echo "FAIL: did not find $iifname . $addr . $type in $setname with $count packets" ip netns exec "$nsrouter" nft list set inet t "$setname" ret=1 - return 1 + # do not fail right away, delete entry if it exists so later test that + # checks for unwanted keys don't get confused by this *expected* key. + lret=1 fi # delete the entry, this allows to check if anything unexpected appeared @@ -456,7 +459,7 @@ check_type() return 1 fi - return 0 + return $lret } check_local() diff --git a/tools/testing/selftests/net/ovpn/Makefile b/tools/testing/selftests/net/ovpn/Makefile index e0926d76b4c8..dbe0388c8512 100644 --- a/tools/testing/selftests/net/ovpn/Makefile +++ b/tools/testing/selftests/net/ovpn/Makefile @@ -19,13 +19,15 @@ LDLIBS += $(VAR_LDLIBS) TEST_FILES = common.sh -TEST_PROGS = test.sh \ - test-large-mtu.sh \ +TEST_PROGS := \ test-chachapoly.sh \ - test-tcp.sh \ - test-float.sh \ + test-close-socket-tcp.sh \ test-close-socket.sh \ - test-close-socket-tcp.sh + test-float.sh \ + test-large-mtu.sh \ + test-tcp.sh \ + test.sh \ +# end of TEST_PROGS TEST_GEN_FILES := ovpn-cli diff --git a/tools/testing/selftests/net/ovpn/config b/tools/testing/selftests/net/ovpn/config index 71946ba9fa17..42699740936d 100644 --- a/tools/testing/selftests/net/ovpn/config +++ b/tools/testing/selftests/net/ovpn/config @@ -1,10 +1,10 @@ -CONFIG_NET=y -CONFIG_INET=y -CONFIG_STREAM_PARSER=y -CONFIG_NET_UDP_TUNNEL=y -CONFIG_DST_CACHE=y CONFIG_CRYPTO=y CONFIG_CRYPTO_AES=y -CONFIG_CRYPTO_GCM=y CONFIG_CRYPTO_CHACHA20POLY1305=y +CONFIG_CRYPTO_GCM=y +CONFIG_DST_CACHE=y +CONFIG_INET=y +CONFIG_NET=y +CONFIG_NET_UDP_TUNNEL=y CONFIG_OVPN=m +CONFIG_STREAM_PARSER=y diff --git a/tools/testing/selftests/net/ovpn/ovpn-cli.c b/tools/testing/selftests/net/ovpn/ovpn-cli.c index 688a5fa6fdac..0a5226196a2e 100644 --- a/tools/testing/selftests/net/ovpn/ovpn-cli.c +++ b/tools/testing/selftests/net/ovpn/ovpn-cli.c @@ -1587,6 +1587,7 @@ static int ovpn_listen_mcast(void) sock = nl_socket_alloc(); if (!sock) { fprintf(stderr, "cannot allocate netlink socket\n"); + ret = -ENOMEM; goto err_free; } @@ -2106,6 +2107,7 @@ static int ovpn_run_cmd(struct ovpn_ctx *ovpn) ret = ovpn_listen_mcast(); break; case CMD_INVALID: + ret = -EINVAL; break; } diff --git a/tools/testing/selftests/net/packetdrill/Makefile b/tools/testing/selftests/net/packetdrill/Makefile index 31cfb666ba8b..ff54641493e9 100644 --- a/tools/testing/selftests/net/packetdrill/Makefile +++ b/tools/testing/selftests/net/packetdrill/Makefile @@ -1,9 +1,11 @@ # SPDX-License-Identifier: GPL-2.0 -TEST_INCLUDES := ksft_runner.sh \ - defaults.sh \ - set_sysctls.py \ - ../../kselftest/ktap_helpers.sh +TEST_INCLUDES := \ + defaults.sh \ + ksft_runner.sh \ + set_sysctls.py \ + ../../kselftest/ktap_helpers.sh \ +# end of TEST_INCLUDES TEST_PROGS := $(wildcard *.pkt) diff --git a/tools/testing/selftests/net/packetdrill/config b/tools/testing/selftests/net/packetdrill/config index 0237ed98f3c0..c4a19a785521 100644 --- a/tools/testing/selftests/net/packetdrill/config +++ b/tools/testing/selftests/net/packetdrill/config @@ -1,6 +1,6 @@ -CONFIG_IPV6=y -CONFIG_HZ_1000=y CONFIG_HZ=1000 +CONFIG_HZ_1000=y +CONFIG_IPV6=y CONFIG_NET_NS=y CONFIG_NET_SCH_FIFO=y CONFIG_NET_SCH_FQ=y diff --git a/tools/testing/selftests/net/rds/Makefile b/tools/testing/selftests/net/rds/Makefile index 612a7219990e..762845cc973c 100644 --- a/tools/testing/selftests/net/rds/Makefile +++ b/tools/testing/selftests/net/rds/Makefile @@ -5,8 +5,14 @@ all: TEST_PROGS := run.sh -TEST_FILES := include.sh test.py +TEST_FILES := \ + include.sh \ + test.py \ +# end of TEST_FILES -EXTRA_CLEAN := /tmp/rds_logs include.sh +EXTRA_CLEAN := \ + include.sh \ + /tmp/rds_logs \ +# end of EXTRA_CLEAN include ../../lib.mk diff --git a/tools/testing/selftests/net/tcp_ao/config b/tools/testing/selftests/net/tcp_ao/config index 3605e38711cb..971cb6fa2d63 100644 --- a/tools/testing/selftests/net/tcp_ao/config +++ b/tools/testing/selftests/net/tcp_ao/config @@ -1,8 +1,8 @@ CONFIG_CRYPTO_HMAC=y CONFIG_CRYPTO_RMD160=y CONFIG_CRYPTO_SHA1=y -CONFIG_IPV6_MULTIPLE_TABLES=y CONFIG_IPV6=y +CONFIG_IPV6_MULTIPLE_TABLES=y CONFIG_NET_L3_MASTER_DEV=y CONFIG_NET_VRF=y CONFIG_TCP_AO=y diff --git a/tools/testing/selftests/pci_endpoint/pci_endpoint_test.c b/tools/testing/selftests/pci_endpoint/pci_endpoint_test.c index da0db0e7c969..cd9075444c32 100644 --- a/tools/testing/selftests/pci_endpoint/pci_endpoint_test.c +++ b/tools/testing/selftests/pci_endpoint/pci_endpoint_test.c @@ -121,6 +121,8 @@ TEST_F(pci_ep_basic, MSI_TEST) for (i = 1; i <= 32; i++) { pci_ep_ioctl(PCITEST_MSI, i); + if (ret == -EINVAL) + SKIP(return, "MSI%d is disabled", i); EXPECT_FALSE(ret) TH_LOG("Test failed for MSI%d", i); } } @@ -137,6 +139,8 @@ TEST_F(pci_ep_basic, MSIX_TEST) for (i = 1; i <= 2048; i++) { pci_ep_ioctl(PCITEST_MSIX, i); + if (ret == -EINVAL) + SKIP(return, "MSI-X%d is disabled", i); EXPECT_FALSE(ret) TH_LOG("Test failed for MSI-X%d", i); } } diff --git a/tools/testing/selftests/rcutorture/bin/jitter.sh b/tools/testing/selftests/rcutorture/bin/jitter.sh index fd1ffaa5a135..3c1e5d3f8805 100755 --- a/tools/testing/selftests/rcutorture/bin/jitter.sh +++ b/tools/testing/selftests/rcutorture/bin/jitter.sh @@ -39,6 +39,22 @@ do fi done +# Uses global variables startsecs, startns, endsecs, endns, and limit. +# Exit code is success for time not yet elapsed and failure otherwise. +function timecheck { + local done=`awk -v limit=$limit \ + -v startsecs=$startsecs \ + -v startns=$startns \ + -v endsecs=$endsecs \ + -v endns=$endns < /dev/null ' + BEGIN { + delta = (endsecs - startsecs) * 1000 * 1000; + delta += int((endns - startns) / 1000); + print delta >= limit; + }'` + return $done +} + while : do # Check for done. @@ -85,15 +101,20 @@ do n=$(($n+1)) sleep .$sleeptime - # Spin a random duration + # Spin a random duration, but with rather coarse granularity. limit=`awk -v me=$me -v n=$n -v spinmax=$spinmax 'BEGIN { srand(n + me + systime()); printf("%06d", int(rand() * spinmax)); }' < /dev/null` n=$(($n+1)) - for i in {1..$limit} + startsecs=`date +%s` + startns=`date +%N` + endsecs=$startns + endns=$endns + while timecheck do - echo > /dev/null + endsecs=`date +%s` + endns=`date +%N` done done diff --git a/tools/testing/selftests/rcutorture/bin/torture.sh b/tools/testing/selftests/rcutorture/bin/torture.sh index 611bc03a8dc7..a33ba109ef0b 100755 --- a/tools/testing/selftests/rcutorture/bin/torture.sh +++ b/tools/testing/selftests/rcutorture/bin/torture.sh @@ -94,6 +94,7 @@ usage () { echo " --do-kvfree / --do-no-kvfree / --no-kvfree" echo " --do-locktorture / --do-no-locktorture / --no-locktorture" echo " --do-none" + echo " --do-normal / --do-no-normal / --no-normal" echo " --do-rcuscale / --do-no-rcuscale / --no-rcuscale" echo " --do-rcutasksflavors / --do-no-rcutasksflavors / --no-rcutasksflavors" echo " --do-rcutorture / --do-no-rcutorture / --no-rcutorture" diff --git a/tools/testing/selftests/rseq/rseq-riscv.h b/tools/testing/selftests/rseq/rseq-riscv.h index 67d544aaa9a3..06c840e81c8b 100644 --- a/tools/testing/selftests/rseq/rseq-riscv.h +++ b/tools/testing/selftests/rseq/rseq-riscv.h @@ -8,6 +8,7 @@ * exception when executed in all modes. */ #include <endian.h> +#include <asm/fence.h> #if defined(__BYTE_ORDER) ? (__BYTE_ORDER == __LITTLE_ENDIAN) : defined(__LITTLE_ENDIAN) #define RSEQ_SIG 0xf1401073 /* csrr mhartid, x0 */ @@ -24,8 +25,6 @@ #define REG_L __REG_SEL("ld ", "lw ") #define REG_S __REG_SEL("sd ", "sw ") -#define RISCV_FENCE(p, s) \ - __asm__ __volatile__ ("fence " #p "," #s : : : "memory") #define rseq_smp_mb() RISCV_FENCE(rw, rw) #define rseq_smp_rmb() RISCV_FENCE(r, r) #define rseq_smp_wmb() RISCV_FENCE(w, w) diff --git a/tools/testing/selftests/vfio/.gitignore b/tools/testing/selftests/vfio/.gitignore new file mode 100644 index 000000000000..7fadc19d3bca --- /dev/null +++ b/tools/testing/selftests/vfio/.gitignore @@ -0,0 +1,10 @@ +# SPDX-License-Identifier: GPL-2.0-only +* +!/**/ +!*.c +!*.h +!*.S +!*.sh +!*.mk +!.gitignore +!Makefile diff --git a/tools/testing/selftests/vfio/Makefile b/tools/testing/selftests/vfio/Makefile new file mode 100644 index 000000000000..324ba0175a33 --- /dev/null +++ b/tools/testing/selftests/vfio/Makefile @@ -0,0 +1,21 @@ +CFLAGS = $(KHDR_INCLUDES) +TEST_GEN_PROGS += vfio_dma_mapping_test +TEST_GEN_PROGS += vfio_iommufd_setup_test +TEST_GEN_PROGS += vfio_pci_device_test +TEST_GEN_PROGS += vfio_pci_driver_test +TEST_PROGS_EXTENDED := run.sh +include ../lib.mk +include lib/libvfio.mk + +CFLAGS += -I$(top_srcdir)/tools/include +CFLAGS += -MD +CFLAGS += $(EXTRA_CFLAGS) + +$(TEST_GEN_PROGS): %: %.o $(LIBVFIO_O) + $(CC) $(CFLAGS) $(CPPFLAGS) $(LDFLAGS) $< $(LIBVFIO_O) $(LDLIBS) -o $@ + +TEST_GEN_PROGS_O = $(patsubst %, %.o, $(TEST_GEN_PROGS)) +TEST_DEP_FILES = $(patsubst %.o, %.d, $(TEST_GEN_PROGS_O) $(LIBVFIO_O)) +-include $(TEST_DEP_FILES) + +EXTRA_CLEAN += $(TEST_GEN_PROGS_O) $(TEST_DEP_FILES) diff --git a/tools/testing/selftests/vfio/lib/drivers/dsa/dsa.c b/tools/testing/selftests/vfio/lib/drivers/dsa/dsa.c new file mode 100644 index 000000000000..0ca2cbc2a316 --- /dev/null +++ b/tools/testing/selftests/vfio/lib/drivers/dsa/dsa.c @@ -0,0 +1,416 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include <stdint.h> +#include <unistd.h> + +#include <linux/bits.h> +#include <linux/errno.h> +#include <linux/idxd.h> +#include <linux/io.h> +#include <linux/pci_ids.h> +#include <linux/sizes.h> + +#include <vfio_util.h> + +#include "registers.h" + +/* Vectors 1+ are available for work queue completion interrupts. */ +#define MSIX_VECTOR 1 + +struct dsa_state { + /* Descriptors for copy and batch operations. */ + struct dsa_hw_desc batch[32]; + struct dsa_hw_desc copy[1024]; + + /* Completion records for copy and batch operations. */ + struct dsa_completion_record copy_completion; + struct dsa_completion_record batch_completion; + + /* Cached device registers (and derived data) for easy access */ + union gen_cap_reg gen_cap; + union wq_cap_reg wq_cap; + union group_cap_reg group_cap; + union engine_cap_reg engine_cap; + union offsets_reg table_offsets; + void *wqcfg_table; + void *grpcfg_table; + u64 max_batches; + u64 max_copies_per_batch; + + /* The number of ongoing memcpy operations. */ + u64 memcpy_count; + + /* Buffers used by dsa_send_msi() to generate an interrupt */ + u64 send_msi_src; + u64 send_msi_dst; +}; + +static inline struct dsa_state *to_dsa_state(struct vfio_pci_device *device) +{ + return device->driver.region.vaddr; +} + +static bool dsa_int_handle_request_required(struct vfio_pci_device *device) +{ + void *bar0 = device->bars[0].vaddr; + union gen_cap_reg gen_cap; + u32 cmd_cap; + + gen_cap.bits = readq(bar0 + IDXD_GENCAP_OFFSET); + if (!gen_cap.cmd_cap) + return false; + + cmd_cap = readl(bar0 + IDXD_CMDCAP_OFFSET); + return (cmd_cap >> IDXD_CMD_REQUEST_INT_HANDLE) & 1; +} + +static int dsa_probe(struct vfio_pci_device *device) +{ + if (!vfio_pci_device_match(device, PCI_VENDOR_ID_INTEL, + PCI_DEVICE_ID_INTEL_DSA_SPR0)) + return -EINVAL; + + if (dsa_int_handle_request_required(device)) { + printf("Device requires requesting interrupt handles\n"); + return -EINVAL; + } + + return 0; +} + +static void dsa_check_sw_err(struct vfio_pci_device *device) +{ + void *reg = device->bars[0].vaddr + IDXD_SWERR_OFFSET; + union sw_err_reg err = {}; + int i; + + for (i = 0; i < ARRAY_SIZE(err.bits); i++) { + err.bits[i] = readq(reg + offsetof(union sw_err_reg, bits[i])); + + /* No errors */ + if (i == 0 && !err.valid) + return; + } + + fprintf(stderr, "SWERR: 0x%016lx 0x%016lx 0x%016lx 0x%016lx\n", + err.bits[0], err.bits[1], err.bits[2], err.bits[3]); + + fprintf(stderr, " valid: 0x%x\n", err.valid); + fprintf(stderr, " overflow: 0x%x\n", err.overflow); + fprintf(stderr, " desc_valid: 0x%x\n", err.desc_valid); + fprintf(stderr, " wq_idx_valid: 0x%x\n", err.wq_idx_valid); + fprintf(stderr, " batch: 0x%x\n", err.batch); + fprintf(stderr, " fault_rw: 0x%x\n", err.fault_rw); + fprintf(stderr, " priv: 0x%x\n", err.priv); + fprintf(stderr, " error: 0x%x\n", err.error); + fprintf(stderr, " wq_idx: 0x%x\n", err.wq_idx); + fprintf(stderr, " operation: 0x%x\n", err.operation); + fprintf(stderr, " pasid: 0x%x\n", err.pasid); + fprintf(stderr, " batch_idx: 0x%x\n", err.batch_idx); + fprintf(stderr, " invalid_flags: 0x%x\n", err.invalid_flags); + fprintf(stderr, " fault_addr: 0x%lx\n", err.fault_addr); + + VFIO_FAIL("Software Error Detected!\n"); +} + +static void dsa_command(struct vfio_pci_device *device, u32 cmd) +{ + union idxd_command_reg cmd_reg = { .cmd = cmd }; + u32 sleep_ms = 1, attempts = 5000 / sleep_ms; + void *bar0 = device->bars[0].vaddr; + u32 status; + u8 err; + + writel(cmd_reg.bits, bar0 + IDXD_CMD_OFFSET); + + for (;;) { + dsa_check_sw_err(device); + + status = readl(bar0 + IDXD_CMDSTS_OFFSET); + if (!(status & IDXD_CMDSTS_ACTIVE)) + break; + + VFIO_ASSERT_GT(--attempts, 0); + usleep(sleep_ms * 1000); + } + + err = status & IDXD_CMDSTS_ERR_MASK; + VFIO_ASSERT_EQ(err, 0, "Error issuing command 0x%x: 0x%x\n", cmd, err); +} + +static void dsa_wq_init(struct vfio_pci_device *device) +{ + struct dsa_state *dsa = to_dsa_state(device); + union wq_cap_reg wq_cap = dsa->wq_cap; + union wqcfg wqcfg; + u64 wqcfg_size; + int i; + + VFIO_ASSERT_GT((u32)wq_cap.num_wqs, 0); + + wqcfg = (union wqcfg) { + .wq_size = wq_cap.total_wq_size, + .mode = 1, + .priority = 1, + /* + * Disable Address Translation Service (if enabled) so that VFIO + * selftests using this driver can generate I/O page faults. + */ + .wq_ats_disable = wq_cap.wq_ats_support, + .max_xfer_shift = dsa->gen_cap.max_xfer_shift, + .max_batch_shift = dsa->gen_cap.max_batch_shift, + .op_config[0] = BIT(DSA_OPCODE_MEMMOVE) | BIT(DSA_OPCODE_BATCH), + }; + + wqcfg_size = 1UL << (wq_cap.wqcfg_size + IDXD_WQCFG_MIN); + + for (i = 0; i < wqcfg_size / sizeof(wqcfg.bits[0]); i++) + writel(wqcfg.bits[i], dsa->wqcfg_table + offsetof(union wqcfg, bits[i])); +} + +static void dsa_group_init(struct vfio_pci_device *device) +{ + struct dsa_state *dsa = to_dsa_state(device); + union group_cap_reg group_cap = dsa->group_cap; + union engine_cap_reg engine_cap = dsa->engine_cap; + + VFIO_ASSERT_GT((u32)group_cap.num_groups, 0); + VFIO_ASSERT_GT((u32)engine_cap.num_engines, 0); + + /* Assign work queue 0 and engine 0 to group 0 */ + writeq(1, dsa->grpcfg_table + offsetof(struct grpcfg, wqs[0])); + writeq(1, dsa->grpcfg_table + offsetof(struct grpcfg, engines)); +} + +static void dsa_register_cache_init(struct vfio_pci_device *device) +{ + struct dsa_state *dsa = to_dsa_state(device); + void *bar0 = device->bars[0].vaddr; + + dsa->gen_cap.bits = readq(bar0 + IDXD_GENCAP_OFFSET); + dsa->wq_cap.bits = readq(bar0 + IDXD_WQCAP_OFFSET); + dsa->group_cap.bits = readq(bar0 + IDXD_GRPCAP_OFFSET); + dsa->engine_cap.bits = readq(bar0 + IDXD_ENGCAP_OFFSET); + + dsa->table_offsets.bits[0] = readq(bar0 + IDXD_TABLE_OFFSET); + dsa->table_offsets.bits[1] = readq(bar0 + IDXD_TABLE_OFFSET + 8); + + dsa->wqcfg_table = bar0 + dsa->table_offsets.wqcfg * IDXD_TABLE_MULT; + dsa->grpcfg_table = bar0 + dsa->table_offsets.grpcfg * IDXD_TABLE_MULT; + + dsa->max_batches = 1U << (dsa->wq_cap.total_wq_size + IDXD_WQCFG_MIN); + dsa->max_batches = min(dsa->max_batches, ARRAY_SIZE(dsa->batch)); + + dsa->max_copies_per_batch = 1UL << dsa->gen_cap.max_batch_shift; + dsa->max_copies_per_batch = min(dsa->max_copies_per_batch, ARRAY_SIZE(dsa->copy)); +} + +static void dsa_init(struct vfio_pci_device *device) +{ + struct dsa_state *dsa = to_dsa_state(device); + + VFIO_ASSERT_GE(device->driver.region.size, sizeof(*dsa)); + + vfio_pci_config_writew(device, PCI_COMMAND, + PCI_COMMAND_MEMORY | + PCI_COMMAND_MASTER | + PCI_COMMAND_INTX_DISABLE); + + dsa_command(device, IDXD_CMD_RESET_DEVICE); + + dsa_register_cache_init(device); + dsa_wq_init(device); + dsa_group_init(device); + + dsa_command(device, IDXD_CMD_ENABLE_DEVICE); + dsa_command(device, IDXD_CMD_ENABLE_WQ); + + vfio_pci_msix_enable(device, MSIX_VECTOR, 1); + + device->driver.max_memcpy_count = + dsa->max_batches * dsa->max_copies_per_batch; + device->driver.max_memcpy_size = 1UL << dsa->gen_cap.max_xfer_shift; + device->driver.msi = MSIX_VECTOR; +} + +static void dsa_remove(struct vfio_pci_device *device) +{ + dsa_command(device, IDXD_CMD_RESET_DEVICE); + vfio_pci_msix_disable(device); +} + +static int dsa_completion_wait(struct vfio_pci_device *device, + struct dsa_completion_record *completion) +{ + u8 status; + + for (;;) { + dsa_check_sw_err(device); + + status = READ_ONCE(completion->status); + if (status) + break; + + usleep(1000); + } + + if (status == DSA_COMP_SUCCESS) + return 0; + + printf("Error detected during memcpy operation: 0x%x\n", status); + return -1; +} + +static void dsa_copy_desc_init(struct vfio_pci_device *device, + struct dsa_hw_desc *desc, + iova_t src, iova_t dst, u64 size, + bool interrupt) +{ + struct dsa_state *dsa = to_dsa_state(device); + u16 flags; + + flags = IDXD_OP_FLAG_CRAV | IDXD_OP_FLAG_RCR; + + if (interrupt) + flags |= IDXD_OP_FLAG_RCI; + + *desc = (struct dsa_hw_desc) { + .opcode = DSA_OPCODE_MEMMOVE, + .flags = flags, + .priv = 1, + .src_addr = src, + .dst_addr = dst, + .xfer_size = size, + .completion_addr = to_iova(device, &dsa->copy_completion), + .int_handle = interrupt ? MSIX_VECTOR : 0, + }; +} + +static void dsa_batch_desc_init(struct vfio_pci_device *device, + struct dsa_hw_desc *desc, + u64 count) +{ + struct dsa_state *dsa = to_dsa_state(device); + + *desc = (struct dsa_hw_desc) { + .opcode = DSA_OPCODE_BATCH, + .flags = IDXD_OP_FLAG_CRAV, + .priv = 1, + .completion_addr = to_iova(device, &dsa->batch_completion), + .desc_list_addr = to_iova(device, &dsa->copy[0]), + .desc_count = count, + }; +} + +static void dsa_desc_write(struct vfio_pci_device *device, struct dsa_hw_desc *desc) +{ + /* Write the contents (not address) of the 64-byte descriptor to the device. */ + iosubmit_cmds512(device->bars[2].vaddr, desc, 1); +} + +static void dsa_memcpy_one(struct vfio_pci_device *device, + iova_t src, iova_t dst, u64 size, bool interrupt) +{ + struct dsa_state *dsa = to_dsa_state(device); + + memset(&dsa->copy_completion, 0, sizeof(dsa->copy_completion)); + + dsa_copy_desc_init(device, &dsa->copy[0], src, dst, size, interrupt); + dsa_desc_write(device, &dsa->copy[0]); +} + +static void dsa_memcpy_batch(struct vfio_pci_device *device, + iova_t src, iova_t dst, u64 size, u64 count) +{ + struct dsa_state *dsa = to_dsa_state(device); + int i; + + memset(&dsa->batch_completion, 0, sizeof(dsa->batch_completion)); + + for (i = 0; i < ARRAY_SIZE(dsa->copy); i++) { + struct dsa_hw_desc *copy_desc = &dsa->copy[i]; + + dsa_copy_desc_init(device, copy_desc, src, dst, size, false); + + /* Don't request completions for individual copies. */ + copy_desc->flags &= ~IDXD_OP_FLAG_RCR; + } + + for (i = 0; i < ARRAY_SIZE(dsa->batch) && count; i++) { + struct dsa_hw_desc *batch_desc = &dsa->batch[i]; + int nr_copies; + + nr_copies = min(count, dsa->max_copies_per_batch); + count -= nr_copies; + + /* + * Batches must have at least 2 copies, so handle the case where + * there is exactly 1 copy left by doing one less copy in this + * batch and then 2 in the next. + */ + if (count == 1) { + nr_copies--; + count++; + } + + dsa_batch_desc_init(device, batch_desc, nr_copies); + + /* Request a completion for the last batch. */ + if (!count) + batch_desc->flags |= IDXD_OP_FLAG_RCR; + + dsa_desc_write(device, batch_desc); + } + + VFIO_ASSERT_EQ(count, 0, "Failed to start %lu copies.\n", count); +} + +static void dsa_memcpy_start(struct vfio_pci_device *device, + iova_t src, iova_t dst, u64 size, u64 count) +{ + struct dsa_state *dsa = to_dsa_state(device); + + /* DSA devices require at least 2 copies per batch. */ + if (count == 1) + dsa_memcpy_one(device, src, dst, size, false); + else + dsa_memcpy_batch(device, src, dst, size, count); + + dsa->memcpy_count = count; +} + +static int dsa_memcpy_wait(struct vfio_pci_device *device) +{ + struct dsa_state *dsa = to_dsa_state(device); + int r; + + if (dsa->memcpy_count == 1) + r = dsa_completion_wait(device, &dsa->copy_completion); + else + r = dsa_completion_wait(device, &dsa->batch_completion); + + dsa->memcpy_count = 0; + + return r; +} + +static void dsa_send_msi(struct vfio_pci_device *device) +{ + struct dsa_state *dsa = to_dsa_state(device); + + dsa_memcpy_one(device, + to_iova(device, &dsa->send_msi_src), + to_iova(device, &dsa->send_msi_dst), + sizeof(dsa->send_msi_src), true); + + VFIO_ASSERT_EQ(dsa_completion_wait(device, &dsa->copy_completion), 0); +} + +const struct vfio_pci_driver_ops dsa_ops = { + .name = "dsa", + .probe = dsa_probe, + .init = dsa_init, + .remove = dsa_remove, + .memcpy_start = dsa_memcpy_start, + .memcpy_wait = dsa_memcpy_wait, + .send_msi = dsa_send_msi, +}; diff --git a/tools/testing/selftests/vfio/lib/drivers/dsa/registers.h b/tools/testing/selftests/vfio/lib/drivers/dsa/registers.h new file mode 120000 index 000000000000..bde657c3c2af --- /dev/null +++ b/tools/testing/selftests/vfio/lib/drivers/dsa/registers.h @@ -0,0 +1 @@ +../../../../../../../drivers/dma/idxd/registers.h
\ No newline at end of file diff --git a/tools/testing/selftests/vfio/lib/drivers/ioat/hw.h b/tools/testing/selftests/vfio/lib/drivers/ioat/hw.h new file mode 120000 index 000000000000..8ab52ddd4458 --- /dev/null +++ b/tools/testing/selftests/vfio/lib/drivers/ioat/hw.h @@ -0,0 +1 @@ +../../../../../../../drivers/dma/ioat/hw.h
\ No newline at end of file diff --git a/tools/testing/selftests/vfio/lib/drivers/ioat/ioat.c b/tools/testing/selftests/vfio/lib/drivers/ioat/ioat.c new file mode 100644 index 000000000000..c3b91d9b1f59 --- /dev/null +++ b/tools/testing/selftests/vfio/lib/drivers/ioat/ioat.c @@ -0,0 +1,235 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include <stdint.h> +#include <unistd.h> + +#include <linux/errno.h> +#include <linux/io.h> +#include <linux/pci_ids.h> +#include <linux/sizes.h> + +#include <vfio_util.h> + +#include "hw.h" +#include "registers.h" + +#define IOAT_DMACOUNT_MAX UINT16_MAX + +struct ioat_state { + /* Single descriptor used to issue DMA memcpy operations */ + struct ioat_dma_descriptor desc; + + /* Copy buffers used by ioat_send_msi() to generate an interrupt. */ + u64 send_msi_src; + u64 send_msi_dst; +}; + +static inline struct ioat_state *to_ioat_state(struct vfio_pci_device *device) +{ + return device->driver.region.vaddr; +} + +static inline void *ioat_channel_registers(struct vfio_pci_device *device) +{ + return device->bars[0].vaddr + IOAT_CHANNEL_MMIO_SIZE; +} + +static int ioat_probe(struct vfio_pci_device *device) +{ + u8 version; + int r; + + if (!vfio_pci_device_match(device, PCI_VENDOR_ID_INTEL, + PCI_DEVICE_ID_INTEL_IOAT_SKX)) + return -EINVAL; + + VFIO_ASSERT_NOT_NULL(device->bars[0].vaddr); + + version = readb(device->bars[0].vaddr + IOAT_VER_OFFSET); + switch (version) { + case IOAT_VER_3_2: + case IOAT_VER_3_3: + r = 0; + break; + default: + printf("ioat: Unsupported version: 0x%x\n", version); + r = -EINVAL; + } + return r; +} + +static u64 ioat_channel_status(void *bar) +{ + return readq(bar + IOAT_CHANSTS_OFFSET) & IOAT_CHANSTS_STATUS; +} + +static void ioat_clear_errors(struct vfio_pci_device *device) +{ + void *registers = ioat_channel_registers(device); + u32 errors; + + errors = vfio_pci_config_readl(device, IOAT_PCI_CHANERR_INT_OFFSET); + vfio_pci_config_writel(device, IOAT_PCI_CHANERR_INT_OFFSET, errors); + + errors = vfio_pci_config_readl(device, IOAT_PCI_DMAUNCERRSTS_OFFSET); + vfio_pci_config_writel(device, IOAT_PCI_CHANERR_INT_OFFSET, errors); + + errors = readl(registers + IOAT_CHANERR_OFFSET); + writel(errors, registers + IOAT_CHANERR_OFFSET); +} + +static void ioat_reset(struct vfio_pci_device *device) +{ + void *registers = ioat_channel_registers(device); + u32 sleep_ms = 1, attempts = 5000 / sleep_ms; + u8 chancmd; + + ioat_clear_errors(device); + + writeb(IOAT_CHANCMD_RESET, registers + IOAT2_CHANCMD_OFFSET); + + for (;;) { + chancmd = readb(registers + IOAT2_CHANCMD_OFFSET); + if (!(chancmd & IOAT_CHANCMD_RESET)) + break; + + VFIO_ASSERT_GT(--attempts, 0); + usleep(sleep_ms * 1000); + } + + VFIO_ASSERT_EQ(ioat_channel_status(registers), IOAT_CHANSTS_HALTED); +} + +static void ioat_init(struct vfio_pci_device *device) +{ + struct ioat_state *ioat = to_ioat_state(device); + u8 intrctrl; + + VFIO_ASSERT_GE(device->driver.region.size, sizeof(*ioat)); + + vfio_pci_config_writew(device, PCI_COMMAND, + PCI_COMMAND_MEMORY | + PCI_COMMAND_MASTER | + PCI_COMMAND_INTX_DISABLE); + + ioat_reset(device); + + /* Enable the use of MXI-x interrupts for channel interrupts. */ + intrctrl = IOAT_INTRCTRL_MSIX_VECTOR_CONTROL; + writeb(intrctrl, device->bars[0].vaddr + IOAT_INTRCTRL_OFFSET); + + vfio_pci_msix_enable(device, 0, device->msix_info.count); + + device->driver.msi = 0; + device->driver.max_memcpy_size = + 1UL << readb(device->bars[0].vaddr + IOAT_XFERCAP_OFFSET); + device->driver.max_memcpy_count = IOAT_DMACOUNT_MAX; +} + +static void ioat_remove(struct vfio_pci_device *device) +{ + ioat_reset(device); + vfio_pci_msix_disable(device); +} + +static void ioat_handle_error(struct vfio_pci_device *device) +{ + void *registers = ioat_channel_registers(device); + + printf("Error detected during memcpy operation!\n" + " CHANERR: 0x%x\n" + " CHANERR_INT: 0x%x\n" + " DMAUNCERRSTS: 0x%x\n", + readl(registers + IOAT_CHANERR_OFFSET), + vfio_pci_config_readl(device, IOAT_PCI_CHANERR_INT_OFFSET), + vfio_pci_config_readl(device, IOAT_PCI_DMAUNCERRSTS_OFFSET)); + + ioat_reset(device); +} + +static int ioat_memcpy_wait(struct vfio_pci_device *device) +{ + void *registers = ioat_channel_registers(device); + u64 status; + int r = 0; + + /* Wait until all operations complete. */ + for (;;) { + status = ioat_channel_status(registers); + if (status == IOAT_CHANSTS_DONE) + break; + + if (status == IOAT_CHANSTS_HALTED) { + ioat_handle_error(device); + return -1; + } + } + + /* Put the channel into the SUSPENDED state. */ + writeb(IOAT_CHANCMD_SUSPEND, registers + IOAT2_CHANCMD_OFFSET); + for (;;) { + status = ioat_channel_status(registers); + if (status == IOAT_CHANSTS_SUSPENDED) + break; + } + + return r; +} + +static void __ioat_memcpy_start(struct vfio_pci_device *device, + iova_t src, iova_t dst, u64 size, + u16 count, bool interrupt) +{ + void *registers = ioat_channel_registers(device); + struct ioat_state *ioat = to_ioat_state(device); + u64 desc_iova; + u16 chanctrl; + + desc_iova = to_iova(device, &ioat->desc); + ioat->desc = (struct ioat_dma_descriptor) { + .ctl_f.op = IOAT_OP_COPY, + .ctl_f.int_en = interrupt, + .src_addr = src, + .dst_addr = dst, + .size = size, + .next = desc_iova, + }; + + /* Tell the device the address of the descriptor. */ + writeq(desc_iova, registers + IOAT2_CHAINADDR_OFFSET); + + /* (Re)Enable the channel interrupt and abort on any errors */ + chanctrl = IOAT_CHANCTRL_INT_REARM | IOAT_CHANCTRL_ANY_ERR_ABORT_EN; + writew(chanctrl, registers + IOAT_CHANCTRL_OFFSET); + + /* Kick off @count DMA copy operation(s). */ + writew(count, registers + IOAT_CHAN_DMACOUNT_OFFSET); +} + +static void ioat_memcpy_start(struct vfio_pci_device *device, + iova_t src, iova_t dst, u64 size, + u64 count) +{ + __ioat_memcpy_start(device, src, dst, size, count, false); +} + +static void ioat_send_msi(struct vfio_pci_device *device) +{ + struct ioat_state *ioat = to_ioat_state(device); + + __ioat_memcpy_start(device, + to_iova(device, &ioat->send_msi_src), + to_iova(device, &ioat->send_msi_dst), + sizeof(ioat->send_msi_src), 1, true); + + VFIO_ASSERT_EQ(ioat_memcpy_wait(device), 0); +} + +const struct vfio_pci_driver_ops ioat_ops = { + .name = "ioat", + .probe = ioat_probe, + .init = ioat_init, + .remove = ioat_remove, + .memcpy_start = ioat_memcpy_start, + .memcpy_wait = ioat_memcpy_wait, + .send_msi = ioat_send_msi, +}; diff --git a/tools/testing/selftests/vfio/lib/drivers/ioat/registers.h b/tools/testing/selftests/vfio/lib/drivers/ioat/registers.h new file mode 120000 index 000000000000..0b809cfd8fe6 --- /dev/null +++ b/tools/testing/selftests/vfio/lib/drivers/ioat/registers.h @@ -0,0 +1 @@ +../../../../../../../drivers/dma/ioat/registers.h
\ No newline at end of file diff --git a/tools/testing/selftests/vfio/lib/include/vfio_util.h b/tools/testing/selftests/vfio/lib/include/vfio_util.h new file mode 100644 index 000000000000..ed31606e01b7 --- /dev/null +++ b/tools/testing/selftests/vfio/lib/include/vfio_util.h @@ -0,0 +1,295 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef SELFTESTS_VFIO_LIB_INCLUDE_VFIO_UTIL_H +#define SELFTESTS_VFIO_LIB_INCLUDE_VFIO_UTIL_H + +#include <fcntl.h> +#include <string.h> +#include <linux/vfio.h> +#include <linux/list.h> +#include <linux/pci_regs.h> + +#include "../../../kselftest.h" + +#define VFIO_LOG_AND_EXIT(...) do { \ + fprintf(stderr, " " __VA_ARGS__); \ + fprintf(stderr, "\n"); \ + exit(KSFT_FAIL); \ +} while (0) + +#define VFIO_ASSERT_OP(_lhs, _rhs, _op, ...) do { \ + typeof(_lhs) __lhs = (_lhs); \ + typeof(_rhs) __rhs = (_rhs); \ + \ + if (__lhs _op __rhs) \ + break; \ + \ + fprintf(stderr, "%s:%u: Assertion Failure\n\n", __FILE__, __LINE__); \ + fprintf(stderr, " Expression: " #_lhs " " #_op " " #_rhs "\n"); \ + fprintf(stderr, " Observed: %#lx %s %#lx\n", \ + (u64)__lhs, #_op, (u64)__rhs); \ + fprintf(stderr, " [errno: %d - %s]\n", errno, strerror(errno)); \ + VFIO_LOG_AND_EXIT(__VA_ARGS__); \ +} while (0) + +#define VFIO_ASSERT_EQ(_a, _b, ...) VFIO_ASSERT_OP(_a, _b, ==, ##__VA_ARGS__) +#define VFIO_ASSERT_NE(_a, _b, ...) VFIO_ASSERT_OP(_a, _b, !=, ##__VA_ARGS__) +#define VFIO_ASSERT_LT(_a, _b, ...) VFIO_ASSERT_OP(_a, _b, <, ##__VA_ARGS__) +#define VFIO_ASSERT_LE(_a, _b, ...) VFIO_ASSERT_OP(_a, _b, <=, ##__VA_ARGS__) +#define VFIO_ASSERT_GT(_a, _b, ...) VFIO_ASSERT_OP(_a, _b, >, ##__VA_ARGS__) +#define VFIO_ASSERT_GE(_a, _b, ...) VFIO_ASSERT_OP(_a, _b, >=, ##__VA_ARGS__) +#define VFIO_ASSERT_TRUE(_a, ...) VFIO_ASSERT_NE(false, (_a), ##__VA_ARGS__) +#define VFIO_ASSERT_FALSE(_a, ...) VFIO_ASSERT_EQ(false, (_a), ##__VA_ARGS__) +#define VFIO_ASSERT_NULL(_a, ...) VFIO_ASSERT_EQ(NULL, _a, ##__VA_ARGS__) +#define VFIO_ASSERT_NOT_NULL(_a, ...) VFIO_ASSERT_NE(NULL, _a, ##__VA_ARGS__) + +#define VFIO_FAIL(_fmt, ...) do { \ + fprintf(stderr, "%s:%u: FAIL\n\n", __FILE__, __LINE__); \ + VFIO_LOG_AND_EXIT(_fmt, ##__VA_ARGS__); \ +} while (0) + +struct vfio_iommu_mode { + const char *name; + const char *container_path; + unsigned long iommu_type; +}; + +/* + * Generator for VFIO selftests fixture variants that replicate across all + * possible IOMMU modes. Tests must define FIXTURE_VARIANT_ADD_IOMMU_MODE() + * which should then use FIXTURE_VARIANT_ADD() to create the variant. + */ +#define FIXTURE_VARIANT_ADD_ALL_IOMMU_MODES(...) \ +FIXTURE_VARIANT_ADD_IOMMU_MODE(vfio_type1_iommu, ##__VA_ARGS__); \ +FIXTURE_VARIANT_ADD_IOMMU_MODE(vfio_type1v2_iommu, ##__VA_ARGS__); \ +FIXTURE_VARIANT_ADD_IOMMU_MODE(iommufd_compat_type1, ##__VA_ARGS__); \ +FIXTURE_VARIANT_ADD_IOMMU_MODE(iommufd_compat_type1v2, ##__VA_ARGS__); \ +FIXTURE_VARIANT_ADD_IOMMU_MODE(iommufd, ##__VA_ARGS__) + +struct vfio_pci_bar { + struct vfio_region_info info; + void *vaddr; +}; + +typedef u64 iova_t; + +#define INVALID_IOVA UINT64_MAX + +struct vfio_dma_region { + struct list_head link; + void *vaddr; + iova_t iova; + u64 size; +}; + +struct vfio_pci_device; + +struct vfio_pci_driver_ops { + const char *name; + + /** + * @probe() - Check if the driver supports the given device. + * + * Return: 0 on success, non-0 on failure. + */ + int (*probe)(struct vfio_pci_device *device); + + /** + * @init() - Initialize the driver for @device. + * + * Must be called after device->driver.region has been initialized. + */ + void (*init)(struct vfio_pci_device *device); + + /** + * remove() - Deinitialize the driver for @device. + */ + void (*remove)(struct vfio_pci_device *device); + + /** + * memcpy_start() - Kick off @count repeated memcpy operations from + * [@src, @src + @size) to [@dst, @dst + @size). + * + * Guarantees: + * - The device will attempt DMA reads on [src, src + size). + * - The device will attempt DMA writes on [dst, dst + size). + * - The device will not generate any interrupts. + * + * memcpy_start() returns immediately, it does not wait for the + * copies to complete. + */ + void (*memcpy_start)(struct vfio_pci_device *device, + iova_t src, iova_t dst, u64 size, u64 count); + + /** + * memcpy_wait() - Wait until the memcpy operations started by + * memcpy_start() have finished. + * + * Guarantees: + * - All in-flight DMAs initiated by memcpy_start() are fully complete + * before memcpy_wait() returns. + * + * Returns non-0 if the driver detects that an error occurred during the + * memcpy, 0 otherwise. + */ + int (*memcpy_wait)(struct vfio_pci_device *device); + + /** + * send_msi() - Make the device send the MSI device->driver.msi. + * + * Guarantees: + * - The device will send the MSI once. + */ + void (*send_msi)(struct vfio_pci_device *device); +}; + +struct vfio_pci_driver { + const struct vfio_pci_driver_ops *ops; + bool initialized; + bool memcpy_in_progress; + + /* Region to be used by the driver (e.g. for in-memory descriptors) */ + struct vfio_dma_region region; + + /* The maximum size that can be passed to memcpy_start(). */ + u64 max_memcpy_size; + + /* The maximum count that can be passed to memcpy_start(). */ + u64 max_memcpy_count; + + /* The MSI vector the device will signal in ops->send_msi(). */ + int msi; +}; + +struct vfio_pci_device { + int fd; + + const struct vfio_iommu_mode *iommu_mode; + int group_fd; + int container_fd; + + int iommufd; + u32 ioas_id; + + struct vfio_device_info info; + struct vfio_region_info config_space; + struct vfio_pci_bar bars[PCI_STD_NUM_BARS]; + + struct vfio_irq_info msi_info; + struct vfio_irq_info msix_info; + + struct list_head dma_regions; + + /* eventfds for MSI and MSI-x interrupts */ + int msi_eventfds[PCI_MSIX_FLAGS_QSIZE + 1]; + + struct vfio_pci_driver driver; +}; + +/* + * Return the BDF string of the device that the test should use. + * + * If a BDF string is provided by the user on the command line (as the last + * element of argv[]), then this function will return that and decrement argc + * by 1. + * + * Otherwise this function will attempt to use the environment variable + * $VFIO_SELFTESTS_BDF. + * + * If BDF cannot be determined then the test will exit with KSFT_SKIP. + */ +const char *vfio_selftests_get_bdf(int *argc, char *argv[]); +const char *vfio_pci_get_cdev_path(const char *bdf); + +extern const char *default_iommu_mode; + +struct vfio_pci_device *vfio_pci_device_init(const char *bdf, const char *iommu_mode); +void vfio_pci_device_cleanup(struct vfio_pci_device *device); +void vfio_pci_device_reset(struct vfio_pci_device *device); + +void vfio_pci_dma_map(struct vfio_pci_device *device, + struct vfio_dma_region *region); +void vfio_pci_dma_unmap(struct vfio_pci_device *device, + struct vfio_dma_region *region); + +void vfio_pci_config_access(struct vfio_pci_device *device, bool write, + size_t config, size_t size, void *data); + +#define vfio_pci_config_read(_device, _offset, _type) ({ \ + _type __data; \ + vfio_pci_config_access((_device), false, _offset, sizeof(__data), &__data); \ + __data; \ +}) + +#define vfio_pci_config_readb(_d, _o) vfio_pci_config_read(_d, _o, u8) +#define vfio_pci_config_readw(_d, _o) vfio_pci_config_read(_d, _o, u16) +#define vfio_pci_config_readl(_d, _o) vfio_pci_config_read(_d, _o, u32) + +#define vfio_pci_config_write(_device, _offset, _value, _type) do { \ + _type __data = (_value); \ + vfio_pci_config_access((_device), true, _offset, sizeof(_type), &__data); \ +} while (0) + +#define vfio_pci_config_writeb(_d, _o, _v) vfio_pci_config_write(_d, _o, _v, u8) +#define vfio_pci_config_writew(_d, _o, _v) vfio_pci_config_write(_d, _o, _v, u16) +#define vfio_pci_config_writel(_d, _o, _v) vfio_pci_config_write(_d, _o, _v, u32) + +void vfio_pci_irq_enable(struct vfio_pci_device *device, u32 index, + u32 vector, int count); +void vfio_pci_irq_disable(struct vfio_pci_device *device, u32 index); +void vfio_pci_irq_trigger(struct vfio_pci_device *device, u32 index, u32 vector); + +static inline void fcntl_set_nonblock(int fd) +{ + int r; + + r = fcntl(fd, F_GETFL, 0); + VFIO_ASSERT_NE(r, -1, "F_GETFL failed for fd %d\n", fd); + + r = fcntl(fd, F_SETFL, r | O_NONBLOCK); + VFIO_ASSERT_NE(r, -1, "F_SETFL O_NONBLOCK failed for fd %d\n", fd); +} + +static inline void vfio_pci_msi_enable(struct vfio_pci_device *device, + u32 vector, int count) +{ + vfio_pci_irq_enable(device, VFIO_PCI_MSI_IRQ_INDEX, vector, count); +} + +static inline void vfio_pci_msi_disable(struct vfio_pci_device *device) +{ + vfio_pci_irq_disable(device, VFIO_PCI_MSI_IRQ_INDEX); +} + +static inline void vfio_pci_msix_enable(struct vfio_pci_device *device, + u32 vector, int count) +{ + vfio_pci_irq_enable(device, VFIO_PCI_MSIX_IRQ_INDEX, vector, count); +} + +static inline void vfio_pci_msix_disable(struct vfio_pci_device *device) +{ + vfio_pci_irq_disable(device, VFIO_PCI_MSIX_IRQ_INDEX); +} + +iova_t __to_iova(struct vfio_pci_device *device, void *vaddr); +iova_t to_iova(struct vfio_pci_device *device, void *vaddr); + +static inline bool vfio_pci_device_match(struct vfio_pci_device *device, + u16 vendor_id, u16 device_id) +{ + return (vendor_id == vfio_pci_config_readw(device, PCI_VENDOR_ID)) && + (device_id == vfio_pci_config_readw(device, PCI_DEVICE_ID)); +} + +void vfio_pci_driver_probe(struct vfio_pci_device *device); +void vfio_pci_driver_init(struct vfio_pci_device *device); +void vfio_pci_driver_remove(struct vfio_pci_device *device); +int vfio_pci_driver_memcpy(struct vfio_pci_device *device, + iova_t src, iova_t dst, u64 size); +void vfio_pci_driver_memcpy_start(struct vfio_pci_device *device, + iova_t src, iova_t dst, u64 size, + u64 count); +int vfio_pci_driver_memcpy_wait(struct vfio_pci_device *device); +void vfio_pci_driver_send_msi(struct vfio_pci_device *device); + +#endif /* SELFTESTS_VFIO_LIB_INCLUDE_VFIO_UTIL_H */ diff --git a/tools/testing/selftests/vfio/lib/libvfio.mk b/tools/testing/selftests/vfio/lib/libvfio.mk new file mode 100644 index 000000000000..5d11c3a89a28 --- /dev/null +++ b/tools/testing/selftests/vfio/lib/libvfio.mk @@ -0,0 +1,24 @@ +include $(top_srcdir)/scripts/subarch.include +ARCH ?= $(SUBARCH) + +VFIO_DIR := $(selfdir)/vfio + +LIBVFIO_C := lib/vfio_pci_device.c +LIBVFIO_C += lib/vfio_pci_driver.c + +ifeq ($(ARCH:x86_64=x86),x86) +LIBVFIO_C += lib/drivers/ioat/ioat.c +LIBVFIO_C += lib/drivers/dsa/dsa.c +endif + +LIBVFIO_O := $(patsubst %.c, $(OUTPUT)/%.o, $(LIBVFIO_C)) + +LIBVFIO_O_DIRS := $(shell dirname $(LIBVFIO_O) | uniq) +$(shell mkdir -p $(LIBVFIO_O_DIRS)) + +CFLAGS += -I$(VFIO_DIR)/lib/include + +$(LIBVFIO_O): $(OUTPUT)/%.o : $(VFIO_DIR)/%.c + $(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c $< -o $@ + +EXTRA_CLEAN += $(LIBVFIO_O) diff --git a/tools/testing/selftests/vfio/lib/vfio_pci_device.c b/tools/testing/selftests/vfio/lib/vfio_pci_device.c new file mode 100644 index 000000000000..0921b2451ba5 --- /dev/null +++ b/tools/testing/selftests/vfio/lib/vfio_pci_device.c @@ -0,0 +1,594 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include <dirent.h> +#include <fcntl.h> +#include <libgen.h> +#include <stdlib.h> +#include <string.h> +#include <unistd.h> + +#include <sys/eventfd.h> +#include <sys/ioctl.h> +#include <sys/mman.h> + +#include <uapi/linux/types.h> +#include <linux/limits.h> +#include <linux/mman.h> +#include <linux/types.h> +#include <linux/vfio.h> +#include <linux/iommufd.h> + +#include "../../../kselftest.h" +#include <vfio_util.h> + +#define PCI_SYSFS_PATH "/sys/bus/pci/devices" + +#define ioctl_assert(_fd, _op, _arg) do { \ + void *__arg = (_arg); \ + int __ret = ioctl((_fd), (_op), (__arg)); \ + VFIO_ASSERT_EQ(__ret, 0, "ioctl(%s, %s, %s) returned %d\n", #_fd, #_op, #_arg, __ret); \ +} while (0) + +iova_t __to_iova(struct vfio_pci_device *device, void *vaddr) +{ + struct vfio_dma_region *region; + + list_for_each_entry(region, &device->dma_regions, link) { + if (vaddr < region->vaddr) + continue; + + if (vaddr >= region->vaddr + region->size) + continue; + + return region->iova + (vaddr - region->vaddr); + } + + return INVALID_IOVA; +} + +iova_t to_iova(struct vfio_pci_device *device, void *vaddr) +{ + iova_t iova; + + iova = __to_iova(device, vaddr); + VFIO_ASSERT_NE(iova, INVALID_IOVA, "%p is not mapped into device.\n", vaddr); + + return iova; +} + +static void vfio_pci_irq_set(struct vfio_pci_device *device, + u32 index, u32 vector, u32 count, int *fds) +{ + u8 buf[sizeof(struct vfio_irq_set) + sizeof(int) * count] = {}; + struct vfio_irq_set *irq = (void *)&buf; + int *irq_fds = (void *)&irq->data; + + irq->argsz = sizeof(buf); + irq->flags = VFIO_IRQ_SET_ACTION_TRIGGER; + irq->index = index; + irq->start = vector; + irq->count = count; + + if (count) { + irq->flags |= VFIO_IRQ_SET_DATA_EVENTFD; + memcpy(irq_fds, fds, sizeof(int) * count); + } else { + irq->flags |= VFIO_IRQ_SET_DATA_NONE; + } + + ioctl_assert(device->fd, VFIO_DEVICE_SET_IRQS, irq); +} + +void vfio_pci_irq_trigger(struct vfio_pci_device *device, u32 index, u32 vector) +{ + struct vfio_irq_set irq = { + .argsz = sizeof(irq), + .flags = VFIO_IRQ_SET_ACTION_TRIGGER | VFIO_IRQ_SET_DATA_NONE, + .index = index, + .start = vector, + .count = 1, + }; + + ioctl_assert(device->fd, VFIO_DEVICE_SET_IRQS, &irq); +} + +static void check_supported_irq_index(u32 index) +{ + /* VFIO selftests only supports MSI and MSI-x for now. */ + VFIO_ASSERT_TRUE(index == VFIO_PCI_MSI_IRQ_INDEX || + index == VFIO_PCI_MSIX_IRQ_INDEX, + "Unsupported IRQ index: %u\n", index); +} + +void vfio_pci_irq_enable(struct vfio_pci_device *device, u32 index, u32 vector, + int count) +{ + int i; + + check_supported_irq_index(index); + + for (i = vector; i < vector + count; i++) { + VFIO_ASSERT_LT(device->msi_eventfds[i], 0); + device->msi_eventfds[i] = eventfd(0, 0); + VFIO_ASSERT_GE(device->msi_eventfds[i], 0); + } + + vfio_pci_irq_set(device, index, vector, count, device->msi_eventfds + vector); +} + +void vfio_pci_irq_disable(struct vfio_pci_device *device, u32 index) +{ + int i; + + check_supported_irq_index(index); + + for (i = 0; i < ARRAY_SIZE(device->msi_eventfds); i++) { + if (device->msi_eventfds[i] < 0) + continue; + + VFIO_ASSERT_EQ(close(device->msi_eventfds[i]), 0); + device->msi_eventfds[i] = -1; + } + + vfio_pci_irq_set(device, index, 0, 0, NULL); +} + +static void vfio_pci_irq_get(struct vfio_pci_device *device, u32 index, + struct vfio_irq_info *irq_info) +{ + irq_info->argsz = sizeof(*irq_info); + irq_info->index = index; + + ioctl_assert(device->fd, VFIO_DEVICE_GET_IRQ_INFO, irq_info); +} + +static void vfio_iommu_dma_map(struct vfio_pci_device *device, + struct vfio_dma_region *region) +{ + struct vfio_iommu_type1_dma_map args = { + .argsz = sizeof(args), + .flags = VFIO_DMA_MAP_FLAG_READ | VFIO_DMA_MAP_FLAG_WRITE, + .vaddr = (u64)region->vaddr, + .iova = region->iova, + .size = region->size, + }; + + ioctl_assert(device->container_fd, VFIO_IOMMU_MAP_DMA, &args); +} + +static void iommufd_dma_map(struct vfio_pci_device *device, + struct vfio_dma_region *region) +{ + struct iommu_ioas_map args = { + .size = sizeof(args), + .flags = IOMMU_IOAS_MAP_READABLE | + IOMMU_IOAS_MAP_WRITEABLE | + IOMMU_IOAS_MAP_FIXED_IOVA, + .user_va = (u64)region->vaddr, + .iova = region->iova, + .length = region->size, + .ioas_id = device->ioas_id, + }; + + ioctl_assert(device->iommufd, IOMMU_IOAS_MAP, &args); +} + +void vfio_pci_dma_map(struct vfio_pci_device *device, + struct vfio_dma_region *region) +{ + if (device->iommufd) + iommufd_dma_map(device, region); + else + vfio_iommu_dma_map(device, region); + + list_add(®ion->link, &device->dma_regions); +} + +static void vfio_iommu_dma_unmap(struct vfio_pci_device *device, + struct vfio_dma_region *region) +{ + struct vfio_iommu_type1_dma_unmap args = { + .argsz = sizeof(args), + .iova = region->iova, + .size = region->size, + }; + + ioctl_assert(device->container_fd, VFIO_IOMMU_UNMAP_DMA, &args); +} + +static void iommufd_dma_unmap(struct vfio_pci_device *device, + struct vfio_dma_region *region) +{ + struct iommu_ioas_unmap args = { + .size = sizeof(args), + .iova = region->iova, + .length = region->size, + .ioas_id = device->ioas_id, + }; + + ioctl_assert(device->iommufd, IOMMU_IOAS_UNMAP, &args); +} + +void vfio_pci_dma_unmap(struct vfio_pci_device *device, + struct vfio_dma_region *region) +{ + if (device->iommufd) + iommufd_dma_unmap(device, region); + else + vfio_iommu_dma_unmap(device, region); + + list_del(®ion->link); +} + +static void vfio_pci_region_get(struct vfio_pci_device *device, int index, + struct vfio_region_info *info) +{ + memset(info, 0, sizeof(*info)); + + info->argsz = sizeof(*info); + info->index = index; + + ioctl_assert(device->fd, VFIO_DEVICE_GET_REGION_INFO, info); +} + +static void vfio_pci_bar_map(struct vfio_pci_device *device, int index) +{ + struct vfio_pci_bar *bar = &device->bars[index]; + int prot = 0; + + VFIO_ASSERT_LT(index, PCI_STD_NUM_BARS); + VFIO_ASSERT_NULL(bar->vaddr); + VFIO_ASSERT_TRUE(bar->info.flags & VFIO_REGION_INFO_FLAG_MMAP); + + if (bar->info.flags & VFIO_REGION_INFO_FLAG_READ) + prot |= PROT_READ; + if (bar->info.flags & VFIO_REGION_INFO_FLAG_WRITE) + prot |= PROT_WRITE; + + bar->vaddr = mmap(NULL, bar->info.size, prot, MAP_FILE | MAP_SHARED, + device->fd, bar->info.offset); + VFIO_ASSERT_NE(bar->vaddr, MAP_FAILED); +} + +static void vfio_pci_bar_unmap(struct vfio_pci_device *device, int index) +{ + struct vfio_pci_bar *bar = &device->bars[index]; + + VFIO_ASSERT_LT(index, PCI_STD_NUM_BARS); + VFIO_ASSERT_NOT_NULL(bar->vaddr); + + VFIO_ASSERT_EQ(munmap(bar->vaddr, bar->info.size), 0); + bar->vaddr = NULL; +} + +static void vfio_pci_bar_unmap_all(struct vfio_pci_device *device) +{ + int i; + + for (i = 0; i < PCI_STD_NUM_BARS; i++) { + if (device->bars[i].vaddr) + vfio_pci_bar_unmap(device, i); + } +} + +void vfio_pci_config_access(struct vfio_pci_device *device, bool write, + size_t config, size_t size, void *data) +{ + struct vfio_region_info *config_space = &device->config_space; + int ret; + + if (write) + ret = pwrite(device->fd, data, size, config_space->offset + config); + else + ret = pread(device->fd, data, size, config_space->offset + config); + + VFIO_ASSERT_EQ(ret, size, "Failed to %s PCI config space: 0x%lx\n", + write ? "write to" : "read from", config); +} + +void vfio_pci_device_reset(struct vfio_pci_device *device) +{ + ioctl_assert(device->fd, VFIO_DEVICE_RESET, NULL); +} + +static unsigned int vfio_pci_get_group_from_dev(const char *bdf) +{ + char dev_iommu_group_path[PATH_MAX] = {0}; + char sysfs_path[PATH_MAX] = {0}; + unsigned int group; + int ret; + + snprintf(sysfs_path, PATH_MAX, "%s/%s/iommu_group", PCI_SYSFS_PATH, bdf); + + ret = readlink(sysfs_path, dev_iommu_group_path, sizeof(dev_iommu_group_path)); + VFIO_ASSERT_NE(ret, -1, "Failed to get the IOMMU group for device: %s\n", bdf); + + ret = sscanf(basename(dev_iommu_group_path), "%u", &group); + VFIO_ASSERT_EQ(ret, 1, "Failed to get the IOMMU group for device: %s\n", bdf); + + return group; +} + +static void vfio_pci_group_setup(struct vfio_pci_device *device, const char *bdf) +{ + struct vfio_group_status group_status = { + .argsz = sizeof(group_status), + }; + char group_path[32]; + int group; + + group = vfio_pci_get_group_from_dev(bdf); + snprintf(group_path, sizeof(group_path), "/dev/vfio/%d", group); + + device->group_fd = open(group_path, O_RDWR); + VFIO_ASSERT_GE(device->group_fd, 0, "open(%s) failed\n", group_path); + + ioctl_assert(device->group_fd, VFIO_GROUP_GET_STATUS, &group_status); + VFIO_ASSERT_TRUE(group_status.flags & VFIO_GROUP_FLAGS_VIABLE); + + ioctl_assert(device->group_fd, VFIO_GROUP_SET_CONTAINER, &device->container_fd); +} + +static void vfio_pci_container_setup(struct vfio_pci_device *device, const char *bdf) +{ + unsigned long iommu_type = device->iommu_mode->iommu_type; + const char *path = device->iommu_mode->container_path; + int version; + int ret; + + device->container_fd = open(path, O_RDWR); + VFIO_ASSERT_GE(device->container_fd, 0, "open(%s) failed\n", path); + + version = ioctl(device->container_fd, VFIO_GET_API_VERSION); + VFIO_ASSERT_EQ(version, VFIO_API_VERSION, "Unsupported version: %d\n", version); + + vfio_pci_group_setup(device, bdf); + + ret = ioctl(device->container_fd, VFIO_CHECK_EXTENSION, iommu_type); + VFIO_ASSERT_GT(ret, 0, "VFIO IOMMU type %lu not supported\n", iommu_type); + + ioctl_assert(device->container_fd, VFIO_SET_IOMMU, (void *)iommu_type); + + device->fd = ioctl(device->group_fd, VFIO_GROUP_GET_DEVICE_FD, bdf); + VFIO_ASSERT_GE(device->fd, 0); +} + +static void vfio_pci_device_setup(struct vfio_pci_device *device) +{ + int i; + + device->info.argsz = sizeof(device->info); + ioctl_assert(device->fd, VFIO_DEVICE_GET_INFO, &device->info); + + vfio_pci_region_get(device, VFIO_PCI_CONFIG_REGION_INDEX, &device->config_space); + + /* Sanity check VFIO does not advertise mmap for config space */ + VFIO_ASSERT_TRUE(!(device->config_space.flags & VFIO_REGION_INFO_FLAG_MMAP), + "PCI config space should not support mmap()\n"); + + for (i = 0; i < PCI_STD_NUM_BARS; i++) { + struct vfio_pci_bar *bar = device->bars + i; + + vfio_pci_region_get(device, i, &bar->info); + if (bar->info.flags & VFIO_REGION_INFO_FLAG_MMAP) + vfio_pci_bar_map(device, i); + } + + vfio_pci_irq_get(device, VFIO_PCI_MSI_IRQ_INDEX, &device->msi_info); + vfio_pci_irq_get(device, VFIO_PCI_MSIX_IRQ_INDEX, &device->msix_info); + + for (i = 0; i < ARRAY_SIZE(device->msi_eventfds); i++) + device->msi_eventfds[i] = -1; +} + +const char *vfio_pci_get_cdev_path(const char *bdf) +{ + char dir_path[PATH_MAX]; + struct dirent *entry; + char *cdev_path; + DIR *dir; + + cdev_path = calloc(PATH_MAX, 1); + VFIO_ASSERT_NOT_NULL(cdev_path); + + snprintf(dir_path, sizeof(dir_path), "/sys/bus/pci/devices/%s/vfio-dev/", bdf); + + dir = opendir(dir_path); + VFIO_ASSERT_NOT_NULL(dir, "Failed to open directory %s\n", dir_path); + + while ((entry = readdir(dir)) != NULL) { + /* Find the file that starts with "vfio" */ + if (strncmp("vfio", entry->d_name, 4)) + continue; + + snprintf(cdev_path, PATH_MAX, "/dev/vfio/devices/%s", entry->d_name); + break; + } + + VFIO_ASSERT_NE(cdev_path[0], 0, "Failed to find vfio cdev file.\n"); + VFIO_ASSERT_EQ(closedir(dir), 0); + + return cdev_path; +} + +/* Reminder: Keep in sync with FIXTURE_VARIANT_ADD_ALL_IOMMU_MODES(). */ +static const struct vfio_iommu_mode iommu_modes[] = { + { + .name = "vfio_type1_iommu", + .container_path = "/dev/vfio/vfio", + .iommu_type = VFIO_TYPE1_IOMMU, + }, + { + .name = "vfio_type1v2_iommu", + .container_path = "/dev/vfio/vfio", + .iommu_type = VFIO_TYPE1v2_IOMMU, + }, + { + .name = "iommufd_compat_type1", + .container_path = "/dev/iommu", + .iommu_type = VFIO_TYPE1_IOMMU, + }, + { + .name = "iommufd_compat_type1v2", + .container_path = "/dev/iommu", + .iommu_type = VFIO_TYPE1v2_IOMMU, + }, + { + .name = "iommufd", + }, +}; + +const char *default_iommu_mode = "iommufd"; + +static const struct vfio_iommu_mode *lookup_iommu_mode(const char *iommu_mode) +{ + int i; + + if (!iommu_mode) + iommu_mode = default_iommu_mode; + + for (i = 0; i < ARRAY_SIZE(iommu_modes); i++) { + if (strcmp(iommu_mode, iommu_modes[i].name)) + continue; + + return &iommu_modes[i]; + } + + VFIO_FAIL("Unrecognized IOMMU mode: %s\n", iommu_mode); +} + +static void vfio_device_bind_iommufd(int device_fd, int iommufd) +{ + struct vfio_device_bind_iommufd args = { + .argsz = sizeof(args), + .iommufd = iommufd, + }; + + ioctl_assert(device_fd, VFIO_DEVICE_BIND_IOMMUFD, &args); +} + +static u32 iommufd_ioas_alloc(int iommufd) +{ + struct iommu_ioas_alloc args = { + .size = sizeof(args), + }; + + ioctl_assert(iommufd, IOMMU_IOAS_ALLOC, &args); + return args.out_ioas_id; +} + +static void vfio_device_attach_iommufd_pt(int device_fd, u32 pt_id) +{ + struct vfio_device_attach_iommufd_pt args = { + .argsz = sizeof(args), + .pt_id = pt_id, + }; + + ioctl_assert(device_fd, VFIO_DEVICE_ATTACH_IOMMUFD_PT, &args); +} + +static void vfio_pci_iommufd_setup(struct vfio_pci_device *device, const char *bdf) +{ + const char *cdev_path = vfio_pci_get_cdev_path(bdf); + + device->fd = open(cdev_path, O_RDWR); + VFIO_ASSERT_GE(device->fd, 0); + free((void *)cdev_path); + + /* + * Require device->iommufd to be >0 so that a simple non-0 check can be + * used to check if iommufd is enabled. In practice open() will never + * return 0 unless stdin is closed. + */ + device->iommufd = open("/dev/iommu", O_RDWR); + VFIO_ASSERT_GT(device->iommufd, 0); + + vfio_device_bind_iommufd(device->fd, device->iommufd); + device->ioas_id = iommufd_ioas_alloc(device->iommufd); + vfio_device_attach_iommufd_pt(device->fd, device->ioas_id); +} + +struct vfio_pci_device *vfio_pci_device_init(const char *bdf, const char *iommu_mode) +{ + struct vfio_pci_device *device; + + device = calloc(1, sizeof(*device)); + VFIO_ASSERT_NOT_NULL(device); + + INIT_LIST_HEAD(&device->dma_regions); + + device->iommu_mode = lookup_iommu_mode(iommu_mode); + + if (device->iommu_mode->container_path) + vfio_pci_container_setup(device, bdf); + else + vfio_pci_iommufd_setup(device, bdf); + + vfio_pci_device_setup(device); + vfio_pci_driver_probe(device); + + return device; +} + +void vfio_pci_device_cleanup(struct vfio_pci_device *device) +{ + int i; + + if (device->driver.initialized) + vfio_pci_driver_remove(device); + + vfio_pci_bar_unmap_all(device); + + VFIO_ASSERT_EQ(close(device->fd), 0); + + for (i = 0; i < ARRAY_SIZE(device->msi_eventfds); i++) { + if (device->msi_eventfds[i] < 0) + continue; + + VFIO_ASSERT_EQ(close(device->msi_eventfds[i]), 0); + } + + if (device->iommufd) { + VFIO_ASSERT_EQ(close(device->iommufd), 0); + } else { + VFIO_ASSERT_EQ(close(device->group_fd), 0); + VFIO_ASSERT_EQ(close(device->container_fd), 0); + } + + free(device); +} + +static bool is_bdf(const char *str) +{ + unsigned int s, b, d, f; + int length, count; + + count = sscanf(str, "%4x:%2x:%2x.%2x%n", &s, &b, &d, &f, &length); + return count == 4 && length == strlen(str); +} + +const char *vfio_selftests_get_bdf(int *argc, char *argv[]) +{ + char *bdf; + + if (*argc > 1 && is_bdf(argv[*argc - 1])) + return argv[--(*argc)]; + + bdf = getenv("VFIO_SELFTESTS_BDF"); + if (bdf) { + VFIO_ASSERT_TRUE(is_bdf(bdf), "Invalid BDF: %s\n", bdf); + return bdf; + } + + fprintf(stderr, "Unable to determine which device to use, skipping test.\n"); + fprintf(stderr, "\n"); + fprintf(stderr, "To pass the device address via environment variable:\n"); + fprintf(stderr, "\n"); + fprintf(stderr, " export VFIO_SELFTESTS_BDF=segment:bus:device.function\n"); + fprintf(stderr, " %s [options]\n", argv[0]); + fprintf(stderr, "\n"); + fprintf(stderr, "To pass the device address via argv:\n"); + fprintf(stderr, "\n"); + fprintf(stderr, " %s [options] segment:bus:device.function\n", argv[0]); + fprintf(stderr, "\n"); + exit(KSFT_SKIP); +} diff --git a/tools/testing/selftests/vfio/lib/vfio_pci_driver.c b/tools/testing/selftests/vfio/lib/vfio_pci_driver.c new file mode 100644 index 000000000000..e5e8723ecb41 --- /dev/null +++ b/tools/testing/selftests/vfio/lib/vfio_pci_driver.c @@ -0,0 +1,126 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include <stdio.h> + +#include "../../../kselftest.h" +#include <vfio_util.h> + +#ifdef __x86_64__ +extern struct vfio_pci_driver_ops dsa_ops; +extern struct vfio_pci_driver_ops ioat_ops; +#endif + +static struct vfio_pci_driver_ops *driver_ops[] = { +#ifdef __x86_64__ + &dsa_ops, + &ioat_ops, +#endif +}; + +void vfio_pci_driver_probe(struct vfio_pci_device *device) +{ + struct vfio_pci_driver_ops *ops; + int i; + + VFIO_ASSERT_NULL(device->driver.ops); + + for (i = 0; i < ARRAY_SIZE(driver_ops); i++) { + ops = driver_ops[i]; + + if (ops->probe(device)) + continue; + + printf("Driver found: %s\n", ops->name); + device->driver.ops = ops; + } +} + +static void vfio_check_driver_op(struct vfio_pci_driver *driver, void *op, + const char *op_name) +{ + VFIO_ASSERT_NOT_NULL(driver->ops); + VFIO_ASSERT_NOT_NULL(op, "Driver has no %s()\n", op_name); + VFIO_ASSERT_EQ(driver->initialized, op != driver->ops->init); + VFIO_ASSERT_EQ(driver->memcpy_in_progress, op == driver->ops->memcpy_wait); +} + +#define VFIO_CHECK_DRIVER_OP(_driver, _op) do { \ + struct vfio_pci_driver *__driver = (_driver); \ + vfio_check_driver_op(__driver, __driver->ops->_op, #_op); \ +} while (0) + +void vfio_pci_driver_init(struct vfio_pci_device *device) +{ + struct vfio_pci_driver *driver = &device->driver; + + VFIO_ASSERT_NOT_NULL(driver->region.vaddr); + VFIO_CHECK_DRIVER_OP(driver, init); + + driver->ops->init(device); + + driver->initialized = true; + + printf("%s: region: vaddr %p, iova 0x%lx, size 0x%lx\n", + driver->ops->name, + driver->region.vaddr, + driver->region.iova, + driver->region.size); + + printf("%s: max_memcpy_size 0x%lx, max_memcpy_count 0x%lx\n", + driver->ops->name, + driver->max_memcpy_size, + driver->max_memcpy_count); +} + +void vfio_pci_driver_remove(struct vfio_pci_device *device) +{ + struct vfio_pci_driver *driver = &device->driver; + + VFIO_CHECK_DRIVER_OP(driver, remove); + + driver->ops->remove(device); + driver->initialized = false; +} + +void vfio_pci_driver_send_msi(struct vfio_pci_device *device) +{ + struct vfio_pci_driver *driver = &device->driver; + + VFIO_CHECK_DRIVER_OP(driver, send_msi); + + driver->ops->send_msi(device); +} + +void vfio_pci_driver_memcpy_start(struct vfio_pci_device *device, + iova_t src, iova_t dst, u64 size, + u64 count) +{ + struct vfio_pci_driver *driver = &device->driver; + + VFIO_ASSERT_LE(size, driver->max_memcpy_size); + VFIO_ASSERT_LE(count, driver->max_memcpy_count); + VFIO_CHECK_DRIVER_OP(driver, memcpy_start); + + driver->ops->memcpy_start(device, src, dst, size, count); + driver->memcpy_in_progress = true; +} + +int vfio_pci_driver_memcpy_wait(struct vfio_pci_device *device) +{ + struct vfio_pci_driver *driver = &device->driver; + int r; + + VFIO_CHECK_DRIVER_OP(driver, memcpy_wait); + + r = driver->ops->memcpy_wait(device); + driver->memcpy_in_progress = false; + + return r; +} + +int vfio_pci_driver_memcpy(struct vfio_pci_device *device, + iova_t src, iova_t dst, u64 size) +{ + vfio_pci_driver_memcpy_start(device, src, dst, size, 1); + + return vfio_pci_driver_memcpy_wait(device); +} diff --git a/tools/testing/selftests/vfio/run.sh b/tools/testing/selftests/vfio/run.sh new file mode 100755 index 000000000000..0476b6d7adc3 --- /dev/null +++ b/tools/testing/selftests/vfio/run.sh @@ -0,0 +1,109 @@ +# SPDX-License-Identifier: GPL-2.0-or-later + +# Global variables initialized in main() and then used during cleanup() when +# the script exits. +declare DEVICE_BDF +declare NEW_DRIVER +declare OLD_DRIVER +declare OLD_NUMVFS +declare DRIVER_OVERRIDE + +function write_to() { + # Unfortunately set -x does not show redirects so use echo to manually + # tell the user what commands are being run. + echo "+ echo \"${2}\" > ${1}" + echo "${2}" > ${1} +} + +function bind() { + write_to /sys/bus/pci/drivers/${2}/bind ${1} +} + +function unbind() { + write_to /sys/bus/pci/drivers/${2}/unbind ${1} +} + +function set_sriov_numvfs() { + write_to /sys/bus/pci/devices/${1}/sriov_numvfs ${2} +} + +function set_driver_override() { + write_to /sys/bus/pci/devices/${1}/driver_override ${2} +} + +function clear_driver_override() { + set_driver_override ${1} "" +} + +function cleanup() { + if [ "${NEW_DRIVER}" ]; then unbind ${DEVICE_BDF} ${NEW_DRIVER} ; fi + if [ "${DRIVER_OVERRIDE}" ]; then clear_driver_override ${DEVICE_BDF} ; fi + if [ "${OLD_DRIVER}" ]; then bind ${DEVICE_BDF} ${OLD_DRIVER} ; fi + if [ "${OLD_NUMVFS}" ]; then set_sriov_numvfs ${DEVICE_BDF} ${OLD_NUMVFS} ; fi +} + +function usage() { + echo "usage: $0 [-d segment:bus:device.function] [-s] [-h] [cmd ...]" >&2 + echo >&2 + echo " -d: The BDF of the device to use for the test (required)" >&2 + echo " -h: Show this help message" >&2 + echo " -s: Drop into a shell rather than running a command" >&2 + echo >&2 + echo " cmd: The command to run and arguments to pass to it." >&2 + echo " Required when not using -s. The SBDF will be " >&2 + echo " appended to the argument list." >&2 + exit 1 +} + +function main() { + local shell + + while getopts "d:hs" opt; do + case $opt in + d) DEVICE_BDF="$OPTARG" ;; + s) shell=true ;; + *) usage ;; + esac + done + + # Shift past all optional arguments. + shift $((OPTIND - 1)) + + # Check that the user passed in the command to run. + [ ! "${shell}" ] && [ $# = 0 ] && usage + + # Check that the user passed in a BDF. + [ "${DEVICE_BDF}" ] || usage + + trap cleanup EXIT + set -e + + test -d /sys/bus/pci/devices/${DEVICE_BDF} + + if [ -f /sys/bus/pci/devices/${DEVICE_BDF}/sriov_numvfs ]; then + OLD_NUMVFS=$(cat /sys/bus/pci/devices/${DEVICE_BDF}/sriov_numvfs) + set_sriov_numvfs ${DEVICE_BDF} 0 + fi + + if [ -L /sys/bus/pci/devices/${DEVICE_BDF}/driver ]; then + OLD_DRIVER=$(basename $(readlink -m /sys/bus/pci/devices/${DEVICE_BDF}/driver)) + unbind ${DEVICE_BDF} ${OLD_DRIVER} + fi + + set_driver_override ${DEVICE_BDF} vfio-pci + DRIVER_OVERRIDE=true + + bind ${DEVICE_BDF} vfio-pci + NEW_DRIVER=vfio-pci + + echo + if [ "${shell}" ]; then + echo "Dropping into ${SHELL} with VFIO_SELFTESTS_BDF=${DEVICE_BDF}" + VFIO_SELFTESTS_BDF=${DEVICE_BDF} ${SHELL} + else + "$@" ${DEVICE_BDF} + fi + echo +} + +main "$@" diff --git a/tools/testing/selftests/vfio/vfio_dma_mapping_test.c b/tools/testing/selftests/vfio/vfio_dma_mapping_test.c new file mode 100644 index 000000000000..ab19c54a774d --- /dev/null +++ b/tools/testing/selftests/vfio/vfio_dma_mapping_test.c @@ -0,0 +1,199 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include <stdio.h> +#include <sys/mman.h> +#include <unistd.h> + +#include <linux/limits.h> +#include <linux/mman.h> +#include <linux/sizes.h> +#include <linux/vfio.h> + +#include <vfio_util.h> + +#include "../kselftest_harness.h" + +static const char *device_bdf; + +struct iommu_mapping { + u64 pgd; + u64 p4d; + u64 pud; + u64 pmd; + u64 pte; +}; + +static void parse_next_value(char **line, u64 *value) +{ + char *token; + + token = strtok_r(*line, " \t|\n", line); + if (!token) + return; + + /* Caller verifies `value`. No need to check return value. */ + sscanf(token, "0x%lx", value); +} + +static int intel_iommu_mapping_get(const char *bdf, u64 iova, + struct iommu_mapping *mapping) +{ + char iommu_mapping_path[PATH_MAX], line[PATH_MAX]; + u64 line_iova = -1; + int ret = -ENOENT; + FILE *file; + char *rest; + + snprintf(iommu_mapping_path, sizeof(iommu_mapping_path), + "/sys/kernel/debug/iommu/intel/%s/domain_translation_struct", + bdf); + + printf("Searching for IOVA 0x%lx in %s\n", iova, iommu_mapping_path); + + file = fopen(iommu_mapping_path, "r"); + VFIO_ASSERT_NOT_NULL(file, "fopen(%s) failed", iommu_mapping_path); + + while (fgets(line, sizeof(line), file)) { + rest = line; + + parse_next_value(&rest, &line_iova); + if (line_iova != (iova / getpagesize())) + continue; + + /* + * Ensure each struct field is initialized in case of empty + * page table values. + */ + memset(mapping, 0, sizeof(*mapping)); + parse_next_value(&rest, &mapping->pgd); + parse_next_value(&rest, &mapping->p4d); + parse_next_value(&rest, &mapping->pud); + parse_next_value(&rest, &mapping->pmd); + parse_next_value(&rest, &mapping->pte); + + ret = 0; + break; + } + + fclose(file); + + if (ret) + printf("IOVA not found\n"); + + return ret; +} + +static int iommu_mapping_get(const char *bdf, u64 iova, + struct iommu_mapping *mapping) +{ + if (!access("/sys/kernel/debug/iommu/intel", F_OK)) + return intel_iommu_mapping_get(bdf, iova, mapping); + + return -EOPNOTSUPP; +} + +FIXTURE(vfio_dma_mapping_test) { + struct vfio_pci_device *device; +}; + +FIXTURE_VARIANT(vfio_dma_mapping_test) { + const char *iommu_mode; + u64 size; + int mmap_flags; +}; + +#define FIXTURE_VARIANT_ADD_IOMMU_MODE(_iommu_mode, _name, _size, _mmap_flags) \ +FIXTURE_VARIANT_ADD(vfio_dma_mapping_test, _iommu_mode ## _ ## _name) { \ + .iommu_mode = #_iommu_mode, \ + .size = (_size), \ + .mmap_flags = MAP_ANONYMOUS | MAP_PRIVATE | (_mmap_flags), \ +} + +FIXTURE_VARIANT_ADD_ALL_IOMMU_MODES(anonymous, 0, 0); +FIXTURE_VARIANT_ADD_ALL_IOMMU_MODES(anonymous_hugetlb_2mb, SZ_2M, MAP_HUGETLB | MAP_HUGE_2MB); +FIXTURE_VARIANT_ADD_ALL_IOMMU_MODES(anonymous_hugetlb_1gb, SZ_1G, MAP_HUGETLB | MAP_HUGE_1GB); + +FIXTURE_SETUP(vfio_dma_mapping_test) +{ + self->device = vfio_pci_device_init(device_bdf, variant->iommu_mode); +} + +FIXTURE_TEARDOWN(vfio_dma_mapping_test) +{ + vfio_pci_device_cleanup(self->device); +} + +TEST_F(vfio_dma_mapping_test, dma_map_unmap) +{ + const u64 size = variant->size ?: getpagesize(); + const int flags = variant->mmap_flags; + struct vfio_dma_region region; + struct iommu_mapping mapping; + u64 mapping_size = size; + int rc; + + region.vaddr = mmap(NULL, size, PROT_READ | PROT_WRITE, flags, -1, 0); + + /* Skip the test if there aren't enough HugeTLB pages available. */ + if (flags & MAP_HUGETLB && region.vaddr == MAP_FAILED) + SKIP(return, "mmap() failed: %s (%d)\n", strerror(errno), errno); + else + ASSERT_NE(region.vaddr, MAP_FAILED); + + region.iova = (u64)region.vaddr; + region.size = size; + + vfio_pci_dma_map(self->device, ®ion); + printf("Mapped HVA %p (size 0x%lx) at IOVA 0x%lx\n", region.vaddr, size, region.iova); + + ASSERT_EQ(region.iova, to_iova(self->device, region.vaddr)); + + rc = iommu_mapping_get(device_bdf, region.iova, &mapping); + if (rc == -EOPNOTSUPP) + goto unmap; + + /* + * IOMMUFD compatibility-mode does not support huge mappings when + * using VFIO_TYPE1_IOMMU. + */ + if (!strcmp(variant->iommu_mode, "iommufd_compat_type1")) + mapping_size = SZ_4K; + + ASSERT_EQ(0, rc); + printf("Found IOMMU mappings for IOVA 0x%lx:\n", region.iova); + printf("PGD: 0x%016lx\n", mapping.pgd); + printf("P4D: 0x%016lx\n", mapping.p4d); + printf("PUD: 0x%016lx\n", mapping.pud); + printf("PMD: 0x%016lx\n", mapping.pmd); + printf("PTE: 0x%016lx\n", mapping.pte); + + switch (mapping_size) { + case SZ_4K: + ASSERT_NE(0, mapping.pte); + break; + case SZ_2M: + ASSERT_EQ(0, mapping.pte); + ASSERT_NE(0, mapping.pmd); + break; + case SZ_1G: + ASSERT_EQ(0, mapping.pte); + ASSERT_EQ(0, mapping.pmd); + ASSERT_NE(0, mapping.pud); + break; + default: + VFIO_FAIL("Unrecognized size: 0x%lx\n", mapping_size); + } + +unmap: + vfio_pci_dma_unmap(self->device, ®ion); + printf("Unmapped IOVA 0x%lx\n", region.iova); + ASSERT_EQ(INVALID_IOVA, __to_iova(self->device, region.vaddr)); + ASSERT_NE(0, iommu_mapping_get(device_bdf, region.iova, &mapping)); + + ASSERT_TRUE(!munmap(region.vaddr, size)); +} + +int main(int argc, char *argv[]) +{ + device_bdf = vfio_selftests_get_bdf(&argc, argv); + return test_harness_run(argc, argv); +} diff --git a/tools/testing/selftests/vfio/vfio_iommufd_setup_test.c b/tools/testing/selftests/vfio/vfio_iommufd_setup_test.c new file mode 100644 index 000000000000..3655106b912d --- /dev/null +++ b/tools/testing/selftests/vfio/vfio_iommufd_setup_test.c @@ -0,0 +1,127 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <uapi/linux/types.h> +#include <linux/limits.h> +#include <linux/sizes.h> +#include <linux/vfio.h> +#include <linux/iommufd.h> + +#include <stdint.h> +#include <stdio.h> +#include <sys/ioctl.h> +#include <unistd.h> + +#include <vfio_util.h> +#include "../kselftest_harness.h" + +static const char iommu_dev_path[] = "/dev/iommu"; +static const char *cdev_path; + +static int vfio_device_bind_iommufd_ioctl(int cdev_fd, int iommufd) +{ + struct vfio_device_bind_iommufd bind_args = { + .argsz = sizeof(bind_args), + .iommufd = iommufd, + }; + + return ioctl(cdev_fd, VFIO_DEVICE_BIND_IOMMUFD, &bind_args); +} + +static int vfio_device_get_info_ioctl(int cdev_fd) +{ + struct vfio_device_info info_args = { .argsz = sizeof(info_args) }; + + return ioctl(cdev_fd, VFIO_DEVICE_GET_INFO, &info_args); +} + +static int vfio_device_ioas_alloc_ioctl(int iommufd, struct iommu_ioas_alloc *alloc_args) +{ + *alloc_args = (struct iommu_ioas_alloc){ + .size = sizeof(struct iommu_ioas_alloc), + }; + + return ioctl(iommufd, IOMMU_IOAS_ALLOC, alloc_args); +} + +static int vfio_device_attach_iommufd_pt_ioctl(int cdev_fd, u32 pt_id) +{ + struct vfio_device_attach_iommufd_pt attach_args = { + .argsz = sizeof(attach_args), + .pt_id = pt_id, + }; + + return ioctl(cdev_fd, VFIO_DEVICE_ATTACH_IOMMUFD_PT, &attach_args); +} + +static int vfio_device_detach_iommufd_pt_ioctl(int cdev_fd) +{ + struct vfio_device_detach_iommufd_pt detach_args = { + .argsz = sizeof(detach_args), + }; + + return ioctl(cdev_fd, VFIO_DEVICE_DETACH_IOMMUFD_PT, &detach_args); +} + +FIXTURE(vfio_cdev) { + int cdev_fd; + int iommufd; +}; + +FIXTURE_SETUP(vfio_cdev) +{ + ASSERT_LE(0, (self->cdev_fd = open(cdev_path, O_RDWR, 0))); + ASSERT_LE(0, (self->iommufd = open(iommu_dev_path, O_RDWR, 0))); +} + +FIXTURE_TEARDOWN(vfio_cdev) +{ + ASSERT_EQ(0, close(self->cdev_fd)); + ASSERT_EQ(0, close(self->iommufd)); +} + +TEST_F(vfio_cdev, bind) +{ + ASSERT_EQ(0, vfio_device_bind_iommufd_ioctl(self->cdev_fd, self->iommufd)); + ASSERT_EQ(0, vfio_device_get_info_ioctl(self->cdev_fd)); +} + +TEST_F(vfio_cdev, get_info_without_bind_fails) +{ + ASSERT_NE(0, vfio_device_get_info_ioctl(self->cdev_fd)); +} + +TEST_F(vfio_cdev, bind_bad_iommufd_fails) +{ + ASSERT_NE(0, vfio_device_bind_iommufd_ioctl(self->cdev_fd, -2)); +} + +TEST_F(vfio_cdev, repeated_bind_fails) +{ + ASSERT_EQ(0, vfio_device_bind_iommufd_ioctl(self->cdev_fd, self->iommufd)); + ASSERT_NE(0, vfio_device_bind_iommufd_ioctl(self->cdev_fd, self->iommufd)); +} + +TEST_F(vfio_cdev, attach_detatch_pt) +{ + struct iommu_ioas_alloc alloc_args; + + ASSERT_EQ(0, vfio_device_bind_iommufd_ioctl(self->cdev_fd, self->iommufd)); + ASSERT_EQ(0, vfio_device_ioas_alloc_ioctl(self->iommufd, &alloc_args)); + ASSERT_EQ(0, vfio_device_attach_iommufd_pt_ioctl(self->cdev_fd, alloc_args.out_ioas_id)); + ASSERT_EQ(0, vfio_device_detach_iommufd_pt_ioctl(self->cdev_fd)); +} + +TEST_F(vfio_cdev, attach_invalid_pt_fails) +{ + ASSERT_EQ(0, vfio_device_bind_iommufd_ioctl(self->cdev_fd, self->iommufd)); + ASSERT_NE(0, vfio_device_attach_iommufd_pt_ioctl(self->cdev_fd, UINT32_MAX)); +} + +int main(int argc, char *argv[]) +{ + const char *device_bdf = vfio_selftests_get_bdf(&argc, argv); + + cdev_path = vfio_pci_get_cdev_path(device_bdf); + printf("Using cdev device %s\n", cdev_path); + + return test_harness_run(argc, argv); +} diff --git a/tools/testing/selftests/vfio/vfio_pci_device_test.c b/tools/testing/selftests/vfio/vfio_pci_device_test.c new file mode 100644 index 000000000000..7a270698e4d2 --- /dev/null +++ b/tools/testing/selftests/vfio/vfio_pci_device_test.c @@ -0,0 +1,176 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include <fcntl.h> +#include <stdlib.h> + +#include <sys/ioctl.h> +#include <sys/mman.h> + +#include <linux/limits.h> +#include <linux/pci_regs.h> +#include <linux/sizes.h> +#include <linux/vfio.h> + +#include <vfio_util.h> + +#include "../kselftest_harness.h" + +static const char *device_bdf; + +/* + * Limit the number of MSIs enabled/disabled by the test regardless of the + * number of MSIs the device itself supports, e.g. to avoid hitting IRTE limits. + */ +#define MAX_TEST_MSI 16U + +FIXTURE(vfio_pci_device_test) { + struct vfio_pci_device *device; +}; + +FIXTURE_SETUP(vfio_pci_device_test) +{ + self->device = vfio_pci_device_init(device_bdf, default_iommu_mode); +} + +FIXTURE_TEARDOWN(vfio_pci_device_test) +{ + vfio_pci_device_cleanup(self->device); +} + +#define read_pci_id_from_sysfs(_file) ({ \ + char __sysfs_path[PATH_MAX]; \ + char __buf[32]; \ + int __fd; \ + \ + snprintf(__sysfs_path, PATH_MAX, "/sys/bus/pci/devices/%s/%s", device_bdf, _file); \ + ASSERT_GT((__fd = open(__sysfs_path, O_RDONLY)), 0); \ + ASSERT_GT(read(__fd, __buf, ARRAY_SIZE(__buf)), 0); \ + ASSERT_EQ(0, close(__fd)); \ + (u16)strtoul(__buf, NULL, 0); \ +}) + +TEST_F(vfio_pci_device_test, config_space_read_write) +{ + u16 vendor, device; + u16 command; + + /* Check that Vendor and Device match what the kernel reports. */ + vendor = read_pci_id_from_sysfs("vendor"); + device = read_pci_id_from_sysfs("device"); + ASSERT_TRUE(vfio_pci_device_match(self->device, vendor, device)); + + printf("Vendor: %04x, Device: %04x\n", vendor, device); + + command = vfio_pci_config_readw(self->device, PCI_COMMAND); + ASSERT_FALSE(command & PCI_COMMAND_MASTER); + + vfio_pci_config_writew(self->device, PCI_COMMAND, command | PCI_COMMAND_MASTER); + command = vfio_pci_config_readw(self->device, PCI_COMMAND); + ASSERT_TRUE(command & PCI_COMMAND_MASTER); + printf("Enabled Bus Mastering (command: %04x)\n", command); + + vfio_pci_config_writew(self->device, PCI_COMMAND, command & ~PCI_COMMAND_MASTER); + command = vfio_pci_config_readw(self->device, PCI_COMMAND); + ASSERT_FALSE(command & PCI_COMMAND_MASTER); + printf("Disabled Bus Mastering (command: %04x)\n", command); +} + +TEST_F(vfio_pci_device_test, validate_bars) +{ + struct vfio_pci_bar *bar; + int i; + + for (i = 0; i < PCI_STD_NUM_BARS; i++) { + bar = &self->device->bars[i]; + + if (!(bar->info.flags & VFIO_REGION_INFO_FLAG_MMAP)) { + printf("BAR %d does not support mmap()\n", i); + ASSERT_EQ(NULL, bar->vaddr); + continue; + } + + /* + * BARs that support mmap() should be automatically mapped by + * vfio_pci_device_init(). + */ + ASSERT_NE(NULL, bar->vaddr); + ASSERT_NE(0, bar->info.size); + printf("BAR %d mapped at %p (size 0x%llx)\n", i, bar->vaddr, bar->info.size); + } +} + +FIXTURE(vfio_pci_irq_test) { + struct vfio_pci_device *device; +}; + +FIXTURE_VARIANT(vfio_pci_irq_test) { + int irq_index; +}; + +FIXTURE_VARIANT_ADD(vfio_pci_irq_test, msi) { + .irq_index = VFIO_PCI_MSI_IRQ_INDEX, +}; + +FIXTURE_VARIANT_ADD(vfio_pci_irq_test, msix) { + .irq_index = VFIO_PCI_MSIX_IRQ_INDEX, +}; + +FIXTURE_SETUP(vfio_pci_irq_test) +{ + self->device = vfio_pci_device_init(device_bdf, default_iommu_mode); +} + +FIXTURE_TEARDOWN(vfio_pci_irq_test) +{ + vfio_pci_device_cleanup(self->device); +} + +TEST_F(vfio_pci_irq_test, enable_trigger_disable) +{ + bool msix = variant->irq_index == VFIO_PCI_MSIX_IRQ_INDEX; + int msi_eventfd; + u32 count; + u64 value; + int i; + + if (msix) + count = self->device->msix_info.count; + else + count = self->device->msi_info.count; + + count = min(count, MAX_TEST_MSI); + + if (!count) + SKIP(return, "MSI%s: not supported\n", msix ? "-x" : ""); + + vfio_pci_irq_enable(self->device, variant->irq_index, 0, count); + printf("MSI%s: enabled %d interrupts\n", msix ? "-x" : "", count); + + for (i = 0; i < count; i++) { + msi_eventfd = self->device->msi_eventfds[i]; + + fcntl_set_nonblock(msi_eventfd); + ASSERT_EQ(-1, read(msi_eventfd, &value, 8)); + ASSERT_EQ(EAGAIN, errno); + + vfio_pci_irq_trigger(self->device, variant->irq_index, i); + + ASSERT_EQ(8, read(msi_eventfd, &value, 8)); + ASSERT_EQ(1, value); + } + + vfio_pci_irq_disable(self->device, variant->irq_index); +} + +TEST_F(vfio_pci_device_test, reset) +{ + if (!(self->device->info.flags & VFIO_DEVICE_FLAGS_RESET)) + SKIP(return, "Device does not support reset\n"); + + vfio_pci_device_reset(self->device); +} + +int main(int argc, char *argv[]) +{ + device_bdf = vfio_selftests_get_bdf(&argc, argv); + return test_harness_run(argc, argv); +} diff --git a/tools/testing/selftests/vfio/vfio_pci_driver_test.c b/tools/testing/selftests/vfio/vfio_pci_driver_test.c new file mode 100644 index 000000000000..2dbd70b7db62 --- /dev/null +++ b/tools/testing/selftests/vfio/vfio_pci_driver_test.c @@ -0,0 +1,244 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include <sys/ioctl.h> +#include <sys/mman.h> + +#include <linux/sizes.h> +#include <linux/vfio.h> + +#include <vfio_util.h> + +#include "../kselftest_harness.h" + +static const char *device_bdf; + +#define ASSERT_NO_MSI(_eventfd) do { \ + u64 __value; \ + \ + ASSERT_EQ(-1, read(_eventfd, &__value, 8)); \ + ASSERT_EQ(EAGAIN, errno); \ +} while (0) + +static void region_setup(struct vfio_pci_device *device, + struct vfio_dma_region *region, u64 size) +{ + const int flags = MAP_SHARED | MAP_ANONYMOUS; + const int prot = PROT_READ | PROT_WRITE; + void *vaddr; + + vaddr = mmap(NULL, size, prot, flags, -1, 0); + VFIO_ASSERT_NE(vaddr, MAP_FAILED); + + region->vaddr = vaddr; + region->iova = (u64)vaddr; + region->size = size; + + vfio_pci_dma_map(device, region); +} + +static void region_teardown(struct vfio_pci_device *device, + struct vfio_dma_region *region) +{ + vfio_pci_dma_unmap(device, region); + VFIO_ASSERT_EQ(munmap(region->vaddr, region->size), 0); +} + +FIXTURE(vfio_pci_driver_test) { + struct vfio_pci_device *device; + struct vfio_dma_region memcpy_region; + void *vaddr; + int msi_fd; + + u64 size; + void *src; + void *dst; + iova_t src_iova; + iova_t dst_iova; + iova_t unmapped_iova; +}; + +FIXTURE_VARIANT(vfio_pci_driver_test) { + const char *iommu_mode; +}; + +#define FIXTURE_VARIANT_ADD_IOMMU_MODE(_iommu_mode) \ +FIXTURE_VARIANT_ADD(vfio_pci_driver_test, _iommu_mode) { \ + .iommu_mode = #_iommu_mode, \ +} + +FIXTURE_VARIANT_ADD_ALL_IOMMU_MODES(); + +FIXTURE_SETUP(vfio_pci_driver_test) +{ + struct vfio_pci_driver *driver; + + self->device = vfio_pci_device_init(device_bdf, variant->iommu_mode); + + driver = &self->device->driver; + + region_setup(self->device, &self->memcpy_region, SZ_1G); + region_setup(self->device, &driver->region, SZ_2M); + + /* Any IOVA that doesn't overlap memcpy_region and driver->region. */ + self->unmapped_iova = 8UL * SZ_1G; + + vfio_pci_driver_init(self->device); + self->msi_fd = self->device->msi_eventfds[driver->msi]; + + /* + * Use the maximum size supported by the device for memcpy operations, + * slimmed down to fit into the memcpy region (divided by 2 so src and + * dst regions do not overlap). + */ + self->size = self->device->driver.max_memcpy_size; + self->size = min(self->size, self->memcpy_region.size / 2); + + self->src = self->memcpy_region.vaddr; + self->dst = self->src + self->size; + + self->src_iova = to_iova(self->device, self->src); + self->dst_iova = to_iova(self->device, self->dst); +} + +FIXTURE_TEARDOWN(vfio_pci_driver_test) +{ + struct vfio_pci_driver *driver = &self->device->driver; + + vfio_pci_driver_remove(self->device); + + region_teardown(self->device, &self->memcpy_region); + region_teardown(self->device, &driver->region); + + vfio_pci_device_cleanup(self->device); +} + +TEST_F(vfio_pci_driver_test, init_remove) +{ + int i; + + for (i = 0; i < 10; i++) { + vfio_pci_driver_remove(self->device); + vfio_pci_driver_init(self->device); + } +} + +TEST_F(vfio_pci_driver_test, memcpy_success) +{ + fcntl_set_nonblock(self->msi_fd); + + memset(self->src, 'x', self->size); + memset(self->dst, 'y', self->size); + + ASSERT_EQ(0, vfio_pci_driver_memcpy(self->device, + self->src_iova, + self->dst_iova, + self->size)); + + ASSERT_EQ(0, memcmp(self->src, self->dst, self->size)); + ASSERT_NO_MSI(self->msi_fd); +} + +TEST_F(vfio_pci_driver_test, memcpy_from_unmapped_iova) +{ + fcntl_set_nonblock(self->msi_fd); + + /* + * Ignore the return value since not all devices will detect and report + * accesses to unmapped IOVAs as errors. + */ + vfio_pci_driver_memcpy(self->device, self->unmapped_iova, + self->dst_iova, self->size); + + ASSERT_NO_MSI(self->msi_fd); +} + +TEST_F(vfio_pci_driver_test, memcpy_to_unmapped_iova) +{ + fcntl_set_nonblock(self->msi_fd); + + /* + * Ignore the return value since not all devices will detect and report + * accesses to unmapped IOVAs as errors. + */ + vfio_pci_driver_memcpy(self->device, self->src_iova, + self->unmapped_iova, self->size); + + ASSERT_NO_MSI(self->msi_fd); +} + +TEST_F(vfio_pci_driver_test, send_msi) +{ + u64 value; + + vfio_pci_driver_send_msi(self->device); + ASSERT_EQ(8, read(self->msi_fd, &value, 8)); + ASSERT_EQ(1, value); +} + +TEST_F(vfio_pci_driver_test, mix_and_match) +{ + u64 value; + int i; + + for (i = 0; i < 10; i++) { + memset(self->src, 'x', self->size); + memset(self->dst, 'y', self->size); + + ASSERT_EQ(0, vfio_pci_driver_memcpy(self->device, + self->src_iova, + self->dst_iova, + self->size)); + + ASSERT_EQ(0, memcmp(self->src, self->dst, self->size)); + + vfio_pci_driver_memcpy(self->device, + self->unmapped_iova, + self->dst_iova, + self->size); + + vfio_pci_driver_send_msi(self->device); + ASSERT_EQ(8, read(self->msi_fd, &value, 8)); + ASSERT_EQ(1, value); + } +} + +TEST_F_TIMEOUT(vfio_pci_driver_test, memcpy_storm, 60) +{ + struct vfio_pci_driver *driver = &self->device->driver; + u64 total_size; + u64 count; + + fcntl_set_nonblock(self->msi_fd); + + /* + * Perform up to 250GiB worth of DMA reads and writes across several + * memcpy operations. Some devices can support even more but the test + * will take too long. + */ + total_size = 250UL * SZ_1G; + count = min(total_size / self->size, driver->max_memcpy_count); + + printf("Kicking off %lu memcpys of size 0x%lx\n", count, self->size); + vfio_pci_driver_memcpy_start(self->device, + self->src_iova, + self->dst_iova, + self->size, count); + + ASSERT_EQ(0, vfio_pci_driver_memcpy_wait(self->device)); + ASSERT_NO_MSI(self->msi_fd); +} + +int main(int argc, char *argv[]) +{ + struct vfio_pci_device *device; + + device_bdf = vfio_selftests_get_bdf(&argc, argv); + + device = vfio_pci_device_init(device_bdf, default_iommu_mode); + if (!device->driver.ops) { + fprintf(stderr, "No driver found for device %s\n", device_bdf); + return KSFT_SKIP; + } + vfio_pci_device_cleanup(device); + + return test_harness_run(argc, argv); +} |