diff options
Diffstat (limited to 'tools/testing')
512 files changed, 30684 insertions, 5174 deletions
diff --git a/tools/testing/cxl/Kbuild b/tools/testing/cxl/Kbuild index 1acdf2fc31c5..82e49ab0937d 100644 --- a/tools/testing/cxl/Kbuild +++ b/tools/testing/cxl/Kbuild @@ -3,8 +3,11 @@ ldflags-y += --wrap=acpi_table_parse_cedt ldflags-y += --wrap=is_acpi_device_node ldflags-y += --wrap=acpi_evaluate_integer ldflags-y += --wrap=acpi_pci_find_root -ldflags-y += --wrap=pci_walk_bus 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 DRIVERS := ../../../drivers CXL_SRC := $(DRIVERS)/cxl @@ -23,15 +26,26 @@ obj-m += cxl_pmem.o cxl_pmem-y := $(CXL_SRC)/pmem.o cxl_pmem-y += config_check.o +obj-m += cxl_port.o + +cxl_port-y := $(CXL_SRC)/port.o +cxl_port-y += config_check.o + +obj-m += cxl_mem.o + +cxl_mem-y := $(CXL_SRC)/mem.o +cxl_mem-y += mock_mem.o +cxl_mem-y += config_check.o + obj-m += cxl_core.o -cxl_core-y := $(CXL_CORE_SRC)/bus.o +cxl_core-y := $(CXL_CORE_SRC)/port.o cxl_core-y += $(CXL_CORE_SRC)/pmem.o cxl_core-y += $(CXL_CORE_SRC)/regs.o cxl_core-y += $(CXL_CORE_SRC)/memdev.o cxl_core-y += $(CXL_CORE_SRC)/mbox.o +cxl_core-y += $(CXL_CORE_SRC)/pci.o +cxl_core-y += $(CXL_CORE_SRC)/hdm.o cxl_core-y += config_check.o -cxl_core-y += mock_pmem.o - obj-m += test/ diff --git a/tools/testing/cxl/mock_acpi.c b/tools/testing/cxl/mock_acpi.c index 4c8a493ace56..55813de26d46 100644 --- a/tools/testing/cxl/mock_acpi.c +++ b/tools/testing/cxl/mock_acpi.c @@ -4,7 +4,6 @@ #include <linux/platform_device.h> #include <linux/device.h> #include <linux/acpi.h> -#include <linux/pci.h> #include <cxl.h> #include "test/mock.h" @@ -34,76 +33,3 @@ out: put_cxl_mock_ops(index); return found; } - -static int match_add_root_port(struct pci_dev *pdev, void *data) -{ - struct cxl_walk_context *ctx = data; - struct pci_bus *root_bus = ctx->root; - struct cxl_port *port = ctx->port; - int type = pci_pcie_type(pdev); - struct device *dev = ctx->dev; - u32 lnkcap, port_num; - int rc; - - if (pdev->bus != root_bus) - return 0; - if (!pci_is_pcie(pdev)) - return 0; - if (type != PCI_EXP_TYPE_ROOT_PORT) - return 0; - if (pci_read_config_dword(pdev, pci_pcie_cap(pdev) + PCI_EXP_LNKCAP, - &lnkcap) != PCIBIOS_SUCCESSFUL) - return 0; - - /* TODO walk DVSEC to find component register base */ - port_num = FIELD_GET(PCI_EXP_LNKCAP_PN, lnkcap); - rc = cxl_add_dport(port, &pdev->dev, port_num, CXL_RESOURCE_NONE); - if (rc) { - dev_err(dev, "failed to add dport: %s (%d)\n", - dev_name(&pdev->dev), rc); - ctx->error = rc; - return rc; - } - ctx->count++; - - dev_dbg(dev, "add dport%d: %s\n", port_num, dev_name(&pdev->dev)); - - return 0; -} - -static int mock_add_root_port(struct platform_device *pdev, void *data) -{ - struct cxl_walk_context *ctx = data; - struct cxl_port *port = ctx->port; - struct device *dev = ctx->dev; - int rc; - - rc = cxl_add_dport(port, &pdev->dev, pdev->id, CXL_RESOURCE_NONE); - if (rc) { - dev_err(dev, "failed to add dport: %s (%d)\n", - dev_name(&pdev->dev), rc); - ctx->error = rc; - return rc; - } - ctx->count++; - - dev_dbg(dev, "add dport%d: %s\n", pdev->id, dev_name(&pdev->dev)); - - return 0; -} - -int match_add_root_ports(struct pci_dev *dev, void *data) -{ - int index, rc; - struct cxl_mock_ops *ops = get_cxl_mock_ops(&index); - struct platform_device *pdev = (struct platform_device *) dev; - - if (ops && ops->is_mock_port(pdev)) - rc = mock_add_root_port(pdev, data); - else - rc = match_add_root_port(dev, data); - - put_cxl_mock_ops(index); - - return rc; -} diff --git a/tools/testing/cxl/mock_mem.c b/tools/testing/cxl/mock_mem.c new file mode 100644 index 000000000000..d1dec5845139 --- /dev/null +++ b/tools/testing/cxl/mock_mem.c @@ -0,0 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright(c) 2022 Intel Corporation. All rights reserved. */ + +#include <linux/types.h> + +struct cxl_dev_state; +bool cxl_dvsec_decode_init(struct cxl_dev_state *cxlds) +{ + return true; +} diff --git a/tools/testing/cxl/mock_pmem.c b/tools/testing/cxl/mock_pmem.c deleted file mode 100644 index f7315e6f52c0..000000000000 --- a/tools/testing/cxl/mock_pmem.c +++ /dev/null @@ -1,24 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* Copyright(c) 2021 Intel Corporation. All rights reserved. */ -#include <cxl.h> -#include "test/mock.h" -#include <core/core.h> - -int match_nvdimm_bridge(struct device *dev, const void *data) -{ - int index, rc = 0; - struct cxl_mock_ops *ops = get_cxl_mock_ops(&index); - const struct cxl_nvdimm *cxl_nvd = data; - - if (ops) { - if (dev->type == &cxl_nvdimm_bridge_type && - (ops->is_mock_dev(dev->parent->parent) == - ops->is_mock_dev(cxl_nvd->dev.parent->parent))) - rc = 1; - } else - rc = dev->type == &cxl_nvdimm_bridge_type; - - put_cxl_mock_ops(index); - - return rc; -} diff --git a/tools/testing/cxl/test/cxl.c b/tools/testing/cxl/test/cxl.c index 736d99006fb7..431f2bddf6c8 100644 --- a/tools/testing/cxl/test/cxl.c +++ b/tools/testing/cxl/test/cxl.c @@ -8,16 +8,25 @@ #include <linux/acpi.h> #include <linux/pci.h> #include <linux/mm.h> +#include <cxlmem.h> #include "mock.h" -#define NR_CXL_HOST_BRIDGES 4 +#define NR_CXL_HOST_BRIDGES 2 #define NR_CXL_ROOT_PORTS 2 +#define NR_CXL_SWITCH_PORTS 2 +#define NR_CXL_PORT_DECODERS 2 static struct platform_device *cxl_acpi; static struct platform_device *cxl_host_bridge[NR_CXL_HOST_BRIDGES]; static struct platform_device *cxl_root_port[NR_CXL_HOST_BRIDGES * NR_CXL_ROOT_PORTS]; -struct platform_device *cxl_mem[NR_CXL_HOST_BRIDGES * NR_CXL_ROOT_PORTS]; +static struct platform_device + *cxl_switch_uport[NR_CXL_HOST_BRIDGES * NR_CXL_ROOT_PORTS]; +static struct platform_device + *cxl_switch_dport[NR_CXL_HOST_BRIDGES * NR_CXL_ROOT_PORTS * + NR_CXL_SWITCH_PORTS]; +struct platform_device + *cxl_mem[NR_CXL_HOST_BRIDGES * NR_CXL_ROOT_PORTS * NR_CXL_SWITCH_PORTS]; static struct acpi_device acpi0017_mock; static struct acpi_device host_bridge[NR_CXL_HOST_BRIDGES] = { @@ -27,12 +36,6 @@ static struct acpi_device host_bridge[NR_CXL_HOST_BRIDGES] = { [1] = { .handle = &host_bridge[1], }, - [2] = { - .handle = &host_bridge[2], - }, - [3] = { - .handle = &host_bridge[3], - }, }; static bool is_mock_dev(struct device *dev) @@ -70,7 +73,7 @@ static struct { } cfmws0; struct { struct acpi_cedt_cfmws cfmws; - u32 target[4]; + u32 target[2]; } cfmws1; struct { struct acpi_cedt_cfmws cfmws; @@ -78,7 +81,7 @@ static struct { } cfmws2; struct { struct acpi_cedt_cfmws cfmws; - u32 target[4]; + u32 target[2]; } cfmws3; } __packed mock_cedt = { .cedt = { @@ -104,22 +107,6 @@ static struct { .uid = 1, .cxl_version = ACPI_CEDT_CHBS_VERSION_CXL20, }, - .chbs[2] = { - .header = { - .type = ACPI_CEDT_TYPE_CHBS, - .length = sizeof(mock_cedt.chbs[0]), - }, - .uid = 2, - .cxl_version = ACPI_CEDT_CHBS_VERSION_CXL20, - }, - .chbs[3] = { - .header = { - .type = ACPI_CEDT_TYPE_CHBS, - .length = sizeof(mock_cedt.chbs[0]), - }, - .uid = 3, - .cxl_version = ACPI_CEDT_CHBS_VERSION_CXL20, - }, .cfmws0 = { .cfmws = { .header = { @@ -141,14 +128,14 @@ static struct { .type = ACPI_CEDT_TYPE_CFMWS, .length = sizeof(mock_cedt.cfmws1), }, - .interleave_ways = 2, + .interleave_ways = 1, .granularity = 4, .restrictions = ACPI_CEDT_CFMWS_RESTRICT_TYPE3 | ACPI_CEDT_CFMWS_RESTRICT_VOLATILE, .qtg_id = 1, - .window_size = SZ_256M * 4, + .window_size = SZ_256M * 2, }, - .target = { 0, 1, 2, 3 }, + .target = { 0, 1, }, }, .cfmws2 = { .cfmws = { @@ -171,14 +158,14 @@ static struct { .type = ACPI_CEDT_TYPE_CFMWS, .length = sizeof(mock_cedt.cfmws3), }, - .interleave_ways = 2, + .interleave_ways = 1, .granularity = 4, .restrictions = ACPI_CEDT_CFMWS_RESTRICT_TYPE3 | ACPI_CEDT_CFMWS_RESTRICT_PMEM, .qtg_id = 3, - .window_size = SZ_256M * 4, + .window_size = SZ_256M * 2, }, - .target = { 0, 1, 2, 3 }, + .target = { 0, 1, }, }, }; @@ -317,6 +304,30 @@ static bool is_mock_bridge(struct device *dev) for (i = 0; i < ARRAY_SIZE(cxl_host_bridge); i++) if (dev == &cxl_host_bridge[i]->dev) return true; + return false; +} + +static bool is_mock_port(struct device *dev) +{ + int i; + + if (is_mock_bridge(dev)) + return true; + + for (i = 0; i < ARRAY_SIZE(cxl_root_port); i++) + if (dev == &cxl_root_port[i]->dev) + return true; + + for (i = 0; i < ARRAY_SIZE(cxl_switch_uport); i++) + if (dev == &cxl_switch_uport[i]->dev) + return true; + + for (i = 0; i < ARRAY_SIZE(cxl_switch_dport); i++) + if (dev == &cxl_switch_dport[i]->dev) + return true; + + if (is_cxl_memdev(dev)) + return is_mock_dev(dev->parent); return false; } @@ -358,34 +369,8 @@ static struct acpi_pci_root mock_pci_root[NR_CXL_HOST_BRIDGES] = { [1] = { .bus = &mock_pci_bus[1], }, - [2] = { - .bus = &mock_pci_bus[2], - }, - [3] = { - .bus = &mock_pci_bus[3], - }, }; -static struct platform_device *mock_cxl_root_port(struct pci_bus *bus, int index) -{ - int i; - - for (i = 0; i < ARRAY_SIZE(mock_pci_bus); i++) - if (bus == &mock_pci_bus[i]) - return cxl_root_port[index + i * NR_CXL_ROOT_PORTS]; - return NULL; -} - -static bool is_mock_port(struct platform_device *pdev) -{ - int i; - - for (i = 0; i < ARRAY_SIZE(cxl_root_port); i++) - if (pdev == cxl_root_port[i]) - return true; - return false; -} - static bool is_mock_bus(struct pci_bus *bus) { int i; @@ -405,16 +390,166 @@ static struct acpi_pci_root *mock_acpi_pci_find_root(acpi_handle handle) return &mock_pci_root[host_bridge_index(adev)]; } +static struct cxl_hdm *mock_cxl_setup_hdm(struct cxl_port *port) +{ + struct cxl_hdm *cxlhdm = devm_kzalloc(&port->dev, sizeof(*cxlhdm), GFP_KERNEL); + + if (!cxlhdm) + return ERR_PTR(-ENOMEM); + + cxlhdm->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; + int index; + int target_count; +}; + +static int map_targets(struct device *dev, void *data) +{ + struct platform_device *pdev = to_platform_device(dev); + struct target_map_ctx *ctx = data; + + ctx->target_map[ctx->index++] = pdev->id; + + if (ctx->index > ctx->target_count) { + dev_WARN_ONCE(dev, 1, "too many targets found?\n"); + return -ENXIO; + } + + return 0; +} + +static int mock_cxl_enumerate_decoders(struct cxl_hdm *cxlhdm) +{ + struct cxl_port *port = cxlhdm->port; + struct cxl_port *parent_port = to_cxl_port(port->dev.parent); + int target_count, i; + + if (is_cxl_endpoint(port)) + target_count = 0; + else if (is_cxl_root(parent_port)) + target_count = NR_CXL_ROOT_PORTS; + else + 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; + int rc; + + if (target_count) + cxld = cxl_switch_decoder_alloc(port, target_count); + else + cxld = cxl_endpoint_decoder_alloc(port); + if (IS_ERR(cxld)) { + dev_warn(&port->dev, + "Failed to allocate the decoder\n"); + return PTR_ERR(cxld); + } + + cxld->decoder_range = (struct range) { + .start = 0, + .end = -1, + }; + + cxld->flags = CXL_DECODER_F_ENABLE; + cxld->interleave_ways = min_not_zero(target_count, 1); + cxld->interleave_granularity = SZ_4K; + cxld->target_type = CXL_DECODER_EXPANDER; + + if (target_count) { + rc = device_for_each_child(port->uport, &ctx, + map_targets); + if (rc) { + put_device(&cxld->dev); + return rc; + } + } + + rc = cxl_decoder_add_locked(cxld, target_map); + if (rc) { + put_device(&cxld->dev); + dev_err(&port->dev, "Failed to add decoder\n"); + return rc; + } + + rc = cxl_decoder_autoremove(&port->dev, cxld); + if (rc) + return rc; + dev_dbg(&cxld->dev, "Added to port %s\n", dev_name(&port->dev)); + } + + return 0; +} + +static int mock_cxl_port_enumerate_dports(struct cxl_port *port) +{ + struct device *dev = &port->dev; + struct platform_device **array; + int i, array_size; + + if (port->depth == 1) { + array_size = ARRAY_SIZE(cxl_root_port); + array = cxl_root_port; + } else if (port->depth == 2) { + array_size = ARRAY_SIZE(cxl_switch_dport); + array = cxl_switch_dport; + } else { + dev_WARN_ONCE(&port->dev, 1, "unexpected depth %d\n", + port->depth); + return -ENXIO; + } + + for (i = 0; i < array_size; i++) { + struct platform_device *pdev = array[i]; + struct cxl_dport *dport; + + if (pdev->dev.parent != port->uport) + continue; + + dport = devm_cxl_add_dport(port, &pdev->dev, pdev->id, + CXL_RESOURCE_NONE); + + if (IS_ERR(dport)) { + dev_err(dev, "failed to add dport: %s (%ld)\n", + dev_name(&pdev->dev), PTR_ERR(dport)); + return PTR_ERR(dport); + } + + dev_dbg(dev, "add dport%d: %s\n", pdev->id, + dev_name(&pdev->dev)); + } + + return 0; +} + static struct cxl_mock_ops cxl_mock_ops = { .is_mock_adev = is_mock_adev, .is_mock_bridge = is_mock_bridge, .is_mock_bus = is_mock_bus, .is_mock_port = is_mock_port, .is_mock_dev = is_mock_dev, - .mock_port = mock_cxl_root_port, .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_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, .list = LIST_HEAD_INIT(cxl_mock_ops.list), }; @@ -506,12 +641,17 @@ static __init int cxl_test_init(void) platform_device_put(pdev); goto err_bridge; } + cxl_host_bridge[i] = pdev; + rc = sysfs_create_link(&pdev->dev.kobj, &pdev->dev.kobj, + "physical_node"); + if (rc) + goto err_bridge; } for (i = 0; i < ARRAY_SIZE(cxl_root_port); i++) { struct platform_device *bridge = - cxl_host_bridge[i / NR_CXL_ROOT_PORTS]; + cxl_host_bridge[i % ARRAY_SIZE(cxl_host_bridge)]; struct platform_device *pdev; pdev = platform_device_alloc("cxl_root_port", i); @@ -527,15 +667,52 @@ static __init int cxl_test_init(void) cxl_root_port[i] = pdev; } - BUILD_BUG_ON(ARRAY_SIZE(cxl_mem) != ARRAY_SIZE(cxl_root_port)); + BUILD_BUG_ON(ARRAY_SIZE(cxl_switch_uport) != ARRAY_SIZE(cxl_root_port)); + for (i = 0; i < ARRAY_SIZE(cxl_switch_uport); i++) { + struct platform_device *root_port = cxl_root_port[i]; + struct platform_device *pdev; + + pdev = platform_device_alloc("cxl_switch_uport", i); + if (!pdev) + goto err_port; + pdev->dev.parent = &root_port->dev; + + rc = platform_device_add(pdev); + if (rc) { + platform_device_put(pdev); + goto err_uport; + } + cxl_switch_uport[i] = pdev; + } + + for (i = 0; i < ARRAY_SIZE(cxl_switch_dport); i++) { + struct platform_device *uport = + cxl_switch_uport[i % ARRAY_SIZE(cxl_switch_uport)]; + struct platform_device *pdev; + + pdev = platform_device_alloc("cxl_switch_dport", i); + if (!pdev) + goto err_port; + pdev->dev.parent = &uport->dev; + + rc = platform_device_add(pdev); + if (rc) { + platform_device_put(pdev); + goto err_dport; + } + cxl_switch_dport[i] = pdev; + } + + BUILD_BUG_ON(ARRAY_SIZE(cxl_mem) != ARRAY_SIZE(cxl_switch_dport)); for (i = 0; i < ARRAY_SIZE(cxl_mem); i++) { - struct platform_device *port = cxl_root_port[i]; + struct platform_device *dport = cxl_switch_dport[i]; struct platform_device *pdev; pdev = alloc_memdev(i); if (!pdev) goto err_mem; - pdev->dev.parent = &port->dev; + pdev->dev.parent = &dport->dev; + set_dev_node(&pdev->dev, i % 2); rc = platform_device_add(pdev); if (rc) { @@ -563,12 +740,24 @@ err_add: err_mem: for (i = ARRAY_SIZE(cxl_mem) - 1; i >= 0; i--) platform_device_unregister(cxl_mem[i]); +err_dport: + for (i = ARRAY_SIZE(cxl_switch_dport) - 1; i >= 0; i--) + platform_device_unregister(cxl_switch_dport[i]); +err_uport: + for (i = ARRAY_SIZE(cxl_switch_uport) - 1; i >= 0; i--) + platform_device_unregister(cxl_switch_uport[i]); err_port: for (i = ARRAY_SIZE(cxl_root_port) - 1; i >= 0; i--) platform_device_unregister(cxl_root_port[i]); err_bridge: - for (i = ARRAY_SIZE(cxl_host_bridge) - 1; i >= 0; i--) + for (i = ARRAY_SIZE(cxl_host_bridge) - 1; i >= 0; i--) { + struct platform_device *pdev = cxl_host_bridge[i]; + + if (!pdev) + continue; + sysfs_remove_link(&pdev->dev.kobj, "physical_node"); platform_device_unregister(cxl_host_bridge[i]); + } err_populate: depopulate_all_mock_resources(); err_gen_pool_add: @@ -585,10 +774,20 @@ static __exit void cxl_test_exit(void) platform_device_unregister(cxl_acpi); for (i = ARRAY_SIZE(cxl_mem) - 1; i >= 0; i--) platform_device_unregister(cxl_mem[i]); + for (i = ARRAY_SIZE(cxl_switch_dport) - 1; i >= 0; i--) + platform_device_unregister(cxl_switch_dport[i]); + for (i = ARRAY_SIZE(cxl_switch_uport) - 1; i >= 0; i--) + platform_device_unregister(cxl_switch_uport[i]); for (i = ARRAY_SIZE(cxl_root_port) - 1; i >= 0; i--) platform_device_unregister(cxl_root_port[i]); - for (i = ARRAY_SIZE(cxl_host_bridge) - 1; i >= 0; i--) + for (i = ARRAY_SIZE(cxl_host_bridge) - 1; i >= 0; i--) { + struct platform_device *pdev = cxl_host_bridge[i]; + + if (!pdev) + continue; + sysfs_remove_link(&pdev->dev.kobj, "physical_node"); platform_device_unregister(cxl_host_bridge[i]); + } depopulate_all_mock_resources(); gen_pool_destroy(cxl_mock_pool); unregister_cxl_mock_ops(&cxl_mock_ops); @@ -598,3 +797,4 @@ module_init(cxl_test_init); module_exit(cxl_test_exit); MODULE_LICENSE("GPL v2"); MODULE_IMPORT_NS(ACPI); +MODULE_IMPORT_NS(CXL); diff --git a/tools/testing/cxl/test/mem.c b/tools/testing/cxl/test/mem.c index 8c2086c4caef..b6b726eff3e2 100644 --- a/tools/testing/cxl/test/mem.c +++ b/tools/testing/cxl/test/mem.c @@ -4,6 +4,7 @@ #include <linux/platform_device.h> #include <linux/mod_devicetable.h> #include <linux/module.h> +#include <linux/delay.h> #include <linux/sizes.h> #include <linux/bits.h> #include <cxlmem.h> @@ -236,11 +237,25 @@ static int cxl_mock_mbox_send(struct cxl_dev_state *cxlds, struct cxl_mbox_cmd * return rc; } +static int cxl_mock_wait_media_ready(struct cxl_dev_state *cxlds) +{ + msleep(100); + return 0; +} + static void label_area_release(void *lsa) { vfree(lsa); } +static void mock_validate_dvsec_ranges(struct cxl_dev_state *cxlds) +{ + struct cxl_endpoint_dvsec_info *info; + + info = &cxlds->info; + info->mem_enabled = true; +} + static int cxl_mock_mem_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; @@ -261,7 +276,9 @@ static int cxl_mock_mem_probe(struct platform_device *pdev) if (IS_ERR(cxlds)) return PTR_ERR(cxlds); + cxlds->serial = pdev->id; cxlds->mbox_send = cxl_mock_mbox_send; + cxlds->wait_media_ready = cxl_mock_wait_media_ready; cxlds->payload_size = SZ_4K; rc = cxl_enumerate_cmds(cxlds); @@ -276,6 +293,8 @@ static int cxl_mock_mem_probe(struct platform_device *pdev) if (rc) return rc; + mock_validate_dvsec_ranges(cxlds); + cxlmd = devm_cxl_add_memdev(cxlds); if (IS_ERR(cxlmd)) return PTR_ERR(cxlmd); diff --git a/tools/testing/cxl/test/mock.c b/tools/testing/cxl/test/mock.c index 17408f892df4..6e8c9d63c92d 100644 --- a/tools/testing/cxl/test/mock.c +++ b/tools/testing/cxl/test/mock.c @@ -7,6 +7,8 @@ #include <linux/export.h> #include <linux/acpi.h> #include <linux/pci.h> +#include <cxlmem.h> +#include <cxlpci.h> #include "mock.h" static LIST_HEAD(mock); @@ -114,32 +116,6 @@ struct acpi_pci_root *__wrap_acpi_pci_find_root(acpi_handle handle) } EXPORT_SYMBOL_GPL(__wrap_acpi_pci_find_root); -void __wrap_pci_walk_bus(struct pci_bus *bus, - int (*cb)(struct pci_dev *, void *), void *userdata) -{ - int index; - struct cxl_mock_ops *ops = get_cxl_mock_ops(&index); - - if (ops && ops->is_mock_bus(bus)) { - int rc, i; - - /* - * Simulate 2 root ports per host-bridge and no - * depth recursion. - */ - for (i = 0; i < 2; i++) { - rc = cb((struct pci_dev *) ops->mock_port(bus, i), - userdata); - if (rc) - break; - } - } else - pci_walk_bus(bus, cb, userdata); - - put_cxl_mock_ops(index); -} -EXPORT_SYMBOL_GPL(__wrap_pci_walk_bus); - struct nvdimm_bus * __wrap_nvdimm_bus_register(struct device *dev, struct nvdimm_bus_descriptor *nd_desc) @@ -155,5 +131,68 @@ __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) +{ + int index; + struct cxl_hdm *cxlhdm; + struct cxl_mock_ops *ops = get_cxl_mock_ops(&index); + + if (ops && ops->is_mock_port(port->uport)) + cxlhdm = ops->devm_cxl_setup_hdm(port); + else + cxlhdm = devm_cxl_setup_hdm(port); + 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 rc, index; + struct cxl_mock_ops *ops = get_cxl_mock_ops(&index); + + if (ops && ops->is_mock_port(port->uport)) + rc = ops->devm_cxl_add_passthrough_decoder(port); + else + rc = devm_cxl_add_passthrough_decoder(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) +{ + 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)) + rc = ops->devm_cxl_enumerate_decoders(cxlhdm); + else + rc = devm_cxl_enumerate_decoders(cxlhdm); + put_cxl_mock_ops(index); + + return rc; +} +EXPORT_SYMBOL_NS_GPL(__wrap_devm_cxl_enumerate_decoders, CXL); + +int __wrap_devm_cxl_port_enumerate_dports(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)) + rc = ops->devm_cxl_port_enumerate_dports(port); + else + rc = devm_cxl_port_enumerate_dports(port); + put_cxl_mock_ops(index); + + return rc; +} +EXPORT_SYMBOL_NS_GPL(__wrap_devm_cxl_port_enumerate_dports, CXL); + MODULE_LICENSE("GPL v2"); MODULE_IMPORT_NS(ACPI); +MODULE_IMPORT_NS(CXL); diff --git a/tools/testing/cxl/test/mock.h b/tools/testing/cxl/test/mock.h index 15ed0fd877e4..738f24e3988a 100644 --- a/tools/testing/cxl/test/mock.h +++ b/tools/testing/cxl/test/mock.h @@ -2,6 +2,7 @@ #include <linux/list.h> #include <linux/acpi.h> +#include <cxl.h> struct cxl_mock_ops { struct list_head list; @@ -15,10 +16,13 @@ struct cxl_mock_ops { struct acpi_object_list *arguments, unsigned long long *data); struct acpi_pci_root *(*acpi_pci_find_root)(acpi_handle handle); - struct platform_device *(*mock_port)(struct pci_bus *bus, int index); bool (*is_mock_bus)(struct pci_bus *bus); - bool (*is_mock_port)(struct platform_device *pdev); + 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); + int (*devm_cxl_add_passthrough_decoder)(struct cxl_port *port); + int (*devm_cxl_enumerate_decoders)(struct cxl_hdm *hdm); }; void register_cxl_mock_ops(struct cxl_mock_ops *ops); diff --git a/tools/testing/kunit/kunit.py b/tools/testing/kunit/kunit.py index 7a706f96f68d..9274c6355809 100755 --- a/tools/testing/kunit/kunit.py +++ b/tools/testing/kunit/kunit.py @@ -17,7 +17,7 @@ assert sys.version_info >= (3, 7), "Python version is too old" from dataclasses import dataclass from enum import Enum, auto -from typing import Any, Iterable, Sequence, List, Optional +from typing import Iterable, List, Optional, Sequence, Tuple import kunit_json import kunit_kernel @@ -32,7 +32,6 @@ class KunitStatus(Enum): @dataclass class KunitResult: status: KunitStatus - result: Any elapsed_time: float @dataclass @@ -82,10 +81,8 @@ def config_tests(linux: kunit_kernel.LinuxSourceTree, config_end = time.time() if not success: return KunitResult(KunitStatus.CONFIG_FAILURE, - 'could not configure kernel', config_end - config_start) return KunitResult(KunitStatus.SUCCESS, - 'configured kernel successfully', config_end - config_start) def build_tests(linux: kunit_kernel.LinuxSourceTree, @@ -100,14 +97,11 @@ def build_tests(linux: kunit_kernel.LinuxSourceTree, build_end = time.time() if not success: return KunitResult(KunitStatus.BUILD_FAILURE, - 'could not build kernel', build_end - build_start) if not success: return KunitResult(KunitStatus.BUILD_FAILURE, - 'could not build kernel', build_end - build_start) return KunitResult(KunitStatus.SUCCESS, - 'built kernel successfully', build_end - build_start) def config_and_build_tests(linux: kunit_kernel.LinuxSourceTree, @@ -173,14 +167,14 @@ def exec_tests(linux: kunit_kernel.LinuxSourceTree, request: KunitExecRequest) - filter_glob=filter_glob, build_dir=request.build_dir) - result = parse_tests(request, run_result) + _, test_result = parse_tests(request, run_result) # run_kernel() doesn't block on the kernel exiting. # That only happens after we get the last line of output from `run_result`. # So exec_time here actually contains parsing + execution time, which is fine. test_end = time.time() exec_time += test_end - test_start - test_counts.add_subtest_counts(result.result.counts) + test_counts.add_subtest_counts(test_result.counts) if len(filter_globs) == 1 and test_counts.crashed > 0: bd = request.build_dir @@ -189,7 +183,7 @@ def exec_tests(linux: kunit_kernel.LinuxSourceTree, request: KunitExecRequest) - bd, bd, kunit_kernel.get_outfile_path(bd), bd, sys.argv[0])) kunit_status = _map_to_overall_status(test_counts.get_status()) - return KunitResult(status=kunit_status, result=result, elapsed_time=exec_time) + return KunitResult(status=kunit_status, elapsed_time=exec_time) def _map_to_overall_status(test_status: kunit_parser.TestStatus) -> KunitStatus: if test_status in (kunit_parser.TestStatus.SUCCESS, kunit_parser.TestStatus.SKIPPED): @@ -197,7 +191,7 @@ def _map_to_overall_status(test_status: kunit_parser.TestStatus) -> KunitStatus: else: return KunitStatus.TEST_FAILURE -def parse_tests(request: KunitParseRequest, input_data: Iterable[str]) -> KunitResult: +def parse_tests(request: KunitParseRequest, input_data: Iterable[str]) -> Tuple[KunitResult, kunit_parser.Test]: parse_start = time.time() test_result = kunit_parser.Test() @@ -231,11 +225,9 @@ def parse_tests(request: KunitParseRequest, input_data: Iterable[str]) -> KunitR print(json_obj) if test_result.status != kunit_parser.TestStatus.SUCCESS: - return KunitResult(KunitStatus.TEST_FAILURE, test_result, - parse_end - parse_start) + return KunitResult(KunitStatus.TEST_FAILURE, parse_end - parse_start), test_result - return KunitResult(KunitStatus.SUCCESS, test_result, - parse_end - parse_start) + return KunitResult(KunitStatus.SUCCESS, parse_end - parse_start), test_result def run_tests(linux: kunit_kernel.LinuxSourceTree, request: KunitRequest) -> KunitResult: @@ -513,7 +505,7 @@ def main(argv, linux=None): request = KunitParseRequest(raw_output=cli_args.raw_output, build_dir='', json=cli_args.json) - result = parse_tests(request, kunit_output) + result, _ = parse_tests(request, kunit_output) if result.status != KunitStatus.SUCCESS: sys.exit(1) else: diff --git a/tools/testing/kunit/kunit_kernel.py b/tools/testing/kunit/kunit_kernel.py index 44bbe54f25f1..3c4196cef3ed 100644 --- a/tools/testing/kunit/kunit_kernel.py +++ b/tools/testing/kunit/kunit_kernel.py @@ -6,6 +6,7 @@ # Author: Felix Guo <felixguoxiuping@gmail.com> # Author: Brendan Higgins <brendanhiggins@google.com> +import importlib.abc import importlib.util import logging import subprocess diff --git a/tools/testing/kunit/run_checks.py b/tools/testing/kunit/run_checks.py index 4f32133ed77c..13d854afca9d 100755 --- a/tools/testing/kunit/run_checks.py +++ b/tools/testing/kunit/run_checks.py @@ -61,7 +61,7 @@ def main(argv: Sequence[str]) -> None: elif isinstance(ex, subprocess.CalledProcessError): print(f'{name}: FAILED') else: - print('{name}: unexpected exception: {ex}') + print(f'{name}: unexpected exception: {ex}') continue output = ex.output diff --git a/tools/testing/memblock/.gitignore b/tools/testing/memblock/.gitignore new file mode 100644 index 000000000000..654338e0be52 --- /dev/null +++ b/tools/testing/memblock/.gitignore @@ -0,0 +1,4 @@ +main +memblock.c +linux/memblock.h +asm/cmpxchg.h diff --git a/tools/testing/memblock/Makefile b/tools/testing/memblock/Makefile new file mode 100644 index 000000000000..a698e24b35e7 --- /dev/null +++ b/tools/testing/memblock/Makefile @@ -0,0 +1,55 @@ +# SPDX-License-Identifier: GPL-2.0 + +# Memblock simulator requires AddressSanitizer (libasan) and liburcu development +# packages installed +CFLAGS += -I. -I../../include -Wall -O2 -fsanitize=address \ + -fsanitize=undefined -D CONFIG_PHYS_ADDR_T_64BIT +LDFLAGS += -fsanitize=address -fsanitize=undefined +TARGETS = main +TEST_OFILES = tests/alloc_nid_api.o tests/alloc_helpers_api.o tests/alloc_api.o \ + tests/basic_api.o tests/common.o +DEP_OFILES = memblock.o lib/slab.o mmzone.o slab.o +OFILES = main.o $(DEP_OFILES) $(TEST_OFILES) +EXTR_SRC = ../../../mm/memblock.c + +ifeq ($(BUILD), 32) + CFLAGS += -m32 + LDFLAGS += -m32 +endif + +# Process user parameters +include scripts/Makefile.include + +main: $(OFILES) + +$(OFILES): include + +include: ../../../include/linux/memblock.h ../../include/linux/*.h \ + ../../include/asm/*.h + + @mkdir -p linux + test -L linux/memblock.h || ln -s ../../../../include/linux/memblock.h linux/memblock.h + test -L asm/cmpxchg.h || ln -s ../../../arch/x86/include/asm/cmpxchg.h asm/cmpxchg.h + +memblock.c: $(EXTR_SRC) + test -L memblock.c || ln -s $(EXTR_SRC) memblock.c + +clean: + $(RM) $(TARGETS) $(OFILES) linux/memblock.h memblock.c asm/cmpxchg.h + +help: + @echo 'Memblock simulator' + @echo '' + @echo 'Available targets:' + @echo ' main - Build the memblock simulator' + @echo ' clean - Remove generated files and symlinks in the directory' + @echo '' + @echo 'Configuration:' + @echo ' make NUMA=1 - simulate enabled NUMA' + @echo ' make MOVABLE_NODE=1 - override `movable_node_is_enabled`' + @echo ' definition to simulate movable NUMA nodes' + @echo ' make 32BIT_PHYS_ADDR_T=1 - Use 32 bit physical addresses' + +vpath %.c ../../lib + +.PHONY: clean include help diff --git a/tools/testing/memblock/README b/tools/testing/memblock/README new file mode 100644 index 000000000000..ca6afcff013a --- /dev/null +++ b/tools/testing/memblock/README @@ -0,0 +1,107 @@ +================== +Memblock simulator +================== + +Introduction +============ + +Memblock is a boot time memory allocator[1] that manages memory regions before +the actual memory management is initialized. Its APIs allow to register physical +memory regions, mark them as available or reserved, allocate a block of memory +within the requested range and/or in specific NUMA node, and many more. + +Because it is used so early in the booting process, testing and debugging it is +difficult. This test suite, usually referred as memblock simulator, is +an attempt at testing the memblock mechanism. It runs one monolithic test that +consist of a series of checks that exercise both the basic operations and +allocation functionalities of memblock. The main data structure of the boot time +memory allocator is initialized at the build time, so the checks here reuse its +instance throughout the duration of the test. To ensure that tests don't affect +each other, region arrays are reset in between. + +As this project uses the actual memblock code and has to run in user space, +some of the kernel definitions were stubbed by the initial commit that +introduced memblock simulator (commit 16802e55dea9 ("memblock tests: Add +skeleton of the memblock simulator")) and a few preparation commits just +before it. Most of them don't match the kernel implementation, so one should +consult them first before making any significant changes to the project. + +Usage +===== + +To run the tests, build the main target and run it: + +$ make && ./main + +A successful run produces no output. It is also possible to override different +configuration parameters. For example, to simulate enabled NUMA, use: + +$ make NUMA=1 + +For the full list of options, see `make help`. + +Project structure +================= + +The project has one target, main, which calls a group of checks for basic and +allocation functions. Tests for each group are defined in dedicated files, as it +can be seen here: + +memblock +|-- asm ------------------, +|-- lib |-- implement function and struct stubs +|-- linux ------------------' +|-- scripts +| |-- Makefile.include -- handles `make` parameters +|-- tests +| |-- alloc_api.(c|h) -- memblock_alloc tests +| |-- alloc_helpers_api.(c|h) -- memblock_alloc_from tests +| |-- alloc_nid_api.(c|h) -- memblock_alloc_try_nid tests +| |-- basic_api.(c|h) -- memblock_add/memblock_reserve/... tests +| |-- common.(c|h) -- helper functions for resetting memblock; +|-- main.c --------------. dummy physical memory definition +|-- Makefile `- test runner +|-- README +|-- TODO +|-- .gitignore + +Simulating physical memory +========================== + +Some allocation functions clear the memory in the process, so it is required for +memblock to track valid memory ranges. To achieve this, the test suite registers +with memblock memory stored by test_memory struct. It is a small wrapper that +points to a block of memory allocated via malloc. For each group of allocation +tests, dummy physical memory is allocated, added to memblock, and then released +at the end of the test run. The structure of a test runner checking allocation +functions is as follows: + +int memblock_alloc_foo_checks(void) +{ + reset_memblock_attributes(); /* data structure reset */ + dummy_physical_memory_init(); /* allocate and register memory */ + + (...allocation checks...) + + dummy_physical_memory_cleanup(); /* free the memory */ +} + +There's no need to explicitly free the dummy memory from memblock via +memblock_free() call. The entry will be erased by reset_memblock_regions(), +called at the beginning of each test. + +Known issues +============ + +1. Requesting a specific NUMA node via memblock_alloc_node() does not work as + intended. Once the fix is in place, tests for this function can be added. + +2. Tests for memblock_alloc_low() can't be easily implemented. The function uses + ARCH_LOW_ADDRESS_LIMIT marco, which can't be changed to point at the low + memory of the memory_block. + +References +========== + +1. Boot time memory management documentation page: + https://www.kernel.org/doc/html/latest/core-api/boot-time-mm.html diff --git a/tools/testing/memblock/TODO b/tools/testing/memblock/TODO new file mode 100644 index 000000000000..c25b2fdec45e --- /dev/null +++ b/tools/testing/memblock/TODO @@ -0,0 +1,28 @@ +TODO +===== + +1. Add verbose output (e.g., what is being tested and how many tests cases are + passing) + +2. Add flags to Makefile: + + verbosity level + + enable memblock_dbg() messages (i.e. pass "-D CONFIG_DEBUG_MEMORY_INIT" + flag) + +3. Add tests trying to memblock_add() or memblock_reserve() 129th region. + This will trigger memblock_double_array(), make sure it succeeds. + *Important:* These tests require valid memory ranges, use dummy physical + memory block from common.c to implement them. It is also very + likely that the current MEM_SIZE won't be enough for these + test cases. Use realloc to adjust the size accordingly. + +4. Add test cases using this functions (implement them for both directions): + + memblock_alloc_raw() + + memblock_alloc_exact_nid_raw() + + memblock_alloc_try_nid_raw() + +5. Add tests for memblock_alloc_node() to check if the correct NUMA node is set + for the new region + +6. Update comments in tests/basic_api.c to match the style used in + tests/alloc_*.c diff --git a/tools/testing/memblock/asm/dma.h b/tools/testing/memblock/asm/dma.h new file mode 100644 index 000000000000..13ff8e5d22ef --- /dev/null +++ b/tools/testing/memblock/asm/dma.h @@ -0,0 +1,5 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _TOOLS_DMA_H +#define _TOOLS_DMA_H + +#endif diff --git a/tools/testing/memblock/internal.h b/tools/testing/memblock/internal.h new file mode 100644 index 000000000000..94b52a8718b5 --- /dev/null +++ b/tools/testing/memblock/internal.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef _MM_INTERNAL_H +#define _MM_INTERNAL_H + +struct page {}; + +void memblock_free_pages(struct page *page, unsigned long pfn, + unsigned int order) +{ +} + +#endif diff --git a/tools/testing/memblock/lib/slab.c b/tools/testing/memblock/lib/slab.c new file mode 100644 index 000000000000..6be6020328fb --- /dev/null +++ b/tools/testing/memblock/lib/slab.c @@ -0,0 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/slab.h> + +enum slab_state slab_state; + +bool slab_is_available(void) +{ + return slab_state >= UP; +} diff --git a/tools/testing/memblock/linux/init.h b/tools/testing/memblock/linux/init.h new file mode 100644 index 000000000000..828e0ee0bc6c --- /dev/null +++ b/tools/testing/memblock/linux/init.h @@ -0,0 +1,34 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_INIT_H +#define _LINUX_INIT_H + +#include <linux/compiler.h> +#include <asm/export.h> +#include <linux/memory_hotplug.h> + +#define __section(section) __attribute__((__section__(section))) + +#define __initconst +#define __meminit +#define __meminitdata +#define __refdata +#define __initdata + +struct obs_kernel_param { + const char *str; + int (*setup_func)(char *st); + int early; +}; + +#define __setup_param(str, unique_id, fn, early) \ + static const char __setup_str_##unique_id[] __initconst \ + __aligned(1) = str; \ + static struct obs_kernel_param __setup_##unique_id \ + __used __section(".init.setup") \ + __aligned(__alignof__(struct obs_kernel_param)) = \ + { __setup_str_##unique_id, fn, early } + +#define early_param(str, fn) \ + __setup_param(str, fn, fn, 1) + +#endif diff --git a/tools/testing/memblock/linux/kernel.h b/tools/testing/memblock/linux/kernel.h new file mode 100644 index 000000000000..d2f148bd8902 --- /dev/null +++ b/tools/testing/memblock/linux/kernel.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef _MEMBLOCK_LINUX_KERNEL_H +#define _MEMBLOCK_LINUX_KERNEL_H + +#include <../../include/linux/kernel.h> +#include <linux/errno.h> +#include <string.h> +#include <linux/printk.h> +#include <linux/linkage.h> +#include <linux/kconfig.h> + +#endif diff --git a/tools/testing/memblock/linux/kmemleak.h b/tools/testing/memblock/linux/kmemleak.h new file mode 100644 index 000000000000..462f8c5e8aa0 --- /dev/null +++ b/tools/testing/memblock/linux/kmemleak.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef _KMEMLEAK_H +#define _KMEMLEAK_H + +static inline void kmemleak_free_part_phys(phys_addr_t phys, size_t size) +{ +} + +static inline void kmemleak_alloc_phys(phys_addr_t phys, size_t size, + int min_count, gfp_t gfp) +{ +} + +static inline void dump_stack(void) +{ +} + +#endif diff --git a/tools/testing/memblock/linux/memory_hotplug.h b/tools/testing/memblock/linux/memory_hotplug.h new file mode 100644 index 000000000000..47988765a219 --- /dev/null +++ b/tools/testing/memblock/linux/memory_hotplug.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_MEMORY_HOTPLUG_H +#define _LINUX_MEMORY_HOTPLUG_H + +#include <linux/numa.h> +#include <linux/pfn.h> +#include <linux/cache.h> +#include <linux/types.h> + +static inline bool movable_node_is_enabled(void) +{ +#ifdef MOVABLE_NODE + return true; +#else + return false; +#endif +} + +#endif diff --git a/tools/testing/memblock/linux/mmzone.h b/tools/testing/memblock/linux/mmzone.h new file mode 100644 index 000000000000..7c2eb5c9bb54 --- /dev/null +++ b/tools/testing/memblock/linux/mmzone.h @@ -0,0 +1,35 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _TOOLS_MMZONE_H +#define _TOOLS_MMZONE_H + +#include <linux/atomic.h> + +struct pglist_data *first_online_pgdat(void); +struct pglist_data *next_online_pgdat(struct pglist_data *pgdat); + +#define for_each_online_pgdat(pgdat) \ + for (pgdat = first_online_pgdat(); \ + pgdat; \ + pgdat = next_online_pgdat(pgdat)) + +enum zone_type { + __MAX_NR_ZONES +}; + +#define MAX_NR_ZONES __MAX_NR_ZONES +#define MAX_ORDER 11 +#define MAX_ORDER_NR_PAGES (1 << (MAX_ORDER - 1)) + +#define pageblock_order (MAX_ORDER - 1) +#define pageblock_nr_pages BIT(pageblock_order) + +struct zone { + atomic_long_t managed_pages; +}; + +typedef struct pglist_data { + struct zone node_zones[MAX_NR_ZONES]; + +} pg_data_t; + +#endif diff --git a/tools/testing/memblock/linux/printk.h b/tools/testing/memblock/linux/printk.h new file mode 100644 index 000000000000..61af424d8c6c --- /dev/null +++ b/tools/testing/memblock/linux/printk.h @@ -0,0 +1,25 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _PRINTK_H +#define _PRINTK_H + +#include <stdio.h> +#include <asm/bug.h> + +/* + * memblock_dbg is called with u64 arguments that don't match the "%llu" + * specifier in printf. This results in warnings that cannot be fixed without + * modifying memblock.c, which we wish to avoid. As these messaged are not used + * in testing anyway, the mismatch can be ignored. + */ +#pragma GCC diagnostic push +#pragma GCC diagnostic ignored "-Wformat" +#define printk printf +#pragma GCC diagnostic push + +#define pr_info printk +#define pr_debug printk +#define pr_cont printk +#define pr_err printk +#define pr_warn printk + +#endif diff --git a/tools/testing/memblock/main.c b/tools/testing/memblock/main.c new file mode 100644 index 000000000000..fb183c9e76d1 --- /dev/null +++ b/tools/testing/memblock/main.c @@ -0,0 +1,15 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +#include "tests/basic_api.h" +#include "tests/alloc_api.h" +#include "tests/alloc_helpers_api.h" +#include "tests/alloc_nid_api.h" + +int main(int argc, char **argv) +{ + memblock_basic_checks(); + memblock_alloc_checks(); + memblock_alloc_helpers_checks(); + memblock_alloc_nid_checks(); + + return 0; +} diff --git a/tools/testing/memblock/mmzone.c b/tools/testing/memblock/mmzone.c new file mode 100644 index 000000000000..7b0909e8b759 --- /dev/null +++ b/tools/testing/memblock/mmzone.c @@ -0,0 +1,20 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +#include <linux/mmzone.h> + +struct pglist_data *first_online_pgdat(void) +{ + return NULL; +} + +struct pglist_data *next_online_pgdat(struct pglist_data *pgdat) +{ + return NULL; +} + +void reserve_bootmem_region(phys_addr_t start, phys_addr_t end) +{ +} + +void atomic_long_set(atomic_long_t *v, long i) +{ +} diff --git a/tools/testing/memblock/scripts/Makefile.include b/tools/testing/memblock/scripts/Makefile.include new file mode 100644 index 000000000000..641569ccb7b0 --- /dev/null +++ b/tools/testing/memblock/scripts/Makefile.include @@ -0,0 +1,19 @@ +# SPDX-License-Identifier: GPL-2.0 +# Definitions for user-provided arguments + +# Simulate CONFIG_NUMA=y +ifeq ($(NUMA), 1) + CFLAGS += -D CONFIG_NUMA +endif + +# Simulate movable NUMA memory regions +ifeq ($(MOVABLE_NODE), 1) + CFLAGS += -D MOVABLE_NODE +endif + +# Use 32 bit physical addresses. +# Remember to install 32-bit version of dependencies. +ifeq ($(32BIT_PHYS_ADDR_T), 1) + CFLAGS += -m32 -U CONFIG_PHYS_ADDR_T_64BIT + LDFLAGS += -m32 +endif diff --git a/tools/testing/memblock/tests/alloc_api.c b/tools/testing/memblock/tests/alloc_api.c new file mode 100644 index 000000000000..d1aa7e15c18d --- /dev/null +++ b/tools/testing/memblock/tests/alloc_api.c @@ -0,0 +1,750 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +#include "alloc_api.h" + +/* + * A simple test that tries to allocate a small memory region. + * Expect to allocate an aligned region near the end of the available memory. + */ +static int alloc_top_down_simple_check(void) +{ + struct memblock_region *rgn = &memblock.reserved.regions[0]; + void *allocated_ptr = NULL; + + phys_addr_t size = SZ_2; + phys_addr_t expected_start; + + setup_memblock(); + + expected_start = memblock_end_of_DRAM() - SMP_CACHE_BYTES; + + allocated_ptr = memblock_alloc(size, SMP_CACHE_BYTES); + + assert(allocated_ptr); + assert(rgn->size == size); + assert(rgn->base == expected_start); + + assert(memblock.reserved.cnt == 1); + assert(memblock.reserved.total_size == size); + + return 0; +} + +/* + * A test that tries to allocate memory next to a reserved region that starts at + * the misaligned address. Expect to create two separate entries, with the new + * entry aligned to the provided alignment: + * + * + + * | +--------+ +--------| + * | | rgn2 | | rgn1 | + * +------------+--------+---------+--------+ + * ^ + * | + * Aligned address boundary + * + * The allocation direction is top-down and region arrays are sorted from lower + * to higher addresses, so the new region will be the first entry in + * memory.reserved array. The previously reserved region does not get modified. + * Region counter and total size get updated. + */ +static int alloc_top_down_disjoint_check(void) +{ + /* After allocation, this will point to the "old" region */ + struct memblock_region *rgn1 = &memblock.reserved.regions[1]; + struct memblock_region *rgn2 = &memblock.reserved.regions[0]; + struct region r1; + void *allocated_ptr = NULL; + + phys_addr_t r2_size = SZ_16; + /* Use custom alignment */ + phys_addr_t alignment = SMP_CACHE_BYTES * 2; + phys_addr_t total_size; + phys_addr_t expected_start; + + setup_memblock(); + + r1.base = memblock_end_of_DRAM() - SZ_2; + r1.size = SZ_2; + + total_size = r1.size + r2_size; + expected_start = memblock_end_of_DRAM() - alignment; + + memblock_reserve(r1.base, r1.size); + + allocated_ptr = memblock_alloc(r2_size, alignment); + + assert(allocated_ptr); + assert(rgn1->size == r1.size); + assert(rgn1->base == r1.base); + + assert(rgn2->size == r2_size); + assert(rgn2->base == expected_start); + + assert(memblock.reserved.cnt == 2); + assert(memblock.reserved.total_size == total_size); + + return 0; +} + +/* + * A test that tries to allocate memory when there is enough space at the end + * of the previously reserved block (i.e. first fit): + * + * | +--------+--------------| + * | | r1 | r2 | + * +--------------+--------+--------------+ + * + * Expect a merge of both regions. Only the region size gets updated. + */ +static int alloc_top_down_before_check(void) +{ + struct memblock_region *rgn = &memblock.reserved.regions[0]; + void *allocated_ptr = NULL; + + /* + * The first region ends at the aligned address to test region merging + */ + phys_addr_t r1_size = SMP_CACHE_BYTES; + phys_addr_t r2_size = SZ_512; + phys_addr_t total_size = r1_size + r2_size; + + setup_memblock(); + + memblock_reserve(memblock_end_of_DRAM() - total_size, r1_size); + + allocated_ptr = memblock_alloc(r2_size, SMP_CACHE_BYTES); + + assert(allocated_ptr); + assert(rgn->size == total_size); + assert(rgn->base == memblock_end_of_DRAM() - total_size); + + assert(memblock.reserved.cnt == 1); + assert(memblock.reserved.total_size == total_size); + + return 0; +} + +/* + * A test that tries to allocate memory when there is not enough space at the + * end of the previously reserved block (i.e. second fit): + * + * | +-----------+------+ | + * | | r2 | r1 | | + * +------------+-----------+------+-----+ + * + * Expect a merge of both regions. Both the base address and size of the region + * get updated. + */ +static int alloc_top_down_after_check(void) +{ + struct memblock_region *rgn = &memblock.reserved.regions[0]; + struct region r1; + void *allocated_ptr = NULL; + + phys_addr_t r2_size = SZ_512; + phys_addr_t total_size; + + setup_memblock(); + + /* + * The first region starts at the aligned address to test region merging + */ + r1.base = memblock_end_of_DRAM() - SMP_CACHE_BYTES; + r1.size = SZ_8; + + total_size = r1.size + r2_size; + + memblock_reserve(r1.base, r1.size); + + allocated_ptr = memblock_alloc(r2_size, SMP_CACHE_BYTES); + + assert(allocated_ptr); + assert(rgn->size == total_size); + assert(rgn->base == r1.base - r2_size); + + assert(memblock.reserved.cnt == 1); + assert(memblock.reserved.total_size == total_size); + + return 0; +} + +/* + * A test that tries to allocate memory when there are two reserved regions with + * a gap too small to fit the new region: + * + * | +--------+----------+ +------| + * | | r3 | r2 | | r1 | + * +-------+--------+----------+---+------+ + * + * Expect to allocate a region before the one that starts at the lower address, + * and merge them into one. The region counter and total size fields get + * updated. + */ +static int alloc_top_down_second_fit_check(void) +{ + struct memblock_region *rgn = &memblock.reserved.regions[0]; + struct region r1, r2; + void *allocated_ptr = NULL; + + phys_addr_t r3_size = SZ_1K; + phys_addr_t total_size; + + setup_memblock(); + + r1.base = memblock_end_of_DRAM() - SZ_512; + r1.size = SZ_512; + + r2.base = r1.base - SZ_512; + r2.size = SZ_256; + + total_size = r1.size + r2.size + r3_size; + + memblock_reserve(r1.base, r1.size); + memblock_reserve(r2.base, r2.size); + + allocated_ptr = memblock_alloc(r3_size, SMP_CACHE_BYTES); + + assert(allocated_ptr); + assert(rgn->size == r2.size + r3_size); + assert(rgn->base == r2.base - r3_size); + + assert(memblock.reserved.cnt == 2); + assert(memblock.reserved.total_size == total_size); + + return 0; +} + +/* + * A test that tries to allocate memory when there are two reserved regions with + * a gap big enough to accommodate the new region: + * + * | +--------+--------+--------+ | + * | | r2 | r3 | r1 | | + * +-----+--------+--------+--------+-----+ + * + * Expect to merge all of them, creating one big entry in memblock.reserved + * array. The region counter and total size fields get updated. + */ +static int alloc_in_between_generic_check(void) +{ + struct memblock_region *rgn = &memblock.reserved.regions[0]; + struct region r1, r2; + void *allocated_ptr = NULL; + + phys_addr_t gap_size = SMP_CACHE_BYTES; + phys_addr_t r3_size = SZ_64; + /* + * Calculate regions size so there's just enough space for the new entry + */ + phys_addr_t rgn_size = (MEM_SIZE - (2 * gap_size + r3_size)) / 2; + phys_addr_t total_size; + + setup_memblock(); + + r1.size = rgn_size; + r1.base = memblock_end_of_DRAM() - (gap_size + rgn_size); + + r2.size = rgn_size; + r2.base = memblock_start_of_DRAM() + gap_size; + + total_size = r1.size + r2.size + r3_size; + + memblock_reserve(r1.base, r1.size); + memblock_reserve(r2.base, r2.size); + + allocated_ptr = memblock_alloc(r3_size, SMP_CACHE_BYTES); + + assert(allocated_ptr); + assert(rgn->size == total_size); + assert(rgn->base == r1.base - r2.size - r3_size); + + assert(memblock.reserved.cnt == 1); + assert(memblock.reserved.total_size == total_size); + + return 0; +} + +/* + * A test that tries to allocate memory when the memory is filled with reserved + * regions with memory gaps too small to fit the new region: + * + * +-------+ + * | new | + * +--+----+ + * | +-----+ +-----+ +-----+ | + * | | res | | res | | res | | + * +----+-----+----+-----+----+-----+----+ + * + * Expect no allocation to happen. + */ +static int alloc_small_gaps_generic_check(void) +{ + void *allocated_ptr = NULL; + + phys_addr_t region_size = SZ_1K; + phys_addr_t gap_size = SZ_256; + phys_addr_t region_end; + + setup_memblock(); + + region_end = memblock_start_of_DRAM(); + + while (region_end < memblock_end_of_DRAM()) { + memblock_reserve(region_end + gap_size, region_size); + region_end += gap_size + region_size; + } + + allocated_ptr = memblock_alloc(region_size, SMP_CACHE_BYTES); + + assert(!allocated_ptr); + + return 0; +} + +/* + * A test that tries to allocate memory when all memory is reserved. + * Expect no allocation to happen. + */ +static int alloc_all_reserved_generic_check(void) +{ + void *allocated_ptr = NULL; + + setup_memblock(); + + /* Simulate full memory */ + memblock_reserve(memblock_start_of_DRAM(), MEM_SIZE); + + allocated_ptr = memblock_alloc(SZ_256, SMP_CACHE_BYTES); + + assert(!allocated_ptr); + + return 0; +} + +/* + * A test that tries to allocate memory when the memory is almost full, + * with not enough space left for the new region: + * + * +-------+ + * | new | + * +-------+ + * |-----------------------------+ | + * | reserved | | + * +-----------------------------+---+ + * + * Expect no allocation to happen. + */ +static int alloc_no_space_generic_check(void) +{ + void *allocated_ptr = NULL; + + setup_memblock(); + + phys_addr_t available_size = SZ_256; + phys_addr_t reserved_size = MEM_SIZE - available_size; + + /* Simulate almost-full memory */ + memblock_reserve(memblock_start_of_DRAM(), reserved_size); + + allocated_ptr = memblock_alloc(SZ_1K, SMP_CACHE_BYTES); + + assert(!allocated_ptr); + + return 0; +} + +/* + * A test that tries to allocate memory when the memory is almost full, + * but there is just enough space left: + * + * |---------------------------+---------| + * | reserved | new | + * +---------------------------+---------+ + * + * Expect to allocate memory and merge all the regions. The total size field + * gets updated. + */ +static int alloc_limited_space_generic_check(void) +{ + struct memblock_region *rgn = &memblock.reserved.regions[0]; + void *allocated_ptr = NULL; + + phys_addr_t available_size = SZ_256; + phys_addr_t reserved_size = MEM_SIZE - available_size; + + setup_memblock(); + + /* Simulate almost-full memory */ + memblock_reserve(memblock_start_of_DRAM(), reserved_size); + + allocated_ptr = memblock_alloc(available_size, SMP_CACHE_BYTES); + + assert(allocated_ptr); + assert(rgn->size == MEM_SIZE); + assert(rgn->base == memblock_start_of_DRAM()); + + assert(memblock.reserved.cnt == 1); + assert(memblock.reserved.total_size == MEM_SIZE); + + return 0; +} + +/* + * A test that tries to allocate memory when there is no available memory + * registered (i.e. memblock.memory has only a dummy entry). + * Expect no allocation to happen. + */ +static int alloc_no_memory_generic_check(void) +{ + struct memblock_region *rgn = &memblock.reserved.regions[0]; + void *allocated_ptr = NULL; + + reset_memblock_regions(); + + allocated_ptr = memblock_alloc(SZ_1K, SMP_CACHE_BYTES); + + assert(!allocated_ptr); + assert(rgn->size == 0); + assert(rgn->base == 0); + assert(memblock.reserved.total_size == 0); + + return 0; +} + +/* + * A simple test that tries to allocate a small memory region. + * Expect to allocate an aligned region at the beginning of the available + * memory. + */ +static int alloc_bottom_up_simple_check(void) +{ + struct memblock_region *rgn = &memblock.reserved.regions[0]; + void *allocated_ptr = NULL; + + setup_memblock(); + + allocated_ptr = memblock_alloc(SZ_2, SMP_CACHE_BYTES); + + assert(allocated_ptr); + assert(rgn->size == SZ_2); + assert(rgn->base == memblock_start_of_DRAM()); + + assert(memblock.reserved.cnt == 1); + assert(memblock.reserved.total_size == SZ_2); + + return 0; +} + +/* + * A test that tries to allocate memory next to a reserved region that starts at + * the misaligned address. Expect to create two separate entries, with the new + * entry aligned to the provided alignment: + * + * + + * | +----------+ +----------+ | + * | | rgn1 | | rgn2 | | + * +----+----------+---+----------+-----+ + * ^ + * | + * Aligned address boundary + * + * The allocation direction is bottom-up, so the new region will be the second + * entry in memory.reserved array. The previously reserved region does not get + * modified. Region counter and total size get updated. + */ +static int alloc_bottom_up_disjoint_check(void) +{ + struct memblock_region *rgn1 = &memblock.reserved.regions[0]; + struct memblock_region *rgn2 = &memblock.reserved.regions[1]; + struct region r1; + void *allocated_ptr = NULL; + + phys_addr_t r2_size = SZ_16; + /* Use custom alignment */ + phys_addr_t alignment = SMP_CACHE_BYTES * 2; + phys_addr_t total_size; + phys_addr_t expected_start; + + setup_memblock(); + + r1.base = memblock_start_of_DRAM() + SZ_2; + r1.size = SZ_2; + + total_size = r1.size + r2_size; + expected_start = memblock_start_of_DRAM() + alignment; + + memblock_reserve(r1.base, r1.size); + + allocated_ptr = memblock_alloc(r2_size, alignment); + + assert(allocated_ptr); + + assert(rgn1->size == r1.size); + assert(rgn1->base == r1.base); + + assert(rgn2->size == r2_size); + assert(rgn2->base == expected_start); + + assert(memblock.reserved.cnt == 2); + assert(memblock.reserved.total_size == total_size); + + return 0; +} + +/* + * A test that tries to allocate memory when there is enough space at + * the beginning of the previously reserved block (i.e. first fit): + * + * |------------------+--------+ | + * | r1 | r2 | | + * +------------------+--------+---------+ + * + * Expect a merge of both regions. Only the region size gets updated. + */ +static int alloc_bottom_up_before_check(void) +{ + struct memblock_region *rgn = &memblock.reserved.regions[0]; + void *allocated_ptr = NULL; + + phys_addr_t r1_size = SZ_512; + phys_addr_t r2_size = SZ_128; + phys_addr_t total_size = r1_size + r2_size; + + setup_memblock(); + + memblock_reserve(memblock_start_of_DRAM() + r1_size, r2_size); + + allocated_ptr = memblock_alloc(r1_size, SMP_CACHE_BYTES); + + assert(allocated_ptr); + assert(rgn->size == total_size); + assert(rgn->base == memblock_start_of_DRAM()); + + assert(memblock.reserved.cnt == 1); + assert(memblock.reserved.total_size == total_size); + + return 0; +} + +/* + * A test that tries to allocate memory when there is not enough space at + * the beginning of the previously reserved block (i.e. second fit): + * + * | +--------+--------------+ | + * | | r1 | r2 | | + * +----+--------+--------------+---------+ + * + * Expect a merge of both regions. Only the region size gets updated. + */ +static int alloc_bottom_up_after_check(void) +{ + struct memblock_region *rgn = &memblock.reserved.regions[0]; + struct region r1; + void *allocated_ptr = NULL; + + phys_addr_t r2_size = SZ_512; + phys_addr_t total_size; + + setup_memblock(); + + /* + * The first region starts at the aligned address to test region merging + */ + r1.base = memblock_start_of_DRAM() + SMP_CACHE_BYTES; + r1.size = SZ_64; + + total_size = r1.size + r2_size; + + memblock_reserve(r1.base, r1.size); + + allocated_ptr = memblock_alloc(r2_size, SMP_CACHE_BYTES); + + assert(allocated_ptr); + assert(rgn->size == total_size); + assert(rgn->base == r1.base); + + assert(memblock.reserved.cnt == 1); + assert(memblock.reserved.total_size == total_size); + + return 0; +} + +/* + * A test that tries to allocate memory when there are two reserved regions, the + * first one starting at the beginning of the available memory, with a gap too + * small to fit the new region: + * + * |------------+ +--------+--------+ | + * | r1 | | r2 | r3 | | + * +------------+-----+--------+--------+--+ + * + * Expect to allocate after the second region, which starts at the higher + * address, and merge them into one. The region counter and total size fields + * get updated. + */ +static int alloc_bottom_up_second_fit_check(void) +{ + struct memblock_region *rgn = &memblock.reserved.regions[1]; + struct region r1, r2; + void *allocated_ptr = NULL; + + phys_addr_t r3_size = SZ_1K; + phys_addr_t total_size; + + setup_memblock(); + + r1.base = memblock_start_of_DRAM(); + r1.size = SZ_512; + + r2.base = r1.base + r1.size + SZ_512; + r2.size = SZ_256; + + total_size = r1.size + r2.size + r3_size; + + memblock_reserve(r1.base, r1.size); + memblock_reserve(r2.base, r2.size); + + allocated_ptr = memblock_alloc(r3_size, SMP_CACHE_BYTES); + + assert(allocated_ptr); + assert(rgn->size == r2.size + r3_size); + assert(rgn->base == r2.base); + + assert(memblock.reserved.cnt == 2); + assert(memblock.reserved.total_size == total_size); + + return 0; +} + +/* Test case wrappers */ +static int alloc_simple_check(void) +{ + memblock_set_bottom_up(false); + alloc_top_down_simple_check(); + memblock_set_bottom_up(true); + alloc_bottom_up_simple_check(); + + return 0; +} + +static int alloc_disjoint_check(void) +{ + memblock_set_bottom_up(false); + alloc_top_down_disjoint_check(); + memblock_set_bottom_up(true); + alloc_bottom_up_disjoint_check(); + + return 0; +} + +static int alloc_before_check(void) +{ + memblock_set_bottom_up(false); + alloc_top_down_before_check(); + memblock_set_bottom_up(true); + alloc_bottom_up_before_check(); + + return 0; +} + +static int alloc_after_check(void) +{ + memblock_set_bottom_up(false); + alloc_top_down_after_check(); + memblock_set_bottom_up(true); + alloc_bottom_up_after_check(); + + return 0; +} + +static int alloc_in_between_check(void) +{ + memblock_set_bottom_up(false); + alloc_in_between_generic_check(); + memblock_set_bottom_up(true); + alloc_in_between_generic_check(); + + return 0; +} + +static int alloc_second_fit_check(void) +{ + memblock_set_bottom_up(false); + alloc_top_down_second_fit_check(); + memblock_set_bottom_up(true); + alloc_bottom_up_second_fit_check(); + + return 0; +} + +static int alloc_small_gaps_check(void) +{ + memblock_set_bottom_up(false); + alloc_small_gaps_generic_check(); + memblock_set_bottom_up(true); + alloc_small_gaps_generic_check(); + + return 0; +} + +static int alloc_all_reserved_check(void) +{ + memblock_set_bottom_up(false); + alloc_all_reserved_generic_check(); + memblock_set_bottom_up(true); + alloc_all_reserved_generic_check(); + + return 0; +} + +static int alloc_no_space_check(void) +{ + memblock_set_bottom_up(false); + alloc_no_space_generic_check(); + memblock_set_bottom_up(true); + alloc_no_space_generic_check(); + + return 0; +} + +static int alloc_limited_space_check(void) +{ + memblock_set_bottom_up(false); + alloc_limited_space_generic_check(); + memblock_set_bottom_up(true); + alloc_limited_space_generic_check(); + + return 0; +} + +static int alloc_no_memory_check(void) +{ + memblock_set_bottom_up(false); + alloc_no_memory_generic_check(); + memblock_set_bottom_up(true); + alloc_no_memory_generic_check(); + + return 0; +} + +int memblock_alloc_checks(void) +{ + reset_memblock_attributes(); + dummy_physical_memory_init(); + + alloc_simple_check(); + alloc_disjoint_check(); + alloc_before_check(); + alloc_after_check(); + alloc_second_fit_check(); + alloc_small_gaps_check(); + alloc_in_between_check(); + alloc_all_reserved_check(); + alloc_no_space_check(); + alloc_limited_space_check(); + alloc_no_memory_check(); + + dummy_physical_memory_cleanup(); + + return 0; +} diff --git a/tools/testing/memblock/tests/alloc_api.h b/tools/testing/memblock/tests/alloc_api.h new file mode 100644 index 000000000000..585b085baf21 --- /dev/null +++ b/tools/testing/memblock/tests/alloc_api.h @@ -0,0 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef _MEMBLOCK_ALLOCS_H +#define _MEMBLOCK_ALLOCS_H + +#include "common.h" + +int memblock_alloc_checks(void); + +#endif diff --git a/tools/testing/memblock/tests/alloc_helpers_api.c b/tools/testing/memblock/tests/alloc_helpers_api.c new file mode 100644 index 000000000000..963a966db461 --- /dev/null +++ b/tools/testing/memblock/tests/alloc_helpers_api.c @@ -0,0 +1,393 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +#include "alloc_helpers_api.h" + +/* + * A simple test that tries to allocate a memory region above a specified, + * aligned address: + * + * + + * | +-----------+ | + * | | rgn | | + * +----------+-----------+---------+ + * ^ + * | + * Aligned min_addr + * + * Expect to allocate a cleared region at the minimal memory address. + */ +static int alloc_from_simple_generic_check(void) +{ + struct memblock_region *rgn = &memblock.reserved.regions[0]; + void *allocated_ptr = NULL; + char *b; + + phys_addr_t size = SZ_16; + phys_addr_t min_addr; + + setup_memblock(); + + min_addr = memblock_end_of_DRAM() - SMP_CACHE_BYTES; + + allocated_ptr = memblock_alloc_from(size, SMP_CACHE_BYTES, min_addr); + b = (char *)allocated_ptr; + + assert(allocated_ptr); + assert(*b == 0); + + assert(rgn->size == size); + assert(rgn->base == min_addr); + + assert(memblock.reserved.cnt == 1); + assert(memblock.reserved.total_size == size); + + return 0; +} + +/* + * A test that tries to allocate a memory region above a certain address. + * The minimal address here is not aligned: + * + * + + + * | + +---------+ | + * | | | rgn | | + * +------+------+---------+------------+ + * ^ ^------. + * | | + * min_addr Aligned address + * boundary + * + * Expect to allocate a cleared region at the closest aligned memory address. + */ +static int alloc_from_misaligned_generic_check(void) +{ + struct memblock_region *rgn = &memblock.reserved.regions[0]; + void *allocated_ptr = NULL; + char *b; + + phys_addr_t size = SZ_32; + phys_addr_t min_addr; + + setup_memblock(); + + /* A misaligned address */ + min_addr = memblock_end_of_DRAM() - (SMP_CACHE_BYTES * 2 - 1); + + allocated_ptr = memblock_alloc_from(size, SMP_CACHE_BYTES, min_addr); + b = (char *)allocated_ptr; + + assert(allocated_ptr); + assert(*b == 0); + + assert(rgn->size == size); + assert(rgn->base == memblock_end_of_DRAM() - SMP_CACHE_BYTES); + + assert(memblock.reserved.cnt == 1); + assert(memblock.reserved.total_size == size); + + return 0; +} + +/* + * A test that tries to allocate a memory region above an address that is too + * close to the end of the memory: + * + * + + + * | +--------+---+ | + * | | rgn + | | + * +-----------+--------+---+------+ + * ^ ^ + * | | + * | min_addr + * | + * Aligned address + * boundary + * + * Expect to prioritize granting memory over satisfying the minimal address + * requirement. + */ +static int alloc_from_top_down_high_addr_check(void) +{ + struct memblock_region *rgn = &memblock.reserved.regions[0]; + void *allocated_ptr = NULL; + + phys_addr_t size = SZ_32; + phys_addr_t min_addr; + + setup_memblock(); + + /* The address is too close to the end of the memory */ + min_addr = memblock_end_of_DRAM() - SZ_16; + + allocated_ptr = memblock_alloc_from(size, SMP_CACHE_BYTES, min_addr); + + assert(allocated_ptr); + assert(rgn->size == size); + assert(rgn->base == memblock_end_of_DRAM() - SMP_CACHE_BYTES); + + assert(memblock.reserved.cnt == 1); + assert(memblock.reserved.total_size == size); + + return 0; +} + +/* + * A test that tries to allocate a memory region when there is no space + * available above the minimal address above a certain address: + * + * + + * | +---------+-------------| + * | | rgn | | + * +--------+---------+-------------+ + * ^ + * | + * min_addr + * + * Expect to prioritize granting memory over satisfying the minimal address + * requirement and to allocate next to the previously reserved region. The + * regions get merged into one. + */ +static int alloc_from_top_down_no_space_above_check(void) +{ + struct memblock_region *rgn = &memblock.reserved.regions[0]; + void *allocated_ptr = NULL; + + phys_addr_t r1_size = SZ_64; + phys_addr_t r2_size = SZ_2; + phys_addr_t total_size = r1_size + r2_size; + phys_addr_t min_addr; + + setup_memblock(); + + min_addr = memblock_end_of_DRAM() - SMP_CACHE_BYTES * 2; + + /* No space above this address */ + memblock_reserve(min_addr, r2_size); + + allocated_ptr = memblock_alloc_from(r1_size, SMP_CACHE_BYTES, min_addr); + + assert(allocated_ptr); + assert(rgn->base == min_addr - r1_size); + assert(rgn->size == total_size); + + assert(memblock.reserved.cnt == 1); + assert(memblock.reserved.total_size == total_size); + + return 0; +} + +/* + * A test that tries to allocate a memory region with a minimal address below + * the start address of the available memory. As the allocation is top-down, + * first reserve a region that will force allocation near the start. + * Expect successful allocation and merge of both regions. + */ +static int alloc_from_top_down_min_addr_cap_check(void) +{ + struct memblock_region *rgn = &memblock.reserved.regions[0]; + void *allocated_ptr = NULL; + + phys_addr_t r1_size = SZ_64; + phys_addr_t min_addr; + phys_addr_t start_addr; + + setup_memblock(); + + start_addr = (phys_addr_t)memblock_start_of_DRAM(); + min_addr = start_addr - SMP_CACHE_BYTES * 3; + + memblock_reserve(start_addr + r1_size, MEM_SIZE - r1_size); + + allocated_ptr = memblock_alloc_from(r1_size, SMP_CACHE_BYTES, min_addr); + + assert(allocated_ptr); + assert(rgn->base == start_addr); + assert(rgn->size == MEM_SIZE); + + assert(memblock.reserved.cnt == 1); + assert(memblock.reserved.total_size == MEM_SIZE); + + return 0; +} + +/* + * A test that tries to allocate a memory region above an address that is too + * close to the end of the memory: + * + * + + * |-----------+ + | + * | rgn | | | + * +-----------+--------------+-----+ + * ^ ^ + * | | + * Aligned address min_addr + * boundary + * + * Expect to prioritize granting memory over satisfying the minimal address + * requirement. Allocation happens at beginning of the available memory. + */ +static int alloc_from_bottom_up_high_addr_check(void) +{ + struct memblock_region *rgn = &memblock.reserved.regions[0]; + void *allocated_ptr = NULL; + + phys_addr_t size = SZ_32; + phys_addr_t min_addr; + + setup_memblock(); + + /* The address is too close to the end of the memory */ + min_addr = memblock_end_of_DRAM() - SZ_8; + + allocated_ptr = memblock_alloc_from(size, SMP_CACHE_BYTES, min_addr); + + assert(allocated_ptr); + assert(rgn->size == size); + assert(rgn->base == memblock_start_of_DRAM()); + + assert(memblock.reserved.cnt == 1); + assert(memblock.reserved.total_size == size); + + return 0; +} + +/* + * A test that tries to allocate a memory region when there is no space + * available above the minimal address above a certain address: + * + * + + * |-----------+ +-------------------| + * | rgn | | | + * +-----------+----+-------------------+ + * ^ + * | + * min_addr + * + * Expect to prioritize granting memory over satisfying the minimal address + * requirement and to allocate at the beginning of the available memory. + */ +static int alloc_from_bottom_up_no_space_above_check(void) +{ + struct memblock_region *rgn = &memblock.reserved.regions[0]; + void *allocated_ptr = NULL; + + phys_addr_t r1_size = SZ_64; + phys_addr_t min_addr; + phys_addr_t r2_size; + + setup_memblock(); + + min_addr = memblock_start_of_DRAM() + SZ_128; + r2_size = memblock_end_of_DRAM() - min_addr; + + /* No space above this address */ + memblock_reserve(min_addr - SMP_CACHE_BYTES, r2_size); + + allocated_ptr = memblock_alloc_from(r1_size, SMP_CACHE_BYTES, min_addr); + + assert(allocated_ptr); + assert(rgn->base == memblock_start_of_DRAM()); + assert(rgn->size == r1_size); + + assert(memblock.reserved.cnt == 2); + assert(memblock.reserved.total_size == r1_size + r2_size); + + return 0; +} + +/* + * A test that tries to allocate a memory region with a minimal address below + * the start address of the available memory. Expect to allocate a region + * at the beginning of the available memory. + */ +static int alloc_from_bottom_up_min_addr_cap_check(void) +{ + struct memblock_region *rgn = &memblock.reserved.regions[0]; + void *allocated_ptr = NULL; + + phys_addr_t r1_size = SZ_64; + phys_addr_t min_addr; + phys_addr_t start_addr; + + setup_memblock(); + + start_addr = (phys_addr_t)memblock_start_of_DRAM(); + min_addr = start_addr - SMP_CACHE_BYTES * 3; + + allocated_ptr = memblock_alloc_from(r1_size, SMP_CACHE_BYTES, min_addr); + + assert(allocated_ptr); + assert(rgn->base == start_addr); + assert(rgn->size == r1_size); + + assert(memblock.reserved.cnt == 1); + assert(memblock.reserved.total_size == r1_size); + + return 0; +} + +/* Test case wrappers */ +static int alloc_from_simple_check(void) +{ + memblock_set_bottom_up(false); + alloc_from_simple_generic_check(); + memblock_set_bottom_up(true); + alloc_from_simple_generic_check(); + + return 0; +} + +static int alloc_from_misaligned_check(void) +{ + memblock_set_bottom_up(false); + alloc_from_misaligned_generic_check(); + memblock_set_bottom_up(true); + alloc_from_misaligned_generic_check(); + + return 0; +} + +static int alloc_from_high_addr_check(void) +{ + memblock_set_bottom_up(false); + alloc_from_top_down_high_addr_check(); + memblock_set_bottom_up(true); + alloc_from_bottom_up_high_addr_check(); + + return 0; +} + +static int alloc_from_no_space_above_check(void) +{ + memblock_set_bottom_up(false); + alloc_from_top_down_no_space_above_check(); + memblock_set_bottom_up(true); + alloc_from_bottom_up_no_space_above_check(); + + return 0; +} + +static int alloc_from_min_addr_cap_check(void) +{ + memblock_set_bottom_up(false); + alloc_from_top_down_min_addr_cap_check(); + memblock_set_bottom_up(true); + alloc_from_bottom_up_min_addr_cap_check(); + + return 0; +} + +int memblock_alloc_helpers_checks(void) +{ + reset_memblock_attributes(); + dummy_physical_memory_init(); + + alloc_from_simple_check(); + alloc_from_misaligned_check(); + alloc_from_high_addr_check(); + alloc_from_no_space_above_check(); + alloc_from_min_addr_cap_check(); + + dummy_physical_memory_cleanup(); + + return 0; +} diff --git a/tools/testing/memblock/tests/alloc_helpers_api.h b/tools/testing/memblock/tests/alloc_helpers_api.h new file mode 100644 index 000000000000..c9e4827b1623 --- /dev/null +++ b/tools/testing/memblock/tests/alloc_helpers_api.h @@ -0,0 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef _MEMBLOCK_ALLOC_HELPERS_H +#define _MEMBLOCK_ALLOC_HELPERS_H + +#include "common.h" + +int memblock_alloc_helpers_checks(void); + +#endif diff --git a/tools/testing/memblock/tests/alloc_nid_api.c b/tools/testing/memblock/tests/alloc_nid_api.c new file mode 100644 index 000000000000..6390206e50e1 --- /dev/null +++ b/tools/testing/memblock/tests/alloc_nid_api.c @@ -0,0 +1,1174 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +#include "alloc_nid_api.h" + +/* + * A simple test that tries to allocate a memory region within min_addr and + * max_addr range: + * + * + + + * | + +-----------+ | + * | | | rgn | | + * +----+-------+-----------+------+ + * ^ ^ + * | | + * min_addr max_addr + * + * Expect to allocate a cleared region that ends at max_addr. + */ +static int alloc_try_nid_top_down_simple_check(void) +{ + struct memblock_region *rgn = &memblock.reserved.regions[0]; + void *allocated_ptr = NULL; + char *b; + + phys_addr_t size = SZ_128; + phys_addr_t min_addr; + phys_addr_t max_addr; + phys_addr_t rgn_end; + + setup_memblock(); + + min_addr = memblock_start_of_DRAM() + SMP_CACHE_BYTES * 2; + max_addr = min_addr + SZ_512; + + allocated_ptr = memblock_alloc_try_nid(size, SMP_CACHE_BYTES, + min_addr, max_addr, NUMA_NO_NODE); + b = (char *)allocated_ptr; + rgn_end = rgn->base + rgn->size; + + assert(allocated_ptr); + assert(*b == 0); + + assert(rgn->size == size); + assert(rgn->base == max_addr - size); + assert(rgn_end == max_addr); + + assert(memblock.reserved.cnt == 1); + assert(memblock.reserved.total_size == size); + + return 0; +} + +/* + * A simple test that tries to allocate a memory region within min_addr and + * max_addr range, where the end address is misaligned: + * + * + + + + * | + +---------+ + | + * | | | rgn | | | + * +------+-------+---------+--+----+ + * ^ ^ ^ + * | | | + * min_add | max_addr + * | + * Aligned address + * boundary + * + * Expect to allocate a cleared, aligned region that ends before max_addr. + */ +static int alloc_try_nid_top_down_end_misaligned_check(void) +{ + struct memblock_region *rgn = &memblock.reserved.regions[0]; + void *allocated_ptr = NULL; + char *b; + + phys_addr_t size = SZ_128; + phys_addr_t misalign = SZ_2; + phys_addr_t min_addr; + phys_addr_t max_addr; + phys_addr_t rgn_end; + + setup_memblock(); + + min_addr = memblock_start_of_DRAM() + SMP_CACHE_BYTES * 2; + max_addr = min_addr + SZ_512 + misalign; + + allocated_ptr = memblock_alloc_try_nid(size, SMP_CACHE_BYTES, + min_addr, max_addr, NUMA_NO_NODE); + b = (char *)allocated_ptr; + rgn_end = rgn->base + rgn->size; + + assert(allocated_ptr); + assert(*b == 0); + + assert(rgn->size == size); + assert(rgn->base == max_addr - size - misalign); + assert(rgn_end < max_addr); + + assert(memblock.reserved.cnt == 1); + assert(memblock.reserved.total_size == size); + + return 0; +} + +/* + * A simple test that tries to allocate a memory region, which spans over the + * min_addr and max_addr range: + * + * + + + * | +---------------+ | + * | | rgn | | + * +------+---------------+-------+ + * ^ ^ + * | | + * min_addr max_addr + * + * Expect to allocate a cleared region that starts at min_addr and ends at + * max_addr, given that min_addr is aligned. + */ +static int alloc_try_nid_exact_address_generic_check(void) +{ + struct memblock_region *rgn = &memblock.reserved.regions[0]; + void *allocated_ptr = NULL; + char *b; + + phys_addr_t size = SZ_1K; + phys_addr_t min_addr; + phys_addr_t max_addr; + phys_addr_t rgn_end; + + setup_memblock(); + + min_addr = memblock_start_of_DRAM() + SMP_CACHE_BYTES; + max_addr = min_addr + size; + + allocated_ptr = memblock_alloc_try_nid(size, SMP_CACHE_BYTES, + min_addr, max_addr, NUMA_NO_NODE); + b = (char *)allocated_ptr; + rgn_end = rgn->base + rgn->size; + + assert(allocated_ptr); + assert(*b == 0); + + assert(rgn->size == size); + assert(rgn->base == min_addr); + assert(rgn_end == max_addr); + + assert(memblock.reserved.cnt == 1); + assert(memblock.reserved.total_size == size); + + return 0; +} + +/* + * A test that tries to allocate a memory region, which can't fit into + * min_addr and max_addr range: + * + * + + + + * | +----------+-----+ | + * | | rgn + | | + * +--------+----------+-----+----+ + * ^ ^ ^ + * | | | + * Aligned | max_addr + * address | + * boundary min_add + * + * Expect to drop the lower limit and allocate a cleared memory region which + * ends at max_addr (if the address is aligned). + */ +static int alloc_try_nid_top_down_narrow_range_check(void) +{ + struct memblock_region *rgn = &memblock.reserved.regions[0]; + void *allocated_ptr = NULL; + char *b; + + phys_addr_t size = SZ_256; + phys_addr_t min_addr; + phys_addr_t max_addr; + + setup_memblock(); + + min_addr = memblock_start_of_DRAM() + SZ_512; + max_addr = min_addr + SMP_CACHE_BYTES; + + allocated_ptr = memblock_alloc_try_nid(size, SMP_CACHE_BYTES, + min_addr, max_addr, NUMA_NO_NODE); + b = (char *)allocated_ptr; + + assert(allocated_ptr); + assert(*b == 0); + + assert(rgn->size == size); + assert(rgn->base == max_addr - size); + + assert(memblock.reserved.cnt == 1); + assert(memblock.reserved.total_size == size); + + return 0; +} + +/* + * A test that tries to allocate a memory region, which can't fit into + * min_addr and max_addr range, with the latter being too close to the beginning + * of the available memory: + * + * +-------------+ + * | new | + * +-------------+ + * + + + * | + | + * | | | + * +-------+--------------+ + * ^ ^ + * | | + * | max_addr + * | + * min_addr + * + * Expect no allocation to happen. + */ +static int alloc_try_nid_low_max_generic_check(void) +{ + void *allocated_ptr = NULL; + + phys_addr_t size = SZ_1K; + phys_addr_t min_addr; + phys_addr_t max_addr; + + setup_memblock(); + + min_addr = memblock_start_of_DRAM(); + max_addr = min_addr + SMP_CACHE_BYTES; + + allocated_ptr = memblock_alloc_try_nid(size, SMP_CACHE_BYTES, + min_addr, max_addr, NUMA_NO_NODE); + + assert(!allocated_ptr); + + return 0; +} + +/* + * A test that tries to allocate a memory region within min_addr min_addr range, + * with min_addr being so close that it's next to an allocated region: + * + * + + + * | +--------+---------------| + * | | r1 | rgn | + * +-------+--------+---------------+ + * ^ ^ + * | | + * min_addr max_addr + * + * Expect a merge of both regions. Only the region size gets updated. + */ +static int alloc_try_nid_min_reserved_generic_check(void) +{ + struct memblock_region *rgn = &memblock.reserved.regions[0]; + void *allocated_ptr = NULL; + char *b; + + phys_addr_t r1_size = SZ_128; + phys_addr_t r2_size = SZ_64; + phys_addr_t total_size = r1_size + r2_size; + phys_addr_t min_addr; + phys_addr_t max_addr; + phys_addr_t reserved_base; + + setup_memblock(); + + max_addr = memblock_end_of_DRAM(); + min_addr = max_addr - r2_size; + reserved_base = min_addr - r1_size; + + memblock_reserve(reserved_base, r1_size); + + allocated_ptr = memblock_alloc_try_nid(r2_size, SMP_CACHE_BYTES, + min_addr, max_addr, NUMA_NO_NODE); + b = (char *)allocated_ptr; + + assert(allocated_ptr); + assert(*b == 0); + + assert(rgn->size == total_size); + assert(rgn->base == reserved_base); + + assert(memblock.reserved.cnt == 1); + assert(memblock.reserved.total_size == total_size); + + return 0; +} + +/* + * A test that tries to allocate a memory region within min_addr and max_addr, + * with max_addr being so close that it's next to an allocated region: + * + * + + + * | +-------------+--------| + * | | rgn | r1 | + * +----------+-------------+--------+ + * ^ ^ + * | | + * min_addr max_addr + * + * Expect a merge of regions. Only the region size gets updated. + */ +static int alloc_try_nid_max_reserved_generic_check(void) +{ + struct memblock_region *rgn = &memblock.reserved.regions[0]; + void *allocated_ptr = NULL; + char *b; + + phys_addr_t r1_size = SZ_64; + phys_addr_t r2_size = SZ_128; + phys_addr_t total_size = r1_size + r2_size; + phys_addr_t min_addr; + phys_addr_t max_addr; + + setup_memblock(); + + max_addr = memblock_end_of_DRAM() - r1_size; + min_addr = max_addr - r2_size; + + memblock_reserve(max_addr, r1_size); + + allocated_ptr = memblock_alloc_try_nid(r2_size, SMP_CACHE_BYTES, + min_addr, max_addr, NUMA_NO_NODE); + b = (char *)allocated_ptr; + + assert(allocated_ptr); + assert(*b == 0); + + assert(rgn->size == total_size); + assert(rgn->base == min_addr); + + assert(memblock.reserved.cnt == 1); + assert(memblock.reserved.total_size == total_size); + + return 0; +} + +/* + * A test that tries to allocate memory within min_addr and max_add range, when + * there are two reserved regions at the borders, with a gap big enough to fit + * a new region: + * + * + + + * | +--------+ +-------+------+ | + * | | r2 | | rgn | r1 | | + * +----+--------+---+-------+------+--+ + * ^ ^ + * | | + * min_addr max_addr + * + * Expect to merge the new region with r1. The second region does not get + * updated. The total size field gets updated. + */ + +static int alloc_try_nid_top_down_reserved_with_space_check(void) +{ + struct memblock_region *rgn1 = &memblock.reserved.regions[1]; + struct memblock_region *rgn2 = &memblock.reserved.regions[0]; + void *allocated_ptr = NULL; + char *b; + struct region r1, r2; + + phys_addr_t r3_size = SZ_64; + phys_addr_t gap_size = SMP_CACHE_BYTES; + phys_addr_t total_size; + phys_addr_t max_addr; + phys_addr_t min_addr; + + setup_memblock(); + + r1.base = memblock_end_of_DRAM() - SMP_CACHE_BYTES * 2; + r1.size = SMP_CACHE_BYTES; + + r2.size = SZ_128; + r2.base = r1.base - (r3_size + gap_size + r2.size); + + total_size = r1.size + r2.size + r3_size; + min_addr = r2.base + r2.size; + max_addr = r1.base; + + memblock_reserve(r1.base, r1.size); + memblock_reserve(r2.base, r2.size); + + allocated_ptr = memblock_alloc_try_nid(r3_size, SMP_CACHE_BYTES, + min_addr, max_addr, NUMA_NO_NODE); + b = (char *)allocated_ptr; + + assert(allocated_ptr); + assert(*b == 0); + + assert(rgn1->size == r1.size + r3_size); + assert(rgn1->base == max_addr - r3_size); + + assert(rgn2->size == r2.size); + assert(rgn2->base == r2.base); + + assert(memblock.reserved.cnt == 2); + assert(memblock.reserved.total_size == total_size); + + return 0; +} + +/* + * A test that tries to allocate memory within min_addr and max_add range, when + * there are two reserved regions at the borders, with a gap of a size equal to + * the size of the new region: + * + * + + + * | +--------+--------+--------+ | + * | | r2 | r3 | r1 | | + * +-----+--------+--------+--------+-----+ + * ^ ^ + * | | + * min_addr max_addr + * + * Expect to merge all of the regions into one. The region counter and total + * size fields get updated. + */ +static int alloc_try_nid_reserved_full_merge_generic_check(void) +{ + struct memblock_region *rgn = &memblock.reserved.regions[0]; + void *allocated_ptr = NULL; + char *b; + struct region r1, r2; + + phys_addr_t r3_size = SZ_64; + phys_addr_t total_size; + phys_addr_t max_addr; + phys_addr_t min_addr; + + setup_memblock(); + + r1.base = memblock_end_of_DRAM() - SMP_CACHE_BYTES * 2; + r1.size = SMP_CACHE_BYTES; + + r2.size = SZ_128; + r2.base = r1.base - (r3_size + r2.size); + + total_size = r1.size + r2.size + r3_size; + min_addr = r2.base + r2.size; + max_addr = r1.base; + + memblock_reserve(r1.base, r1.size); + memblock_reserve(r2.base, r2.size); + + allocated_ptr = memblock_alloc_try_nid(r3_size, SMP_CACHE_BYTES, + min_addr, max_addr, NUMA_NO_NODE); + b = (char *)allocated_ptr; + + assert(allocated_ptr); + assert(*b == 0); + + assert(rgn->size == total_size); + assert(rgn->base == r2.base); + + assert(memblock.reserved.cnt == 1); + assert(memblock.reserved.total_size == total_size); + + return 0; +} + +/* + * A test that tries to allocate memory within min_addr and max_add range, when + * there are two reserved regions at the borders, with a gap that can't fit + * a new region: + * + * + + + * | +----------+------+ +------+ | + * | | r3 | r2 | | r1 | | + * +--+----------+------+----+------+---+ + * ^ ^ + * | | + * | max_addr + * | + * min_addr + * + * Expect to merge the new region with r2. The second region does not get + * updated. The total size counter gets updated. + */ +static int alloc_try_nid_top_down_reserved_no_space_check(void) +{ + struct memblock_region *rgn1 = &memblock.reserved.regions[1]; + struct memblock_region *rgn2 = &memblock.reserved.regions[0]; + void *allocated_ptr = NULL; + char *b; + struct region r1, r2; + + phys_addr_t r3_size = SZ_256; + phys_addr_t gap_size = SMP_CACHE_BYTES; + phys_addr_t total_size; + phys_addr_t max_addr; + phys_addr_t min_addr; + + setup_memblock(); + + r1.base = memblock_end_of_DRAM() - SMP_CACHE_BYTES * 2; + r1.size = SMP_CACHE_BYTES; + + r2.size = SZ_128; + r2.base = r1.base - (r2.size + gap_size); + + total_size = r1.size + r2.size + r3_size; + min_addr = r2.base + r2.size; + max_addr = r1.base; + + memblock_reserve(r1.base, r1.size); + memblock_reserve(r2.base, r2.size); + + allocated_ptr = memblock_alloc_try_nid(r3_size, SMP_CACHE_BYTES, + min_addr, max_addr, NUMA_NO_NODE); + b = (char *)allocated_ptr; + + assert(allocated_ptr); + assert(*b == 0); + + assert(rgn1->size == r1.size); + assert(rgn1->base == r1.base); + + assert(rgn2->size == r2.size + r3_size); + assert(rgn2->base == r2.base - r3_size); + + assert(memblock.reserved.cnt == 2); + assert(memblock.reserved.total_size == total_size); + + return 0; +} + +/* + * A test that tries to allocate memory within min_addr and max_add range, but + * it's too narrow and everything else is reserved: + * + * +-----------+ + * | new | + * +-----------+ + * + + + * |--------------+ +----------| + * | r2 | | r1 | + * +--------------+------+----------+ + * ^ ^ + * | | + * | max_addr + * | + * min_addr + * + * Expect no allocation to happen. + */ + +static int alloc_try_nid_reserved_all_generic_check(void) +{ + void *allocated_ptr = NULL; + struct region r1, r2; + + phys_addr_t r3_size = SZ_256; + phys_addr_t gap_size = SMP_CACHE_BYTES; + phys_addr_t max_addr; + phys_addr_t min_addr; + + setup_memblock(); + + r1.base = memblock_end_of_DRAM() - SMP_CACHE_BYTES; + r1.size = SMP_CACHE_BYTES; + + r2.size = MEM_SIZE - (r1.size + gap_size); + r2.base = memblock_start_of_DRAM(); + + min_addr = r2.base + r2.size; + max_addr = r1.base; + + memblock_reserve(r1.base, r1.size); + memblock_reserve(r2.base, r2.size); + + allocated_ptr = memblock_alloc_try_nid(r3_size, SMP_CACHE_BYTES, + min_addr, max_addr, NUMA_NO_NODE); + + assert(!allocated_ptr); + + return 0; +} + +/* + * A test that tries to allocate a memory region, where max_addr is + * bigger than the end address of the available memory. Expect to allocate + * a cleared region that ends before the end of the memory. + */ +static int alloc_try_nid_top_down_cap_max_check(void) +{ + struct memblock_region *rgn = &memblock.reserved.regions[0]; + void *allocated_ptr = NULL; + char *b; + + phys_addr_t size = SZ_256; + phys_addr_t min_addr; + phys_addr_t max_addr; + + setup_memblock(); + + min_addr = memblock_end_of_DRAM() - SZ_1K; + max_addr = memblock_end_of_DRAM() + SZ_256; + + allocated_ptr = memblock_alloc_try_nid(size, SMP_CACHE_BYTES, + min_addr, max_addr, NUMA_NO_NODE); + b = (char *)allocated_ptr; + + assert(allocated_ptr); + assert(*b == 0); + + assert(rgn->size == size); + assert(rgn->base == memblock_end_of_DRAM() - size); + + assert(memblock.reserved.cnt == 1); + assert(memblock.reserved.total_size == size); + + return 0; +} + +/* + * A test that tries to allocate a memory region, where min_addr is + * smaller than the start address of the available memory. Expect to allocate + * a cleared region that ends before the end of the memory. + */ +static int alloc_try_nid_top_down_cap_min_check(void) +{ + struct memblock_region *rgn = &memblock.reserved.regions[0]; + void *allocated_ptr = NULL; + char *b; + + phys_addr_t size = SZ_1K; + phys_addr_t min_addr; + phys_addr_t max_addr; + + setup_memblock(); + + min_addr = memblock_start_of_DRAM() - SZ_256; + max_addr = memblock_end_of_DRAM(); + + allocated_ptr = memblock_alloc_try_nid(size, SMP_CACHE_BYTES, + min_addr, max_addr, NUMA_NO_NODE); + b = (char *)allocated_ptr; + + assert(allocated_ptr); + assert(*b == 0); + + assert(rgn->size == size); + assert(rgn->base == memblock_end_of_DRAM() - size); + + assert(memblock.reserved.cnt == 1); + assert(memblock.reserved.total_size == size); + + return 0; +} + +/* + * A simple test that tries to allocate a memory region within min_addr and + * max_addr range: + * + * + + + * | +-----------+ | | + * | | rgn | | | + * +----+-----------+-----------+------+ + * ^ ^ + * | | + * min_addr max_addr + * + * Expect to allocate a cleared region that ends before max_addr. + */ +static int alloc_try_nid_bottom_up_simple_check(void) +{ + struct memblock_region *rgn = &memblock.reserved.regions[0]; + void *allocated_ptr = NULL; + char *b; + + phys_addr_t size = SZ_128; + phys_addr_t min_addr; + phys_addr_t max_addr; + phys_addr_t rgn_end; + + setup_memblock(); + + min_addr = memblock_start_of_DRAM() + SMP_CACHE_BYTES * 2; + max_addr = min_addr + SZ_512; + + allocated_ptr = memblock_alloc_try_nid(size, SMP_CACHE_BYTES, + min_addr, max_addr, + NUMA_NO_NODE); + b = (char *)allocated_ptr; + rgn_end = rgn->base + rgn->size; + + assert(allocated_ptr); + assert(*b == 0); + + assert(rgn->size == size); + assert(rgn->base == min_addr); + assert(rgn_end < max_addr); + + assert(memblock.reserved.cnt == 1); + assert(memblock.reserved.total_size == size); + + return 0; +} + +/* + * A simple test that tries to allocate a memory region within min_addr and + * max_addr range, where the start address is misaligned: + * + * + + + * | + +-----------+ + | + * | | | rgn | | | + * +-----+---+-----------+-----+-----+ + * ^ ^----. ^ + * | | | + * min_add | max_addr + * | + * Aligned address + * boundary + * + * Expect to allocate a cleared, aligned region that ends before max_addr. + */ +static int alloc_try_nid_bottom_up_start_misaligned_check(void) +{ + struct memblock_region *rgn = &memblock.reserved.regions[0]; + void *allocated_ptr = NULL; + char *b; + + phys_addr_t size = SZ_128; + phys_addr_t misalign = SZ_2; + phys_addr_t min_addr; + phys_addr_t max_addr; + phys_addr_t rgn_end; + + setup_memblock(); + + min_addr = memblock_start_of_DRAM() + misalign; + max_addr = min_addr + SZ_512; + + allocated_ptr = memblock_alloc_try_nid(size, SMP_CACHE_BYTES, + min_addr, max_addr, + NUMA_NO_NODE); + b = (char *)allocated_ptr; + rgn_end = rgn->base + rgn->size; + + assert(allocated_ptr); + assert(*b == 0); + + assert(rgn->size == size); + assert(rgn->base == min_addr + (SMP_CACHE_BYTES - misalign)); + assert(rgn_end < max_addr); + + assert(memblock.reserved.cnt == 1); + assert(memblock.reserved.total_size == size); + + return 0; +} + +/* + * A test that tries to allocate a memory region, which can't fit into min_addr + * and max_addr range: + * + * + + + * |---------+ + + | + * | rgn | | | | + * +---------+---------+----+------+ + * ^ ^ + * | | + * | max_addr + * | + * min_add + * + * Expect to drop the lower limit and allocate a cleared memory region which + * starts at the beginning of the available memory. + */ +static int alloc_try_nid_bottom_up_narrow_range_check(void) +{ + struct memblock_region *rgn = &memblock.reserved.regions[0]; + void *allocated_ptr = NULL; + char *b; + + phys_addr_t size = SZ_256; + phys_addr_t min_addr; + phys_addr_t max_addr; + + setup_memblock(); + + min_addr = memblock_start_of_DRAM() + SZ_512; + max_addr = min_addr + SMP_CACHE_BYTES; + + allocated_ptr = memblock_alloc_try_nid(size, SMP_CACHE_BYTES, + min_addr, max_addr, + NUMA_NO_NODE); + b = (char *)allocated_ptr; + + assert(allocated_ptr); + assert(*b == 0); + + assert(rgn->size == size); + assert(rgn->base == memblock_start_of_DRAM()); + + assert(memblock.reserved.cnt == 1); + assert(memblock.reserved.total_size == size); + + return 0; +} + +/* + * A test that tries to allocate memory within min_addr and max_add range, when + * there are two reserved regions at the borders, with a gap big enough to fit + * a new region: + * + * + + + * | +--------+-------+ +------+ | + * | | r2 | rgn | | r1 | | + * +----+--------+-------+---+------+--+ + * ^ ^ + * | | + * min_addr max_addr + * + * Expect to merge the new region with r2. The second region does not get + * updated. The total size field gets updated. + */ + +static int alloc_try_nid_bottom_up_reserved_with_space_check(void) +{ + struct memblock_region *rgn1 = &memblock.reserved.regions[1]; + struct memblock_region *rgn2 = &memblock.reserved.regions[0]; + void *allocated_ptr = NULL; + char *b; + struct region r1, r2; + + phys_addr_t r3_size = SZ_64; + phys_addr_t gap_size = SMP_CACHE_BYTES; + phys_addr_t total_size; + phys_addr_t max_addr; + phys_addr_t min_addr; + + setup_memblock(); + + r1.base = memblock_end_of_DRAM() - SMP_CACHE_BYTES * 2; + r1.size = SMP_CACHE_BYTES; + + r2.size = SZ_128; + r2.base = r1.base - (r3_size + gap_size + r2.size); + + total_size = r1.size + r2.size + r3_size; + min_addr = r2.base + r2.size; + max_addr = r1.base; + + memblock_reserve(r1.base, r1.size); + memblock_reserve(r2.base, r2.size); + + allocated_ptr = memblock_alloc_try_nid(r3_size, SMP_CACHE_BYTES, + min_addr, max_addr, + NUMA_NO_NODE); + b = (char *)allocated_ptr; + + assert(allocated_ptr); + assert(*b == 0); + + assert(rgn1->size == r1.size); + assert(rgn1->base == max_addr); + + assert(rgn2->size == r2.size + r3_size); + assert(rgn2->base == r2.base); + + assert(memblock.reserved.cnt == 2); + assert(memblock.reserved.total_size == total_size); + + return 0; +} + +/* + * A test that tries to allocate memory within min_addr and max_add range, when + * there are two reserved regions at the borders, with a gap of a size equal to + * the size of the new region: + * + * + + + * |----------+ +------+ +----+ | + * | r3 | | r2 | | r1 | | + * +----------+----+------+---+----+--+ + * ^ ^ + * | | + * | max_addr + * | + * min_addr + * + * Expect to drop the lower limit and allocate memory at the beginning of the + * available memory. The region counter and total size fields get updated. + * Other regions are not modified. + */ + +static int alloc_try_nid_bottom_up_reserved_no_space_check(void) +{ + struct memblock_region *rgn1 = &memblock.reserved.regions[2]; + struct memblock_region *rgn2 = &memblock.reserved.regions[1]; + struct memblock_region *rgn3 = &memblock.reserved.regions[0]; + void *allocated_ptr = NULL; + char *b; + struct region r1, r2; + + phys_addr_t r3_size = SZ_256; + phys_addr_t gap_size = SMP_CACHE_BYTES; + phys_addr_t total_size; + phys_addr_t max_addr; + phys_addr_t min_addr; + + setup_memblock(); + + r1.base = memblock_end_of_DRAM() - SMP_CACHE_BYTES * 2; + r1.size = SMP_CACHE_BYTES; + + r2.size = SZ_128; + r2.base = r1.base - (r2.size + gap_size); + + total_size = r1.size + r2.size + r3_size; + min_addr = r2.base + r2.size; + max_addr = r1.base; + + memblock_reserve(r1.base, r1.size); + memblock_reserve(r2.base, r2.size); + + allocated_ptr = memblock_alloc_try_nid(r3_size, SMP_CACHE_BYTES, + min_addr, max_addr, + NUMA_NO_NODE); + b = (char *)allocated_ptr; + + assert(allocated_ptr); + assert(*b == 0); + + assert(rgn3->size == r3_size); + assert(rgn3->base == memblock_start_of_DRAM()); + + assert(rgn2->size == r2.size); + assert(rgn2->base == r2.base); + + assert(rgn1->size == r1.size); + assert(rgn1->base == r1.base); + + assert(memblock.reserved.cnt == 3); + assert(memblock.reserved.total_size == total_size); + + return 0; +} + +/* + * A test that tries to allocate a memory region, where max_addr is + * bigger than the end address of the available memory. Expect to allocate + * a cleared region that starts at the min_addr + */ +static int alloc_try_nid_bottom_up_cap_max_check(void) +{ + struct memblock_region *rgn = &memblock.reserved.regions[0]; + void *allocated_ptr = NULL; + char *b; + + phys_addr_t size = SZ_256; + phys_addr_t min_addr; + phys_addr_t max_addr; + + setup_memblock(); + + min_addr = memblock_start_of_DRAM() + SZ_1K; + max_addr = memblock_end_of_DRAM() + SZ_256; + + allocated_ptr = memblock_alloc_try_nid(size, SMP_CACHE_BYTES, + min_addr, max_addr, + NUMA_NO_NODE); + b = (char *)allocated_ptr; + + assert(allocated_ptr); + assert(*b == 0); + + assert(rgn->size == size); + assert(rgn->base == min_addr); + + assert(memblock.reserved.cnt == 1); + assert(memblock.reserved.total_size == size); + + return 0; +} + +/* + * A test that tries to allocate a memory region, where min_addr is + * smaller than the start address of the available memory. Expect to allocate + * a cleared region at the beginning of the available memory. + */ +static int alloc_try_nid_bottom_up_cap_min_check(void) +{ + struct memblock_region *rgn = &memblock.reserved.regions[0]; + void *allocated_ptr = NULL; + char *b; + + phys_addr_t size = SZ_1K; + phys_addr_t min_addr; + phys_addr_t max_addr; + + setup_memblock(); + + min_addr = memblock_start_of_DRAM(); + max_addr = memblock_end_of_DRAM() - SZ_256; + + allocated_ptr = memblock_alloc_try_nid(size, SMP_CACHE_BYTES, + min_addr, max_addr, + NUMA_NO_NODE); + b = (char *)allocated_ptr; + + assert(allocated_ptr); + assert(*b == 0); + + assert(rgn->size == size); + assert(rgn->base == memblock_start_of_DRAM()); + + assert(memblock.reserved.cnt == 1); + assert(memblock.reserved.total_size == size); + + return 0; +} + +/* Test case wrappers */ +static int alloc_try_nid_simple_check(void) +{ + memblock_set_bottom_up(false); + alloc_try_nid_top_down_simple_check(); + memblock_set_bottom_up(true); + alloc_try_nid_bottom_up_simple_check(); + + return 0; +} + +static int alloc_try_nid_misaligned_check(void) +{ + memblock_set_bottom_up(false); + alloc_try_nid_top_down_end_misaligned_check(); + memblock_set_bottom_up(true); + alloc_try_nid_bottom_up_start_misaligned_check(); + + return 0; +} + +static int alloc_try_nid_narrow_range_check(void) +{ + memblock_set_bottom_up(false); + alloc_try_nid_top_down_narrow_range_check(); + memblock_set_bottom_up(true); + alloc_try_nid_bottom_up_narrow_range_check(); + + return 0; +} + +static int alloc_try_nid_reserved_with_space_check(void) +{ + memblock_set_bottom_up(false); + alloc_try_nid_top_down_reserved_with_space_check(); + memblock_set_bottom_up(true); + alloc_try_nid_bottom_up_reserved_with_space_check(); + + return 0; +} + +static int alloc_try_nid_reserved_no_space_check(void) +{ + memblock_set_bottom_up(false); + alloc_try_nid_top_down_reserved_no_space_check(); + memblock_set_bottom_up(true); + alloc_try_nid_bottom_up_reserved_no_space_check(); + + return 0; +} + +static int alloc_try_nid_cap_max_check(void) +{ + memblock_set_bottom_up(false); + alloc_try_nid_top_down_cap_max_check(); + memblock_set_bottom_up(true); + alloc_try_nid_bottom_up_cap_max_check(); + + return 0; +} + +static int alloc_try_nid_cap_min_check(void) +{ + memblock_set_bottom_up(false); + alloc_try_nid_top_down_cap_min_check(); + memblock_set_bottom_up(true); + alloc_try_nid_bottom_up_cap_min_check(); + + return 0; +} + +static int alloc_try_nid_min_reserved_check(void) +{ + memblock_set_bottom_up(false); + alloc_try_nid_min_reserved_generic_check(); + memblock_set_bottom_up(true); + alloc_try_nid_min_reserved_generic_check(); + + return 0; +} + +static int alloc_try_nid_max_reserved_check(void) +{ + memblock_set_bottom_up(false); + alloc_try_nid_max_reserved_generic_check(); + memblock_set_bottom_up(true); + alloc_try_nid_max_reserved_generic_check(); + + return 0; +} + +static int alloc_try_nid_exact_address_check(void) +{ + memblock_set_bottom_up(false); + alloc_try_nid_exact_address_generic_check(); + memblock_set_bottom_up(true); + alloc_try_nid_exact_address_generic_check(); + + return 0; +} + +static int alloc_try_nid_reserved_full_merge_check(void) +{ + memblock_set_bottom_up(false); + alloc_try_nid_reserved_full_merge_generic_check(); + memblock_set_bottom_up(true); + alloc_try_nid_reserved_full_merge_generic_check(); + + return 0; +} + +static int alloc_try_nid_reserved_all_check(void) +{ + memblock_set_bottom_up(false); + alloc_try_nid_reserved_all_generic_check(); + memblock_set_bottom_up(true); + alloc_try_nid_reserved_all_generic_check(); + + return 0; +} + +static int alloc_try_nid_low_max_check(void) +{ + memblock_set_bottom_up(false); + alloc_try_nid_low_max_generic_check(); + memblock_set_bottom_up(true); + alloc_try_nid_low_max_generic_check(); + + return 0; +} + +int memblock_alloc_nid_checks(void) +{ + reset_memblock_attributes(); + dummy_physical_memory_init(); + + alloc_try_nid_simple_check(); + alloc_try_nid_misaligned_check(); + alloc_try_nid_narrow_range_check(); + alloc_try_nid_reserved_with_space_check(); + alloc_try_nid_reserved_no_space_check(); + alloc_try_nid_cap_max_check(); + alloc_try_nid_cap_min_check(); + + alloc_try_nid_min_reserved_check(); + alloc_try_nid_max_reserved_check(); + alloc_try_nid_exact_address_check(); + alloc_try_nid_reserved_full_merge_check(); + alloc_try_nid_reserved_all_check(); + alloc_try_nid_low_max_check(); + + dummy_physical_memory_cleanup(); + + return 0; +} diff --git a/tools/testing/memblock/tests/alloc_nid_api.h b/tools/testing/memblock/tests/alloc_nid_api.h new file mode 100644 index 000000000000..b35cf3c3f489 --- /dev/null +++ b/tools/testing/memblock/tests/alloc_nid_api.h @@ -0,0 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef _MEMBLOCK_ALLOC_NID_H +#define _MEMBLOCK_ALLOC_NID_H + +#include "common.h" + +int memblock_alloc_nid_checks(void); + +#endif diff --git a/tools/testing/memblock/tests/basic_api.c b/tools/testing/memblock/tests/basic_api.c new file mode 100644 index 000000000000..fbc1ce160303 --- /dev/null +++ b/tools/testing/memblock/tests/basic_api.c @@ -0,0 +1,903 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +#include <string.h> +#include <linux/memblock.h> +#include "basic_api.h" + +#define EXPECTED_MEMBLOCK_REGIONS 128 + +static int memblock_initialization_check(void) +{ + assert(memblock.memory.regions); + assert(memblock.memory.cnt == 1); + assert(memblock.memory.max == EXPECTED_MEMBLOCK_REGIONS); + assert(strcmp(memblock.memory.name, "memory") == 0); + + assert(memblock.reserved.regions); + assert(memblock.reserved.cnt == 1); + assert(memblock.memory.max == EXPECTED_MEMBLOCK_REGIONS); + assert(strcmp(memblock.reserved.name, "reserved") == 0); + + assert(!memblock.bottom_up); + assert(memblock.current_limit == MEMBLOCK_ALLOC_ANYWHERE); + + return 0; +} + +/* + * A simple test that adds a memory block of a specified base address + * and size to the collection of available memory regions (memblock.memory). + * It checks if a new entry was created and if region counter and total memory + * were correctly updated. + */ +static int memblock_add_simple_check(void) +{ + struct memblock_region *rgn; + + rgn = &memblock.memory.regions[0]; + + struct region r = { + .base = SZ_1G, + .size = SZ_4M + }; + + reset_memblock_regions(); + memblock_add(r.base, r.size); + + assert(rgn->base == r.base); + assert(rgn->size == r.size); + + assert(memblock.memory.cnt == 1); + assert(memblock.memory.total_size == r.size); + + return 0; +} + +/* + * A simple test that adds a memory block of a specified base address, size + * NUMA node and memory flags to the collection of available memory regions. + * It checks if the new entry, region counter and total memory size have + * expected values. + */ +static int memblock_add_node_simple_check(void) +{ + struct memblock_region *rgn; + + rgn = &memblock.memory.regions[0]; + + struct region r = { + .base = SZ_1M, + .size = SZ_16M + }; + + reset_memblock_regions(); + memblock_add_node(r.base, r.size, 1, MEMBLOCK_HOTPLUG); + + assert(rgn->base == r.base); + assert(rgn->size == r.size); +#ifdef CONFIG_NUMA + assert(rgn->nid == 1); +#endif + assert(rgn->flags == MEMBLOCK_HOTPLUG); + + assert(memblock.memory.cnt == 1); + assert(memblock.memory.total_size == r.size); + + return 0; +} + +/* + * A test that tries to add two memory blocks that don't overlap with one + * another. It checks if two correctly initialized entries were added to the + * collection of available memory regions (memblock.memory) and if this + * change was reflected in memblock.memory's total size and region counter. + */ +static int memblock_add_disjoint_check(void) +{ + struct memblock_region *rgn1, *rgn2; + + rgn1 = &memblock.memory.regions[0]; + rgn2 = &memblock.memory.regions[1]; + + struct region r1 = { + .base = SZ_1G, + .size = SZ_8K + }; + struct region r2 = { + .base = SZ_1G + SZ_16K, + .size = SZ_8K + }; + + reset_memblock_regions(); + memblock_add(r1.base, r1.size); + memblock_add(r2.base, r2.size); + + assert(rgn1->base == r1.base); + assert(rgn1->size == r1.size); + + assert(rgn2->base == r2.base); + assert(rgn2->size == r2.size); + + assert(memblock.memory.cnt == 2); + assert(memblock.memory.total_size == r1.size + r2.size); + + return 0; +} + +/* + * A test that tries to add two memory blocks, where the second one overlaps + * with the beginning of the first entry (that is r1.base < r2.base + r2.size). + * After this, it checks if two entries are merged into one region that starts + * at r2.base and has size of two regions minus their intersection. It also + * verifies the reported total size of the available memory and region counter. + */ +static int memblock_add_overlap_top_check(void) +{ + struct memblock_region *rgn; + phys_addr_t total_size; + + rgn = &memblock.memory.regions[0]; + + struct region r1 = { + .base = SZ_512M, + .size = SZ_1G + }; + struct region r2 = { + .base = SZ_256M, + .size = SZ_512M + }; + + total_size = (r1.base - r2.base) + r1.size; + + reset_memblock_regions(); + memblock_add(r1.base, r1.size); + memblock_add(r2.base, r2.size); + + assert(rgn->base == r2.base); + assert(rgn->size == total_size); + + assert(memblock.memory.cnt == 1); + assert(memblock.memory.total_size == total_size); + + return 0; +} + +/* + * A test that tries to add two memory blocks, where the second one overlaps + * with the end of the first entry (that is r2.base < r1.base + r1.size). + * After this, it checks if two entries are merged into one region that starts + * at r1.base and has size of two regions minus their intersection. It verifies + * that memblock can still see only one entry and has a correct total size of + * the available memory. + */ +static int memblock_add_overlap_bottom_check(void) +{ + struct memblock_region *rgn; + phys_addr_t total_size; + + rgn = &memblock.memory.regions[0]; + + struct region r1 = { + .base = SZ_128M, + .size = SZ_512M + }; + struct region r2 = { + .base = SZ_256M, + .size = SZ_1G + }; + + total_size = (r2.base - r1.base) + r2.size; + + reset_memblock_regions(); + memblock_add(r1.base, r1.size); + memblock_add(r2.base, r2.size); + + assert(rgn->base == r1.base); + assert(rgn->size == total_size); + + assert(memblock.memory.cnt == 1); + assert(memblock.memory.total_size == total_size); + + return 0; +} + +/* + * A test that tries to add two memory blocks, where the second one is + * within the range of the first entry (that is r1.base < r2.base && + * r2.base + r2.size < r1.base + r1.size). It checks if two entries are merged + * into one region that stays the same. The counter and total size of available + * memory are expected to not be updated. + */ +static int memblock_add_within_check(void) +{ + struct memblock_region *rgn; + + rgn = &memblock.memory.regions[0]; + + struct region r1 = { + .base = SZ_8M, + .size = SZ_32M + }; + struct region r2 = { + .base = SZ_16M, + .size = SZ_1M + }; + + reset_memblock_regions(); + memblock_add(r1.base, r1.size); + memblock_add(r2.base, r2.size); + + assert(rgn->base == r1.base); + assert(rgn->size == r1.size); + + assert(memblock.memory.cnt == 1); + assert(memblock.memory.total_size == r1.size); + + return 0; +} + +/* + * A simple test that tries to add the same memory block twice. The counter + * and total size of available memory are expected to not be updated. + */ +static int memblock_add_twice_check(void) +{ + struct region r = { + .base = SZ_16K, + .size = SZ_2M + }; + + reset_memblock_regions(); + + memblock_add(r.base, r.size); + memblock_add(r.base, r.size); + + assert(memblock.memory.cnt == 1); + assert(memblock.memory.total_size == r.size); + + return 0; +} + +static int memblock_add_checks(void) +{ + memblock_add_simple_check(); + memblock_add_node_simple_check(); + memblock_add_disjoint_check(); + memblock_add_overlap_top_check(); + memblock_add_overlap_bottom_check(); + memblock_add_within_check(); + memblock_add_twice_check(); + + return 0; +} + + /* + * A simple test that marks a memory block of a specified base address + * and size as reserved and to the collection of reserved memory regions + * (memblock.reserved). It checks if a new entry was created and if region + * counter and total memory size were correctly updated. + */ +static int memblock_reserve_simple_check(void) +{ + struct memblock_region *rgn; + + rgn = &memblock.reserved.regions[0]; + + struct region r = { + .base = SZ_2G, + .size = SZ_128M + }; + + reset_memblock_regions(); + memblock_reserve(r.base, r.size); + + assert(rgn->base == r.base); + assert(rgn->size == r.size); + + return 0; +} + +/* + * A test that tries to mark two memory blocks that don't overlap as reserved + * and checks if two entries were correctly added to the collection of reserved + * memory regions (memblock.reserved) and if this change was reflected in + * memblock.reserved's total size and region counter. + */ +static int memblock_reserve_disjoint_check(void) +{ + struct memblock_region *rgn1, *rgn2; + + rgn1 = &memblock.reserved.regions[0]; + rgn2 = &memblock.reserved.regions[1]; + + struct region r1 = { + .base = SZ_256M, + .size = SZ_16M + }; + struct region r2 = { + .base = SZ_512M, + .size = SZ_512M + }; + + reset_memblock_regions(); + memblock_reserve(r1.base, r1.size); + memblock_reserve(r2.base, r2.size); + + assert(rgn1->base == r1.base); + assert(rgn1->size == r1.size); + + assert(rgn2->base == r2.base); + assert(rgn2->size == r2.size); + + assert(memblock.reserved.cnt == 2); + assert(memblock.reserved.total_size == r1.size + r2.size); + + return 0; +} + +/* + * A test that tries to mark two memory blocks as reserved, where the + * second one overlaps with the beginning of the first (that is + * r1.base < r2.base + r2.size). + * It checks if two entries are merged into one region that starts at r2.base + * and has size of two regions minus their intersection. The test also verifies + * that memblock can still see only one entry and has a correct total size of + * the reserved memory. + */ +static int memblock_reserve_overlap_top_check(void) +{ + struct memblock_region *rgn; + phys_addr_t total_size; + + rgn = &memblock.reserved.regions[0]; + + struct region r1 = { + .base = SZ_1G, + .size = SZ_1G + }; + struct region r2 = { + .base = SZ_128M, + .size = SZ_1G + }; + + total_size = (r1.base - r2.base) + r1.size; + + reset_memblock_regions(); + memblock_reserve(r1.base, r1.size); + memblock_reserve(r2.base, r2.size); + + assert(rgn->base == r2.base); + assert(rgn->size == total_size); + + assert(memblock.reserved.cnt == 1); + assert(memblock.reserved.total_size == total_size); + + return 0; +} + +/* + * A test that tries to mark two memory blocks as reserved, where the + * second one overlaps with the end of the first entry (that is + * r2.base < r1.base + r1.size). + * It checks if two entries are merged into one region that starts at r1.base + * and has size of two regions minus their intersection. It verifies that + * memblock can still see only one entry and has a correct total size of the + * reserved memory. + */ +static int memblock_reserve_overlap_bottom_check(void) +{ + struct memblock_region *rgn; + phys_addr_t total_size; + + rgn = &memblock.reserved.regions[0]; + + struct region r1 = { + .base = SZ_2K, + .size = SZ_128K + }; + struct region r2 = { + .base = SZ_128K, + .size = SZ_128K + }; + + total_size = (r2.base - r1.base) + r2.size; + + reset_memblock_regions(); + memblock_reserve(r1.base, r1.size); + memblock_reserve(r2.base, r2.size); + + assert(rgn->base == r1.base); + assert(rgn->size == total_size); + + assert(memblock.reserved.cnt == 1); + assert(memblock.reserved.total_size == total_size); + + return 0; +} + +/* + * A test that tries to mark two memory blocks as reserved, where the second + * one is within the range of the first entry (that is + * (r1.base < r2.base) && (r2.base + r2.size < r1.base + r1.size)). + * It checks if two entries are merged into one region that stays the + * same. The counter and total size of available memory are expected to not be + * updated. + */ +static int memblock_reserve_within_check(void) +{ + struct memblock_region *rgn; + + rgn = &memblock.reserved.regions[0]; + + struct region r1 = { + .base = SZ_1M, + .size = SZ_8M + }; + struct region r2 = { + .base = SZ_2M, + .size = SZ_64K + }; + + reset_memblock_regions(); + memblock_reserve(r1.base, r1.size); + memblock_reserve(r2.base, r2.size); + + assert(rgn->base == r1.base); + assert(rgn->size == r1.size); + + assert(memblock.reserved.cnt == 1); + assert(memblock.reserved.total_size == r1.size); + + return 0; +} + +/* + * A simple test that tries to reserve the same memory block twice. + * The region counter and total size of reserved memory are expected to not + * be updated. + */ +static int memblock_reserve_twice_check(void) +{ + struct region r = { + .base = SZ_16K, + .size = SZ_2M + }; + + reset_memblock_regions(); + + memblock_reserve(r.base, r.size); + memblock_reserve(r.base, r.size); + + assert(memblock.reserved.cnt == 1); + assert(memblock.reserved.total_size == r.size); + + return 0; +} + +static int memblock_reserve_checks(void) +{ + memblock_reserve_simple_check(); + memblock_reserve_disjoint_check(); + memblock_reserve_overlap_top_check(); + memblock_reserve_overlap_bottom_check(); + memblock_reserve_within_check(); + memblock_reserve_twice_check(); + + return 0; +} + + /* + * A simple test that tries to remove the first entry of the array of + * available memory regions. By "removing" a region we mean overwriting it + * with the next region in memblock.memory. To check this is the case, the + * test adds two memory blocks and verifies that the value of the latter + * was used to erase r1 region. It also checks if the region counter and + * total size were updated to expected values. + */ +static int memblock_remove_simple_check(void) +{ + struct memblock_region *rgn; + + rgn = &memblock.memory.regions[0]; + + struct region r1 = { + .base = SZ_2K, + .size = SZ_4K + }; + struct region r2 = { + .base = SZ_128K, + .size = SZ_4M + }; + + reset_memblock_regions(); + memblock_add(r1.base, r1.size); + memblock_add(r2.base, r2.size); + memblock_remove(r1.base, r1.size); + + assert(rgn->base == r2.base); + assert(rgn->size == r2.size); + + assert(memblock.memory.cnt == 1); + assert(memblock.memory.total_size == r2.size); + + return 0; +} + + /* + * A test that tries to remove a region that was not registered as available + * memory (i.e. has no corresponding entry in memblock.memory). It verifies + * that array, regions counter and total size were not modified. + */ +static int memblock_remove_absent_check(void) +{ + struct memblock_region *rgn; + + rgn = &memblock.memory.regions[0]; + + struct region r1 = { + .base = SZ_512K, + .size = SZ_4M + }; + struct region r2 = { + .base = SZ_64M, + .size = SZ_1G + }; + + reset_memblock_regions(); + memblock_add(r1.base, r1.size); + memblock_remove(r2.base, r2.size); + + assert(rgn->base == r1.base); + assert(rgn->size == r1.size); + + assert(memblock.memory.cnt == 1); + assert(memblock.memory.total_size == r1.size); + + return 0; +} + +/* + * A test that tries to remove a region which overlaps with the beginning of + * the already existing entry r1 (that is r1.base < r2.base + r2.size). It + * checks if only the intersection of both regions is removed from the available + * memory pool. The test also checks if the regions counter and total size are + * updated to expected values. + */ +static int memblock_remove_overlap_top_check(void) +{ + struct memblock_region *rgn; + phys_addr_t r1_end, r2_end, total_size; + + rgn = &memblock.memory.regions[0]; + + struct region r1 = { + .base = SZ_32M, + .size = SZ_32M + }; + struct region r2 = { + .base = SZ_16M, + .size = SZ_32M + }; + + r1_end = r1.base + r1.size; + r2_end = r2.base + r2.size; + total_size = r1_end - r2_end; + + reset_memblock_regions(); + memblock_add(r1.base, r1.size); + memblock_remove(r2.base, r2.size); + + assert(rgn->base == r1.base + r2.base); + assert(rgn->size == total_size); + + assert(memblock.memory.cnt == 1); + assert(memblock.memory.total_size == total_size); + + return 0; +} + +/* + * A test that tries to remove a region which overlaps with the end of the + * first entry (that is r2.base < r1.base + r1.size). It checks if only the + * intersection of both regions is removed from the available memory pool. + * The test also checks if the regions counter and total size are updated to + * expected values. + */ +static int memblock_remove_overlap_bottom_check(void) +{ + struct memblock_region *rgn; + phys_addr_t total_size; + + rgn = &memblock.memory.regions[0]; + + struct region r1 = { + .base = SZ_2M, + .size = SZ_64M + }; + struct region r2 = { + .base = SZ_32M, + .size = SZ_256M + }; + + total_size = r2.base - r1.base; + + reset_memblock_regions(); + memblock_add(r1.base, r1.size); + memblock_remove(r2.base, r2.size); + + assert(rgn->base == r1.base); + assert(rgn->size == total_size); + + assert(memblock.memory.cnt == 1); + assert(memblock.memory.total_size == total_size); + return 0; +} + +/* + * A test that tries to remove a region which is within the range of the + * already existing entry (that is + * (r1.base < r2.base) && (r2.base + r2.size < r1.base + r1.size)). + * It checks if the region is split into two - one that ends at r2.base and + * second that starts at r2.base + size, with appropriate sizes. The test + * also checks if the region counter and total size were updated to + * expected values. + */ +static int memblock_remove_within_check(void) +{ + struct memblock_region *rgn1, *rgn2; + phys_addr_t r1_size, r2_size, total_size; + + rgn1 = &memblock.memory.regions[0]; + rgn2 = &memblock.memory.regions[1]; + + struct region r1 = { + .base = SZ_1M, + .size = SZ_32M + }; + struct region r2 = { + .base = SZ_16M, + .size = SZ_1M + }; + + r1_size = r2.base - r1.base; + r2_size = (r1.base + r1.size) - (r2.base + r2.size); + total_size = r1_size + r2_size; + + reset_memblock_regions(); + memblock_add(r1.base, r1.size); + memblock_remove(r2.base, r2.size); + + assert(rgn1->base == r1.base); + assert(rgn1->size == r1_size); + + assert(rgn2->base == r2.base + r2.size); + assert(rgn2->size == r2_size); + + assert(memblock.memory.cnt == 2); + assert(memblock.memory.total_size == total_size); + + return 0; +} + +static int memblock_remove_checks(void) +{ + memblock_remove_simple_check(); + memblock_remove_absent_check(); + memblock_remove_overlap_top_check(); + memblock_remove_overlap_bottom_check(); + memblock_remove_within_check(); + + return 0; +} + +/* + * A simple test that tries to free a memory block that was marked earlier + * as reserved. By "freeing" a region we mean overwriting it with the next + * entry in memblock.reserved. To check this is the case, the test reserves + * two memory regions and verifies that the value of the latter was used to + * erase r1 region. + * The test also checks if the region counter and total size were updated. + */ +static int memblock_free_simple_check(void) +{ + struct memblock_region *rgn; + + rgn = &memblock.reserved.regions[0]; + + struct region r1 = { + .base = SZ_4M, + .size = SZ_1M + }; + struct region r2 = { + .base = SZ_8M, + .size = SZ_1M + }; + + reset_memblock_regions(); + memblock_reserve(r1.base, r1.size); + memblock_reserve(r2.base, r2.size); + memblock_free((void *)r1.base, r1.size); + + assert(rgn->base == r2.base); + assert(rgn->size == r2.size); + + assert(memblock.reserved.cnt == 1); + assert(memblock.reserved.total_size == r2.size); + + return 0; +} + + /* + * A test that tries to free a region that was not marked as reserved + * (i.e. has no corresponding entry in memblock.reserved). It verifies + * that array, regions counter and total size were not modified. + */ +static int memblock_free_absent_check(void) +{ + struct memblock_region *rgn; + + rgn = &memblock.reserved.regions[0]; + + struct region r1 = { + .base = SZ_2M, + .size = SZ_8K + }; + struct region r2 = { + .base = SZ_16M, + .size = SZ_128M + }; + + reset_memblock_regions(); + memblock_reserve(r1.base, r1.size); + memblock_free((void *)r2.base, r2.size); + + assert(rgn->base == r1.base); + assert(rgn->size == r1.size); + + assert(memblock.reserved.cnt == 1); + assert(memblock.reserved.total_size == r1.size); + + return 0; +} + +/* + * A test that tries to free a region which overlaps with the beginning of + * the already existing entry r1 (that is r1.base < r2.base + r2.size). It + * checks if only the intersection of both regions is freed. The test also + * checks if the regions counter and total size are updated to expected + * values. + */ +static int memblock_free_overlap_top_check(void) +{ + struct memblock_region *rgn; + phys_addr_t total_size; + + rgn = &memblock.reserved.regions[0]; + + struct region r1 = { + .base = SZ_8M, + .size = SZ_32M + }; + struct region r2 = { + .base = SZ_1M, + .size = SZ_8M + }; + + total_size = (r1.size + r1.base) - (r2.base + r2.size); + + reset_memblock_regions(); + memblock_reserve(r1.base, r1.size); + memblock_free((void *)r2.base, r2.size); + + assert(rgn->base == r2.base + r2.size); + assert(rgn->size == total_size); + + assert(memblock.reserved.cnt == 1); + assert(memblock.reserved.total_size == total_size); + + return 0; +} + +/* + * A test that tries to free a region which overlaps with the end of the + * first entry (that is r2.base < r1.base + r1.size). It checks if only the + * intersection of both regions is freed. The test also checks if the + * regions counter and total size are updated to expected values. + */ +static int memblock_free_overlap_bottom_check(void) +{ + struct memblock_region *rgn; + phys_addr_t total_size; + + rgn = &memblock.reserved.regions[0]; + + struct region r1 = { + .base = SZ_8M, + .size = SZ_32M + }; + struct region r2 = { + .base = SZ_32M, + .size = SZ_32M + }; + + total_size = r2.base - r1.base; + + reset_memblock_regions(); + memblock_reserve(r1.base, r1.size); + memblock_free((void *)r2.base, r2.size); + + assert(rgn->base == r1.base); + assert(rgn->size == total_size); + + assert(memblock.reserved.cnt == 1); + assert(memblock.reserved.total_size == total_size); + + return 0; +} + +/* + * A test that tries to free a region which is within the range of the + * already existing entry (that is + * (r1.base < r2.base) && (r2.base + r2.size < r1.base + r1.size)). + * It checks if the region is split into two - one that ends at r2.base and + * second that starts at r2.base + size, with appropriate sizes. It is + * expected that the region counter and total size fields were updated t + * reflect that change. + */ +static int memblock_free_within_check(void) +{ + struct memblock_region *rgn1, *rgn2; + phys_addr_t r1_size, r2_size, total_size; + + rgn1 = &memblock.reserved.regions[0]; + rgn2 = &memblock.reserved.regions[1]; + + struct region r1 = { + .base = SZ_1M, + .size = SZ_8M + }; + struct region r2 = { + .base = SZ_4M, + .size = SZ_1M + }; + + r1_size = r2.base - r1.base; + r2_size = (r1.base + r1.size) - (r2.base + r2.size); + total_size = r1_size + r2_size; + + reset_memblock_regions(); + memblock_reserve(r1.base, r1.size); + memblock_free((void *)r2.base, r2.size); + + assert(rgn1->base == r1.base); + assert(rgn1->size == r1_size); + + assert(rgn2->base == r2.base + r2.size); + assert(rgn2->size == r2_size); + + assert(memblock.reserved.cnt == 2); + assert(memblock.reserved.total_size == total_size); + + return 0; +} + +static int memblock_free_checks(void) +{ + memblock_free_simple_check(); + memblock_free_absent_check(); + memblock_free_overlap_top_check(); + memblock_free_overlap_bottom_check(); + memblock_free_within_check(); + + return 0; +} + +int memblock_basic_checks(void) +{ + memblock_initialization_check(); + memblock_add_checks(); + memblock_reserve_checks(); + memblock_remove_checks(); + memblock_free_checks(); + + return 0; +} diff --git a/tools/testing/memblock/tests/basic_api.h b/tools/testing/memblock/tests/basic_api.h new file mode 100644 index 000000000000..1873faa54754 --- /dev/null +++ b/tools/testing/memblock/tests/basic_api.h @@ -0,0 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef _MEMBLOCK_BASIC_H +#define _MEMBLOCK_BASIC_H + +#include "common.h" + +int memblock_basic_checks(void); + +#endif diff --git a/tools/testing/memblock/tests/common.c b/tools/testing/memblock/tests/common.c new file mode 100644 index 000000000000..62d3191f7c9a --- /dev/null +++ b/tools/testing/memblock/tests/common.c @@ -0,0 +1,48 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +#include "tests/common.h" +#include <string.h> + +#define INIT_MEMBLOCK_REGIONS 128 +#define INIT_MEMBLOCK_RESERVED_REGIONS INIT_MEMBLOCK_REGIONS + +static struct test_memory memory_block; + +void reset_memblock_regions(void) +{ + memset(memblock.memory.regions, 0, + memblock.memory.cnt * sizeof(struct memblock_region)); + memblock.memory.cnt = 1; + memblock.memory.max = INIT_MEMBLOCK_REGIONS; + memblock.memory.total_size = 0; + + memset(memblock.reserved.regions, 0, + memblock.reserved.cnt * sizeof(struct memblock_region)); + memblock.reserved.cnt = 1; + memblock.reserved.max = INIT_MEMBLOCK_RESERVED_REGIONS; + memblock.reserved.total_size = 0; +} + +void reset_memblock_attributes(void) +{ + memblock.memory.name = "memory"; + memblock.reserved.name = "reserved"; + memblock.bottom_up = false; + memblock.current_limit = MEMBLOCK_ALLOC_ANYWHERE; +} + +void setup_memblock(void) +{ + reset_memblock_regions(); + memblock_add((phys_addr_t)memory_block.base, MEM_SIZE); +} + +void dummy_physical_memory_init(void) +{ + memory_block.base = malloc(MEM_SIZE); + assert(memory_block.base); +} + +void dummy_physical_memory_cleanup(void) +{ + free(memory_block.base); +} diff --git a/tools/testing/memblock/tests/common.h b/tools/testing/memblock/tests/common.h new file mode 100644 index 000000000000..619054d03219 --- /dev/null +++ b/tools/testing/memblock/tests/common.h @@ -0,0 +1,34 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef _MEMBLOCK_TEST_H +#define _MEMBLOCK_TEST_H + +#include <stdlib.h> +#include <assert.h> +#include <linux/types.h> +#include <linux/memblock.h> +#include <linux/sizes.h> + +#define MEM_SIZE SZ_16K + +/* + * Available memory registered with memblock needs to be valid for allocs + * test to run. This is a convenience wrapper for memory allocated in + * dummy_physical_memory_init() that is later registered with memblock + * in setup_memblock(). + */ +struct test_memory { + void *base; +}; + +struct region { + phys_addr_t base; + phys_addr_t size; +}; + +void reset_memblock_regions(void); +void reset_memblock_attributes(void); +void setup_memblock(void); +void dummy_physical_memory_init(void); +void dummy_physical_memory_cleanup(void); + +#endif diff --git a/tools/testing/radix-tree/Makefile b/tools/testing/radix-tree/Makefile index aa6abfe0749c..c4ea4fbb0bfc 100644 --- a/tools/testing/radix-tree/Makefile +++ b/tools/testing/radix-tree/Makefile @@ -5,7 +5,8 @@ CFLAGS += -I. -I../../include -g -Og -Wall -D_LGPL_SOURCE -fsanitize=address \ LDFLAGS += -fsanitize=address -fsanitize=undefined LDLIBS+= -lpthread -lurcu TARGETS = main idr-test multiorder xarray -CORE_OFILES := xarray.o radix-tree.o idr.o linux.o test.o find_bit.o bitmap.o +CORE_OFILES := xarray.o radix-tree.o idr.o linux.o test.o find_bit.o bitmap.o \ + slab.o OFILES = main.o $(CORE_OFILES) regression1.o regression2.o regression3.o \ regression4.o tag_check.o multiorder.o idr-test.o iteration_check.o \ iteration_check_2.o benchmark.o diff --git a/tools/testing/radix-tree/linux.c b/tools/testing/radix-tree/linux.c index 2d9c59df60de..81539f543954 100644 --- a/tools/testing/radix-tree/linux.c +++ b/tools/testing/radix-tree/linux.c @@ -14,7 +14,6 @@ int nr_allocated; int preempt_count; -int kmalloc_verbose; int test_verbose; struct kmem_cache { @@ -78,32 +77,6 @@ void kmem_cache_free(struct kmem_cache *cachep, void *objp) pthread_mutex_unlock(&cachep->lock); } -void *kmalloc(size_t size, gfp_t gfp) -{ - void *ret; - - if (!(gfp & __GFP_DIRECT_RECLAIM)) - return NULL; - - ret = malloc(size); - uatomic_inc(&nr_allocated); - if (kmalloc_verbose) - printf("Allocating %p from malloc\n", ret); - if (gfp & __GFP_ZERO) - memset(ret, 0, size); - return ret; -} - -void kfree(void *p) -{ - if (!p) - return; - uatomic_dec(&nr_allocated); - if (kmalloc_verbose) - printf("Freeing %p to malloc\n", p); - free(p); -} - struct kmem_cache * kmem_cache_create(const char *name, unsigned int size, unsigned int align, unsigned int flags, void (*ctor)(void *)) diff --git a/tools/testing/radix-tree/linux/gfp.h b/tools/testing/radix-tree/linux/gfp.h deleted file mode 100644 index 32159c08a52e..000000000000 --- a/tools/testing/radix-tree/linux/gfp.h +++ /dev/null @@ -1,33 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _GFP_H -#define _GFP_H - -#include <linux/types.h> - -#define __GFP_BITS_SHIFT 26 -#define __GFP_BITS_MASK ((gfp_t)((1 << __GFP_BITS_SHIFT) - 1)) - -#define __GFP_HIGH 0x20u -#define __GFP_IO 0x40u -#define __GFP_FS 0x80u -#define __GFP_NOWARN 0x200u -#define __GFP_ZERO 0x8000u -#define __GFP_ATOMIC 0x80000u -#define __GFP_ACCOUNT 0x100000u -#define __GFP_DIRECT_RECLAIM 0x400000u -#define __GFP_KSWAPD_RECLAIM 0x2000000u - -#define __GFP_RECLAIM (__GFP_DIRECT_RECLAIM|__GFP_KSWAPD_RECLAIM) - -#define GFP_ZONEMASK 0x0fu -#define GFP_ATOMIC (__GFP_HIGH|__GFP_ATOMIC|__GFP_KSWAPD_RECLAIM) -#define GFP_KERNEL (__GFP_RECLAIM | __GFP_IO | __GFP_FS) -#define GFP_NOWAIT (__GFP_KSWAPD_RECLAIM) - - -static inline bool gfpflags_allow_blocking(const gfp_t gfp_flags) -{ - return !!(gfp_flags & __GFP_DIRECT_RECLAIM); -} - -#endif diff --git a/tools/testing/radix-tree/linux/slab.h b/tools/testing/radix-tree/linux/slab.h deleted file mode 100644 index 2958830ce4d7..000000000000 --- a/tools/testing/radix-tree/linux/slab.h +++ /dev/null @@ -1,27 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef SLAB_H -#define SLAB_H - -#include <linux/types.h> -#include <linux/gfp.h> - -#define SLAB_HWCACHE_ALIGN 1 -#define SLAB_PANIC 2 -#define SLAB_RECLAIM_ACCOUNT 0x00020000UL /* Objects are reclaimable */ - -void *kmalloc(size_t size, gfp_t); -void kfree(void *); - -static inline void *kzalloc(size_t size, gfp_t gfp) -{ - return kmalloc(size, gfp | __GFP_ZERO); -} - -void *kmem_cache_alloc(struct kmem_cache *cachep, int flags); -void kmem_cache_free(struct kmem_cache *cachep, void *objp); - -struct kmem_cache *kmem_cache_create(const char *name, unsigned int size, - unsigned int align, unsigned int flags, - void (*ctor)(void *)); - -#endif /* SLAB_H */ diff --git a/tools/testing/scatterlist/linux/mm.h b/tools/testing/scatterlist/linux/mm.h index 16ec895bbe5f..5bd9e6e80625 100644 --- a/tools/testing/scatterlist/linux/mm.h +++ b/tools/testing/scatterlist/linux/mm.h @@ -74,7 +74,7 @@ static inline unsigned long page_to_phys(struct page *page) __UNIQUE_ID(min1_), __UNIQUE_ID(min2_), \ x, y) -#define preemptible() (1) +#define pagefault_disabled() (0) static inline void *kmap(struct page *page) { @@ -127,6 +127,7 @@ kmalloc_array(unsigned int n, unsigned int size, unsigned int flags) #define kmemleak_free(a) #define PageSlab(p) (0) +#define flush_dcache_page(p) #define MAX_ERRNO 4095 diff --git a/tools/testing/selftests/.gitignore b/tools/testing/selftests/.gitignore index 055a5019b13c..cb24124ac5b9 100644 --- a/tools/testing/selftests/.gitignore +++ b/tools/testing/selftests/.gitignore @@ -3,6 +3,7 @@ gpiogpio-event-mon gpiogpio-hammer gpioinclude/ gpiolsgpio +kselftest_install/ tpm2/SpaceTest.log # Python bytecode and cache diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index d08fe4cfe811..2319ec87f53d 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -114,23 +114,35 @@ ifdef building_out_of_srctree override LDFLAGS = endif -ifneq ($(O),) - BUILD := $(O)/kselftest +top_srcdir ?= ../../.. + +ifeq ("$(origin O)", "command line") + KBUILD_OUTPUT := $(O) +endif + +ifneq ($(KBUILD_OUTPUT),) + # Make's built-in functions such as $(abspath ...), $(realpath ...) cannot + # expand a shell special character '~'. We use a somewhat tedious way here. + abs_objtree := $(shell cd $(top_srcdir) && mkdir -p $(KBUILD_OUTPUT) && cd $(KBUILD_OUTPUT) && pwd) + $(if $(abs_objtree),, \ + $(error failed to create output directory "$(KBUILD_OUTPUT)")) + # $(realpath ...) resolves symlinks + abs_objtree := $(realpath $(abs_objtree)) + BUILD := $(abs_objtree)/kselftest + KHDR_INCLUDES := -isystem ${abs_objtree}/usr/include else - ifneq ($(KBUILD_OUTPUT),) - BUILD := $(KBUILD_OUTPUT)/kselftest - else - BUILD := $(shell pwd) - DEFAULT_INSTALL_HDR_PATH := 1 - endif + BUILD := $(CURDIR) + abs_srctree := $(shell cd $(top_srcdir) && pwd) + KHDR_INCLUDES := -isystem ${abs_srctree}/usr/include + DEFAULT_INSTALL_HDR_PATH := 1 endif # Prepare for headers install -top_srcdir ?= ../../.. include $(top_srcdir)/scripts/subarch.include ARCH ?= $(SUBARCH) export KSFT_KHDR_INSTALL_DONE := 1 export BUILD +export KHDR_INCLUDES # set default goal to all, so make without a target runs all, even when # all isn't the first target in the file. @@ -155,7 +167,7 @@ khdr: ifeq (1,$(DEFAULT_INSTALL_HDR_PATH)) $(MAKE) --no-builtin-rules ARCH=$(ARCH) -C $(top_srcdir) headers_install else - $(MAKE) --no-builtin-rules INSTALL_HDR_PATH=$$BUILD/usr \ + $(MAKE) --no-builtin-rules INSTALL_HDR_PATH=$(abs_objtree)/usr \ ARCH=$(ARCH) -C $(top_srcdir) headers_install endif @@ -165,6 +177,7 @@ all: khdr BUILD_TARGET=$$BUILD/$$TARGET; \ mkdir $$BUILD_TARGET -p; \ $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET \ + O=$(abs_objtree) \ $(if $(FORCE_TARGETS),|| exit); \ ret=$$((ret * $$?)); \ done; exit $$ret; @@ -172,7 +185,8 @@ all: khdr run_tests: all @for TARGET in $(TARGETS); do \ BUILD_TARGET=$$BUILD/$$TARGET; \ - $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET run_tests;\ + $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET run_tests \ + O=$(abs_objtree); \ done; hotplug: @@ -223,6 +237,7 @@ ifdef INSTALL_PATH for TARGET in $(TARGETS); do \ BUILD_TARGET=$$BUILD/$$TARGET; \ $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET INSTALL_PATH=$(INSTALL_PATH)/$$TARGET install \ + O=$(abs_objtree) \ $(if $(FORCE_TARGETS),|| exit); \ ret=$$((ret * $$?)); \ done; exit $$ret; diff --git a/tools/testing/selftests/alsa/mixer-test.c b/tools/testing/selftests/alsa/mixer-test.c index 17f158d7a767..eb2213540fe3 100644 --- a/tools/testing/selftests/alsa/mixer-test.c +++ b/tools/testing/selftests/alsa/mixer-test.c @@ -3,7 +3,7 @@ // kselftest for the ALSA mixer API // // Original author: Mark Brown <broonie@kernel.org> -// Copyright (c) 2021 Arm Limited +// Copyright (c) 2021-2 Arm Limited // This test will iterate over all cards detected in the system, exercising // every mixer control it can find. This may conflict with other system @@ -13,6 +13,7 @@ #include <stdio.h> #include <stdlib.h> #include <stdbool.h> +#include <limits.h> #include <string.h> #include <getopt.h> #include <stdarg.h> @@ -26,11 +27,12 @@ #include "../kselftest.h" -#define TESTS_PER_CONTROL 3 +#define TESTS_PER_CONTROL 6 struct card_data { snd_ctl_t *handle; int card; + struct pollfd pollfd; int num_ctls; snd_ctl_elem_list_t *ctls; struct card_data *next; @@ -42,6 +44,8 @@ struct ctl_data { snd_ctl_elem_info_t *info; snd_ctl_elem_value_t *def_val; int elem; + int event_missing; + int event_spurious; struct card_data *card; struct ctl_data *next; }; @@ -67,7 +71,8 @@ struct ctl_data *ctl_list = NULL; #endif #ifndef LIB_HAS_LOAD_STRING -int snd_config_load_string(snd_config_t **config, const char *s, size_t size) +static int snd_config_load_string(snd_config_t **config, const char *s, + size_t size) { snd_input_t *input; snd_config_t *dst; @@ -95,7 +100,7 @@ int snd_config_load_string(snd_config_t **config, const char *s, size_t size) } #endif -void find_controls(void) +static void find_controls(void) { char name[32]; int card, ctl, err; @@ -148,6 +153,7 @@ void find_controls(void) if (!ctl_data) ksft_exit_fail_msg("Out of memory\n"); + memset(ctl_data, 0, sizeof(*ctl_data)); ctl_data->card = card_data; ctl_data->elem = ctl; ctl_data->name = snd_ctl_elem_list_get_name(card_data->ctls, @@ -183,6 +189,26 @@ void find_controls(void) ctl_list = ctl_data; } + /* Set up for events */ + err = snd_ctl_subscribe_events(card_data->handle, true); + if (err < 0) { + ksft_exit_fail_msg("snd_ctl_subscribe_events() failed for card %d: %d\n", + card, err); + } + + err = snd_ctl_poll_descriptors_count(card_data->handle); + if (err != 1) { + ksft_exit_fail_msg("Unexpected descriptor count %d for card %d\n", + err, card); + } + + err = snd_ctl_poll_descriptors(card_data->handle, + &card_data->pollfd, 1); + if (err != 1) { + ksft_exit_fail_msg("snd_ctl_poll_descriptors() failed for %d\n", + card, err); + } + next_card: if (snd_card_next(&card) < 0) { ksft_print_msg("snd_card_next"); @@ -193,8 +219,82 @@ void find_controls(void) snd_config_delete(config); } -bool ctl_value_index_valid(struct ctl_data *ctl, snd_ctl_elem_value_t *val, - int index) +/* + * Block for up to timeout ms for an event, returns a negative value + * on error, 0 for no event and 1 for an event. + */ +static int wait_for_event(struct ctl_data *ctl, int timeout) +{ + unsigned short revents; + snd_ctl_event_t *event; + int count, err; + unsigned int mask = 0; + unsigned int ev_id; + + snd_ctl_event_alloca(&event); + + do { + err = poll(&(ctl->card->pollfd), 1, timeout); + if (err < 0) { + ksft_print_msg("poll() failed for %s: %s (%d)\n", + ctl->name, strerror(errno), errno); + return -1; + } + /* Timeout */ + if (err == 0) + return 0; + + err = snd_ctl_poll_descriptors_revents(ctl->card->handle, + &(ctl->card->pollfd), + 1, &revents); + if (err < 0) { + ksft_print_msg("snd_ctl_poll_descriptors_revents() failed for %s: %d\n", + ctl->name, err); + return err; + } + if (revents & POLLERR) { + ksft_print_msg("snd_ctl_poll_descriptors_revents() reported POLLERR for %s\n", + ctl->name); + return -1; + } + /* No read events */ + if (!(revents & POLLIN)) { + ksft_print_msg("No POLLIN\n"); + continue; + } + + err = snd_ctl_read(ctl->card->handle, event); + if (err < 0) { + ksft_print_msg("snd_ctl_read() failed for %s: %d\n", + ctl->name, err); + return err; + } + + if (snd_ctl_event_get_type(event) != SND_CTL_EVENT_ELEM) + continue; + + /* The ID returned from the event is 1 less than numid */ + mask = snd_ctl_event_elem_get_mask(event); + ev_id = snd_ctl_event_elem_get_numid(event); + if (ev_id != snd_ctl_elem_info_get_numid(ctl->info)) { + ksft_print_msg("Event for unexpected ctl %s\n", + snd_ctl_event_elem_get_name(event)); + continue; + } + + if ((mask & SND_CTL_EVENT_MASK_REMOVE) == SND_CTL_EVENT_MASK_REMOVE) { + ksft_print_msg("Removal event for %s\n", + ctl->name); + return -1; + } + } while ((mask & SND_CTL_EVENT_MASK_VALUE) != SND_CTL_EVENT_MASK_VALUE); + + return 1; +} + +static bool ctl_value_index_valid(struct ctl_data *ctl, + snd_ctl_elem_value_t *val, + int index) { long int_val; long long int64_val; @@ -305,7 +405,7 @@ bool ctl_value_index_valid(struct ctl_data *ctl, snd_ctl_elem_value_t *val, * Check that the provided value meets the constraints for the * provided control. */ -bool ctl_value_valid(struct ctl_data *ctl, snd_ctl_elem_value_t *val) +static bool ctl_value_valid(struct ctl_data *ctl, snd_ctl_elem_value_t *val) { int i; bool valid = true; @@ -321,7 +421,7 @@ bool ctl_value_valid(struct ctl_data *ctl, snd_ctl_elem_value_t *val) * Check that we can read the default value and it is valid. Write * tests use the read value to restore the default. */ -void test_ctl_get_value(struct ctl_data *ctl) +static void test_ctl_get_value(struct ctl_data *ctl) { int err; @@ -356,9 +456,9 @@ out: ctl->card->card, ctl->elem); } -bool show_mismatch(struct ctl_data *ctl, int index, - snd_ctl_elem_value_t *read_val, - snd_ctl_elem_value_t *expected_val) +static bool show_mismatch(struct ctl_data *ctl, int index, + snd_ctl_elem_value_t *read_val, + snd_ctl_elem_value_t *expected_val) { long long expected_int, read_int; @@ -421,13 +521,14 @@ bool show_mismatch(struct ctl_data *ctl, int index, * the write to fail, for verifying that invalid writes don't corrupt * anything. */ -int write_and_verify(struct ctl_data *ctl, - snd_ctl_elem_value_t *write_val, - snd_ctl_elem_value_t *expected_val) +static int write_and_verify(struct ctl_data *ctl, + snd_ctl_elem_value_t *write_val, + snd_ctl_elem_value_t *expected_val) { int err, i; bool error_expected, mismatch_shown; - snd_ctl_elem_value_t *read_val, *w_val; + snd_ctl_elem_value_t *initial_val, *read_val, *w_val; + snd_ctl_elem_value_alloca(&initial_val); snd_ctl_elem_value_alloca(&read_val); snd_ctl_elem_value_alloca(&w_val); @@ -445,6 +546,18 @@ int write_and_verify(struct ctl_data *ctl, snd_ctl_elem_value_copy(expected_val, write_val); } + /* Store the value before we write */ + if (snd_ctl_elem_info_is_readable(ctl->info)) { + snd_ctl_elem_value_set_id(initial_val, ctl->id); + + err = snd_ctl_elem_read(ctl->card->handle, initial_val); + if (err < 0) { + ksft_print_msg("snd_ctl_elem_read() failed: %s\n", + snd_strerror(err)); + return err; + } + } + /* * Do the write, if we have an expected value ignore the error * and carry on to validate the expected value. @@ -470,6 +583,30 @@ int write_and_verify(struct ctl_data *ctl, } /* + * Check for an event if the value changed, or confirm that + * there was none if it didn't. We rely on the kernel + * generating the notification before it returns from the + * write, this is currently true, should that ever change this + * will most likely break and need updating. + */ + if (!snd_ctl_elem_info_is_volatile(ctl->info)) { + err = wait_for_event(ctl, 0); + if (snd_ctl_elem_value_compare(initial_val, read_val)) { + if (err < 1) { + ksft_print_msg("No event generated for %s\n", + ctl->name); + ctl->event_missing++; + } + } else { + if (err != 0) { + ksft_print_msg("Spurious event generated for %s\n", + ctl->name); + ctl->event_spurious++; + } + } + } + + /* * Use the libray to compare values, if there's a mismatch * carry on and try to provide a more useful diagnostic than * just "mismatch". @@ -493,7 +630,7 @@ int write_and_verify(struct ctl_data *ctl, * Make sure we can write the default value back to the control, this * should validate that at least some write works. */ -void test_ctl_write_default(struct ctl_data *ctl) +static void test_ctl_write_default(struct ctl_data *ctl) { int err; @@ -526,7 +663,7 @@ void test_ctl_write_default(struct ctl_data *ctl) ctl->card->card, ctl->elem); } -bool test_ctl_write_valid_boolean(struct ctl_data *ctl) +static bool test_ctl_write_valid_boolean(struct ctl_data *ctl) { int err, i, j; bool fail = false; @@ -547,7 +684,7 @@ bool test_ctl_write_valid_boolean(struct ctl_data *ctl) return !fail; } -bool test_ctl_write_valid_integer(struct ctl_data *ctl) +static bool test_ctl_write_valid_integer(struct ctl_data *ctl) { int err; int i; @@ -577,7 +714,7 @@ bool test_ctl_write_valid_integer(struct ctl_data *ctl) return !fail; } -bool test_ctl_write_valid_integer64(struct ctl_data *ctl) +static bool test_ctl_write_valid_integer64(struct ctl_data *ctl) { int err, i; long long j, step; @@ -605,7 +742,7 @@ bool test_ctl_write_valid_integer64(struct ctl_data *ctl) return !fail; } -bool test_ctl_write_valid_enumerated(struct ctl_data *ctl) +static bool test_ctl_write_valid_enumerated(struct ctl_data *ctl) { int err, i, j; bool fail = false; @@ -626,7 +763,7 @@ bool test_ctl_write_valid_enumerated(struct ctl_data *ctl) return !fail; } -void test_ctl_write_valid(struct ctl_data *ctl) +static void test_ctl_write_valid(struct ctl_data *ctl) { bool pass; int err; @@ -679,6 +816,236 @@ void test_ctl_write_valid(struct ctl_data *ctl) ctl->card->card, ctl->elem); } +static bool test_ctl_write_invalid_value(struct ctl_data *ctl, + snd_ctl_elem_value_t *val) +{ + int err; + long val_read; + + /* Ideally this will fail... */ + err = snd_ctl_elem_write(ctl->card->handle, val); + if (err < 0) + return false; + + /* ...but some devices will clamp to an in range value */ + err = snd_ctl_elem_read(ctl->card->handle, val); + if (err < 0) { + ksft_print_msg("%s failed to read: %s\n", + ctl->name, snd_strerror(err)); + return true; + } + + return !ctl_value_valid(ctl, val); +} + +static bool test_ctl_write_invalid_boolean(struct ctl_data *ctl) +{ + int err, i; + long val_read; + bool fail = false; + snd_ctl_elem_value_t *val; + snd_ctl_elem_value_alloca(&val); + + for (i = 0; i < snd_ctl_elem_info_get_count(ctl->info); i++) { + snd_ctl_elem_value_copy(val, ctl->def_val); + snd_ctl_elem_value_set_boolean(val, i, 2); + + if (test_ctl_write_invalid_value(ctl, val)) + fail = true; + } + + return !fail; +} + +static bool test_ctl_write_invalid_integer(struct ctl_data *ctl) +{ + int i; + bool fail = false; + snd_ctl_elem_value_t *val; + snd_ctl_elem_value_alloca(&val); + + for (i = 0; i < snd_ctl_elem_info_get_count(ctl->info); i++) { + if (snd_ctl_elem_info_get_min(ctl->info) != LONG_MIN) { + /* Just under range */ + snd_ctl_elem_value_copy(val, ctl->def_val); + snd_ctl_elem_value_set_integer(val, i, + snd_ctl_elem_info_get_min(ctl->info) - 1); + + if (test_ctl_write_invalid_value(ctl, val)) + fail = true; + + /* Minimum representable value */ + snd_ctl_elem_value_copy(val, ctl->def_val); + snd_ctl_elem_value_set_integer(val, i, LONG_MIN); + + if (test_ctl_write_invalid_value(ctl, val)) + fail = true; + } + + if (snd_ctl_elem_info_get_max(ctl->info) != LONG_MAX) { + /* Just over range */ + snd_ctl_elem_value_copy(val, ctl->def_val); + snd_ctl_elem_value_set_integer(val, i, + snd_ctl_elem_info_get_max(ctl->info) + 1); + + if (test_ctl_write_invalid_value(ctl, val)) + fail = true; + + /* Maximum representable value */ + snd_ctl_elem_value_copy(val, ctl->def_val); + snd_ctl_elem_value_set_integer(val, i, LONG_MAX); + + if (test_ctl_write_invalid_value(ctl, val)) + fail = true; + } + } + + return !fail; +} + +static bool test_ctl_write_invalid_integer64(struct ctl_data *ctl) +{ + int i; + bool fail = false; + snd_ctl_elem_value_t *val; + snd_ctl_elem_value_alloca(&val); + + for (i = 0; i < snd_ctl_elem_info_get_count(ctl->info); i++) { + if (snd_ctl_elem_info_get_min64(ctl->info) != LLONG_MIN) { + /* Just under range */ + snd_ctl_elem_value_copy(val, ctl->def_val); + snd_ctl_elem_value_set_integer64(val, i, + snd_ctl_elem_info_get_min64(ctl->info) - 1); + + if (test_ctl_write_invalid_value(ctl, val)) + fail = true; + + /* Minimum representable value */ + snd_ctl_elem_value_copy(val, ctl->def_val); + snd_ctl_elem_value_set_integer64(val, i, LLONG_MIN); + + if (test_ctl_write_invalid_value(ctl, val)) + fail = true; + } + + if (snd_ctl_elem_info_get_max64(ctl->info) != LLONG_MAX) { + /* Just over range */ + snd_ctl_elem_value_copy(val, ctl->def_val); + snd_ctl_elem_value_set_integer64(val, i, + snd_ctl_elem_info_get_max64(ctl->info) + 1); + + if (test_ctl_write_invalid_value(ctl, val)) + fail = true; + + /* Maximum representable value */ + snd_ctl_elem_value_copy(val, ctl->def_val); + snd_ctl_elem_value_set_integer64(val, i, LLONG_MAX); + + if (test_ctl_write_invalid_value(ctl, val)) + fail = true; + } + } + + return !fail; +} + +static bool test_ctl_write_invalid_enumerated(struct ctl_data *ctl) +{ + int err, i; + unsigned int val_read; + bool fail = false; + snd_ctl_elem_value_t *val; + snd_ctl_elem_value_alloca(&val); + + snd_ctl_elem_value_set_id(val, ctl->id); + + for (i = 0; i < snd_ctl_elem_info_get_count(ctl->info); i++) { + /* One beyond maximum */ + snd_ctl_elem_value_copy(val, ctl->def_val); + snd_ctl_elem_value_set_enumerated(val, i, + snd_ctl_elem_info_get_items(ctl->info)); + + if (test_ctl_write_invalid_value(ctl, val)) + fail = true; + + /* Maximum representable value */ + snd_ctl_elem_value_copy(val, ctl->def_val); + snd_ctl_elem_value_set_enumerated(val, i, UINT_MAX); + + if (test_ctl_write_invalid_value(ctl, val)) + fail = true; + + } + + return !fail; +} + + +static void test_ctl_write_invalid(struct ctl_data *ctl) +{ + bool pass; + int err; + + /* If the control is turned off let's be polite */ + if (snd_ctl_elem_info_is_inactive(ctl->info)) { + ksft_print_msg("%s is inactive\n", ctl->name); + ksft_test_result_skip("write_invalid.%d.%d\n", + ctl->card->card, ctl->elem); + return; + } + + if (!snd_ctl_elem_info_is_writable(ctl->info)) { + ksft_print_msg("%s is not writeable\n", ctl->name); + ksft_test_result_skip("write_invalid.%d.%d\n", + ctl->card->card, ctl->elem); + return; + } + + switch (snd_ctl_elem_info_get_type(ctl->info)) { + case SND_CTL_ELEM_TYPE_BOOLEAN: + pass = test_ctl_write_invalid_boolean(ctl); + break; + + case SND_CTL_ELEM_TYPE_INTEGER: + pass = test_ctl_write_invalid_integer(ctl); + break; + + case SND_CTL_ELEM_TYPE_INTEGER64: + pass = test_ctl_write_invalid_integer64(ctl); + break; + + case SND_CTL_ELEM_TYPE_ENUMERATED: + pass = test_ctl_write_invalid_enumerated(ctl); + break; + + default: + /* No tests for this yet */ + ksft_test_result_skip("write_invalid.%d.%d\n", + ctl->card->card, ctl->elem); + return; + } + + /* Restore the default value to minimise disruption */ + err = write_and_verify(ctl, ctl->def_val, NULL); + if (err < 0) + pass = false; + + ksft_test_result(pass, "write_invalid.%d.%d\n", + ctl->card->card, ctl->elem); +} + +static void test_ctl_event_missing(struct ctl_data *ctl) +{ + ksft_test_result(!ctl->event_missing, "event_missing.%d.%d\n", + ctl->card->card, ctl->elem); +} + +static void test_ctl_event_spurious(struct ctl_data *ctl) +{ + ksft_test_result(!ctl->event_spurious, "event_spurious.%d.%d\n", + ctl->card->card, ctl->elem); +} + int main(void) { struct ctl_data *ctl; @@ -697,6 +1064,9 @@ int main(void) test_ctl_get_value(ctl); test_ctl_write_default(ctl); test_ctl_write_valid(ctl); + test_ctl_write_invalid(ctl); + test_ctl_event_missing(ctl); + test_ctl_event_spurious(ctl); } ksft_exit_pass(); diff --git a/tools/testing/selftests/arm64/abi/syscall-abi.c b/tools/testing/selftests/arm64/abi/syscall-abi.c index d8eeeafb50dc..1e13b7523918 100644 --- a/tools/testing/selftests/arm64/abi/syscall-abi.c +++ b/tools/testing/selftests/arm64/abi/syscall-abi.c @@ -18,7 +18,6 @@ #include "../../kselftest.h" -#define ARRAY_SIZE(a) (sizeof(a) / sizeof(a[0])) #define NUM_VL ((SVE_VQ_MAX - SVE_VQ_MIN) + 1) extern void do_syscall(int sve_vl); diff --git a/tools/testing/selftests/arm64/fp/sve-ptrace.c b/tools/testing/selftests/arm64/fp/sve-ptrace.c index af798b9d232c..4c418b2021e0 100644 --- a/tools/testing/selftests/arm64/fp/sve-ptrace.c +++ b/tools/testing/selftests/arm64/fp/sve-ptrace.c @@ -21,8 +21,6 @@ #include "../../kselftest.h" -#define ARRAY_SIZE(a) (sizeof(a) / sizeof(a[0])) - /* <linux/elf.h> and <sys/auxv.h> don't like each other, so: */ #ifndef NT_ARM_SVE #define NT_ARM_SVE 0x405 @@ -261,7 +259,7 @@ static void ptrace_sve_fpsimd(pid_t child, const struct vec_type *type) } ksft_test_result((sve->flags & SVE_PT_REGS_MASK) == SVE_PT_REGS_FPSIMD, - "Set FPSIMD registers via %s\n", type->name); + "Got FPSIMD registers via %s\n", type->name); if ((sve->flags & SVE_PT_REGS_MASK) != SVE_PT_REGS_FPSIMD) goto out; @@ -489,6 +487,8 @@ static int do_parent(pid_t child) unsigned int vq, vl; bool vl_supported; + ksft_print_msg("Parent is %d, child is %d\n", getpid(), child); + /* Attach to the child */ while (1) { int sig; @@ -557,7 +557,14 @@ static int do_parent(pid_t child) } /* prctl() flags */ - ptrace_set_get_inherit(child, &vec_types[i]); + if (getauxval(vec_types[i].hwcap_type) & vec_types[i].hwcap) { + ptrace_set_get_inherit(child, &vec_types[i]); + } else { + ksft_test_result_skip("%s SVE_PT_VL_INHERIT set\n", + vec_types[i].name); + ksft_test_result_skip("%s SVE_PT_VL_INHERIT cleared\n", + vec_types[i].name); + } /* Step through every possible VQ */ for (vq = SVE_VQ_MIN; vq <= SVE_VQ_MAX; vq++) { diff --git a/tools/testing/selftests/arm64/mte/check_gcr_el1_cswitch.c b/tools/testing/selftests/arm64/mte/check_gcr_el1_cswitch.c index a876db1f096a..325bca0de0f6 100644 --- a/tools/testing/selftests/arm64/mte/check_gcr_el1_cswitch.c +++ b/tools/testing/selftests/arm64/mte/check_gcr_el1_cswitch.c @@ -19,17 +19,6 @@ #include "kselftest.h" #include "mte_common_util.h" -#define PR_SET_TAGGED_ADDR_CTRL 55 -#define PR_GET_TAGGED_ADDR_CTRL 56 -# define PR_TAGGED_ADDR_ENABLE (1UL << 0) -# define PR_MTE_TCF_SHIFT 1 -# define PR_MTE_TCF_NONE (0UL << PR_MTE_TCF_SHIFT) -# define PR_MTE_TCF_SYNC (1UL << PR_MTE_TCF_SHIFT) -# define PR_MTE_TCF_ASYNC (2UL << PR_MTE_TCF_SHIFT) -# define PR_MTE_TCF_MASK (3UL << PR_MTE_TCF_SHIFT) -# define PR_MTE_TAG_SHIFT 3 -# define PR_MTE_TAG_MASK (0xffffUL << PR_MTE_TAG_SHIFT) - #include "mte_def.h" #define NUM_ITERATIONS 1024 diff --git a/tools/testing/selftests/arm64/mte/check_user_mem.c b/tools/testing/selftests/arm64/mte/check_user_mem.c index 1de7a0abd0ae..f4ae5f87a3b7 100644 --- a/tools/testing/selftests/arm64/mte/check_user_mem.c +++ b/tools/testing/selftests/arm64/mte/check_user_mem.c @@ -3,6 +3,7 @@ #define _GNU_SOURCE +#include <assert.h> #include <errno.h> #include <fcntl.h> #include <signal.h> @@ -11,6 +12,7 @@ #include <string.h> #include <ucontext.h> #include <unistd.h> +#include <sys/uio.h> #include <sys/mman.h> #include "kselftest.h" @@ -19,14 +21,28 @@ static size_t page_sz; -static int check_usermem_access_fault(int mem_type, int mode, int mapping) +#define TEST_NAME_MAX 100 + +enum test_type { + READ_TEST, + WRITE_TEST, + READV_TEST, + WRITEV_TEST, + LAST_TEST, +}; + +static int check_usermem_access_fault(int mem_type, int mode, int mapping, + int tag_offset, int tag_len, + enum test_type test_type) { int fd, i, err; char val = 'A'; - size_t len, read_len; + ssize_t len, syscall_len; void *ptr, *ptr_next; + int fileoff, ptroff, size; + int sizes[] = {1, 2, 3, 8, 16, 32, 4096, page_sz}; - err = KSFT_FAIL; + err = KSFT_PASS; len = 2 * page_sz; mte_switch_mode(mode, MTE_ALLOW_NON_ZERO_TAG); fd = create_temp_file(); @@ -43,9 +59,9 @@ static int check_usermem_access_fault(int mem_type, int mode, int mapping) } mte_initialize_current_context(mode, (uintptr_t)ptr, len); /* Copy from file into buffer with valid tag */ - read_len = read(fd, ptr, len); + syscall_len = read(fd, ptr, len); mte_wait_after_trig(); - if (cur_mte_cxt.fault_valid || read_len < len) + if (cur_mte_cxt.fault_valid || syscall_len < len) goto usermem_acc_err; /* Verify same pattern is read */ for (i = 0; i < len; i++) @@ -54,36 +70,136 @@ static int check_usermem_access_fault(int mem_type, int mode, int mapping) if (i < len) goto usermem_acc_err; - /* Tag the next half of memory with different value */ - ptr_next = (void *)((unsigned long)ptr + page_sz); + if (!tag_len) + tag_len = len - tag_offset; + /* Tag a part of memory with different value */ + ptr_next = (void *)((unsigned long)ptr + tag_offset); ptr_next = mte_insert_new_tag(ptr_next); - mte_set_tag_address_range(ptr_next, page_sz); + mte_set_tag_address_range(ptr_next, tag_len); - lseek(fd, 0, 0); - /* Copy from file into buffer with invalid tag */ - read_len = read(fd, ptr, len); - mte_wait_after_trig(); - /* - * Accessing user memory in kernel with invalid tag should fail in sync - * mode without fault but may not fail in async mode as per the - * implemented MTE userspace support in Arm64 kernel. - */ - if (mode == MTE_SYNC_ERR && - !cur_mte_cxt.fault_valid && read_len < len) { - err = KSFT_PASS; - } else if (mode == MTE_ASYNC_ERR && - !cur_mte_cxt.fault_valid && read_len == len) { - err = KSFT_PASS; + for (fileoff = 0; fileoff < 16; fileoff++) { + for (ptroff = 0; ptroff < 16; ptroff++) { + for (i = 0; i < ARRAY_SIZE(sizes); i++) { + size = sizes[i]; + lseek(fd, 0, 0); + + /* perform file operation on buffer with invalid tag */ + switch (test_type) { + case READ_TEST: + syscall_len = read(fd, ptr + ptroff, size); + break; + case WRITE_TEST: + syscall_len = write(fd, ptr + ptroff, size); + break; + case READV_TEST: { + struct iovec iov[1]; + iov[0].iov_base = ptr + ptroff; + iov[0].iov_len = size; + syscall_len = readv(fd, iov, 1); + break; + } + case WRITEV_TEST: { + struct iovec iov[1]; + iov[0].iov_base = ptr + ptroff; + iov[0].iov_len = size; + syscall_len = writev(fd, iov, 1); + break; + } + case LAST_TEST: + goto usermem_acc_err; + } + + mte_wait_after_trig(); + /* + * Accessing user memory in kernel with invalid tag should fail in sync + * mode without fault but may not fail in async mode as per the + * implemented MTE userspace support in Arm64 kernel. + */ + if (cur_mte_cxt.fault_valid) { + goto usermem_acc_err; + } + if (mode == MTE_SYNC_ERR && syscall_len < len) { + /* test passed */ + } else if (mode == MTE_ASYNC_ERR && syscall_len == size) { + /* test passed */ + } else { + goto usermem_acc_err; + } + } + } } + + goto exit; + usermem_acc_err: + err = KSFT_FAIL; +exit: mte_free_memory((void *)ptr, len, mem_type, true); close(fd); return err; } +void format_test_name(char* name, int name_len, int type, int sync, int map, int len, int offset) { + const char* test_type; + const char* mte_type; + const char* map_type; + + switch (type) { + case READ_TEST: + test_type = "read"; + break; + case WRITE_TEST: + test_type = "write"; + break; + case READV_TEST: + test_type = "readv"; + break; + case WRITEV_TEST: + test_type = "writev"; + break; + default: + assert(0); + break; + } + + switch (sync) { + case MTE_SYNC_ERR: + mte_type = "MTE_SYNC_ERR"; + break; + case MTE_ASYNC_ERR: + mte_type = "MTE_ASYNC_ERR"; + break; + default: + assert(0); + break; + } + + switch (map) { + case MAP_SHARED: + map_type = "MAP_SHARED"; + break; + case MAP_PRIVATE: + map_type = "MAP_PRIVATE"; + break; + default: + assert(0); + break; + } + + snprintf(name, name_len, + "test type: %s, %s, %s, tag len: %d, tag offset: %d\n", + test_type, mte_type, map_type, len, offset); +} + int main(int argc, char *argv[]) { int err; + int t, s, m, l, o; + int mte_sync[] = {MTE_SYNC_ERR, MTE_ASYNC_ERR}; + int maps[] = {MAP_SHARED, MAP_PRIVATE}; + int tag_lens[] = {0, MT_GRANULE_SIZE}; + int tag_offsets[] = {page_sz, MT_GRANULE_SIZE}; + char test_name[TEST_NAME_MAX]; page_sz = getpagesize(); if (!page_sz) { @@ -98,17 +214,28 @@ int main(int argc, char *argv[]) mte_register_signal(SIGSEGV, mte_default_handler); /* Set test plan */ - ksft_set_plan(4); + ksft_set_plan(64); - evaluate_test(check_usermem_access_fault(USE_MMAP, MTE_SYNC_ERR, MAP_PRIVATE), - "Check memory access from kernel in sync mode, private mapping and mmap memory\n"); - evaluate_test(check_usermem_access_fault(USE_MMAP, MTE_SYNC_ERR, MAP_SHARED), - "Check memory access from kernel in sync mode, shared mapping and mmap memory\n"); - - evaluate_test(check_usermem_access_fault(USE_MMAP, MTE_ASYNC_ERR, MAP_PRIVATE), - "Check memory access from kernel in async mode, private mapping and mmap memory\n"); - evaluate_test(check_usermem_access_fault(USE_MMAP, MTE_ASYNC_ERR, MAP_SHARED), - "Check memory access from kernel in async mode, shared mapping and mmap memory\n"); + for (t = 0; t < LAST_TEST; t++) { + for (s = 0; s < ARRAY_SIZE(mte_sync); s++) { + for (m = 0; m < ARRAY_SIZE(maps); m++) { + for (l = 0; l < ARRAY_SIZE(tag_lens); l++) { + for (o = 0; o < ARRAY_SIZE(tag_offsets); o++) { + int sync = mte_sync[s]; + int map = maps[m]; + int offset = tag_offsets[o]; + int tag_len = tag_lens[l]; + int res = check_usermem_access_fault(USE_MMAP, sync, + map, offset, + tag_len, t); + format_test_name(test_name, TEST_NAME_MAX, + t, sync, map, tag_len, offset); + evaluate_test(res, test_name); + } + } + } + } + } mte_restore_setup(); ksft_print_cnts(); diff --git a/tools/testing/selftests/arm64/signal/test_signals.h b/tools/testing/selftests/arm64/signal/test_signals.h index ebe8694dbef0..f909b70d9e98 100644 --- a/tools/testing/selftests/arm64/signal/test_signals.h +++ b/tools/testing/selftests/arm64/signal/test_signals.h @@ -53,6 +53,7 @@ struct tdescr { char *name; char *descr; unsigned long feats_required; + unsigned long feats_incompatible; /* bitmask of effectively supported feats: populated at run-time */ unsigned long feats_supported; bool initialized; diff --git a/tools/testing/selftests/arm64/signal/test_signals_utils.c b/tools/testing/selftests/arm64/signal/test_signals_utils.c index 2f8c23af3b5e..5743897984b0 100644 --- a/tools/testing/selftests/arm64/signal/test_signals_utils.c +++ b/tools/testing/selftests/arm64/signal/test_signals_utils.c @@ -36,6 +36,8 @@ static inline char *feats_to_string(unsigned long feats) { size_t flen = MAX_FEATS_SZ - 1; + feats_string[0] = '\0'; + for (int i = 0; i < FMAX_END; i++) { if (feats & (1UL << i)) { size_t tlen = strlen(feats_names[i]); @@ -256,7 +258,7 @@ int test_init(struct tdescr *td) td->minsigstksz = MINSIGSTKSZ; fprintf(stderr, "Detected MINSTKSIGSZ:%d\n", td->minsigstksz); - if (td->feats_required) { + if (td->feats_required || td->feats_incompatible) { td->feats_supported = 0; /* * Checking for CPU required features using both the @@ -267,15 +269,29 @@ int test_init(struct tdescr *td) if (getauxval(AT_HWCAP) & HWCAP_SVE) td->feats_supported |= FEAT_SVE; if (feats_ok(td)) { - fprintf(stderr, - "Required Features: [%s] supported\n", - feats_to_string(td->feats_required & - td->feats_supported)); + if (td->feats_required & td->feats_supported) + fprintf(stderr, + "Required Features: [%s] supported\n", + feats_to_string(td->feats_required & + td->feats_supported)); + if (!(td->feats_incompatible & td->feats_supported)) + fprintf(stderr, + "Incompatible Features: [%s] absent\n", + feats_to_string(td->feats_incompatible)); } else { - fprintf(stderr, - "Required Features: [%s] NOT supported\n", - feats_to_string(td->feats_required & - ~td->feats_supported)); + if ((td->feats_required & td->feats_supported) != + td->feats_supported) + fprintf(stderr, + "Required Features: [%s] NOT supported\n", + feats_to_string(td->feats_required & + ~td->feats_supported)); + if (td->feats_incompatible & td->feats_supported) + fprintf(stderr, + "Incompatible Features: [%s] supported\n", + feats_to_string(td->feats_incompatible & + ~td->feats_supported)); + + td->result = KSFT_SKIP; return 0; } diff --git a/tools/testing/selftests/arm64/signal/test_signals_utils.h b/tools/testing/selftests/arm64/signal/test_signals_utils.h index 6772b5c8d274..f3aa99ba67bb 100644 --- a/tools/testing/selftests/arm64/signal/test_signals_utils.h +++ b/tools/testing/selftests/arm64/signal/test_signals_utils.h @@ -18,6 +18,8 @@ void test_result(struct tdescr *td); static inline bool feats_ok(struct tdescr *td) { + if (td->feats_incompatible & td->feats_supported) + return false; return (td->feats_required & td->feats_supported) == td->feats_required; } diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore index 1dad8d617da8..595565eb68c0 100644 --- a/tools/testing/selftests/bpf/.gitignore +++ b/tools/testing/selftests/bpf/.gitignore @@ -1,4 +1,5 @@ # SPDX-License-Identifier: GPL-2.0-only +bpftool bpf-helpers* bpf-syscall* test_verifier @@ -30,6 +31,7 @@ test_tcp_check_syncookie_user test_sysctl xdping test_cpp +*.subskel.h *.skel.h *.lskel.h /no_alu32 diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 42ffc24e9e71..3820608faf57 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -21,11 +21,11 @@ endif BPF_GCC ?= $(shell command -v bpf-gcc;) SAN_CFLAGS ?= -CFLAGS += -g -O0 -rdynamic -Wall $(GENFLAGS) $(SAN_CFLAGS) \ +CFLAGS += -g -O0 -rdynamic -Wall -Werror $(GENFLAGS) $(SAN_CFLAGS) \ -I$(CURDIR) -I$(INCLUDE_DIR) -I$(GENDIR) -I$(LIBDIR) \ -I$(TOOLSINCDIR) -I$(APIDIR) -I$(OUTPUT) LDFLAGS += $(SAN_CFLAGS) -LDLIBS += -lcap -lelf -lz -lrt -lpthread +LDLIBS += -lelf -lz -lrt -lpthread # Silence some warnings when compiled with clang ifneq ($(LLVM),) @@ -195,6 +195,7 @@ $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED): $(BPFOBJ) CGROUP_HELPERS := $(OUTPUT)/cgroup_helpers.o TESTING_HELPERS := $(OUTPUT)/testing_helpers.o TRACE_HELPERS := $(OUTPUT)/trace_helpers.o +CAP_HELPERS := $(OUTPUT)/cap_helpers.o $(OUTPUT)/test_dev_cgroup: $(CGROUP_HELPERS) $(TESTING_HELPERS) $(OUTPUT)/test_skb_cgroup_id_user: $(CGROUP_HELPERS) $(TESTING_HELPERS) @@ -211,7 +212,7 @@ $(OUTPUT)/test_lirc_mode2_user: $(TESTING_HELPERS) $(OUTPUT)/xdping: $(TESTING_HELPERS) $(OUTPUT)/flow_dissector_load: $(TESTING_HELPERS) $(OUTPUT)/test_maps: $(TESTING_HELPERS) -$(OUTPUT)/test_verifier: $(TESTING_HELPERS) +$(OUTPUT)/test_verifier: $(TESTING_HELPERS) $(CAP_HELPERS) BPFTOOL ?= $(DEFAULT_BPFTOOL) $(DEFAULT_BPFTOOL): $(wildcard $(BPFTOOLDIR)/*.[ch] $(BPFTOOLDIR)/Makefile) \ @@ -292,7 +293,7 @@ IS_LITTLE_ENDIAN = $(shell $(CC) -dM -E - </dev/null | \ MENDIAN=$(if $(IS_LITTLE_ENDIAN),-mlittle-endian,-mbig-endian) CLANG_SYS_INCLUDES = $(call get_sys_includes,$(CLANG)) -BPF_CFLAGS = -g -D__TARGET_ARCH_$(SRCARCH) $(MENDIAN) \ +BPF_CFLAGS = -g -Werror -D__TARGET_ARCH_$(SRCARCH) $(MENDIAN) \ -I$(INCLUDE_DIR) -I$(CURDIR) -I$(APIDIR) \ -I$(abspath $(OUTPUT)/../usr/include) @@ -326,11 +327,17 @@ endef SKEL_BLACKLIST := btf__% test_pinning_invalid.c test_sk_assign.c LINKED_SKELS := test_static_linked.skel.h linked_funcs.skel.h \ - linked_vars.skel.h linked_maps.skel.h + linked_vars.skel.h linked_maps.skel.h \ + test_subskeleton.skel.h test_subskeleton_lib.skel.h + +# In the subskeleton case, we want the test_subskeleton_lib.subskel.h file +# but that's created as a side-effect of the skel.h generation. +test_subskeleton.skel.h-deps := test_subskeleton_lib2.o test_subskeleton_lib.o test_subskeleton.o +test_subskeleton_lib.skel.h-deps := test_subskeleton_lib2.o test_subskeleton_lib.o LSKELS := kfunc_call_test.c fentry_test.c fexit_test.c fexit_sleep.c \ test_ringbuf.c atomics.c trace_printk.c trace_vprintk.c \ - map_ptr_kern.c core_kern.c + map_ptr_kern.c core_kern.c core_kern_overflow.c # Generate both light skeleton and libbpf skeleton for these LSKELS_EXTRA := test_ksyms_module.c test_ksyms_weak.c kfunc_call_test_subprog.c SKEL_BLACKLIST += $$(LSKELS) @@ -404,6 +411,7 @@ $(TRUNNER_BPF_SKELS): %.skel.h: %.o $(BPFTOOL) | $(TRUNNER_OUTPUT) $(Q)$$(BPFTOOL) gen object $$(<:.o=.linked3.o) $$(<:.o=.linked2.o) $(Q)diff $$(<:.o=.linked2.o) $$(<:.o=.linked3.o) $(Q)$$(BPFTOOL) gen skeleton $$(<:.o=.linked3.o) name $$(notdir $$(<:.o=)) > $$@ + $(Q)$$(BPFTOOL) gen subskeleton $$(<:.o=.linked3.o) name $$(notdir $$(<:.o=)) > $$(@:.skel.h=.subskel.h) $(TRUNNER_BPF_LSKELS): %.lskel.h: %.o $(BPFTOOL) | $(TRUNNER_OUTPUT) $$(call msg,GEN-SKEL,$(TRUNNER_BINARY),$$@) @@ -421,6 +429,7 @@ $(TRUNNER_BPF_SKELS_LINKED): $(TRUNNER_BPF_OBJS) $(BPFTOOL) | $(TRUNNER_OUTPUT) $(Q)diff $$(@:.skel.h=.linked2.o) $$(@:.skel.h=.linked3.o) $$(call msg,GEN-SKEL,$(TRUNNER_BINARY),$$@) $(Q)$$(BPFTOOL) gen skeleton $$(@:.skel.h=.linked3.o) name $$(notdir $$(@:.skel.h=)) > $$@ + $(Q)$$(BPFTOOL) gen subskeleton $$(@:.skel.h=.linked3.o) name $$(notdir $$(@:.skel.h=)) > $$(@:.skel.h=.subskel.h) endif # ensure we set up tests.h header generation rule just once @@ -470,6 +479,7 @@ $(OUTPUT)/$(TRUNNER_BINARY): $(TRUNNER_TEST_OBJS) \ $$(call msg,BINARY,,$$@) $(Q)$$(CC) $$(CFLAGS) $$(filter %.a %.o,$$^) $$(LDLIBS) -o $$@ $(Q)$(RESOLVE_BTFIDS) --btf $(TRUNNER_OUTPUT)/btf_data.o $$@ + $(Q)ln -sf $(if $2,..,.)/tools/build/bpftool/bootstrap/bpftool $(if $2,$2/)bpftool endef @@ -478,7 +488,8 @@ TRUNNER_TESTS_DIR := prog_tests TRUNNER_BPF_PROGS_DIR := progs TRUNNER_EXTRA_SOURCES := test_progs.c cgroup_helpers.c trace_helpers.c \ network_helpers.c testing_helpers.c \ - btf_helpers.c flow_dissector_load.h + btf_helpers.c flow_dissector_load.h \ + cap_helpers.c TRUNNER_EXTRA_FILES := $(OUTPUT)/urandom_read $(OUTPUT)/bpf_testmod.ko \ ima_setup.sh \ $(wildcard progs/btf_dump_test_case_*.c) @@ -555,7 +566,7 @@ $(OUTPUT)/bench: $(OUTPUT)/bench.o \ EXTRA_CLEAN := $(TEST_CUSTOM_PROGS) $(SCRATCH_DIR) $(HOST_SCRATCH_DIR) \ prog_tests/tests.h map_tests/tests.h verifier/tests.h \ - feature \ - $(addprefix $(OUTPUT)/,*.o *.skel.h *.lskel.h no_alu32 bpf_gcc bpf_testmod.ko) + feature bpftool \ + $(addprefix $(OUTPUT)/,*.o *.skel.h *.lskel.h *.subskel.h no_alu32 bpf_gcc bpf_testmod.ko) .PHONY: docs docs-clean diff --git a/tools/testing/selftests/bpf/README.rst b/tools/testing/selftests/bpf/README.rst index 42ef250c7acc..eb1b7541f39d 100644 --- a/tools/testing/selftests/bpf/README.rst +++ b/tools/testing/selftests/bpf/README.rst @@ -32,11 +32,19 @@ For more information on about using the script, run: $ tools/testing/selftests/bpf/vmtest.sh -h +In case of linker errors when running selftests, try using static linking: + +.. code-block:: console + + $ LDLIBS=-static vmtest.sh + +.. note:: Some distros may not support static linking. + .. note:: The script uses pahole and clang based on host environment setting. If you want to change pahole and llvm, you can change `PATH` environment variable in the beginning of script. -.. note:: The script currently only supports x86_64. +.. note:: The script currently only supports x86_64 and s390x architectures. Additional information about selftest failures are documented here. @@ -206,6 +214,8 @@ btf_tag test and Clang version The btf_tag selftest requires LLVM support to recognize the btf_decl_tag and btf_type_tag attributes. They are introduced in `Clang 14` [0_, 1_]. +The subtests ``btf_type_tag_user_{mod1, mod2, vmlinux}`` also requires +pahole version ``1.23``. Without them, the btf_tag selftest will be skipped and you will observe: diff --git a/tools/testing/selftests/bpf/benchs/bench_ringbufs.c b/tools/testing/selftests/bpf/benchs/bench_ringbufs.c index da8593b3494a..c2554f9695ff 100644 --- a/tools/testing/selftests/bpf/benchs/bench_ringbufs.c +++ b/tools/testing/selftests/bpf/benchs/bench_ringbufs.c @@ -151,7 +151,7 @@ static struct ringbuf_bench *ringbuf_setup_skeleton(void) /* record data + header take 16 bytes */ skel->rodata->wakeup_data_size = args.sample_rate * 16; - bpf_map__resize(skel->maps.ringbuf, args.ringbuf_sz); + bpf_map__set_max_entries(skel->maps.ringbuf, args.ringbuf_sz); if (ringbuf_bench__load(skel)) { fprintf(stderr, "failed to load skeleton\n"); diff --git a/tools/testing/selftests/bpf/benchs/bench_trigger.c b/tools/testing/selftests/bpf/benchs/bench_trigger.c index 7f957c55a3ca..0c481de2833d 100644 --- a/tools/testing/selftests/bpf/benchs/bench_trigger.c +++ b/tools/testing/selftests/bpf/benchs/bench_trigger.c @@ -154,7 +154,6 @@ static void *uprobe_producer_without_nop(void *input) static void usetup(bool use_retprobe, bool use_nop) { size_t uprobe_offset; - ssize_t base_addr; struct bpf_link *link; setup_libbpf(); @@ -165,11 +164,10 @@ static void usetup(bool use_retprobe, bool use_nop) exit(1); } - base_addr = get_base_addr(); if (use_nop) - uprobe_offset = get_uprobe_offset(&uprobe_target_with_nop, base_addr); + uprobe_offset = get_uprobe_offset(&uprobe_target_with_nop); else - uprobe_offset = get_uprobe_offset(&uprobe_target_without_nop, base_addr); + uprobe_offset = get_uprobe_offset(&uprobe_target_without_nop); link = bpf_program__attach_uprobe(ctx.skel->progs.bench_trigger_uprobe, use_retprobe, diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c index df3b292a8ffe..e585e1cefc77 100644 --- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c +++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c @@ -13,6 +13,10 @@ #define CREATE_TRACE_POINTS #include "bpf_testmod-events.h" +typedef int (*func_proto_typedef)(long); +typedef int (*func_proto_typedef_nested1)(func_proto_typedef); +typedef int (*func_proto_typedef_nested2)(func_proto_typedef_nested1); + DEFINE_PER_CPU(int, bpf_testmod_ksym_percpu) = 123; noinline void @@ -21,6 +25,41 @@ bpf_testmod_test_mod_kfunc(int i) *(int *)this_cpu_ptr(&bpf_testmod_ksym_percpu) = i; } +struct bpf_testmod_btf_type_tag_1 { + int a; +}; + +struct bpf_testmod_btf_type_tag_2 { + struct bpf_testmod_btf_type_tag_1 __user *p; +}; + +struct bpf_testmod_btf_type_tag_3 { + struct bpf_testmod_btf_type_tag_1 __percpu *p; +}; + +noinline int +bpf_testmod_test_btf_type_tag_user_1(struct bpf_testmod_btf_type_tag_1 __user *arg) { + BTF_TYPE_EMIT(func_proto_typedef); + BTF_TYPE_EMIT(func_proto_typedef_nested1); + BTF_TYPE_EMIT(func_proto_typedef_nested2); + return arg->a; +} + +noinline int +bpf_testmod_test_btf_type_tag_user_2(struct bpf_testmod_btf_type_tag_2 *arg) { + return arg->p->a; +} + +noinline int +bpf_testmod_test_btf_type_tag_percpu_1(struct bpf_testmod_btf_type_tag_1 __percpu *arg) { + return arg->a; +} + +noinline int +bpf_testmod_test_btf_type_tag_percpu_2(struct bpf_testmod_btf_type_tag_3 *arg) { + return arg->p->a; +} + noinline int bpf_testmod_loop_test(int n) { int i, sum = 0; @@ -109,26 +148,31 @@ static struct bin_attribute bin_attr_bpf_testmod_file __ro_after_init = { .write = bpf_testmod_test_write, }; -BTF_SET_START(bpf_testmod_kfunc_ids) +BTF_SET_START(bpf_testmod_check_kfunc_ids) BTF_ID(func, bpf_testmod_test_mod_kfunc) -BTF_SET_END(bpf_testmod_kfunc_ids) +BTF_SET_END(bpf_testmod_check_kfunc_ids) + +static const struct btf_kfunc_id_set bpf_testmod_kfunc_set = { + .owner = THIS_MODULE, + .check_set = &bpf_testmod_check_kfunc_ids, +}; -static DEFINE_KFUNC_BTF_ID_SET(&bpf_testmod_kfunc_ids, bpf_testmod_kfunc_btf_set); +extern int bpf_fentry_test1(int a); static int bpf_testmod_init(void) { int ret; - ret = sysfs_create_bin_file(kernel_kobj, &bin_attr_bpf_testmod_file); - if (ret) + ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS, &bpf_testmod_kfunc_set); + if (ret < 0) return ret; - register_kfunc_btf_id_set(&prog_test_kfunc_list, &bpf_testmod_kfunc_btf_set); - return 0; + if (bpf_fentry_test1(0) < 0) + return -EINVAL; + return sysfs_create_bin_file(kernel_kobj, &bin_attr_bpf_testmod_file); } static void bpf_testmod_exit(void) { - unregister_kfunc_btf_id_set(&prog_test_kfunc_list, &bpf_testmod_kfunc_btf_set); return sysfs_remove_bin_file(kernel_kobj, &bin_attr_bpf_testmod_file); } diff --git a/tools/testing/selftests/bpf/cap_helpers.c b/tools/testing/selftests/bpf/cap_helpers.c new file mode 100644 index 000000000000..d5ac507401d7 --- /dev/null +++ b/tools/testing/selftests/bpf/cap_helpers.c @@ -0,0 +1,67 @@ +// SPDX-License-Identifier: GPL-2.0 +#include "cap_helpers.h" + +/* Avoid including <sys/capability.h> from the libcap-devel package, + * so directly declare them here and use them from glibc. + */ +int capget(cap_user_header_t header, cap_user_data_t data); +int capset(cap_user_header_t header, const cap_user_data_t data); + +int cap_enable_effective(__u64 caps, __u64 *old_caps) +{ + struct __user_cap_data_struct data[_LINUX_CAPABILITY_U32S_3]; + struct __user_cap_header_struct hdr = { + .version = _LINUX_CAPABILITY_VERSION_3, + }; + __u32 cap0 = caps; + __u32 cap1 = caps >> 32; + int err; + + err = capget(&hdr, data); + if (err) + return err; + + if (old_caps) + *old_caps = (__u64)(data[1].effective) << 32 | data[0].effective; + + if ((data[0].effective & cap0) == cap0 && + (data[1].effective & cap1) == cap1) + return 0; + + data[0].effective |= cap0; + data[1].effective |= cap1; + err = capset(&hdr, data); + if (err) + return err; + + return 0; +} + +int cap_disable_effective(__u64 caps, __u64 *old_caps) +{ + struct __user_cap_data_struct data[_LINUX_CAPABILITY_U32S_3]; + struct __user_cap_header_struct hdr = { + .version = _LINUX_CAPABILITY_VERSION_3, + }; + __u32 cap0 = caps; + __u32 cap1 = caps >> 32; + int err; + + err = capget(&hdr, data); + if (err) + return err; + + if (old_caps) + *old_caps = (__u64)(data[1].effective) << 32 | data[0].effective; + + if (!(data[0].effective & cap0) && !(data[1].effective & cap1)) + return 0; + + data[0].effective &= ~cap0; + data[1].effective &= ~cap1; + err = capset(&hdr, data); + if (err) + return err; + + return 0; +} diff --git a/tools/testing/selftests/bpf/cap_helpers.h b/tools/testing/selftests/bpf/cap_helpers.h new file mode 100644 index 000000000000..6d163530cb0f --- /dev/null +++ b/tools/testing/selftests/bpf/cap_helpers.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __CAP_HELPERS_H +#define __CAP_HELPERS_H + +#include <linux/types.h> +#include <linux/capability.h> + +#ifndef CAP_PERFMON +#define CAP_PERFMON 38 +#endif + +#ifndef CAP_BPF +#define CAP_BPF 39 +#endif + +int cap_enable_effective(__u64 caps, __u64 *old_caps); +int cap_disable_effective(__u64 caps, __u64 *old_caps); + +#endif diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config index f6287132fa89..763db63a3890 100644 --- a/tools/testing/selftests/bpf/config +++ b/tools/testing/selftests/bpf/config @@ -48,3 +48,8 @@ CONFIG_IMA_READ_POLICY=y CONFIG_BLK_DEV_LOOP=y CONFIG_FUNCTION_TRACER=y CONFIG_DYNAMIC_FTRACE=y +CONFIG_NETFILTER=y +CONFIG_NF_DEFRAG_IPV4=y +CONFIG_NF_DEFRAG_IPV6=y +CONFIG_NF_CONNTRACK=y +CONFIG_USERFAULTFD=y diff --git a/tools/testing/selftests/bpf/ima_setup.sh b/tools/testing/selftests/bpf/ima_setup.sh index 8e62581113a3..8ecead4ccad0 100755 --- a/tools/testing/selftests/bpf/ima_setup.sh +++ b/tools/testing/selftests/bpf/ima_setup.sh @@ -12,7 +12,7 @@ LOG_FILE="$(mktemp /tmp/ima_setup.XXXX.log)" usage() { - echo "Usage: $0 <setup|cleanup|run> <existing_tmp_dir>" + echo "Usage: $0 <setup|cleanup|run|modify-bin|restore-bin|load-policy> <existing_tmp_dir>" exit 1 } @@ -51,6 +51,7 @@ setup() ensure_mount_securityfs echo "measure func=BPRM_CHECK fsuuid=${mount_uuid}" > ${IMA_POLICY_FILE} + echo "measure func=BPRM_CHECK fsuuid=${mount_uuid}" > ${mount_dir}/policy_test } cleanup() { @@ -77,6 +78,32 @@ run() exec "${copied_bin_path}" } +modify_bin() +{ + local tmp_dir="$1" + local mount_dir="${tmp_dir}/mnt" + local copied_bin_path="${mount_dir}/$(basename ${TEST_BINARY})" + + echo "mod" >> "${copied_bin_path}" +} + +restore_bin() +{ + local tmp_dir="$1" + local mount_dir="${tmp_dir}/mnt" + local copied_bin_path="${mount_dir}/$(basename ${TEST_BINARY})" + + truncate -s -4 "${copied_bin_path}" +} + +load_policy() +{ + local tmp_dir="$1" + local mount_dir="${tmp_dir}/mnt" + + echo ${mount_dir}/policy_test > ${IMA_POLICY_FILE} 2> /dev/null +} + catch() { local exit_code="$1" @@ -105,6 +132,12 @@ main() cleanup "${tmp_dir}" elif [[ "${action}" == "run" ]]; then run "${tmp_dir}" + elif [[ "${action}" == "modify-bin" ]]; then + modify_bin "${tmp_dir}" + elif [[ "${action}" == "restore-bin" ]]; then + restore_bin "${tmp_dir}" + elif [[ "${action}" == "load-policy" ]]; then + load_policy "${tmp_dir}" else echo "Unknown action: ${action}" exit 1 diff --git a/tools/testing/selftests/bpf/network_helpers.c b/tools/testing/selftests/bpf/network_helpers.c index 6db1af8fdee7..2bb1f9b3841d 100644 --- a/tools/testing/selftests/bpf/network_helpers.c +++ b/tools/testing/selftests/bpf/network_helpers.c @@ -1,18 +1,25 @@ // SPDX-License-Identifier: GPL-2.0-only +#define _GNU_SOURCE + #include <errno.h> #include <stdbool.h> #include <stdio.h> #include <string.h> #include <unistd.h> +#include <sched.h> #include <arpa/inet.h> +#include <sys/mount.h> +#include <sys/stat.h> #include <linux/err.h> #include <linux/in.h> #include <linux/in6.h> +#include <linux/limits.h> #include "bpf_util.h" #include "network_helpers.h" +#include "test_progs.h" #define clean_errno() (errno == 0 ? "None" : strerror(errno)) #define log_err(MSG, ...) ({ \ @@ -356,3 +363,82 @@ char *ping_command(int family) } return "ping"; } + +struct nstoken { + int orig_netns_fd; +}; + +static int setns_by_fd(int nsfd) +{ + int err; + + err = setns(nsfd, CLONE_NEWNET); + close(nsfd); + + if (!ASSERT_OK(err, "setns")) + return err; + + /* Switch /sys to the new namespace so that e.g. /sys/class/net + * reflects the devices in the new namespace. + */ + err = unshare(CLONE_NEWNS); + if (!ASSERT_OK(err, "unshare")) + return err; + + /* Make our /sys mount private, so the following umount won't + * trigger the global umount in case it's shared. + */ + err = mount("none", "/sys", NULL, MS_PRIVATE, NULL); + if (!ASSERT_OK(err, "remount private /sys")) + return err; + + err = umount2("/sys", MNT_DETACH); + if (!ASSERT_OK(err, "umount2 /sys")) + return err; + + err = mount("sysfs", "/sys", "sysfs", 0, NULL); + if (!ASSERT_OK(err, "mount /sys")) + return err; + + err = mount("bpffs", "/sys/fs/bpf", "bpf", 0, NULL); + if (!ASSERT_OK(err, "mount /sys/fs/bpf")) + return err; + + return 0; +} + +struct nstoken *open_netns(const char *name) +{ + int nsfd; + char nspath[PATH_MAX]; + int err; + struct nstoken *token; + + token = malloc(sizeof(struct nstoken)); + if (!ASSERT_OK_PTR(token, "malloc token")) + return NULL; + + token->orig_netns_fd = open("/proc/self/ns/net", O_RDONLY); + if (!ASSERT_GE(token->orig_netns_fd, 0, "open /proc/self/ns/net")) + goto fail; + + snprintf(nspath, sizeof(nspath), "%s/%s", "/var/run/netns", name); + nsfd = open(nspath, O_RDONLY | O_CLOEXEC); + if (!ASSERT_GE(nsfd, 0, "open netns fd")) + goto fail; + + err = setns_by_fd(nsfd); + if (!ASSERT_OK(err, "setns_by_fd")) + goto fail; + + return token; +fail: + free(token); + return NULL; +} + +void close_netns(struct nstoken *token) +{ + ASSERT_OK(setns_by_fd(token->orig_netns_fd), "setns_by_fd"); + free(token); +} diff --git a/tools/testing/selftests/bpf/network_helpers.h b/tools/testing/selftests/bpf/network_helpers.h index d198181a5648..a4b3b2f9877b 100644 --- a/tools/testing/selftests/bpf/network_helpers.h +++ b/tools/testing/selftests/bpf/network_helpers.h @@ -55,4 +55,13 @@ int make_sockaddr(int family, const char *addr_str, __u16 port, struct sockaddr_storage *addr, socklen_t *len); char *ping_command(int family); +struct nstoken; +/** + * open_netns() - Switch to specified network namespace by name. + * + * Returns token with which to restore the original namespace + * using close_netns(). + */ +struct nstoken *open_netns(const char *name); +void close_netns(struct nstoken *token); #endif diff --git a/tools/testing/selftests/bpf/prog_tests/align.c b/tools/testing/selftests/bpf/prog_tests/align.c index 0ee29e11eaee..970f09156eb4 100644 --- a/tools/testing/selftests/bpf/prog_tests/align.c +++ b/tools/testing/selftests/bpf/prog_tests/align.c @@ -39,13 +39,13 @@ static struct bpf_align_test tests[] = { }, .prog_type = BPF_PROG_TYPE_SCHED_CLS, .matches = { - {0, "R1=ctx(id=0,off=0,imm=0)"}, + {0, "R1=ctx(off=0,imm=0)"}, {0, "R10=fp0"}, - {0, "R3_w=inv2"}, - {1, "R3_w=inv4"}, - {2, "R3_w=inv8"}, - {3, "R3_w=inv16"}, - {4, "R3_w=inv32"}, + {0, "R3_w=2"}, + {1, "R3_w=4"}, + {2, "R3_w=8"}, + {3, "R3_w=16"}, + {4, "R3_w=32"}, }, }, { @@ -67,19 +67,19 @@ static struct bpf_align_test tests[] = { }, .prog_type = BPF_PROG_TYPE_SCHED_CLS, .matches = { - {0, "R1=ctx(id=0,off=0,imm=0)"}, + {0, "R1=ctx(off=0,imm=0)"}, {0, "R10=fp0"}, - {0, "R3_w=inv1"}, - {1, "R3_w=inv2"}, - {2, "R3_w=inv4"}, - {3, "R3_w=inv8"}, - {4, "R3_w=inv16"}, - {5, "R3_w=inv1"}, - {6, "R4_w=inv32"}, - {7, "R4_w=inv16"}, - {8, "R4_w=inv8"}, - {9, "R4_w=inv4"}, - {10, "R4_w=inv2"}, + {0, "R3_w=1"}, + {1, "R3_w=2"}, + {2, "R3_w=4"}, + {3, "R3_w=8"}, + {4, "R3_w=16"}, + {5, "R3_w=1"}, + {6, "R4_w=32"}, + {7, "R4_w=16"}, + {8, "R4_w=8"}, + {9, "R4_w=4"}, + {10, "R4_w=2"}, }, }, { @@ -96,14 +96,14 @@ static struct bpf_align_test tests[] = { }, .prog_type = BPF_PROG_TYPE_SCHED_CLS, .matches = { - {0, "R1=ctx(id=0,off=0,imm=0)"}, + {0, "R1=ctx(off=0,imm=0)"}, {0, "R10=fp0"}, - {0, "R3_w=inv4"}, - {1, "R3_w=inv8"}, - {2, "R3_w=inv10"}, - {3, "R4_w=inv8"}, - {4, "R4_w=inv12"}, - {5, "R4_w=inv14"}, + {0, "R3_w=4"}, + {1, "R3_w=8"}, + {2, "R3_w=10"}, + {3, "R4_w=8"}, + {4, "R4_w=12"}, + {5, "R4_w=14"}, }, }, { @@ -118,12 +118,12 @@ static struct bpf_align_test tests[] = { }, .prog_type = BPF_PROG_TYPE_SCHED_CLS, .matches = { - {0, "R1=ctx(id=0,off=0,imm=0)"}, + {0, "R1=ctx(off=0,imm=0)"}, {0, "R10=fp0"}, - {0, "R3_w=inv7"}, - {1, "R3_w=inv7"}, - {2, "R3_w=inv14"}, - {3, "R3_w=inv56"}, + {0, "R3_w=7"}, + {1, "R3_w=7"}, + {2, "R3_w=14"}, + {3, "R3_w=56"}, }, }, @@ -161,19 +161,19 @@ static struct bpf_align_test tests[] = { }, .prog_type = BPF_PROG_TYPE_SCHED_CLS, .matches = { - {6, "R0_w=pkt(id=0,off=8,r=8,imm=0)"}, - {6, "R3_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"}, - {7, "R3_w=inv(id=0,umax_value=510,var_off=(0x0; 0x1fe))"}, - {8, "R3_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, - {9, "R3_w=inv(id=0,umax_value=2040,var_off=(0x0; 0x7f8))"}, - {10, "R3_w=inv(id=0,umax_value=4080,var_off=(0x0; 0xff0))"}, - {12, "R3_w=pkt_end(id=0,off=0,imm=0)"}, - {17, "R4_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"}, - {18, "R4_w=inv(id=0,umax_value=8160,var_off=(0x0; 0x1fe0))"}, - {19, "R4_w=inv(id=0,umax_value=4080,var_off=(0x0; 0xff0))"}, - {20, "R4_w=inv(id=0,umax_value=2040,var_off=(0x0; 0x7f8))"}, - {21, "R4_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, - {22, "R4_w=inv(id=0,umax_value=510,var_off=(0x0; 0x1fe))"}, + {6, "R0_w=pkt(off=8,r=8,imm=0)"}, + {6, "R3_w=scalar(umax=255,var_off=(0x0; 0xff))"}, + {7, "R3_w=scalar(umax=510,var_off=(0x0; 0x1fe))"}, + {8, "R3_w=scalar(umax=1020,var_off=(0x0; 0x3fc))"}, + {9, "R3_w=scalar(umax=2040,var_off=(0x0; 0x7f8))"}, + {10, "R3_w=scalar(umax=4080,var_off=(0x0; 0xff0))"}, + {12, "R3_w=pkt_end(off=0,imm=0)"}, + {17, "R4_w=scalar(umax=255,var_off=(0x0; 0xff))"}, + {18, "R4_w=scalar(umax=8160,var_off=(0x0; 0x1fe0))"}, + {19, "R4_w=scalar(umax=4080,var_off=(0x0; 0xff0))"}, + {20, "R4_w=scalar(umax=2040,var_off=(0x0; 0x7f8))"}, + {21, "R4_w=scalar(umax=1020,var_off=(0x0; 0x3fc))"}, + {22, "R4_w=scalar(umax=510,var_off=(0x0; 0x1fe))"}, }, }, { @@ -194,16 +194,16 @@ static struct bpf_align_test tests[] = { }, .prog_type = BPF_PROG_TYPE_SCHED_CLS, .matches = { - {6, "R3_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"}, - {7, "R4_w=inv(id=1,umax_value=255,var_off=(0x0; 0xff))"}, - {8, "R4_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"}, - {9, "R4_w=inv(id=1,umax_value=255,var_off=(0x0; 0xff))"}, - {10, "R4_w=inv(id=0,umax_value=510,var_off=(0x0; 0x1fe))"}, - {11, "R4_w=inv(id=1,umax_value=255,var_off=(0x0; 0xff))"}, - {12, "R4_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, - {13, "R4_w=inv(id=1,umax_value=255,var_off=(0x0; 0xff))"}, - {14, "R4_w=inv(id=0,umax_value=2040,var_off=(0x0; 0x7f8))"}, - {15, "R4_w=inv(id=0,umax_value=4080,var_off=(0x0; 0xff0))"}, + {6, "R3_w=scalar(umax=255,var_off=(0x0; 0xff))"}, + {7, "R4_w=scalar(id=1,umax=255,var_off=(0x0; 0xff))"}, + {8, "R4_w=scalar(umax=255,var_off=(0x0; 0xff))"}, + {9, "R4_w=scalar(id=1,umax=255,var_off=(0x0; 0xff))"}, + {10, "R4_w=scalar(umax=510,var_off=(0x0; 0x1fe))"}, + {11, "R4_w=scalar(id=1,umax=255,var_off=(0x0; 0xff))"}, + {12, "R4_w=scalar(umax=1020,var_off=(0x0; 0x3fc))"}, + {13, "R4_w=scalar(id=1,umax=255,var_off=(0x0; 0xff))"}, + {14, "R4_w=scalar(umax=2040,var_off=(0x0; 0x7f8))"}, + {15, "R4_w=scalar(umax=4080,var_off=(0x0; 0xff0))"}, }, }, { @@ -234,14 +234,14 @@ static struct bpf_align_test tests[] = { }, .prog_type = BPF_PROG_TYPE_SCHED_CLS, .matches = { - {2, "R5_w=pkt(id=0,off=0,r=0,imm=0)"}, - {4, "R5_w=pkt(id=0,off=14,r=0,imm=0)"}, - {5, "R4_w=pkt(id=0,off=14,r=0,imm=0)"}, - {9, "R2=pkt(id=0,off=0,r=18,imm=0)"}, - {10, "R5=pkt(id=0,off=14,r=18,imm=0)"}, - {10, "R4_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"}, - {13, "R4_w=inv(id=0,umax_value=65535,var_off=(0x0; 0xffff))"}, - {14, "R4_w=inv(id=0,umax_value=65535,var_off=(0x0; 0xffff))"}, + {2, "R5_w=pkt(off=0,r=0,imm=0)"}, + {4, "R5_w=pkt(off=14,r=0,imm=0)"}, + {5, "R4_w=pkt(off=14,r=0,imm=0)"}, + {9, "R2=pkt(off=0,r=18,imm=0)"}, + {10, "R5=pkt(off=14,r=18,imm=0)"}, + {10, "R4_w=scalar(umax=255,var_off=(0x0; 0xff))"}, + {13, "R4_w=scalar(umax=65535,var_off=(0x0; 0xffff))"}, + {14, "R4_w=scalar(umax=65535,var_off=(0x0; 0xffff))"}, }, }, { @@ -296,59 +296,59 @@ static struct bpf_align_test tests[] = { /* Calculated offset in R6 has unknown value, but known * alignment of 4. */ - {6, "R2_w=pkt(id=0,off=0,r=8,imm=0)"}, - {7, "R6_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, + {6, "R2_w=pkt(off=0,r=8,imm=0)"}, + {7, "R6_w=scalar(umax=1020,var_off=(0x0; 0x3fc))"}, /* Offset is added to packet pointer R5, resulting in * known fixed offset, and variable offset from R6. */ - {11, "R5_w=pkt(id=1,off=14,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, + {11, "R5_w=pkt(id=1,off=14,r=0,umax=1020,var_off=(0x0; 0x3fc))"}, /* At the time the word size load is performed from R5, * it's total offset is NET_IP_ALIGN + reg->off (0) + * reg->aux_off (14) which is 16. Then the variable * offset is considered using reg->aux_off_align which * is 4 and meets the load's requirements. */ - {15, "R4=pkt(id=1,off=18,r=18,umax_value=1020,var_off=(0x0; 0x3fc))"}, - {15, "R5=pkt(id=1,off=14,r=18,umax_value=1020,var_off=(0x0; 0x3fc))"}, + {15, "R4=pkt(id=1,off=18,r=18,umax=1020,var_off=(0x0; 0x3fc))"}, + {15, "R5=pkt(id=1,off=14,r=18,umax=1020,var_off=(0x0; 0x3fc))"}, /* Variable offset is added to R5 packet pointer, * resulting in auxiliary alignment of 4. */ - {17, "R5_w=pkt(id=2,off=0,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, + {17, "R5_w=pkt(id=2,off=0,r=0,umax=1020,var_off=(0x0; 0x3fc))"}, /* Constant offset is added to R5, resulting in * reg->off of 14. */ - {18, "R5_w=pkt(id=2,off=14,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, + {18, "R5_w=pkt(id=2,off=14,r=0,umax=1020,var_off=(0x0; 0x3fc))"}, /* At the time the word size load is performed from R5, * its total fixed offset is NET_IP_ALIGN + reg->off * (14) which is 16. Then the variable offset is 4-byte * aligned, so the total offset is 4-byte aligned and * meets the load's requirements. */ - {23, "R4=pkt(id=2,off=18,r=18,umax_value=1020,var_off=(0x0; 0x3fc))"}, - {23, "R5=pkt(id=2,off=14,r=18,umax_value=1020,var_off=(0x0; 0x3fc))"}, + {23, "R4=pkt(id=2,off=18,r=18,umax=1020,var_off=(0x0; 0x3fc))"}, + {23, "R5=pkt(id=2,off=14,r=18,umax=1020,var_off=(0x0; 0x3fc))"}, /* Constant offset is added to R5 packet pointer, * resulting in reg->off value of 14. */ - {25, "R5_w=pkt(id=0,off=14,r=8"}, + {25, "R5_w=pkt(off=14,r=8"}, /* Variable offset is added to R5, resulting in a * variable offset of (4n). */ - {26, "R5_w=pkt(id=3,off=14,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, + {26, "R5_w=pkt(id=3,off=14,r=0,umax=1020,var_off=(0x0; 0x3fc))"}, /* Constant is added to R5 again, setting reg->off to 18. */ - {27, "R5_w=pkt(id=3,off=18,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, + {27, "R5_w=pkt(id=3,off=18,r=0,umax=1020,var_off=(0x0; 0x3fc))"}, /* And once more we add a variable; resulting var_off * is still (4n), fixed offset is not changed. * Also, we create a new reg->id. */ - {28, "R5_w=pkt(id=4,off=18,r=0,umax_value=2040,var_off=(0x0; 0x7fc)"}, + {28, "R5_w=pkt(id=4,off=18,r=0,umax=2040,var_off=(0x0; 0x7fc)"}, /* At the time the word size load is performed from R5, * its total fixed offset is NET_IP_ALIGN + reg->off (18) * which is 20. Then the variable offset is (4n), so * the total offset is 4-byte aligned and meets the * load's requirements. */ - {33, "R4=pkt(id=4,off=22,r=22,umax_value=2040,var_off=(0x0; 0x7fc)"}, - {33, "R5=pkt(id=4,off=18,r=22,umax_value=2040,var_off=(0x0; 0x7fc)"}, + {33, "R4=pkt(id=4,off=22,r=22,umax=2040,var_off=(0x0; 0x7fc)"}, + {33, "R5=pkt(id=4,off=18,r=22,umax=2040,var_off=(0x0; 0x7fc)"}, }, }, { @@ -386,36 +386,36 @@ static struct bpf_align_test tests[] = { /* Calculated offset in R6 has unknown value, but known * alignment of 4. */ - {6, "R2_w=pkt(id=0,off=0,r=8,imm=0)"}, - {7, "R6_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, + {6, "R2_w=pkt(off=0,r=8,imm=0)"}, + {7, "R6_w=scalar(umax=1020,var_off=(0x0; 0x3fc))"}, /* Adding 14 makes R6 be (4n+2) */ - {8, "R6_w=inv(id=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc))"}, + {8, "R6_w=scalar(umin=14,umax=1034,var_off=(0x2; 0x7fc))"}, /* Packet pointer has (4n+2) offset */ - {11, "R5_w=pkt(id=1,off=0,r=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc)"}, - {12, "R4=pkt(id=1,off=4,r=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc)"}, + {11, "R5_w=pkt(id=1,off=0,r=0,umin=14,umax=1034,var_off=(0x2; 0x7fc)"}, + {12, "R4=pkt(id=1,off=4,r=0,umin=14,umax=1034,var_off=(0x2; 0x7fc)"}, /* At the time the word size load is performed from R5, * its total fixed offset is NET_IP_ALIGN + reg->off (0) * which is 2. Then the variable offset is (4n+2), so * the total offset is 4-byte aligned and meets the * load's requirements. */ - {15, "R5=pkt(id=1,off=0,r=4,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc)"}, + {15, "R5=pkt(id=1,off=0,r=4,umin=14,umax=1034,var_off=(0x2; 0x7fc)"}, /* Newly read value in R6 was shifted left by 2, so has * known alignment of 4. */ - {17, "R6_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, + {17, "R6_w=scalar(umax=1020,var_off=(0x0; 0x3fc))"}, /* Added (4n) to packet pointer's (4n+2) var_off, giving * another (4n+2). */ - {19, "R5_w=pkt(id=2,off=0,r=0,umin_value=14,umax_value=2054,var_off=(0x2; 0xffc)"}, - {20, "R4=pkt(id=2,off=4,r=0,umin_value=14,umax_value=2054,var_off=(0x2; 0xffc)"}, + {19, "R5_w=pkt(id=2,off=0,r=0,umin=14,umax=2054,var_off=(0x2; 0xffc)"}, + {20, "R4=pkt(id=2,off=4,r=0,umin=14,umax=2054,var_off=(0x2; 0xffc)"}, /* At the time the word size load is performed from R5, * its total fixed offset is NET_IP_ALIGN + reg->off (0) * which is 2. Then the variable offset is (4n+2), so * the total offset is 4-byte aligned and meets the * load's requirements. */ - {23, "R5=pkt(id=2,off=0,r=4,umin_value=14,umax_value=2054,var_off=(0x2; 0xffc)"}, + {23, "R5=pkt(id=2,off=0,r=4,umin=14,umax=2054,var_off=(0x2; 0xffc)"}, }, }, { @@ -448,18 +448,18 @@ static struct bpf_align_test tests[] = { .prog_type = BPF_PROG_TYPE_SCHED_CLS, .result = REJECT, .matches = { - {3, "R5_w=pkt_end(id=0,off=0,imm=0)"}, + {3, "R5_w=pkt_end(off=0,imm=0)"}, /* (ptr - ptr) << 2 == unknown, (4n) */ - {5, "R5_w=inv(id=0,smax_value=9223372036854775804,umax_value=18446744073709551612,var_off=(0x0; 0xfffffffffffffffc)"}, + {5, "R5_w=scalar(smax=9223372036854775804,umax=18446744073709551612,var_off=(0x0; 0xfffffffffffffffc)"}, /* (4n) + 14 == (4n+2). We blow our bounds, because * the add could overflow. */ - {6, "R5_w=inv(id=0,smin_value=-9223372036854775806,smax_value=9223372036854775806,umin_value=2,umax_value=18446744073709551614,var_off=(0x2; 0xfffffffffffffffc)"}, + {6, "R5_w=scalar(smin=-9223372036854775806,smax=9223372036854775806,umin=2,umax=18446744073709551614,var_off=(0x2; 0xfffffffffffffffc)"}, /* Checked s>=0 */ - {9, "R5=inv(id=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc)"}, + {9, "R5=scalar(umin=2,umax=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc)"}, /* packet pointer + nonnegative (4n+2) */ - {11, "R6_w=pkt(id=1,off=0,r=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc)"}, - {12, "R4_w=pkt(id=1,off=4,r=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc)"}, + {11, "R6_w=pkt(id=1,off=0,r=0,umin=2,umax=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc)"}, + {12, "R4_w=pkt(id=1,off=4,r=0,umin=2,umax=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc)"}, /* NET_IP_ALIGN + (4n+2) == (4n), alignment is fine. * We checked the bounds, but it might have been able * to overflow if the packet pointer started in the @@ -467,7 +467,7 @@ static struct bpf_align_test tests[] = { * So we did not get a 'range' on R6, and the access * attempt will fail. */ - {15, "R6_w=pkt(id=1,off=0,r=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc)"}, + {15, "R6_w=pkt(id=1,off=0,r=0,umin=2,umax=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc)"}, } }, { @@ -502,23 +502,23 @@ static struct bpf_align_test tests[] = { /* Calculated offset in R6 has unknown value, but known * alignment of 4. */ - {6, "R2_w=pkt(id=0,off=0,r=8,imm=0)"}, - {8, "R6_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, + {6, "R2_w=pkt(off=0,r=8,imm=0)"}, + {8, "R6_w=scalar(umax=1020,var_off=(0x0; 0x3fc))"}, /* Adding 14 makes R6 be (4n+2) */ - {9, "R6_w=inv(id=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc))"}, + {9, "R6_w=scalar(umin=14,umax=1034,var_off=(0x2; 0x7fc))"}, /* New unknown value in R7 is (4n) */ - {10, "R7_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, + {10, "R7_w=scalar(umax=1020,var_off=(0x0; 0x3fc))"}, /* Subtracting it from R6 blows our unsigned bounds */ - {11, "R6=inv(id=0,smin_value=-1006,smax_value=1034,umin_value=2,umax_value=18446744073709551614,var_off=(0x2; 0xfffffffffffffffc)"}, + {11, "R6=scalar(smin=-1006,smax=1034,umin=2,umax=18446744073709551614,var_off=(0x2; 0xfffffffffffffffc)"}, /* Checked s>= 0 */ - {14, "R6=inv(id=0,umin_value=2,umax_value=1034,var_off=(0x2; 0x7fc))"}, + {14, "R6=scalar(umin=2,umax=1034,var_off=(0x2; 0x7fc))"}, /* At the time the word size load is performed from R5, * its total fixed offset is NET_IP_ALIGN + reg->off (0) * which is 2. Then the variable offset is (4n+2), so * the total offset is 4-byte aligned and meets the * load's requirements. */ - {20, "R5=pkt(id=2,off=0,r=4,umin_value=2,umax_value=1034,var_off=(0x2; 0x7fc)"}, + {20, "R5=pkt(id=2,off=0,r=4,umin=2,umax=1034,var_off=(0x2; 0x7fc)"}, }, }, @@ -556,23 +556,23 @@ static struct bpf_align_test tests[] = { /* Calculated offset in R6 has unknown value, but known * alignment of 4. */ - {6, "R2_w=pkt(id=0,off=0,r=8,imm=0)"}, - {9, "R6_w=inv(id=0,umax_value=60,var_off=(0x0; 0x3c))"}, + {6, "R2_w=pkt(off=0,r=8,imm=0)"}, + {9, "R6_w=scalar(umax=60,var_off=(0x0; 0x3c))"}, /* Adding 14 makes R6 be (4n+2) */ - {10, "R6_w=inv(id=0,umin_value=14,umax_value=74,var_off=(0x2; 0x7c))"}, + {10, "R6_w=scalar(umin=14,umax=74,var_off=(0x2; 0x7c))"}, /* Subtracting from packet pointer overflows ubounds */ - {13, "R5_w=pkt(id=2,off=0,r=8,umin_value=18446744073709551542,umax_value=18446744073709551602,var_off=(0xffffffffffffff82; 0x7c)"}, + {13, "R5_w=pkt(id=2,off=0,r=8,umin=18446744073709551542,umax=18446744073709551602,var_off=(0xffffffffffffff82; 0x7c)"}, /* New unknown value in R7 is (4n), >= 76 */ - {14, "R7_w=inv(id=0,umin_value=76,umax_value=1096,var_off=(0x0; 0x7fc))"}, + {14, "R7_w=scalar(umin=76,umax=1096,var_off=(0x0; 0x7fc))"}, /* Adding it to packet pointer gives nice bounds again */ - {16, "R5_w=pkt(id=3,off=0,r=0,umin_value=2,umax_value=1082,var_off=(0x2; 0xfffffffc)"}, + {16, "R5_w=pkt(id=3,off=0,r=0,umin=2,umax=1082,var_off=(0x2; 0xfffffffc)"}, /* At the time the word size load is performed from R5, * its total fixed offset is NET_IP_ALIGN + reg->off (0) * which is 2. Then the variable offset is (4n+2), so * the total offset is 4-byte aligned and meets the * load's requirements. */ - {20, "R5=pkt(id=3,off=0,r=4,umin_value=2,umax_value=1082,var_off=(0x2; 0xfffffffc)"}, + {20, "R5=pkt(id=3,off=0,r=4,umin=2,umax=1082,var_off=(0x2; 0xfffffffc)"}, }, }, }; @@ -648,8 +648,8 @@ static int do_test_single(struct bpf_align_test *test) /* Check the next line as well in case the previous line * did not have a corresponding bpf insn. Example: * func#0 @0 - * 0: R1=ctx(id=0,off=0,imm=0) R10=fp0 - * 0: (b7) r3 = 2 ; R3_w=inv2 + * 0: R1=ctx(off=0,imm=0) R10=fp0 + * 0: (b7) r3 = 2 ; R3_w=2 */ if (!strstr(line_ptr, m.match)) { cur_line = -1; diff --git a/tools/testing/selftests/bpf/prog_tests/atomics.c b/tools/testing/selftests/bpf/prog_tests/atomics.c index 86b7d5d84eec..13e101f370a1 100644 --- a/tools/testing/selftests/bpf/prog_tests/atomics.c +++ b/tools/testing/selftests/bpf/prog_tests/atomics.c @@ -7,19 +7,15 @@ static void test_add(struct atomics_lskel *skel) { int err, prog_fd; - __u32 duration = 0, retval; - int link_fd; - - link_fd = atomics_lskel__add__attach(skel); - if (!ASSERT_GT(link_fd, 0, "attach(add)")) - return; + LIBBPF_OPTS(bpf_test_run_opts, topts); + /* No need to attach it, just run it directly */ prog_fd = skel->progs.add.prog_fd; - err = bpf_prog_test_run(prog_fd, 1, NULL, 0, - NULL, NULL, &retval, &duration); - if (CHECK(err || retval, "test_run add", - "err %d errno %d retval %d duration %d\n", err, errno, retval, duration)) - goto cleanup; + err = bpf_prog_test_run_opts(prog_fd, &topts); + if (!ASSERT_OK(err, "test_run_opts err")) + return; + if (!ASSERT_OK(topts.retval, "test_run_opts retval")) + return; ASSERT_EQ(skel->data->add64_value, 3, "add64_value"); ASSERT_EQ(skel->bss->add64_result, 1, "add64_result"); @@ -31,28 +27,20 @@ static void test_add(struct atomics_lskel *skel) ASSERT_EQ(skel->bss->add_stack_result, 1, "add_stack_result"); ASSERT_EQ(skel->data->add_noreturn_value, 3, "add_noreturn_value"); - -cleanup: - close(link_fd); } static void test_sub(struct atomics_lskel *skel) { int err, prog_fd; - __u32 duration = 0, retval; - int link_fd; - - link_fd = atomics_lskel__sub__attach(skel); - if (!ASSERT_GT(link_fd, 0, "attach(sub)")) - return; + LIBBPF_OPTS(bpf_test_run_opts, topts); + /* No need to attach it, just run it directly */ prog_fd = skel->progs.sub.prog_fd; - err = bpf_prog_test_run(prog_fd, 1, NULL, 0, - NULL, NULL, &retval, &duration); - if (CHECK(err || retval, "test_run sub", - "err %d errno %d retval %d duration %d\n", - err, errno, retval, duration)) - goto cleanup; + err = bpf_prog_test_run_opts(prog_fd, &topts); + if (!ASSERT_OK(err, "test_run_opts err")) + return; + if (!ASSERT_OK(topts.retval, "test_run_opts retval")) + return; ASSERT_EQ(skel->data->sub64_value, -1, "sub64_value"); ASSERT_EQ(skel->bss->sub64_result, 1, "sub64_result"); @@ -64,27 +52,20 @@ static void test_sub(struct atomics_lskel *skel) ASSERT_EQ(skel->bss->sub_stack_result, 1, "sub_stack_result"); ASSERT_EQ(skel->data->sub_noreturn_value, -1, "sub_noreturn_value"); - -cleanup: - close(link_fd); } static void test_and(struct atomics_lskel *skel) { int err, prog_fd; - __u32 duration = 0, retval; - int link_fd; - - link_fd = atomics_lskel__and__attach(skel); - if (!ASSERT_GT(link_fd, 0, "attach(and)")) - return; + LIBBPF_OPTS(bpf_test_run_opts, topts); + /* No need to attach it, just run it directly */ prog_fd = skel->progs.and.prog_fd; - err = bpf_prog_test_run(prog_fd, 1, NULL, 0, - NULL, NULL, &retval, &duration); - if (CHECK(err || retval, "test_run and", - "err %d errno %d retval %d duration %d\n", err, errno, retval, duration)) - goto cleanup; + err = bpf_prog_test_run_opts(prog_fd, &topts); + if (!ASSERT_OK(err, "test_run_opts err")) + return; + if (!ASSERT_OK(topts.retval, "test_run_opts retval")) + return; ASSERT_EQ(skel->data->and64_value, 0x010ull << 32, "and64_value"); ASSERT_EQ(skel->bss->and64_result, 0x110ull << 32, "and64_result"); @@ -93,27 +74,20 @@ static void test_and(struct atomics_lskel *skel) ASSERT_EQ(skel->bss->and32_result, 0x110, "and32_result"); ASSERT_EQ(skel->data->and_noreturn_value, 0x010ull << 32, "and_noreturn_value"); -cleanup: - close(link_fd); } static void test_or(struct atomics_lskel *skel) { int err, prog_fd; - __u32 duration = 0, retval; - int link_fd; - - link_fd = atomics_lskel__or__attach(skel); - if (!ASSERT_GT(link_fd, 0, "attach(or)")) - return; + LIBBPF_OPTS(bpf_test_run_opts, topts); + /* No need to attach it, just run it directly */ prog_fd = skel->progs.or.prog_fd; - err = bpf_prog_test_run(prog_fd, 1, NULL, 0, - NULL, NULL, &retval, &duration); - if (CHECK(err || retval, "test_run or", - "err %d errno %d retval %d duration %d\n", - err, errno, retval, duration)) - goto cleanup; + err = bpf_prog_test_run_opts(prog_fd, &topts); + if (!ASSERT_OK(err, "test_run_opts err")) + return; + if (!ASSERT_OK(topts.retval, "test_run_opts retval")) + return; ASSERT_EQ(skel->data->or64_value, 0x111ull << 32, "or64_value"); ASSERT_EQ(skel->bss->or64_result, 0x110ull << 32, "or64_result"); @@ -122,26 +96,20 @@ static void test_or(struct atomics_lskel *skel) ASSERT_EQ(skel->bss->or32_result, 0x110, "or32_result"); ASSERT_EQ(skel->data->or_noreturn_value, 0x111ull << 32, "or_noreturn_value"); -cleanup: - close(link_fd); } static void test_xor(struct atomics_lskel *skel) { int err, prog_fd; - __u32 duration = 0, retval; - int link_fd; - - link_fd = atomics_lskel__xor__attach(skel); - if (!ASSERT_GT(link_fd, 0, "attach(xor)")) - return; + LIBBPF_OPTS(bpf_test_run_opts, topts); + /* No need to attach it, just run it directly */ prog_fd = skel->progs.xor.prog_fd; - err = bpf_prog_test_run(prog_fd, 1, NULL, 0, - NULL, NULL, &retval, &duration); - if (CHECK(err || retval, "test_run xor", - "err %d errno %d retval %d duration %d\n", err, errno, retval, duration)) - goto cleanup; + err = bpf_prog_test_run_opts(prog_fd, &topts); + if (!ASSERT_OK(err, "test_run_opts err")) + return; + if (!ASSERT_OK(topts.retval, "test_run_opts retval")) + return; ASSERT_EQ(skel->data->xor64_value, 0x101ull << 32, "xor64_value"); ASSERT_EQ(skel->bss->xor64_result, 0x110ull << 32, "xor64_result"); @@ -150,26 +118,20 @@ static void test_xor(struct atomics_lskel *skel) ASSERT_EQ(skel->bss->xor32_result, 0x110, "xor32_result"); ASSERT_EQ(skel->data->xor_noreturn_value, 0x101ull << 32, "xor_nxoreturn_value"); -cleanup: - close(link_fd); } static void test_cmpxchg(struct atomics_lskel *skel) { int err, prog_fd; - __u32 duration = 0, retval; - int link_fd; - - link_fd = atomics_lskel__cmpxchg__attach(skel); - if (!ASSERT_GT(link_fd, 0, "attach(cmpxchg)")) - return; + LIBBPF_OPTS(bpf_test_run_opts, topts); + /* No need to attach it, just run it directly */ prog_fd = skel->progs.cmpxchg.prog_fd; - err = bpf_prog_test_run(prog_fd, 1, NULL, 0, - NULL, NULL, &retval, &duration); - if (CHECK(err || retval, "test_run cmpxchg", - "err %d errno %d retval %d duration %d\n", err, errno, retval, duration)) - goto cleanup; + err = bpf_prog_test_run_opts(prog_fd, &topts); + if (!ASSERT_OK(err, "test_run_opts err")) + return; + if (!ASSERT_OK(topts.retval, "test_run_opts retval")) + return; ASSERT_EQ(skel->data->cmpxchg64_value, 2, "cmpxchg64_value"); ASSERT_EQ(skel->bss->cmpxchg64_result_fail, 1, "cmpxchg_result_fail"); @@ -178,45 +140,34 @@ static void test_cmpxchg(struct atomics_lskel *skel) ASSERT_EQ(skel->data->cmpxchg32_value, 2, "lcmpxchg32_value"); ASSERT_EQ(skel->bss->cmpxchg32_result_fail, 1, "cmpxchg_result_fail"); ASSERT_EQ(skel->bss->cmpxchg32_result_succeed, 1, "cmpxchg_result_succeed"); - -cleanup: - close(link_fd); } static void test_xchg(struct atomics_lskel *skel) { int err, prog_fd; - __u32 duration = 0, retval; - int link_fd; - - link_fd = atomics_lskel__xchg__attach(skel); - if (!ASSERT_GT(link_fd, 0, "attach(xchg)")) - return; + LIBBPF_OPTS(bpf_test_run_opts, topts); + /* No need to attach it, just run it directly */ prog_fd = skel->progs.xchg.prog_fd; - err = bpf_prog_test_run(prog_fd, 1, NULL, 0, - NULL, NULL, &retval, &duration); - if (CHECK(err || retval, "test_run xchg", - "err %d errno %d retval %d duration %d\n", err, errno, retval, duration)) - goto cleanup; + err = bpf_prog_test_run_opts(prog_fd, &topts); + if (!ASSERT_OK(err, "test_run_opts err")) + return; + if (!ASSERT_OK(topts.retval, "test_run_opts retval")) + return; ASSERT_EQ(skel->data->xchg64_value, 2, "xchg64_value"); ASSERT_EQ(skel->bss->xchg64_result, 1, "xchg64_result"); ASSERT_EQ(skel->data->xchg32_value, 2, "xchg32_value"); ASSERT_EQ(skel->bss->xchg32_result, 1, "xchg32_result"); - -cleanup: - close(link_fd); } void test_atomics(void) { struct atomics_lskel *skel; - __u32 duration = 0; skel = atomics_lskel__open_and_load(); - if (CHECK(!skel, "skel_load", "atomics skeleton failed\n")) + if (!ASSERT_OK_PTR(skel, "atomics skeleton load")) return; if (skel->data->skip_tests) { diff --git a/tools/testing/selftests/bpf/prog_tests/attach_probe.c b/tools/testing/selftests/bpf/prog_tests/attach_probe.c index d0bd51eb23c8..d48f6e533e1e 100644 --- a/tools/testing/selftests/bpf/prog_tests/attach_probe.c +++ b/tools/testing/selftests/bpf/prog_tests/attach_probe.c @@ -5,9 +5,10 @@ /* this is how USDT semaphore is actually defined, except volatile modifier */ volatile unsigned short uprobe_ref_ctr __attribute__((unused)) __attribute((section(".probes"))); -/* attach point */ -static void method(void) { - return ; +/* uprobe attach point */ +static void trigger_func(void) +{ + asm volatile (""); } void test_attach_probe(void) @@ -17,8 +18,7 @@ void test_attach_probe(void) struct bpf_link *kprobe_link, *kretprobe_link; struct bpf_link *uprobe_link, *uretprobe_link; struct test_attach_probe* skel; - size_t uprobe_offset; - ssize_t base_addr, ref_ctr_offset; + ssize_t uprobe_offset, ref_ctr_offset; bool legacy; /* Check if new-style kprobe/uprobe API is supported. @@ -34,11 +34,9 @@ void test_attach_probe(void) */ legacy = access("/sys/bus/event_source/devices/kprobe/type", F_OK) != 0; - base_addr = get_base_addr(); - if (CHECK(base_addr < 0, "get_base_addr", - "failed to find base addr: %zd", base_addr)) + uprobe_offset = get_uprobe_offset(&trigger_func); + if (!ASSERT_GE(uprobe_offset, 0, "uprobe_offset")) return; - uprobe_offset = get_uprobe_offset(&method, base_addr); ref_ctr_offset = get_rel_offset((uintptr_t)&uprobe_ref_ctr); if (!ASSERT_GE(ref_ctr_offset, 0, "ref_ctr_offset")) @@ -103,7 +101,7 @@ void test_attach_probe(void) goto cleanup; /* trigger & validate uprobe & uretprobe */ - method(); + trigger_func(); if (CHECK(skel->bss->uprobe_res != 3, "check_uprobe_res", "wrong uprobe res: %d\n", skel->bss->uprobe_res)) diff --git a/tools/testing/selftests/bpf/prog_tests/bind_perm.c b/tools/testing/selftests/bpf/prog_tests/bind_perm.c index d0f06e40c16d..a1766a298bb7 100644 --- a/tools/testing/selftests/bpf/prog_tests/bind_perm.c +++ b/tools/testing/selftests/bpf/prog_tests/bind_perm.c @@ -1,13 +1,24 @@ // SPDX-License-Identifier: GPL-2.0 -#include <test_progs.h> -#include "bind_perm.skel.h" - +#define _GNU_SOURCE +#include <sched.h> +#include <stdlib.h> #include <sys/types.h> #include <sys/socket.h> -#include <sys/capability.h> + +#include "test_progs.h" +#include "cap_helpers.h" +#include "bind_perm.skel.h" static int duration; +static int create_netns(void) +{ + if (!ASSERT_OK(unshare(CLONE_NEWNET), "create netns")) + return -1; + + return 0; +} + void try_bind(int family, int port, int expected_errno) { struct sockaddr_storage addr = {}; @@ -38,43 +49,16 @@ close_socket: close(fd); } -bool cap_net_bind_service(cap_flag_value_t flag) -{ - const cap_value_t cap_net_bind_service = CAP_NET_BIND_SERVICE; - cap_flag_value_t original_value; - bool was_effective = false; - cap_t caps; - - caps = cap_get_proc(); - if (CHECK(!caps, "cap_get_proc", "errno %d", errno)) - goto free_caps; - - if (CHECK(cap_get_flag(caps, CAP_NET_BIND_SERVICE, CAP_EFFECTIVE, - &original_value), - "cap_get_flag", "errno %d", errno)) - goto free_caps; - - was_effective = (original_value == CAP_SET); - - if (CHECK(cap_set_flag(caps, CAP_EFFECTIVE, 1, &cap_net_bind_service, - flag), - "cap_set_flag", "errno %d", errno)) - goto free_caps; - - if (CHECK(cap_set_proc(caps), "cap_set_proc", "errno %d", errno)) - goto free_caps; - -free_caps: - CHECK(cap_free(caps), "cap_free", "errno %d", errno); - return was_effective; -} - void test_bind_perm(void) { - bool cap_was_effective; + const __u64 net_bind_svc_cap = 1ULL << CAP_NET_BIND_SERVICE; struct bind_perm *skel; + __u64 old_caps = 0; int cgroup_fd; + if (create_netns()) + return; + cgroup_fd = test__join_cgroup("/bind_perm"); if (CHECK(cgroup_fd < 0, "cg-join", "errno %d", errno)) return; @@ -91,7 +75,8 @@ void test_bind_perm(void) if (!ASSERT_OK_PTR(skel, "bind_v6_prog")) goto close_skeleton; - cap_was_effective = cap_net_bind_service(CAP_CLEAR); + ASSERT_OK(cap_disable_effective(net_bind_svc_cap, &old_caps), + "cap_disable_effective"); try_bind(AF_INET, 110, EACCES); try_bind(AF_INET6, 110, EACCES); @@ -99,8 +84,9 @@ void test_bind_perm(void) try_bind(AF_INET, 111, 0); try_bind(AF_INET6, 111, 0); - if (cap_was_effective) - cap_net_bind_service(CAP_SET); + if (old_caps & net_bind_svc_cap) + ASSERT_OK(cap_enable_effective(net_bind_svc_cap, NULL), + "cap_enable_effective"); close_skeleton: bind_perm__destroy(skel); diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c b/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c index 5eea3c3a40fe..923a6139b2d8 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c @@ -7,6 +7,13 @@ #include <unistd.h> #include <test_progs.h> #include "test_bpf_cookie.skel.h" +#include "kprobe_multi.skel.h" + +/* uprobe attach point */ +static void trigger_func(void) +{ + asm volatile (""); +} static void kprobe_subtest(struct test_bpf_cookie *skel) { @@ -57,16 +64,188 @@ cleanup: bpf_link__destroy(retlink2); } +static void kprobe_multi_test_run(struct kprobe_multi *skel) +{ + LIBBPF_OPTS(bpf_test_run_opts, topts); + int err, prog_fd; + + prog_fd = bpf_program__fd(skel->progs.trigger); + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "test_run"); + ASSERT_EQ(topts.retval, 0, "test_run"); + + ASSERT_EQ(skel->bss->kprobe_test1_result, 1, "kprobe_test1_result"); + ASSERT_EQ(skel->bss->kprobe_test2_result, 1, "kprobe_test2_result"); + ASSERT_EQ(skel->bss->kprobe_test3_result, 1, "kprobe_test3_result"); + ASSERT_EQ(skel->bss->kprobe_test4_result, 1, "kprobe_test4_result"); + ASSERT_EQ(skel->bss->kprobe_test5_result, 1, "kprobe_test5_result"); + ASSERT_EQ(skel->bss->kprobe_test6_result, 1, "kprobe_test6_result"); + ASSERT_EQ(skel->bss->kprobe_test7_result, 1, "kprobe_test7_result"); + ASSERT_EQ(skel->bss->kprobe_test8_result, 1, "kprobe_test8_result"); + + ASSERT_EQ(skel->bss->kretprobe_test1_result, 1, "kretprobe_test1_result"); + ASSERT_EQ(skel->bss->kretprobe_test2_result, 1, "kretprobe_test2_result"); + ASSERT_EQ(skel->bss->kretprobe_test3_result, 1, "kretprobe_test3_result"); + ASSERT_EQ(skel->bss->kretprobe_test4_result, 1, "kretprobe_test4_result"); + ASSERT_EQ(skel->bss->kretprobe_test5_result, 1, "kretprobe_test5_result"); + ASSERT_EQ(skel->bss->kretprobe_test6_result, 1, "kretprobe_test6_result"); + ASSERT_EQ(skel->bss->kretprobe_test7_result, 1, "kretprobe_test7_result"); + ASSERT_EQ(skel->bss->kretprobe_test8_result, 1, "kretprobe_test8_result"); +} + +static void kprobe_multi_link_api_subtest(void) +{ + int prog_fd, link1_fd = -1, link2_fd = -1; + struct kprobe_multi *skel = NULL; + LIBBPF_OPTS(bpf_link_create_opts, opts); + unsigned long long addrs[8]; + __u64 cookies[8]; + + if (!ASSERT_OK(load_kallsyms(), "load_kallsyms")) + goto cleanup; + + skel = kprobe_multi__open_and_load(); + if (!ASSERT_OK_PTR(skel, "fentry_raw_skel_load")) + goto cleanup; + + skel->bss->pid = getpid(); + skel->bss->test_cookie = true; + +#define GET_ADDR(__sym, __addr) ({ \ + __addr = ksym_get_addr(__sym); \ + if (!ASSERT_NEQ(__addr, 0, "ksym_get_addr " #__sym)) \ + goto cleanup; \ +}) + + GET_ADDR("bpf_fentry_test1", addrs[0]); + GET_ADDR("bpf_fentry_test2", addrs[1]); + GET_ADDR("bpf_fentry_test3", addrs[2]); + GET_ADDR("bpf_fentry_test4", addrs[3]); + GET_ADDR("bpf_fentry_test5", addrs[4]); + GET_ADDR("bpf_fentry_test6", addrs[5]); + GET_ADDR("bpf_fentry_test7", addrs[6]); + GET_ADDR("bpf_fentry_test8", addrs[7]); + +#undef GET_ADDR + + cookies[0] = 1; + cookies[1] = 2; + cookies[2] = 3; + cookies[3] = 4; + cookies[4] = 5; + cookies[5] = 6; + cookies[6] = 7; + cookies[7] = 8; + + opts.kprobe_multi.addrs = (const unsigned long *) &addrs; + opts.kprobe_multi.cnt = ARRAY_SIZE(addrs); + opts.kprobe_multi.cookies = (const __u64 *) &cookies; + prog_fd = bpf_program__fd(skel->progs.test_kprobe); + + link1_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_KPROBE_MULTI, &opts); + if (!ASSERT_GE(link1_fd, 0, "link1_fd")) + goto cleanup; + + cookies[0] = 8; + cookies[1] = 7; + cookies[2] = 6; + cookies[3] = 5; + cookies[4] = 4; + cookies[5] = 3; + cookies[6] = 2; + cookies[7] = 1; + + opts.kprobe_multi.flags = BPF_F_KPROBE_MULTI_RETURN; + prog_fd = bpf_program__fd(skel->progs.test_kretprobe); + + link2_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_KPROBE_MULTI, &opts); + if (!ASSERT_GE(link2_fd, 0, "link2_fd")) + goto cleanup; + + kprobe_multi_test_run(skel); + +cleanup: + close(link1_fd); + close(link2_fd); + kprobe_multi__destroy(skel); +} + +static void kprobe_multi_attach_api_subtest(void) +{ + struct bpf_link *link1 = NULL, *link2 = NULL; + LIBBPF_OPTS(bpf_kprobe_multi_opts, opts); + LIBBPF_OPTS(bpf_test_run_opts, topts); + struct kprobe_multi *skel = NULL; + const char *syms[8] = { + "bpf_fentry_test1", + "bpf_fentry_test2", + "bpf_fentry_test3", + "bpf_fentry_test4", + "bpf_fentry_test5", + "bpf_fentry_test6", + "bpf_fentry_test7", + "bpf_fentry_test8", + }; + __u64 cookies[8]; + + skel = kprobe_multi__open_and_load(); + if (!ASSERT_OK_PTR(skel, "fentry_raw_skel_load")) + goto cleanup; + + skel->bss->pid = getpid(); + skel->bss->test_cookie = true; + + cookies[0] = 1; + cookies[1] = 2; + cookies[2] = 3; + cookies[3] = 4; + cookies[4] = 5; + cookies[5] = 6; + cookies[6] = 7; + cookies[7] = 8; + + opts.syms = syms; + opts.cnt = ARRAY_SIZE(syms); + opts.cookies = cookies; + + link1 = bpf_program__attach_kprobe_multi_opts(skel->progs.test_kprobe, + NULL, &opts); + if (!ASSERT_OK_PTR(link1, "bpf_program__attach_kprobe_multi_opts")) + goto cleanup; + + cookies[0] = 8; + cookies[1] = 7; + cookies[2] = 6; + cookies[3] = 5; + cookies[4] = 4; + cookies[5] = 3; + cookies[6] = 2; + cookies[7] = 1; + + opts.retprobe = true; + + link2 = bpf_program__attach_kprobe_multi_opts(skel->progs.test_kretprobe, + NULL, &opts); + if (!ASSERT_OK_PTR(link2, "bpf_program__attach_kprobe_multi_opts")) + goto cleanup; + + kprobe_multi_test_run(skel); + +cleanup: + bpf_link__destroy(link2); + bpf_link__destroy(link1); + kprobe_multi__destroy(skel); +} static void uprobe_subtest(struct test_bpf_cookie *skel) { DECLARE_LIBBPF_OPTS(bpf_uprobe_opts, opts); struct bpf_link *link1 = NULL, *link2 = NULL; struct bpf_link *retlink1 = NULL, *retlink2 = NULL; - size_t uprobe_offset; - ssize_t base_addr; + ssize_t uprobe_offset; - base_addr = get_base_addr(); - uprobe_offset = get_uprobe_offset(&get_base_addr, base_addr); + uprobe_offset = get_uprobe_offset(&trigger_func); + if (!ASSERT_GE(uprobe_offset, 0, "uprobe_offset")) + goto cleanup; /* attach two uprobes */ opts.bpf_cookie = 0x100; @@ -99,7 +278,7 @@ static void uprobe_subtest(struct test_bpf_cookie *skel) goto cleanup; /* trigger uprobe && uretprobe */ - get_base_addr(); + trigger_func(); ASSERT_EQ(skel->bss->uprobe_res, 0x100 | 0x200, "uprobe_res"); ASSERT_EQ(skel->bss->uretprobe_res, 0x1000 | 0x2000, "uretprobe_res"); @@ -193,7 +372,7 @@ static void pe_subtest(struct test_bpf_cookie *skel) attr.type = PERF_TYPE_SOFTWARE; attr.config = PERF_COUNT_SW_CPU_CLOCK; attr.freq = 1; - attr.sample_freq = 4000; + attr.sample_freq = 1000; pfd = syscall(__NR_perf_event_open, &attr, -1, 0, -1, PERF_FLAG_FD_CLOEXEC); if (!ASSERT_GE(pfd, 0, "perf_fd")) goto cleanup; @@ -243,6 +422,10 @@ void test_bpf_cookie(void) if (test__start_subtest("kprobe")) kprobe_subtest(skel); + if (test__start_subtest("multi_kprobe_link_api")) + kprobe_multi_link_api_subtest(); + if (test__start_subtest("multi_kprobe_attach_api")) + kprobe_multi_attach_api_subtest(); if (test__start_subtest("uprobe")) uprobe_subtest(skel); if (test__start_subtest("tracepoint")) diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c index b84f859b1267..5142a7d130b2 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c @@ -138,6 +138,24 @@ static void test_task(void) bpf_iter_task__destroy(skel); } +static void test_task_sleepable(void) +{ + struct bpf_iter_task *skel; + + skel = bpf_iter_task__open_and_load(); + if (!ASSERT_OK_PTR(skel, "bpf_iter_task__open_and_load")) + return; + + do_dummy_read(skel->progs.dump_task_sleepable); + + ASSERT_GT(skel->bss->num_expected_failure_copy_from_user_task, 0, + "num_expected_failure_copy_from_user_task"); + ASSERT_GT(skel->bss->num_success_copy_from_user_task, 0, + "num_success_copy_from_user_task"); + + bpf_iter_task__destroy(skel); +} + static void test_task_stack(void) { struct bpf_iter_task_stack *skel; @@ -1252,6 +1270,8 @@ void test_bpf_iter(void) test_bpf_map(); if (test__start_subtest("task")) test_task(); + if (test__start_subtest("task_sleepable")) + test_task_sleepable(); if (test__start_subtest("task_stack")) test_task_stack(); if (test__start_subtest("task_file")) diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_iter_setsockopt_unix.c b/tools/testing/selftests/bpf/prog_tests/bpf_iter_setsockopt_unix.c new file mode 100644 index 000000000000..ee725d4d98a5 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/bpf_iter_setsockopt_unix.c @@ -0,0 +1,100 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright Amazon.com Inc. or its affiliates. */ +#include <sys/socket.h> +#include <sys/un.h> +#include <test_progs.h> +#include "bpf_iter_setsockopt_unix.skel.h" + +#define NR_CASES 5 + +static int create_unix_socket(struct bpf_iter_setsockopt_unix *skel) +{ + struct sockaddr_un addr = { + .sun_family = AF_UNIX, + .sun_path = "", + }; + socklen_t len; + int fd, err; + + fd = socket(AF_UNIX, SOCK_STREAM, 0); + if (!ASSERT_NEQ(fd, -1, "socket")) + return -1; + + len = offsetof(struct sockaddr_un, sun_path); + err = bind(fd, (struct sockaddr *)&addr, len); + if (!ASSERT_OK(err, "bind")) + return -1; + + len = sizeof(addr); + err = getsockname(fd, (struct sockaddr *)&addr, &len); + if (!ASSERT_OK(err, "getsockname")) + return -1; + + memcpy(&skel->bss->sun_path, &addr.sun_path, + len - offsetof(struct sockaddr_un, sun_path)); + + return fd; +} + +static void test_sndbuf(struct bpf_iter_setsockopt_unix *skel, int fd) +{ + socklen_t optlen; + int i, err; + + for (i = 0; i < NR_CASES; i++) { + if (!ASSERT_NEQ(skel->data->sndbuf_getsockopt[i], -1, + "bpf_(get|set)sockopt")) + return; + + err = setsockopt(fd, SOL_SOCKET, SO_SNDBUF, + &(skel->data->sndbuf_setsockopt[i]), + sizeof(skel->data->sndbuf_setsockopt[i])); + if (!ASSERT_OK(err, "setsockopt")) + return; + + optlen = sizeof(skel->bss->sndbuf_getsockopt_expected[i]); + err = getsockopt(fd, SOL_SOCKET, SO_SNDBUF, + &(skel->bss->sndbuf_getsockopt_expected[i]), + &optlen); + if (!ASSERT_OK(err, "getsockopt")) + return; + + if (!ASSERT_EQ(skel->data->sndbuf_getsockopt[i], + skel->bss->sndbuf_getsockopt_expected[i], + "bpf_(get|set)sockopt")) + return; + } +} + +void test_bpf_iter_setsockopt_unix(void) +{ + struct bpf_iter_setsockopt_unix *skel; + int err, unix_fd, iter_fd; + char buf; + + skel = bpf_iter_setsockopt_unix__open_and_load(); + if (!ASSERT_OK_PTR(skel, "open_and_load")) + return; + + unix_fd = create_unix_socket(skel); + if (!ASSERT_NEQ(unix_fd, -1, "create_unix_server")) + goto destroy; + + skel->links.change_sndbuf = bpf_program__attach_iter(skel->progs.change_sndbuf, NULL); + if (!ASSERT_OK_PTR(skel->links.change_sndbuf, "bpf_program__attach_iter")) + goto destroy; + + iter_fd = bpf_iter_create(bpf_link__fd(skel->links.change_sndbuf)); + if (!ASSERT_GE(iter_fd, 0, "bpf_iter_create")) + goto destroy; + + while ((err = read(iter_fd, &buf, sizeof(buf))) == -1 && + errno == EAGAIN) + ; + if (!ASSERT_OK(err, "read iter error")) + goto destroy; + + test_sndbuf(skel, unix_fd); +destroy: + bpf_iter_setsockopt_unix__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_mod_race.c b/tools/testing/selftests/bpf/prog_tests/bpf_mod_race.c new file mode 100644 index 000000000000..d43f548c572c --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/bpf_mod_race.c @@ -0,0 +1,230 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <unistd.h> +#include <pthread.h> +#include <sys/mman.h> +#include <stdatomic.h> +#include <test_progs.h> +#include <sys/syscall.h> +#include <linux/module.h> +#include <linux/userfaultfd.h> + +#include "ksym_race.skel.h" +#include "bpf_mod_race.skel.h" +#include "kfunc_call_race.skel.h" + +/* This test crafts a race between btf_try_get_module and do_init_module, and + * checks whether btf_try_get_module handles the invocation for a well-formed + * but uninitialized module correctly. Unless the module has completed its + * initcalls, the verifier should fail the program load and return ENXIO. + * + * userfaultfd is used to trigger a fault in an fmod_ret program, and make it + * sleep, then the BPF program is loaded and the return value from verifier is + * inspected. After this, the userfaultfd is closed so that the module loading + * thread makes forward progress, and fmod_ret injects an error so that the + * module load fails and it is freed. + * + * If the verifier succeeded in loading the supplied program, it will end up + * taking reference to freed module, and trigger a crash when the program fd + * is closed later. This is true for both kfuncs and ksyms. In both cases, + * the crash is triggered inside bpf_prog_free_deferred, when module reference + * is finally released. + */ + +struct test_config { + const char *str_open; + void *(*bpf_open_and_load)(); + void (*bpf_destroy)(void *); +}; + +enum test_state { + _TS_INVALID, + TS_MODULE_LOAD, + TS_MODULE_LOAD_FAIL, +}; + +static _Atomic enum test_state state = _TS_INVALID; + +static int sys_finit_module(int fd, const char *param_values, int flags) +{ + return syscall(__NR_finit_module, fd, param_values, flags); +} + +static int sys_delete_module(const char *name, unsigned int flags) +{ + return syscall(__NR_delete_module, name, flags); +} + +static int load_module(const char *mod) +{ + int ret, fd; + + fd = open("bpf_testmod.ko", O_RDONLY); + if (fd < 0) + return fd; + + ret = sys_finit_module(fd, "", 0); + close(fd); + if (ret < 0) + return ret; + return 0; +} + +static void *load_module_thread(void *p) +{ + + if (!ASSERT_NEQ(load_module("bpf_testmod.ko"), 0, "load_module_thread must fail")) + atomic_store(&state, TS_MODULE_LOAD); + else + atomic_store(&state, TS_MODULE_LOAD_FAIL); + return p; +} + +static int sys_userfaultfd(int flags) +{ + return syscall(__NR_userfaultfd, flags); +} + +static int test_setup_uffd(void *fault_addr) +{ + struct uffdio_register uffd_register = {}; + struct uffdio_api uffd_api = {}; + int uffd; + + uffd = sys_userfaultfd(O_CLOEXEC); + if (uffd < 0) + return -errno; + + uffd_api.api = UFFD_API; + uffd_api.features = 0; + if (ioctl(uffd, UFFDIO_API, &uffd_api)) { + close(uffd); + return -1; + } + + uffd_register.range.start = (unsigned long)fault_addr; + uffd_register.range.len = 4096; + uffd_register.mode = UFFDIO_REGISTER_MODE_MISSING; + if (ioctl(uffd, UFFDIO_REGISTER, &uffd_register)) { + close(uffd); + return -1; + } + return uffd; +} + +static void test_bpf_mod_race_config(const struct test_config *config) +{ + void *fault_addr, *skel_fail; + struct bpf_mod_race *skel; + struct uffd_msg uffd_msg; + pthread_t load_mod_thrd; + _Atomic int *blockingp; + int uffd, ret; + + fault_addr = mmap(0, 4096, PROT_READ, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); + if (!ASSERT_NEQ(fault_addr, MAP_FAILED, "mmap for uffd registration")) + return; + + if (!ASSERT_OK(sys_delete_module("bpf_testmod", 0), "unload bpf_testmod")) + goto end_mmap; + + skel = bpf_mod_race__open(); + if (!ASSERT_OK_PTR(skel, "bpf_mod_kfunc_race__open")) + goto end_module; + + skel->rodata->bpf_mod_race_config.tgid = getpid(); + skel->rodata->bpf_mod_race_config.inject_error = -4242; + skel->rodata->bpf_mod_race_config.fault_addr = fault_addr; + if (!ASSERT_OK(bpf_mod_race__load(skel), "bpf_mod___load")) + goto end_destroy; + blockingp = (_Atomic int *)&skel->bss->bpf_blocking; + + if (!ASSERT_OK(bpf_mod_race__attach(skel), "bpf_mod_kfunc_race__attach")) + goto end_destroy; + + uffd = test_setup_uffd(fault_addr); + if (!ASSERT_GE(uffd, 0, "userfaultfd open + register address")) + goto end_destroy; + + if (!ASSERT_OK(pthread_create(&load_mod_thrd, NULL, load_module_thread, NULL), + "load module thread")) + goto end_uffd; + + /* Now, we either fail loading module, or block in bpf prog, spin to find out */ + while (!atomic_load(&state) && !atomic_load(blockingp)) + ; + if (!ASSERT_EQ(state, _TS_INVALID, "module load should block")) + goto end_join; + if (!ASSERT_EQ(*blockingp, 1, "module load blocked")) { + pthread_kill(load_mod_thrd, SIGKILL); + goto end_uffd; + } + + /* We might have set bpf_blocking to 1, but may have not blocked in + * bpf_copy_from_user. Read userfaultfd descriptor to verify that. + */ + if (!ASSERT_EQ(read(uffd, &uffd_msg, sizeof(uffd_msg)), sizeof(uffd_msg), + "read uffd block event")) + goto end_join; + if (!ASSERT_EQ(uffd_msg.event, UFFD_EVENT_PAGEFAULT, "read uffd event is pagefault")) + goto end_join; + + /* We know that load_mod_thrd is blocked in the fmod_ret program, the + * module state is still MODULE_STATE_COMING because mod->init hasn't + * returned. This is the time we try to load a program calling kfunc and + * check if we get ENXIO from verifier. + */ + skel_fail = config->bpf_open_and_load(); + ret = errno; + if (!ASSERT_EQ(skel_fail, NULL, config->str_open)) { + /* Close uffd to unblock load_mod_thrd */ + close(uffd); + uffd = -1; + while (atomic_load(blockingp) != 2) + ; + ASSERT_OK(kern_sync_rcu(), "kern_sync_rcu"); + config->bpf_destroy(skel_fail); + goto end_join; + + } + ASSERT_EQ(ret, ENXIO, "verifier returns ENXIO"); + ASSERT_EQ(skel->data->res_try_get_module, false, "btf_try_get_module == false"); + + close(uffd); + uffd = -1; +end_join: + pthread_join(load_mod_thrd, NULL); + if (uffd < 0) + ASSERT_EQ(atomic_load(&state), TS_MODULE_LOAD_FAIL, "load_mod_thrd success"); +end_uffd: + if (uffd >= 0) + close(uffd); +end_destroy: + bpf_mod_race__destroy(skel); + ASSERT_OK(kern_sync_rcu(), "kern_sync_rcu"); +end_module: + sys_delete_module("bpf_testmod", 0); + ASSERT_OK(load_module("bpf_testmod.ko"), "restore bpf_testmod"); +end_mmap: + munmap(fault_addr, 4096); + atomic_store(&state, _TS_INVALID); +} + +static const struct test_config ksym_config = { + .str_open = "ksym_race__open_and_load", + .bpf_open_and_load = (void *)ksym_race__open_and_load, + .bpf_destroy = (void *)ksym_race__destroy, +}; + +static const struct test_config kfunc_config = { + .str_open = "kfunc_call_race__open_and_load", + .bpf_open_and_load = (void *)kfunc_call_race__open_and_load, + .bpf_destroy = (void *)kfunc_call_race__destroy, +}; + +void serial_test_bpf_mod_race(void) +{ + if (test__start_subtest("ksym (used_btfs UAF)")) + test_bpf_mod_race_config(&ksym_config); + if (test__start_subtest("kfunc (kfunc_btf_tab UAF)")) + test_bpf_mod_race_config(&kfunc_config); +} diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_nf.c b/tools/testing/selftests/bpf/prog_tests/bpf_nf.c new file mode 100644 index 000000000000..dd30b1e3a67c --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/bpf_nf.c @@ -0,0 +1,52 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <test_progs.h> +#include <network_helpers.h> +#include "test_bpf_nf.skel.h" + +enum { + TEST_XDP, + TEST_TC_BPF, +}; + +void test_bpf_nf_ct(int mode) +{ + struct test_bpf_nf *skel; + int prog_fd, err; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .repeat = 1, + ); + + skel = test_bpf_nf__open_and_load(); + if (!ASSERT_OK_PTR(skel, "test_bpf_nf__open_and_load")) + return; + + if (mode == TEST_XDP) + prog_fd = bpf_program__fd(skel->progs.nf_xdp_ct_test); + else + prog_fd = bpf_program__fd(skel->progs.nf_skb_ct_test); + + err = bpf_prog_test_run_opts(prog_fd, &topts); + if (!ASSERT_OK(err, "bpf_prog_test_run")) + goto end; + + ASSERT_EQ(skel->bss->test_einval_bpf_tuple, -EINVAL, "Test EINVAL for NULL bpf_tuple"); + ASSERT_EQ(skel->bss->test_einval_reserved, -EINVAL, "Test EINVAL for reserved not set to 0"); + ASSERT_EQ(skel->bss->test_einval_netns_id, -EINVAL, "Test EINVAL for netns_id < -1"); + ASSERT_EQ(skel->bss->test_einval_len_opts, -EINVAL, "Test EINVAL for len__opts != NF_BPF_CT_OPTS_SZ"); + ASSERT_EQ(skel->bss->test_eproto_l4proto, -EPROTO, "Test EPROTO for l4proto != TCP or UDP"); + ASSERT_EQ(skel->bss->test_enonet_netns_id, -ENONET, "Test ENONET for bad but valid netns_id"); + ASSERT_EQ(skel->bss->test_enoent_lookup, -ENOENT, "Test ENOENT for failed lookup"); + ASSERT_EQ(skel->bss->test_eafnosupport, -EAFNOSUPPORT, "Test EAFNOSUPPORT for invalid len__tuple"); +end: + test_bpf_nf__destroy(skel); +} + +void test_bpf_nf(void) +{ + if (test__start_subtest("xdp-ct")) + test_bpf_nf_ct(TEST_XDP); + if (test__start_subtest("tc-bpf-ct")) + test_bpf_nf_ct(TEST_TC_BPF); +} diff --git a/tools/testing/selftests/bpf/prog_tests/btf.c b/tools/testing/selftests/bpf/prog_tests/btf.c index 8ba53acf9eb4..ec823561b912 100644 --- a/tools/testing/selftests/bpf/prog_tests/btf.c +++ b/tools/testing/selftests/bpf/prog_tests/btf.c @@ -3939,6 +3939,25 @@ static struct btf_raw_test raw_tests[] = { .err_str = "Invalid component_idx", }, { + .descr = "decl_tag test #15, func, invalid func proto", + .raw_types = { + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_DECL_TAG_ENC(NAME_TBD, 3, 0), /* [2] */ + BTF_FUNC_ENC(NAME_TBD, 8), /* [3] */ + BTF_END_RAW, + }, + BTF_STR_SEC("\0tag\0func"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "tag_type_check_btf", + .key_size = sizeof(int), + .value_size = 4, + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 1, + .btf_load_err = true, + .err_str = "Invalid type_id", +}, +{ .descr = "type_tag test #1", .raw_types = { BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ @@ -4560,6 +4579,8 @@ static void do_test_file(unsigned int test_num) has_btf_ext = btf_ext != NULL; btf_ext__free(btf_ext); + /* temporary disable LIBBPF_STRICT_MAP_DEFINITIONS to test legacy maps */ + libbpf_set_strict_mode(LIBBPF_STRICT_ALL & ~LIBBPF_STRICT_MAP_DEFINITIONS); obj = bpf_object__open(test->file); err = libbpf_get_error(obj); if (CHECK(err, "obj: %d", err)) @@ -4684,6 +4705,8 @@ skip: fprintf(stderr, "OK"); done: + libbpf_set_strict_mode(LIBBPF_STRICT_ALL); + btf__free(btf); free(func_info); bpf_object__close(obj); @@ -6533,7 +6556,7 @@ done: static void do_test_info_raw(unsigned int test_num) { const struct prog_info_raw_test *test = &info_raw_tests[test_num - 1]; - unsigned int raw_btf_size, linfo_str_off, linfo_size; + unsigned int raw_btf_size, linfo_str_off, linfo_size = 0; int btf_fd = -1, prog_fd = -1, err = 0; void *raw_btf, *patched_linfo = NULL; const char *ret_next_str; diff --git a/tools/testing/selftests/bpf/prog_tests/btf_dump.c b/tools/testing/selftests/bpf/prog_tests/btf_dump.c index 9e26903f9170..5fce7008d1ff 100644 --- a/tools/testing/selftests/bpf/prog_tests/btf_dump.c +++ b/tools/testing/selftests/bpf/prog_tests/btf_dump.c @@ -148,22 +148,38 @@ static void test_btf_dump_incremental(void) /* First, generate BTF corresponding to the following C code: * - * enum { VAL = 1 }; + * enum x; + * + * enum x { X = 1 }; + * + * enum { Y = 1 }; + * + * struct s; * * struct s { int x; }; * */ + id = btf__add_enum(btf, "x", 4); + ASSERT_EQ(id, 1, "enum_declaration_id"); + id = btf__add_enum(btf, "x", 4); + ASSERT_EQ(id, 2, "named_enum_id"); + err = btf__add_enum_value(btf, "X", 1); + ASSERT_OK(err, "named_enum_val_ok"); + id = btf__add_enum(btf, NULL, 4); - ASSERT_EQ(id, 1, "enum_id"); - err = btf__add_enum_value(btf, "VAL", 1); - ASSERT_OK(err, "enum_val_ok"); + ASSERT_EQ(id, 3, "anon_enum_id"); + err = btf__add_enum_value(btf, "Y", 1); + ASSERT_OK(err, "anon_enum_val_ok"); id = btf__add_int(btf, "int", 4, BTF_INT_SIGNED); - ASSERT_EQ(id, 2, "int_id"); + ASSERT_EQ(id, 4, "int_id"); + + id = btf__add_fwd(btf, "s", BTF_FWD_STRUCT); + ASSERT_EQ(id, 5, "fwd_id"); id = btf__add_struct(btf, "s", 4); - ASSERT_EQ(id, 3, "struct_id"); - err = btf__add_field(btf, "x", 2, 0, 0); + ASSERT_EQ(id, 6, "struct_id"); + err = btf__add_field(btf, "x", 4, 0, 0); ASSERT_OK(err, "field_ok"); for (i = 1; i < btf__type_cnt(btf); i++) { @@ -173,11 +189,20 @@ static void test_btf_dump_incremental(void) fflush(dump_buf_file); dump_buf[dump_buf_sz] = 0; /* some libc implementations don't do this */ + ASSERT_STREQ(dump_buf, +"enum x;\n" +"\n" +"enum x {\n" +" X = 1,\n" +"};\n" +"\n" "enum {\n" -" VAL = 1,\n" +" Y = 1,\n" "};\n" "\n" +"struct s;\n" +"\n" "struct s {\n" " int x;\n" "};\n\n", "c_dump1"); @@ -199,10 +224,12 @@ static void test_btf_dump_incremental(void) fseek(dump_buf_file, 0, SEEK_SET); id = btf__add_struct(btf, "s", 4); - ASSERT_EQ(id, 4, "struct_id"); - err = btf__add_field(btf, "x", 1, 0, 0); + ASSERT_EQ(id, 7, "struct_id"); + err = btf__add_field(btf, "x", 2, 0, 0); + ASSERT_OK(err, "field_ok"); + err = btf__add_field(btf, "y", 3, 32, 0); ASSERT_OK(err, "field_ok"); - err = btf__add_field(btf, "s", 3, 32, 0); + err = btf__add_field(btf, "s", 6, 64, 0); ASSERT_OK(err, "field_ok"); for (i = 1; i < btf__type_cnt(btf); i++) { @@ -214,9 +241,10 @@ static void test_btf_dump_incremental(void) dump_buf[dump_buf_sz] = 0; /* some libc implementations don't do this */ ASSERT_STREQ(dump_buf, "struct s___2 {\n" +" enum x x;\n" " enum {\n" -" VAL___2 = 1,\n" -" } x;\n" +" Y___2 = 1,\n" +" } y;\n" " struct s s;\n" "};\n\n" , "c_dump1"); diff --git a/tools/testing/selftests/bpf/prog_tests/btf_tag.c b/tools/testing/selftests/bpf/prog_tests/btf_tag.c index 88d63e23e35f..071430cd54de 100644 --- a/tools/testing/selftests/bpf/prog_tests/btf_tag.c +++ b/tools/testing/selftests/bpf/prog_tests/btf_tag.c @@ -1,19 +1,22 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2021 Facebook */ #include <test_progs.h> -#include "btf_decl_tag.skel.h" +#include <bpf/btf.h> +#include "test_btf_decl_tag.skel.h" /* struct btf_type_tag_test is referenced in btf_type_tag.skel.h */ struct btf_type_tag_test { int **p; }; #include "btf_type_tag.skel.h" +#include "btf_type_tag_user.skel.h" +#include "btf_type_tag_percpu.skel.h" static void test_btf_decl_tag(void) { - struct btf_decl_tag *skel; + struct test_btf_decl_tag *skel; - skel = btf_decl_tag__open_and_load(); + skel = test_btf_decl_tag__open_and_load(); if (!ASSERT_OK_PTR(skel, "btf_decl_tag")) return; @@ -22,7 +25,7 @@ static void test_btf_decl_tag(void) test__skip(); } - btf_decl_tag__destroy(skel); + test_btf_decl_tag__destroy(skel); } static void test_btf_type_tag(void) @@ -41,10 +44,206 @@ static void test_btf_type_tag(void) btf_type_tag__destroy(skel); } +/* loads vmlinux_btf as well as module_btf. If the caller passes NULL as + * module_btf, it will not load module btf. + * + * Returns 0 on success. + * Return -1 On error. In case of error, the loaded btf will be freed and the + * input parameters will be set to pointing to NULL. + */ +static int load_btfs(struct btf **vmlinux_btf, struct btf **module_btf, + bool needs_vmlinux_tag) +{ + const char *module_name = "bpf_testmod"; + __s32 type_id; + + if (!env.has_testmod) { + test__skip(); + return -1; + } + + *vmlinux_btf = btf__load_vmlinux_btf(); + if (!ASSERT_OK_PTR(*vmlinux_btf, "could not load vmlinux BTF")) + return -1; + + if (!needs_vmlinux_tag) + goto load_module_btf; + + /* skip the test if the vmlinux does not have __user tags */ + type_id = btf__find_by_name_kind(*vmlinux_btf, "user", BTF_KIND_TYPE_TAG); + if (type_id <= 0) { + printf("%s:SKIP: btf_type_tag attribute not in vmlinux btf", __func__); + test__skip(); + goto free_vmlinux_btf; + } + +load_module_btf: + /* skip loading module_btf, if not requested by caller */ + if (!module_btf) + return 0; + + *module_btf = btf__load_module_btf(module_name, *vmlinux_btf); + if (!ASSERT_OK_PTR(*module_btf, "could not load module BTF")) + goto free_vmlinux_btf; + + /* skip the test if the module does not have __user tags */ + type_id = btf__find_by_name_kind(*module_btf, "user", BTF_KIND_TYPE_TAG); + if (type_id <= 0) { + printf("%s:SKIP: btf_type_tag attribute not in %s", __func__, module_name); + test__skip(); + goto free_module_btf; + } + + return 0; + +free_module_btf: + btf__free(*module_btf); +free_vmlinux_btf: + btf__free(*vmlinux_btf); + + *vmlinux_btf = NULL; + if (module_btf) + *module_btf = NULL; + return -1; +} + +static void test_btf_type_tag_mod_user(bool load_test_user1) +{ + struct btf *vmlinux_btf = NULL, *module_btf = NULL; + struct btf_type_tag_user *skel; + int err; + + if (load_btfs(&vmlinux_btf, &module_btf, /*needs_vmlinux_tag=*/false)) + return; + + skel = btf_type_tag_user__open(); + if (!ASSERT_OK_PTR(skel, "btf_type_tag_user")) + goto cleanup; + + bpf_program__set_autoload(skel->progs.test_sys_getsockname, false); + if (load_test_user1) + bpf_program__set_autoload(skel->progs.test_user2, false); + else + bpf_program__set_autoload(skel->progs.test_user1, false); + + err = btf_type_tag_user__load(skel); + ASSERT_ERR(err, "btf_type_tag_user"); + + btf_type_tag_user__destroy(skel); + +cleanup: + btf__free(module_btf); + btf__free(vmlinux_btf); +} + +static void test_btf_type_tag_vmlinux_user(void) +{ + struct btf_type_tag_user *skel; + struct btf *vmlinux_btf = NULL; + int err; + + if (load_btfs(&vmlinux_btf, NULL, /*needs_vmlinux_tag=*/true)) + return; + + skel = btf_type_tag_user__open(); + if (!ASSERT_OK_PTR(skel, "btf_type_tag_user")) + goto cleanup; + + bpf_program__set_autoload(skel->progs.test_user2, false); + bpf_program__set_autoload(skel->progs.test_user1, false); + + err = btf_type_tag_user__load(skel); + ASSERT_ERR(err, "btf_type_tag_user"); + + btf_type_tag_user__destroy(skel); + +cleanup: + btf__free(vmlinux_btf); +} + +static void test_btf_type_tag_mod_percpu(bool load_test_percpu1) +{ + struct btf *vmlinux_btf, *module_btf; + struct btf_type_tag_percpu *skel; + int err; + + if (load_btfs(&vmlinux_btf, &module_btf, /*needs_vmlinux_tag=*/false)) + return; + + skel = btf_type_tag_percpu__open(); + if (!ASSERT_OK_PTR(skel, "btf_type_tag_percpu")) + goto cleanup; + + bpf_program__set_autoload(skel->progs.test_percpu_load, false); + bpf_program__set_autoload(skel->progs.test_percpu_helper, false); + if (load_test_percpu1) + bpf_program__set_autoload(skel->progs.test_percpu2, false); + else + bpf_program__set_autoload(skel->progs.test_percpu1, false); + + err = btf_type_tag_percpu__load(skel); + ASSERT_ERR(err, "btf_type_tag_percpu"); + + btf_type_tag_percpu__destroy(skel); + +cleanup: + btf__free(module_btf); + btf__free(vmlinux_btf); +} + +static void test_btf_type_tag_vmlinux_percpu(bool load_test) +{ + struct btf_type_tag_percpu *skel; + struct btf *vmlinux_btf = NULL; + int err; + + if (load_btfs(&vmlinux_btf, NULL, /*needs_vmlinux_tag=*/true)) + return; + + skel = btf_type_tag_percpu__open(); + if (!ASSERT_OK_PTR(skel, "btf_type_tag_percpu")) + goto cleanup; + + bpf_program__set_autoload(skel->progs.test_percpu2, false); + bpf_program__set_autoload(skel->progs.test_percpu1, false); + if (load_test) { + bpf_program__set_autoload(skel->progs.test_percpu_helper, false); + + err = btf_type_tag_percpu__load(skel); + ASSERT_ERR(err, "btf_type_tag_percpu_load"); + } else { + bpf_program__set_autoload(skel->progs.test_percpu_load, false); + + err = btf_type_tag_percpu__load(skel); + ASSERT_OK(err, "btf_type_tag_percpu_helper"); + } + + btf_type_tag_percpu__destroy(skel); + +cleanup: + btf__free(vmlinux_btf); +} + void test_btf_tag(void) { if (test__start_subtest("btf_decl_tag")) test_btf_decl_tag(); if (test__start_subtest("btf_type_tag")) test_btf_type_tag(); + + if (test__start_subtest("btf_type_tag_user_mod1")) + test_btf_type_tag_mod_user(true); + if (test__start_subtest("btf_type_tag_user_mod2")) + test_btf_type_tag_mod_user(false); + if (test__start_subtest("btf_type_tag_sys_user_vmlinux")) + test_btf_type_tag_vmlinux_user(); + + if (test__start_subtest("btf_type_tag_percpu_mod1")) + test_btf_type_tag_mod_percpu(true); + if (test__start_subtest("btf_type_tag_percpu_mod2")) + test_btf_type_tag_mod_percpu(false); + if (test__start_subtest("btf_type_tag_percpu_vmlinux_load")) + test_btf_type_tag_vmlinux_percpu(true); + if (test__start_subtest("btf_type_tag_percpu_vmlinux_helper")) + test_btf_type_tag_vmlinux_percpu(false); } diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_attach_autodetach.c b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_autodetach.c index 858916d11e2e..9367bd2f0ae1 100644 --- a/tools/testing/selftests/bpf/prog_tests/cgroup_attach_autodetach.c +++ b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_autodetach.c @@ -14,7 +14,7 @@ static int prog_load(void) BPF_MOV64_IMM(BPF_REG_0, 1), /* r0 = 1 */ BPF_EXIT_INSN(), }; - size_t insns_cnt = sizeof(prog) / sizeof(struct bpf_insn); + size_t insns_cnt = ARRAY_SIZE(prog); return bpf_test_load_program(BPF_PROG_TYPE_CGROUP_SKB, prog, insns_cnt, "GPL", 0, diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_attach_multi.c b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_multi.c index d3e8f729c623..db0b7bac78d1 100644 --- a/tools/testing/selftests/bpf/prog_tests/cgroup_attach_multi.c +++ b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_multi.c @@ -63,7 +63,7 @@ static int prog_load_cnt(int verdict, int val) BPF_MOV64_IMM(BPF_REG_0, verdict), /* r0 = verdict */ BPF_EXIT_INSN(), }; - size_t insns_cnt = sizeof(prog) / sizeof(struct bpf_insn); + size_t insns_cnt = ARRAY_SIZE(prog); int ret; ret = bpf_test_load_program(BPF_PROG_TYPE_CGROUP_SKB, @@ -194,14 +194,14 @@ void serial_test_cgroup_attach_multi(void) attach_opts.flags = BPF_F_ALLOW_OVERRIDE | BPF_F_REPLACE; attach_opts.replace_prog_fd = allow_prog[0]; - if (CHECK(!bpf_prog_attach_xattr(allow_prog[6], cg1, + if (CHECK(!bpf_prog_attach_opts(allow_prog[6], cg1, BPF_CGROUP_INET_EGRESS, &attach_opts), "fail_prog_replace_override", "unexpected success\n")) goto err; CHECK_FAIL(errno != EINVAL); attach_opts.flags = BPF_F_REPLACE; - if (CHECK(!bpf_prog_attach_xattr(allow_prog[6], cg1, + if (CHECK(!bpf_prog_attach_opts(allow_prog[6], cg1, BPF_CGROUP_INET_EGRESS, &attach_opts), "fail_prog_replace_no_multi", "unexpected success\n")) goto err; @@ -209,7 +209,7 @@ void serial_test_cgroup_attach_multi(void) attach_opts.flags = BPF_F_ALLOW_MULTI | BPF_F_REPLACE; attach_opts.replace_prog_fd = -1; - if (CHECK(!bpf_prog_attach_xattr(allow_prog[6], cg1, + if (CHECK(!bpf_prog_attach_opts(allow_prog[6], cg1, BPF_CGROUP_INET_EGRESS, &attach_opts), "fail_prog_replace_bad_fd", "unexpected success\n")) goto err; @@ -217,7 +217,7 @@ void serial_test_cgroup_attach_multi(void) /* replacing a program that is not attached to cgroup should fail */ attach_opts.replace_prog_fd = allow_prog[3]; - if (CHECK(!bpf_prog_attach_xattr(allow_prog[6], cg1, + if (CHECK(!bpf_prog_attach_opts(allow_prog[6], cg1, BPF_CGROUP_INET_EGRESS, &attach_opts), "fail_prog_replace_no_ent", "unexpected success\n")) goto err; @@ -225,14 +225,14 @@ void serial_test_cgroup_attach_multi(void) /* replace 1st from the top program */ attach_opts.replace_prog_fd = allow_prog[0]; - if (CHECK(bpf_prog_attach_xattr(allow_prog[6], cg1, + if (CHECK(bpf_prog_attach_opts(allow_prog[6], cg1, BPF_CGROUP_INET_EGRESS, &attach_opts), "prog_replace", "errno=%d\n", errno)) goto err; /* replace program with itself */ attach_opts.replace_prog_fd = allow_prog[6]; - if (CHECK(bpf_prog_attach_xattr(allow_prog[6], cg1, + if (CHECK(bpf_prog_attach_opts(allow_prog[6], cg1, BPF_CGROUP_INET_EGRESS, &attach_opts), "prog_replace", "errno=%d\n", errno)) goto err; diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_attach_override.c b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_override.c index 356547e849e2..9421a5b7f4e1 100644 --- a/tools/testing/selftests/bpf/prog_tests/cgroup_attach_override.c +++ b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_override.c @@ -16,7 +16,7 @@ static int prog_load(int verdict) BPF_MOV64_IMM(BPF_REG_0, verdict), /* r0 = verdict */ BPF_EXIT_INSN(), }; - size_t insns_cnt = sizeof(prog) / sizeof(struct bpf_insn); + size_t insns_cnt = ARRAY_SIZE(prog); return bpf_test_load_program(BPF_PROG_TYPE_CGROUP_SKB, prog, insns_cnt, "GPL", 0, diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_getset_retval.c b/tools/testing/selftests/bpf/prog_tests/cgroup_getset_retval.c new file mode 100644 index 000000000000..0b47c3c000c7 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/cgroup_getset_retval.c @@ -0,0 +1,481 @@ +// SPDX-License-Identifier: GPL-2.0-only + +/* + * Copyright 2021 Google LLC. + */ + +#include <test_progs.h> +#include <cgroup_helpers.h> +#include <network_helpers.h> + +#include "cgroup_getset_retval_setsockopt.skel.h" +#include "cgroup_getset_retval_getsockopt.skel.h" + +#define SOL_CUSTOM 0xdeadbeef + +static int zero; + +static void test_setsockopt_set(int cgroup_fd, int sock_fd) +{ + struct cgroup_getset_retval_setsockopt *obj; + struct bpf_link *link_set_eunatch = NULL; + + obj = cgroup_getset_retval_setsockopt__open_and_load(); + if (!ASSERT_OK_PTR(obj, "skel-load")) + return; + + /* Attach setsockopt that sets EUNATCH, assert that + * we actually get that error when we run setsockopt() + */ + link_set_eunatch = bpf_program__attach_cgroup(obj->progs.set_eunatch, + cgroup_fd); + if (!ASSERT_OK_PTR(link_set_eunatch, "cg-attach-set_eunatch")) + goto close_bpf_object; + + if (!ASSERT_ERR(setsockopt(sock_fd, SOL_SOCKET, SO_REUSEADDR, + &zero, sizeof(int)), "setsockopt")) + goto close_bpf_object; + if (!ASSERT_EQ(errno, EUNATCH, "setsockopt-errno")) + goto close_bpf_object; + + if (!ASSERT_EQ(obj->bss->invocations, 1, "invocations")) + goto close_bpf_object; + if (!ASSERT_FALSE(obj->bss->assertion_error, "assertion_error")) + goto close_bpf_object; + +close_bpf_object: + bpf_link__destroy(link_set_eunatch); + + cgroup_getset_retval_setsockopt__destroy(obj); +} + +static void test_setsockopt_set_and_get(int cgroup_fd, int sock_fd) +{ + struct cgroup_getset_retval_setsockopt *obj; + struct bpf_link *link_set_eunatch = NULL, *link_get_retval = NULL; + + obj = cgroup_getset_retval_setsockopt__open_and_load(); + if (!ASSERT_OK_PTR(obj, "skel-load")) + return; + + /* Attach setsockopt that sets EUNATCH, and one that gets the + * previously set errno. Assert that we get the same errno back. + */ + link_set_eunatch = bpf_program__attach_cgroup(obj->progs.set_eunatch, + cgroup_fd); + if (!ASSERT_OK_PTR(link_set_eunatch, "cg-attach-set_eunatch")) + goto close_bpf_object; + link_get_retval = bpf_program__attach_cgroup(obj->progs.get_retval, + cgroup_fd); + if (!ASSERT_OK_PTR(link_get_retval, "cg-attach-get_retval")) + goto close_bpf_object; + + if (!ASSERT_ERR(setsockopt(sock_fd, SOL_SOCKET, SO_REUSEADDR, + &zero, sizeof(int)), "setsockopt")) + goto close_bpf_object; + if (!ASSERT_EQ(errno, EUNATCH, "setsockopt-errno")) + goto close_bpf_object; + + if (!ASSERT_EQ(obj->bss->invocations, 2, "invocations")) + goto close_bpf_object; + if (!ASSERT_FALSE(obj->bss->assertion_error, "assertion_error")) + goto close_bpf_object; + if (!ASSERT_EQ(obj->bss->retval_value, -EUNATCH, "retval_value")) + goto close_bpf_object; + +close_bpf_object: + bpf_link__destroy(link_set_eunatch); + bpf_link__destroy(link_get_retval); + + cgroup_getset_retval_setsockopt__destroy(obj); +} + +static void test_setsockopt_default_zero(int cgroup_fd, int sock_fd) +{ + struct cgroup_getset_retval_setsockopt *obj; + struct bpf_link *link_get_retval = NULL; + + obj = cgroup_getset_retval_setsockopt__open_and_load(); + if (!ASSERT_OK_PTR(obj, "skel-load")) + return; + + /* Attach setsockopt that gets the previously set errno. + * Assert that, without anything setting one, we get 0. + */ + link_get_retval = bpf_program__attach_cgroup(obj->progs.get_retval, + cgroup_fd); + if (!ASSERT_OK_PTR(link_get_retval, "cg-attach-get_retval")) + goto close_bpf_object; + + if (!ASSERT_OK(setsockopt(sock_fd, SOL_SOCKET, SO_REUSEADDR, + &zero, sizeof(int)), "setsockopt")) + goto close_bpf_object; + + if (!ASSERT_EQ(obj->bss->invocations, 1, "invocations")) + goto close_bpf_object; + if (!ASSERT_FALSE(obj->bss->assertion_error, "assertion_error")) + goto close_bpf_object; + if (!ASSERT_EQ(obj->bss->retval_value, 0, "retval_value")) + goto close_bpf_object; + +close_bpf_object: + bpf_link__destroy(link_get_retval); + + cgroup_getset_retval_setsockopt__destroy(obj); +} + +static void test_setsockopt_default_zero_and_set(int cgroup_fd, int sock_fd) +{ + struct cgroup_getset_retval_setsockopt *obj; + struct bpf_link *link_get_retval = NULL, *link_set_eunatch = NULL; + + obj = cgroup_getset_retval_setsockopt__open_and_load(); + if (!ASSERT_OK_PTR(obj, "skel-load")) + return; + + /* Attach setsockopt that gets the previously set errno, and then + * one that sets the errno to EUNATCH. Assert that the get does not + * see EUNATCH set later, and does not prevent EUNATCH from being set. + */ + link_get_retval = bpf_program__attach_cgroup(obj->progs.get_retval, + cgroup_fd); + if (!ASSERT_OK_PTR(link_get_retval, "cg-attach-get_retval")) + goto close_bpf_object; + link_set_eunatch = bpf_program__attach_cgroup(obj->progs.set_eunatch, + cgroup_fd); + if (!ASSERT_OK_PTR(link_set_eunatch, "cg-attach-set_eunatch")) + goto close_bpf_object; + + if (!ASSERT_ERR(setsockopt(sock_fd, SOL_SOCKET, SO_REUSEADDR, + &zero, sizeof(int)), "setsockopt")) + goto close_bpf_object; + if (!ASSERT_EQ(errno, EUNATCH, "setsockopt-errno")) + goto close_bpf_object; + + if (!ASSERT_EQ(obj->bss->invocations, 2, "invocations")) + goto close_bpf_object; + if (!ASSERT_FALSE(obj->bss->assertion_error, "assertion_error")) + goto close_bpf_object; + if (!ASSERT_EQ(obj->bss->retval_value, 0, "retval_value")) + goto close_bpf_object; + +close_bpf_object: + bpf_link__destroy(link_get_retval); + bpf_link__destroy(link_set_eunatch); + + cgroup_getset_retval_setsockopt__destroy(obj); +} + +static void test_setsockopt_override(int cgroup_fd, int sock_fd) +{ + struct cgroup_getset_retval_setsockopt *obj; + struct bpf_link *link_set_eunatch = NULL, *link_set_eisconn = NULL; + struct bpf_link *link_get_retval = NULL; + + obj = cgroup_getset_retval_setsockopt__open_and_load(); + if (!ASSERT_OK_PTR(obj, "skel-load")) + return; + + /* Attach setsockopt that sets EUNATCH, then one that sets EISCONN, + * and then one that gets the exported errno. Assert both the syscall + * and the helper sees the last set errno. + */ + link_set_eunatch = bpf_program__attach_cgroup(obj->progs.set_eunatch, + cgroup_fd); + if (!ASSERT_OK_PTR(link_set_eunatch, "cg-attach-set_eunatch")) + goto close_bpf_object; + link_set_eisconn = bpf_program__attach_cgroup(obj->progs.set_eisconn, + cgroup_fd); + if (!ASSERT_OK_PTR(link_set_eisconn, "cg-attach-set_eisconn")) + goto close_bpf_object; + link_get_retval = bpf_program__attach_cgroup(obj->progs.get_retval, + cgroup_fd); + if (!ASSERT_OK_PTR(link_get_retval, "cg-attach-get_retval")) + goto close_bpf_object; + + if (!ASSERT_ERR(setsockopt(sock_fd, SOL_SOCKET, SO_REUSEADDR, + &zero, sizeof(int)), "setsockopt")) + goto close_bpf_object; + if (!ASSERT_EQ(errno, EISCONN, "setsockopt-errno")) + goto close_bpf_object; + + if (!ASSERT_EQ(obj->bss->invocations, 3, "invocations")) + goto close_bpf_object; + if (!ASSERT_FALSE(obj->bss->assertion_error, "assertion_error")) + goto close_bpf_object; + if (!ASSERT_EQ(obj->bss->retval_value, -EISCONN, "retval_value")) + goto close_bpf_object; + +close_bpf_object: + bpf_link__destroy(link_set_eunatch); + bpf_link__destroy(link_set_eisconn); + bpf_link__destroy(link_get_retval); + + cgroup_getset_retval_setsockopt__destroy(obj); +} + +static void test_setsockopt_legacy_eperm(int cgroup_fd, int sock_fd) +{ + struct cgroup_getset_retval_setsockopt *obj; + struct bpf_link *link_legacy_eperm = NULL, *link_get_retval = NULL; + + obj = cgroup_getset_retval_setsockopt__open_and_load(); + if (!ASSERT_OK_PTR(obj, "skel-load")) + return; + + /* Attach setsockopt that return a reject without setting errno + * (legacy reject), and one that gets the errno. Assert that for + * backward compatibility the syscall result in EPERM, and this + * is also visible to the helper. + */ + link_legacy_eperm = bpf_program__attach_cgroup(obj->progs.legacy_eperm, + cgroup_fd); + if (!ASSERT_OK_PTR(link_legacy_eperm, "cg-attach-legacy_eperm")) + goto close_bpf_object; + link_get_retval = bpf_program__attach_cgroup(obj->progs.get_retval, + cgroup_fd); + if (!ASSERT_OK_PTR(link_get_retval, "cg-attach-get_retval")) + goto close_bpf_object; + + if (!ASSERT_ERR(setsockopt(sock_fd, SOL_SOCKET, SO_REUSEADDR, + &zero, sizeof(int)), "setsockopt")) + goto close_bpf_object; + if (!ASSERT_EQ(errno, EPERM, "setsockopt-errno")) + goto close_bpf_object; + + if (!ASSERT_EQ(obj->bss->invocations, 2, "invocations")) + goto close_bpf_object; + if (!ASSERT_FALSE(obj->bss->assertion_error, "assertion_error")) + goto close_bpf_object; + if (!ASSERT_EQ(obj->bss->retval_value, -EPERM, "retval_value")) + goto close_bpf_object; + +close_bpf_object: + bpf_link__destroy(link_legacy_eperm); + bpf_link__destroy(link_get_retval); + + cgroup_getset_retval_setsockopt__destroy(obj); +} + +static void test_setsockopt_legacy_no_override(int cgroup_fd, int sock_fd) +{ + struct cgroup_getset_retval_setsockopt *obj; + struct bpf_link *link_set_eunatch = NULL, *link_legacy_eperm = NULL; + struct bpf_link *link_get_retval = NULL; + + obj = cgroup_getset_retval_setsockopt__open_and_load(); + if (!ASSERT_OK_PTR(obj, "skel-load")) + return; + + /* Attach setsockopt that sets EUNATCH, then one that return a reject + * without setting errno, and then one that gets the exported errno. + * Assert both the syscall and the helper's errno are unaffected by + * the second prog (i.e. legacy rejects does not override the errno + * to EPERM). + */ + link_set_eunatch = bpf_program__attach_cgroup(obj->progs.set_eunatch, + cgroup_fd); + if (!ASSERT_OK_PTR(link_set_eunatch, "cg-attach-set_eunatch")) + goto close_bpf_object; + link_legacy_eperm = bpf_program__attach_cgroup(obj->progs.legacy_eperm, + cgroup_fd); + if (!ASSERT_OK_PTR(link_legacy_eperm, "cg-attach-legacy_eperm")) + goto close_bpf_object; + link_get_retval = bpf_program__attach_cgroup(obj->progs.get_retval, + cgroup_fd); + if (!ASSERT_OK_PTR(link_get_retval, "cg-attach-get_retval")) + goto close_bpf_object; + + if (!ASSERT_ERR(setsockopt(sock_fd, SOL_SOCKET, SO_REUSEADDR, + &zero, sizeof(int)), "setsockopt")) + goto close_bpf_object; + if (!ASSERT_EQ(errno, EUNATCH, "setsockopt-errno")) + goto close_bpf_object; + + if (!ASSERT_EQ(obj->bss->invocations, 3, "invocations")) + goto close_bpf_object; + if (!ASSERT_FALSE(obj->bss->assertion_error, "assertion_error")) + goto close_bpf_object; + if (!ASSERT_EQ(obj->bss->retval_value, -EUNATCH, "retval_value")) + goto close_bpf_object; + +close_bpf_object: + bpf_link__destroy(link_set_eunatch); + bpf_link__destroy(link_legacy_eperm); + bpf_link__destroy(link_get_retval); + + cgroup_getset_retval_setsockopt__destroy(obj); +} + +static void test_getsockopt_get(int cgroup_fd, int sock_fd) +{ + struct cgroup_getset_retval_getsockopt *obj; + struct bpf_link *link_get_retval = NULL; + int buf; + socklen_t optlen = sizeof(buf); + + obj = cgroup_getset_retval_getsockopt__open_and_load(); + if (!ASSERT_OK_PTR(obj, "skel-load")) + return; + + /* Attach getsockopt that gets previously set errno. Assert that the + * error from kernel is in both ctx_retval_value and retval_value. + */ + link_get_retval = bpf_program__attach_cgroup(obj->progs.get_retval, + cgroup_fd); + if (!ASSERT_OK_PTR(link_get_retval, "cg-attach-get_retval")) + goto close_bpf_object; + + if (!ASSERT_ERR(getsockopt(sock_fd, SOL_CUSTOM, 0, + &buf, &optlen), "getsockopt")) + goto close_bpf_object; + if (!ASSERT_EQ(errno, EOPNOTSUPP, "getsockopt-errno")) + goto close_bpf_object; + + if (!ASSERT_EQ(obj->bss->invocations, 1, "invocations")) + goto close_bpf_object; + if (!ASSERT_FALSE(obj->bss->assertion_error, "assertion_error")) + goto close_bpf_object; + if (!ASSERT_EQ(obj->bss->retval_value, -EOPNOTSUPP, "retval_value")) + goto close_bpf_object; + if (!ASSERT_EQ(obj->bss->ctx_retval_value, -EOPNOTSUPP, "ctx_retval_value")) + goto close_bpf_object; + +close_bpf_object: + bpf_link__destroy(link_get_retval); + + cgroup_getset_retval_getsockopt__destroy(obj); +} + +static void test_getsockopt_override(int cgroup_fd, int sock_fd) +{ + struct cgroup_getset_retval_getsockopt *obj; + struct bpf_link *link_set_eisconn = NULL; + int buf; + socklen_t optlen = sizeof(buf); + + obj = cgroup_getset_retval_getsockopt__open_and_load(); + if (!ASSERT_OK_PTR(obj, "skel-load")) + return; + + /* Attach getsockopt that sets retval to -EISCONN. Assert that this + * overrides the value from kernel. + */ + link_set_eisconn = bpf_program__attach_cgroup(obj->progs.set_eisconn, + cgroup_fd); + if (!ASSERT_OK_PTR(link_set_eisconn, "cg-attach-set_eisconn")) + goto close_bpf_object; + + if (!ASSERT_ERR(getsockopt(sock_fd, SOL_CUSTOM, 0, + &buf, &optlen), "getsockopt")) + goto close_bpf_object; + if (!ASSERT_EQ(errno, EISCONN, "getsockopt-errno")) + goto close_bpf_object; + + if (!ASSERT_EQ(obj->bss->invocations, 1, "invocations")) + goto close_bpf_object; + if (!ASSERT_FALSE(obj->bss->assertion_error, "assertion_error")) + goto close_bpf_object; + +close_bpf_object: + bpf_link__destroy(link_set_eisconn); + + cgroup_getset_retval_getsockopt__destroy(obj); +} + +static void test_getsockopt_retval_sync(int cgroup_fd, int sock_fd) +{ + struct cgroup_getset_retval_getsockopt *obj; + struct bpf_link *link_set_eisconn = NULL, *link_clear_retval = NULL; + struct bpf_link *link_get_retval = NULL; + int buf; + socklen_t optlen = sizeof(buf); + + obj = cgroup_getset_retval_getsockopt__open_and_load(); + if (!ASSERT_OK_PTR(obj, "skel-load")) + return; + + /* Attach getsockopt that sets retval to -EISCONN, and one that clears + * ctx retval. Assert that the clearing ctx retval is synced to helper + * and clears any errors both from kernel and BPF.. + */ + link_set_eisconn = bpf_program__attach_cgroup(obj->progs.set_eisconn, + cgroup_fd); + if (!ASSERT_OK_PTR(link_set_eisconn, "cg-attach-set_eisconn")) + goto close_bpf_object; + link_clear_retval = bpf_program__attach_cgroup(obj->progs.clear_retval, + cgroup_fd); + if (!ASSERT_OK_PTR(link_clear_retval, "cg-attach-clear_retval")) + goto close_bpf_object; + link_get_retval = bpf_program__attach_cgroup(obj->progs.get_retval, + cgroup_fd); + if (!ASSERT_OK_PTR(link_get_retval, "cg-attach-get_retval")) + goto close_bpf_object; + + if (!ASSERT_OK(getsockopt(sock_fd, SOL_CUSTOM, 0, + &buf, &optlen), "getsockopt")) + goto close_bpf_object; + + if (!ASSERT_EQ(obj->bss->invocations, 3, "invocations")) + goto close_bpf_object; + if (!ASSERT_FALSE(obj->bss->assertion_error, "assertion_error")) + goto close_bpf_object; + if (!ASSERT_EQ(obj->bss->retval_value, 0, "retval_value")) + goto close_bpf_object; + if (!ASSERT_EQ(obj->bss->ctx_retval_value, 0, "ctx_retval_value")) + goto close_bpf_object; + +close_bpf_object: + bpf_link__destroy(link_set_eisconn); + bpf_link__destroy(link_clear_retval); + bpf_link__destroy(link_get_retval); + + cgroup_getset_retval_getsockopt__destroy(obj); +} + +void test_cgroup_getset_retval(void) +{ + int cgroup_fd = -1; + int sock_fd = -1; + + cgroup_fd = test__join_cgroup("/cgroup_getset_retval"); + if (!ASSERT_GE(cgroup_fd, 0, "cg-create")) + goto close_fd; + + sock_fd = start_server(AF_INET, SOCK_DGRAM, NULL, 0, 0); + if (!ASSERT_GE(sock_fd, 0, "start-server")) + goto close_fd; + + if (test__start_subtest("setsockopt-set")) + test_setsockopt_set(cgroup_fd, sock_fd); + + if (test__start_subtest("setsockopt-set_and_get")) + test_setsockopt_set_and_get(cgroup_fd, sock_fd); + + if (test__start_subtest("setsockopt-default_zero")) + test_setsockopt_default_zero(cgroup_fd, sock_fd); + + if (test__start_subtest("setsockopt-default_zero_and_set")) + test_setsockopt_default_zero_and_set(cgroup_fd, sock_fd); + + if (test__start_subtest("setsockopt-override")) + test_setsockopt_override(cgroup_fd, sock_fd); + + if (test__start_subtest("setsockopt-legacy_eperm")) + test_setsockopt_legacy_eperm(cgroup_fd, sock_fd); + + if (test__start_subtest("setsockopt-legacy_no_override")) + test_setsockopt_legacy_no_override(cgroup_fd, sock_fd); + + if (test__start_subtest("getsockopt-get")) + test_getsockopt_get(cgroup_fd, sock_fd); + + if (test__start_subtest("getsockopt-override")) + test_getsockopt_override(cgroup_fd, sock_fd); + + if (test__start_subtest("getsockopt-retval_sync")) + test_getsockopt_retval_sync(cgroup_fd, sock_fd); + +close_fd: + close(cgroup_fd); +} diff --git a/tools/testing/selftests/bpf/prog_tests/check_mtu.c b/tools/testing/selftests/bpf/prog_tests/check_mtu.c index f73e6e36b74d..12f4395f18b3 100644 --- a/tools/testing/selftests/bpf/prog_tests/check_mtu.c +++ b/tools/testing/selftests/bpf/prog_tests/check_mtu.c @@ -79,28 +79,21 @@ static void test_check_mtu_run_xdp(struct test_check_mtu *skel, struct bpf_program *prog, __u32 mtu_expect) { - const char *prog_name = bpf_program__name(prog); int retval_expect = XDP_PASS; __u32 mtu_result = 0; char buf[256] = {}; - int err; - struct bpf_prog_test_run_attr tattr = { + int err, prog_fd = bpf_program__fd(prog); + LIBBPF_OPTS(bpf_test_run_opts, topts, .repeat = 1, .data_in = &pkt_v4, .data_size_in = sizeof(pkt_v4), .data_out = buf, .data_size_out = sizeof(buf), - .prog_fd = bpf_program__fd(prog), - }; - - err = bpf_prog_test_run_xattr(&tattr); - CHECK_ATTR(err != 0, "bpf_prog_test_run", - "prog_name:%s (err %d errno %d retval %d)\n", - prog_name, err, errno, tattr.retval); + ); - CHECK(tattr.retval != retval_expect, "retval", - "progname:%s unexpected retval=%d expected=%d\n", - prog_name, tattr.retval, retval_expect); + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "test_run"); + ASSERT_EQ(topts.retval, retval_expect, "retval"); /* Extract MTU that BPF-prog got */ mtu_result = skel->bss->global_bpf_mtu_xdp; @@ -139,28 +132,21 @@ static void test_check_mtu_run_tc(struct test_check_mtu *skel, struct bpf_program *prog, __u32 mtu_expect) { - const char *prog_name = bpf_program__name(prog); int retval_expect = BPF_OK; __u32 mtu_result = 0; char buf[256] = {}; - int err; - struct bpf_prog_test_run_attr tattr = { - .repeat = 1, + int err, prog_fd = bpf_program__fd(prog); + LIBBPF_OPTS(bpf_test_run_opts, topts, .data_in = &pkt_v4, .data_size_in = sizeof(pkt_v4), .data_out = buf, .data_size_out = sizeof(buf), - .prog_fd = bpf_program__fd(prog), - }; - - err = bpf_prog_test_run_xattr(&tattr); - CHECK_ATTR(err != 0, "bpf_prog_test_run", - "prog_name:%s (err %d errno %d retval %d)\n", - prog_name, err, errno, tattr.retval); + .repeat = 1, + ); - CHECK(tattr.retval != retval_expect, "retval", - "progname:%s unexpected retval=%d expected=%d\n", - prog_name, tattr.retval, retval_expect); + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "test_run"); + ASSERT_EQ(topts.retval, retval_expect, "retval"); /* Extract MTU that BPF-prog got */ mtu_result = skel->bss->global_bpf_mtu_tc; diff --git a/tools/testing/selftests/bpf/prog_tests/cls_redirect.c b/tools/testing/selftests/bpf/prog_tests/cls_redirect.c index e075d03ab630..224f016b0a53 100644 --- a/tools/testing/selftests/bpf/prog_tests/cls_redirect.c +++ b/tools/testing/selftests/bpf/prog_tests/cls_redirect.c @@ -161,7 +161,7 @@ static socklen_t prepare_addr(struct sockaddr_storage *addr, int family) } } -static bool was_decapsulated(struct bpf_prog_test_run_attr *tattr) +static bool was_decapsulated(struct bpf_test_run_opts *tattr) { return tattr->data_size_out < tattr->data_size_in; } @@ -367,12 +367,12 @@ static void close_fds(int *fds, int n) static void test_cls_redirect_common(struct bpf_program *prog) { - struct bpf_prog_test_run_attr tattr = {}; + LIBBPF_OPTS(bpf_test_run_opts, tattr); int families[] = { AF_INET, AF_INET6 }; struct sockaddr_storage ss; struct sockaddr *addr; socklen_t slen; - int i, j, err; + int i, j, err, prog_fd; int servers[__NR_KIND][ARRAY_SIZE(families)] = {}; int conns[__NR_KIND][ARRAY_SIZE(families)] = {}; struct tuple tuples[__NR_KIND][ARRAY_SIZE(families)]; @@ -394,7 +394,7 @@ static void test_cls_redirect_common(struct bpf_program *prog) goto cleanup; } - tattr.prog_fd = bpf_program__fd(prog); + prog_fd = bpf_program__fd(prog); for (i = 0; i < ARRAY_SIZE(tests); i++) { struct test_cfg *test = &tests[i]; @@ -415,7 +415,7 @@ static void test_cls_redirect_common(struct bpf_program *prog) if (CHECK_FAIL(!tattr.data_size_in)) continue; - err = bpf_prog_test_run_xattr(&tattr); + err = bpf_prog_test_run_opts(prog_fd, &tattr); if (CHECK_FAIL(err)) continue; diff --git a/tools/testing/selftests/bpf/prog_tests/core_kern.c b/tools/testing/selftests/bpf/prog_tests/core_kern.c index 561c5185d886..6a5a1c019a5d 100644 --- a/tools/testing/selftests/bpf/prog_tests/core_kern.c +++ b/tools/testing/selftests/bpf/prog_tests/core_kern.c @@ -7,8 +7,22 @@ void test_core_kern_lskel(void) { struct core_kern_lskel *skel; + int link_fd; skel = core_kern_lskel__open_and_load(); - ASSERT_OK_PTR(skel, "open_and_load"); + if (!ASSERT_OK_PTR(skel, "open_and_load")) + return; + + link_fd = core_kern_lskel__core_relo_proto__attach(skel); + if (!ASSERT_GT(link_fd, 0, "attach(core_relo_proto)")) + goto cleanup; + + /* trigger tracepoints */ + usleep(1); + ASSERT_TRUE(skel->bss->proto_out[0], "bpf_core_type_exists"); + ASSERT_FALSE(skel->bss->proto_out[1], "!bpf_core_type_exists"); + ASSERT_TRUE(skel->bss->proto_out[2], "bpf_core_type_exists. nested"); + +cleanup: core_kern_lskel__destroy(skel); } diff --git a/tools/testing/selftests/bpf/prog_tests/core_kern_overflow.c b/tools/testing/selftests/bpf/prog_tests/core_kern_overflow.c new file mode 100644 index 000000000000..04cc145bc26a --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/core_kern_overflow.c @@ -0,0 +1,13 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include "test_progs.h" +#include "core_kern_overflow.lskel.h" + +void test_core_kern_overflow_lskel(void) +{ + struct core_kern_overflow_lskel *skel; + + skel = core_kern_overflow_lskel__open_and_load(); + if (!ASSERT_NULL(skel, "open_and_load")) + core_kern_overflow_lskel__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/core_reloc.c b/tools/testing/selftests/bpf/prog_tests/core_reloc.c index b8bdd1c3efca..f28f75aa9154 100644 --- a/tools/testing/selftests/bpf/prog_tests/core_reloc.c +++ b/tools/testing/selftests/bpf/prog_tests/core_reloc.c @@ -2,6 +2,7 @@ #include <test_progs.h> #include "progs/core_reloc_types.h" #include "bpf_testmod/bpf_testmod.h" +#include <linux/limits.h> #include <sys/mman.h> #include <sys/syscall.h> #include <bpf/btf.h> @@ -511,7 +512,7 @@ static int __trigger_module_test_read(const struct core_reloc_test_case *test) } -static struct core_reloc_test_case test_cases[] = { +static const struct core_reloc_test_case test_cases[] = { /* validate we can find kernel image and use its BTF for relocs */ { .case_name = "kernel", @@ -836,13 +837,27 @@ static size_t roundup_page(size_t sz) return (sz + page_size - 1) / page_size * page_size; } -void test_core_reloc(void) +static int run_btfgen(const char *src_btf, const char *dst_btf, const char *objpath) +{ + char command[4096]; + int n; + + n = snprintf(command, sizeof(command), + "./bpftool gen min_core_btf %s %s %s", + src_btf, dst_btf, objpath); + if (n < 0 || n >= sizeof(command)) + return -1; + + return system(command); +} + +static void run_core_reloc_tests(bool use_btfgen) { const size_t mmap_sz = roundup_page(sizeof(struct data)); DECLARE_LIBBPF_OPTS(bpf_object_open_opts, open_opts); - struct core_reloc_test_case *test_case; + struct core_reloc_test_case *test_case, test_case_copy; const char *tp_name, *probe_name; - int err, i, equal; + int err, i, equal, fd; struct bpf_link *link = NULL; struct bpf_map *data_map; struct bpf_program *prog; @@ -854,7 +869,11 @@ void test_core_reloc(void) my_pid_tgid = getpid() | ((uint64_t)syscall(SYS_gettid) << 32); for (i = 0; i < ARRAY_SIZE(test_cases); i++) { - test_case = &test_cases[i]; + char btf_file[] = "/tmp/core_reloc.btf.XXXXXX"; + + test_case_copy = test_cases[i]; + test_case = &test_case_copy; + if (!test__start_subtest(test_case->case_name)) continue; @@ -863,6 +882,26 @@ void test_core_reloc(void) continue; } + /* generate a "minimal" BTF file and use it as source */ + if (use_btfgen) { + + if (!test_case->btf_src_file || test_case->fails) { + test__skip(); + continue; + } + + fd = mkstemp(btf_file); + if (!ASSERT_GE(fd, 0, "btf_tmp")) + continue; + close(fd); /* we only need the path */ + err = run_btfgen(test_case->btf_src_file, btf_file, + test_case->bpf_obj_file); + if (!ASSERT_OK(err, "run_btfgen")) + continue; + + test_case->btf_src_file = btf_file; + } + if (test_case->setup) { err = test_case->setup(test_case); if (CHECK(err, "test_setup", "test #%d setup failed: %d\n", i, err)) @@ -872,7 +911,7 @@ void test_core_reloc(void) if (test_case->btf_src_file) { err = access(test_case->btf_src_file, R_OK); if (!ASSERT_OK(err, "btf_src_file")) - goto cleanup; + continue; } open_opts.btf_custom_path = test_case->btf_src_file; @@ -954,8 +993,20 @@ cleanup: CHECK_FAIL(munmap(mmap_data, mmap_sz)); mmap_data = NULL; } + if (use_btfgen) + remove(test_case->btf_src_file); bpf_link__destroy(link); link = NULL; bpf_object__close(obj); } } + +void test_core_reloc(void) +{ + run_core_reloc_tests(false); +} + +void test_core_reloc_btfgen(void) +{ + run_core_reloc_tests(true); +} diff --git a/tools/testing/selftests/bpf/prog_tests/custom_sec_handlers.c b/tools/testing/selftests/bpf/prog_tests/custom_sec_handlers.c new file mode 100644 index 000000000000..b2dfc5954aea --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/custom_sec_handlers.c @@ -0,0 +1,176 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2022 Facebook */ + +#include <test_progs.h> +#include "test_custom_sec_handlers.skel.h" + +#define COOKIE_ABC1 1 +#define COOKIE_ABC2 2 +#define COOKIE_CUSTOM 3 +#define COOKIE_FALLBACK 4 +#define COOKIE_KPROBE 5 + +static int custom_setup_prog(struct bpf_program *prog, long cookie) +{ + if (cookie == COOKIE_ABC1) + bpf_program__set_autoload(prog, false); + + return 0; +} + +static int custom_prepare_load_prog(struct bpf_program *prog, + struct bpf_prog_load_opts *opts, long cookie) +{ + if (cookie == COOKIE_FALLBACK) + opts->prog_flags |= BPF_F_SLEEPABLE; + else if (cookie == COOKIE_ABC1) + ASSERT_FALSE(true, "unexpected preload for abc"); + + return 0; +} + +static int custom_attach_prog(const struct bpf_program *prog, long cookie, + struct bpf_link **link) +{ + switch (cookie) { + case COOKIE_ABC2: + *link = bpf_program__attach_raw_tracepoint(prog, "sys_enter"); + return libbpf_get_error(*link); + case COOKIE_CUSTOM: + *link = bpf_program__attach_tracepoint(prog, "syscalls", "sys_enter_nanosleep"); + return libbpf_get_error(*link); + case COOKIE_KPROBE: + case COOKIE_FALLBACK: + /* no auto-attach for SEC("xyz") and SEC("kprobe") */ + *link = NULL; + return 0; + default: + ASSERT_FALSE(true, "unexpected cookie"); + return -EINVAL; + } +} + +static int abc1_id; +static int abc2_id; +static int custom_id; +static int fallback_id; +static int kprobe_id; + +__attribute__((constructor)) +static void register_sec_handlers(void) +{ + LIBBPF_OPTS(libbpf_prog_handler_opts, abc1_opts, + .cookie = COOKIE_ABC1, + .prog_setup_fn = custom_setup_prog, + .prog_prepare_load_fn = custom_prepare_load_prog, + .prog_attach_fn = NULL, + ); + LIBBPF_OPTS(libbpf_prog_handler_opts, abc2_opts, + .cookie = COOKIE_ABC2, + .prog_setup_fn = custom_setup_prog, + .prog_prepare_load_fn = custom_prepare_load_prog, + .prog_attach_fn = custom_attach_prog, + ); + LIBBPF_OPTS(libbpf_prog_handler_opts, custom_opts, + .cookie = COOKIE_CUSTOM, + .prog_setup_fn = NULL, + .prog_prepare_load_fn = NULL, + .prog_attach_fn = custom_attach_prog, + ); + + abc1_id = libbpf_register_prog_handler("abc", BPF_PROG_TYPE_RAW_TRACEPOINT, 0, &abc1_opts); + abc2_id = libbpf_register_prog_handler("abc/", BPF_PROG_TYPE_RAW_TRACEPOINT, 0, &abc2_opts); + custom_id = libbpf_register_prog_handler("custom+", BPF_PROG_TYPE_TRACEPOINT, 0, &custom_opts); +} + +__attribute__((destructor)) +static void unregister_sec_handlers(void) +{ + libbpf_unregister_prog_handler(abc1_id); + libbpf_unregister_prog_handler(abc2_id); + libbpf_unregister_prog_handler(custom_id); +} + +void test_custom_sec_handlers(void) +{ + LIBBPF_OPTS(libbpf_prog_handler_opts, opts, + .prog_setup_fn = custom_setup_prog, + .prog_prepare_load_fn = custom_prepare_load_prog, + .prog_attach_fn = custom_attach_prog, + ); + struct test_custom_sec_handlers* skel; + int err; + + ASSERT_GT(abc1_id, 0, "abc1_id"); + ASSERT_GT(abc2_id, 0, "abc2_id"); + ASSERT_GT(custom_id, 0, "custom_id"); + + /* override libbpf's handle of SEC("kprobe/...") but also allow pure + * SEC("kprobe") due to "kprobe+" specifier. Register it as + * TRACEPOINT, just for fun. + */ + opts.cookie = COOKIE_KPROBE; + kprobe_id = libbpf_register_prog_handler("kprobe+", BPF_PROG_TYPE_TRACEPOINT, 0, &opts); + /* fallback treats everything as BPF_PROG_TYPE_SYSCALL program to test + * setting custom BPF_F_SLEEPABLE bit in preload handler + */ + opts.cookie = COOKIE_FALLBACK; + fallback_id = libbpf_register_prog_handler(NULL, BPF_PROG_TYPE_SYSCALL, 0, &opts); + + if (!ASSERT_GT(fallback_id, 0, "fallback_id") /* || !ASSERT_GT(kprobe_id, 0, "kprobe_id")*/) { + if (fallback_id > 0) + libbpf_unregister_prog_handler(fallback_id); + if (kprobe_id > 0) + libbpf_unregister_prog_handler(kprobe_id); + return; + } + + /* open skeleton and validate assumptions */ + skel = test_custom_sec_handlers__open(); + if (!ASSERT_OK_PTR(skel, "skel_open")) + goto cleanup; + + ASSERT_EQ(bpf_program__type(skel->progs.abc1), BPF_PROG_TYPE_RAW_TRACEPOINT, "abc1_type"); + ASSERT_FALSE(bpf_program__autoload(skel->progs.abc1), "abc1_autoload"); + + ASSERT_EQ(bpf_program__type(skel->progs.abc2), BPF_PROG_TYPE_RAW_TRACEPOINT, "abc2_type"); + ASSERT_EQ(bpf_program__type(skel->progs.custom1), BPF_PROG_TYPE_TRACEPOINT, "custom1_type"); + ASSERT_EQ(bpf_program__type(skel->progs.custom2), BPF_PROG_TYPE_TRACEPOINT, "custom2_type"); + ASSERT_EQ(bpf_program__type(skel->progs.kprobe1), BPF_PROG_TYPE_TRACEPOINT, "kprobe1_type"); + ASSERT_EQ(bpf_program__type(skel->progs.xyz), BPF_PROG_TYPE_SYSCALL, "xyz_type"); + + skel->rodata->my_pid = getpid(); + + /* now attempt to load everything */ + err = test_custom_sec_handlers__load(skel); + if (!ASSERT_OK(err, "skel_load")) + goto cleanup; + + /* now try to auto-attach everything */ + err = test_custom_sec_handlers__attach(skel); + if (!ASSERT_OK(err, "skel_attach")) + goto cleanup; + + skel->links.xyz = bpf_program__attach(skel->progs.kprobe1); + ASSERT_EQ(errno, EOPNOTSUPP, "xyz_attach_err"); + ASSERT_ERR_PTR(skel->links.xyz, "xyz_attach"); + + /* trigger programs */ + usleep(1); + + /* SEC("abc") is set to not auto-loaded */ + ASSERT_FALSE(skel->bss->abc1_called, "abc1_called"); + ASSERT_TRUE(skel->bss->abc2_called, "abc2_called"); + ASSERT_TRUE(skel->bss->custom1_called, "custom1_called"); + ASSERT_TRUE(skel->bss->custom2_called, "custom2_called"); + /* SEC("kprobe") shouldn't be auto-attached */ + ASSERT_FALSE(skel->bss->kprobe1_called, "kprobe1_called"); + /* SEC("xyz") shouldn't be auto-attached */ + ASSERT_FALSE(skel->bss->xyz_called, "xyz_called"); + +cleanup: + test_custom_sec_handlers__destroy(skel); + + ASSERT_OK(libbpf_unregister_prog_handler(fallback_id), "unregister_fallback"); + ASSERT_OK(libbpf_unregister_prog_handler(kprobe_id), "unregister_kprobe"); +} diff --git a/tools/testing/selftests/bpf/prog_tests/d_path.c b/tools/testing/selftests/bpf/prog_tests/d_path.c index 32fc5b3b5cf6..911345c526e6 100644 --- a/tools/testing/selftests/bpf/prog_tests/d_path.c +++ b/tools/testing/selftests/bpf/prog_tests/d_path.c @@ -10,6 +10,7 @@ #include "test_d_path.skel.h" #include "test_d_path_check_rdonly_mem.skel.h" +#include "test_d_path_check_types.skel.h" static int duration; @@ -167,6 +168,16 @@ static void test_d_path_check_rdonly_mem(void) test_d_path_check_rdonly_mem__destroy(skel); } +static void test_d_path_check_types(void) +{ + struct test_d_path_check_types *skel; + + skel = test_d_path_check_types__open_and_load(); + ASSERT_ERR_PTR(skel, "unexpected_load_passing_wrong_type"); + + test_d_path_check_types__destroy(skel); +} + void test_d_path(void) { if (test__start_subtest("basic")) @@ -174,4 +185,7 @@ void test_d_path(void) if (test__start_subtest("check_rdonly_mem")) test_d_path_check_rdonly_mem(); + + if (test__start_subtest("check_alloc_mem")) + test_d_path_check_types(); } diff --git a/tools/testing/selftests/bpf/prog_tests/dummy_st_ops.c b/tools/testing/selftests/bpf/prog_tests/dummy_st_ops.c index cbaa44ffb8c6..5aa52cc31dc2 100644 --- a/tools/testing/selftests/bpf/prog_tests/dummy_st_ops.c +++ b/tools/testing/selftests/bpf/prog_tests/dummy_st_ops.c @@ -26,10 +26,10 @@ static void test_dummy_st_ops_attach(void) static void test_dummy_init_ret_value(void) { __u64 args[1] = {0}; - struct bpf_prog_test_run_attr attr = { - .ctx_size_in = sizeof(args), + LIBBPF_OPTS(bpf_test_run_opts, attr, .ctx_in = args, - }; + .ctx_size_in = sizeof(args), + ); struct dummy_st_ops *skel; int fd, err; @@ -38,8 +38,7 @@ static void test_dummy_init_ret_value(void) return; fd = bpf_program__fd(skel->progs.test_1); - attr.prog_fd = fd; - err = bpf_prog_test_run_xattr(&attr); + err = bpf_prog_test_run_opts(fd, &attr); ASSERT_OK(err, "test_run"); ASSERT_EQ(attr.retval, 0xf2f3f4f5, "test_ret"); @@ -53,10 +52,10 @@ static void test_dummy_init_ptr_arg(void) .val = exp_retval, }; __u64 args[1] = {(unsigned long)&in_state}; - struct bpf_prog_test_run_attr attr = { - .ctx_size_in = sizeof(args), + LIBBPF_OPTS(bpf_test_run_opts, attr, .ctx_in = args, - }; + .ctx_size_in = sizeof(args), + ); struct dummy_st_ops *skel; int fd, err; @@ -65,8 +64,7 @@ static void test_dummy_init_ptr_arg(void) return; fd = bpf_program__fd(skel->progs.test_1); - attr.prog_fd = fd; - err = bpf_prog_test_run_xattr(&attr); + err = bpf_prog_test_run_opts(fd, &attr); ASSERT_OK(err, "test_run"); ASSERT_EQ(in_state.val, 0x5a, "test_ptr_ret"); ASSERT_EQ(attr.retval, exp_retval, "test_ret"); @@ -77,10 +75,10 @@ static void test_dummy_init_ptr_arg(void) static void test_dummy_multiple_args(void) { __u64 args[5] = {0, -100, 0x8a5f, 'c', 0x1234567887654321ULL}; - struct bpf_prog_test_run_attr attr = { - .ctx_size_in = sizeof(args), + LIBBPF_OPTS(bpf_test_run_opts, attr, .ctx_in = args, - }; + .ctx_size_in = sizeof(args), + ); struct dummy_st_ops *skel; int fd, err; size_t i; @@ -91,8 +89,7 @@ static void test_dummy_multiple_args(void) return; fd = bpf_program__fd(skel->progs.test_2); - attr.prog_fd = fd; - err = bpf_prog_test_run_xattr(&attr); + err = bpf_prog_test_run_opts(fd, &attr); ASSERT_OK(err, "test_run"); for (i = 0; i < ARRAY_SIZE(args); i++) { snprintf(name, sizeof(name), "arg %zu", i); diff --git a/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c b/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c index 4374ac8a8a91..130f5b82d2e6 100644 --- a/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c +++ b/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c @@ -9,38 +9,34 @@ void test_fentry_fexit(void) struct fentry_test_lskel *fentry_skel = NULL; struct fexit_test_lskel *fexit_skel = NULL; __u64 *fentry_res, *fexit_res; - __u32 duration = 0, retval; int err, prog_fd, i; + LIBBPF_OPTS(bpf_test_run_opts, topts); fentry_skel = fentry_test_lskel__open_and_load(); - if (CHECK(!fentry_skel, "fentry_skel_load", "fentry skeleton failed\n")) + if (!ASSERT_OK_PTR(fentry_skel, "fentry_skel_load")) goto close_prog; fexit_skel = fexit_test_lskel__open_and_load(); - if (CHECK(!fexit_skel, "fexit_skel_load", "fexit skeleton failed\n")) + if (!ASSERT_OK_PTR(fexit_skel, "fexit_skel_load")) goto close_prog; err = fentry_test_lskel__attach(fentry_skel); - if (CHECK(err, "fentry_attach", "fentry attach failed: %d\n", err)) + if (!ASSERT_OK(err, "fentry_attach")) goto close_prog; err = fexit_test_lskel__attach(fexit_skel); - if (CHECK(err, "fexit_attach", "fexit attach failed: %d\n", err)) + if (!ASSERT_OK(err, "fexit_attach")) goto close_prog; prog_fd = fexit_skel->progs.test1.prog_fd; - err = bpf_prog_test_run(prog_fd, 1, NULL, 0, - NULL, NULL, &retval, &duration); - CHECK(err || retval, "ipv6", - "err %d errno %d retval %d duration %d\n", - err, errno, retval, duration); + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "ipv6 test_run"); + ASSERT_OK(topts.retval, "ipv6 test retval"); fentry_res = (__u64 *)fentry_skel->bss; fexit_res = (__u64 *)fexit_skel->bss; printf("%lld\n", fentry_skel->bss->test1_result); for (i = 0; i < 8; i++) { - CHECK(fentry_res[i] != 1, "result", - "fentry_test%d failed err %lld\n", i + 1, fentry_res[i]); - CHECK(fexit_res[i] != 1, "result", - "fexit_test%d failed err %lld\n", i + 1, fexit_res[i]); + ASSERT_EQ(fentry_res[i], 1, "fentry result"); + ASSERT_EQ(fexit_res[i], 1, "fexit result"); } close_prog: diff --git a/tools/testing/selftests/bpf/prog_tests/fentry_test.c b/tools/testing/selftests/bpf/prog_tests/fentry_test.c index 12921b3850d2..c0d1d61d5f66 100644 --- a/tools/testing/selftests/bpf/prog_tests/fentry_test.c +++ b/tools/testing/selftests/bpf/prog_tests/fentry_test.c @@ -6,9 +6,9 @@ static int fentry_test(struct fentry_test_lskel *fentry_skel) { int err, prog_fd, i; - __u32 duration = 0, retval; int link_fd; __u64 *result; + LIBBPF_OPTS(bpf_test_run_opts, topts); err = fentry_test_lskel__attach(fentry_skel); if (!ASSERT_OK(err, "fentry_attach")) @@ -20,10 +20,9 @@ static int fentry_test(struct fentry_test_lskel *fentry_skel) return -1; prog_fd = fentry_skel->progs.test1.prog_fd; - err = bpf_prog_test_run(prog_fd, 1, NULL, 0, - NULL, NULL, &retval, &duration); + err = bpf_prog_test_run_opts(prog_fd, &topts); ASSERT_OK(err, "test_run"); - ASSERT_EQ(retval, 0, "test_run"); + ASSERT_EQ(topts.retval, 0, "test_run"); result = (__u64 *)fentry_skel->bss; for (i = 0; i < sizeof(*fentry_skel->bss) / sizeof(__u64); i++) { diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c b/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c index c52f99f6a909..d9aad15e0d24 100644 --- a/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c +++ b/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c @@ -58,12 +58,17 @@ static void test_fexit_bpf2bpf_common(const char *obj_file, test_cb cb) { struct bpf_object *obj = NULL, *tgt_obj; - __u32 retval, tgt_prog_id, info_len; + __u32 tgt_prog_id, info_len; struct bpf_prog_info prog_info = {}; struct bpf_program **prog = NULL, *p; struct bpf_link **link = NULL; int err, tgt_fd, i; struct btf *btf; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v6, + .data_size_in = sizeof(pkt_v6), + .repeat = 1, + ); err = bpf_prog_test_load(target_obj_file, BPF_PROG_TYPE_UNSPEC, &tgt_obj, &tgt_fd); @@ -132,7 +137,7 @@ static void test_fexit_bpf2bpf_common(const char *obj_file, &link_info, &info_len); ASSERT_OK(err, "link_fd_get_info"); ASSERT_EQ(link_info.tracing.attach_type, - bpf_program__get_expected_attach_type(prog[i]), + bpf_program__expected_attach_type(prog[i]), "link_attach_type"); ASSERT_EQ(link_info.tracing.target_obj_id, tgt_prog_id, "link_tgt_obj_id"); ASSERT_EQ(link_info.tracing.target_btf_id, btf_id, "link_tgt_btf_id"); @@ -147,10 +152,9 @@ static void test_fexit_bpf2bpf_common(const char *obj_file, if (!run_prog) goto close_prog; - err = bpf_prog_test_run(tgt_fd, 1, &pkt_v6, sizeof(pkt_v6), - NULL, NULL, &retval, NULL); + err = bpf_prog_test_run_opts(tgt_fd, &topts); ASSERT_OK(err, "prog_run"); - ASSERT_EQ(retval, 0, "prog_run_ret"); + ASSERT_EQ(topts.retval, 0, "prog_run_ret"); if (check_data_map(obj, prog_cnt, false)) goto close_prog; @@ -225,29 +229,31 @@ static int test_second_attach(struct bpf_object *obj) const char *tgt_obj_file = "./test_pkt_access.o"; struct bpf_program *prog = NULL; struct bpf_object *tgt_obj; - __u32 duration = 0, retval; struct bpf_link *link; int err = 0, tgt_fd; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v6, + .data_size_in = sizeof(pkt_v6), + .repeat = 1, + ); prog = bpf_object__find_program_by_name(obj, prog_name); - if (CHECK(!prog, "find_prog", "prog %s not found\n", prog_name)) + if (!ASSERT_OK_PTR(prog, "find_prog")) return -ENOENT; err = bpf_prog_test_load(tgt_obj_file, BPF_PROG_TYPE_UNSPEC, &tgt_obj, &tgt_fd); - if (CHECK(err, "second_prog_load", "file %s err %d errno %d\n", - tgt_obj_file, err, errno)) + if (!ASSERT_OK(err, "second_prog_load")) return err; link = bpf_program__attach_freplace(prog, tgt_fd, tgt_name); if (!ASSERT_OK_PTR(link, "second_link")) goto out; - err = bpf_prog_test_run(tgt_fd, 1, &pkt_v6, sizeof(pkt_v6), - NULL, NULL, &retval, &duration); - if (CHECK(err || retval, "ipv6", - "err %d errno %d retval %d duration %d\n", - err, errno, retval, duration)) + err = bpf_prog_test_run_opts(tgt_fd, &topts); + if (!ASSERT_OK(err, "ipv6 test_run")) + goto out; + if (!ASSERT_OK(topts.retval, "ipv6 retval")) goto out; err = check_data_map(obj, 1, true); diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_stress.c b/tools/testing/selftests/bpf/prog_tests/fexit_stress.c index e4cede6b4b2d..3ee2107bbf7a 100644 --- a/tools/testing/selftests/bpf/prog_tests/fexit_stress.c +++ b/tools/testing/selftests/bpf/prog_tests/fexit_stress.c @@ -10,9 +10,7 @@ void test_fexit_stress(void) char test_skb[128] = {}; int fexit_fd[CNT] = {}; int link_fd[CNT] = {}; - __u32 duration = 0; char error[4096]; - __u32 prog_ret; int err, i, filter_fd; const struct bpf_insn trace_program[] = { @@ -36,9 +34,15 @@ void test_fexit_stress(void) .log_size = sizeof(error), ); + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = test_skb, + .data_size_in = sizeof(test_skb), + .repeat = 1, + ); + err = libbpf_find_vmlinux_btf_id("bpf_fentry_test1", trace_opts.expected_attach_type); - if (CHECK(err <= 0, "find_vmlinux_btf_id", "failed: %d\n", err)) + if (!ASSERT_GT(err, 0, "find_vmlinux_btf_id")) goto out; trace_opts.attach_btf_id = err; @@ -47,24 +51,20 @@ void test_fexit_stress(void) trace_program, sizeof(trace_program) / sizeof(struct bpf_insn), &trace_opts); - if (CHECK(fexit_fd[i] < 0, "fexit loaded", - "failed: %d errno %d\n", fexit_fd[i], errno)) + if (!ASSERT_GE(fexit_fd[i], 0, "fexit load")) goto out; link_fd[i] = bpf_raw_tracepoint_open(NULL, fexit_fd[i]); - if (CHECK(link_fd[i] < 0, "fexit attach failed", - "prog %d failed: %d err %d\n", i, link_fd[i], errno)) + if (!ASSERT_GE(link_fd[i], 0, "fexit attach")) goto out; } filter_fd = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", skb_program, sizeof(skb_program) / sizeof(struct bpf_insn), &skb_opts); - if (CHECK(filter_fd < 0, "test_program_loaded", "failed: %d errno %d\n", - filter_fd, errno)) + if (!ASSERT_GE(filter_fd, 0, "test_program_loaded")) goto out; - err = bpf_prog_test_run(filter_fd, 1, test_skb, sizeof(test_skb), 0, - 0, &prog_ret, 0); + err = bpf_prog_test_run_opts(filter_fd, &topts); close(filter_fd); CHECK_FAIL(err); out: diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_test.c b/tools/testing/selftests/bpf/prog_tests/fexit_test.c index d4887d8bb396..101b7343036b 100644 --- a/tools/testing/selftests/bpf/prog_tests/fexit_test.c +++ b/tools/testing/selftests/bpf/prog_tests/fexit_test.c @@ -6,9 +6,9 @@ static int fexit_test(struct fexit_test_lskel *fexit_skel) { int err, prog_fd, i; - __u32 duration = 0, retval; int link_fd; __u64 *result; + LIBBPF_OPTS(bpf_test_run_opts, topts); err = fexit_test_lskel__attach(fexit_skel); if (!ASSERT_OK(err, "fexit_attach")) @@ -20,10 +20,9 @@ static int fexit_test(struct fexit_test_lskel *fexit_skel) return -1; prog_fd = fexit_skel->progs.test1.prog_fd; - err = bpf_prog_test_run(prog_fd, 1, NULL, 0, - NULL, NULL, &retval, &duration); + err = bpf_prog_test_run_opts(prog_fd, &topts); ASSERT_OK(err, "test_run"); - ASSERT_EQ(retval, 0, "test_run"); + ASSERT_EQ(topts.retval, 0, "test_run"); result = (__u64 *)fexit_skel->bss; for (i = 0; i < sizeof(*fexit_skel->bss) / sizeof(__u64); i++) { diff --git a/tools/testing/selftests/bpf/prog_tests/find_vma.c b/tools/testing/selftests/bpf/prog_tests/find_vma.c index b74b3c0c555a..5165b38f0e59 100644 --- a/tools/testing/selftests/bpf/prog_tests/find_vma.c +++ b/tools/testing/selftests/bpf/prog_tests/find_vma.c @@ -7,12 +7,14 @@ #include "find_vma_fail1.skel.h" #include "find_vma_fail2.skel.h" -static void test_and_reset_skel(struct find_vma *skel, int expected_find_zero_ret) +static void test_and_reset_skel(struct find_vma *skel, int expected_find_zero_ret, bool need_test) { - ASSERT_EQ(skel->bss->found_vm_exec, 1, "found_vm_exec"); - ASSERT_EQ(skel->data->find_addr_ret, 0, "find_addr_ret"); - ASSERT_EQ(skel->data->find_zero_ret, expected_find_zero_ret, "find_zero_ret"); - ASSERT_OK_PTR(strstr(skel->bss->d_iname, "test_progs"), "find_test_progs"); + if (need_test) { + ASSERT_EQ(skel->bss->found_vm_exec, 1, "found_vm_exec"); + ASSERT_EQ(skel->data->find_addr_ret, 0, "find_addr_ret"); + ASSERT_EQ(skel->data->find_zero_ret, expected_find_zero_ret, "find_zero_ret"); + ASSERT_OK_PTR(strstr(skel->bss->d_iname, "test_progs"), "find_test_progs"); + } skel->bss->found_vm_exec = 0; skel->data->find_addr_ret = -1; @@ -30,17 +32,26 @@ static int open_pe(void) attr.type = PERF_TYPE_HARDWARE; attr.config = PERF_COUNT_HW_CPU_CYCLES; attr.freq = 1; - attr.sample_freq = 4000; + attr.sample_freq = 1000; pfd = syscall(__NR_perf_event_open, &attr, 0, -1, -1, PERF_FLAG_FD_CLOEXEC); return pfd >= 0 ? pfd : -errno; } +static bool find_vma_pe_condition(struct find_vma *skel) +{ + return skel->bss->found_vm_exec == 0 || + skel->data->find_addr_ret != 0 || + skel->data->find_zero_ret == -1 || + strcmp(skel->bss->d_iname, "test_progs") != 0; +} + static void test_find_vma_pe(struct find_vma *skel) { struct bpf_link *link = NULL; volatile int j = 0; int pfd, i; + const int one_bn = 1000000000; pfd = open_pe(); if (pfd < 0) { @@ -57,10 +68,10 @@ static void test_find_vma_pe(struct find_vma *skel) if (!ASSERT_OK_PTR(link, "attach_perf_event")) goto cleanup; - for (i = 0; i < 1000000; ++i) + for (i = 0; i < one_bn && find_vma_pe_condition(skel); ++i) ++j; - test_and_reset_skel(skel, -EBUSY /* in nmi, irq_work is busy */); + test_and_reset_skel(skel, -EBUSY /* in nmi, irq_work is busy */, i == one_bn); cleanup: bpf_link__destroy(link); close(pfd); @@ -75,7 +86,7 @@ static void test_find_vma_kprobe(struct find_vma *skel) return; getpgid(skel->bss->target_pid); - test_and_reset_skel(skel, -ENOENT /* could not find vma for ptr 0 */); + test_and_reset_skel(skel, -ENOENT /* could not find vma for ptr 0 */, true); } static void test_illegal_write_vma(void) @@ -108,7 +119,6 @@ void serial_test_find_vma(void) skel->bss->addr = (__u64)(uintptr_t)test_find_vma_pe; test_find_vma_pe(skel); - usleep(100000); /* allow the irq_work to finish */ test_find_vma_kprobe(skel); find_vma__destroy(skel); diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c index ac54e3f91d42..0c1661ea996e 100644 --- a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c +++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c @@ -13,8 +13,9 @@ #endif #define CHECK_FLOW_KEYS(desc, got, expected) \ - CHECK_ATTR(memcmp(&got, &expected, sizeof(got)) != 0, \ + _CHECK(memcmp(&got, &expected, sizeof(got)) != 0, \ desc, \ + topts.duration, \ "nhoff=%u/%u " \ "thoff=%u/%u " \ "addr_proto=0x%x/0x%x " \ @@ -457,7 +458,7 @@ static int init_prog_array(struct bpf_object *obj, struct bpf_map *prog_array) if (map_fd < 0) return -1; - for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { + for (i = 0; i < bpf_map__max_entries(prog_array); i++) { snprintf(prog_name, sizeof(prog_name), "flow_dissector_%d", i); prog = bpf_object__find_program_by_name(obj, prog_name); @@ -487,7 +488,7 @@ static void run_tests_skb_less(int tap_fd, struct bpf_map *keys) /* Keep in sync with 'flags' from eth_get_headlen. */ __u32 eth_get_headlen_flags = BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG; - struct bpf_prog_test_run_attr tattr = {}; + LIBBPF_OPTS(bpf_test_run_opts, topts); struct bpf_flow_keys flow_keys = {}; __u32 key = (__u32)(tests[i].keys.sport) << 16 | tests[i].keys.dport; @@ -503,13 +504,12 @@ static void run_tests_skb_less(int tap_fd, struct bpf_map *keys) CHECK(err < 0, "tx_tap", "err %d errno %d\n", err, errno); err = bpf_map_lookup_elem(keys_fd, &key, &flow_keys); - CHECK_ATTR(err, tests[i].name, "bpf_map_lookup_elem %d\n", err); + ASSERT_OK(err, "bpf_map_lookup_elem"); - CHECK_ATTR(err, tests[i].name, "skb-less err %d\n", err); CHECK_FLOW_KEYS(tests[i].name, flow_keys, tests[i].keys); err = bpf_map_delete_elem(keys_fd, &key); - CHECK_ATTR(err, tests[i].name, "bpf_map_delete_elem %d\n", err); + ASSERT_OK(err, "bpf_map_delete_elem"); } } @@ -573,27 +573,24 @@ void test_flow_dissector(void) for (i = 0; i < ARRAY_SIZE(tests); i++) { struct bpf_flow_keys flow_keys; - struct bpf_prog_test_run_attr tattr = { - .prog_fd = prog_fd, + LIBBPF_OPTS(bpf_test_run_opts, topts, .data_in = &tests[i].pkt, .data_size_in = sizeof(tests[i].pkt), .data_out = &flow_keys, - }; + ); static struct bpf_flow_keys ctx = {}; if (tests[i].flags) { - tattr.ctx_in = &ctx; - tattr.ctx_size_in = sizeof(ctx); + topts.ctx_in = &ctx; + topts.ctx_size_in = sizeof(ctx); ctx.flags = tests[i].flags; } - err = bpf_prog_test_run_xattr(&tattr); - CHECK_ATTR(tattr.data_size_out != sizeof(flow_keys) || - err || tattr.retval != 1, - tests[i].name, - "err %d errno %d retval %d duration %d size %u/%zu\n", - err, errno, tattr.retval, tattr.duration, - tattr.data_size_out, sizeof(flow_keys)); + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "test_run"); + ASSERT_EQ(topts.retval, 1, "test_run retval"); + ASSERT_EQ(topts.data_size_out, sizeof(flow_keys), + "test_run data_size_out"); CHECK_FLOW_KEYS(tests[i].name, flow_keys, tests[i].keys); } diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector_load_bytes.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector_load_bytes.c index 93ac3f28226c..36afb409c25f 100644 --- a/tools/testing/selftests/bpf/prog_tests/flow_dissector_load_bytes.c +++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector_load_bytes.c @@ -5,7 +5,6 @@ void serial_test_flow_dissector_load_bytes(void) { struct bpf_flow_keys flow_keys; - __u32 duration = 0, retval, size; struct bpf_insn prog[] = { // BPF_REG_1 - 1st argument: context // BPF_REG_2 - 2nd argument: offset, start at first byte @@ -27,22 +26,25 @@ void serial_test_flow_dissector_load_bytes(void) BPF_EXIT_INSN(), }; int fd, err; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .data_out = &flow_keys, + .data_size_out = sizeof(flow_keys), + .repeat = 1, + ); /* make sure bpf_skb_load_bytes is not allowed from skb-less context */ fd = bpf_test_load_program(BPF_PROG_TYPE_FLOW_DISSECTOR, prog, ARRAY_SIZE(prog), "GPL", 0, NULL, 0); - CHECK(fd < 0, - "flow_dissector-bpf_skb_load_bytes-load", - "fd %d errno %d\n", - fd, errno); + ASSERT_GE(fd, 0, "bpf_test_load_program good fd"); - err = bpf_prog_test_run(fd, 1, &pkt_v4, sizeof(pkt_v4), - &flow_keys, &size, &retval, &duration); - CHECK(size != sizeof(flow_keys) || err || retval != 1, - "flow_dissector-bpf_skb_load_bytes", - "err %d errno %d retval %d duration %d size %u/%zu\n", - err, errno, retval, duration, size, sizeof(flow_keys)); + err = bpf_prog_test_run_opts(fd, &topts); + ASSERT_OK(err, "test_run"); + ASSERT_EQ(topts.data_size_out, sizeof(flow_keys), + "test_run data_size_out"); + ASSERT_EQ(topts.retval, 1, "test_run retval"); if (fd >= -1) close(fd); diff --git a/tools/testing/selftests/bpf/prog_tests/for_each.c b/tools/testing/selftests/bpf/prog_tests/for_each.c index 68eb12a287d4..044df13ee069 100644 --- a/tools/testing/selftests/bpf/prog_tests/for_each.c +++ b/tools/testing/selftests/bpf/prog_tests/for_each.c @@ -12,8 +12,13 @@ static void test_hash_map(void) int i, err, hashmap_fd, max_entries, percpu_map_fd; struct for_each_hash_map_elem *skel; __u64 *percpu_valbuf = NULL; - __u32 key, num_cpus, retval; + __u32 key, num_cpus; __u64 val; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .repeat = 1, + ); skel = for_each_hash_map_elem__open_and_load(); if (!ASSERT_OK_PTR(skel, "for_each_hash_map_elem__open_and_load")) @@ -42,11 +47,10 @@ static void test_hash_map(void) if (!ASSERT_OK(err, "percpu_map_update")) goto out; - err = bpf_prog_test_run(bpf_program__fd(skel->progs.test_pkt_access), - 1, &pkt_v4, sizeof(pkt_v4), NULL, NULL, - &retval, &duration); - if (CHECK(err || retval, "ipv4", "err %d errno %d retval %d\n", - err, errno, retval)) + err = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.test_pkt_access), &topts); + duration = topts.duration; + if (CHECK(err || topts.retval, "ipv4", "err %d errno %d retval %d\n", + err, errno, topts.retval)) goto out; ASSERT_EQ(skel->bss->hashmap_output, 4, "hashmap_output"); @@ -69,11 +73,16 @@ out: static void test_array_map(void) { - __u32 key, num_cpus, max_entries, retval; + __u32 key, num_cpus, max_entries; int i, arraymap_fd, percpu_map_fd, err; struct for_each_array_map_elem *skel; __u64 *percpu_valbuf = NULL; __u64 val, expected_total; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .repeat = 1, + ); skel = for_each_array_map_elem__open_and_load(); if (!ASSERT_OK_PTR(skel, "for_each_array_map_elem__open_and_load")) @@ -106,11 +115,10 @@ static void test_array_map(void) if (!ASSERT_OK(err, "percpu_map_update")) goto out; - err = bpf_prog_test_run(bpf_program__fd(skel->progs.test_pkt_access), - 1, &pkt_v4, sizeof(pkt_v4), NULL, NULL, - &retval, &duration); - if (CHECK(err || retval, "ipv4", "err %d errno %d retval %d\n", - err, errno, retval)) + err = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.test_pkt_access), &topts); + duration = topts.duration; + if (CHECK(err || topts.retval, "ipv4", "err %d errno %d retval %d\n", + err, errno, topts.retval)) goto out; ASSERT_EQ(skel->bss->arraymap_output, expected_total, "array_output"); diff --git a/tools/testing/selftests/bpf/prog_tests/get_func_args_test.c b/tools/testing/selftests/bpf/prog_tests/get_func_args_test.c index 85c427119fe9..28cf63963cb7 100644 --- a/tools/testing/selftests/bpf/prog_tests/get_func_args_test.c +++ b/tools/testing/selftests/bpf/prog_tests/get_func_args_test.c @@ -5,8 +5,8 @@ void test_get_func_args_test(void) { struct get_func_args_test *skel = NULL; - __u32 duration = 0, retval; int err, prog_fd; + LIBBPF_OPTS(bpf_test_run_opts, topts); skel = get_func_args_test__open_and_load(); if (!ASSERT_OK_PTR(skel, "get_func_args_test__open_and_load")) @@ -20,19 +20,17 @@ void test_get_func_args_test(void) * fentry/fexit programs. */ prog_fd = bpf_program__fd(skel->progs.test1); - err = bpf_prog_test_run(prog_fd, 1, NULL, 0, - NULL, NULL, &retval, &duration); + err = bpf_prog_test_run_opts(prog_fd, &topts); ASSERT_OK(err, "test_run"); - ASSERT_EQ(retval, 0, "test_run"); + ASSERT_EQ(topts.retval, 0, "test_run"); /* This runs bpf_modify_return_test function and triggers * fmod_ret_test and fexit_test programs. */ prog_fd = bpf_program__fd(skel->progs.fmod_ret_test); - err = bpf_prog_test_run(prog_fd, 1, NULL, 0, - NULL, NULL, &retval, &duration); + err = bpf_prog_test_run_opts(prog_fd, &topts); ASSERT_OK(err, "test_run"); - ASSERT_EQ(retval, 1234, "test_run"); + ASSERT_EQ(topts.retval, 1234, "test_run"); ASSERT_EQ(skel->bss->test1_result, 1, "test1_result"); ASSERT_EQ(skel->bss->test2_result, 1, "test2_result"); diff --git a/tools/testing/selftests/bpf/prog_tests/get_func_ip_test.c b/tools/testing/selftests/bpf/prog_tests/get_func_ip_test.c index 02a465f36d59..938dbd4d7c2f 100644 --- a/tools/testing/selftests/bpf/prog_tests/get_func_ip_test.c +++ b/tools/testing/selftests/bpf/prog_tests/get_func_ip_test.c @@ -5,8 +5,8 @@ void test_get_func_ip_test(void) { struct get_func_ip_test *skel = NULL; - __u32 duration = 0, retval; int err, prog_fd; + LIBBPF_OPTS(bpf_test_run_opts, topts); skel = get_func_ip_test__open(); if (!ASSERT_OK_PTR(skel, "get_func_ip_test__open")) @@ -29,14 +29,12 @@ void test_get_func_ip_test(void) goto cleanup; prog_fd = bpf_program__fd(skel->progs.test1); - err = bpf_prog_test_run(prog_fd, 1, NULL, 0, - NULL, NULL, &retval, &duration); + err = bpf_prog_test_run_opts(prog_fd, &topts); ASSERT_OK(err, "test_run"); - ASSERT_EQ(retval, 0, "test_run"); + ASSERT_EQ(topts.retval, 0, "test_run"); prog_fd = bpf_program__fd(skel->progs.test5); - err = bpf_prog_test_run(prog_fd, 1, NULL, 0, - NULL, NULL, &retval, &duration); + err = bpf_prog_test_run_opts(prog_fd, &topts); ASSERT_OK(err, "test_run"); diff --git a/tools/testing/selftests/bpf/prog_tests/get_stackid_cannot_attach.c b/tools/testing/selftests/bpf/prog_tests/get_stackid_cannot_attach.c index 8d5a6023a1bb..5308de1ed478 100644 --- a/tools/testing/selftests/bpf/prog_tests/get_stackid_cannot_attach.c +++ b/tools/testing/selftests/bpf/prog_tests/get_stackid_cannot_attach.c @@ -27,7 +27,7 @@ void test_get_stackid_cannot_attach(void) return; /* override program type */ - bpf_program__set_perf_event(skel->progs.oncpu); + bpf_program__set_type(skel->progs.oncpu, BPF_PROG_TYPE_PERF_EVENT); err = test_stacktrace_build_id__load(skel); if (CHECK(err, "skel_load", "skeleton load failed: %d\n", err)) diff --git a/tools/testing/selftests/bpf/prog_tests/global_data.c b/tools/testing/selftests/bpf/prog_tests/global_data.c index 9da131b32e13..027685858925 100644 --- a/tools/testing/selftests/bpf/prog_tests/global_data.c +++ b/tools/testing/selftests/bpf/prog_tests/global_data.c @@ -29,7 +29,7 @@ static void test_global_data_number(struct bpf_object *obj, __u32 duration) { "relocate .rodata reference", 10, ~0 }, }; - for (i = 0; i < sizeof(tests) / sizeof(tests[0]); i++) { + for (i = 0; i < ARRAY_SIZE(tests); i++) { err = bpf_map_lookup_elem(map_fd, &tests[i].key, &num); CHECK(err || num != tests[i].num, tests[i].name, "err %d result %llx expected %llx\n", @@ -58,7 +58,7 @@ static void test_global_data_string(struct bpf_object *obj, __u32 duration) { "relocate .bss reference", 4, "\0\0hello" }, }; - for (i = 0; i < sizeof(tests) / sizeof(tests[0]); i++) { + for (i = 0; i < ARRAY_SIZE(tests); i++) { err = bpf_map_lookup_elem(map_fd, &tests[i].key, str); CHECK(err || memcmp(str, tests[i].str, sizeof(str)), tests[i].name, "err %d result \'%s\' expected \'%s\'\n", @@ -92,7 +92,7 @@ static void test_global_data_struct(struct bpf_object *obj, __u32 duration) { "relocate .data reference", 3, { 41, 0xeeeeefef, 0x2111111111111111ULL, } }, }; - for (i = 0; i < sizeof(tests) / sizeof(tests[0]); i++) { + for (i = 0; i < ARRAY_SIZE(tests); i++) { err = bpf_map_lookup_elem(map_fd, &tests[i].key, &val); CHECK(err || memcmp(&val, &tests[i].val, sizeof(val)), tests[i].name, "err %d result { %u, %u, %llu } expected { %u, %u, %llu }\n", @@ -121,7 +121,7 @@ static void test_global_data_rdonly(struct bpf_object *obj, __u32 duration) if (CHECK_FAIL(map_fd < 0)) return; - buff = malloc(bpf_map__def(map)->value_size); + buff = malloc(bpf_map__value_size(map)); if (buff) err = bpf_map_update_elem(map_fd, &zero, buff, 0); free(buff); @@ -132,24 +132,26 @@ static void test_global_data_rdonly(struct bpf_object *obj, __u32 duration) void test_global_data(void) { const char *file = "./test_global_data.o"; - __u32 duration = 0, retval; struct bpf_object *obj; int err, prog_fd; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .repeat = 1, + ); err = bpf_prog_test_load(file, BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd); - if (CHECK(err, "load program", "error %d loading %s\n", err, file)) + if (!ASSERT_OK(err, "load program")) return; - err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4), - NULL, NULL, &retval, &duration); - CHECK(err || retval, "pass global data run", - "err %d errno %d retval %d duration %d\n", - err, errno, retval, duration); + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "pass global data run err"); + ASSERT_OK(topts.retval, "pass global data run retval"); - test_global_data_number(obj, duration); - test_global_data_string(obj, duration); - test_global_data_struct(obj, duration); - test_global_data_rdonly(obj, duration); + test_global_data_number(obj, topts.duration); + test_global_data_string(obj, topts.duration); + test_global_data_struct(obj, topts.duration); + test_global_data_rdonly(obj, topts.duration); bpf_object__close(obj); } diff --git a/tools/testing/selftests/bpf/prog_tests/global_data_init.c b/tools/testing/selftests/bpf/prog_tests/global_data_init.c index 1db86eab101b..57331c606964 100644 --- a/tools/testing/selftests/bpf/prog_tests/global_data_init.c +++ b/tools/testing/selftests/bpf/prog_tests/global_data_init.c @@ -20,7 +20,7 @@ void test_global_data_init(void) if (CHECK_FAIL(!map || !bpf_map__is_internal(map))) goto out; - sz = bpf_map__def(map)->value_size; + sz = bpf_map__value_size(map); newval = malloc(sz); if (CHECK_FAIL(!newval)) goto out; diff --git a/tools/testing/selftests/bpf/prog_tests/global_func_args.c b/tools/testing/selftests/bpf/prog_tests/global_func_args.c index 93a2439237b0..29039a36cce5 100644 --- a/tools/testing/selftests/bpf/prog_tests/global_func_args.c +++ b/tools/testing/selftests/bpf/prog_tests/global_func_args.c @@ -40,19 +40,21 @@ static void test_global_func_args0(struct bpf_object *obj) void test_global_func_args(void) { const char *file = "./test_global_func_args.o"; - __u32 retval; struct bpf_object *obj; int err, prog_fd; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .repeat = 1, + ); err = bpf_prog_test_load(file, BPF_PROG_TYPE_CGROUP_SKB, &obj, &prog_fd); if (CHECK(err, "load program", "error %d loading %s\n", err, file)) return; - err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4), - NULL, NULL, &retval, &duration); - CHECK(err || retval, "pass global func args run", - "err %d errno %d retval %d duration %d\n", - err, errno, retval, duration); + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "test_run"); + ASSERT_OK(topts.retval, "test_run retval"); test_global_func_args0(obj); diff --git a/tools/testing/selftests/bpf/prog_tests/kfree_skb.c b/tools/testing/selftests/bpf/prog_tests/kfree_skb.c index ce10d2fc3a6c..1cee6957285e 100644 --- a/tools/testing/selftests/bpf/prog_tests/kfree_skb.c +++ b/tools/testing/selftests/bpf/prog_tests/kfree_skb.c @@ -53,24 +53,24 @@ static void on_sample(void *ctx, int cpu, void *data, __u32 size) void serial_test_kfree_skb(void) { struct __sk_buff skb = {}; - struct bpf_prog_test_run_attr tattr = { + LIBBPF_OPTS(bpf_test_run_opts, topts, .data_in = &pkt_v6, .data_size_in = sizeof(pkt_v6), .ctx_in = &skb, .ctx_size_in = sizeof(skb), - }; + ); struct kfree_skb *skel = NULL; struct bpf_link *link; struct bpf_object *obj; struct perf_buffer *pb = NULL; - int err; + int err, prog_fd; bool passed = false; __u32 duration = 0; const int zero = 0; bool test_ok[2]; err = bpf_prog_test_load("./test_pkt_access.o", BPF_PROG_TYPE_SCHED_CLS, - &obj, &tattr.prog_fd); + &obj, &prog_fd); if (CHECK(err, "prog_load sched cls", "err %d errno %d\n", err, errno)) return; @@ -100,11 +100,9 @@ void serial_test_kfree_skb(void) goto close_prog; memcpy(skb.cb, &cb, sizeof(cb)); - err = bpf_prog_test_run_xattr(&tattr); - duration = tattr.duration; - CHECK(err || tattr.retval, "ipv6", - "err %d errno %d retval %d duration %d\n", - err, errno, tattr.retval, duration); + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "ipv6 test_run"); + ASSERT_OK(topts.retval, "ipv6 test_run retval"); /* read perf buffer */ err = perf_buffer__poll(pb, 100); diff --git a/tools/testing/selftests/bpf/prog_tests/kfunc_call.c b/tools/testing/selftests/bpf/prog_tests/kfunc_call.c index 7d7445ccc141..c00eb974eb85 100644 --- a/tools/testing/selftests/bpf/prog_tests/kfunc_call.c +++ b/tools/testing/selftests/bpf/prog_tests/kfunc_call.c @@ -9,23 +9,31 @@ static void test_main(void) { struct kfunc_call_test_lskel *skel; - int prog_fd, retval, err; + int prog_fd, err; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .repeat = 1, + ); skel = kfunc_call_test_lskel__open_and_load(); if (!ASSERT_OK_PTR(skel, "skel")) return; prog_fd = skel->progs.kfunc_call_test1.prog_fd; - err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4), - NULL, NULL, (__u32 *)&retval, NULL); + err = bpf_prog_test_run_opts(prog_fd, &topts); ASSERT_OK(err, "bpf_prog_test_run(test1)"); - ASSERT_EQ(retval, 12, "test1-retval"); + ASSERT_EQ(topts.retval, 12, "test1-retval"); prog_fd = skel->progs.kfunc_call_test2.prog_fd; - err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4), - NULL, NULL, (__u32 *)&retval, NULL); + err = bpf_prog_test_run_opts(prog_fd, &topts); ASSERT_OK(err, "bpf_prog_test_run(test2)"); - ASSERT_EQ(retval, 3, "test2-retval"); + ASSERT_EQ(topts.retval, 3, "test2-retval"); + + prog_fd = skel->progs.kfunc_call_test_ref_btf_id.prog_fd; + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "bpf_prog_test_run(test_ref_btf_id)"); + ASSERT_EQ(topts.retval, 0, "test_ref_btf_id-retval"); kfunc_call_test_lskel__destroy(skel); } @@ -33,17 +41,21 @@ static void test_main(void) static void test_subprog(void) { struct kfunc_call_test_subprog *skel; - int prog_fd, retval, err; + int prog_fd, err; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .repeat = 1, + ); skel = kfunc_call_test_subprog__open_and_load(); if (!ASSERT_OK_PTR(skel, "skel")) return; prog_fd = bpf_program__fd(skel->progs.kfunc_call_test1); - err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4), - NULL, NULL, (__u32 *)&retval, NULL); + err = bpf_prog_test_run_opts(prog_fd, &topts); ASSERT_OK(err, "bpf_prog_test_run(test1)"); - ASSERT_EQ(retval, 10, "test1-retval"); + ASSERT_EQ(topts.retval, 10, "test1-retval"); ASSERT_NEQ(skel->data->active_res, -1, "active_res"); ASSERT_EQ(skel->data->sk_state_res, BPF_TCP_CLOSE, "sk_state_res"); @@ -53,17 +65,21 @@ static void test_subprog(void) static void test_subprog_lskel(void) { struct kfunc_call_test_subprog_lskel *skel; - int prog_fd, retval, err; + int prog_fd, err; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .repeat = 1, + ); skel = kfunc_call_test_subprog_lskel__open_and_load(); if (!ASSERT_OK_PTR(skel, "skel")) return; prog_fd = skel->progs.kfunc_call_test1.prog_fd; - err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4), - NULL, NULL, (__u32 *)&retval, NULL); + err = bpf_prog_test_run_opts(prog_fd, &topts); ASSERT_OK(err, "bpf_prog_test_run(test1)"); - ASSERT_EQ(retval, 10, "test1-retval"); + ASSERT_EQ(topts.retval, 10, "test1-retval"); ASSERT_NEQ(skel->data->active_res, -1, "active_res"); ASSERT_EQ(skel->data->sk_state_res, BPF_TCP_CLOSE, "sk_state_res"); diff --git a/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c new file mode 100644 index 000000000000..b9876b55fc0c --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c @@ -0,0 +1,323 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <test_progs.h> +#include "kprobe_multi.skel.h" +#include "trace_helpers.h" + +static void kprobe_multi_test_run(struct kprobe_multi *skel, bool test_return) +{ + LIBBPF_OPTS(bpf_test_run_opts, topts); + int err, prog_fd; + + prog_fd = bpf_program__fd(skel->progs.trigger); + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "test_run"); + ASSERT_EQ(topts.retval, 0, "test_run"); + + ASSERT_EQ(skel->bss->kprobe_test1_result, 1, "kprobe_test1_result"); + ASSERT_EQ(skel->bss->kprobe_test2_result, 1, "kprobe_test2_result"); + ASSERT_EQ(skel->bss->kprobe_test3_result, 1, "kprobe_test3_result"); + ASSERT_EQ(skel->bss->kprobe_test4_result, 1, "kprobe_test4_result"); + ASSERT_EQ(skel->bss->kprobe_test5_result, 1, "kprobe_test5_result"); + ASSERT_EQ(skel->bss->kprobe_test6_result, 1, "kprobe_test6_result"); + ASSERT_EQ(skel->bss->kprobe_test7_result, 1, "kprobe_test7_result"); + ASSERT_EQ(skel->bss->kprobe_test8_result, 1, "kprobe_test8_result"); + + if (test_return) { + ASSERT_EQ(skel->bss->kretprobe_test1_result, 1, "kretprobe_test1_result"); + ASSERT_EQ(skel->bss->kretprobe_test2_result, 1, "kretprobe_test2_result"); + ASSERT_EQ(skel->bss->kretprobe_test3_result, 1, "kretprobe_test3_result"); + ASSERT_EQ(skel->bss->kretprobe_test4_result, 1, "kretprobe_test4_result"); + ASSERT_EQ(skel->bss->kretprobe_test5_result, 1, "kretprobe_test5_result"); + ASSERT_EQ(skel->bss->kretprobe_test6_result, 1, "kretprobe_test6_result"); + ASSERT_EQ(skel->bss->kretprobe_test7_result, 1, "kretprobe_test7_result"); + ASSERT_EQ(skel->bss->kretprobe_test8_result, 1, "kretprobe_test8_result"); + } +} + +static void test_skel_api(void) +{ + struct kprobe_multi *skel = NULL; + int err; + + skel = kprobe_multi__open_and_load(); + if (!ASSERT_OK_PTR(skel, "kprobe_multi__open_and_load")) + goto cleanup; + + skel->bss->pid = getpid(); + err = kprobe_multi__attach(skel); + if (!ASSERT_OK(err, "kprobe_multi__attach")) + goto cleanup; + + kprobe_multi_test_run(skel, true); + +cleanup: + kprobe_multi__destroy(skel); +} + +static void test_link_api(struct bpf_link_create_opts *opts) +{ + int prog_fd, link1_fd = -1, link2_fd = -1; + struct kprobe_multi *skel = NULL; + + skel = kprobe_multi__open_and_load(); + if (!ASSERT_OK_PTR(skel, "fentry_raw_skel_load")) + goto cleanup; + + skel->bss->pid = getpid(); + prog_fd = bpf_program__fd(skel->progs.test_kprobe); + link1_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_KPROBE_MULTI, opts); + if (!ASSERT_GE(link1_fd, 0, "link_fd")) + goto cleanup; + + opts->kprobe_multi.flags = BPF_F_KPROBE_MULTI_RETURN; + prog_fd = bpf_program__fd(skel->progs.test_kretprobe); + link2_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_KPROBE_MULTI, opts); + if (!ASSERT_GE(link2_fd, 0, "link_fd")) + goto cleanup; + + kprobe_multi_test_run(skel, true); + +cleanup: + if (link1_fd != -1) + close(link1_fd); + if (link2_fd != -1) + close(link2_fd); + kprobe_multi__destroy(skel); +} + +#define GET_ADDR(__sym, __addr) ({ \ + __addr = ksym_get_addr(__sym); \ + if (!ASSERT_NEQ(__addr, 0, "kallsyms load failed for " #__sym)) \ + return; \ +}) + +static void test_link_api_addrs(void) +{ + LIBBPF_OPTS(bpf_link_create_opts, opts); + unsigned long long addrs[8]; + + GET_ADDR("bpf_fentry_test1", addrs[0]); + GET_ADDR("bpf_fentry_test2", addrs[1]); + GET_ADDR("bpf_fentry_test3", addrs[2]); + GET_ADDR("bpf_fentry_test4", addrs[3]); + GET_ADDR("bpf_fentry_test5", addrs[4]); + GET_ADDR("bpf_fentry_test6", addrs[5]); + GET_ADDR("bpf_fentry_test7", addrs[6]); + GET_ADDR("bpf_fentry_test8", addrs[7]); + + opts.kprobe_multi.addrs = (const unsigned long*) addrs; + opts.kprobe_multi.cnt = ARRAY_SIZE(addrs); + test_link_api(&opts); +} + +static void test_link_api_syms(void) +{ + LIBBPF_OPTS(bpf_link_create_opts, opts); + const char *syms[8] = { + "bpf_fentry_test1", + "bpf_fentry_test2", + "bpf_fentry_test3", + "bpf_fentry_test4", + "bpf_fentry_test5", + "bpf_fentry_test6", + "bpf_fentry_test7", + "bpf_fentry_test8", + }; + + opts.kprobe_multi.syms = syms; + opts.kprobe_multi.cnt = ARRAY_SIZE(syms); + test_link_api(&opts); +} + +static void +test_attach_api(const char *pattern, struct bpf_kprobe_multi_opts *opts) +{ + struct bpf_link *link1 = NULL, *link2 = NULL; + struct kprobe_multi *skel = NULL; + + skel = kprobe_multi__open_and_load(); + if (!ASSERT_OK_PTR(skel, "fentry_raw_skel_load")) + goto cleanup; + + skel->bss->pid = getpid(); + link1 = bpf_program__attach_kprobe_multi_opts(skel->progs.test_kprobe, + pattern, opts); + if (!ASSERT_OK_PTR(link1, "bpf_program__attach_kprobe_multi_opts")) + goto cleanup; + + if (opts) { + opts->retprobe = true; + link2 = bpf_program__attach_kprobe_multi_opts(skel->progs.test_kretprobe, + pattern, opts); + if (!ASSERT_OK_PTR(link2, "bpf_program__attach_kprobe_multi_opts")) + goto cleanup; + } + + kprobe_multi_test_run(skel, !!opts); + +cleanup: + bpf_link__destroy(link2); + bpf_link__destroy(link1); + kprobe_multi__destroy(skel); +} + +static void test_attach_api_pattern(void) +{ + LIBBPF_OPTS(bpf_kprobe_multi_opts, opts); + + test_attach_api("bpf_fentry_test*", &opts); + test_attach_api("bpf_fentry_test?", NULL); +} + +static void test_attach_api_addrs(void) +{ + LIBBPF_OPTS(bpf_kprobe_multi_opts, opts); + unsigned long long addrs[8]; + + GET_ADDR("bpf_fentry_test1", addrs[0]); + GET_ADDR("bpf_fentry_test2", addrs[1]); + GET_ADDR("bpf_fentry_test3", addrs[2]); + GET_ADDR("bpf_fentry_test4", addrs[3]); + GET_ADDR("bpf_fentry_test5", addrs[4]); + GET_ADDR("bpf_fentry_test6", addrs[5]); + GET_ADDR("bpf_fentry_test7", addrs[6]); + GET_ADDR("bpf_fentry_test8", addrs[7]); + + opts.addrs = (const unsigned long *) addrs; + opts.cnt = ARRAY_SIZE(addrs); + test_attach_api(NULL, &opts); +} + +static void test_attach_api_syms(void) +{ + LIBBPF_OPTS(bpf_kprobe_multi_opts, opts); + const char *syms[8] = { + "bpf_fentry_test1", + "bpf_fentry_test2", + "bpf_fentry_test3", + "bpf_fentry_test4", + "bpf_fentry_test5", + "bpf_fentry_test6", + "bpf_fentry_test7", + "bpf_fentry_test8", + }; + + opts.syms = syms; + opts.cnt = ARRAY_SIZE(syms); + test_attach_api(NULL, &opts); +} + +static void test_attach_api_fails(void) +{ + LIBBPF_OPTS(bpf_kprobe_multi_opts, opts); + struct kprobe_multi *skel = NULL; + struct bpf_link *link = NULL; + unsigned long long addrs[2]; + const char *syms[2] = { + "bpf_fentry_test1", + "bpf_fentry_test2", + }; + __u64 cookies[2]; + + addrs[0] = ksym_get_addr("bpf_fentry_test1"); + addrs[1] = ksym_get_addr("bpf_fentry_test2"); + + if (!ASSERT_FALSE(!addrs[0] || !addrs[1], "ksym_get_addr")) + goto cleanup; + + skel = kprobe_multi__open_and_load(); + if (!ASSERT_OK_PTR(skel, "fentry_raw_skel_load")) + goto cleanup; + + skel->bss->pid = getpid(); + + /* fail_1 - pattern and opts NULL */ + link = bpf_program__attach_kprobe_multi_opts(skel->progs.test_kprobe, + NULL, NULL); + if (!ASSERT_ERR_PTR(link, "fail_1")) + goto cleanup; + + if (!ASSERT_EQ(libbpf_get_error(link), -EINVAL, "fail_1_error")) + goto cleanup; + + /* fail_2 - both addrs and syms set */ + opts.addrs = (const unsigned long *) addrs; + opts.syms = syms; + opts.cnt = ARRAY_SIZE(syms); + opts.cookies = NULL; + + link = bpf_program__attach_kprobe_multi_opts(skel->progs.test_kprobe, + NULL, &opts); + if (!ASSERT_ERR_PTR(link, "fail_2")) + goto cleanup; + + if (!ASSERT_EQ(libbpf_get_error(link), -EINVAL, "fail_2_error")) + goto cleanup; + + /* fail_3 - pattern and addrs set */ + opts.addrs = (const unsigned long *) addrs; + opts.syms = NULL; + opts.cnt = ARRAY_SIZE(syms); + opts.cookies = NULL; + + link = bpf_program__attach_kprobe_multi_opts(skel->progs.test_kprobe, + "ksys_*", &opts); + if (!ASSERT_ERR_PTR(link, "fail_3")) + goto cleanup; + + if (!ASSERT_EQ(libbpf_get_error(link), -EINVAL, "fail_3_error")) + goto cleanup; + + /* fail_4 - pattern and cnt set */ + opts.addrs = NULL; + opts.syms = NULL; + opts.cnt = ARRAY_SIZE(syms); + opts.cookies = NULL; + + link = bpf_program__attach_kprobe_multi_opts(skel->progs.test_kprobe, + "ksys_*", &opts); + if (!ASSERT_ERR_PTR(link, "fail_4")) + goto cleanup; + + if (!ASSERT_EQ(libbpf_get_error(link), -EINVAL, "fail_4_error")) + goto cleanup; + + /* fail_5 - pattern and cookies */ + opts.addrs = NULL; + opts.syms = NULL; + opts.cnt = 0; + opts.cookies = cookies; + + link = bpf_program__attach_kprobe_multi_opts(skel->progs.test_kprobe, + "ksys_*", &opts); + if (!ASSERT_ERR_PTR(link, "fail_5")) + goto cleanup; + + if (!ASSERT_EQ(libbpf_get_error(link), -EINVAL, "fail_5_error")) + goto cleanup; + +cleanup: + bpf_link__destroy(link); + kprobe_multi__destroy(skel); +} + +void test_kprobe_multi_test(void) +{ + if (!ASSERT_OK(load_kallsyms(), "load_kallsyms")) + return; + + if (test__start_subtest("skel_api")) + test_skel_api(); + if (test__start_subtest("link_api_addrs")) + test_link_api_syms(); + if (test__start_subtest("link_api_syms")) + test_link_api_addrs(); + if (test__start_subtest("attach_api_pattern")) + test_attach_api_pattern(); + if (test__start_subtest("attach_api_addrs")) + test_attach_api_addrs(); + if (test__start_subtest("attach_api_syms")) + test_attach_api_syms(); + if (test__start_subtest("attach_api_fails")) + test_attach_api_fails(); +} diff --git a/tools/testing/selftests/bpf/prog_tests/ksyms_module.c b/tools/testing/selftests/bpf/prog_tests/ksyms_module.c index d490ad80eccb..a1ebac70ec29 100644 --- a/tools/testing/selftests/bpf/prog_tests/ksyms_module.c +++ b/tools/testing/selftests/bpf/prog_tests/ksyms_module.c @@ -6,11 +6,15 @@ #include "test_ksyms_module.lskel.h" #include "test_ksyms_module.skel.h" -void test_ksyms_module_lskel(void) +static void test_ksyms_module_lskel(void) { struct test_ksyms_module_lskel *skel; - int retval; int err; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .repeat = 1, + ); if (!env.has_testmod) { test__skip(); @@ -20,20 +24,24 @@ void test_ksyms_module_lskel(void) skel = test_ksyms_module_lskel__open_and_load(); if (!ASSERT_OK_PTR(skel, "test_ksyms_module_lskel__open_and_load")) return; - err = bpf_prog_test_run(skel->progs.load.prog_fd, 1, &pkt_v4, sizeof(pkt_v4), - NULL, NULL, (__u32 *)&retval, NULL); + err = bpf_prog_test_run_opts(skel->progs.load.prog_fd, &topts); if (!ASSERT_OK(err, "bpf_prog_test_run")) goto cleanup; - ASSERT_EQ(retval, 0, "retval"); + ASSERT_EQ(topts.retval, 0, "retval"); ASSERT_EQ(skel->bss->out_bpf_testmod_ksym, 42, "bpf_testmod_ksym"); cleanup: test_ksyms_module_lskel__destroy(skel); } -void test_ksyms_module_libbpf(void) +static void test_ksyms_module_libbpf(void) { struct test_ksyms_module *skel; - int retval, err; + int err; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .repeat = 1, + ); if (!env.has_testmod) { test__skip(); @@ -43,11 +51,10 @@ void test_ksyms_module_libbpf(void) skel = test_ksyms_module__open_and_load(); if (!ASSERT_OK_PTR(skel, "test_ksyms_module__open")) return; - err = bpf_prog_test_run(bpf_program__fd(skel->progs.load), 1, &pkt_v4, - sizeof(pkt_v4), NULL, NULL, (__u32 *)&retval, NULL); + err = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.load), &topts); if (!ASSERT_OK(err, "bpf_prog_test_run")) goto cleanup; - ASSERT_EQ(retval, 0, "retval"); + ASSERT_EQ(topts.retval, 0, "retval"); ASSERT_EQ(skel->bss->out_bpf_testmod_ksym, 42, "bpf_testmod_ksym"); cleanup: test_ksyms_module__destroy(skel); diff --git a/tools/testing/selftests/bpf/prog_tests/l4lb_all.c b/tools/testing/selftests/bpf/prog_tests/l4lb_all.c index 540ef28fabff..55f733ff4109 100644 --- a/tools/testing/selftests/bpf/prog_tests/l4lb_all.c +++ b/tools/testing/selftests/bpf/prog_tests/l4lb_all.c @@ -23,12 +23,16 @@ static void test_l4lb(const char *file) __u8 flags; } real_def = {.dst = MAGIC_VAL}; __u32 ch_key = 11, real_num = 3; - __u32 duration, retval, size; int err, i, prog_fd, map_fd; __u64 bytes = 0, pkts = 0; struct bpf_object *obj; char buf[128]; u32 *magic = (u32 *)buf; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_out = buf, + .data_size_out = sizeof(buf), + .repeat = NUM_ITER, + ); err = bpf_prog_test_load(file, BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd); if (CHECK_FAIL(err)) @@ -49,19 +53,24 @@ static void test_l4lb(const char *file) goto out; bpf_map_update_elem(map_fd, &real_num, &real_def, 0); - err = bpf_prog_test_run(prog_fd, NUM_ITER, &pkt_v4, sizeof(pkt_v4), - buf, &size, &retval, &duration); - CHECK(err || retval != 7/*TC_ACT_REDIRECT*/ || size != 54 || - *magic != MAGIC_VAL, "ipv4", - "err %d errno %d retval %d size %d magic %x\n", - err, errno, retval, size, *magic); + topts.data_in = &pkt_v4; + topts.data_size_in = sizeof(pkt_v4); - err = bpf_prog_test_run(prog_fd, NUM_ITER, &pkt_v6, sizeof(pkt_v6), - buf, &size, &retval, &duration); - CHECK(err || retval != 7/*TC_ACT_REDIRECT*/ || size != 74 || - *magic != MAGIC_VAL, "ipv6", - "err %d errno %d retval %d size %d magic %x\n", - err, errno, retval, size, *magic); + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "test_run"); + ASSERT_EQ(topts.retval, 7 /*TC_ACT_REDIRECT*/, "ipv4 test_run retval"); + ASSERT_EQ(topts.data_size_out, 54, "ipv4 test_run data_size_out"); + ASSERT_EQ(*magic, MAGIC_VAL, "ipv4 magic"); + + topts.data_in = &pkt_v6; + topts.data_size_in = sizeof(pkt_v6); + topts.data_size_out = sizeof(buf); /* reset out size */ + + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "test_run"); + ASSERT_EQ(topts.retval, 7 /*TC_ACT_REDIRECT*/, "ipv6 test_run retval"); + ASSERT_EQ(topts.data_size_out, 74, "ipv6 test_run data_size_out"); + ASSERT_EQ(*magic, MAGIC_VAL, "ipv6 magic"); map_fd = bpf_find_map(__func__, obj, "stats"); if (map_fd < 0) diff --git a/tools/testing/selftests/bpf/prog_tests/log_buf.c b/tools/testing/selftests/bpf/prog_tests/log_buf.c index e469b023962b..fe9a23e65ef4 100644 --- a/tools/testing/selftests/bpf/prog_tests/log_buf.c +++ b/tools/testing/selftests/bpf/prog_tests/log_buf.c @@ -78,7 +78,7 @@ static void obj_load_log_buf(void) ASSERT_OK_PTR(strstr(libbpf_log_buf, "prog 'bad_prog': BPF program load failed"), "libbpf_log_not_empty"); ASSERT_OK_PTR(strstr(obj_log_buf, "DATASEC license"), "obj_log_not_empty"); - ASSERT_OK_PTR(strstr(good_log_buf, "0: R1=ctx(id=0,off=0,imm=0) R10=fp0"), + ASSERT_OK_PTR(strstr(good_log_buf, "0: R1=ctx(off=0,imm=0) R10=fp0"), "good_log_verbose"); ASSERT_OK_PTR(strstr(bad_log_buf, "invalid access to map value, value_size=16 off=16000 size=4"), "bad_log_not_empty"); @@ -175,7 +175,7 @@ static void bpf_prog_load_log_buf(void) opts.log_level = 2; fd = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, "good_prog", "GPL", good_prog_insns, good_prog_insn_cnt, &opts); - ASSERT_OK_PTR(strstr(log_buf, "0: R1=ctx(id=0,off=0,imm=0) R10=fp0"), "good_log_2"); + ASSERT_OK_PTR(strstr(log_buf, "0: R1=ctx(off=0,imm=0) R10=fp0"), "good_log_2"); ASSERT_GE(fd, 0, "good_fd2"); if (fd >= 0) close(fd); @@ -202,7 +202,7 @@ static void bpf_btf_load_log_buf(void) const void *raw_btf_data; __u32 raw_btf_size; struct btf *btf; - char *log_buf; + char *log_buf = NULL; int fd = -1; btf = btf__new_empty(); diff --git a/tools/testing/selftests/bpf/prog_tests/map_lock.c b/tools/testing/selftests/bpf/prog_tests/map_lock.c index 23d19e9cf26a..e4e99b37df64 100644 --- a/tools/testing/selftests/bpf/prog_tests/map_lock.c +++ b/tools/testing/selftests/bpf/prog_tests/map_lock.c @@ -4,14 +4,17 @@ static void *spin_lock_thread(void *arg) { - __u32 duration, retval; int err, prog_fd = *(u32 *) arg; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .repeat = 10000, + ); + + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "test_run_opts err"); + ASSERT_OK(topts.retval, "test_run_opts retval"); - err = bpf_prog_test_run(prog_fd, 10000, &pkt_v4, sizeof(pkt_v4), - NULL, NULL, &retval, &duration); - CHECK(err || retval, "", - "err %d errno %d retval %d duration %d\n", - err, errno, retval, duration); pthread_exit(arg); } diff --git a/tools/testing/selftests/bpf/prog_tests/map_ptr.c b/tools/testing/selftests/bpf/prog_tests/map_ptr.c index 273725504f11..43e502acf050 100644 --- a/tools/testing/selftests/bpf/prog_tests/map_ptr.c +++ b/tools/testing/selftests/bpf/prog_tests/map_ptr.c @@ -9,10 +9,16 @@ void test_map_ptr(void) { struct map_ptr_kern_lskel *skel; - __u32 duration = 0, retval; char buf[128]; int err; int page_size = getpagesize(); + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .data_out = buf, + .data_size_out = sizeof(buf), + .repeat = 1, + ); skel = map_ptr_kern_lskel__open(); if (!ASSERT_OK_PTR(skel, "skel_open")) @@ -26,14 +32,12 @@ void test_map_ptr(void) skel->bss->page_size = page_size; - err = bpf_prog_test_run(skel->progs.cg_skb.prog_fd, 1, &pkt_v4, - sizeof(pkt_v4), buf, NULL, &retval, NULL); + err = bpf_prog_test_run_opts(skel->progs.cg_skb.prog_fd, &topts); - if (CHECK(err, "test_run", "err=%d errno=%d\n", err, errno)) + if (!ASSERT_OK(err, "test_run")) goto cleanup; - if (CHECK(!retval, "retval", "retval=%d map_type=%u line=%u\n", retval, - skel->bss->g_map_type, skel->bss->g_line)) + if (!ASSERT_NEQ(topts.retval, 0, "test_run retval")) goto cleanup; cleanup: diff --git a/tools/testing/selftests/bpf/prog_tests/modify_return.c b/tools/testing/selftests/bpf/prog_tests/modify_return.c index b772fe30ce9b..5d9955af6247 100644 --- a/tools/testing/selftests/bpf/prog_tests/modify_return.c +++ b/tools/testing/selftests/bpf/prog_tests/modify_return.c @@ -15,39 +15,31 @@ static void run_test(__u32 input_retval, __u16 want_side_effect, __s16 want_ret) { struct modify_return *skel = NULL; int err, prog_fd; - __u32 duration = 0, retval; __u16 side_effect; __s16 ret; + LIBBPF_OPTS(bpf_test_run_opts, topts); skel = modify_return__open_and_load(); - if (CHECK(!skel, "skel_load", "modify_return skeleton failed\n")) + if (!ASSERT_OK_PTR(skel, "skel_load")) goto cleanup; err = modify_return__attach(skel); - if (CHECK(err, "modify_return", "attach failed: %d\n", err)) + if (!ASSERT_OK(err, "modify_return__attach failed")) goto cleanup; skel->bss->input_retval = input_retval; prog_fd = bpf_program__fd(skel->progs.fmod_ret_test); - err = bpf_prog_test_run(prog_fd, 1, NULL, 0, NULL, 0, - &retval, &duration); + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "test_run"); - CHECK(err, "test_run", "err %d errno %d\n", err, errno); + side_effect = UPPER(topts.retval); + ret = LOWER(topts.retval); - side_effect = UPPER(retval); - ret = LOWER(retval); - - CHECK(ret != want_ret, "test_run", - "unexpected ret: %d, expected: %d\n", ret, want_ret); - CHECK(side_effect != want_side_effect, "modify_return", - "unexpected side_effect: %d\n", side_effect); - - CHECK(skel->bss->fentry_result != 1, "modify_return", - "fentry failed\n"); - CHECK(skel->bss->fexit_result != 1, "modify_return", - "fexit failed\n"); - CHECK(skel->bss->fmod_ret_result != 1, "modify_return", - "fmod_ret failed\n"); + ASSERT_EQ(ret, want_ret, "test_run ret"); + ASSERT_EQ(side_effect, want_side_effect, "modify_return side_effect"); + ASSERT_EQ(skel->bss->fentry_result, 1, "modify_return fentry_result"); + ASSERT_EQ(skel->bss->fexit_result, 1, "modify_return fexit_result"); + ASSERT_EQ(skel->bss->fmod_ret_result, 1, "modify_return fmod_ret_result"); cleanup: modify_return__destroy(skel); @@ -63,4 +55,3 @@ void serial_test_modify_return(void) 0 /* want_side_effect */, -EINVAL /* want_ret */); } - diff --git a/tools/testing/selftests/bpf/prog_tests/obj_name.c b/tools/testing/selftests/bpf/prog_tests/obj_name.c index 6194b776a28b..7093edca6e08 100644 --- a/tools/testing/selftests/bpf/prog_tests/obj_name.c +++ b/tools/testing/selftests/bpf/prog_tests/obj_name.c @@ -20,7 +20,7 @@ void test_obj_name(void) __u32 duration = 0; int i; - for (i = 0; i < sizeof(tests) / sizeof(tests[0]); i++) { + for (i = 0; i < ARRAY_SIZE(tests); i++) { size_t name_len = strlen(tests[i].name) + 1; union bpf_attr attr; size_t ncopy; diff --git a/tools/testing/selftests/bpf/prog_tests/perf_branches.c b/tools/testing/selftests/bpf/prog_tests/perf_branches.c index 12c4f45cee1a..bc24f83339d6 100644 --- a/tools/testing/selftests/bpf/prog_tests/perf_branches.c +++ b/tools/testing/selftests/bpf/prog_tests/perf_branches.c @@ -110,7 +110,7 @@ static void test_perf_branches_hw(void) attr.type = PERF_TYPE_HARDWARE; attr.config = PERF_COUNT_HW_CPU_CYCLES; attr.freq = 1; - attr.sample_freq = 4000; + attr.sample_freq = 1000; attr.sample_type = PERF_SAMPLE_BRANCH_STACK; attr.branch_sample_type = PERF_SAMPLE_BRANCH_USER | PERF_SAMPLE_BRANCH_ANY; pfd = syscall(__NR_perf_event_open, &attr, -1, 0, -1, PERF_FLAG_FD_CLOEXEC); @@ -151,7 +151,7 @@ static void test_perf_branches_no_hw(void) attr.type = PERF_TYPE_SOFTWARE; attr.config = PERF_COUNT_SW_CPU_CLOCK; attr.freq = 1; - attr.sample_freq = 4000; + attr.sample_freq = 1000; pfd = syscall(__NR_perf_event_open, &attr, -1, 0, -1, PERF_FLAG_FD_CLOEXEC); if (CHECK(pfd < 0, "perf_event_open", "err %d\n", pfd)) return; diff --git a/tools/testing/selftests/bpf/prog_tests/perf_link.c b/tools/testing/selftests/bpf/prog_tests/perf_link.c index ede07344f264..224eba6fef2e 100644 --- a/tools/testing/selftests/bpf/prog_tests/perf_link.c +++ b/tools/testing/selftests/bpf/prog_tests/perf_link.c @@ -39,7 +39,7 @@ void serial_test_perf_link(void) attr.type = PERF_TYPE_SOFTWARE; attr.config = PERF_COUNT_SW_CPU_CLOCK; attr.freq = 1; - attr.sample_freq = 4000; + attr.sample_freq = 1000; pfd = syscall(__NR_perf_event_open, &attr, -1, 0, -1, PERF_FLAG_FD_CLOEXEC); if (!ASSERT_GE(pfd, 0, "perf_fd")) goto cleanup; diff --git a/tools/testing/selftests/bpf/prog_tests/pkt_access.c b/tools/testing/selftests/bpf/prog_tests/pkt_access.c index 6628710ec3c6..0bcccdc34fbc 100644 --- a/tools/testing/selftests/bpf/prog_tests/pkt_access.c +++ b/tools/testing/selftests/bpf/prog_tests/pkt_access.c @@ -6,23 +6,27 @@ void test_pkt_access(void) { const char *file = "./test_pkt_access.o"; struct bpf_object *obj; - __u32 duration, retval; int err, prog_fd; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .repeat = 100000, + ); err = bpf_prog_test_load(file, BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd); if (CHECK_FAIL(err)) return; - err = bpf_prog_test_run(prog_fd, 100000, &pkt_v4, sizeof(pkt_v4), - NULL, NULL, &retval, &duration); - CHECK(err || retval, "ipv4", - "err %d errno %d retval %d duration %d\n", - err, errno, retval, duration); + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "ipv4 test_run_opts err"); + ASSERT_OK(topts.retval, "ipv4 test_run_opts retval"); + + topts.data_in = &pkt_v6; + topts.data_size_in = sizeof(pkt_v6); + topts.data_size_out = 0; /* reset from last call */ + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "ipv6 test_run_opts err"); + ASSERT_OK(topts.retval, "ipv6 test_run_opts retval"); - err = bpf_prog_test_run(prog_fd, 100000, &pkt_v6, sizeof(pkt_v6), - NULL, NULL, &retval, &duration); - CHECK(err || retval, "ipv6", - "err %d errno %d retval %d duration %d\n", - err, errno, retval, duration); bpf_object__close(obj); } diff --git a/tools/testing/selftests/bpf/prog_tests/pkt_md_access.c b/tools/testing/selftests/bpf/prog_tests/pkt_md_access.c index c9d2d6a1bfcc..00ee1dd792aa 100644 --- a/tools/testing/selftests/bpf/prog_tests/pkt_md_access.c +++ b/tools/testing/selftests/bpf/prog_tests/pkt_md_access.c @@ -6,18 +6,20 @@ void test_pkt_md_access(void) { const char *file = "./test_pkt_md_access.o"; struct bpf_object *obj; - __u32 duration, retval; int err, prog_fd; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .repeat = 10, + ); err = bpf_prog_test_load(file, BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd); if (CHECK_FAIL(err)) return; - err = bpf_prog_test_run(prog_fd, 10, &pkt_v4, sizeof(pkt_v4), - NULL, NULL, &retval, &duration); - CHECK(err || retval, "", - "err %d errno %d retval %d duration %d\n", - err, errno, retval, duration); + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "test_run_opts err"); + ASSERT_OK(topts.retval, "test_run_opts retval"); bpf_object__close(obj); } diff --git a/tools/testing/selftests/bpf/prog_tests/prog_run_opts.c b/tools/testing/selftests/bpf/prog_tests/prog_run_opts.c new file mode 100644 index 000000000000..1ccd2bdf8fa8 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/prog_run_opts.c @@ -0,0 +1,77 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <test_progs.h> +#include <network_helpers.h> + +#include "test_pkt_access.skel.h" + +static const __u32 duration; + +static void check_run_cnt(int prog_fd, __u64 run_cnt) +{ + struct bpf_prog_info info = {}; + __u32 info_len = sizeof(info); + int err; + + err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len); + if (CHECK(err, "get_prog_info", "failed to get bpf_prog_info for fd %d\n", prog_fd)) + return; + + CHECK(run_cnt != info.run_cnt, "run_cnt", + "incorrect number of repetitions, want %llu have %llu\n", run_cnt, info.run_cnt); +} + +void test_prog_run_opts(void) +{ + struct test_pkt_access *skel; + int err, stats_fd = -1, prog_fd; + char buf[10] = {}; + __u64 run_cnt = 0; + + LIBBPF_OPTS(bpf_test_run_opts, topts, + .repeat = 1, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .data_out = buf, + .data_size_out = 5, + ); + + stats_fd = bpf_enable_stats(BPF_STATS_RUN_TIME); + if (!ASSERT_GE(stats_fd, 0, "enable_stats good fd")) + return; + + skel = test_pkt_access__open_and_load(); + if (!ASSERT_OK_PTR(skel, "open_and_load")) + goto cleanup; + + prog_fd = bpf_program__fd(skel->progs.test_pkt_access); + + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_EQ(errno, ENOSPC, "test_run errno"); + ASSERT_ERR(err, "test_run"); + ASSERT_OK(topts.retval, "test_run retval"); + + ASSERT_EQ(topts.data_size_out, sizeof(pkt_v4), "test_run data_size_out"); + ASSERT_EQ(buf[5], 0, "overflow, BPF_PROG_TEST_RUN ignored size hint"); + + run_cnt += topts.repeat; + check_run_cnt(prog_fd, run_cnt); + + topts.data_out = NULL; + topts.data_size_out = 0; + topts.repeat = 2; + errno = 0; + + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(errno, "run_no_output errno"); + ASSERT_OK(err, "run_no_output err"); + ASSERT_OK(topts.retval, "run_no_output retval"); + + run_cnt += topts.repeat; + check_run_cnt(prog_fd, run_cnt); + +cleanup: + if (skel) + test_pkt_access__destroy(skel); + if (stats_fd >= 0) + close(stats_fd); +} diff --git a/tools/testing/selftests/bpf/prog_tests/prog_run_xattr.c b/tools/testing/selftests/bpf/prog_tests/prog_run_xattr.c deleted file mode 100644 index 89fc98faf19e..000000000000 --- a/tools/testing/selftests/bpf/prog_tests/prog_run_xattr.c +++ /dev/null @@ -1,83 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <test_progs.h> -#include <network_helpers.h> - -#include "test_pkt_access.skel.h" - -static const __u32 duration; - -static void check_run_cnt(int prog_fd, __u64 run_cnt) -{ - struct bpf_prog_info info = {}; - __u32 info_len = sizeof(info); - int err; - - err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len); - if (CHECK(err, "get_prog_info", "failed to get bpf_prog_info for fd %d\n", prog_fd)) - return; - - CHECK(run_cnt != info.run_cnt, "run_cnt", - "incorrect number of repetitions, want %llu have %llu\n", run_cnt, info.run_cnt); -} - -void test_prog_run_xattr(void) -{ - struct test_pkt_access *skel; - int err, stats_fd = -1; - char buf[10] = {}; - __u64 run_cnt = 0; - - struct bpf_prog_test_run_attr tattr = { - .repeat = 1, - .data_in = &pkt_v4, - .data_size_in = sizeof(pkt_v4), - .data_out = buf, - .data_size_out = 5, - }; - - stats_fd = bpf_enable_stats(BPF_STATS_RUN_TIME); - if (CHECK_ATTR(stats_fd < 0, "enable_stats", "failed %d\n", errno)) - return; - - skel = test_pkt_access__open_and_load(); - if (CHECK_ATTR(!skel, "open_and_load", "failed\n")) - goto cleanup; - - tattr.prog_fd = bpf_program__fd(skel->progs.test_pkt_access); - - err = bpf_prog_test_run_xattr(&tattr); - CHECK_ATTR(err >= 0 || errno != ENOSPC || tattr.retval, "run", - "err %d errno %d retval %d\n", err, errno, tattr.retval); - - CHECK_ATTR(tattr.data_size_out != sizeof(pkt_v4), "data_size_out", - "incorrect output size, want %zu have %u\n", - sizeof(pkt_v4), tattr.data_size_out); - - CHECK_ATTR(buf[5] != 0, "overflow", - "BPF_PROG_TEST_RUN ignored size hint\n"); - - run_cnt += tattr.repeat; - check_run_cnt(tattr.prog_fd, run_cnt); - - tattr.data_out = NULL; - tattr.data_size_out = 0; - tattr.repeat = 2; - errno = 0; - - err = bpf_prog_test_run_xattr(&tattr); - CHECK_ATTR(err || errno || tattr.retval, "run_no_output", - "err %d errno %d retval %d\n", err, errno, tattr.retval); - - tattr.data_size_out = 1; - err = bpf_prog_test_run_xattr(&tattr); - CHECK_ATTR(err != -EINVAL, "run_wrong_size_out", "err %d\n", err); - - run_cnt += tattr.repeat; - check_run_cnt(tattr.prog_fd, run_cnt); - -cleanup: - if (skel) - test_pkt_access__destroy(skel); - if (stats_fd >= 0) - close(stats_fd); -} diff --git a/tools/testing/selftests/bpf/prog_tests/queue_stack_map.c b/tools/testing/selftests/bpf/prog_tests/queue_stack_map.c index b9822f914eeb..d2743fc10032 100644 --- a/tools/testing/selftests/bpf/prog_tests/queue_stack_map.c +++ b/tools/testing/selftests/bpf/prog_tests/queue_stack_map.c @@ -10,11 +10,18 @@ enum { static void test_queue_stack_map_by_type(int type) { const int MAP_SIZE = 32; - __u32 vals[MAP_SIZE], duration, retval, size, val; + __u32 vals[MAP_SIZE], val; int i, err, prog_fd, map_in_fd, map_out_fd; char file[32], buf[128]; struct bpf_object *obj; struct iphdr iph; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .data_out = buf, + .data_size_out = sizeof(buf), + .repeat = 1, + ); /* Fill test values to be used */ for (i = 0; i < MAP_SIZE; i++) @@ -58,38 +65,37 @@ static void test_queue_stack_map_by_type(int type) pkt_v4.iph.saddr = vals[MAP_SIZE - 1 - i] * 5; } - err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4), - buf, &size, &retval, &duration); - if (err || retval || size != sizeof(pkt_v4)) + topts.data_size_out = sizeof(buf); + err = bpf_prog_test_run_opts(prog_fd, &topts); + if (err || topts.retval || + topts.data_size_out != sizeof(pkt_v4)) break; memcpy(&iph, buf + sizeof(struct ethhdr), sizeof(iph)); if (iph.daddr != val) break; } - CHECK(err || retval || size != sizeof(pkt_v4) || iph.daddr != val, - "bpf_map_pop_elem", - "err %d errno %d retval %d size %d iph->daddr %u\n", - err, errno, retval, size, iph.daddr); + ASSERT_OK(err, "bpf_map_pop_elem"); + ASSERT_OK(topts.retval, "bpf_map_pop_elem test retval"); + ASSERT_EQ(topts.data_size_out, sizeof(pkt_v4), + "bpf_map_pop_elem data_size_out"); + ASSERT_EQ(iph.daddr, val, "bpf_map_pop_elem iph.daddr"); /* Queue is empty, program should return TC_ACT_SHOT */ - err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4), - buf, &size, &retval, &duration); - CHECK(err || retval != 2 /* TC_ACT_SHOT */|| size != sizeof(pkt_v4), - "check-queue-stack-map-empty", - "err %d errno %d retval %d size %d\n", - err, errno, retval, size); + topts.data_size_out = sizeof(buf); + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "check-queue-stack-map-empty"); + ASSERT_EQ(topts.retval, 2 /* TC_ACT_SHOT */, + "check-queue-stack-map-empty test retval"); + ASSERT_EQ(topts.data_size_out, sizeof(pkt_v4), + "check-queue-stack-map-empty data_size_out"); /* Check that the program pushed elements correctly */ for (i = 0; i < MAP_SIZE; i++) { err = bpf_map_lookup_and_delete_elem(map_out_fd, NULL, &val); - if (err || val != vals[i] * 5) - break; + ASSERT_OK(err, "bpf_map_lookup_and_delete_elem"); + ASSERT_EQ(val, vals[i] * 5, "bpf_map_push_elem val"); } - - CHECK(i != MAP_SIZE && (err || val != vals[i] * 5), - "bpf_map_push_elem", "err %d value %u\n", err, val); - out: pkt_v4.iph.saddr = 0; bpf_object__close(obj); diff --git a/tools/testing/selftests/bpf/prog_tests/raw_tp_test_run.c b/tools/testing/selftests/bpf/prog_tests/raw_tp_test_run.c index 41720a62c4fa..fe5b8fae2c36 100644 --- a/tools/testing/selftests/bpf/prog_tests/raw_tp_test_run.c +++ b/tools/testing/selftests/bpf/prog_tests/raw_tp_test_run.c @@ -5,59 +5,54 @@ #include "bpf/libbpf_internal.h" #include "test_raw_tp_test_run.skel.h" -static int duration; - void test_raw_tp_test_run(void) { - struct bpf_prog_test_run_attr test_attr = {}; int comm_fd = -1, err, nr_online, i, prog_fd; __u64 args[2] = {0x1234ULL, 0x5678ULL}; int expected_retval = 0x1234 + 0x5678; struct test_raw_tp_test_run *skel; char buf[] = "new_name"; bool *online = NULL; - DECLARE_LIBBPF_OPTS(bpf_test_run_opts, opts, - .ctx_in = args, - .ctx_size_in = sizeof(args), - .flags = BPF_F_TEST_RUN_ON_CPU, - ); + LIBBPF_OPTS(bpf_test_run_opts, opts, + .ctx_in = args, + .ctx_size_in = sizeof(args), + .flags = BPF_F_TEST_RUN_ON_CPU, + ); err = parse_cpu_mask_file("/sys/devices/system/cpu/online", &online, &nr_online); - if (CHECK(err, "parse_cpu_mask_file", "err %d\n", err)) + if (!ASSERT_OK(err, "parse_cpu_mask_file")) return; skel = test_raw_tp_test_run__open_and_load(); - if (CHECK(!skel, "skel_open", "failed to open skeleton\n")) + if (!ASSERT_OK_PTR(skel, "skel_open")) goto cleanup; err = test_raw_tp_test_run__attach(skel); - if (CHECK(err, "skel_attach", "skeleton attach failed: %d\n", err)) + if (!ASSERT_OK(err, "skel_attach")) goto cleanup; comm_fd = open("/proc/self/comm", O_WRONLY|O_TRUNC); - if (CHECK(comm_fd < 0, "open /proc/self/comm", "err %d\n", errno)) + if (!ASSERT_GE(comm_fd, 0, "open /proc/self/comm")) goto cleanup; err = write(comm_fd, buf, sizeof(buf)); - CHECK(err < 0, "task rename", "err %d", errno); + ASSERT_GE(err, 0, "task rename"); - CHECK(skel->bss->count == 0, "check_count", "didn't increase\n"); - CHECK(skel->data->on_cpu != 0xffffffff, "check_on_cpu", "got wrong value\n"); + ASSERT_NEQ(skel->bss->count, 0, "check_count"); + ASSERT_EQ(skel->data->on_cpu, 0xffffffff, "check_on_cpu"); prog_fd = bpf_program__fd(skel->progs.rename); - test_attr.prog_fd = prog_fd; - test_attr.ctx_in = args; - test_attr.ctx_size_in = sizeof(__u64); + opts.ctx_in = args; + opts.ctx_size_in = sizeof(__u64); - err = bpf_prog_test_run_xattr(&test_attr); - CHECK(err == 0, "test_run", "should fail for too small ctx\n"); + err = bpf_prog_test_run_opts(prog_fd, &opts); + ASSERT_NEQ(err, 0, "test_run should fail for too small ctx"); - test_attr.ctx_size_in = sizeof(args); - err = bpf_prog_test_run_xattr(&test_attr); - CHECK(err < 0, "test_run", "err %d\n", errno); - CHECK(test_attr.retval != expected_retval, "check_retval", - "expect 0x%x, got 0x%x\n", expected_retval, test_attr.retval); + opts.ctx_size_in = sizeof(args); + err = bpf_prog_test_run_opts(prog_fd, &opts); + ASSERT_OK(err, "test_run"); + ASSERT_EQ(opts.retval, expected_retval, "check_retval"); for (i = 0; i < nr_online; i++) { if (!online[i]) @@ -66,28 +61,23 @@ void test_raw_tp_test_run(void) opts.cpu = i; opts.retval = 0; err = bpf_prog_test_run_opts(prog_fd, &opts); - CHECK(err < 0, "test_run_opts", "err %d\n", errno); - CHECK(skel->data->on_cpu != i, "check_on_cpu", - "expect %d got %d\n", i, skel->data->on_cpu); - CHECK(opts.retval != expected_retval, - "check_retval", "expect 0x%x, got 0x%x\n", - expected_retval, opts.retval); + ASSERT_OK(err, "test_run_opts"); + ASSERT_EQ(skel->data->on_cpu, i, "check_on_cpu"); + ASSERT_EQ(opts.retval, expected_retval, "check_retval"); } /* invalid cpu ID should fail with ENXIO */ opts.cpu = 0xffffffff; err = bpf_prog_test_run_opts(prog_fd, &opts); - CHECK(err >= 0 || errno != ENXIO, - "test_run_opts_fail", - "should failed with ENXIO\n"); + ASSERT_EQ(errno, ENXIO, "test_run_opts should fail with ENXIO"); + ASSERT_ERR(err, "test_run_opts_fail"); /* non-zero cpu w/o BPF_F_TEST_RUN_ON_CPU should fail with EINVAL */ opts.cpu = 1; opts.flags = 0; err = bpf_prog_test_run_opts(prog_fd, &opts); - CHECK(err >= 0 || errno != EINVAL, - "test_run_opts_fail", - "should failed with EINVAL\n"); + ASSERT_EQ(errno, EINVAL, "test_run_opts should fail with EINVAL"); + ASSERT_ERR(err, "test_run_opts_fail"); cleanup: close(comm_fd); diff --git a/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_test_run.c b/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_test_run.c index 239baccabccb..f4aa7dab4766 100644 --- a/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_test_run.c +++ b/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_test_run.c @@ -56,21 +56,23 @@ void serial_test_raw_tp_writable_test_run(void) 0, }; - __u32 prog_ret; - int err = bpf_prog_test_run(filter_fd, 1, test_skb, sizeof(test_skb), 0, - 0, &prog_ret, 0); + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = test_skb, + .data_size_in = sizeof(test_skb), + .repeat = 1, + ); + int err = bpf_prog_test_run_opts(filter_fd, &topts); CHECK(err != 42, "test_run", "tracepoint did not modify return value\n"); - CHECK(prog_ret != 0, "test_run_ret", + CHECK(topts.retval != 0, "test_run_ret", "socket_filter did not return 0\n"); close(tp_fd); - err = bpf_prog_test_run(filter_fd, 1, test_skb, sizeof(test_skb), 0, 0, - &prog_ret, 0); + err = bpf_prog_test_run_opts(filter_fd, &topts); CHECK(err != 0, "test_run_notrace", "test_run failed with %d errno %d\n", err, errno); - CHECK(prog_ret != 0, "test_run_ret_notrace", + CHECK(topts.retval != 0, "test_run_ret_notrace", "socket_filter did not return 0\n"); out_filterfd: diff --git a/tools/testing/selftests/bpf/prog_tests/send_signal.c b/tools/testing/selftests/bpf/prog_tests/send_signal.c index 776916b61c40..d71226e34c34 100644 --- a/tools/testing/selftests/bpf/prog_tests/send_signal.c +++ b/tools/testing/selftests/bpf/prog_tests/send_signal.c @@ -4,11 +4,11 @@ #include <sys/resource.h> #include "test_send_signal_kern.skel.h" -int sigusr1_received = 0; +static int sigusr1_received; static void sigusr1_handler(int signum) { - sigusr1_received++; + sigusr1_received = 1; } static void test_send_signal_common(struct perf_event_attr *attr, @@ -40,9 +40,10 @@ static void test_send_signal_common(struct perf_event_attr *attr, if (pid == 0) { int old_prio; + volatile int j = 0; /* install signal handler and notify parent */ - signal(SIGUSR1, sigusr1_handler); + ASSERT_NEQ(signal(SIGUSR1, sigusr1_handler), SIG_ERR, "signal"); close(pipe_c2p[0]); /* close read */ close(pipe_p2c[1]); /* close write */ @@ -63,9 +64,11 @@ static void test_send_signal_common(struct perf_event_attr *attr, ASSERT_EQ(read(pipe_p2c[0], buf, 1), 1, "pipe_read"); /* wait a little for signal handler */ - sleep(1); + for (int i = 0; i < 100000000 && !sigusr1_received; i++) + j /= i + j + 1; buf[0] = sigusr1_received ? '2' : '0'; + ASSERT_EQ(sigusr1_received, 1, "sigusr1_received"); ASSERT_EQ(write(pipe_c2p[1], buf, 1), 1, "pipe_write"); /* wait for parent notification and exit */ @@ -93,7 +96,7 @@ static void test_send_signal_common(struct perf_event_attr *attr, goto destroy_skel; } } else { - pmu_fd = syscall(__NR_perf_event_open, attr, pid, -1, + pmu_fd = syscall(__NR_perf_event_open, attr, pid, -1 /* cpu */, -1 /* group id */, 0 /* flags */); if (!ASSERT_GE(pmu_fd, 0, "perf_event_open")) { err = -1; @@ -110,9 +113,9 @@ static void test_send_signal_common(struct perf_event_attr *attr, ASSERT_EQ(read(pipe_c2p[0], buf, 1), 1, "pipe_read"); /* trigger the bpf send_signal */ - skel->bss->pid = pid; - skel->bss->sig = SIGUSR1; skel->bss->signal_thread = signal_thread; + skel->bss->sig = SIGUSR1; + skel->bss->pid = pid; /* notify child that bpf program can send_signal now */ ASSERT_EQ(write(pipe_p2c[1], buf, 1), 1, "pipe_write"); diff --git a/tools/testing/selftests/bpf/prog_tests/signal_pending.c b/tools/testing/selftests/bpf/prog_tests/signal_pending.c index aecfe662c070..70b49da5ca0a 100644 --- a/tools/testing/selftests/bpf/prog_tests/signal_pending.c +++ b/tools/testing/selftests/bpf/prog_tests/signal_pending.c @@ -13,10 +13,14 @@ static void test_signal_pending_by_type(enum bpf_prog_type prog_type) struct itimerval timeo = { .it_value.tv_usec = 100000, /* 100ms */ }; - __u32 duration = 0, retval; int prog_fd; int err; int i; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .repeat = 0xffffffff, + ); for (i = 0; i < ARRAY_SIZE(prog); i++) prog[i] = BPF_ALU64_IMM(BPF_MOV, BPF_REG_0, 0); @@ -24,20 +28,17 @@ static void test_signal_pending_by_type(enum bpf_prog_type prog_type) prog_fd = bpf_test_load_program(prog_type, prog, ARRAY_SIZE(prog), "GPL", 0, NULL, 0); - CHECK(prog_fd < 0, "test-run", "errno %d\n", errno); + ASSERT_GE(prog_fd, 0, "test-run load"); err = sigaction(SIGALRM, &sigalrm_action, NULL); - CHECK(err, "test-run-signal-sigaction", "errno %d\n", errno); + ASSERT_OK(err, "test-run-signal-sigaction"); err = setitimer(ITIMER_REAL, &timeo, NULL); - CHECK(err, "test-run-signal-timer", "errno %d\n", errno); - - err = bpf_prog_test_run(prog_fd, 0xffffffff, &pkt_v4, sizeof(pkt_v4), - NULL, NULL, &retval, &duration); - CHECK(duration > 500000000, /* 500ms */ - "test-run-signal-duration", - "duration %dns > 500ms\n", - duration); + ASSERT_OK(err, "test-run-signal-timer"); + + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_LE(topts.duration, 500000000 /* 500ms */, + "test-run-signal-duration"); signal(SIGALRM, SIG_DFL); } diff --git a/tools/testing/selftests/bpf/prog_tests/skb_ctx.c b/tools/testing/selftests/bpf/prog_tests/skb_ctx.c index b5319ba2ee27..ce0e555b5e38 100644 --- a/tools/testing/selftests/bpf/prog_tests/skb_ctx.c +++ b/tools/testing/selftests/bpf/prog_tests/skb_ctx.c @@ -20,97 +20,72 @@ void test_skb_ctx(void) .gso_size = 10, .hwtstamp = 11, }; - struct bpf_prog_test_run_attr tattr = { + LIBBPF_OPTS(bpf_test_run_opts, tattr, .data_in = &pkt_v4, .data_size_in = sizeof(pkt_v4), .ctx_in = &skb, .ctx_size_in = sizeof(skb), .ctx_out = &skb, .ctx_size_out = sizeof(skb), - }; + ); struct bpf_object *obj; - int err; - int i; + int err, prog_fd, i; - err = bpf_prog_test_load("./test_skb_ctx.o", BPF_PROG_TYPE_SCHED_CLS, &obj, - &tattr.prog_fd); - if (CHECK_ATTR(err, "load", "err %d errno %d\n", err, errno)) + err = bpf_prog_test_load("./test_skb_ctx.o", BPF_PROG_TYPE_SCHED_CLS, + &obj, &prog_fd); + if (!ASSERT_OK(err, "load")) return; /* ctx_in != NULL, ctx_size_in == 0 */ tattr.ctx_size_in = 0; - err = bpf_prog_test_run_xattr(&tattr); - CHECK_ATTR(err == 0, "ctx_size_in", "err %d errno %d\n", err, errno); + err = bpf_prog_test_run_opts(prog_fd, &tattr); + ASSERT_NEQ(err, 0, "ctx_size_in"); tattr.ctx_size_in = sizeof(skb); /* ctx_out != NULL, ctx_size_out == 0 */ tattr.ctx_size_out = 0; - err = bpf_prog_test_run_xattr(&tattr); - CHECK_ATTR(err == 0, "ctx_size_out", "err %d errno %d\n", err, errno); + err = bpf_prog_test_run_opts(prog_fd, &tattr); + ASSERT_NEQ(err, 0, "ctx_size_out"); tattr.ctx_size_out = sizeof(skb); /* non-zero [len, tc_index] fields should be rejected*/ skb.len = 1; - err = bpf_prog_test_run_xattr(&tattr); - CHECK_ATTR(err == 0, "len", "err %d errno %d\n", err, errno); + err = bpf_prog_test_run_opts(prog_fd, &tattr); + ASSERT_NEQ(err, 0, "len"); skb.len = 0; skb.tc_index = 1; - err = bpf_prog_test_run_xattr(&tattr); - CHECK_ATTR(err == 0, "tc_index", "err %d errno %d\n", err, errno); + err = bpf_prog_test_run_opts(prog_fd, &tattr); + ASSERT_NEQ(err, 0, "tc_index"); skb.tc_index = 0; /* non-zero [hash, sk] fields should be rejected */ skb.hash = 1; - err = bpf_prog_test_run_xattr(&tattr); - CHECK_ATTR(err == 0, "hash", "err %d errno %d\n", err, errno); + err = bpf_prog_test_run_opts(prog_fd, &tattr); + ASSERT_NEQ(err, 0, "hash"); skb.hash = 0; skb.sk = (struct bpf_sock *)1; - err = bpf_prog_test_run_xattr(&tattr); - CHECK_ATTR(err == 0, "sk", "err %d errno %d\n", err, errno); + err = bpf_prog_test_run_opts(prog_fd, &tattr); + ASSERT_NEQ(err, 0, "sk"); skb.sk = 0; - err = bpf_prog_test_run_xattr(&tattr); - CHECK_ATTR(err != 0 || tattr.retval, - "run", - "err %d errno %d retval %d\n", - err, errno, tattr.retval); - - CHECK_ATTR(tattr.ctx_size_out != sizeof(skb), - "ctx_size_out", - "incorrect output size, want %zu have %u\n", - sizeof(skb), tattr.ctx_size_out); + err = bpf_prog_test_run_opts(prog_fd, &tattr); + ASSERT_OK(err, "test_run"); + ASSERT_OK(tattr.retval, "test_run retval"); + ASSERT_EQ(tattr.ctx_size_out, sizeof(skb), "ctx_size_out"); for (i = 0; i < 5; i++) - CHECK_ATTR(skb.cb[i] != i + 2, - "ctx_out_cb", - "skb->cb[i] == %d, expected %d\n", - skb.cb[i], i + 2); - CHECK_ATTR(skb.priority != 7, - "ctx_out_priority", - "skb->priority == %d, expected %d\n", - skb.priority, 7); - CHECK_ATTR(skb.ifindex != 1, - "ctx_out_ifindex", - "skb->ifindex == %d, expected %d\n", - skb.ifindex, 1); - CHECK_ATTR(skb.ingress_ifindex != 11, - "ctx_out_ingress_ifindex", - "skb->ingress_ifindex == %d, expected %d\n", - skb.ingress_ifindex, 11); - CHECK_ATTR(skb.tstamp != 8, - "ctx_out_tstamp", - "skb->tstamp == %lld, expected %d\n", - skb.tstamp, 8); - CHECK_ATTR(skb.mark != 10, - "ctx_out_mark", - "skb->mark == %u, expected %d\n", - skb.mark, 10); + ASSERT_EQ(skb.cb[i], i + 2, "ctx_out_cb"); + ASSERT_EQ(skb.priority, 7, "ctx_out_priority"); + ASSERT_EQ(skb.ifindex, 1, "ctx_out_ifindex"); + ASSERT_EQ(skb.ingress_ifindex, 11, "ctx_out_ingress_ifindex"); + ASSERT_EQ(skb.tstamp, 8, "ctx_out_tstamp"); + ASSERT_EQ(skb.mark, 10, "ctx_out_mark"); bpf_object__close(obj); } diff --git a/tools/testing/selftests/bpf/prog_tests/skb_helpers.c b/tools/testing/selftests/bpf/prog_tests/skb_helpers.c index 6f802a1c0800..97dc8b14be48 100644 --- a/tools/testing/selftests/bpf/prog_tests/skb_helpers.c +++ b/tools/testing/selftests/bpf/prog_tests/skb_helpers.c @@ -9,22 +9,22 @@ void test_skb_helpers(void) .gso_segs = 8, .gso_size = 10, }; - struct bpf_prog_test_run_attr tattr = { + LIBBPF_OPTS(bpf_test_run_opts, topts, .data_in = &pkt_v4, .data_size_in = sizeof(pkt_v4), .ctx_in = &skb, .ctx_size_in = sizeof(skb), .ctx_out = &skb, .ctx_size_out = sizeof(skb), - }; + ); struct bpf_object *obj; - int err; + int err, prog_fd; - err = bpf_prog_test_load("./test_skb_helpers.o", BPF_PROG_TYPE_SCHED_CLS, &obj, - &tattr.prog_fd); - if (CHECK_ATTR(err, "load", "err %d errno %d\n", err, errno)) + err = bpf_prog_test_load("./test_skb_helpers.o", + BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd); + if (!ASSERT_OK(err, "load")) return; - err = bpf_prog_test_run_xattr(&tattr); - CHECK_ATTR(err, "len", "err %d errno %d\n", err, errno); + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "test_run"); bpf_object__close(obj); } diff --git a/tools/testing/selftests/bpf/prog_tests/sock_fields.c b/tools/testing/selftests/bpf/prog_tests/sock_fields.c index 9fc040eaa482..9d211b5c22c4 100644 --- a/tools/testing/selftests/bpf/prog_tests/sock_fields.c +++ b/tools/testing/selftests/bpf/prog_tests/sock_fields.c @@ -1,9 +1,11 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2019 Facebook */ +#define _GNU_SOURCE #include <netinet/in.h> #include <arpa/inet.h> #include <unistd.h> +#include <sched.h> #include <stdlib.h> #include <string.h> #include <errno.h> @@ -20,6 +22,7 @@ enum bpf_linum_array_idx { EGRESS_LINUM_IDX, INGRESS_LINUM_IDX, + READ_SK_DST_PORT_LINUM_IDX, __NR_BPF_LINUM_ARRAY_IDX, }; @@ -42,8 +45,16 @@ static __u64 child_cg_id; static int linum_map_fd; static __u32 duration; -static __u32 egress_linum_idx = EGRESS_LINUM_IDX; -static __u32 ingress_linum_idx = INGRESS_LINUM_IDX; +static bool create_netns(void) +{ + if (!ASSERT_OK(unshare(CLONE_NEWNET), "create netns")) + return false; + + if (!ASSERT_OK(system("ip link set dev lo up"), "bring up lo")) + return false; + + return true; +} static void print_sk(const struct bpf_sock *sk, const char *prefix) { @@ -91,19 +102,24 @@ static void check_result(void) { struct bpf_tcp_sock srv_tp, cli_tp, listen_tp; struct bpf_sock srv_sk, cli_sk, listen_sk; - __u32 ingress_linum, egress_linum; + __u32 idx, ingress_linum, egress_linum, linum; int err; - err = bpf_map_lookup_elem(linum_map_fd, &egress_linum_idx, - &egress_linum); + idx = EGRESS_LINUM_IDX; + err = bpf_map_lookup_elem(linum_map_fd, &idx, &egress_linum); CHECK(err < 0, "bpf_map_lookup_elem(linum_map_fd)", "err:%d errno:%d\n", err, errno); - err = bpf_map_lookup_elem(linum_map_fd, &ingress_linum_idx, - &ingress_linum); + idx = INGRESS_LINUM_IDX; + err = bpf_map_lookup_elem(linum_map_fd, &idx, &ingress_linum); CHECK(err < 0, "bpf_map_lookup_elem(linum_map_fd)", "err:%d errno:%d\n", err, errno); + idx = READ_SK_DST_PORT_LINUM_IDX; + err = bpf_map_lookup_elem(linum_map_fd, &idx, &linum); + ASSERT_OK(err, "bpf_map_lookup_elem(linum_map_fd, READ_SK_DST_PORT_IDX)"); + ASSERT_EQ(linum, 0, "failure in read_sk_dst_port on line"); + memcpy(&srv_sk, &skel->bss->srv_sk, sizeof(srv_sk)); memcpy(&srv_tp, &skel->bss->srv_tp, sizeof(srv_tp)); memcpy(&cli_sk, &skel->bss->cli_sk, sizeof(cli_sk)); @@ -262,7 +278,7 @@ static void test(void) char buf[DATA_LEN]; /* Prepare listen_fd */ - listen_fd = start_server(AF_INET6, SOCK_STREAM, "::1", 0, 0); + listen_fd = start_server(AF_INET6, SOCK_STREAM, "::1", 0xcafe, 0); /* start_server() has logged the error details */ if (CHECK_FAIL(listen_fd == -1)) goto done; @@ -330,8 +346,12 @@ done: void serial_test_sock_fields(void) { - struct bpf_link *egress_link = NULL, *ingress_link = NULL; int parent_cg_fd = -1, child_cg_fd = -1; + struct bpf_link *link; + + /* Use a dedicated netns to have a fixed listen port */ + if (!create_netns()) + return; /* Create a cgroup, get fd, and join it */ parent_cg_fd = test__join_cgroup(PARENT_CGROUP); @@ -352,15 +372,20 @@ void serial_test_sock_fields(void) if (CHECK(!skel, "test_sock_fields__open_and_load", "failed\n")) goto done; - egress_link = bpf_program__attach_cgroup(skel->progs.egress_read_sock_fields, - child_cg_fd); - if (!ASSERT_OK_PTR(egress_link, "attach_cgroup(egress)")) + link = bpf_program__attach_cgroup(skel->progs.egress_read_sock_fields, child_cg_fd); + if (!ASSERT_OK_PTR(link, "attach_cgroup(egress_read_sock_fields)")) + goto done; + skel->links.egress_read_sock_fields = link; + + link = bpf_program__attach_cgroup(skel->progs.ingress_read_sock_fields, child_cg_fd); + if (!ASSERT_OK_PTR(link, "attach_cgroup(ingress_read_sock_fields)")) goto done; + skel->links.ingress_read_sock_fields = link; - ingress_link = bpf_program__attach_cgroup(skel->progs.ingress_read_sock_fields, - child_cg_fd); - if (!ASSERT_OK_PTR(ingress_link, "attach_cgroup(ingress)")) + link = bpf_program__attach_cgroup(skel->progs.read_sk_dst_port, child_cg_fd); + if (!ASSERT_OK_PTR(link, "attach_cgroup(read_sk_dst_port")) goto done; + skel->links.read_sk_dst_port = link; linum_map_fd = bpf_map__fd(skel->maps.linum_map); sk_pkt_out_cnt_fd = bpf_map__fd(skel->maps.sk_pkt_out_cnt); @@ -369,8 +394,7 @@ void serial_test_sock_fields(void) test(); done: - bpf_link__destroy(egress_link); - bpf_link__destroy(ingress_link); + test_sock_fields__detach(skel); test_sock_fields__destroy(skel); if (child_cg_fd >= 0) close(child_cg_fd); diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c index 85db0f4cdd95..cec5c0882372 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c @@ -8,6 +8,7 @@ #include "test_sockmap_update.skel.h" #include "test_sockmap_invalid_update.skel.h" #include "test_sockmap_skb_verdict_attach.skel.h" +#include "test_sockmap_progs_query.skel.h" #include "bpf_iter_sockmap.skel.h" #define TCP_REPAIR 19 /* TCP sock is under repair right now */ @@ -139,12 +140,16 @@ out: static void test_sockmap_update(enum bpf_map_type map_type) { - struct bpf_prog_test_run_attr tattr; int err, prog, src, duration = 0; struct test_sockmap_update *skel; struct bpf_map *dst_map; const __u32 zero = 0; char dummy[14] = {0}; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = dummy, + .data_size_in = sizeof(dummy), + .repeat = 1, + ); __s64 sk; sk = connected_socket_v4(); @@ -166,16 +171,10 @@ static void test_sockmap_update(enum bpf_map_type map_type) if (CHECK(err, "update_elem(src)", "errno=%u\n", errno)) goto out; - tattr = (struct bpf_prog_test_run_attr){ - .prog_fd = prog, - .repeat = 1, - .data_in = dummy, - .data_size_in = sizeof(dummy), - }; - - err = bpf_prog_test_run_xattr(&tattr); - if (CHECK_ATTR(err || !tattr.retval, "bpf_prog_test_run", - "errno=%u retval=%u\n", errno, tattr.retval)) + err = bpf_prog_test_run_opts(prog, &topts); + if (!ASSERT_OK(err, "test_run")) + goto out; + if (!ASSERT_NEQ(topts.retval, 0, "test_run retval")) goto out; compare_cookies(skel->maps.src, dst_map); @@ -315,6 +314,63 @@ out: test_sockmap_skb_verdict_attach__destroy(skel); } +static __u32 query_prog_id(int prog_fd) +{ + struct bpf_prog_info info = {}; + __u32 info_len = sizeof(info); + int err; + + err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len); + if (!ASSERT_OK(err, "bpf_obj_get_info_by_fd") || + !ASSERT_EQ(info_len, sizeof(info), "bpf_obj_get_info_by_fd")) + return 0; + + return info.id; +} + +static void test_sockmap_progs_query(enum bpf_attach_type attach_type) +{ + struct test_sockmap_progs_query *skel; + int err, map_fd, verdict_fd; + __u32 attach_flags = 0; + __u32 prog_ids[3] = {}; + __u32 prog_cnt = 3; + + skel = test_sockmap_progs_query__open_and_load(); + if (!ASSERT_OK_PTR(skel, "test_sockmap_progs_query__open_and_load")) + return; + + map_fd = bpf_map__fd(skel->maps.sock_map); + + if (attach_type == BPF_SK_MSG_VERDICT) + verdict_fd = bpf_program__fd(skel->progs.prog_skmsg_verdict); + else + verdict_fd = bpf_program__fd(skel->progs.prog_skb_verdict); + + err = bpf_prog_query(map_fd, attach_type, 0 /* query flags */, + &attach_flags, prog_ids, &prog_cnt); + ASSERT_OK(err, "bpf_prog_query failed"); + ASSERT_EQ(attach_flags, 0, "wrong attach_flags on query"); + ASSERT_EQ(prog_cnt, 0, "wrong program count on query"); + + err = bpf_prog_attach(verdict_fd, map_fd, attach_type, 0); + if (!ASSERT_OK(err, "bpf_prog_attach failed")) + goto out; + + prog_cnt = 1; + err = bpf_prog_query(map_fd, attach_type, 0 /* query flags */, + &attach_flags, prog_ids, &prog_cnt); + ASSERT_OK(err, "bpf_prog_query failed"); + ASSERT_EQ(attach_flags, 0, "wrong attach_flags on query"); + ASSERT_EQ(prog_cnt, 1, "wrong program count on query"); + ASSERT_EQ(prog_ids[0], query_prog_id(verdict_fd), + "wrong prog_ids on query"); + + bpf_prog_detach2(verdict_fd, map_fd, attach_type); +out: + test_sockmap_progs_query__destroy(skel); +} + void test_sockmap_basic(void) { if (test__start_subtest("sockmap create_update_free")) @@ -341,4 +397,12 @@ void test_sockmap_basic(void) test_sockmap_skb_verdict_attach(BPF_SK_SKB_STREAM_VERDICT, BPF_SK_SKB_VERDICT); } + if (test__start_subtest("sockmap msg_verdict progs query")) + test_sockmap_progs_query(BPF_SK_MSG_VERDICT); + if (test__start_subtest("sockmap stream_parser progs query")) + test_sockmap_progs_query(BPF_SK_SKB_STREAM_PARSER); + if (test__start_subtest("sockmap stream_verdict progs query")) + test_sockmap_progs_query(BPF_SK_SKB_STREAM_VERDICT); + if (test__start_subtest("sockmap skb_verdict progs query")) + test_sockmap_progs_query(BPF_SK_SKB_VERDICT); } diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c index 7e21bfab6358..2cf0c7a3fe23 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c @@ -1413,14 +1413,12 @@ close_srv1: static void test_ops_cleanup(const struct bpf_map *map) { - const struct bpf_map_def *def; int err, mapfd; u32 key; - def = bpf_map__def(map); mapfd = bpf_map__fd(map); - for (key = 0; key < def->max_entries; key++) { + for (key = 0; key < bpf_map__max_entries(map); key++) { err = bpf_map_delete_elem(mapfd, &key); if (err && errno != EINVAL && errno != ENOENT) FAIL_ERRNO("map_delete: expected EINVAL/ENOENT"); @@ -1443,13 +1441,13 @@ static const char *family_str(sa_family_t family) static const char *map_type_str(const struct bpf_map *map) { - const struct bpf_map_def *def; + int type; - def = bpf_map__def(map); - if (IS_ERR(def)) + if (!map) return "invalid"; + type = bpf_map__type(map); - switch (def->type) { + switch (type) { case BPF_MAP_TYPE_SOCKMAP: return "sockmap"; case BPF_MAP_TYPE_SOCKHASH: diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c b/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c index 4b937e5dbaca..30a99d2ed5c6 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c +++ b/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c @@ -173,11 +173,11 @@ static int getsetsockopt(void) } memset(&buf, 0, sizeof(buf)); - buf.zc.address = 12345; /* rejected by BPF */ + buf.zc.address = 12345; /* Not page aligned. Rejected by tcp_zerocopy_receive() */ optlen = sizeof(buf.zc); errno = 0; err = getsockopt(fd, SOL_TCP, TCP_ZEROCOPY_RECEIVE, &buf, &optlen); - if (errno != EPERM) { + if (errno != EINVAL) { log_err("Unexpected getsockopt(TCP_ZEROCOPY_RECEIVE) err=%d errno=%d", err, errno); goto err; diff --git a/tools/testing/selftests/bpf/prog_tests/spinlock.c b/tools/testing/selftests/bpf/prog_tests/spinlock.c index 6307f5d2b417..8e329eaee6d7 100644 --- a/tools/testing/selftests/bpf/prog_tests/spinlock.c +++ b/tools/testing/selftests/bpf/prog_tests/spinlock.c @@ -4,14 +4,16 @@ static void *spin_lock_thread(void *arg) { - __u32 duration, retval; int err, prog_fd = *(u32 *) arg; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .repeat = 10000, + ); - err = bpf_prog_test_run(prog_fd, 10000, &pkt_v4, sizeof(pkt_v4), - NULL, NULL, &retval, &duration); - CHECK(err || retval, "", - "err %d errno %d retval %d duration %d\n", - err, errno, retval, duration); + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "test_run"); + ASSERT_OK(topts.retval, "test_run retval"); pthread_exit(arg); } diff --git a/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c b/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c index 0a91d8d9954b..f45a1d7b0a28 100644 --- a/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c +++ b/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c @@ -42,7 +42,7 @@ retry: return; /* override program type */ - bpf_program__set_perf_event(skel->progs.oncpu); + bpf_program__set_type(skel->progs.oncpu, BPF_PROG_TYPE_PERF_EVENT); err = test_stacktrace_build_id__load(skel); if (CHECK(err, "skel_load", "skeleton load failed: %d\n", err)) diff --git a/tools/testing/selftests/bpf/prog_tests/stacktrace_map_skip.c b/tools/testing/selftests/bpf/prog_tests/stacktrace_map_skip.c new file mode 100644 index 000000000000..1932b1e0685c --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/stacktrace_map_skip.c @@ -0,0 +1,63 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <test_progs.h> +#include "stacktrace_map_skip.skel.h" + +#define TEST_STACK_DEPTH 2 + +void test_stacktrace_map_skip(void) +{ + struct stacktrace_map_skip *skel; + int stackid_hmap_fd, stackmap_fd, stack_amap_fd; + int err, stack_trace_len; + + skel = stacktrace_map_skip__open_and_load(); + if (!ASSERT_OK_PTR(skel, "skel_open_and_load")) + return; + + /* find map fds */ + stackid_hmap_fd = bpf_map__fd(skel->maps.stackid_hmap); + if (!ASSERT_GE(stackid_hmap_fd, 0, "stackid_hmap fd")) + goto out; + + stackmap_fd = bpf_map__fd(skel->maps.stackmap); + if (!ASSERT_GE(stackmap_fd, 0, "stackmap fd")) + goto out; + + stack_amap_fd = bpf_map__fd(skel->maps.stack_amap); + if (!ASSERT_GE(stack_amap_fd, 0, "stack_amap fd")) + goto out; + + skel->bss->pid = getpid(); + + err = stacktrace_map_skip__attach(skel); + if (!ASSERT_OK(err, "skel_attach")) + goto out; + + /* give some time for bpf program run */ + sleep(1); + + /* disable stack trace collection */ + skel->bss->control = 1; + + /* for every element in stackid_hmap, we can find a corresponding one + * in stackmap, and vise versa. + */ + err = compare_map_keys(stackid_hmap_fd, stackmap_fd); + if (!ASSERT_OK(err, "compare_map_keys stackid_hmap vs. stackmap")) + goto out; + + err = compare_map_keys(stackmap_fd, stackid_hmap_fd); + if (!ASSERT_OK(err, "compare_map_keys stackmap vs. stackid_hmap")) + goto out; + + stack_trace_len = TEST_STACK_DEPTH * sizeof(__u64); + err = compare_stack_ips(stackmap_fd, stack_amap_fd, stack_trace_len); + if (!ASSERT_OK(err, "compare_stack_ips stackmap vs. stack_amap")) + goto out; + + if (!ASSERT_EQ(skel->bss->failed, 0, "skip_failed")) + goto out; + +out: + stacktrace_map_skip__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/subprogs.c b/tools/testing/selftests/bpf/prog_tests/subprogs.c index 3f3d2ac4dd57..903f35a9e62e 100644 --- a/tools/testing/selftests/bpf/prog_tests/subprogs.c +++ b/tools/testing/selftests/bpf/prog_tests/subprogs.c @@ -1,32 +1,83 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2020 Facebook */ #include <test_progs.h> -#include <time.h> #include "test_subprogs.skel.h" #include "test_subprogs_unused.skel.h" -static int duration; +struct toggler_ctx { + int fd; + bool stop; +}; -void test_subprogs(void) +static void *toggle_jit_harden(void *arg) +{ + struct toggler_ctx *ctx = arg; + char two = '2'; + char zero = '0'; + + while (!ctx->stop) { + lseek(ctx->fd, SEEK_SET, 0); + write(ctx->fd, &two, sizeof(two)); + lseek(ctx->fd, SEEK_SET, 0); + write(ctx->fd, &zero, sizeof(zero)); + } + + return NULL; +} + +static void test_subprogs_with_jit_harden_toggling(void) +{ + struct toggler_ctx ctx; + pthread_t toggler; + int err; + unsigned int i, loop = 10; + + ctx.fd = open("/proc/sys/net/core/bpf_jit_harden", O_RDWR); + if (!ASSERT_GE(ctx.fd, 0, "open bpf_jit_harden")) + return; + + ctx.stop = false; + err = pthread_create(&toggler, NULL, toggle_jit_harden, &ctx); + if (!ASSERT_OK(err, "new toggler")) + goto out; + + /* Make toggler thread to run */ + usleep(1); + + for (i = 0; i < loop; i++) { + struct test_subprogs *skel = test_subprogs__open_and_load(); + + if (!ASSERT_OK_PTR(skel, "skel open")) + break; + test_subprogs__destroy(skel); + } + + ctx.stop = true; + pthread_join(toggler, NULL); +out: + close(ctx.fd); +} + +static void test_subprogs_alone(void) { struct test_subprogs *skel; struct test_subprogs_unused *skel2; int err; skel = test_subprogs__open_and_load(); - if (CHECK(!skel, "skel_open", "failed to open skeleton\n")) + if (!ASSERT_OK_PTR(skel, "skel_open")) return; err = test_subprogs__attach(skel); - if (CHECK(err, "skel_attach", "failed to attach skeleton: %d\n", err)) + if (!ASSERT_OK(err, "skel attach")) goto cleanup; usleep(1); - CHECK(skel->bss->res1 != 12, "res1", "got %d, exp %d\n", skel->bss->res1, 12); - CHECK(skel->bss->res2 != 17, "res2", "got %d, exp %d\n", skel->bss->res2, 17); - CHECK(skel->bss->res3 != 19, "res3", "got %d, exp %d\n", skel->bss->res3, 19); - CHECK(skel->bss->res4 != 36, "res4", "got %d, exp %d\n", skel->bss->res4, 36); + ASSERT_EQ(skel->bss->res1, 12, "res1"); + ASSERT_EQ(skel->bss->res2, 17, "res2"); + ASSERT_EQ(skel->bss->res3, 19, "res3"); + ASSERT_EQ(skel->bss->res4, 36, "res4"); skel2 = test_subprogs_unused__open_and_load(); ASSERT_OK_PTR(skel2, "unused_progs_skel"); @@ -35,3 +86,11 @@ void test_subprogs(void) cleanup: test_subprogs__destroy(skel); } + +void test_subprogs(void) +{ + if (test__start_subtest("subprogs_alone")) + test_subprogs_alone(); + if (test__start_subtest("subprogs_and_jit_harden")) + test_subprogs_with_jit_harden_toggling(); +} diff --git a/tools/testing/selftests/bpf/prog_tests/subskeleton.c b/tools/testing/selftests/bpf/prog_tests/subskeleton.c new file mode 100644 index 000000000000..9c31b7004f9c --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/subskeleton.c @@ -0,0 +1,78 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) Meta Platforms, Inc. and affiliates. */ + +#include <test_progs.h> +#include "test_subskeleton.skel.h" +#include "test_subskeleton_lib.subskel.h" + +static void subskeleton_lib_setup(struct bpf_object *obj) +{ + struct test_subskeleton_lib *lib = test_subskeleton_lib__open(obj); + + if (!ASSERT_OK_PTR(lib, "open subskeleton")) + return; + + *lib->rodata.var1 = 1; + *lib->data.var2 = 2; + lib->bss.var3->var3_1 = 3; + lib->bss.var3->var3_2 = 4; + + test_subskeleton_lib__destroy(lib); +} + +static int subskeleton_lib_subresult(struct bpf_object *obj) +{ + struct test_subskeleton_lib *lib = test_subskeleton_lib__open(obj); + int result; + + if (!ASSERT_OK_PTR(lib, "open subskeleton")) + return -EINVAL; + + result = *lib->bss.libout1; + ASSERT_EQ(result, 1 + 2 + 3 + 4 + 5 + 6, "lib subresult"); + + ASSERT_OK_PTR(lib->progs.lib_perf_handler, "lib_perf_handler"); + ASSERT_STREQ(bpf_program__name(lib->progs.lib_perf_handler), + "lib_perf_handler", "program name"); + + ASSERT_OK_PTR(lib->maps.map1, "map1"); + ASSERT_STREQ(bpf_map__name(lib->maps.map1), "map1", "map name"); + + ASSERT_EQ(*lib->data.var5, 5, "__weak var5"); + ASSERT_EQ(*lib->data.var6, 6, "extern var6"); + ASSERT_TRUE(*lib->kconfig.CONFIG_BPF_SYSCALL, "CONFIG_BPF_SYSCALL"); + + test_subskeleton_lib__destroy(lib); + return result; +} + +void test_subskeleton(void) +{ + int err, result; + struct test_subskeleton *skel; + + skel = test_subskeleton__open(); + if (!ASSERT_OK_PTR(skel, "skel_open")) + return; + + skel->rodata->rovar1 = 10; + skel->rodata->var1 = 1; + subskeleton_lib_setup(skel->obj); + + err = test_subskeleton__load(skel); + if (!ASSERT_OK(err, "skel_load")) + goto cleanup; + + err = test_subskeleton__attach(skel); + if (!ASSERT_OK(err, "skel_attach")) + goto cleanup; + + /* trigger tracepoint */ + usleep(1); + + result = subskeleton_lib_subresult(skel->obj) * 10; + ASSERT_EQ(skel->bss->out1, result, "unexpected calculation"); + +cleanup: + test_subskeleton__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/syscall.c b/tools/testing/selftests/bpf/prog_tests/syscall.c index 81e997a69f7a..f4d40001155a 100644 --- a/tools/testing/selftests/bpf/prog_tests/syscall.c +++ b/tools/testing/selftests/bpf/prog_tests/syscall.c @@ -20,20 +20,20 @@ void test_syscall(void) .log_buf = (uintptr_t) verifier_log, .log_size = sizeof(verifier_log), }; - struct bpf_prog_test_run_attr tattr = { + LIBBPF_OPTS(bpf_test_run_opts, tattr, .ctx_in = &ctx, .ctx_size_in = sizeof(ctx), - }; + ); struct syscall *skel = NULL; __u64 key = 12, value = 0; - int err; + int err, prog_fd; skel = syscall__open_and_load(); if (!ASSERT_OK_PTR(skel, "skel_load")) goto cleanup; - tattr.prog_fd = bpf_program__fd(skel->progs.bpf_prog); - err = bpf_prog_test_run_xattr(&tattr); + prog_fd = bpf_program__fd(skel->progs.bpf_prog); + err = bpf_prog_test_run_opts(prog_fd, &tattr); ASSERT_EQ(err, 0, "err"); ASSERT_EQ(tattr.retval, 1, "retval"); ASSERT_GT(ctx.map_fd, 0, "ctx.map_fd"); diff --git a/tools/testing/selftests/bpf/prog_tests/tailcalls.c b/tools/testing/selftests/bpf/prog_tests/tailcalls.c index 5dc0f425bd11..c4da87ec3ba4 100644 --- a/tools/testing/selftests/bpf/prog_tests/tailcalls.c +++ b/tools/testing/selftests/bpf/prog_tests/tailcalls.c @@ -12,9 +12,13 @@ static void test_tailcall_1(void) struct bpf_map *prog_array; struct bpf_program *prog; struct bpf_object *obj; - __u32 retval, duration; char prog_name[32]; char buff[128] = {}; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = buff, + .data_size_in = sizeof(buff), + .repeat = 1, + ); err = bpf_prog_test_load("tailcall1.o", BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd); @@ -37,7 +41,7 @@ static void test_tailcall_1(void) if (CHECK_FAIL(map_fd < 0)) goto out; - for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { + for (i = 0; i < bpf_map__max_entries(prog_array); i++) { snprintf(prog_name, sizeof(prog_name), "classifier_%d", i); prog = bpf_object__find_program_by_name(obj, prog_name); @@ -53,23 +57,21 @@ static void test_tailcall_1(void) goto out; } - for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { - err = bpf_prog_test_run(main_fd, 1, buff, sizeof(buff), 0, - &duration, &retval, NULL); - CHECK(err || retval != i, "tailcall", - "err %d errno %d retval %d\n", err, errno, retval); + for (i = 0; i < bpf_map__max_entries(prog_array); i++) { + err = bpf_prog_test_run_opts(main_fd, &topts); + ASSERT_OK(err, "tailcall"); + ASSERT_EQ(topts.retval, i, "tailcall retval"); err = bpf_map_delete_elem(map_fd, &i); if (CHECK_FAIL(err)) goto out; } - err = bpf_prog_test_run(main_fd, 1, buff, sizeof(buff), 0, - &duration, &retval, NULL); - CHECK(err || retval != 3, "tailcall", "err %d errno %d retval %d\n", - err, errno, retval); + err = bpf_prog_test_run_opts(main_fd, &topts); + ASSERT_OK(err, "tailcall"); + ASSERT_EQ(topts.retval, 3, "tailcall retval"); - for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { + for (i = 0; i < bpf_map__max_entries(prog_array); i++) { snprintf(prog_name, sizeof(prog_name), "classifier_%d", i); prog = bpf_object__find_program_by_name(obj, prog_name); @@ -85,13 +87,12 @@ static void test_tailcall_1(void) goto out; } - err = bpf_prog_test_run(main_fd, 1, buff, sizeof(buff), 0, - &duration, &retval, NULL); - CHECK(err || retval != 0, "tailcall", "err %d errno %d retval %d\n", - err, errno, retval); + err = bpf_prog_test_run_opts(main_fd, &topts); + ASSERT_OK(err, "tailcall"); + ASSERT_OK(topts.retval, "tailcall retval"); - for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { - j = bpf_map__def(prog_array)->max_entries - 1 - i; + for (i = 0; i < bpf_map__max_entries(prog_array); i++) { + j = bpf_map__max_entries(prog_array) - 1 - i; snprintf(prog_name, sizeof(prog_name), "classifier_%d", j); prog = bpf_object__find_program_by_name(obj, prog_name); @@ -107,33 +108,30 @@ static void test_tailcall_1(void) goto out; } - for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { - j = bpf_map__def(prog_array)->max_entries - 1 - i; + for (i = 0; i < bpf_map__max_entries(prog_array); i++) { + j = bpf_map__max_entries(prog_array) - 1 - i; - err = bpf_prog_test_run(main_fd, 1, buff, sizeof(buff), 0, - &duration, &retval, NULL); - CHECK(err || retval != j, "tailcall", - "err %d errno %d retval %d\n", err, errno, retval); + err = bpf_prog_test_run_opts(main_fd, &topts); + ASSERT_OK(err, "tailcall"); + ASSERT_EQ(topts.retval, j, "tailcall retval"); err = bpf_map_delete_elem(map_fd, &i); if (CHECK_FAIL(err)) goto out; } - err = bpf_prog_test_run(main_fd, 1, buff, sizeof(buff), 0, - &duration, &retval, NULL); - CHECK(err || retval != 3, "tailcall", "err %d errno %d retval %d\n", - err, errno, retval); + err = bpf_prog_test_run_opts(main_fd, &topts); + ASSERT_OK(err, "tailcall"); + ASSERT_EQ(topts.retval, 3, "tailcall retval"); - for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { + for (i = 0; i < bpf_map__max_entries(prog_array); i++) { err = bpf_map_delete_elem(map_fd, &i); if (CHECK_FAIL(err >= 0 || errno != ENOENT)) goto out; - err = bpf_prog_test_run(main_fd, 1, buff, sizeof(buff), 0, - &duration, &retval, NULL); - CHECK(err || retval != 3, "tailcall", - "err %d errno %d retval %d\n", err, errno, retval); + err = bpf_prog_test_run_opts(main_fd, &topts); + ASSERT_OK(err, "tailcall"); + ASSERT_EQ(topts.retval, 3, "tailcall retval"); } out: @@ -150,9 +148,13 @@ static void test_tailcall_2(void) struct bpf_map *prog_array; struct bpf_program *prog; struct bpf_object *obj; - __u32 retval, duration; char prog_name[32]; char buff[128] = {}; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = buff, + .data_size_in = sizeof(buff), + .repeat = 1, + ); err = bpf_prog_test_load("tailcall2.o", BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd); @@ -175,7 +177,7 @@ static void test_tailcall_2(void) if (CHECK_FAIL(map_fd < 0)) goto out; - for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { + for (i = 0; i < bpf_map__max_entries(prog_array); i++) { snprintf(prog_name, sizeof(prog_name), "classifier_%d", i); prog = bpf_object__find_program_by_name(obj, prog_name); @@ -191,30 +193,27 @@ static void test_tailcall_2(void) goto out; } - err = bpf_prog_test_run(main_fd, 1, buff, sizeof(buff), 0, - &duration, &retval, NULL); - CHECK(err || retval != 2, "tailcall", "err %d errno %d retval %d\n", - err, errno, retval); + err = bpf_prog_test_run_opts(main_fd, &topts); + ASSERT_OK(err, "tailcall"); + ASSERT_EQ(topts.retval, 2, "tailcall retval"); i = 2; err = bpf_map_delete_elem(map_fd, &i); if (CHECK_FAIL(err)) goto out; - err = bpf_prog_test_run(main_fd, 1, buff, sizeof(buff), 0, - &duration, &retval, NULL); - CHECK(err || retval != 1, "tailcall", "err %d errno %d retval %d\n", - err, errno, retval); + err = bpf_prog_test_run_opts(main_fd, &topts); + ASSERT_OK(err, "tailcall"); + ASSERT_EQ(topts.retval, 1, "tailcall retval"); i = 0; err = bpf_map_delete_elem(map_fd, &i); if (CHECK_FAIL(err)) goto out; - err = bpf_prog_test_run(main_fd, 1, buff, sizeof(buff), 0, - &duration, &retval, NULL); - CHECK(err || retval != 3, "tailcall", "err %d errno %d retval %d\n", - err, errno, retval); + err = bpf_prog_test_run_opts(main_fd, &topts); + ASSERT_OK(err, "tailcall"); + ASSERT_EQ(topts.retval, 3, "tailcall retval"); out: bpf_object__close(obj); } @@ -225,8 +224,12 @@ static void test_tailcall_count(const char *which) struct bpf_map *prog_array, *data_map; struct bpf_program *prog; struct bpf_object *obj; - __u32 retval, duration; char buff[128] = {}; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = buff, + .data_size_in = sizeof(buff), + .repeat = 1, + ); err = bpf_prog_test_load(which, BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd); @@ -262,10 +265,9 @@ static void test_tailcall_count(const char *which) if (CHECK_FAIL(err)) goto out; - err = bpf_prog_test_run(main_fd, 1, buff, sizeof(buff), 0, - &duration, &retval, NULL); - CHECK(err || retval != 1, "tailcall", "err %d errno %d retval %d\n", - err, errno, retval); + err = bpf_prog_test_run_opts(main_fd, &topts); + ASSERT_OK(err, "tailcall"); + ASSERT_EQ(topts.retval, 1, "tailcall retval"); data_map = bpf_object__find_map_by_name(obj, "tailcall.bss"); if (CHECK_FAIL(!data_map || !bpf_map__is_internal(data_map))) @@ -277,18 +279,17 @@ static void test_tailcall_count(const char *which) i = 0; err = bpf_map_lookup_elem(data_fd, &i, &val); - CHECK(err || val != 33, "tailcall count", "err %d errno %d count %d\n", - err, errno, val); + ASSERT_OK(err, "tailcall count"); + ASSERT_EQ(val, 33, "tailcall count"); i = 0; err = bpf_map_delete_elem(map_fd, &i); if (CHECK_FAIL(err)) goto out; - err = bpf_prog_test_run(main_fd, 1, buff, sizeof(buff), 0, - &duration, &retval, NULL); - CHECK(err || retval != 0, "tailcall", "err %d errno %d retval %d\n", - err, errno, retval); + err = bpf_prog_test_run_opts(main_fd, &topts); + ASSERT_OK(err, "tailcall"); + ASSERT_OK(topts.retval, "tailcall retval"); out: bpf_object__close(obj); } @@ -319,10 +320,14 @@ static void test_tailcall_4(void) struct bpf_map *prog_array, *data_map; struct bpf_program *prog; struct bpf_object *obj; - __u32 retval, duration; static const int zero = 0; char buff[128] = {}; char prog_name[32]; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = buff, + .data_size_in = sizeof(buff), + .repeat = 1, + ); err = bpf_prog_test_load("tailcall4.o", BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd); @@ -353,7 +358,7 @@ static void test_tailcall_4(void) if (CHECK_FAIL(map_fd < 0)) return; - for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { + for (i = 0; i < bpf_map__max_entries(prog_array); i++) { snprintf(prog_name, sizeof(prog_name), "classifier_%d", i); prog = bpf_object__find_program_by_name(obj, prog_name); @@ -369,18 +374,17 @@ static void test_tailcall_4(void) goto out; } - for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { + for (i = 0; i < bpf_map__max_entries(prog_array); i++) { err = bpf_map_update_elem(data_fd, &zero, &i, BPF_ANY); if (CHECK_FAIL(err)) goto out; - err = bpf_prog_test_run(main_fd, 1, buff, sizeof(buff), 0, - &duration, &retval, NULL); - CHECK(err || retval != i, "tailcall", - "err %d errno %d retval %d\n", err, errno, retval); + err = bpf_prog_test_run_opts(main_fd, &topts); + ASSERT_OK(err, "tailcall"); + ASSERT_EQ(topts.retval, i, "tailcall retval"); } - for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { + for (i = 0; i < bpf_map__max_entries(prog_array); i++) { err = bpf_map_update_elem(data_fd, &zero, &i, BPF_ANY); if (CHECK_FAIL(err)) goto out; @@ -389,10 +393,9 @@ static void test_tailcall_4(void) if (CHECK_FAIL(err)) goto out; - err = bpf_prog_test_run(main_fd, 1, buff, sizeof(buff), 0, - &duration, &retval, NULL); - CHECK(err || retval != 3, "tailcall", - "err %d errno %d retval %d\n", err, errno, retval); + err = bpf_prog_test_run_opts(main_fd, &topts); + ASSERT_OK(err, "tailcall"); + ASSERT_EQ(topts.retval, 3, "tailcall retval"); } out: bpf_object__close(obj); @@ -407,10 +410,14 @@ static void test_tailcall_5(void) struct bpf_map *prog_array, *data_map; struct bpf_program *prog; struct bpf_object *obj; - __u32 retval, duration; static const int zero = 0; char buff[128] = {}; char prog_name[32]; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = buff, + .data_size_in = sizeof(buff), + .repeat = 1, + ); err = bpf_prog_test_load("tailcall5.o", BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd); @@ -441,7 +448,7 @@ static void test_tailcall_5(void) if (CHECK_FAIL(map_fd < 0)) return; - for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { + for (i = 0; i < bpf_map__max_entries(prog_array); i++) { snprintf(prog_name, sizeof(prog_name), "classifier_%d", i); prog = bpf_object__find_program_by_name(obj, prog_name); @@ -457,18 +464,17 @@ static void test_tailcall_5(void) goto out; } - for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { + for (i = 0; i < bpf_map__max_entries(prog_array); i++) { err = bpf_map_update_elem(data_fd, &zero, &key[i], BPF_ANY); if (CHECK_FAIL(err)) goto out; - err = bpf_prog_test_run(main_fd, 1, buff, sizeof(buff), 0, - &duration, &retval, NULL); - CHECK(err || retval != i, "tailcall", - "err %d errno %d retval %d\n", err, errno, retval); + err = bpf_prog_test_run_opts(main_fd, &topts); + ASSERT_OK(err, "tailcall"); + ASSERT_EQ(topts.retval, i, "tailcall retval"); } - for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { + for (i = 0; i < bpf_map__max_entries(prog_array); i++) { err = bpf_map_update_elem(data_fd, &zero, &key[i], BPF_ANY); if (CHECK_FAIL(err)) goto out; @@ -477,10 +483,9 @@ static void test_tailcall_5(void) if (CHECK_FAIL(err)) goto out; - err = bpf_prog_test_run(main_fd, 1, buff, sizeof(buff), 0, - &duration, &retval, NULL); - CHECK(err || retval != 3, "tailcall", - "err %d errno %d retval %d\n", err, errno, retval); + err = bpf_prog_test_run_opts(main_fd, &topts); + ASSERT_OK(err, "tailcall"); + ASSERT_EQ(topts.retval, 3, "tailcall retval"); } out: bpf_object__close(obj); @@ -495,8 +500,12 @@ static void test_tailcall_bpf2bpf_1(void) struct bpf_map *prog_array; struct bpf_program *prog; struct bpf_object *obj; - __u32 retval, duration; char prog_name[32]; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .repeat = 1, + ); err = bpf_prog_test_load("tailcall_bpf2bpf1.o", BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd); @@ -520,7 +529,7 @@ static void test_tailcall_bpf2bpf_1(void) goto out; /* nop -> jmp */ - for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { + for (i = 0; i < bpf_map__max_entries(prog_array); i++) { snprintf(prog_name, sizeof(prog_name), "classifier_%d", i); prog = bpf_object__find_program_by_name(obj, prog_name); @@ -536,10 +545,9 @@ static void test_tailcall_bpf2bpf_1(void) goto out; } - err = bpf_prog_test_run(main_fd, 1, &pkt_v4, sizeof(pkt_v4), 0, - 0, &retval, &duration); - CHECK(err || retval != 1, "tailcall", - "err %d errno %d retval %d\n", err, errno, retval); + err = bpf_prog_test_run_opts(main_fd, &topts); + ASSERT_OK(err, "tailcall"); + ASSERT_EQ(topts.retval, 1, "tailcall retval"); /* jmp -> nop, call subprog that will do tailcall */ i = 1; @@ -547,10 +555,9 @@ static void test_tailcall_bpf2bpf_1(void) if (CHECK_FAIL(err)) goto out; - err = bpf_prog_test_run(main_fd, 1, &pkt_v4, sizeof(pkt_v4), 0, - 0, &retval, &duration); - CHECK(err || retval != 0, "tailcall", "err %d errno %d retval %d\n", - err, errno, retval); + err = bpf_prog_test_run_opts(main_fd, &topts); + ASSERT_OK(err, "tailcall"); + ASSERT_OK(topts.retval, "tailcall retval"); /* make sure that subprog can access ctx and entry prog that * called this subprog can properly return @@ -560,11 +567,9 @@ static void test_tailcall_bpf2bpf_1(void) if (CHECK_FAIL(err)) goto out; - err = bpf_prog_test_run(main_fd, 1, &pkt_v4, sizeof(pkt_v4), 0, - 0, &retval, &duration); - CHECK(err || retval != sizeof(pkt_v4) * 2, - "tailcall", "err %d errno %d retval %d\n", - err, errno, retval); + err = bpf_prog_test_run_opts(main_fd, &topts); + ASSERT_OK(err, "tailcall"); + ASSERT_EQ(topts.retval, sizeof(pkt_v4) * 2, "tailcall retval"); out: bpf_object__close(obj); } @@ -579,8 +584,12 @@ static void test_tailcall_bpf2bpf_2(void) struct bpf_map *prog_array, *data_map; struct bpf_program *prog; struct bpf_object *obj; - __u32 retval, duration; char buff[128] = {}; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = buff, + .data_size_in = sizeof(buff), + .repeat = 1, + ); err = bpf_prog_test_load("tailcall_bpf2bpf2.o", BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd); @@ -616,10 +625,9 @@ static void test_tailcall_bpf2bpf_2(void) if (CHECK_FAIL(err)) goto out; - err = bpf_prog_test_run(main_fd, 1, buff, sizeof(buff), 0, - &duration, &retval, NULL); - CHECK(err || retval != 1, "tailcall", "err %d errno %d retval %d\n", - err, errno, retval); + err = bpf_prog_test_run_opts(main_fd, &topts); + ASSERT_OK(err, "tailcall"); + ASSERT_EQ(topts.retval, 1, "tailcall retval"); data_map = bpf_object__find_map_by_name(obj, "tailcall.bss"); if (CHECK_FAIL(!data_map || !bpf_map__is_internal(data_map))) @@ -631,18 +639,17 @@ static void test_tailcall_bpf2bpf_2(void) i = 0; err = bpf_map_lookup_elem(data_fd, &i, &val); - CHECK(err || val != 33, "tailcall count", "err %d errno %d count %d\n", - err, errno, val); + ASSERT_OK(err, "tailcall count"); + ASSERT_EQ(val, 33, "tailcall count"); i = 0; err = bpf_map_delete_elem(map_fd, &i); if (CHECK_FAIL(err)) goto out; - err = bpf_prog_test_run(main_fd, 1, buff, sizeof(buff), 0, - &duration, &retval, NULL); - CHECK(err || retval != 0, "tailcall", "err %d errno %d retval %d\n", - err, errno, retval); + err = bpf_prog_test_run_opts(main_fd, &topts); + ASSERT_OK(err, "tailcall"); + ASSERT_OK(topts.retval, "tailcall retval"); out: bpf_object__close(obj); } @@ -657,8 +664,12 @@ static void test_tailcall_bpf2bpf_3(void) struct bpf_map *prog_array; struct bpf_program *prog; struct bpf_object *obj; - __u32 retval, duration; char prog_name[32]; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .repeat = 1, + ); err = bpf_prog_test_load("tailcall_bpf2bpf3.o", BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd); @@ -681,7 +692,7 @@ static void test_tailcall_bpf2bpf_3(void) if (CHECK_FAIL(map_fd < 0)) goto out; - for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { + for (i = 0; i < bpf_map__max_entries(prog_array); i++) { snprintf(prog_name, sizeof(prog_name), "classifier_%d", i); prog = bpf_object__find_program_by_name(obj, prog_name); @@ -697,33 +708,27 @@ static void test_tailcall_bpf2bpf_3(void) goto out; } - err = bpf_prog_test_run(main_fd, 1, &pkt_v4, sizeof(pkt_v4), 0, - &duration, &retval, NULL); - CHECK(err || retval != sizeof(pkt_v4) * 3, - "tailcall", "err %d errno %d retval %d\n", - err, errno, retval); + err = bpf_prog_test_run_opts(main_fd, &topts); + ASSERT_OK(err, "tailcall"); + ASSERT_EQ(topts.retval, sizeof(pkt_v4) * 3, "tailcall retval"); i = 1; err = bpf_map_delete_elem(map_fd, &i); if (CHECK_FAIL(err)) goto out; - err = bpf_prog_test_run(main_fd, 1, &pkt_v4, sizeof(pkt_v4), 0, - &duration, &retval, NULL); - CHECK(err || retval != sizeof(pkt_v4), - "tailcall", "err %d errno %d retval %d\n", - err, errno, retval); + err = bpf_prog_test_run_opts(main_fd, &topts); + ASSERT_OK(err, "tailcall"); + ASSERT_EQ(topts.retval, sizeof(pkt_v4), "tailcall retval"); i = 0; err = bpf_map_delete_elem(map_fd, &i); if (CHECK_FAIL(err)) goto out; - err = bpf_prog_test_run(main_fd, 1, &pkt_v4, sizeof(pkt_v4), 0, - &duration, &retval, NULL); - CHECK(err || retval != sizeof(pkt_v4) * 2, - "tailcall", "err %d errno %d retval %d\n", - err, errno, retval); + err = bpf_prog_test_run_opts(main_fd, &topts); + ASSERT_OK(err, "tailcall"); + ASSERT_EQ(topts.retval, sizeof(pkt_v4) * 2, "tailcall retval"); out: bpf_object__close(obj); } @@ -754,8 +759,12 @@ static void test_tailcall_bpf2bpf_4(bool noise) struct bpf_map *prog_array, *data_map; struct bpf_program *prog; struct bpf_object *obj; - __u32 retval, duration; char prog_name[32]; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .repeat = 1, + ); err = bpf_prog_test_load("tailcall_bpf2bpf4.o", BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd); @@ -778,7 +787,7 @@ static void test_tailcall_bpf2bpf_4(bool noise) if (CHECK_FAIL(map_fd < 0)) goto out; - for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { + for (i = 0; i < bpf_map__max_entries(prog_array); i++) { snprintf(prog_name, sizeof(prog_name), "classifier_%d", i); prog = bpf_object__find_program_by_name(obj, prog_name); @@ -809,15 +818,14 @@ static void test_tailcall_bpf2bpf_4(bool noise) if (CHECK_FAIL(err)) goto out; - err = bpf_prog_test_run(main_fd, 1, &pkt_v4, sizeof(pkt_v4), 0, - &duration, &retval, NULL); - CHECK(err || retval != sizeof(pkt_v4) * 3, "tailcall", "err %d errno %d retval %d\n", - err, errno, retval); + err = bpf_prog_test_run_opts(main_fd, &topts); + ASSERT_OK(err, "tailcall"); + ASSERT_EQ(topts.retval, sizeof(pkt_v4) * 3, "tailcall retval"); i = 0; err = bpf_map_lookup_elem(data_fd, &i, &val); - CHECK(err || val.count != 31, "tailcall count", "err %d errno %d count %d\n", - err, errno, val.count); + ASSERT_OK(err, "tailcall count"); + ASSERT_EQ(val.count, 31, "tailcall count"); out: bpf_object__close(obj); diff --git a/tools/testing/selftests/bpf/prog_tests/task_pt_regs.c b/tools/testing/selftests/bpf/prog_tests/task_pt_regs.c index 37c20b5ffa70..61935e7e056a 100644 --- a/tools/testing/selftests/bpf/prog_tests/task_pt_regs.c +++ b/tools/testing/selftests/bpf/prog_tests/task_pt_regs.c @@ -3,18 +3,22 @@ #include <test_progs.h> #include "test_task_pt_regs.skel.h" +/* uprobe attach point */ +static void trigger_func(void) +{ + asm volatile (""); +} + void test_task_pt_regs(void) { struct test_task_pt_regs *skel; struct bpf_link *uprobe_link; - size_t uprobe_offset; - ssize_t base_addr; + ssize_t uprobe_offset; bool match; - base_addr = get_base_addr(); - if (!ASSERT_GT(base_addr, 0, "get_base_addr")) + uprobe_offset = get_uprobe_offset(&trigger_func); + if (!ASSERT_GE(uprobe_offset, 0, "uprobe_offset")) return; - uprobe_offset = get_uprobe_offset(&get_base_addr, base_addr); skel = test_task_pt_regs__open_and_load(); if (!ASSERT_OK_PTR(skel, "skel_open")) @@ -32,7 +36,7 @@ void test_task_pt_regs(void) skel->links.handle_uprobe = uprobe_link; /* trigger & validate uprobe */ - get_base_addr(); + trigger_func(); if (!ASSERT_EQ(skel->bss->uprobe_res, 1, "check_uprobe_res")) goto cleanup; diff --git a/tools/testing/selftests/bpf/prog_tests/tc_redirect.c b/tools/testing/selftests/bpf/prog_tests/tc_redirect.c index c2426df58e17..7ad66a247c02 100644 --- a/tools/testing/selftests/bpf/prog_tests/tc_redirect.c +++ b/tools/testing/selftests/bpf/prog_tests/tc_redirect.c @@ -10,17 +10,15 @@ * to drop unexpected traffic. */ -#define _GNU_SOURCE - #include <arpa/inet.h> #include <linux/if.h> #include <linux/if_tun.h> #include <linux/limits.h> #include <linux/sysctl.h> -#include <sched.h> +#include <linux/time_types.h> +#include <linux/net_tstamp.h> #include <stdbool.h> #include <stdio.h> -#include <sys/mount.h> #include <sys/stat.h> #include <unistd.h> @@ -29,6 +27,11 @@ #include "test_tc_neigh_fib.skel.h" #include "test_tc_neigh.skel.h" #include "test_tc_peer.skel.h" +#include "test_tc_dtime.skel.h" + +#ifndef TCP_TX_DELAY +#define TCP_TX_DELAY 37 +#endif #define NS_SRC "ns_src" #define NS_FWD "ns_fwd" @@ -61,6 +64,7 @@ #define CHK_PROG_PIN_FILE "/sys/fs/bpf/test_tc_chk" #define TIMEOUT_MILLIS 10000 +#define NSEC_PER_SEC 1000000000ULL #define log_err(MSG, ...) \ fprintf(stderr, "(%s:%d: errno: %s) " MSG "\n", \ @@ -84,91 +88,6 @@ static int write_file(const char *path, const char *newval) return 0; } -struct nstoken { - int orig_netns_fd; -}; - -static int setns_by_fd(int nsfd) -{ - int err; - - err = setns(nsfd, CLONE_NEWNET); - close(nsfd); - - if (!ASSERT_OK(err, "setns")) - return err; - - /* Switch /sys to the new namespace so that e.g. /sys/class/net - * reflects the devices in the new namespace. - */ - err = unshare(CLONE_NEWNS); - if (!ASSERT_OK(err, "unshare")) - return err; - - /* Make our /sys mount private, so the following umount won't - * trigger the global umount in case it's shared. - */ - err = mount("none", "/sys", NULL, MS_PRIVATE, NULL); - if (!ASSERT_OK(err, "remount private /sys")) - return err; - - err = umount2("/sys", MNT_DETACH); - if (!ASSERT_OK(err, "umount2 /sys")) - return err; - - err = mount("sysfs", "/sys", "sysfs", 0, NULL); - if (!ASSERT_OK(err, "mount /sys")) - return err; - - err = mount("bpffs", "/sys/fs/bpf", "bpf", 0, NULL); - if (!ASSERT_OK(err, "mount /sys/fs/bpf")) - return err; - - return 0; -} - -/** - * open_netns() - Switch to specified network namespace by name. - * - * Returns token with which to restore the original namespace - * using close_netns(). - */ -static struct nstoken *open_netns(const char *name) -{ - int nsfd; - char nspath[PATH_MAX]; - int err; - struct nstoken *token; - - token = malloc(sizeof(struct nstoken)); - if (!ASSERT_OK_PTR(token, "malloc token")) - return NULL; - - token->orig_netns_fd = open("/proc/self/ns/net", O_RDONLY); - if (!ASSERT_GE(token->orig_netns_fd, 0, "open /proc/self/ns/net")) - goto fail; - - snprintf(nspath, sizeof(nspath), "%s/%s", "/var/run/netns", name); - nsfd = open(nspath, O_RDONLY | O_CLOEXEC); - if (!ASSERT_GE(nsfd, 0, "open netns fd")) - goto fail; - - err = setns_by_fd(nsfd); - if (!ASSERT_OK(err, "setns_by_fd")) - goto fail; - - return token; -fail: - free(token); - return NULL; -} - -static void close_netns(struct nstoken *token) -{ - ASSERT_OK(setns_by_fd(token->orig_netns_fd), "setns_by_fd"); - free(token); -} - static int netns_setup_namespaces(const char *verb) { const char * const *ns = namespaces; @@ -440,6 +359,431 @@ static int set_forwarding(bool enable) return 0; } +static void rcv_tstamp(int fd, const char *expected, size_t s) +{ + struct __kernel_timespec pkt_ts = {}; + char ctl[CMSG_SPACE(sizeof(pkt_ts))]; + struct timespec now_ts; + struct msghdr msg = {}; + __u64 now_ns, pkt_ns; + struct cmsghdr *cmsg; + struct iovec iov; + char data[32]; + int ret; + + iov.iov_base = data; + iov.iov_len = sizeof(data); + msg.msg_iov = &iov; + msg.msg_iovlen = 1; + msg.msg_control = &ctl; + msg.msg_controllen = sizeof(ctl); + + ret = recvmsg(fd, &msg, 0); + if (!ASSERT_EQ(ret, s, "recvmsg")) + return; + ASSERT_STRNEQ(data, expected, s, "expected rcv data"); + + cmsg = CMSG_FIRSTHDR(&msg); + if (cmsg && cmsg->cmsg_level == SOL_SOCKET && + cmsg->cmsg_type == SO_TIMESTAMPNS_NEW) + memcpy(&pkt_ts, CMSG_DATA(cmsg), sizeof(pkt_ts)); + + pkt_ns = pkt_ts.tv_sec * NSEC_PER_SEC + pkt_ts.tv_nsec; + ASSERT_NEQ(pkt_ns, 0, "pkt rcv tstamp"); + + ret = clock_gettime(CLOCK_REALTIME, &now_ts); + ASSERT_OK(ret, "clock_gettime"); + now_ns = now_ts.tv_sec * NSEC_PER_SEC + now_ts.tv_nsec; + + if (ASSERT_GE(now_ns, pkt_ns, "check rcv tstamp")) + ASSERT_LT(now_ns - pkt_ns, 5 * NSEC_PER_SEC, + "check rcv tstamp"); +} + +static void snd_tstamp(int fd, char *b, size_t s) +{ + struct sock_txtime opt = { .clockid = CLOCK_TAI }; + char ctl[CMSG_SPACE(sizeof(__u64))]; + struct timespec now_ts; + struct msghdr msg = {}; + struct cmsghdr *cmsg; + struct iovec iov; + __u64 now_ns; + int ret; + + ret = clock_gettime(CLOCK_TAI, &now_ts); + ASSERT_OK(ret, "clock_get_time(CLOCK_TAI)"); + now_ns = now_ts.tv_sec * NSEC_PER_SEC + now_ts.tv_nsec; + + iov.iov_base = b; + iov.iov_len = s; + msg.msg_iov = &iov; + msg.msg_iovlen = 1; + msg.msg_control = &ctl; + msg.msg_controllen = sizeof(ctl); + + cmsg = CMSG_FIRSTHDR(&msg); + cmsg->cmsg_level = SOL_SOCKET; + cmsg->cmsg_type = SCM_TXTIME; + cmsg->cmsg_len = CMSG_LEN(sizeof(now_ns)); + *(__u64 *)CMSG_DATA(cmsg) = now_ns; + + ret = setsockopt(fd, SOL_SOCKET, SO_TXTIME, &opt, sizeof(opt)); + ASSERT_OK(ret, "setsockopt(SO_TXTIME)"); + + ret = sendmsg(fd, &msg, 0); + ASSERT_EQ(ret, s, "sendmsg"); +} + +static void test_inet_dtime(int family, int type, const char *addr, __u16 port) +{ + int opt = 1, accept_fd = -1, client_fd = -1, listen_fd, err; + char buf[] = "testing testing"; + struct nstoken *nstoken; + + nstoken = open_netns(NS_DST); + if (!ASSERT_OK_PTR(nstoken, "setns dst")) + return; + listen_fd = start_server(family, type, addr, port, 0); + close_netns(nstoken); + + if (!ASSERT_GE(listen_fd, 0, "listen")) + return; + + /* Ensure the kernel puts the (rcv) timestamp for all skb */ + err = setsockopt(listen_fd, SOL_SOCKET, SO_TIMESTAMPNS_NEW, + &opt, sizeof(opt)); + if (!ASSERT_OK(err, "setsockopt(SO_TIMESTAMPNS_NEW)")) + goto done; + + if (type == SOCK_STREAM) { + /* Ensure the kernel set EDT when sending out rst/ack + * from the kernel's ctl_sk. + */ + err = setsockopt(listen_fd, SOL_TCP, TCP_TX_DELAY, &opt, + sizeof(opt)); + if (!ASSERT_OK(err, "setsockopt(TCP_TX_DELAY)")) + goto done; + } + + nstoken = open_netns(NS_SRC); + if (!ASSERT_OK_PTR(nstoken, "setns src")) + goto done; + client_fd = connect_to_fd(listen_fd, TIMEOUT_MILLIS); + close_netns(nstoken); + + if (!ASSERT_GE(client_fd, 0, "connect_to_fd")) + goto done; + + if (type == SOCK_STREAM) { + int n; + + accept_fd = accept(listen_fd, NULL, NULL); + if (!ASSERT_GE(accept_fd, 0, "accept")) + goto done; + + n = write(client_fd, buf, sizeof(buf)); + if (!ASSERT_EQ(n, sizeof(buf), "send to server")) + goto done; + rcv_tstamp(accept_fd, buf, sizeof(buf)); + } else { + snd_tstamp(client_fd, buf, sizeof(buf)); + rcv_tstamp(listen_fd, buf, sizeof(buf)); + } + +done: + close(listen_fd); + if (accept_fd != -1) + close(accept_fd); + if (client_fd != -1) + close(client_fd); +} + +static int netns_load_dtime_bpf(struct test_tc_dtime *skel) +{ + struct nstoken *nstoken; + +#define PIN_FNAME(__file) "/sys/fs/bpf/" #__file +#define PIN(__prog) ({ \ + int err = bpf_program__pin(skel->progs.__prog, PIN_FNAME(__prog)); \ + if (!ASSERT_OK(err, "pin " #__prog)) \ + goto fail; \ + }) + + /* setup ns_src tc progs */ + nstoken = open_netns(NS_SRC); + if (!ASSERT_OK_PTR(nstoken, "setns " NS_SRC)) + return -1; + PIN(egress_host); + PIN(ingress_host); + SYS("tc qdisc add dev veth_src clsact"); + SYS("tc filter add dev veth_src ingress bpf da object-pinned " + PIN_FNAME(ingress_host)); + SYS("tc filter add dev veth_src egress bpf da object-pinned " + PIN_FNAME(egress_host)); + close_netns(nstoken); + + /* setup ns_dst tc progs */ + nstoken = open_netns(NS_DST); + if (!ASSERT_OK_PTR(nstoken, "setns " NS_DST)) + return -1; + PIN(egress_host); + PIN(ingress_host); + SYS("tc qdisc add dev veth_dst clsact"); + SYS("tc filter add dev veth_dst ingress bpf da object-pinned " + PIN_FNAME(ingress_host)); + SYS("tc filter add dev veth_dst egress bpf da object-pinned " + PIN_FNAME(egress_host)); + close_netns(nstoken); + + /* setup ns_fwd tc progs */ + nstoken = open_netns(NS_FWD); + if (!ASSERT_OK_PTR(nstoken, "setns " NS_FWD)) + return -1; + PIN(ingress_fwdns_prio100); + PIN(egress_fwdns_prio100); + PIN(ingress_fwdns_prio101); + PIN(egress_fwdns_prio101); + SYS("tc qdisc add dev veth_dst_fwd clsact"); + SYS("tc filter add dev veth_dst_fwd ingress prio 100 bpf da object-pinned " + PIN_FNAME(ingress_fwdns_prio100)); + SYS("tc filter add dev veth_dst_fwd ingress prio 101 bpf da object-pinned " + PIN_FNAME(ingress_fwdns_prio101)); + SYS("tc filter add dev veth_dst_fwd egress prio 100 bpf da object-pinned " + PIN_FNAME(egress_fwdns_prio100)); + SYS("tc filter add dev veth_dst_fwd egress prio 101 bpf da object-pinned " + PIN_FNAME(egress_fwdns_prio101)); + SYS("tc qdisc add dev veth_src_fwd clsact"); + SYS("tc filter add dev veth_src_fwd ingress prio 100 bpf da object-pinned " + PIN_FNAME(ingress_fwdns_prio100)); + SYS("tc filter add dev veth_src_fwd ingress prio 101 bpf da object-pinned " + PIN_FNAME(ingress_fwdns_prio101)); + SYS("tc filter add dev veth_src_fwd egress prio 100 bpf da object-pinned " + PIN_FNAME(egress_fwdns_prio100)); + SYS("tc filter add dev veth_src_fwd egress prio 101 bpf da object-pinned " + PIN_FNAME(egress_fwdns_prio101)); + close_netns(nstoken); + +#undef PIN + + return 0; + +fail: + close_netns(nstoken); + return -1; +} + +enum { + INGRESS_FWDNS_P100, + INGRESS_FWDNS_P101, + EGRESS_FWDNS_P100, + EGRESS_FWDNS_P101, + INGRESS_ENDHOST, + EGRESS_ENDHOST, + SET_DTIME, + __MAX_CNT, +}; + +const char *cnt_names[] = { + "ingress_fwdns_p100", + "ingress_fwdns_p101", + "egress_fwdns_p100", + "egress_fwdns_p101", + "ingress_endhost", + "egress_endhost", + "set_dtime", +}; + +enum { + TCP_IP6_CLEAR_DTIME, + TCP_IP4, + TCP_IP6, + UDP_IP4, + UDP_IP6, + TCP_IP4_RT_FWD, + TCP_IP6_RT_FWD, + UDP_IP4_RT_FWD, + UDP_IP6_RT_FWD, + UKN_TEST, + __NR_TESTS, +}; + +const char *test_names[] = { + "tcp ip6 clear dtime", + "tcp ip4", + "tcp ip6", + "udp ip4", + "udp ip6", + "tcp ip4 rt fwd", + "tcp ip6 rt fwd", + "udp ip4 rt fwd", + "udp ip6 rt fwd", +}; + +static const char *dtime_cnt_str(int test, int cnt) +{ + static char name[64]; + + snprintf(name, sizeof(name), "%s %s", test_names[test], cnt_names[cnt]); + + return name; +} + +static const char *dtime_err_str(int test, int cnt) +{ + static char name[64]; + + snprintf(name, sizeof(name), "%s %s errs", test_names[test], + cnt_names[cnt]); + + return name; +} + +static void test_tcp_clear_dtime(struct test_tc_dtime *skel) +{ + int i, t = TCP_IP6_CLEAR_DTIME; + __u32 *dtimes = skel->bss->dtimes[t]; + __u32 *errs = skel->bss->errs[t]; + + skel->bss->test = t; + test_inet_dtime(AF_INET6, SOCK_STREAM, IP6_DST, 0); + + ASSERT_EQ(dtimes[INGRESS_FWDNS_P100], 0, + dtime_cnt_str(t, INGRESS_FWDNS_P100)); + ASSERT_EQ(dtimes[INGRESS_FWDNS_P101], 0, + dtime_cnt_str(t, INGRESS_FWDNS_P101)); + ASSERT_GT(dtimes[EGRESS_FWDNS_P100], 0, + dtime_cnt_str(t, EGRESS_FWDNS_P100)); + ASSERT_EQ(dtimes[EGRESS_FWDNS_P101], 0, + dtime_cnt_str(t, EGRESS_FWDNS_P101)); + ASSERT_GT(dtimes[EGRESS_ENDHOST], 0, + dtime_cnt_str(t, EGRESS_ENDHOST)); + ASSERT_GT(dtimes[INGRESS_ENDHOST], 0, + dtime_cnt_str(t, INGRESS_ENDHOST)); + + for (i = INGRESS_FWDNS_P100; i < __MAX_CNT; i++) + ASSERT_EQ(errs[i], 0, dtime_err_str(t, i)); +} + +static void test_tcp_dtime(struct test_tc_dtime *skel, int family, bool bpf_fwd) +{ + __u32 *dtimes, *errs; + const char *addr; + int i, t; + + if (family == AF_INET) { + t = bpf_fwd ? TCP_IP4 : TCP_IP4_RT_FWD; + addr = IP4_DST; + } else { + t = bpf_fwd ? TCP_IP6 : TCP_IP6_RT_FWD; + addr = IP6_DST; + } + + dtimes = skel->bss->dtimes[t]; + errs = skel->bss->errs[t]; + + skel->bss->test = t; + test_inet_dtime(family, SOCK_STREAM, addr, 0); + + /* fwdns_prio100 prog does not read delivery_time_type, so + * kernel puts the (rcv) timetamp in __sk_buff->tstamp + */ + ASSERT_EQ(dtimes[INGRESS_FWDNS_P100], 0, + dtime_cnt_str(t, INGRESS_FWDNS_P100)); + for (i = INGRESS_FWDNS_P101; i < SET_DTIME; i++) + ASSERT_GT(dtimes[i], 0, dtime_cnt_str(t, i)); + + for (i = INGRESS_FWDNS_P100; i < __MAX_CNT; i++) + ASSERT_EQ(errs[i], 0, dtime_err_str(t, i)); +} + +static void test_udp_dtime(struct test_tc_dtime *skel, int family, bool bpf_fwd) +{ + __u32 *dtimes, *errs; + const char *addr; + int i, t; + + if (family == AF_INET) { + t = bpf_fwd ? UDP_IP4 : UDP_IP4_RT_FWD; + addr = IP4_DST; + } else { + t = bpf_fwd ? UDP_IP6 : UDP_IP6_RT_FWD; + addr = IP6_DST; + } + + dtimes = skel->bss->dtimes[t]; + errs = skel->bss->errs[t]; + + skel->bss->test = t; + test_inet_dtime(family, SOCK_DGRAM, addr, 0); + + ASSERT_EQ(dtimes[INGRESS_FWDNS_P100], 0, + dtime_cnt_str(t, INGRESS_FWDNS_P100)); + /* non mono delivery time is not forwarded */ + ASSERT_EQ(dtimes[INGRESS_FWDNS_P101], 0, + dtime_cnt_str(t, INGRESS_FWDNS_P100)); + for (i = EGRESS_FWDNS_P100; i < SET_DTIME; i++) + ASSERT_GT(dtimes[i], 0, dtime_cnt_str(t, i)); + + for (i = INGRESS_FWDNS_P100; i < __MAX_CNT; i++) + ASSERT_EQ(errs[i], 0, dtime_err_str(t, i)); +} + +static void test_tc_redirect_dtime(struct netns_setup_result *setup_result) +{ + struct test_tc_dtime *skel; + struct nstoken *nstoken; + int err; + + skel = test_tc_dtime__open(); + if (!ASSERT_OK_PTR(skel, "test_tc_dtime__open")) + return; + + skel->rodata->IFINDEX_SRC = setup_result->ifindex_veth_src_fwd; + skel->rodata->IFINDEX_DST = setup_result->ifindex_veth_dst_fwd; + + err = test_tc_dtime__load(skel); + if (!ASSERT_OK(err, "test_tc_dtime__load")) + goto done; + + if (netns_load_dtime_bpf(skel)) + goto done; + + nstoken = open_netns(NS_FWD); + if (!ASSERT_OK_PTR(nstoken, "setns fwd")) + goto done; + err = set_forwarding(false); + close_netns(nstoken); + if (!ASSERT_OK(err, "disable forwarding")) + goto done; + + test_tcp_clear_dtime(skel); + + test_tcp_dtime(skel, AF_INET, true); + test_tcp_dtime(skel, AF_INET6, true); + test_udp_dtime(skel, AF_INET, true); + test_udp_dtime(skel, AF_INET6, true); + + /* Test the kernel ip[6]_forward path instead + * of bpf_redirect_neigh(). + */ + nstoken = open_netns(NS_FWD); + if (!ASSERT_OK_PTR(nstoken, "setns fwd")) + goto done; + err = set_forwarding(true); + close_netns(nstoken); + if (!ASSERT_OK(err, "enable forwarding")) + goto done; + + test_tcp_dtime(skel, AF_INET, false); + test_tcp_dtime(skel, AF_INET6, false); + test_udp_dtime(skel, AF_INET, false); + test_udp_dtime(skel, AF_INET6, false); + +done: + test_tc_dtime__destroy(skel); +} + static void test_tc_redirect_neigh_fib(struct netns_setup_result *setup_result) { struct nstoken *nstoken = NULL; @@ -787,6 +1131,7 @@ static void *test_tc_redirect_run_tests(void *arg) RUN_TEST(tc_redirect_peer_l3); RUN_TEST(tc_redirect_neigh); RUN_TEST(tc_redirect_neigh_fib); + RUN_TEST(tc_redirect_dtime); return NULL; } diff --git a/tools/testing/selftests/bpf/prog_tests/test_bpf_syscall_macro.c b/tools/testing/selftests/bpf/prog_tests/test_bpf_syscall_macro.c new file mode 100644 index 000000000000..c381faaae741 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/test_bpf_syscall_macro.c @@ -0,0 +1,73 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright 2022 Sony Group Corporation */ +#include <sys/prctl.h> +#include <test_progs.h> +#include "bpf_syscall_macro.skel.h" + +void test_bpf_syscall_macro(void) +{ + struct bpf_syscall_macro *skel = NULL; + int err; + int exp_arg1 = 1001; + unsigned long exp_arg2 = 12; + unsigned long exp_arg3 = 13; + unsigned long exp_arg4 = 14; + unsigned long exp_arg5 = 15; + + /* check whether it can open program */ + skel = bpf_syscall_macro__open(); + if (!ASSERT_OK_PTR(skel, "bpf_syscall_macro__open")) + return; + + skel->rodata->filter_pid = getpid(); + + /* check whether it can load program */ + err = bpf_syscall_macro__load(skel); + if (!ASSERT_OK(err, "bpf_syscall_macro__load")) + goto cleanup; + + /* check whether it can attach kprobe */ + err = bpf_syscall_macro__attach(skel); + if (!ASSERT_OK(err, "bpf_syscall_macro__attach")) + goto cleanup; + + /* check whether args of syscall are copied correctly */ + prctl(exp_arg1, exp_arg2, exp_arg3, exp_arg4, exp_arg5); +#if defined(__aarch64__) || defined(__s390__) + ASSERT_NEQ(skel->bss->arg1, exp_arg1, "syscall_arg1"); +#else + ASSERT_EQ(skel->bss->arg1, exp_arg1, "syscall_arg1"); +#endif + ASSERT_EQ(skel->bss->arg2, exp_arg2, "syscall_arg2"); + ASSERT_EQ(skel->bss->arg3, exp_arg3, "syscall_arg3"); + /* it cannot copy arg4 when uses PT_REGS_PARM4 on x86_64 */ +#ifdef __x86_64__ + ASSERT_NEQ(skel->bss->arg4_cx, exp_arg4, "syscall_arg4_from_cx"); +#else + ASSERT_EQ(skel->bss->arg4_cx, exp_arg4, "syscall_arg4_from_cx"); +#endif + ASSERT_EQ(skel->bss->arg4, exp_arg4, "syscall_arg4"); + ASSERT_EQ(skel->bss->arg5, exp_arg5, "syscall_arg5"); + + /* check whether args of syscall are copied correctly for CORE variants */ + ASSERT_EQ(skel->bss->arg1_core, exp_arg1, "syscall_arg1_core_variant"); + ASSERT_EQ(skel->bss->arg2_core, exp_arg2, "syscall_arg2_core_variant"); + ASSERT_EQ(skel->bss->arg3_core, exp_arg3, "syscall_arg3_core_variant"); + /* it cannot copy arg4 when uses PT_REGS_PARM4_CORE on x86_64 */ +#ifdef __x86_64__ + ASSERT_NEQ(skel->bss->arg4_core_cx, exp_arg4, "syscall_arg4_from_cx_core_variant"); +#else + ASSERT_EQ(skel->bss->arg4_core_cx, exp_arg4, "syscall_arg4_from_cx_core_variant"); +#endif + ASSERT_EQ(skel->bss->arg4_core, exp_arg4, "syscall_arg4_core_variant"); + ASSERT_EQ(skel->bss->arg5_core, exp_arg5, "syscall_arg5_core_variant"); + + ASSERT_EQ(skel->bss->option_syscall, exp_arg1, "BPF_KPROBE_SYSCALL_option"); + ASSERT_EQ(skel->bss->arg2_syscall, exp_arg2, "BPF_KPROBE_SYSCALL_arg2"); + ASSERT_EQ(skel->bss->arg3_syscall, exp_arg3, "BPF_KPROBE_SYSCALL_arg3"); + ASSERT_EQ(skel->bss->arg4_syscall, exp_arg4, "BPF_KPROBE_SYSCALL_arg4"); + ASSERT_EQ(skel->bss->arg5_syscall, exp_arg5, "BPF_KPROBE_SYSCALL_arg5"); + +cleanup: + bpf_syscall_macro__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/test_ima.c b/tools/testing/selftests/bpf/prog_tests/test_ima.c index 97d8a6f84f4a..b13feceb38f1 100644 --- a/tools/testing/selftests/bpf/prog_tests/test_ima.c +++ b/tools/testing/selftests/bpf/prog_tests/test_ima.c @@ -13,14 +13,17 @@ #include "ima.skel.h" -static int run_measured_process(const char *measured_dir, u32 *monitored_pid) +#define MAX_SAMPLES 4 + +static int _run_measured_process(const char *measured_dir, u32 *monitored_pid, + const char *cmd) { int child_pid, child_status; child_pid = fork(); if (child_pid == 0) { *monitored_pid = getpid(); - execlp("./ima_setup.sh", "./ima_setup.sh", "run", measured_dir, + execlp("./ima_setup.sh", "./ima_setup.sh", cmd, measured_dir, NULL); exit(errno); @@ -32,19 +35,39 @@ static int run_measured_process(const char *measured_dir, u32 *monitored_pid) return -EINVAL; } -static u64 ima_hash_from_bpf; +static int run_measured_process(const char *measured_dir, u32 *monitored_pid) +{ + return _run_measured_process(measured_dir, monitored_pid, "run"); +} + +static u64 ima_hash_from_bpf[MAX_SAMPLES]; +static int ima_hash_from_bpf_idx; static int process_sample(void *ctx, void *data, size_t len) { - ima_hash_from_bpf = *((u64 *)data); + if (ima_hash_from_bpf_idx >= MAX_SAMPLES) + return -ENOSPC; + + ima_hash_from_bpf[ima_hash_from_bpf_idx++] = *((u64 *)data); return 0; } +static void test_init(struct ima__bss *bss) +{ + ima_hash_from_bpf_idx = 0; + + bss->use_ima_file_hash = false; + bss->enable_bprm_creds_for_exec = false; + bss->enable_kernel_read_file = false; + bss->test_deny = false; +} + void test_test_ima(void) { char measured_dir_template[] = "/tmp/ima_measuredXXXXXX"; struct ring_buffer *ringbuf = NULL; const char *measured_dir; + u64 bin_true_sample; char cmd[256]; int err, duration = 0; @@ -72,13 +95,127 @@ void test_test_ima(void) if (CHECK(err, "failed to run command", "%s, errno = %d\n", cmd, errno)) goto close_clean; + /* + * Test #1 + * - Goal: obtain a sample with the bpf_ima_inode_hash() helper + * - Expected result: 1 sample (/bin/true) + */ + test_init(skel->bss); err = run_measured_process(measured_dir, &skel->bss->monitored_pid); - if (CHECK(err, "run_measured_process", "err = %d\n", err)) + if (CHECK(err, "run_measured_process #1", "err = %d\n", err)) goto close_clean; err = ring_buffer__consume(ringbuf); ASSERT_EQ(err, 1, "num_samples_or_err"); - ASSERT_NEQ(ima_hash_from_bpf, 0, "ima_hash"); + ASSERT_NEQ(ima_hash_from_bpf[0], 0, "ima_hash"); + + /* + * Test #2 + * - Goal: obtain samples with the bpf_ima_file_hash() helper + * - Expected result: 2 samples (./ima_setup.sh, /bin/true) + */ + test_init(skel->bss); + skel->bss->use_ima_file_hash = true; + err = run_measured_process(measured_dir, &skel->bss->monitored_pid); + if (CHECK(err, "run_measured_process #2", "err = %d\n", err)) + goto close_clean; + + err = ring_buffer__consume(ringbuf); + ASSERT_EQ(err, 2, "num_samples_or_err"); + ASSERT_NEQ(ima_hash_from_bpf[0], 0, "ima_hash"); + ASSERT_NEQ(ima_hash_from_bpf[1], 0, "ima_hash"); + bin_true_sample = ima_hash_from_bpf[1]; + + /* + * Test #3 + * - Goal: confirm that bpf_ima_inode_hash() returns a non-fresh digest + * - Expected result: 2 samples (/bin/true: non-fresh, fresh) + */ + test_init(skel->bss); + + err = _run_measured_process(measured_dir, &skel->bss->monitored_pid, + "modify-bin"); + if (CHECK(err, "modify-bin #3", "err = %d\n", err)) + goto close_clean; + + skel->bss->enable_bprm_creds_for_exec = true; + err = run_measured_process(measured_dir, &skel->bss->monitored_pid); + if (CHECK(err, "run_measured_process #3", "err = %d\n", err)) + goto close_clean; + + err = ring_buffer__consume(ringbuf); + ASSERT_EQ(err, 2, "num_samples_or_err"); + ASSERT_NEQ(ima_hash_from_bpf[0], 0, "ima_hash"); + ASSERT_NEQ(ima_hash_from_bpf[1], 0, "ima_hash"); + ASSERT_EQ(ima_hash_from_bpf[0], bin_true_sample, "sample_equal_or_err"); + /* IMA refreshed the digest. */ + ASSERT_NEQ(ima_hash_from_bpf[1], bin_true_sample, + "sample_different_or_err"); + + /* + * Test #4 + * - Goal: verify that bpf_ima_file_hash() returns a fresh digest + * - Expected result: 4 samples (./ima_setup.sh: fresh, fresh; + * /bin/true: fresh, fresh) + */ + test_init(skel->bss); + skel->bss->use_ima_file_hash = true; + skel->bss->enable_bprm_creds_for_exec = true; + err = run_measured_process(measured_dir, &skel->bss->monitored_pid); + if (CHECK(err, "run_measured_process #4", "err = %d\n", err)) + goto close_clean; + + err = ring_buffer__consume(ringbuf); + ASSERT_EQ(err, 4, "num_samples_or_err"); + ASSERT_NEQ(ima_hash_from_bpf[0], 0, "ima_hash"); + ASSERT_NEQ(ima_hash_from_bpf[1], 0, "ima_hash"); + ASSERT_NEQ(ima_hash_from_bpf[2], 0, "ima_hash"); + ASSERT_NEQ(ima_hash_from_bpf[3], 0, "ima_hash"); + ASSERT_NEQ(ima_hash_from_bpf[2], bin_true_sample, + "sample_different_or_err"); + ASSERT_EQ(ima_hash_from_bpf[3], ima_hash_from_bpf[2], + "sample_equal_or_err"); + + skel->bss->use_ima_file_hash = false; + skel->bss->enable_bprm_creds_for_exec = false; + err = _run_measured_process(measured_dir, &skel->bss->monitored_pid, + "restore-bin"); + if (CHECK(err, "restore-bin #3", "err = %d\n", err)) + goto close_clean; + + /* + * Test #5 + * - Goal: obtain a sample from the kernel_read_file hook + * - Expected result: 2 samples (./ima_setup.sh, policy_test) + */ + test_init(skel->bss); + skel->bss->use_ima_file_hash = true; + skel->bss->enable_kernel_read_file = true; + err = _run_measured_process(measured_dir, &skel->bss->monitored_pid, + "load-policy"); + if (CHECK(err, "run_measured_process #5", "err = %d\n", err)) + goto close_clean; + + err = ring_buffer__consume(ringbuf); + ASSERT_EQ(err, 2, "num_samples_or_err"); + ASSERT_NEQ(ima_hash_from_bpf[0], 0, "ima_hash"); + ASSERT_NEQ(ima_hash_from_bpf[1], 0, "ima_hash"); + + /* + * Test #6 + * - Goal: ensure that the kernel_read_file hook denies an operation + * - Expected result: 0 samples + */ + test_init(skel->bss); + skel->bss->enable_kernel_read_file = true; + skel->bss->test_deny = true; + err = _run_measured_process(measured_dir, &skel->bss->monitored_pid, + "load-policy"); + if (CHECK(!err, "run_measured_process #6", "err = %d\n", err)) + goto close_clean; + + err = ring_buffer__consume(ringbuf); + ASSERT_EQ(err, 0, "num_samples_or_err"); close_clean: snprintf(cmd, sizeof(cmd), "./ima_setup.sh cleanup %s", measured_dir); diff --git a/tools/testing/selftests/bpf/prog_tests/test_profiler.c b/tools/testing/selftests/bpf/prog_tests/test_profiler.c index 4ca275101ee0..de24e8f0e738 100644 --- a/tools/testing/selftests/bpf/prog_tests/test_profiler.c +++ b/tools/testing/selftests/bpf/prog_tests/test_profiler.c @@ -8,20 +8,20 @@ static int sanity_run(struct bpf_program *prog) { - struct bpf_prog_test_run_attr test_attr = {}; + LIBBPF_OPTS(bpf_test_run_opts, test_attr); __u64 args[] = {1, 2, 3}; - __u32 duration = 0; int err, prog_fd; prog_fd = bpf_program__fd(prog); - test_attr.prog_fd = prog_fd; test_attr.ctx_in = args; test_attr.ctx_size_in = sizeof(args); - err = bpf_prog_test_run_xattr(&test_attr); - if (CHECK(err || test_attr.retval, "test_run", - "err %d errno %d retval %d duration %d\n", - err, errno, test_attr.retval, duration)) + err = bpf_prog_test_run_opts(prog_fd, &test_attr); + if (!ASSERT_OK(err, "test_run")) + return -1; + + if (!ASSERT_OK(test_attr.retval, "test_run retval")) return -1; + return 0; } diff --git a/tools/testing/selftests/bpf/prog_tests/test_skb_pkt_end.c b/tools/testing/selftests/bpf/prog_tests/test_skb_pkt_end.c index cf1215531920..ae93411fd582 100644 --- a/tools/testing/selftests/bpf/prog_tests/test_skb_pkt_end.c +++ b/tools/testing/selftests/bpf/prog_tests/test_skb_pkt_end.c @@ -6,15 +6,18 @@ static int sanity_run(struct bpf_program *prog) { - __u32 duration, retval; int err, prog_fd; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .repeat = 1, + ); prog_fd = bpf_program__fd(prog); - err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4), - NULL, NULL, &retval, &duration); - if (CHECK(err || retval != 123, "test_run", - "err %d errno %d retval %d duration %d\n", - err, errno, retval, duration)) + err = bpf_prog_test_run_opts(prog_fd, &topts); + if (!ASSERT_OK(err, "test_run")) + return -1; + if (!ASSERT_EQ(topts.retval, 123, "test_run retval")) return -1; return 0; } diff --git a/tools/testing/selftests/bpf/prog_tests/timer.c b/tools/testing/selftests/bpf/prog_tests/timer.c index 0f4e49e622cd..7eb049214859 100644 --- a/tools/testing/selftests/bpf/prog_tests/timer.c +++ b/tools/testing/selftests/bpf/prog_tests/timer.c @@ -6,7 +6,7 @@ static int timer(struct timer *timer_skel) { int err, prog_fd; - __u32 duration = 0, retval; + LIBBPF_OPTS(bpf_test_run_opts, topts); err = timer__attach(timer_skel); if (!ASSERT_OK(err, "timer_attach")) @@ -16,10 +16,9 @@ static int timer(struct timer *timer_skel) ASSERT_EQ(timer_skel->data->callback2_check, 52, "callback2_check1"); prog_fd = bpf_program__fd(timer_skel->progs.test1); - err = bpf_prog_test_run(prog_fd, 1, NULL, 0, - NULL, NULL, &retval, &duration); + err = bpf_prog_test_run_opts(prog_fd, &topts); ASSERT_OK(err, "test_run"); - ASSERT_EQ(retval, 0, "test_run"); + ASSERT_EQ(topts.retval, 0, "test_run"); timer__detach(timer_skel); usleep(50); /* 10 usecs should be enough, but give it extra */ diff --git a/tools/testing/selftests/bpf/prog_tests/timer_crash.c b/tools/testing/selftests/bpf/prog_tests/timer_crash.c new file mode 100644 index 000000000000..f74b82305da8 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/timer_crash.c @@ -0,0 +1,32 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <test_progs.h> +#include "timer_crash.skel.h" + +enum { + MODE_ARRAY, + MODE_HASH, +}; + +static void test_timer_crash_mode(int mode) +{ + struct timer_crash *skel; + + skel = timer_crash__open_and_load(); + if (!ASSERT_OK_PTR(skel, "timer_crash__open_and_load")) + return; + skel->bss->pid = getpid(); + skel->bss->crash_map = mode; + if (!ASSERT_OK(timer_crash__attach(skel), "timer_crash__attach")) + goto end; + usleep(1); +end: + timer_crash__destroy(skel); +} + +void test_timer_crash(void) +{ + if (test__start_subtest("array")) + test_timer_crash_mode(MODE_ARRAY); + if (test__start_subtest("hash")) + test_timer_crash_mode(MODE_HASH); +} diff --git a/tools/testing/selftests/bpf/prog_tests/timer_mim.c b/tools/testing/selftests/bpf/prog_tests/timer_mim.c index 949a0617869d..2ee5f5ae11d4 100644 --- a/tools/testing/selftests/bpf/prog_tests/timer_mim.c +++ b/tools/testing/selftests/bpf/prog_tests/timer_mim.c @@ -6,19 +6,18 @@ static int timer_mim(struct timer_mim *timer_skel) { - __u32 duration = 0, retval; __u64 cnt1, cnt2; int err, prog_fd, key1 = 1; + LIBBPF_OPTS(bpf_test_run_opts, topts); err = timer_mim__attach(timer_skel); if (!ASSERT_OK(err, "timer_attach")) return err; prog_fd = bpf_program__fd(timer_skel->progs.test1); - err = bpf_prog_test_run(prog_fd, 1, NULL, 0, - NULL, NULL, &retval, &duration); + err = bpf_prog_test_run_opts(prog_fd, &topts); ASSERT_OK(err, "test_run"); - ASSERT_EQ(retval, 0, "test_run"); + ASSERT_EQ(topts.retval, 0, "test_run"); timer_mim__detach(timer_skel); /* check that timer_cb[12] are incrementing 'cnt' */ diff --git a/tools/testing/selftests/bpf/prog_tests/trace_ext.c b/tools/testing/selftests/bpf/prog_tests/trace_ext.c index 924441d4362d..aabdff7bea3e 100644 --- a/tools/testing/selftests/bpf/prog_tests/trace_ext.c +++ b/tools/testing/selftests/bpf/prog_tests/trace_ext.c @@ -23,8 +23,12 @@ void test_trace_ext(void) int err, pkt_fd, ext_fd; struct bpf_program *prog; char buf[100]; - __u32 retval; __u64 len; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .repeat = 1, + ); /* open/load/attach test_pkt_md_access */ skel_pkt = test_pkt_md_access__open_and_load(); @@ -77,32 +81,32 @@ void test_trace_ext(void) /* load/attach tracing */ err = test_trace_ext_tracing__load(skel_trace); - if (CHECK(err, "setup", "tracing/test_pkt_md_access_new load failed\n")) { + if (!ASSERT_OK(err, "tracing/test_pkt_md_access_new load")) { libbpf_strerror(err, buf, sizeof(buf)); fprintf(stderr, "%s\n", buf); goto cleanup; } err = test_trace_ext_tracing__attach(skel_trace); - if (CHECK(err, "setup", "tracing/test_pkt_md_access_new attach failed: %d\n", err)) + if (!ASSERT_OK(err, "tracing/test_pkt_md_access_new attach")) goto cleanup; /* trigger the test */ - err = bpf_prog_test_run(pkt_fd, 1, &pkt_v4, sizeof(pkt_v4), - NULL, NULL, &retval, &duration); - CHECK(err || retval, "run", "err %d errno %d retval %d\n", err, errno, retval); + err = bpf_prog_test_run_opts(pkt_fd, &topts); + ASSERT_OK(err, "test_run_opts err"); + ASSERT_OK(topts.retval, "test_run_opts retval"); bss_ext = skel_ext->bss; bss_trace = skel_trace->bss; len = bss_ext->ext_called; - CHECK(bss_ext->ext_called == 0, - "check", "failed to trigger freplace/test_pkt_md_access\n"); - CHECK(bss_trace->fentry_called != len, - "check", "failed to trigger fentry/test_pkt_md_access_new\n"); - CHECK(bss_trace->fexit_called != len, - "check", "failed to trigger fexit/test_pkt_md_access_new\n"); + ASSERT_NEQ(bss_ext->ext_called, 0, + "failed to trigger freplace/test_pkt_md_access"); + ASSERT_EQ(bss_trace->fentry_called, len, + "failed to trigger fentry/test_pkt_md_access_new"); + ASSERT_EQ(bss_trace->fexit_called, len, + "failed to trigger fexit/test_pkt_md_access_new"); cleanup: test_trace_ext_tracing__destroy(skel_trace); diff --git a/tools/testing/selftests/bpf/prog_tests/xdp.c b/tools/testing/selftests/bpf/prog_tests/xdp.c index ac65456b7ab8..ec21c53cb1da 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp.c @@ -13,8 +13,14 @@ void test_xdp(void) char buf[128]; struct ipv6hdr iph6; struct iphdr iph; - __u32 duration, retval, size; int err, prog_fd, map_fd; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .data_out = buf, + .data_size_out = sizeof(buf), + .repeat = 1, + ); err = bpf_prog_test_load(file, BPF_PROG_TYPE_XDP, &obj, &prog_fd); if (CHECK_FAIL(err)) @@ -26,21 +32,23 @@ void test_xdp(void) bpf_map_update_elem(map_fd, &key4, &value4, 0); bpf_map_update_elem(map_fd, &key6, &value6, 0); - err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4), - buf, &size, &retval, &duration); + err = bpf_prog_test_run_opts(prog_fd, &topts); memcpy(&iph, buf + sizeof(struct ethhdr), sizeof(iph)); - CHECK(err || retval != XDP_TX || size != 74 || - iph.protocol != IPPROTO_IPIP, "ipv4", - "err %d errno %d retval %d size %d\n", - err, errno, retval, size); + ASSERT_OK(err, "test_run"); + ASSERT_EQ(topts.retval, XDP_TX, "ipv4 test_run retval"); + ASSERT_EQ(topts.data_size_out, 74, "ipv4 test_run data_size_out"); + ASSERT_EQ(iph.protocol, IPPROTO_IPIP, "ipv4 test_run iph.protocol"); - err = bpf_prog_test_run(prog_fd, 1, &pkt_v6, sizeof(pkt_v6), - buf, &size, &retval, &duration); + topts.data_in = &pkt_v6; + topts.data_size_in = sizeof(pkt_v6); + topts.data_size_out = sizeof(buf); + + err = bpf_prog_test_run_opts(prog_fd, &topts); memcpy(&iph6, buf + sizeof(struct ethhdr), sizeof(iph6)); - CHECK(err || retval != XDP_TX || size != 114 || - iph6.nexthdr != IPPROTO_IPV6, "ipv6", - "err %d errno %d retval %d size %d\n", - err, errno, retval, size); + ASSERT_OK(err, "test_run"); + ASSERT_EQ(topts.retval, XDP_TX, "ipv6 test_run retval"); + ASSERT_EQ(topts.data_size_out, 114, "ipv6 test_run data_size_out"); + ASSERT_EQ(iph6.nexthdr, IPPROTO_IPV6, "ipv6 test_run iph6.nexthdr"); out: bpf_object__close(obj); } diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_adjust_frags.c b/tools/testing/selftests/bpf/prog_tests/xdp_adjust_frags.c new file mode 100644 index 000000000000..2f033da4cd45 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/xdp_adjust_frags.c @@ -0,0 +1,146 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <test_progs.h> +#include <network_helpers.h> + +static void test_xdp_update_frags(void) +{ + const char *file = "./test_xdp_update_frags.o"; + int err, prog_fd, max_skb_frags, buf_size, num; + struct bpf_program *prog; + struct bpf_object *obj; + __u32 *offset; + __u8 *buf; + FILE *f; + LIBBPF_OPTS(bpf_test_run_opts, topts); + + obj = bpf_object__open(file); + if (libbpf_get_error(obj)) + return; + + prog = bpf_object__next_program(obj, NULL); + if (bpf_object__load(obj)) + return; + + prog_fd = bpf_program__fd(prog); + + buf = malloc(128); + if (!ASSERT_OK_PTR(buf, "alloc buf 128b")) + goto out; + + memset(buf, 0, 128); + offset = (__u32 *)buf; + *offset = 16; + buf[*offset] = 0xaa; /* marker at offset 16 (head) */ + buf[*offset + 15] = 0xaa; /* marker at offset 31 (head) */ + + topts.data_in = buf; + topts.data_out = buf; + topts.data_size_in = 128; + topts.data_size_out = 128; + + err = bpf_prog_test_run_opts(prog_fd, &topts); + + /* test_xdp_update_frags: buf[16,31]: 0xaa -> 0xbb */ + ASSERT_OK(err, "xdp_update_frag"); + ASSERT_EQ(topts.retval, XDP_PASS, "xdp_update_frag retval"); + ASSERT_EQ(buf[16], 0xbb, "xdp_update_frag buf[16]"); + ASSERT_EQ(buf[31], 0xbb, "xdp_update_frag buf[31]"); + + free(buf); + + buf = malloc(9000); + if (!ASSERT_OK_PTR(buf, "alloc buf 9Kb")) + goto out; + + memset(buf, 0, 9000); + offset = (__u32 *)buf; + *offset = 5000; + buf[*offset] = 0xaa; /* marker at offset 5000 (frag0) */ + buf[*offset + 15] = 0xaa; /* marker at offset 5015 (frag0) */ + + topts.data_in = buf; + topts.data_out = buf; + topts.data_size_in = 9000; + topts.data_size_out = 9000; + + err = bpf_prog_test_run_opts(prog_fd, &topts); + + /* test_xdp_update_frags: buf[5000,5015]: 0xaa -> 0xbb */ + ASSERT_OK(err, "xdp_update_frag"); + ASSERT_EQ(topts.retval, XDP_PASS, "xdp_update_frag retval"); + ASSERT_EQ(buf[5000], 0xbb, "xdp_update_frag buf[5000]"); + ASSERT_EQ(buf[5015], 0xbb, "xdp_update_frag buf[5015]"); + + memset(buf, 0, 9000); + offset = (__u32 *)buf; + *offset = 3510; + buf[*offset] = 0xaa; /* marker at offset 3510 (head) */ + buf[*offset + 15] = 0xaa; /* marker at offset 3525 (frag0) */ + + err = bpf_prog_test_run_opts(prog_fd, &topts); + + /* test_xdp_update_frags: buf[3510,3525]: 0xaa -> 0xbb */ + ASSERT_OK(err, "xdp_update_frag"); + ASSERT_EQ(topts.retval, XDP_PASS, "xdp_update_frag retval"); + ASSERT_EQ(buf[3510], 0xbb, "xdp_update_frag buf[3510]"); + ASSERT_EQ(buf[3525], 0xbb, "xdp_update_frag buf[3525]"); + + memset(buf, 0, 9000); + offset = (__u32 *)buf; + *offset = 7606; + buf[*offset] = 0xaa; /* marker at offset 7606 (frag0) */ + buf[*offset + 15] = 0xaa; /* marker at offset 7621 (frag1) */ + + err = bpf_prog_test_run_opts(prog_fd, &topts); + + /* test_xdp_update_frags: buf[7606,7621]: 0xaa -> 0xbb */ + ASSERT_OK(err, "xdp_update_frag"); + ASSERT_EQ(topts.retval, XDP_PASS, "xdp_update_frag retval"); + ASSERT_EQ(buf[7606], 0xbb, "xdp_update_frag buf[7606]"); + ASSERT_EQ(buf[7621], 0xbb, "xdp_update_frag buf[7621]"); + + free(buf); + + /* test_xdp_update_frags: unsupported buffer size */ + f = fopen("/proc/sys/net/core/max_skb_frags", "r"); + if (!ASSERT_OK_PTR(f, "max_skb_frag file pointer")) + goto out; + + num = fscanf(f, "%d", &max_skb_frags); + fclose(f); + + if (!ASSERT_EQ(num, 1, "max_skb_frags read failed")) + goto out; + + /* xdp_buff linear area size is always set to 4096 in the + * bpf_prog_test_run_xdp routine. + */ + buf_size = 4096 + (max_skb_frags + 1) * sysconf(_SC_PAGE_SIZE); + buf = malloc(buf_size); + if (!ASSERT_OK_PTR(buf, "alloc buf")) + goto out; + + memset(buf, 0, buf_size); + offset = (__u32 *)buf; + *offset = 16; + buf[*offset] = 0xaa; + buf[*offset + 15] = 0xaa; + + topts.data_in = buf; + topts.data_out = buf; + topts.data_size_in = buf_size; + topts.data_size_out = buf_size; + + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_EQ(err, -ENOMEM, + "unsupported buf size, possible non-default /proc/sys/net/core/max_skb_flags?"); + free(buf); +out: + bpf_object__close(obj); +} + +void test_xdp_adjust_frags(void) +{ + if (test__start_subtest("xdp_adjust_frags")) + test_xdp_update_frags(); +} diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c b/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c index 3f5a17c38be5..21ceac24e174 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c @@ -5,28 +5,35 @@ static void test_xdp_adjust_tail_shrink(void) { const char *file = "./test_xdp_adjust_tail_shrink.o"; - __u32 duration, retval, size, expect_sz; + __u32 expect_sz; struct bpf_object *obj; int err, prog_fd; char buf[128]; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .data_out = buf, + .data_size_out = sizeof(buf), + .repeat = 1, + ); err = bpf_prog_test_load(file, BPF_PROG_TYPE_XDP, &obj, &prog_fd); - if (CHECK_FAIL(err)) + if (ASSERT_OK(err, "test_xdp_adjust_tail_shrink")) return; - err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4), - buf, &size, &retval, &duration); - - CHECK(err || retval != XDP_DROP, - "ipv4", "err %d errno %d retval %d size %d\n", - err, errno, retval, size); + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "ipv4"); + ASSERT_EQ(topts.retval, XDP_DROP, "ipv4 retval"); expect_sz = sizeof(pkt_v6) - 20; /* Test shrink with 20 bytes */ - err = bpf_prog_test_run(prog_fd, 1, &pkt_v6, sizeof(pkt_v6), - buf, &size, &retval, &duration); - CHECK(err || retval != XDP_TX || size != expect_sz, - "ipv6", "err %d errno %d retval %d size %d expect-size %d\n", - err, errno, retval, size, expect_sz); + topts.data_in = &pkt_v6; + topts.data_size_in = sizeof(pkt_v6); + topts.data_size_out = sizeof(buf); + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "ipv6"); + ASSERT_EQ(topts.retval, XDP_TX, "ipv6 retval"); + ASSERT_EQ(topts.data_size_out, expect_sz, "ipv6 size"); + bpf_object__close(obj); } @@ -35,25 +42,31 @@ static void test_xdp_adjust_tail_grow(void) const char *file = "./test_xdp_adjust_tail_grow.o"; struct bpf_object *obj; char buf[4096]; /* avoid segfault: large buf to hold grow results */ - __u32 duration, retval, size, expect_sz; + __u32 expect_sz; int err, prog_fd; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .data_out = buf, + .data_size_out = sizeof(buf), + .repeat = 1, + ); err = bpf_prog_test_load(file, BPF_PROG_TYPE_XDP, &obj, &prog_fd); - if (CHECK_FAIL(err)) + if (ASSERT_OK(err, "test_xdp_adjust_tail_grow")) return; - err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4), - buf, &size, &retval, &duration); - CHECK(err || retval != XDP_DROP, - "ipv4", "err %d errno %d retval %d size %d\n", - err, errno, retval, size); + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "ipv4"); + ASSERT_EQ(topts.retval, XDP_DROP, "ipv4 retval"); expect_sz = sizeof(pkt_v6) + 40; /* Test grow with 40 bytes */ - err = bpf_prog_test_run(prog_fd, 1, &pkt_v6, sizeof(pkt_v6) /* 74 */, - buf, &size, &retval, &duration); - CHECK(err || retval != XDP_TX || size != expect_sz, - "ipv6", "err %d errno %d retval %d size %d expect-size %d\n", - err, errno, retval, size, expect_sz); + topts.data_in = &pkt_v6; + topts.data_size_in = sizeof(pkt_v6); + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "ipv6"); + ASSERT_EQ(topts.retval, XDP_TX, "ipv6 retval"); + ASSERT_EQ(topts.data_size_out, expect_sz, "ipv6 size"); bpf_object__close(obj); } @@ -65,18 +78,18 @@ static void test_xdp_adjust_tail_grow2(void) int tailroom = 320; /* SKB_DATA_ALIGN(sizeof(struct skb_shared_info))*/; struct bpf_object *obj; int err, cnt, i; - int max_grow; + int max_grow, prog_fd; - struct bpf_prog_test_run_attr tattr = { + LIBBPF_OPTS(bpf_test_run_opts, tattr, .repeat = 1, .data_in = &buf, .data_out = &buf, .data_size_in = 0, /* Per test */ .data_size_out = 0, /* Per test */ - }; + ); - err = bpf_prog_test_load(file, BPF_PROG_TYPE_XDP, &obj, &tattr.prog_fd); - if (CHECK_ATTR(err, "load", "err %d errno %d\n", err, errno)) + err = bpf_prog_test_load(file, BPF_PROG_TYPE_XDP, &obj, &prog_fd); + if (ASSERT_OK(err, "test_xdp_adjust_tail_grow")) return; /* Test case-64 */ @@ -84,49 +97,171 @@ static void test_xdp_adjust_tail_grow2(void) tattr.data_size_in = 64; /* Determine test case via pkt size */ tattr.data_size_out = 128; /* Limit copy_size */ /* Kernel side alloc packet memory area that is zero init */ - err = bpf_prog_test_run_xattr(&tattr); + err = bpf_prog_test_run_opts(prog_fd, &tattr); - CHECK_ATTR(errno != ENOSPC /* Due limit copy_size in bpf_test_finish */ - || tattr.retval != XDP_TX - || tattr.data_size_out != 192, /* Expected grow size */ - "case-64", - "err %d errno %d retval %d size %d\n", - err, errno, tattr.retval, tattr.data_size_out); + ASSERT_EQ(errno, ENOSPC, "case-64 errno"); /* Due limit copy_size in bpf_test_finish */ + ASSERT_EQ(tattr.retval, XDP_TX, "case-64 retval"); + ASSERT_EQ(tattr.data_size_out, 192, "case-64 data_size_out"); /* Expected grow size */ /* Extra checks for data contents */ - CHECK_ATTR(tattr.data_size_out != 192 - || buf[0] != 1 || buf[63] != 1 /* 0-63 memset to 1 */ - || buf[64] != 0 || buf[127] != 0 /* 64-127 memset to 0 */ - || buf[128] != 1 || buf[191] != 1, /*128-191 memset to 1 */ - "case-64-data", - "err %d errno %d retval %d size %d\n", - err, errno, tattr.retval, tattr.data_size_out); + ASSERT_EQ(buf[0], 1, "case-64-data buf[0]"); /* 0-63 memset to 1 */ + ASSERT_EQ(buf[63], 1, "case-64-data buf[63]"); + ASSERT_EQ(buf[64], 0, "case-64-data buf[64]"); /* 64-127 memset to 0 */ + ASSERT_EQ(buf[127], 0, "case-64-data buf[127]"); + ASSERT_EQ(buf[128], 1, "case-64-data buf[128]"); /* 128-191 memset to 1 */ + ASSERT_EQ(buf[191], 1, "case-64-data buf[191]"); /* Test case-128 */ memset(buf, 2, sizeof(buf)); tattr.data_size_in = 128; /* Determine test case via pkt size */ tattr.data_size_out = sizeof(buf); /* Copy everything */ - err = bpf_prog_test_run_xattr(&tattr); + err = bpf_prog_test_run_opts(prog_fd, &tattr); max_grow = 4096 - XDP_PACKET_HEADROOM - tailroom; /* 3520 */ - CHECK_ATTR(err - || tattr.retval != XDP_TX - || tattr.data_size_out != max_grow,/* Expect max grow size */ - "case-128", - "err %d errno %d retval %d size %d expect-size %d\n", - err, errno, tattr.retval, tattr.data_size_out, max_grow); + ASSERT_OK(err, "case-128"); + ASSERT_EQ(tattr.retval, XDP_TX, "case-128 retval"); + ASSERT_EQ(tattr.data_size_out, max_grow, "case-128 data_size_out"); /* Expect max grow */ /* Extra checks for data content: Count grow size, will contain zeros */ for (i = 0, cnt = 0; i < sizeof(buf); i++) { if (buf[i] == 0) cnt++; } - CHECK_ATTR((cnt != (max_grow - tattr.data_size_in)) /* Grow increase */ - || tattr.data_size_out != max_grow, /* Total grow size */ - "case-128-data", - "err %d errno %d retval %d size %d grow-size %d\n", - err, errno, tattr.retval, tattr.data_size_out, cnt); + ASSERT_EQ(cnt, max_grow - tattr.data_size_in, "case-128-data cnt"); /* Grow increase */ + ASSERT_EQ(tattr.data_size_out, max_grow, "case-128-data data_size_out"); /* Total grow */ + + bpf_object__close(obj); +} + +static void test_xdp_adjust_frags_tail_shrink(void) +{ + const char *file = "./test_xdp_adjust_tail_shrink.o"; + __u32 exp_size; + struct bpf_program *prog; + struct bpf_object *obj; + int err, prog_fd; + __u8 *buf; + LIBBPF_OPTS(bpf_test_run_opts, topts); + + /* For the individual test cases, the first byte in the packet + * indicates which test will be run. + */ + obj = bpf_object__open(file); + if (libbpf_get_error(obj)) + return; + + prog = bpf_object__next_program(obj, NULL); + if (bpf_object__load(obj)) + return; + + prog_fd = bpf_program__fd(prog); + + buf = malloc(9000); + if (!ASSERT_OK_PTR(buf, "alloc buf 9Kb")) + goto out; + + memset(buf, 0, 9000); + + /* Test case removing 10 bytes from last frag, NOT freeing it */ + exp_size = 8990; /* 9000 - 10 */ + topts.data_in = buf; + topts.data_out = buf; + topts.data_size_in = 9000; + topts.data_size_out = 9000; + err = bpf_prog_test_run_opts(prog_fd, &topts); + + ASSERT_OK(err, "9Kb-10b"); + ASSERT_EQ(topts.retval, XDP_TX, "9Kb-10b retval"); + ASSERT_EQ(topts.data_size_out, exp_size, "9Kb-10b size"); + + /* Test case removing one of two pages, assuming 4K pages */ + buf[0] = 1; + exp_size = 4900; /* 9000 - 4100 */ + + topts.data_size_out = 9000; /* reset from previous invocation */ + err = bpf_prog_test_run_opts(prog_fd, &topts); + + ASSERT_OK(err, "9Kb-4Kb"); + ASSERT_EQ(topts.retval, XDP_TX, "9Kb-4Kb retval"); + ASSERT_EQ(topts.data_size_out, exp_size, "9Kb-4Kb size"); + + /* Test case removing two pages resulting in a linear xdp_buff */ + buf[0] = 2; + exp_size = 800; /* 9000 - 8200 */ + topts.data_size_out = 9000; /* reset from previous invocation */ + err = bpf_prog_test_run_opts(prog_fd, &topts); + + ASSERT_OK(err, "9Kb-9Kb"); + ASSERT_EQ(topts.retval, XDP_TX, "9Kb-9Kb retval"); + ASSERT_EQ(topts.data_size_out, exp_size, "9Kb-9Kb size"); + + free(buf); +out: + bpf_object__close(obj); +} + +static void test_xdp_adjust_frags_tail_grow(void) +{ + const char *file = "./test_xdp_adjust_tail_grow.o"; + __u32 exp_size; + struct bpf_program *prog; + struct bpf_object *obj; + int err, i, prog_fd; + __u8 *buf; + LIBBPF_OPTS(bpf_test_run_opts, topts); + + obj = bpf_object__open(file); + if (libbpf_get_error(obj)) + return; + + prog = bpf_object__next_program(obj, NULL); + if (bpf_object__load(obj)) + return; + + prog_fd = bpf_program__fd(prog); + + buf = malloc(16384); + if (!ASSERT_OK_PTR(buf, "alloc buf 16Kb")) + goto out; + + /* Test case add 10 bytes to last frag */ + memset(buf, 1, 16384); + exp_size = 9000 + 10; + + topts.data_in = buf; + topts.data_out = buf; + topts.data_size_in = 9000; + topts.data_size_out = 16384; + err = bpf_prog_test_run_opts(prog_fd, &topts); + + ASSERT_OK(err, "9Kb+10b"); + ASSERT_EQ(topts.retval, XDP_TX, "9Kb+10b retval"); + ASSERT_EQ(topts.data_size_out, exp_size, "9Kb+10b size"); + + for (i = 0; i < 9000; i++) + ASSERT_EQ(buf[i], 1, "9Kb+10b-old"); + + for (i = 9000; i < 9010; i++) + ASSERT_EQ(buf[i], 0, "9Kb+10b-new"); + + for (i = 9010; i < 16384; i++) + ASSERT_EQ(buf[i], 1, "9Kb+10b-untouched"); + + /* Test a too large grow */ + memset(buf, 1, 16384); + exp_size = 9001; + + topts.data_in = topts.data_out = buf; + topts.data_size_in = 9001; + topts.data_size_out = 16384; + err = bpf_prog_test_run_opts(prog_fd, &topts); + + ASSERT_OK(err, "9Kb+10b"); + ASSERT_EQ(topts.retval, XDP_DROP, "9Kb+10b retval"); + ASSERT_EQ(topts.data_size_out, exp_size, "9Kb+10b size"); + free(buf); +out: bpf_object__close(obj); } @@ -138,4 +273,8 @@ void test_xdp_adjust_tail(void) test_xdp_adjust_tail_grow(); if (test__start_subtest("xdp_adjust_tail_grow2")) test_xdp_adjust_tail_grow2(); + if (test__start_subtest("xdp_adjust_frags_tail_shrink")) + test_xdp_adjust_frags_tail_shrink(); + if (test__start_subtest("xdp_adjust_frags_tail_grow")) + test_xdp_adjust_frags_tail_grow(); } diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_attach.c b/tools/testing/selftests/bpf/prog_tests/xdp_attach.c index c6fa390e3aa1..62aa3edda5e6 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_attach.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_attach.c @@ -11,8 +11,7 @@ void serial_test_xdp_attach(void) const char *file = "./test_xdp.o"; struct bpf_prog_info info = {}; int err, fd1, fd2, fd3; - DECLARE_LIBBPF_OPTS(bpf_xdp_set_link_opts, opts, - .old_fd = -1); + LIBBPF_OPTS(bpf_xdp_attach_opts, opts); len = sizeof(info); @@ -38,49 +37,47 @@ void serial_test_xdp_attach(void) if (CHECK_FAIL(err)) goto out_2; - err = bpf_set_link_xdp_fd_opts(IFINDEX_LO, fd1, XDP_FLAGS_REPLACE, - &opts); + err = bpf_xdp_attach(IFINDEX_LO, fd1, XDP_FLAGS_REPLACE, &opts); if (CHECK(err, "load_ok", "initial load failed")) goto out_close; - err = bpf_get_link_xdp_id(IFINDEX_LO, &id0, 0); + err = bpf_xdp_query_id(IFINDEX_LO, 0, &id0); if (CHECK(err || id0 != id1, "id1_check", "loaded prog id %u != id1 %u, err %d", id0, id1, err)) goto out_close; - err = bpf_set_link_xdp_fd_opts(IFINDEX_LO, fd2, XDP_FLAGS_REPLACE, - &opts); + err = bpf_xdp_attach(IFINDEX_LO, fd2, XDP_FLAGS_REPLACE, &opts); if (CHECK(!err, "load_fail", "load with expected id didn't fail")) goto out; - opts.old_fd = fd1; - err = bpf_set_link_xdp_fd_opts(IFINDEX_LO, fd2, 0, &opts); + opts.old_prog_fd = fd1; + err = bpf_xdp_attach(IFINDEX_LO, fd2, 0, &opts); if (CHECK(err, "replace_ok", "replace valid old_fd failed")) goto out; - err = bpf_get_link_xdp_id(IFINDEX_LO, &id0, 0); + err = bpf_xdp_query_id(IFINDEX_LO, 0, &id0); if (CHECK(err || id0 != id2, "id2_check", "loaded prog id %u != id2 %u, err %d", id0, id2, err)) goto out_close; - err = bpf_set_link_xdp_fd_opts(IFINDEX_LO, fd3, 0, &opts); + err = bpf_xdp_attach(IFINDEX_LO, fd3, 0, &opts); if (CHECK(!err, "replace_fail", "replace invalid old_fd didn't fail")) goto out; - err = bpf_set_link_xdp_fd_opts(IFINDEX_LO, -1, 0, &opts); + err = bpf_xdp_detach(IFINDEX_LO, 0, &opts); if (CHECK(!err, "remove_fail", "remove invalid old_fd didn't fail")) goto out; - opts.old_fd = fd2; - err = bpf_set_link_xdp_fd_opts(IFINDEX_LO, -1, 0, &opts); + opts.old_prog_fd = fd2; + err = bpf_xdp_detach(IFINDEX_LO, 0, &opts); if (CHECK(err, "remove_ok", "remove valid old_fd failed")) goto out; - err = bpf_get_link_xdp_id(IFINDEX_LO, &id0, 0); + err = bpf_xdp_query_id(IFINDEX_LO, 0, &id0); if (CHECK(err || id0 != 0, "unload_check", "loaded prog id %u != 0, err %d", id0, err)) goto out_close; out: - bpf_set_link_xdp_fd(IFINDEX_LO, -1, 0); + bpf_xdp_detach(IFINDEX_LO, 0, NULL); out_close: bpf_object__close(obj3); out_2: diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_bpf2bpf.c b/tools/testing/selftests/bpf/prog_tests/xdp_bpf2bpf.c index c98a897ad692..76967d8ace9c 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_bpf2bpf.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_bpf2bpf.c @@ -10,40 +10,101 @@ struct meta { int pkt_len; }; +struct test_ctx_s { + bool passed; + int pkt_size; +}; + +struct test_ctx_s test_ctx; + static void on_sample(void *ctx, int cpu, void *data, __u32 size) { - int duration = 0; struct meta *meta = (struct meta *)data; struct ipv4_packet *trace_pkt_v4 = data + sizeof(*meta); + unsigned char *raw_pkt = data + sizeof(*meta); + struct test_ctx_s *tst_ctx = ctx; + + ASSERT_GE(size, sizeof(pkt_v4) + sizeof(*meta), "check_size"); + ASSERT_EQ(meta->ifindex, if_nametoindex("lo"), "check_meta_ifindex"); + ASSERT_EQ(meta->pkt_len, tst_ctx->pkt_size, "check_meta_pkt_len"); + ASSERT_EQ(memcmp(trace_pkt_v4, &pkt_v4, sizeof(pkt_v4)), 0, + "check_packet_content"); + + if (meta->pkt_len > sizeof(pkt_v4)) { + for (int i = 0; i < meta->pkt_len - sizeof(pkt_v4); i++) + ASSERT_EQ(raw_pkt[i + sizeof(pkt_v4)], (unsigned char)i, + "check_packet_content"); + } + + tst_ctx->passed = true; +} - if (CHECK(size < sizeof(pkt_v4) + sizeof(*meta), - "check_size", "size %u < %zu\n", - size, sizeof(pkt_v4) + sizeof(*meta))) - return; +#define BUF_SZ 9000 - if (CHECK(meta->ifindex != if_nametoindex("lo"), "check_meta_ifindex", - "meta->ifindex = %d\n", meta->ifindex)) +static void run_xdp_bpf2bpf_pkt_size(int pkt_fd, struct perf_buffer *pb, + struct test_xdp_bpf2bpf *ftrace_skel, + int pkt_size) +{ + __u8 *buf, *buf_in; + int err; + LIBBPF_OPTS(bpf_test_run_opts, topts); + + if (!ASSERT_LE(pkt_size, BUF_SZ, "pkt_size") || + !ASSERT_GE(pkt_size, sizeof(pkt_v4), "pkt_size")) return; - if (CHECK(meta->pkt_len != sizeof(pkt_v4), "check_meta_pkt_len", - "meta->pkt_len = %zd\n", sizeof(pkt_v4))) + buf_in = malloc(BUF_SZ); + if (!ASSERT_OK_PTR(buf_in, "buf_in malloc()")) return; - if (CHECK(memcmp(trace_pkt_v4, &pkt_v4, sizeof(pkt_v4)), - "check_packet_content", "content not the same\n")) + buf = malloc(BUF_SZ); + if (!ASSERT_OK_PTR(buf, "buf malloc()")) { + free(buf_in); return; + } + + test_ctx.passed = false; + test_ctx.pkt_size = pkt_size; + + memcpy(buf_in, &pkt_v4, sizeof(pkt_v4)); + if (pkt_size > sizeof(pkt_v4)) { + for (int i = 0; i < (pkt_size - sizeof(pkt_v4)); i++) + buf_in[i + sizeof(pkt_v4)] = i; + } + + /* Run test program */ + topts.data_in = buf_in; + topts.data_size_in = pkt_size; + topts.data_out = buf; + topts.data_size_out = BUF_SZ; + + err = bpf_prog_test_run_opts(pkt_fd, &topts); + + ASSERT_OK(err, "ipv4"); + ASSERT_EQ(topts.retval, XDP_PASS, "ipv4 retval"); + ASSERT_EQ(topts.data_size_out, pkt_size, "ipv4 size"); + + /* Make sure bpf_xdp_output() was triggered and it sent the expected + * data to the perf ring buffer. + */ + err = perf_buffer__poll(pb, 100); + + ASSERT_GE(err, 0, "perf_buffer__poll"); + ASSERT_TRUE(test_ctx.passed, "test passed"); + /* Verify test results */ + ASSERT_EQ(ftrace_skel->bss->test_result_fentry, if_nametoindex("lo"), + "fentry result"); + ASSERT_EQ(ftrace_skel->bss->test_result_fexit, XDP_PASS, "fexit result"); - *(bool *)ctx = true; + free(buf); + free(buf_in); } void test_xdp_bpf2bpf(void) { - __u32 duration = 0, retval, size; - char buf[128]; int err, pkt_fd, map_fd; - bool passed = false; - struct iphdr iph; - struct iptnl_info value4 = {.family = AF_INET}; + int pkt_sizes[] = {sizeof(pkt_v4), 1024, 4100, 8200}; + struct iptnl_info value4 = {.family = AF_INET6}; struct test_xdp *pkt_skel = NULL; struct test_xdp_bpf2bpf *ftrace_skel = NULL; struct vip key4 = {.protocol = 6, .family = AF_INET}; @@ -52,7 +113,7 @@ void test_xdp_bpf2bpf(void) /* Load XDP program to introspect */ pkt_skel = test_xdp__open_and_load(); - if (CHECK(!pkt_skel, "pkt_skel_load", "test_xdp skeleton failed\n")) + if (!ASSERT_OK_PTR(pkt_skel, "test_xdp__open_and_load")) return; pkt_fd = bpf_program__fd(pkt_skel->progs._xdp_tx_iptunnel); @@ -62,7 +123,7 @@ void test_xdp_bpf2bpf(void) /* Load trace program */ ftrace_skel = test_xdp_bpf2bpf__open(); - if (CHECK(!ftrace_skel, "__open", "ftrace skeleton failed\n")) + if (!ASSERT_OK_PTR(ftrace_skel, "test_xdp_bpf2bpf__open")) goto out; /* Demonstrate the bpf_program__set_attach_target() API rather than @@ -77,50 +138,24 @@ void test_xdp_bpf2bpf(void) bpf_program__set_attach_target(prog, pkt_fd, "_xdp_tx_iptunnel"); err = test_xdp_bpf2bpf__load(ftrace_skel); - if (CHECK(err, "__load", "ftrace skeleton failed\n")) + if (!ASSERT_OK(err, "test_xdp_bpf2bpf__load")) goto out; err = test_xdp_bpf2bpf__attach(ftrace_skel); - if (CHECK(err, "ftrace_attach", "ftrace attach failed: %d\n", err)) + if (!ASSERT_OK(err, "test_xdp_bpf2bpf__attach")) goto out; /* Set up perf buffer */ - pb = perf_buffer__new(bpf_map__fd(ftrace_skel->maps.perf_buf_map), 1, - on_sample, NULL, &passed, NULL); + pb = perf_buffer__new(bpf_map__fd(ftrace_skel->maps.perf_buf_map), 8, + on_sample, NULL, &test_ctx, NULL); if (!ASSERT_OK_PTR(pb, "perf_buf__new")) goto out; - /* Run test program */ - err = bpf_prog_test_run(pkt_fd, 1, &pkt_v4, sizeof(pkt_v4), - buf, &size, &retval, &duration); - memcpy(&iph, buf + sizeof(struct ethhdr), sizeof(iph)); - if (CHECK(err || retval != XDP_TX || size != 74 || - iph.protocol != IPPROTO_IPIP, "ipv4", - "err %d errno %d retval %d size %d\n", - err, errno, retval, size)) - goto out; - - /* Make sure bpf_xdp_output() was triggered and it sent the expected - * data to the perf ring buffer. - */ - err = perf_buffer__poll(pb, 100); - if (CHECK(err < 0, "perf_buffer__poll", "err %d\n", err)) - goto out; - - CHECK_FAIL(!passed); - - /* Verify test results */ - if (CHECK(ftrace_skel->bss->test_result_fentry != if_nametoindex("lo"), - "result", "fentry failed err %llu\n", - ftrace_skel->bss->test_result_fentry)) - goto out; - - CHECK(ftrace_skel->bss->test_result_fexit != XDP_TX, "result", - "fexit failed err %llu\n", ftrace_skel->bss->test_result_fexit); - + for (int i = 0; i < ARRAY_SIZE(pkt_sizes); i++) + run_xdp_bpf2bpf_pkt_size(pkt_fd, pb, ftrace_skel, + pkt_sizes[i]); out: - if (pb) - perf_buffer__free(pb); + perf_buffer__free(pb); test_xdp__destroy(pkt_skel); test_xdp_bpf2bpf__destroy(ftrace_skel); } diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c b/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c index fd812bd43600..f775a1613833 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c @@ -3,11 +3,12 @@ #include <linux/if_link.h> #include <test_progs.h> +#include "test_xdp_with_cpumap_frags_helpers.skel.h" #include "test_xdp_with_cpumap_helpers.skel.h" #define IFINDEX_LO 1 -void serial_test_xdp_cpumap_attach(void) +static void test_xdp_with_cpumap_helpers(void) { struct test_xdp_with_cpumap_helpers *skel; struct bpf_prog_info info = {}; @@ -23,11 +24,11 @@ void serial_test_xdp_cpumap_attach(void) return; prog_fd = bpf_program__fd(skel->progs.xdp_redir_prog); - err = bpf_set_link_xdp_fd(IFINDEX_LO, prog_fd, XDP_FLAGS_SKB_MODE); + err = bpf_xdp_attach(IFINDEX_LO, prog_fd, XDP_FLAGS_SKB_MODE, NULL); if (!ASSERT_OK(err, "Generic attach of program with 8-byte CPUMAP")) goto out_close; - err = bpf_set_link_xdp_fd(IFINDEX_LO, -1, XDP_FLAGS_SKB_MODE); + err = bpf_xdp_detach(IFINDEX_LO, XDP_FLAGS_SKB_MODE, NULL); ASSERT_OK(err, "XDP program detach"); prog_fd = bpf_program__fd(skel->progs.xdp_dummy_cm); @@ -45,15 +46,76 @@ void serial_test_xdp_cpumap_attach(void) ASSERT_EQ(info.id, val.bpf_prog.id, "Match program id to cpumap entry prog_id"); /* can not attach BPF_XDP_CPUMAP program to a device */ - err = bpf_set_link_xdp_fd(IFINDEX_LO, prog_fd, XDP_FLAGS_SKB_MODE); + err = bpf_xdp_attach(IFINDEX_LO, prog_fd, XDP_FLAGS_SKB_MODE, NULL); if (!ASSERT_NEQ(err, 0, "Attach of BPF_XDP_CPUMAP program")) - bpf_set_link_xdp_fd(IFINDEX_LO, -1, XDP_FLAGS_SKB_MODE); + bpf_xdp_detach(IFINDEX_LO, XDP_FLAGS_SKB_MODE, NULL); val.qsize = 192; val.bpf_prog.fd = bpf_program__fd(skel->progs.xdp_dummy_prog); err = bpf_map_update_elem(map_fd, &idx, &val, 0); ASSERT_NEQ(err, 0, "Add non-BPF_XDP_CPUMAP program to cpumap entry"); + /* Try to attach BPF_XDP program with frags to cpumap when we have + * already loaded a BPF_XDP program on the map + */ + idx = 1; + val.qsize = 192; + val.bpf_prog.fd = bpf_program__fd(skel->progs.xdp_dummy_cm_frags); + err = bpf_map_update_elem(map_fd, &idx, &val, 0); + ASSERT_NEQ(err, 0, "Add BPF_XDP program with frags to cpumap entry"); + out_close: test_xdp_with_cpumap_helpers__destroy(skel); } + +static void test_xdp_with_cpumap_frags_helpers(void) +{ + struct test_xdp_with_cpumap_frags_helpers *skel; + struct bpf_prog_info info = {}; + __u32 len = sizeof(info); + struct bpf_cpumap_val val = { + .qsize = 192, + }; + int err, frags_prog_fd, map_fd; + __u32 idx = 0; + + skel = test_xdp_with_cpumap_frags_helpers__open_and_load(); + if (!ASSERT_OK_PTR(skel, "test_xdp_with_cpumap_helpers__open_and_load")) + return; + + frags_prog_fd = bpf_program__fd(skel->progs.xdp_dummy_cm_frags); + map_fd = bpf_map__fd(skel->maps.cpu_map); + err = bpf_obj_get_info_by_fd(frags_prog_fd, &info, &len); + if (!ASSERT_OK(err, "bpf_obj_get_info_by_fd")) + goto out_close; + + val.bpf_prog.fd = frags_prog_fd; + err = bpf_map_update_elem(map_fd, &idx, &val, 0); + ASSERT_OK(err, "Add program to cpumap entry"); + + err = bpf_map_lookup_elem(map_fd, &idx, &val); + ASSERT_OK(err, "Read cpumap entry"); + ASSERT_EQ(info.id, val.bpf_prog.id, + "Match program id to cpumap entry prog_id"); + + /* Try to attach BPF_XDP program to cpumap when we have + * already loaded a BPF_XDP program with frags on the map + */ + idx = 1; + val.qsize = 192; + val.bpf_prog.fd = bpf_program__fd(skel->progs.xdp_dummy_cm); + err = bpf_map_update_elem(map_fd, &idx, &val, 0); + ASSERT_NEQ(err, 0, "Add BPF_XDP program to cpumap entry"); + +out_close: + test_xdp_with_cpumap_frags_helpers__destroy(skel); +} + +void serial_test_xdp_cpumap_attach(void) +{ + if (test__start_subtest("CPUMAP with programs in entries")) + test_xdp_with_cpumap_helpers(); + + if (test__start_subtest("CPUMAP with frags programs in entries")) + test_xdp_with_cpumap_frags_helpers(); +} diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c b/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c index 3079d5568f8f..ead40016c324 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c @@ -4,6 +4,7 @@ #include <test_progs.h> #include "test_xdp_devmap_helpers.skel.h" +#include "test_xdp_with_devmap_frags_helpers.skel.h" #include "test_xdp_with_devmap_helpers.skel.h" #define IFINDEX_LO 1 @@ -25,11 +26,11 @@ static void test_xdp_with_devmap_helpers(void) return; dm_fd = bpf_program__fd(skel->progs.xdp_redir_prog); - err = bpf_set_link_xdp_fd(IFINDEX_LO, dm_fd, XDP_FLAGS_SKB_MODE); + err = bpf_xdp_attach(IFINDEX_LO, dm_fd, XDP_FLAGS_SKB_MODE, NULL); if (!ASSERT_OK(err, "Generic attach of program with 8-byte devmap")) goto out_close; - err = bpf_set_link_xdp_fd(IFINDEX_LO, -1, XDP_FLAGS_SKB_MODE); + err = bpf_xdp_detach(IFINDEX_LO, XDP_FLAGS_SKB_MODE, NULL); ASSERT_OK(err, "XDP program detach"); dm_fd = bpf_program__fd(skel->progs.xdp_dummy_dm); @@ -47,15 +48,24 @@ static void test_xdp_with_devmap_helpers(void) ASSERT_EQ(info.id, val.bpf_prog.id, "Match program id to devmap entry prog_id"); /* can not attach BPF_XDP_DEVMAP program to a device */ - err = bpf_set_link_xdp_fd(IFINDEX_LO, dm_fd, XDP_FLAGS_SKB_MODE); + err = bpf_xdp_attach(IFINDEX_LO, dm_fd, XDP_FLAGS_SKB_MODE, NULL); if (!ASSERT_NEQ(err, 0, "Attach of BPF_XDP_DEVMAP program")) - bpf_set_link_xdp_fd(IFINDEX_LO, -1, XDP_FLAGS_SKB_MODE); + bpf_xdp_detach(IFINDEX_LO, XDP_FLAGS_SKB_MODE, NULL); val.ifindex = 1; val.bpf_prog.fd = bpf_program__fd(skel->progs.xdp_dummy_prog); err = bpf_map_update_elem(map_fd, &idx, &val, 0); ASSERT_NEQ(err, 0, "Add non-BPF_XDP_DEVMAP program to devmap entry"); + /* Try to attach BPF_XDP program with frags to devmap when we have + * already loaded a BPF_XDP program on the map + */ + idx = 1; + val.ifindex = 1; + val.bpf_prog.fd = bpf_program__fd(skel->progs.xdp_dummy_dm_frags); + err = bpf_map_update_elem(map_fd, &idx, &val, 0); + ASSERT_NEQ(err, 0, "Add BPF_XDP program with frags to devmap entry"); + out_close: test_xdp_with_devmap_helpers__destroy(skel); } @@ -71,12 +81,57 @@ static void test_neg_xdp_devmap_helpers(void) } } +static void test_xdp_with_devmap_frags_helpers(void) +{ + struct test_xdp_with_devmap_frags_helpers *skel; + struct bpf_prog_info info = {}; + struct bpf_devmap_val val = { + .ifindex = IFINDEX_LO, + }; + __u32 len = sizeof(info); + int err, dm_fd_frags, map_fd; + __u32 idx = 0; + + skel = test_xdp_with_devmap_frags_helpers__open_and_load(); + if (!ASSERT_OK_PTR(skel, "test_xdp_with_devmap_helpers__open_and_load")) + return; + + dm_fd_frags = bpf_program__fd(skel->progs.xdp_dummy_dm_frags); + map_fd = bpf_map__fd(skel->maps.dm_ports); + err = bpf_obj_get_info_by_fd(dm_fd_frags, &info, &len); + if (!ASSERT_OK(err, "bpf_obj_get_info_by_fd")) + goto out_close; + + val.bpf_prog.fd = dm_fd_frags; + err = bpf_map_update_elem(map_fd, &idx, &val, 0); + ASSERT_OK(err, "Add frags program to devmap entry"); + + err = bpf_map_lookup_elem(map_fd, &idx, &val); + ASSERT_OK(err, "Read devmap entry"); + ASSERT_EQ(info.id, val.bpf_prog.id, + "Match program id to devmap entry prog_id"); + + /* Try to attach BPF_XDP program to devmap when we have + * already loaded a BPF_XDP program with frags on the map + */ + idx = 1; + val.ifindex = 1; + val.bpf_prog.fd = bpf_program__fd(skel->progs.xdp_dummy_dm); + err = bpf_map_update_elem(map_fd, &idx, &val, 0); + ASSERT_NEQ(err, 0, "Add BPF_XDP program to devmap entry"); + +out_close: + test_xdp_with_devmap_frags_helpers__destroy(skel); +} void serial_test_xdp_devmap_attach(void) { if (test__start_subtest("DEVMAP with programs in entries")) test_xdp_with_devmap_helpers(); + if (test__start_subtest("DEVMAP with frags programs in entries")) + test_xdp_with_devmap_frags_helpers(); + if (test__start_subtest("Verifier check of DEVMAP programs")) test_neg_xdp_devmap_helpers(); } diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c b/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c new file mode 100644 index 000000000000..a50971c6cf4a --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c @@ -0,0 +1,201 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <test_progs.h> +#include <network_helpers.h> +#include <net/if.h> +#include <linux/if_ether.h> +#include <linux/if_packet.h> +#include <linux/ipv6.h> +#include <linux/in6.h> +#include <linux/udp.h> +#include <bpf/bpf_endian.h> +#include "test_xdp_do_redirect.skel.h" + +#define SYS(fmt, ...) \ + ({ \ + char cmd[1024]; \ + snprintf(cmd, sizeof(cmd), fmt, ##__VA_ARGS__); \ + if (!ASSERT_OK(system(cmd), cmd)) \ + goto out; \ + }) + +struct udp_packet { + struct ethhdr eth; + struct ipv6hdr iph; + struct udphdr udp; + __u8 payload[64 - sizeof(struct udphdr) + - sizeof(struct ethhdr) - sizeof(struct ipv6hdr)]; +} __packed; + +static struct udp_packet pkt_udp = { + .eth.h_proto = __bpf_constant_htons(ETH_P_IPV6), + .eth.h_dest = {0x00, 0x11, 0x22, 0x33, 0x44, 0x55}, + .eth.h_source = {0x66, 0x77, 0x88, 0x99, 0xaa, 0xbb}, + .iph.version = 6, + .iph.nexthdr = IPPROTO_UDP, + .iph.payload_len = bpf_htons(sizeof(struct udp_packet) + - offsetof(struct udp_packet, udp)), + .iph.hop_limit = 2, + .iph.saddr.s6_addr16 = {bpf_htons(0xfc00), 0, 0, 0, 0, 0, 0, bpf_htons(1)}, + .iph.daddr.s6_addr16 = {bpf_htons(0xfc00), 0, 0, 0, 0, 0, 0, bpf_htons(2)}, + .udp.source = bpf_htons(1), + .udp.dest = bpf_htons(1), + .udp.len = bpf_htons(sizeof(struct udp_packet) + - offsetof(struct udp_packet, udp)), + .payload = {0x42}, /* receiver XDP program matches on this */ +}; + +static int attach_tc_prog(struct bpf_tc_hook *hook, int fd) +{ + DECLARE_LIBBPF_OPTS(bpf_tc_opts, opts, .handle = 1, .priority = 1, .prog_fd = fd); + int ret; + + ret = bpf_tc_hook_create(hook); + if (!ASSERT_OK(ret, "create tc hook")) + return ret; + + ret = bpf_tc_attach(hook, &opts); + if (!ASSERT_OK(ret, "bpf_tc_attach")) { + bpf_tc_hook_destroy(hook); + return ret; + } + + return 0; +} + +/* The maximum permissible size is: PAGE_SIZE - sizeof(struct xdp_page_head) - + * sizeof(struct skb_shared_info) - XDP_PACKET_HEADROOM = 3368 bytes + */ +#define MAX_PKT_SIZE 3368 +static void test_max_pkt_size(int fd) +{ + char data[MAX_PKT_SIZE + 1] = {}; + int err; + DECLARE_LIBBPF_OPTS(bpf_test_run_opts, opts, + .data_in = &data, + .data_size_in = MAX_PKT_SIZE, + .flags = BPF_F_TEST_XDP_LIVE_FRAMES, + .repeat = 1, + ); + err = bpf_prog_test_run_opts(fd, &opts); + ASSERT_OK(err, "prog_run_max_size"); + + opts.data_size_in += 1; + err = bpf_prog_test_run_opts(fd, &opts); + ASSERT_EQ(err, -EINVAL, "prog_run_too_big"); +} + +#define NUM_PKTS 10000 +void test_xdp_do_redirect(void) +{ + int err, xdp_prog_fd, tc_prog_fd, ifindex_src, ifindex_dst; + char data[sizeof(pkt_udp) + sizeof(__u32)]; + struct test_xdp_do_redirect *skel = NULL; + struct nstoken *nstoken = NULL; + struct bpf_link *link; + + struct xdp_md ctx_in = { .data = sizeof(__u32), + .data_end = sizeof(data) }; + DECLARE_LIBBPF_OPTS(bpf_test_run_opts, opts, + .data_in = &data, + .data_size_in = sizeof(data), + .ctx_in = &ctx_in, + .ctx_size_in = sizeof(ctx_in), + .flags = BPF_F_TEST_XDP_LIVE_FRAMES, + .repeat = NUM_PKTS, + .batch_size = 64, + ); + DECLARE_LIBBPF_OPTS(bpf_tc_hook, tc_hook, + .attach_point = BPF_TC_INGRESS); + + memcpy(&data[sizeof(__u32)], &pkt_udp, sizeof(pkt_udp)); + *((__u32 *)data) = 0x42; /* metadata test value */ + + skel = test_xdp_do_redirect__open(); + if (!ASSERT_OK_PTR(skel, "skel")) + return; + + /* The XDP program we run with bpf_prog_run() will cycle through all + * three xmit (PASS/TX/REDIRECT) return codes starting from above, and + * ending up with PASS, so we should end up with two packets on the dst + * iface and NUM_PKTS-2 in the TC hook. We match the packets on the UDP + * payload. + */ + SYS("ip netns add testns"); + nstoken = open_netns("testns"); + if (!ASSERT_OK_PTR(nstoken, "setns")) + goto out; + + SYS("ip link add veth_src type veth peer name veth_dst"); + SYS("ip link set dev veth_src address 00:11:22:33:44:55"); + SYS("ip link set dev veth_dst address 66:77:88:99:aa:bb"); + SYS("ip link set dev veth_src up"); + SYS("ip link set dev veth_dst up"); + SYS("ip addr add dev veth_src fc00::1/64"); + SYS("ip addr add dev veth_dst fc00::2/64"); + SYS("ip neigh add fc00::2 dev veth_src lladdr 66:77:88:99:aa:bb"); + + /* We enable forwarding in the test namespace because that will cause + * the packets that go through the kernel stack (with XDP_PASS) to be + * forwarded back out the same interface (because of the packet dst + * combined with the interface addresses). When this happens, the + * regular forwarding path will end up going through the same + * veth_xdp_xmit() call as the XDP_REDIRECT code, which can cause a + * deadlock if it happens on the same CPU. There's a local_bh_disable() + * in the test_run code to prevent this, but an earlier version of the + * code didn't have this, so we keep the test behaviour to make sure the + * bug doesn't resurface. + */ + SYS("sysctl -qw net.ipv6.conf.all.forwarding=1"); + + ifindex_src = if_nametoindex("veth_src"); + ifindex_dst = if_nametoindex("veth_dst"); + if (!ASSERT_NEQ(ifindex_src, 0, "ifindex_src") || + !ASSERT_NEQ(ifindex_dst, 0, "ifindex_dst")) + goto out; + + memcpy(skel->rodata->expect_dst, &pkt_udp.eth.h_dest, ETH_ALEN); + skel->rodata->ifindex_out = ifindex_src; /* redirect back to the same iface */ + skel->rodata->ifindex_in = ifindex_src; + ctx_in.ingress_ifindex = ifindex_src; + tc_hook.ifindex = ifindex_src; + + if (!ASSERT_OK(test_xdp_do_redirect__load(skel), "load")) + goto out; + + link = bpf_program__attach_xdp(skel->progs.xdp_count_pkts, ifindex_dst); + if (!ASSERT_OK_PTR(link, "prog_attach")) + goto out; + skel->links.xdp_count_pkts = link; + + tc_prog_fd = bpf_program__fd(skel->progs.tc_count_pkts); + if (attach_tc_prog(&tc_hook, tc_prog_fd)) + goto out; + + xdp_prog_fd = bpf_program__fd(skel->progs.xdp_redirect); + err = bpf_prog_test_run_opts(xdp_prog_fd, &opts); + if (!ASSERT_OK(err, "prog_run")) + goto out_tc; + + /* wait for the packets to be flushed */ + kern_sync_rcu(); + + /* There will be one packet sent through XDP_REDIRECT and one through + * XDP_TX; these will show up on the XDP counting program, while the + * rest will be counted at the TC ingress hook (and the counting program + * resets the packet payload so they don't get counted twice even though + * they are re-xmited out the veth device + */ + ASSERT_EQ(skel->bss->pkts_seen_xdp, 2, "pkt_count_xdp"); + ASSERT_EQ(skel->bss->pkts_seen_zero, 2, "pkt_count_zero"); + ASSERT_EQ(skel->bss->pkts_seen_tc, NUM_PKTS - 2, "pkt_count_tc"); + + test_max_pkt_size(bpf_program__fd(skel->progs.xdp_count_pkts)); + +out_tc: + bpf_tc_hook_destroy(&tc_hook); +out: + if (nstoken) + close_netns(nstoken); + system("ip netns del testns"); + test_xdp_do_redirect__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_info.c b/tools/testing/selftests/bpf/prog_tests/xdp_info.c index abe48e82e1dc..0d01ff6cb91a 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_info.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_info.c @@ -14,13 +14,13 @@ void serial_test_xdp_info(void) /* Get prog_id for XDP_ATTACHED_NONE mode */ - err = bpf_get_link_xdp_id(IFINDEX_LO, &prog_id, 0); + err = bpf_xdp_query_id(IFINDEX_LO, 0, &prog_id); if (CHECK(err, "get_xdp_none", "errno=%d\n", errno)) return; if (CHECK(prog_id, "prog_id_none", "unexpected prog_id=%u\n", prog_id)) return; - err = bpf_get_link_xdp_id(IFINDEX_LO, &prog_id, XDP_FLAGS_SKB_MODE); + err = bpf_xdp_query_id(IFINDEX_LO, XDP_FLAGS_SKB_MODE, &prog_id); if (CHECK(err, "get_xdp_none_skb", "errno=%d\n", errno)) return; if (CHECK(prog_id, "prog_id_none_skb", "unexpected prog_id=%u\n", @@ -37,32 +37,32 @@ void serial_test_xdp_info(void) if (CHECK(err, "get_prog_info", "errno=%d\n", errno)) goto out_close; - err = bpf_set_link_xdp_fd(IFINDEX_LO, prog_fd, XDP_FLAGS_SKB_MODE); + err = bpf_xdp_attach(IFINDEX_LO, prog_fd, XDP_FLAGS_SKB_MODE, NULL); if (CHECK(err, "set_xdp_skb", "errno=%d\n", errno)) goto out_close; /* Get prog_id for single prog mode */ - err = bpf_get_link_xdp_id(IFINDEX_LO, &prog_id, 0); + err = bpf_xdp_query_id(IFINDEX_LO, 0, &prog_id); if (CHECK(err, "get_xdp", "errno=%d\n", errno)) goto out; if (CHECK(prog_id != info.id, "prog_id", "prog_id not available\n")) goto out; - err = bpf_get_link_xdp_id(IFINDEX_LO, &prog_id, XDP_FLAGS_SKB_MODE); + err = bpf_xdp_query_id(IFINDEX_LO, XDP_FLAGS_SKB_MODE, &prog_id); if (CHECK(err, "get_xdp_skb", "errno=%d\n", errno)) goto out; if (CHECK(prog_id != info.id, "prog_id_skb", "prog_id not available\n")) goto out; - err = bpf_get_link_xdp_id(IFINDEX_LO, &prog_id, XDP_FLAGS_DRV_MODE); + err = bpf_xdp_query_id(IFINDEX_LO, XDP_FLAGS_DRV_MODE, &prog_id); if (CHECK(err, "get_xdp_drv", "errno=%d\n", errno)) goto out; if (CHECK(prog_id, "prog_id_drv", "unexpected prog_id=%u\n", prog_id)) goto out; out: - bpf_set_link_xdp_fd(IFINDEX_LO, -1, 0); + bpf_xdp_detach(IFINDEX_LO, 0, NULL); out_close: bpf_object__close(obj); } diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_link.c b/tools/testing/selftests/bpf/prog_tests/xdp_link.c index 983ab0b47d30..3e9d5c5521f0 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_link.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_link.c @@ -8,61 +8,62 @@ void serial_test_xdp_link(void) { - __u32 duration = 0, id1, id2, id0 = 0, prog_fd1, prog_fd2, err; - DECLARE_LIBBPF_OPTS(bpf_xdp_set_link_opts, opts, .old_fd = -1); struct test_xdp_link *skel1 = NULL, *skel2 = NULL; + __u32 id1, id2, id0 = 0, prog_fd1, prog_fd2; + LIBBPF_OPTS(bpf_xdp_attach_opts, opts); struct bpf_link_info link_info; struct bpf_prog_info prog_info; struct bpf_link *link; + int err; __u32 link_info_len = sizeof(link_info); __u32 prog_info_len = sizeof(prog_info); skel1 = test_xdp_link__open_and_load(); - if (CHECK(!skel1, "skel_load", "skeleton open and load failed\n")) + if (!ASSERT_OK_PTR(skel1, "skel_load")) goto cleanup; prog_fd1 = bpf_program__fd(skel1->progs.xdp_handler); skel2 = test_xdp_link__open_and_load(); - if (CHECK(!skel2, "skel_load", "skeleton open and load failed\n")) + if (!ASSERT_OK_PTR(skel2, "skel_load")) goto cleanup; prog_fd2 = bpf_program__fd(skel2->progs.xdp_handler); memset(&prog_info, 0, sizeof(prog_info)); err = bpf_obj_get_info_by_fd(prog_fd1, &prog_info, &prog_info_len); - if (CHECK(err, "fd_info1", "failed %d\n", -errno)) + if (!ASSERT_OK(err, "fd_info1")) goto cleanup; id1 = prog_info.id; memset(&prog_info, 0, sizeof(prog_info)); err = bpf_obj_get_info_by_fd(prog_fd2, &prog_info, &prog_info_len); - if (CHECK(err, "fd_info2", "failed %d\n", -errno)) + if (!ASSERT_OK(err, "fd_info2")) goto cleanup; id2 = prog_info.id; /* set initial prog attachment */ - err = bpf_set_link_xdp_fd_opts(IFINDEX_LO, prog_fd1, XDP_FLAGS_REPLACE, &opts); - if (CHECK(err, "fd_attach", "initial prog attach failed: %d\n", err)) + err = bpf_xdp_attach(IFINDEX_LO, prog_fd1, XDP_FLAGS_REPLACE, &opts); + if (!ASSERT_OK(err, "fd_attach")) goto cleanup; /* validate prog ID */ - err = bpf_get_link_xdp_id(IFINDEX_LO, &id0, 0); - CHECK(err || id0 != id1, "id1_check", - "loaded prog id %u != id1 %u, err %d", id0, id1, err); + err = bpf_xdp_query_id(IFINDEX_LO, 0, &id0); + if (!ASSERT_OK(err, "id1_check_err") || !ASSERT_EQ(id0, id1, "id1_check_val")) + goto cleanup; /* BPF link is not allowed to replace prog attachment */ link = bpf_program__attach_xdp(skel1->progs.xdp_handler, IFINDEX_LO); if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) { bpf_link__destroy(link); /* best-effort detach prog */ - opts.old_fd = prog_fd1; - bpf_set_link_xdp_fd_opts(IFINDEX_LO, -1, XDP_FLAGS_REPLACE, &opts); + opts.old_prog_fd = prog_fd1; + bpf_xdp_detach(IFINDEX_LO, XDP_FLAGS_REPLACE, &opts); goto cleanup; } /* detach BPF program */ - opts.old_fd = prog_fd1; - err = bpf_set_link_xdp_fd_opts(IFINDEX_LO, -1, XDP_FLAGS_REPLACE, &opts); - if (CHECK(err, "prog_detach", "failed %d\n", err)) + opts.old_prog_fd = prog_fd1; + err = bpf_xdp_detach(IFINDEX_LO, XDP_FLAGS_REPLACE, &opts); + if (!ASSERT_OK(err, "prog_detach")) goto cleanup; /* now BPF link should attach successfully */ @@ -72,25 +73,24 @@ void serial_test_xdp_link(void) skel1->links.xdp_handler = link; /* validate prog ID */ - err = bpf_get_link_xdp_id(IFINDEX_LO, &id0, 0); - if (CHECK(err || id0 != id1, "id1_check", - "loaded prog id %u != id1 %u, err %d", id0, id1, err)) + err = bpf_xdp_query_id(IFINDEX_LO, 0, &id0); + if (!ASSERT_OK(err, "id1_check_err") || !ASSERT_EQ(id0, id1, "id1_check_val")) goto cleanup; /* BPF prog attach is not allowed to replace BPF link */ - opts.old_fd = prog_fd1; - err = bpf_set_link_xdp_fd_opts(IFINDEX_LO, prog_fd2, XDP_FLAGS_REPLACE, &opts); - if (CHECK(!err, "prog_attach_fail", "unexpected success\n")) + opts.old_prog_fd = prog_fd1; + err = bpf_xdp_attach(IFINDEX_LO, prog_fd2, XDP_FLAGS_REPLACE, &opts); + if (!ASSERT_ERR(err, "prog_attach_fail")) goto cleanup; /* Can't force-update when BPF link is active */ - err = bpf_set_link_xdp_fd(IFINDEX_LO, prog_fd2, 0); - if (CHECK(!err, "prog_update_fail", "unexpected success\n")) + err = bpf_xdp_attach(IFINDEX_LO, prog_fd2, 0, NULL); + if (!ASSERT_ERR(err, "prog_update_fail")) goto cleanup; /* Can't force-detach when BPF link is active */ - err = bpf_set_link_xdp_fd(IFINDEX_LO, -1, 0); - if (CHECK(!err, "prog_detach_fail", "unexpected success\n")) + err = bpf_xdp_detach(IFINDEX_LO, 0, NULL); + if (!ASSERT_ERR(err, "prog_detach_fail")) goto cleanup; /* BPF link is not allowed to replace another BPF link */ @@ -109,41 +109,40 @@ void serial_test_xdp_link(void) goto cleanup; skel2->links.xdp_handler = link; - err = bpf_get_link_xdp_id(IFINDEX_LO, &id0, 0); - if (CHECK(err || id0 != id2, "id2_check", - "loaded prog id %u != id2 %u, err %d", id0, id1, err)) + err = bpf_xdp_query_id(IFINDEX_LO, 0, &id0); + if (!ASSERT_OK(err, "id2_check_err") || !ASSERT_EQ(id0, id2, "id2_check_val")) goto cleanup; /* updating program under active BPF link works as expected */ err = bpf_link__update_program(link, skel1->progs.xdp_handler); - if (CHECK(err, "link_upd", "failed: %d\n", err)) + if (!ASSERT_OK(err, "link_upd")) goto cleanup; memset(&link_info, 0, sizeof(link_info)); err = bpf_obj_get_info_by_fd(bpf_link__fd(link), &link_info, &link_info_len); - if (CHECK(err, "link_info", "failed: %d\n", err)) + if (!ASSERT_OK(err, "link_info")) goto cleanup; - CHECK(link_info.type != BPF_LINK_TYPE_XDP, "link_type", - "got %u != exp %u\n", link_info.type, BPF_LINK_TYPE_XDP); - CHECK(link_info.prog_id != id1, "link_prog_id", - "got %u != exp %u\n", link_info.prog_id, id1); - CHECK(link_info.xdp.ifindex != IFINDEX_LO, "link_ifindex", - "got %u != exp %u\n", link_info.xdp.ifindex, IFINDEX_LO); + ASSERT_EQ(link_info.type, BPF_LINK_TYPE_XDP, "link_type"); + ASSERT_EQ(link_info.prog_id, id1, "link_prog_id"); + ASSERT_EQ(link_info.xdp.ifindex, IFINDEX_LO, "link_ifindex"); + + /* updating program under active BPF link with different type fails */ + err = bpf_link__update_program(link, skel1->progs.tc_handler); + if (!ASSERT_ERR(err, "link_upd_invalid")) + goto cleanup; err = bpf_link__detach(link); - if (CHECK(err, "link_detach", "failed %d\n", err)) + if (!ASSERT_OK(err, "link_detach")) goto cleanup; memset(&link_info, 0, sizeof(link_info)); err = bpf_obj_get_info_by_fd(bpf_link__fd(link), &link_info, &link_info_len); - if (CHECK(err, "link_info", "failed: %d\n", err)) - goto cleanup; - CHECK(link_info.prog_id != id1, "link_prog_id", - "got %u != exp %u\n", link_info.prog_id, id1); + + ASSERT_OK(err, "link_info"); + ASSERT_EQ(link_info.prog_id, id1, "link_prog_id"); /* ifindex should be zeroed out */ - CHECK(link_info.xdp.ifindex != 0, "link_ifindex", - "got %u != exp %u\n", link_info.xdp.ifindex, 0); + ASSERT_EQ(link_info.xdp.ifindex, 0, "link_ifindex"); cleanup: test_xdp_link__destroy(skel1); diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_noinline.c b/tools/testing/selftests/bpf/prog_tests/xdp_noinline.c index 0281095de266..92ef0aa50866 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_noinline.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_noinline.c @@ -25,43 +25,49 @@ void test_xdp_noinline(void) __u8 flags; } real_def = {.dst = MAGIC_VAL}; __u32 ch_key = 11, real_num = 3; - __u32 duration = 0, retval, size; int err, i; __u64 bytes = 0, pkts = 0; char buf[128]; u32 *magic = (u32 *)buf; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .data_out = buf, + .data_size_out = sizeof(buf), + .repeat = NUM_ITER, + ); skel = test_xdp_noinline__open_and_load(); - if (CHECK(!skel, "skel_open_and_load", "failed\n")) + if (!ASSERT_OK_PTR(skel, "skel_open_and_load")) return; bpf_map_update_elem(bpf_map__fd(skel->maps.vip_map), &key, &value, 0); bpf_map_update_elem(bpf_map__fd(skel->maps.ch_rings), &ch_key, &real_num, 0); bpf_map_update_elem(bpf_map__fd(skel->maps.reals), &real_num, &real_def, 0); - err = bpf_prog_test_run(bpf_program__fd(skel->progs.balancer_ingress_v4), - NUM_ITER, &pkt_v4, sizeof(pkt_v4), - buf, &size, &retval, &duration); - CHECK(err || retval != 1 || size != 54 || - *magic != MAGIC_VAL, "ipv4", - "err %d errno %d retval %d size %d magic %x\n", - err, errno, retval, size, *magic); + err = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.balancer_ingress_v4), &topts); + ASSERT_OK(err, "ipv4 test_run"); + ASSERT_EQ(topts.retval, 1, "ipv4 test_run retval"); + ASSERT_EQ(topts.data_size_out, 54, "ipv4 test_run data_size_out"); + ASSERT_EQ(*magic, MAGIC_VAL, "ipv4 test_run magic"); - err = bpf_prog_test_run(bpf_program__fd(skel->progs.balancer_ingress_v6), - NUM_ITER, &pkt_v6, sizeof(pkt_v6), - buf, &size, &retval, &duration); - CHECK(err || retval != 1 || size != 74 || - *magic != MAGIC_VAL, "ipv6", - "err %d errno %d retval %d size %d magic %x\n", - err, errno, retval, size, *magic); + topts.data_in = &pkt_v6; + topts.data_size_in = sizeof(pkt_v6); + topts.data_out = buf; + topts.data_size_out = sizeof(buf); + + err = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.balancer_ingress_v6), &topts); + ASSERT_OK(err, "ipv6 test_run"); + ASSERT_EQ(topts.retval, 1, "ipv6 test_run retval"); + ASSERT_EQ(topts.data_size_out, 74, "ipv6 test_run data_size_out"); + ASSERT_EQ(*magic, MAGIC_VAL, "ipv6 test_run magic"); bpf_map_lookup_elem(bpf_map__fd(skel->maps.stats), &stats_key, stats); for (i = 0; i < nr_cpus; i++) { bytes += stats[i].bytes; pkts += stats[i].pkts; } - CHECK(bytes != MAGIC_BYTES * NUM_ITER * 2 || pkts != NUM_ITER * 2, - "stats", "bytes %lld pkts %lld\n", - (unsigned long long)bytes, (unsigned long long)pkts); + ASSERT_EQ(bytes, MAGIC_BYTES * NUM_ITER * 2, "stats bytes"); + ASSERT_EQ(pkts, NUM_ITER * 2, "stats pkts"); test_xdp_noinline__destroy(skel); } diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_perf.c b/tools/testing/selftests/bpf/prog_tests/xdp_perf.c index 15a3900e4370..f543d1bd21b8 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_perf.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_perf.c @@ -4,22 +4,25 @@ void test_xdp_perf(void) { const char *file = "./xdp_dummy.o"; - __u32 duration, retval, size; struct bpf_object *obj; char in[128], out[128]; int err, prog_fd; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = in, + .data_size_in = sizeof(in), + .data_out = out, + .data_size_out = sizeof(out), + .repeat = 1000000, + ); err = bpf_prog_test_load(file, BPF_PROG_TYPE_XDP, &obj, &prog_fd); if (CHECK_FAIL(err)) return; - err = bpf_prog_test_run(prog_fd, 1000000, &in[0], 128, - out, &size, &retval, &duration); - - CHECK(err || retval != XDP_PASS || size != 128, - "xdp-perf", - "err %d errno %d retval %d size %d\n", - err, errno, retval, size); + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "test_run"); + ASSERT_EQ(topts.retval, XDP_PASS, "test_run retval"); + ASSERT_EQ(topts.data_size_out, 128, "test_run data_size_out"); bpf_object__close(obj); } diff --git a/tools/testing/selftests/bpf/progs/atomics.c b/tools/testing/selftests/bpf/progs/atomics.c index 16e57313204a..f89c7f0cc53b 100644 --- a/tools/testing/selftests/bpf/progs/atomics.c +++ b/tools/testing/selftests/bpf/progs/atomics.c @@ -20,8 +20,8 @@ __u64 add_stack_value_copy = 0; __u64 add_stack_result = 0; __u64 add_noreturn_value = 1; -SEC("fentry/bpf_fentry_test1") -int BPF_PROG(add, int a) +SEC("raw_tp/sys_enter") +int add(const void *ctx) { if (pid != (bpf_get_current_pid_tgid() >> 32)) return 0; @@ -46,8 +46,8 @@ __s64 sub_stack_value_copy = 0; __s64 sub_stack_result = 0; __s64 sub_noreturn_value = 1; -SEC("fentry/bpf_fentry_test1") -int BPF_PROG(sub, int a) +SEC("raw_tp/sys_enter") +int sub(const void *ctx) { if (pid != (bpf_get_current_pid_tgid() >> 32)) return 0; @@ -70,8 +70,8 @@ __u32 and32_value = 0x110; __u32 and32_result = 0; __u64 and_noreturn_value = (0x110ull << 32); -SEC("fentry/bpf_fentry_test1") -int BPF_PROG(and, int a) +SEC("raw_tp/sys_enter") +int and(const void *ctx) { if (pid != (bpf_get_current_pid_tgid() >> 32)) return 0; @@ -91,8 +91,8 @@ __u32 or32_value = 0x110; __u32 or32_result = 0; __u64 or_noreturn_value = (0x110ull << 32); -SEC("fentry/bpf_fentry_test1") -int BPF_PROG(or, int a) +SEC("raw_tp/sys_enter") +int or(const void *ctx) { if (pid != (bpf_get_current_pid_tgid() >> 32)) return 0; @@ -111,8 +111,8 @@ __u32 xor32_value = 0x110; __u32 xor32_result = 0; __u64 xor_noreturn_value = (0x110ull << 32); -SEC("fentry/bpf_fentry_test1") -int BPF_PROG(xor, int a) +SEC("raw_tp/sys_enter") +int xor(const void *ctx) { if (pid != (bpf_get_current_pid_tgid() >> 32)) return 0; @@ -132,8 +132,8 @@ __u32 cmpxchg32_value = 1; __u32 cmpxchg32_result_fail = 0; __u32 cmpxchg32_result_succeed = 0; -SEC("fentry/bpf_fentry_test1") -int BPF_PROG(cmpxchg, int a) +SEC("raw_tp/sys_enter") +int cmpxchg(const void *ctx) { if (pid != (bpf_get_current_pid_tgid() >> 32)) return 0; @@ -153,8 +153,8 @@ __u64 xchg64_result = 0; __u32 xchg32_value = 1; __u32 xchg32_result = 0; -SEC("fentry/bpf_fentry_test1") -int BPF_PROG(xchg, int a) +SEC("raw_tp/sys_enter") +int xchg(const void *ctx) { if (pid != (bpf_get_current_pid_tgid() >> 32)) return 0; diff --git a/tools/testing/selftests/bpf/progs/bloom_filter_bench.c b/tools/testing/selftests/bpf/progs/bloom_filter_bench.c index d9a88dd1ea65..7efcbdbe772d 100644 --- a/tools/testing/selftests/bpf/progs/bloom_filter_bench.c +++ b/tools/testing/selftests/bpf/progs/bloom_filter_bench.c @@ -5,6 +5,7 @@ #include <linux/bpf.h> #include <stdbool.h> #include <bpf/bpf_helpers.h> +#include "bpf_misc.h" char _license[] SEC("license") = "GPL"; @@ -87,7 +88,7 @@ bloom_callback(struct bpf_map *map, __u32 *key, void *val, return 0; } -SEC("fentry/__x64_sys_getpgid") +SEC("fentry/" SYS_PREFIX "sys_getpgid") int bloom_lookup(void *ctx) { struct callback_ctx data; @@ -100,7 +101,7 @@ int bloom_lookup(void *ctx) return 0; } -SEC("fentry/__x64_sys_getpgid") +SEC("fentry/" SYS_PREFIX "sys_getpgid") int bloom_update(void *ctx) { struct callback_ctx data; @@ -113,7 +114,7 @@ int bloom_update(void *ctx) return 0; } -SEC("fentry/__x64_sys_getpgid") +SEC("fentry/" SYS_PREFIX "sys_getpgid") int bloom_hashmap_lookup(void *ctx) { __u64 *result; diff --git a/tools/testing/selftests/bpf/progs/bloom_filter_map.c b/tools/testing/selftests/bpf/progs/bloom_filter_map.c index 1316f3db79d9..f245fcfe0c61 100644 --- a/tools/testing/selftests/bpf/progs/bloom_filter_map.c +++ b/tools/testing/selftests/bpf/progs/bloom_filter_map.c @@ -3,6 +3,7 @@ #include <linux/bpf.h> #include <bpf/bpf_helpers.h> +#include "bpf_misc.h" char _license[] SEC("license") = "GPL"; @@ -51,7 +52,7 @@ check_elem(struct bpf_map *map, __u32 *key, __u32 *val, return 0; } -SEC("fentry/__x64_sys_getpgid") +SEC("fentry/" SYS_PREFIX "sys_getpgid") int inner_map(void *ctx) { struct bpf_map *inner_map; @@ -70,7 +71,7 @@ int inner_map(void *ctx) return 0; } -SEC("fentry/__x64_sys_getpgid") +SEC("fentry/" SYS_PREFIX "sys_getpgid") int check_bloom(void *ctx) { struct callback_ctx data; diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_setsockopt_unix.c b/tools/testing/selftests/bpf/progs/bpf_iter_setsockopt_unix.c new file mode 100644 index 000000000000..eafc877ea460 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_iter_setsockopt_unix.c @@ -0,0 +1,60 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright Amazon.com Inc. or its affiliates. */ +#include "bpf_iter.h" +#include "bpf_tracing_net.h" +#include <bpf/bpf_helpers.h> +#include <limits.h> + +#define AUTOBIND_LEN 6 +char sun_path[AUTOBIND_LEN]; + +#define NR_CASES 5 +int sndbuf_setsockopt[NR_CASES] = {-1, 0, 8192, INT_MAX / 2, INT_MAX}; +int sndbuf_getsockopt[NR_CASES] = {-1, -1, -1, -1, -1}; +int sndbuf_getsockopt_expected[NR_CASES]; + +static inline int cmpname(struct unix_sock *unix_sk) +{ + int i; + + for (i = 0; i < AUTOBIND_LEN; i++) { + if (unix_sk->addr->name->sun_path[i] != sun_path[i]) + return -1; + } + + return 0; +} + +SEC("iter/unix") +int change_sndbuf(struct bpf_iter__unix *ctx) +{ + struct unix_sock *unix_sk = ctx->unix_sk; + int i, err; + + if (!unix_sk || !unix_sk->addr) + return 0; + + if (unix_sk->addr->name->sun_path[0]) + return 0; + + if (cmpname(unix_sk)) + return 0; + + for (i = 0; i < NR_CASES; i++) { + err = bpf_setsockopt(unix_sk, SOL_SOCKET, SO_SNDBUF, + &sndbuf_setsockopt[i], + sizeof(sndbuf_setsockopt[i])); + if (err) + break; + + err = bpf_getsockopt(unix_sk, SOL_SOCKET, SO_SNDBUF, + &sndbuf_getsockopt[i], + sizeof(sndbuf_getsockopt[i])); + if (err) + break; + } + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_task.c b/tools/testing/selftests/bpf/progs/bpf_iter_task.c index c86b93f33b32..d22741272692 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_task.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_task.c @@ -2,6 +2,7 @@ /* Copyright (c) 2020 Facebook */ #include "bpf_iter.h" #include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> char _license[] SEC("license") = "GPL"; @@ -23,3 +24,56 @@ int dump_task(struct bpf_iter__task *ctx) BPF_SEQ_PRINTF(seq, "%8d %8d\n", task->tgid, task->pid); return 0; } + +int num_expected_failure_copy_from_user_task = 0; +int num_success_copy_from_user_task = 0; + +SEC("iter.s/task") +int dump_task_sleepable(struct bpf_iter__task *ctx) +{ + struct seq_file *seq = ctx->meta->seq; + struct task_struct *task = ctx->task; + static const char info[] = " === END ==="; + struct pt_regs *regs; + void *ptr; + uint32_t user_data = 0; + int ret; + + if (task == (void *)0) { + BPF_SEQ_PRINTF(seq, "%s\n", info); + return 0; + } + + /* Read an invalid pointer and ensure we get an error */ + ptr = NULL; + ret = bpf_copy_from_user_task(&user_data, sizeof(uint32_t), ptr, task, 0); + if (ret) { + ++num_expected_failure_copy_from_user_task; + } else { + BPF_SEQ_PRINTF(seq, "%s\n", info); + return 0; + } + + /* Try to read the contents of the task's instruction pointer from the + * remote task's address space. + */ + regs = (struct pt_regs *)bpf_task_pt_regs(task); + if (regs == (void *)0) { + BPF_SEQ_PRINTF(seq, "%s\n", info); + return 0; + } + ptr = (void *)PT_REGS_IP(regs); + + ret = bpf_copy_from_user_task(&user_data, sizeof(uint32_t), ptr, task, 0); + if (ret) { + BPF_SEQ_PRINTF(seq, "%s\n", info); + return 0; + } + ++num_success_copy_from_user_task; + + if (ctx->meta->seq_num == 0) + BPF_SEQ_PRINTF(seq, " tgid gid data\n"); + + BPF_SEQ_PRINTF(seq, "%8d %8d %8d\n", task->tgid, task->pid, user_data); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_unix.c b/tools/testing/selftests/bpf/progs/bpf_iter_unix.c index c21e3f545371..e6aefae38894 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_unix.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_unix.c @@ -63,7 +63,7 @@ int dump_unix(struct bpf_iter__unix *ctx) BPF_SEQ_PRINTF(seq, " @"); for (i = 1; i < len; i++) { - /* unix_mkname() tests this upper bound. */ + /* unix_validate_addr() tests this upper bound. */ if (i >= sizeof(struct sockaddr_un)) break; diff --git a/tools/testing/selftests/bpf/progs/bpf_loop.c b/tools/testing/selftests/bpf/progs/bpf_loop.c index 12349e4601e8..e08565282759 100644 --- a/tools/testing/selftests/bpf/progs/bpf_loop.c +++ b/tools/testing/selftests/bpf/progs/bpf_loop.c @@ -3,6 +3,7 @@ #include "vmlinux.h" #include <bpf/bpf_helpers.h> +#include "bpf_misc.h" char _license[] SEC("license") = "GPL"; @@ -53,7 +54,7 @@ static int nested_callback1(__u32 index, void *data) return 0; } -SEC("fentry/__x64_sys_nanosleep") +SEC("fentry/" SYS_PREFIX "sys_nanosleep") int test_prog(void *ctx) { struct callback_ctx data = {}; @@ -71,7 +72,7 @@ int test_prog(void *ctx) return 0; } -SEC("fentry/__x64_sys_nanosleep") +SEC("fentry/" SYS_PREFIX "sys_nanosleep") int prog_null_ctx(void *ctx) { if (bpf_get_current_pid_tgid() >> 32 != pid) @@ -82,7 +83,7 @@ int prog_null_ctx(void *ctx) return 0; } -SEC("fentry/__x64_sys_nanosleep") +SEC("fentry/" SYS_PREFIX "sys_nanosleep") int prog_invalid_flags(void *ctx) { struct callback_ctx data = {}; @@ -95,7 +96,7 @@ int prog_invalid_flags(void *ctx) return 0; } -SEC("fentry/__x64_sys_nanosleep") +SEC("fentry/" SYS_PREFIX "sys_nanosleep") int prog_nested_calls(void *ctx) { struct callback_ctx data = {}; diff --git a/tools/testing/selftests/bpf/progs/bpf_loop_bench.c b/tools/testing/selftests/bpf/progs/bpf_loop_bench.c index 9dafdc244462..4ce76eb064c4 100644 --- a/tools/testing/selftests/bpf/progs/bpf_loop_bench.c +++ b/tools/testing/selftests/bpf/progs/bpf_loop_bench.c @@ -3,6 +3,7 @@ #include "vmlinux.h" #include <bpf/bpf_helpers.h> +#include "bpf_misc.h" char _license[] SEC("license") = "GPL"; @@ -14,7 +15,7 @@ static int empty_callback(__u32 index, void *data) return 0; } -SEC("fentry/__x64_sys_getpgid") +SEC("fentry/" SYS_PREFIX "sys_getpgid") int benchmark(void *ctx) { for (int i = 0; i < 1000; i++) { diff --git a/tools/testing/selftests/bpf/progs/bpf_misc.h b/tools/testing/selftests/bpf/progs/bpf_misc.h new file mode 100644 index 000000000000..5bb11fe595a4 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_misc.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __BPF_MISC_H__ +#define __BPF_MISC_H__ + +#if defined(__TARGET_ARCH_x86) +#define SYSCALL_WRAPPER 1 +#define SYS_PREFIX "__x64_" +#elif defined(__TARGET_ARCH_s390) +#define SYSCALL_WRAPPER 1 +#define SYS_PREFIX "__s390x_" +#elif defined(__TARGET_ARCH_arm64) +#define SYSCALL_WRAPPER 1 +#define SYS_PREFIX "__arm64_" +#else +#define SYSCALL_WRAPPER 0 +#define SYS_PREFIX "__se_" +#endif + +#endif diff --git a/tools/testing/selftests/bpf/progs/bpf_mod_race.c b/tools/testing/selftests/bpf/progs/bpf_mod_race.c new file mode 100644 index 000000000000..82a5c6c6ba83 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_mod_race.c @@ -0,0 +1,100 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <vmlinux.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +const volatile struct { + /* thread to activate trace programs for */ + pid_t tgid; + /* return error from __init function */ + int inject_error; + /* uffd monitored range start address */ + void *fault_addr; +} bpf_mod_race_config = { -1 }; + +int bpf_blocking = 0; +int res_try_get_module = -1; + +static __always_inline bool check_thread_id(void) +{ + struct task_struct *task = bpf_get_current_task_btf(); + + return task->tgid == bpf_mod_race_config.tgid; +} + +/* The trace of execution is something like this: + * + * finit_module() + * load_module() + * prepare_coming_module() + * notifier_call(MODULE_STATE_COMING) + * btf_parse_module() + * btf_alloc_id() // Visible to userspace at this point + * list_add(btf_mod->list, &btf_modules) + * do_init_module() + * freeinit = kmalloc() + * ret = mod->init() + * bpf_prog_widen_race() + * bpf_copy_from_user() + * ...<sleep>... + * if (ret < 0) + * ... + * free_module() + * return ret + * + * At this point, module loading thread is blocked, we now load the program: + * + * bpf_check + * add_kfunc_call/check_pseudo_btf_id + * btf_try_get_module + * try_get_module_live == false + * return -ENXIO + * + * Without the fix (try_get_module_live in btf_try_get_module): + * + * bpf_check + * add_kfunc_call/check_pseudo_btf_id + * btf_try_get_module + * try_get_module == true + * <store module reference in btf_kfunc_tab or used_btf array> + * ... + * return fd + * + * Now, if we inject an error in the blocked program, our module will be freed + * (going straight from MODULE_STATE_COMING to MODULE_STATE_GOING). + * Later, when bpf program is freed, it will try to module_put already freed + * module. This is why try_get_module_live returns false if mod->state is not + * MODULE_STATE_LIVE. + */ + +SEC("fmod_ret.s/bpf_fentry_test1") +int BPF_PROG(widen_race, int a, int ret) +{ + char dst; + + if (!check_thread_id()) + return 0; + /* Indicate that we will attempt to block */ + bpf_blocking = 1; + bpf_copy_from_user(&dst, 1, bpf_mod_race_config.fault_addr); + return bpf_mod_race_config.inject_error; +} + +SEC("fexit/do_init_module") +int BPF_PROG(fexit_init_module, struct module *mod, int ret) +{ + if (!check_thread_id()) + return 0; + /* Indicate that we finished blocking */ + bpf_blocking = 2; + return 0; +} + +SEC("fexit/btf_try_get_module") +int BPF_PROG(fexit_module_get, const struct btf *btf, struct module *mod) +{ + res_try_get_module = !!mod; + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/bpf_syscall_macro.c b/tools/testing/selftests/bpf/progs/bpf_syscall_macro.c new file mode 100644 index 000000000000..05838ed9b89c --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_syscall_macro.c @@ -0,0 +1,84 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright 2022 Sony Group Corporation */ +#include <vmlinux.h> + +#include <bpf/bpf_core_read.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include "bpf_misc.h" + +int arg1 = 0; +unsigned long arg2 = 0; +unsigned long arg3 = 0; +unsigned long arg4_cx = 0; +unsigned long arg4 = 0; +unsigned long arg5 = 0; + +int arg1_core = 0; +unsigned long arg2_core = 0; +unsigned long arg3_core = 0; +unsigned long arg4_core_cx = 0; +unsigned long arg4_core = 0; +unsigned long arg5_core = 0; + +int option_syscall = 0; +unsigned long arg2_syscall = 0; +unsigned long arg3_syscall = 0; +unsigned long arg4_syscall = 0; +unsigned long arg5_syscall = 0; + +const volatile pid_t filter_pid = 0; + +SEC("kprobe/" SYS_PREFIX "sys_prctl") +int BPF_KPROBE(handle_sys_prctl) +{ + struct pt_regs *real_regs; + pid_t pid = bpf_get_current_pid_tgid() >> 32; + unsigned long tmp = 0; + + if (pid != filter_pid) + return 0; + + real_regs = PT_REGS_SYSCALL_REGS(ctx); + + /* test for PT_REGS_PARM */ + +#if !defined(bpf_target_arm64) && !defined(bpf_target_s390) + bpf_probe_read_kernel(&tmp, sizeof(tmp), &PT_REGS_PARM1_SYSCALL(real_regs)); +#endif + arg1 = tmp; + bpf_probe_read_kernel(&arg2, sizeof(arg2), &PT_REGS_PARM2_SYSCALL(real_regs)); + bpf_probe_read_kernel(&arg3, sizeof(arg3), &PT_REGS_PARM3_SYSCALL(real_regs)); + bpf_probe_read_kernel(&arg4_cx, sizeof(arg4_cx), &PT_REGS_PARM4(real_regs)); + bpf_probe_read_kernel(&arg4, sizeof(arg4), &PT_REGS_PARM4_SYSCALL(real_regs)); + bpf_probe_read_kernel(&arg5, sizeof(arg5), &PT_REGS_PARM5_SYSCALL(real_regs)); + + /* test for the CORE variant of PT_REGS_PARM */ + arg1_core = PT_REGS_PARM1_CORE_SYSCALL(real_regs); + arg2_core = PT_REGS_PARM2_CORE_SYSCALL(real_regs); + arg3_core = PT_REGS_PARM3_CORE_SYSCALL(real_regs); + arg4_core_cx = PT_REGS_PARM4_CORE(real_regs); + arg4_core = PT_REGS_PARM4_CORE_SYSCALL(real_regs); + arg5_core = PT_REGS_PARM5_CORE_SYSCALL(real_regs); + + return 0; +} + +SEC("kprobe/" SYS_PREFIX "sys_prctl") +int BPF_KPROBE_SYSCALL(prctl_enter, int option, unsigned long arg2, + unsigned long arg3, unsigned long arg4, unsigned long arg5) +{ + pid_t pid = bpf_get_current_pid_tgid() >> 32; + + if (pid != filter_pid) + return 0; + + option_syscall = option; + arg2_syscall = arg2; + arg3_syscall = arg3; + arg4_syscall = arg4; + arg5_syscall = arg5; + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/bpf_tracing_net.h b/tools/testing/selftests/bpf/progs/bpf_tracing_net.h index e0f42601be9b..1c1289ba5fc5 100644 --- a/tools/testing/selftests/bpf/progs/bpf_tracing_net.h +++ b/tools/testing/selftests/bpf/progs/bpf_tracing_net.h @@ -5,6 +5,8 @@ #define AF_INET 2 #define AF_INET6 10 +#define SOL_SOCKET 1 +#define SO_SNDBUF 7 #define __SO_ACCEPTCON (1 << 16) #define SOL_TCP 6 diff --git a/tools/testing/selftests/bpf/progs/btf_type_tag_percpu.c b/tools/testing/selftests/bpf/progs/btf_type_tag_percpu.c new file mode 100644 index 000000000000..8feddb8289cf --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf_type_tag_percpu.c @@ -0,0 +1,66 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2022 Google */ +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +struct bpf_testmod_btf_type_tag_1 { + int a; +}; + +struct bpf_testmod_btf_type_tag_2 { + struct bpf_testmod_btf_type_tag_1 *p; +}; + +__u64 g; + +SEC("fentry/bpf_testmod_test_btf_type_tag_percpu_1") +int BPF_PROG(test_percpu1, struct bpf_testmod_btf_type_tag_1 *arg) +{ + g = arg->a; + return 0; +} + +SEC("fentry/bpf_testmod_test_btf_type_tag_percpu_2") +int BPF_PROG(test_percpu2, struct bpf_testmod_btf_type_tag_2 *arg) +{ + g = arg->p->a; + return 0; +} + +/* trace_cgroup_mkdir(struct cgroup *cgrp, const char *path) + * + * struct cgroup_rstat_cpu { + * ... + * struct cgroup *updated_children; + * ... + * }; + * + * struct cgroup { + * ... + * struct cgroup_rstat_cpu __percpu *rstat_cpu; + * ... + * }; + */ +SEC("tp_btf/cgroup_mkdir") +int BPF_PROG(test_percpu_load, struct cgroup *cgrp, const char *path) +{ + g = (__u64)cgrp->rstat_cpu->updated_children; + return 0; +} + +SEC("tp_btf/cgroup_mkdir") +int BPF_PROG(test_percpu_helper, struct cgroup *cgrp, const char *path) +{ + struct cgroup_rstat_cpu *rstat; + __u32 cpu; + + cpu = bpf_get_smp_processor_id(); + rstat = (struct cgroup_rstat_cpu *)bpf_per_cpu_ptr(cgrp->rstat_cpu, cpu); + if (rstat) { + /* READ_ONCE */ + *(volatile int *)rstat; + } + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/btf_type_tag_user.c b/tools/testing/selftests/bpf/progs/btf_type_tag_user.c new file mode 100644 index 000000000000..5523f77c5a44 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf_type_tag_user.c @@ -0,0 +1,40 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2022 Facebook */ +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +struct bpf_testmod_btf_type_tag_1 { + int a; +}; + +struct bpf_testmod_btf_type_tag_2 { + struct bpf_testmod_btf_type_tag_1 *p; +}; + +int g; + +SEC("fentry/bpf_testmod_test_btf_type_tag_user_1") +int BPF_PROG(test_user1, struct bpf_testmod_btf_type_tag_1 *arg) +{ + g = arg->a; + return 0; +} + +SEC("fentry/bpf_testmod_test_btf_type_tag_user_2") +int BPF_PROG(test_user2, struct bpf_testmod_btf_type_tag_2 *arg) +{ + g = arg->p->a; + return 0; +} + +/* int __sys_getsockname(int fd, struct sockaddr __user *usockaddr, + * int __user *usockaddr_len); + */ +SEC("fentry/__sys_getsockname") +int BPF_PROG(test_sys_getsockname, int fd, struct sockaddr *usockaddr, + int *usockaddr_len) +{ + g = usockaddr->sa_family; + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/cgroup_getset_retval_getsockopt.c b/tools/testing/selftests/bpf/progs/cgroup_getset_retval_getsockopt.c new file mode 100644 index 000000000000..b2a409e6382a --- /dev/null +++ b/tools/testing/selftests/bpf/progs/cgroup_getset_retval_getsockopt.c @@ -0,0 +1,45 @@ +// SPDX-License-Identifier: GPL-2.0-only + +/* + * Copyright 2021 Google LLC. + */ + +#include <errno.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +__u32 invocations = 0; +__u32 assertion_error = 0; +__u32 retval_value = 0; +__u32 ctx_retval_value = 0; + +SEC("cgroup/getsockopt") +int get_retval(struct bpf_sockopt *ctx) +{ + retval_value = bpf_get_retval(); + ctx_retval_value = ctx->retval; + __sync_fetch_and_add(&invocations, 1); + + return 1; +} + +SEC("cgroup/getsockopt") +int set_eisconn(struct bpf_sockopt *ctx) +{ + __sync_fetch_and_add(&invocations, 1); + + if (bpf_set_retval(-EISCONN)) + assertion_error = 1; + + return 1; +} + +SEC("cgroup/getsockopt") +int clear_retval(struct bpf_sockopt *ctx) +{ + __sync_fetch_and_add(&invocations, 1); + + ctx->retval = 0; + + return 1; +} diff --git a/tools/testing/selftests/bpf/progs/cgroup_getset_retval_setsockopt.c b/tools/testing/selftests/bpf/progs/cgroup_getset_retval_setsockopt.c new file mode 100644 index 000000000000..d6e5903e06ba --- /dev/null +++ b/tools/testing/selftests/bpf/progs/cgroup_getset_retval_setsockopt.c @@ -0,0 +1,52 @@ +// SPDX-License-Identifier: GPL-2.0-only + +/* + * Copyright 2021 Google LLC. + */ + +#include <errno.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +__u32 invocations = 0; +__u32 assertion_error = 0; +__u32 retval_value = 0; + +SEC("cgroup/setsockopt") +int get_retval(struct bpf_sockopt *ctx) +{ + retval_value = bpf_get_retval(); + __sync_fetch_and_add(&invocations, 1); + + return 1; +} + +SEC("cgroup/setsockopt") +int set_eunatch(struct bpf_sockopt *ctx) +{ + __sync_fetch_and_add(&invocations, 1); + + if (bpf_set_retval(-EUNATCH)) + assertion_error = 1; + + return 0; +} + +SEC("cgroup/setsockopt") +int set_eisconn(struct bpf_sockopt *ctx) +{ + __sync_fetch_and_add(&invocations, 1); + + if (bpf_set_retval(-EISCONN)) + assertion_error = 1; + + return 0; +} + +SEC("cgroup/setsockopt") +int legacy_eperm(struct bpf_sockopt *ctx) +{ + __sync_fetch_and_add(&invocations, 1); + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/core_kern.c b/tools/testing/selftests/bpf/progs/core_kern.c index 13499cc15c7d..2715fe27d4cf 100644 --- a/tools/testing/selftests/bpf/progs/core_kern.c +++ b/tools/testing/selftests/bpf/progs/core_kern.c @@ -101,4 +101,20 @@ int balancer_ingress(struct __sk_buff *ctx) return 0; } +typedef int (*func_proto_typedef___match)(long); +typedef int (*func_proto_typedef___doesnt_match)(char *); +typedef int (*func_proto_typedef_nested1)(func_proto_typedef___match); + +int proto_out[3]; + +SEC("raw_tracepoint/sys_enter") +int core_relo_proto(void *ctx) +{ + proto_out[0] = bpf_core_type_exists(func_proto_typedef___match); + proto_out[1] = bpf_core_type_exists(func_proto_typedef___doesnt_match); + proto_out[2] = bpf_core_type_exists(func_proto_typedef_nested1); + + return 0; +} + char LICENSE[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/core_kern_overflow.c b/tools/testing/selftests/bpf/progs/core_kern_overflow.c new file mode 100644 index 000000000000..f0d5652256ba --- /dev/null +++ b/tools/testing/selftests/bpf/progs/core_kern_overflow.c @@ -0,0 +1,22 @@ +// SPDX-License-Identifier: GPL-2.0 +#include "vmlinux.h" + +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_core_read.h> + +typedef int (*func_proto_typedef)(long); +typedef int (*func_proto_typedef_nested1)(func_proto_typedef); +typedef int (*func_proto_typedef_nested2)(func_proto_typedef_nested1); + +int proto_out; + +SEC("raw_tracepoint/sys_enter") +int core_relo_proto(void *ctx) +{ + proto_out = bpf_core_type_exists(func_proto_typedef_nested2); + + return 0; +} + +char LICENSE[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/fexit_sleep.c b/tools/testing/selftests/bpf/progs/fexit_sleep.c index bca92c9bd29a..106dc75efcc4 100644 --- a/tools/testing/selftests/bpf/progs/fexit_sleep.c +++ b/tools/testing/selftests/bpf/progs/fexit_sleep.c @@ -3,6 +3,7 @@ #include "vmlinux.h" #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> +#include "bpf_misc.h" char LICENSE[] SEC("license") = "GPL"; @@ -10,8 +11,8 @@ int pid = 0; int fentry_cnt = 0; int fexit_cnt = 0; -SEC("fentry/__x64_sys_nanosleep") -int BPF_PROG(nanosleep_fentry, const struct pt_regs *regs) +SEC("fentry/" SYS_PREFIX "sys_nanosleep") +int nanosleep_fentry(void *ctx) { if (bpf_get_current_pid_tgid() >> 32 != pid) return 0; @@ -20,8 +21,8 @@ int BPF_PROG(nanosleep_fentry, const struct pt_regs *regs) return 0; } -SEC("fexit/__x64_sys_nanosleep") -int BPF_PROG(nanosleep_fexit, const struct pt_regs *regs, int ret) +SEC("fexit/" SYS_PREFIX "sys_nanosleep") +int nanosleep_fexit(void *ctx) { if (bpf_get_current_pid_tgid() >> 32 != pid) return 0; diff --git a/tools/testing/selftests/bpf/progs/freplace_cls_redirect.c b/tools/testing/selftests/bpf/progs/freplace_cls_redirect.c index 68a5a9db928a..7e94412d47a5 100644 --- a/tools/testing/selftests/bpf/progs/freplace_cls_redirect.c +++ b/tools/testing/selftests/bpf/progs/freplace_cls_redirect.c @@ -7,12 +7,12 @@ #include <bpf/bpf_endian.h> #include <bpf/bpf_helpers.h> -struct bpf_map_def SEC("maps") sock_map = { - .type = BPF_MAP_TYPE_SOCKMAP, - .key_size = sizeof(int), - .value_size = sizeof(int), - .max_entries = 2, -}; +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __type(key, int); + __type(value, int); + __uint(max_entries, 2); +} sock_map SEC(".maps"); SEC("freplace/cls_redirect") int freplace_cls_redirect_test(struct __sk_buff *skb) diff --git a/tools/testing/selftests/bpf/progs/ima.c b/tools/testing/selftests/bpf/progs/ima.c index 96060ff4ffc6..e16a2c208481 100644 --- a/tools/testing/selftests/bpf/progs/ima.c +++ b/tools/testing/selftests/bpf/progs/ima.c @@ -18,8 +18,12 @@ struct { char _license[] SEC("license") = "GPL"; -SEC("lsm.s/bprm_committed_creds") -void BPF_PROG(ima, struct linux_binprm *bprm) +bool use_ima_file_hash; +bool enable_bprm_creds_for_exec; +bool enable_kernel_read_file; +bool test_deny; + +static void ima_test_common(struct file *file) { u64 ima_hash = 0; u64 *sample; @@ -28,8 +32,12 @@ void BPF_PROG(ima, struct linux_binprm *bprm) pid = bpf_get_current_pid_tgid() >> 32; if (pid == monitored_pid) { - ret = bpf_ima_inode_hash(bprm->file->f_inode, &ima_hash, - sizeof(ima_hash)); + if (!use_ima_file_hash) + ret = bpf_ima_inode_hash(file->f_inode, &ima_hash, + sizeof(ima_hash)); + else + ret = bpf_ima_file_hash(file, &ima_hash, + sizeof(ima_hash)); if (ret < 0 || ima_hash == 0) return; @@ -43,3 +51,53 @@ void BPF_PROG(ima, struct linux_binprm *bprm) return; } + +static int ima_test_deny(void) +{ + u32 pid; + + pid = bpf_get_current_pid_tgid() >> 32; + if (pid == monitored_pid && test_deny) + return -EPERM; + + return 0; +} + +SEC("lsm.s/bprm_committed_creds") +void BPF_PROG(bprm_committed_creds, struct linux_binprm *bprm) +{ + ima_test_common(bprm->file); +} + +SEC("lsm.s/bprm_creds_for_exec") +int BPF_PROG(bprm_creds_for_exec, struct linux_binprm *bprm) +{ + if (!enable_bprm_creds_for_exec) + return 0; + + ima_test_common(bprm->file); + return 0; +} + +SEC("lsm.s/kernel_read_file") +int BPF_PROG(kernel_read_file, struct file *file, enum kernel_read_file_id id, + bool contents) +{ + int ret; + + if (!enable_kernel_read_file) + return 0; + + if (!contents) + return 0; + + if (id != READING_POLICY) + return 0; + + ret = ima_test_deny(); + if (ret < 0) + return ret; + + ima_test_common(file); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/kfunc_call_race.c b/tools/testing/selftests/bpf/progs/kfunc_call_race.c new file mode 100644 index 000000000000..4e8fed75a4e0 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/kfunc_call_race.c @@ -0,0 +1,14 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <vmlinux.h> +#include <bpf/bpf_helpers.h> + +extern void bpf_testmod_test_mod_kfunc(int i) __ksym; + +SEC("tc") +int kfunc_call_fail(struct __sk_buff *ctx) +{ + bpf_testmod_test_mod_kfunc(0); + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/kfunc_call_test.c b/tools/testing/selftests/bpf/progs/kfunc_call_test.c index 8a8cf59017aa..5aecbb9fdc68 100644 --- a/tools/testing/selftests/bpf/progs/kfunc_call_test.c +++ b/tools/testing/selftests/bpf/progs/kfunc_call_test.c @@ -1,13 +1,20 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2021 Facebook */ -#include <linux/bpf.h> +#include <vmlinux.h> #include <bpf/bpf_helpers.h> -#include "bpf_tcp_helpers.h" extern int bpf_kfunc_call_test2(struct sock *sk, __u32 a, __u32 b) __ksym; extern __u64 bpf_kfunc_call_test1(struct sock *sk, __u32 a, __u64 b, __u32 c, __u64 d) __ksym; +extern struct prog_test_ref_kfunc *bpf_kfunc_call_test_acquire(unsigned long *sp) __ksym; +extern void bpf_kfunc_call_test_release(struct prog_test_ref_kfunc *p) __ksym; +extern void bpf_kfunc_call_test_pass_ctx(struct __sk_buff *skb) __ksym; +extern void bpf_kfunc_call_test_pass1(struct prog_test_pass1 *p) __ksym; +extern void bpf_kfunc_call_test_pass2(struct prog_test_pass2 *p) __ksym; +extern void bpf_kfunc_call_test_mem_len_pass1(void *mem, int len) __ksym; +extern void bpf_kfunc_call_test_mem_len_fail2(__u64 *mem, int len) __ksym; + SEC("tc") int kfunc_call_test2(struct __sk_buff *skb) { @@ -44,4 +51,45 @@ int kfunc_call_test1(struct __sk_buff *skb) return ret; } +SEC("tc") +int kfunc_call_test_ref_btf_id(struct __sk_buff *skb) +{ + struct prog_test_ref_kfunc *pt; + unsigned long s = 0; + int ret = 0; + + pt = bpf_kfunc_call_test_acquire(&s); + if (pt) { + if (pt->a != 42 || pt->b != 108) + ret = -1; + bpf_kfunc_call_test_release(pt); + } + return ret; +} + +SEC("tc") +int kfunc_call_test_pass(struct __sk_buff *skb) +{ + struct prog_test_pass1 p1 = {}; + struct prog_test_pass2 p2 = {}; + short a = 0; + __u64 b = 0; + long c = 0; + char d = 0; + int e = 0; + + bpf_kfunc_call_test_pass_ctx(skb); + bpf_kfunc_call_test_pass1(&p1); + bpf_kfunc_call_test_pass2(&p2); + + bpf_kfunc_call_test_mem_len_pass1(&a, sizeof(a)); + bpf_kfunc_call_test_mem_len_pass1(&b, sizeof(b)); + bpf_kfunc_call_test_mem_len_pass1(&c, sizeof(c)); + bpf_kfunc_call_test_mem_len_pass1(&d, sizeof(d)); + bpf_kfunc_call_test_mem_len_pass1(&e, sizeof(e)); + bpf_kfunc_call_test_mem_len_fail2(&b, -1); + + return 0; +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/kprobe_multi.c b/tools/testing/selftests/bpf/progs/kprobe_multi.c new file mode 100644 index 000000000000..600be50800f8 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/kprobe_multi.c @@ -0,0 +1,100 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include <stdbool.h> + +char _license[] SEC("license") = "GPL"; + +extern const void bpf_fentry_test1 __ksym; +extern const void bpf_fentry_test2 __ksym; +extern const void bpf_fentry_test3 __ksym; +extern const void bpf_fentry_test4 __ksym; +extern const void bpf_fentry_test5 __ksym; +extern const void bpf_fentry_test6 __ksym; +extern const void bpf_fentry_test7 __ksym; +extern const void bpf_fentry_test8 __ksym; + +int pid = 0; +bool test_cookie = false; + +__u64 kprobe_test1_result = 0; +__u64 kprobe_test2_result = 0; +__u64 kprobe_test3_result = 0; +__u64 kprobe_test4_result = 0; +__u64 kprobe_test5_result = 0; +__u64 kprobe_test6_result = 0; +__u64 kprobe_test7_result = 0; +__u64 kprobe_test8_result = 0; + +__u64 kretprobe_test1_result = 0; +__u64 kretprobe_test2_result = 0; +__u64 kretprobe_test3_result = 0; +__u64 kretprobe_test4_result = 0; +__u64 kretprobe_test5_result = 0; +__u64 kretprobe_test6_result = 0; +__u64 kretprobe_test7_result = 0; +__u64 kretprobe_test8_result = 0; + +extern bool CONFIG_X86_KERNEL_IBT __kconfig __weak; + +static void kprobe_multi_check(void *ctx, bool is_return) +{ + if (bpf_get_current_pid_tgid() >> 32 != pid) + return; + + __u64 cookie = test_cookie ? bpf_get_attach_cookie(ctx) : 0; + __u64 addr = bpf_get_func_ip(ctx) - (CONFIG_X86_KERNEL_IBT ? 4 : 0); + +#define SET(__var, __addr, __cookie) ({ \ + if (((const void *) addr == __addr) && \ + (!test_cookie || (cookie == __cookie))) \ + __var = 1; \ +}) + + if (is_return) { + SET(kretprobe_test1_result, &bpf_fentry_test1, 8); + SET(kretprobe_test2_result, &bpf_fentry_test2, 7); + SET(kretprobe_test3_result, &bpf_fentry_test3, 6); + SET(kretprobe_test4_result, &bpf_fentry_test4, 5); + SET(kretprobe_test5_result, &bpf_fentry_test5, 4); + SET(kretprobe_test6_result, &bpf_fentry_test6, 3); + SET(kretprobe_test7_result, &bpf_fentry_test7, 2); + SET(kretprobe_test8_result, &bpf_fentry_test8, 1); + } else { + SET(kprobe_test1_result, &bpf_fentry_test1, 1); + SET(kprobe_test2_result, &bpf_fentry_test2, 2); + SET(kprobe_test3_result, &bpf_fentry_test3, 3); + SET(kprobe_test4_result, &bpf_fentry_test4, 4); + SET(kprobe_test5_result, &bpf_fentry_test5, 5); + SET(kprobe_test6_result, &bpf_fentry_test6, 6); + SET(kprobe_test7_result, &bpf_fentry_test7, 7); + SET(kprobe_test8_result, &bpf_fentry_test8, 8); + } + +#undef SET +} + +/* + * No tests in here, just to trigger 'bpf_fentry_test*' + * through tracing test_run + */ +SEC("fentry/bpf_modify_return_test") +int BPF_PROG(trigger) +{ + return 0; +} + +SEC("kprobe.multi/bpf_fentry_tes??") +int test_kprobe(struct pt_regs *ctx) +{ + kprobe_multi_check(ctx, false); + return 0; +} + +SEC("kretprobe.multi/bpf_fentry_test*") +int test_kretprobe(struct pt_regs *ctx) +{ + kprobe_multi_check(ctx, true); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/ksym_race.c b/tools/testing/selftests/bpf/progs/ksym_race.c new file mode 100644 index 000000000000..def97f2fed90 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/ksym_race.c @@ -0,0 +1,13 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <vmlinux.h> +#include <bpf/bpf_helpers.h> + +extern int bpf_testmod_ksym_percpu __ksym; + +SEC("tc") +int ksym_fail(struct __sk_buff *ctx) +{ + return *(int *)bpf_this_cpu_ptr(&bpf_testmod_ksym_percpu); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/local_storage.c b/tools/testing/selftests/bpf/progs/local_storage.c index 9b1f9b75d5c2..19423ed862e3 100644 --- a/tools/testing/selftests/bpf/progs/local_storage.c +++ b/tools/testing/selftests/bpf/progs/local_storage.c @@ -37,6 +37,13 @@ struct { } sk_storage_map SEC(".maps"); struct { + __uint(type, BPF_MAP_TYPE_SK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC | BPF_F_CLONE); + __type(key, int); + __type(value, struct local_storage); +} sk_storage_map2 SEC(".maps"); + +struct { __uint(type, BPF_MAP_TYPE_TASK_STORAGE); __uint(map_flags, BPF_F_NO_PREALLOC); __type(key, int); @@ -115,7 +122,19 @@ int BPF_PROG(socket_bind, struct socket *sock, struct sockaddr *address, if (storage->value != DUMMY_STORAGE_VALUE) sk_storage_result = -1; + /* This tests that we can associate multiple elements + * with the local storage. + */ + storage = bpf_sk_storage_get(&sk_storage_map2, sock->sk, 0, + BPF_LOCAL_STORAGE_GET_F_CREATE); + if (!storage) + return 0; + err = bpf_sk_storage_delete(&sk_storage_map, sock->sk); + if (err) + return 0; + + err = bpf_sk_storage_delete(&sk_storage_map2, sock->sk); if (!err) sk_storage_result = err; diff --git a/tools/testing/selftests/bpf/progs/perfbuf_bench.c b/tools/testing/selftests/bpf/progs/perfbuf_bench.c index e5ab4836a641..45204fe0c570 100644 --- a/tools/testing/selftests/bpf/progs/perfbuf_bench.c +++ b/tools/testing/selftests/bpf/progs/perfbuf_bench.c @@ -4,6 +4,7 @@ #include <linux/bpf.h> #include <stdint.h> #include <bpf/bpf_helpers.h> +#include "bpf_misc.h" char _license[] SEC("license") = "GPL"; @@ -18,7 +19,7 @@ const volatile int batch_cnt = 0; long sample_val = 42; long dropped __attribute__((aligned(128))) = 0; -SEC("fentry/__x64_sys_getpgid") +SEC("fentry/" SYS_PREFIX "sys_getpgid") int bench_perfbuf(void *ctx) { __u64 *sample; diff --git a/tools/testing/selftests/bpf/progs/ringbuf_bench.c b/tools/testing/selftests/bpf/progs/ringbuf_bench.c index 123607d314d6..6a468496f539 100644 --- a/tools/testing/selftests/bpf/progs/ringbuf_bench.c +++ b/tools/testing/selftests/bpf/progs/ringbuf_bench.c @@ -4,6 +4,7 @@ #include <linux/bpf.h> #include <stdint.h> #include <bpf/bpf_helpers.h> +#include "bpf_misc.h" char _license[] SEC("license") = "GPL"; @@ -30,7 +31,7 @@ static __always_inline long get_flags() return sz >= wakeup_data_size ? BPF_RB_FORCE_WAKEUP : BPF_RB_NO_WAKEUP; } -SEC("fentry/__x64_sys_getpgid") +SEC("fentry/" SYS_PREFIX "sys_getpgid") int bench_ringbuf(void *ctx) { long *sample, flags; diff --git a/tools/testing/selftests/bpf/progs/sample_map_ret0.c b/tools/testing/selftests/bpf/progs/sample_map_ret0.c index 1612a32007b6..495990d355ef 100644 --- a/tools/testing/selftests/bpf/progs/sample_map_ret0.c +++ b/tools/testing/selftests/bpf/progs/sample_map_ret0.c @@ -2,19 +2,19 @@ #include <linux/bpf.h> #include <bpf/bpf_helpers.h> -struct bpf_map_def SEC("maps") htab = { - .type = BPF_MAP_TYPE_HASH, - .key_size = sizeof(__u32), - .value_size = sizeof(long), - .max_entries = 2, -}; +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, __u32); + __type(value, long); + __uint(max_entries, 2); +} htab SEC(".maps"); -struct bpf_map_def SEC("maps") array = { - .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(long), - .max_entries = 2, -}; +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, __u32); + __type(value, long); + __uint(max_entries, 2); +} array SEC(".maps"); /* Sample program which should always load for testing control paths. */ SEC(".text") int func() diff --git a/tools/testing/selftests/bpf/progs/sockmap_parse_prog.c b/tools/testing/selftests/bpf/progs/sockmap_parse_prog.c index 95d5b941bc1f..c9abfe3a11af 100644 --- a/tools/testing/selftests/bpf/progs/sockmap_parse_prog.c +++ b/tools/testing/selftests/bpf/progs/sockmap_parse_prog.c @@ -7,8 +7,6 @@ int bpf_prog1(struct __sk_buff *skb) { void *data_end = (void *)(long) skb->data_end; void *data = (void *)(long) skb->data; - __u32 lport = skb->local_port; - __u32 rport = skb->remote_port; __u8 *d = data; int err; diff --git a/tools/testing/selftests/bpf/progs/sockopt_sk.c b/tools/testing/selftests/bpf/progs/sockopt_sk.c index 79c8139b63b8..c8d810010a94 100644 --- a/tools/testing/selftests/bpf/progs/sockopt_sk.c +++ b/tools/testing/selftests/bpf/progs/sockopt_sk.c @@ -72,18 +72,19 @@ int _getsockopt(struct bpf_sockopt *ctx) * reasons. */ - if (optval + sizeof(struct tcp_zerocopy_receive) > optval_end) - return 0; /* EPERM, bounds check */ + /* Check that optval contains address (__u64) */ + if (optval + sizeof(__u64) > optval_end) + return 0; /* bounds check */ if (((struct tcp_zerocopy_receive *)optval)->address != 0) - return 0; /* EPERM, unexpected data */ + return 0; /* unexpected data */ return 1; } if (ctx->level == SOL_IP && ctx->optname == IP_FREEBIND) { if (optval + 1 > optval_end) - return 0; /* EPERM, bounds check */ + return 0; /* bounds check */ ctx->retval = 0; /* Reset system call return value to zero */ @@ -96,24 +97,24 @@ int _getsockopt(struct bpf_sockopt *ctx) * bytes of data. */ if (optval_end - optval != page_size) - return 0; /* EPERM, unexpected data size */ + return 0; /* unexpected data size */ return 1; } if (ctx->level != SOL_CUSTOM) - return 0; /* EPERM, deny everything except custom level */ + return 0; /* deny everything except custom level */ if (optval + 1 > optval_end) - return 0; /* EPERM, bounds check */ + return 0; /* bounds check */ storage = bpf_sk_storage_get(&socket_storage_map, ctx->sk, 0, BPF_SK_STORAGE_GET_F_CREATE); if (!storage) - return 0; /* EPERM, couldn't get sk storage */ + return 0; /* couldn't get sk storage */ if (!ctx->retval) - return 0; /* EPERM, kernel should not have handled + return 0; /* kernel should not have handled * SOL_CUSTOM, something is wrong! */ ctx->retval = 0; /* Reset system call return value to zero */ @@ -152,7 +153,7 @@ int _setsockopt(struct bpf_sockopt *ctx) /* Overwrite SO_SNDBUF value */ if (optval + sizeof(__u32) > optval_end) - return 0; /* EPERM, bounds check */ + return 0; /* bounds check */ *(__u32 *)optval = 0x55AA; ctx->optlen = 4; @@ -164,7 +165,7 @@ int _setsockopt(struct bpf_sockopt *ctx) /* Always use cubic */ if (optval + 5 > optval_end) - return 0; /* EPERM, bounds check */ + return 0; /* bounds check */ memcpy(optval, "cubic", 5); ctx->optlen = 5; @@ -175,10 +176,10 @@ int _setsockopt(struct bpf_sockopt *ctx) if (ctx->level == SOL_IP && ctx->optname == IP_FREEBIND) { /* Original optlen is larger than PAGE_SIZE. */ if (ctx->optlen != page_size * 2) - return 0; /* EPERM, unexpected data size */ + return 0; /* unexpected data size */ if (optval + 1 > optval_end) - return 0; /* EPERM, bounds check */ + return 0; /* bounds check */ /* Make sure we can trim the buffer. */ optval[0] = 0; @@ -189,21 +190,21 @@ int _setsockopt(struct bpf_sockopt *ctx) * bytes of data. */ if (optval_end - optval != page_size) - return 0; /* EPERM, unexpected data size */ + return 0; /* unexpected data size */ return 1; } if (ctx->level != SOL_CUSTOM) - return 0; /* EPERM, deny everything except custom level */ + return 0; /* deny everything except custom level */ if (optval + 1 > optval_end) - return 0; /* EPERM, bounds check */ + return 0; /* bounds check */ storage = bpf_sk_storage_get(&socket_storage_map, ctx->sk, 0, BPF_SK_STORAGE_GET_F_CREATE); if (!storage) - return 0; /* EPERM, couldn't get sk storage */ + return 0; /* couldn't get sk storage */ storage->val = optval[0]; ctx->optlen = -1; /* BPF has consumed this option, don't call kernel diff --git a/tools/testing/selftests/bpf/progs/stacktrace_map_skip.c b/tools/testing/selftests/bpf/progs/stacktrace_map_skip.c new file mode 100644 index 000000000000..2eb297df3dd6 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/stacktrace_map_skip.c @@ -0,0 +1,68 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <vmlinux.h> +#include <bpf/bpf_helpers.h> + +#define TEST_STACK_DEPTH 2 +#define TEST_MAX_ENTRIES 16384 + +typedef __u64 stack_trace_t[TEST_STACK_DEPTH]; + +struct { + __uint(type, BPF_MAP_TYPE_STACK_TRACE); + __uint(max_entries, TEST_MAX_ENTRIES); + __type(key, __u32); + __type(value, stack_trace_t); +} stackmap SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, TEST_MAX_ENTRIES); + __type(key, __u32); + __type(value, __u32); +} stackid_hmap SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, TEST_MAX_ENTRIES); + __type(key, __u32); + __type(value, stack_trace_t); +} stack_amap SEC(".maps"); + +int pid = 0; +int control = 0; +int failed = 0; + +SEC("tracepoint/sched/sched_switch") +int oncpu(struct trace_event_raw_sched_switch *ctx) +{ + __u32 max_len = TEST_STACK_DEPTH * sizeof(__u64); + __u32 key = 0, val = 0; + __u64 *stack_p; + + if (pid != (bpf_get_current_pid_tgid() >> 32)) + return 0; + + if (control) + return 0; + + /* it should allow skipping whole buffer size entries */ + key = bpf_get_stackid(ctx, &stackmap, TEST_STACK_DEPTH); + if ((int)key >= 0) { + /* The size of stackmap and stack_amap should be the same */ + bpf_map_update_elem(&stackid_hmap, &key, &val, 0); + stack_p = bpf_map_lookup_elem(&stack_amap, &key); + if (stack_p) { + bpf_get_stack(ctx, stack_p, max_len, TEST_STACK_DEPTH); + /* it wrongly skipped all the entries and filled zero */ + if (stack_p[0] == 0) + failed = 1; + } + } else { + /* old kernel doesn't support skipping that many entries */ + failed = 2; + } + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_bpf_nf.c b/tools/testing/selftests/bpf/progs/test_bpf_nf.c new file mode 100644 index 000000000000..f00a9731930e --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_bpf_nf.c @@ -0,0 +1,118 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <vmlinux.h> +#include <bpf/bpf_helpers.h> + +#define EAFNOSUPPORT 97 +#define EPROTO 71 +#define ENONET 64 +#define EINVAL 22 +#define ENOENT 2 + +int test_einval_bpf_tuple = 0; +int test_einval_reserved = 0; +int test_einval_netns_id = 0; +int test_einval_len_opts = 0; +int test_eproto_l4proto = 0; +int test_enonet_netns_id = 0; +int test_enoent_lookup = 0; +int test_eafnosupport = 0; + +struct nf_conn; + +struct bpf_ct_opts___local { + s32 netns_id; + s32 error; + u8 l4proto; + u8 reserved[3]; +} __attribute__((preserve_access_index)); + +struct nf_conn *bpf_xdp_ct_lookup(struct xdp_md *, struct bpf_sock_tuple *, u32, + struct bpf_ct_opts___local *, u32) __ksym; +struct nf_conn *bpf_skb_ct_lookup(struct __sk_buff *, struct bpf_sock_tuple *, u32, + struct bpf_ct_opts___local *, u32) __ksym; +void bpf_ct_release(struct nf_conn *) __ksym; + +static __always_inline void +nf_ct_test(struct nf_conn *(*func)(void *, struct bpf_sock_tuple *, u32, + struct bpf_ct_opts___local *, u32), + void *ctx) +{ + struct bpf_ct_opts___local opts_def = { .l4proto = IPPROTO_TCP, .netns_id = -1 }; + struct bpf_sock_tuple bpf_tuple; + struct nf_conn *ct; + + __builtin_memset(&bpf_tuple, 0, sizeof(bpf_tuple.ipv4)); + + ct = func(ctx, NULL, 0, &opts_def, sizeof(opts_def)); + if (ct) + bpf_ct_release(ct); + else + test_einval_bpf_tuple = opts_def.error; + + opts_def.reserved[0] = 1; + ct = func(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4), &opts_def, sizeof(opts_def)); + opts_def.reserved[0] = 0; + opts_def.l4proto = IPPROTO_TCP; + if (ct) + bpf_ct_release(ct); + else + test_einval_reserved = opts_def.error; + + opts_def.netns_id = -2; + ct = func(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4), &opts_def, sizeof(opts_def)); + opts_def.netns_id = -1; + if (ct) + bpf_ct_release(ct); + else + test_einval_netns_id = opts_def.error; + + ct = func(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4), &opts_def, sizeof(opts_def) - 1); + if (ct) + bpf_ct_release(ct); + else + test_einval_len_opts = opts_def.error; + + opts_def.l4proto = IPPROTO_ICMP; + ct = func(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4), &opts_def, sizeof(opts_def)); + opts_def.l4proto = IPPROTO_TCP; + if (ct) + bpf_ct_release(ct); + else + test_eproto_l4proto = opts_def.error; + + opts_def.netns_id = 0xf00f; + ct = func(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4), &opts_def, sizeof(opts_def)); + opts_def.netns_id = -1; + if (ct) + bpf_ct_release(ct); + else + test_enonet_netns_id = opts_def.error; + + ct = func(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4), &opts_def, sizeof(opts_def)); + if (ct) + bpf_ct_release(ct); + else + test_enoent_lookup = opts_def.error; + + ct = func(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4) - 1, &opts_def, sizeof(opts_def)); + if (ct) + bpf_ct_release(ct); + else + test_eafnosupport = opts_def.error; +} + +SEC("xdp") +int nf_xdp_ct_test(struct xdp_md *ctx) +{ + nf_ct_test((void *)bpf_xdp_ct_lookup, ctx); + return 0; +} + +SEC("tc") +int nf_skb_ct_test(struct __sk_buff *ctx) +{ + nf_ct_test((void *)bpf_skb_ct_lookup, ctx); + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/btf_decl_tag.c b/tools/testing/selftests/bpf/progs/test_btf_decl_tag.c index c88ccc53529a..c88ccc53529a 100644 --- a/tools/testing/selftests/bpf/progs/btf_decl_tag.c +++ b/tools/testing/selftests/bpf/progs/test_btf_decl_tag.c diff --git a/tools/testing/selftests/bpf/progs/test_btf_haskv.c b/tools/testing/selftests/bpf/progs/test_btf_haskv.c index 160ead6c67b2..07c94df13660 100644 --- a/tools/testing/selftests/bpf/progs/test_btf_haskv.c +++ b/tools/testing/selftests/bpf/progs/test_btf_haskv.c @@ -9,12 +9,15 @@ struct ipv_counts { unsigned int v6; }; +#pragma GCC diagnostic push +#pragma GCC diagnostic ignored "-Wdeprecated-declarations" struct bpf_map_def SEC("maps") btf_map = { .type = BPF_MAP_TYPE_ARRAY, .key_size = sizeof(int), .value_size = sizeof(struct ipv_counts), .max_entries = 4, }; +#pragma GCC diagnostic pop BPF_ANNOTATE_KV_PAIR(btf_map, int, struct ipv_counts); diff --git a/tools/testing/selftests/bpf/progs/test_btf_newkv.c b/tools/testing/selftests/bpf/progs/test_btf_newkv.c index 1884a5bd10f5..762671a2e90c 100644 --- a/tools/testing/selftests/bpf/progs/test_btf_newkv.c +++ b/tools/testing/selftests/bpf/progs/test_btf_newkv.c @@ -9,6 +9,8 @@ struct ipv_counts { unsigned int v6; }; +#pragma GCC diagnostic push +#pragma GCC diagnostic ignored "-Wdeprecated-declarations" /* just to validate we can handle maps in multiple sections */ struct bpf_map_def SEC("maps") btf_map_legacy = { .type = BPF_MAP_TYPE_ARRAY, @@ -16,6 +18,7 @@ struct bpf_map_def SEC("maps") btf_map_legacy = { .value_size = sizeof(long long), .max_entries = 4, }; +#pragma GCC diagnostic pop BPF_ANNOTATE_KV_PAIR(btf_map_legacy, int, struct ipv_counts); diff --git a/tools/testing/selftests/bpf/progs/test_btf_nokv.c b/tools/testing/selftests/bpf/progs/test_btf_nokv.c index 15e0f9945fe4..1dabb88f8cb4 100644 --- a/tools/testing/selftests/bpf/progs/test_btf_nokv.c +++ b/tools/testing/selftests/bpf/progs/test_btf_nokv.c @@ -8,12 +8,12 @@ struct ipv_counts { unsigned int v6; }; -struct bpf_map_def SEC("maps") btf_map = { - .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(int), - .value_size = sizeof(struct ipv_counts), - .max_entries = 4, -}; +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(key_size, sizeof(int)); + __uint(value_size, sizeof(struct ipv_counts)); + __uint(max_entries, 4); +} btf_map SEC(".maps"); __attribute__((noinline)) int test_long_fname_2(void) diff --git a/tools/testing/selftests/bpf/progs/test_custom_sec_handlers.c b/tools/testing/selftests/bpf/progs/test_custom_sec_handlers.c new file mode 100644 index 000000000000..4061f701ca50 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_custom_sec_handlers.c @@ -0,0 +1,63 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2022 Facebook */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +const volatile int my_pid; + +bool abc1_called; +bool abc2_called; +bool custom1_called; +bool custom2_called; +bool kprobe1_called; +bool xyz_called; + +SEC("abc") +int abc1(void *ctx) +{ + abc1_called = true; + return 0; +} + +SEC("abc/whatever") +int abc2(void *ctx) +{ + abc2_called = true; + return 0; +} + +SEC("custom") +int custom1(void *ctx) +{ + custom1_called = true; + return 0; +} + +SEC("custom/something") +int custom2(void *ctx) +{ + custom2_called = true; + return 0; +} + +SEC("kprobe") +int kprobe1(void *ctx) +{ + kprobe1_called = true; + return 0; +} + +SEC("xyz/blah") +int xyz(void *ctx) +{ + int whatever; + + /* use sleepable helper, custom handler should set sleepable flag */ + bpf_copy_from_user(&whatever, sizeof(whatever), NULL); + xyz_called = true; + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_d_path_check_types.c b/tools/testing/selftests/bpf/progs/test_d_path_check_types.c new file mode 100644 index 000000000000..7e02b7361307 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_d_path_check_types.c @@ -0,0 +1,32 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +extern const int bpf_prog_active __ksym; + +struct { + __uint(type, BPF_MAP_TYPE_RINGBUF); + __uint(max_entries, 1 << 12); +} ringbuf SEC(".maps"); + +SEC("fentry/security_inode_getattr") +int BPF_PROG(d_path_check_rdonly_mem, struct path *path, struct kstat *stat, + __u32 request_mask, unsigned int query_flags) +{ + void *active; + u32 cpu; + + cpu = bpf_get_smp_processor_id(); + active = (void *)bpf_per_cpu_ptr(&bpf_prog_active, cpu); + if (active) { + /* FAIL here! 'active' points to 'regular' memory. It + * cannot be submitted to ring buffer. + */ + bpf_ringbuf_submit(active, 0); + } + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_probe_user.c b/tools/testing/selftests/bpf/progs/test_probe_user.c index 8812a90da4eb..702578a5e496 100644 --- a/tools/testing/selftests/bpf/progs/test_probe_user.c +++ b/tools/testing/selftests/bpf/progs/test_probe_user.c @@ -7,20 +7,7 @@ #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> - -#if defined(__TARGET_ARCH_x86) -#define SYSCALL_WRAPPER 1 -#define SYS_PREFIX "__x64_" -#elif defined(__TARGET_ARCH_s390) -#define SYSCALL_WRAPPER 1 -#define SYS_PREFIX "__s390x_" -#elif defined(__TARGET_ARCH_arm64) -#define SYSCALL_WRAPPER 1 -#define SYS_PREFIX "__arm64_" -#else -#define SYSCALL_WRAPPER 0 -#define SYS_PREFIX "" -#endif +#include "bpf_misc.h" static struct sockaddr_in old; diff --git a/tools/testing/selftests/bpf/progs/test_ringbuf.c b/tools/testing/selftests/bpf/progs/test_ringbuf.c index eaa7d9dba0be..5bdc0d38efc0 100644 --- a/tools/testing/selftests/bpf/progs/test_ringbuf.c +++ b/tools/testing/selftests/bpf/progs/test_ringbuf.c @@ -3,6 +3,7 @@ #include <linux/bpf.h> #include <bpf/bpf_helpers.h> +#include "bpf_misc.h" char _license[] SEC("license") = "GPL"; @@ -35,7 +36,7 @@ long prod_pos = 0; /* inner state */ long seq = 0; -SEC("fentry/__x64_sys_getpgid") +SEC("fentry/" SYS_PREFIX "sys_getpgid") int test_ringbuf(void *ctx) { int cur_pid = bpf_get_current_pid_tgid() >> 32; diff --git a/tools/testing/selftests/bpf/progs/test_send_signal_kern.c b/tools/testing/selftests/bpf/progs/test_send_signal_kern.c index b4233d3efac2..92354cd72044 100644 --- a/tools/testing/selftests/bpf/progs/test_send_signal_kern.c +++ b/tools/testing/selftests/bpf/progs/test_send_signal_kern.c @@ -10,7 +10,7 @@ static __always_inline int bpf_send_signal_test(void *ctx) { int ret; - if (status != 0 || sig == 0 || pid == 0) + if (status != 0 || pid == 0) return 0; if ((bpf_get_current_pid_tgid() >> 32) == pid) { diff --git a/tools/testing/selftests/bpf/progs/test_sk_lookup.c b/tools/testing/selftests/bpf/progs/test_sk_lookup.c index 83b0aaa52ef7..6058dcb11b36 100644 --- a/tools/testing/selftests/bpf/progs/test_sk_lookup.c +++ b/tools/testing/selftests/bpf/progs/test_sk_lookup.c @@ -392,6 +392,7 @@ int ctx_narrow_access(struct bpf_sk_lookup *ctx) { struct bpf_sock *sk; int err, family; + __u32 val_u32; bool v4; v4 = (ctx->family == AF_INET); @@ -412,12 +413,22 @@ int ctx_narrow_access(struct bpf_sk_lookup *ctx) /* Narrow loads from remote_port field. Expect SRC_PORT. */ if (LSB(ctx->remote_port, 0) != ((SRC_PORT >> 0) & 0xff) || - LSB(ctx->remote_port, 1) != ((SRC_PORT >> 8) & 0xff) || - LSB(ctx->remote_port, 2) != 0 || LSB(ctx->remote_port, 3) != 0) + LSB(ctx->remote_port, 1) != ((SRC_PORT >> 8) & 0xff)) return SK_DROP; if (LSW(ctx->remote_port, 0) != SRC_PORT) return SK_DROP; + /* + * NOTE: 4-byte load from bpf_sk_lookup at remote_port offset + * is quirky. It gets rewritten by the access converter to a + * 2-byte load for backward compatibility. Treating the load + * result as a be16 value makes the code portable across + * little- and big-endian platforms. + */ + val_u32 = *(__u32 *)&ctx->remote_port; + if (val_u32 != SRC_PORT) + return SK_DROP; + /* Narrow loads from local_port field. Expect DST_PORT. */ if (LSB(ctx->local_port, 0) != ((DST_PORT >> 0) & 0xff) || LSB(ctx->local_port, 1) != ((DST_PORT >> 8) & 0xff) || diff --git a/tools/testing/selftests/bpf/progs/test_skb_cgroup_id_kern.c b/tools/testing/selftests/bpf/progs/test_skb_cgroup_id_kern.c index c304cd5b8cad..37aacc66cd68 100644 --- a/tools/testing/selftests/bpf/progs/test_skb_cgroup_id_kern.c +++ b/tools/testing/selftests/bpf/progs/test_skb_cgroup_id_kern.c @@ -10,12 +10,12 @@ #define NUM_CGROUP_LEVELS 4 -struct bpf_map_def SEC("maps") cgroup_ids = { - .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(__u64), - .max_entries = NUM_CGROUP_LEVELS, -}; +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, __u32); + __type(value, __u64); + __uint(max_entries, NUM_CGROUP_LEVELS); +} cgroup_ids SEC(".maps"); static __always_inline void log_nth_level(struct __sk_buff *skb, __u32 level) { diff --git a/tools/testing/selftests/bpf/progs/test_sock_fields.c b/tools/testing/selftests/bpf/progs/test_sock_fields.c index 81b57b9aaaea..9f4b8f9f1181 100644 --- a/tools/testing/selftests/bpf/progs/test_sock_fields.c +++ b/tools/testing/selftests/bpf/progs/test_sock_fields.c @@ -12,6 +12,7 @@ enum bpf_linum_array_idx { EGRESS_LINUM_IDX, INGRESS_LINUM_IDX, + READ_SK_DST_PORT_LINUM_IDX, __NR_BPF_LINUM_ARRAY_IDX, }; @@ -113,7 +114,7 @@ static void tpcpy(struct bpf_tcp_sock *dst, #define RET_LOG() ({ \ linum = __LINE__; \ - bpf_map_update_elem(&linum_map, &linum_idx, &linum, BPF_NOEXIST); \ + bpf_map_update_elem(&linum_map, &linum_idx, &linum, BPF_ANY); \ return CG_OK; \ }) @@ -133,11 +134,11 @@ int egress_read_sock_fields(struct __sk_buff *skb) if (!sk) RET_LOG(); - /* Not the testing egress traffic or - * TCP_LISTEN (10) socket will be copied at the ingress side. + /* Not testing the egress traffic or the listening socket, + * which are covered by the cgroup_skb/ingress test program. */ if (sk->family != AF_INET6 || !is_loopback6(sk->src_ip6) || - sk->state == 10) + sk->state == BPF_TCP_LISTEN) return CG_OK; if (sk->src_port == bpf_ntohs(srv_sa6.sin6_port)) { @@ -231,8 +232,8 @@ int ingress_read_sock_fields(struct __sk_buff *skb) sk->src_port != bpf_ntohs(srv_sa6.sin6_port)) return CG_OK; - /* Only interested in TCP_LISTEN */ - if (sk->state != 10) + /* Only interested in the listening socket */ + if (sk->state != BPF_TCP_LISTEN) return CG_OK; /* It must be a fullsock for cgroup_skb/ingress prog */ @@ -250,4 +251,54 @@ int ingress_read_sock_fields(struct __sk_buff *skb) return CG_OK; } +/* + * NOTE: 4-byte load from bpf_sock at dst_port offset is quirky. It + * gets rewritten by the access converter to a 2-byte load for + * backward compatibility. Treating the load result as a be16 value + * makes the code portable across little- and big-endian platforms. + */ +static __noinline bool sk_dst_port__load_word(struct bpf_sock *sk) +{ + __u32 *word = (__u32 *)&sk->dst_port; + return word[0] == bpf_htons(0xcafe); +} + +static __noinline bool sk_dst_port__load_half(struct bpf_sock *sk) +{ + __u16 *half = (__u16 *)&sk->dst_port; + return half[0] == bpf_htons(0xcafe); +} + +static __noinline bool sk_dst_port__load_byte(struct bpf_sock *sk) +{ + __u8 *byte = (__u8 *)&sk->dst_port; + return byte[0] == 0xca && byte[1] == 0xfe; +} + +SEC("cgroup_skb/egress") +int read_sk_dst_port(struct __sk_buff *skb) +{ + __u32 linum, linum_idx; + struct bpf_sock *sk; + + linum_idx = READ_SK_DST_PORT_LINUM_IDX; + + sk = skb->sk; + if (!sk) + RET_LOG(); + + /* Ignore everything but the SYN from the client socket */ + if (sk->state != BPF_TCP_SYN_SENT) + return CG_OK; + + if (!sk_dst_port__load_word(sk)) + RET_LOG(); + if (!sk_dst_port__load_half(sk)) + RET_LOG(); + if (!sk_dst_port__load_byte(sk)) + RET_LOG(); + + return CG_OK; +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_kern.h b/tools/testing/selftests/bpf/progs/test_sockmap_kern.h index 2966564b8497..6c85b00f27b2 100644 --- a/tools/testing/selftests/bpf/progs/test_sockmap_kern.h +++ b/tools/testing/selftests/bpf/progs/test_sockmap_kern.h @@ -235,7 +235,7 @@ SEC("sk_msg1") int bpf_prog4(struct sk_msg_md *msg) { int *bytes, zero = 0, one = 1, two = 2, three = 3, four = 4, five = 5; - int *start, *end, *start_push, *end_push, *start_pop, *pop; + int *start, *end, *start_push, *end_push, *start_pop, *pop, err = 0; bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero); if (bytes) @@ -249,8 +249,11 @@ int bpf_prog4(struct sk_msg_md *msg) bpf_msg_pull_data(msg, *start, *end, 0); start_push = bpf_map_lookup_elem(&sock_bytes, &two); end_push = bpf_map_lookup_elem(&sock_bytes, &three); - if (start_push && end_push) - bpf_msg_push_data(msg, *start_push, *end_push, 0); + if (start_push && end_push) { + err = bpf_msg_push_data(msg, *start_push, *end_push, 0); + if (err) + return SK_DROP; + } start_pop = bpf_map_lookup_elem(&sock_bytes, &four); pop = bpf_map_lookup_elem(&sock_bytes, &five); if (start_pop && pop) @@ -263,6 +266,7 @@ int bpf_prog6(struct sk_msg_md *msg) { int zero = 0, one = 1, two = 2, three = 3, four = 4, five = 5, key = 0; int *bytes, *start, *end, *start_push, *end_push, *start_pop, *pop, *f; + int err = 0; __u64 flags = 0; bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero); @@ -279,8 +283,11 @@ int bpf_prog6(struct sk_msg_md *msg) start_push = bpf_map_lookup_elem(&sock_bytes, &two); end_push = bpf_map_lookup_elem(&sock_bytes, &three); - if (start_push && end_push) - bpf_msg_push_data(msg, *start_push, *end_push, 0); + if (start_push && end_push) { + err = bpf_msg_push_data(msg, *start_push, *end_push, 0); + if (err) + return SK_DROP; + } start_pop = bpf_map_lookup_elem(&sock_bytes, &four); pop = bpf_map_lookup_elem(&sock_bytes, &five); @@ -338,7 +345,7 @@ SEC("sk_msg5") int bpf_prog10(struct sk_msg_md *msg) { int *bytes, *start, *end, *start_push, *end_push, *start_pop, *pop; - int zero = 0, one = 1, two = 2, three = 3, four = 4, five = 5; + int zero = 0, one = 1, two = 2, three = 3, four = 4, five = 5, err = 0; bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero); if (bytes) @@ -352,8 +359,11 @@ int bpf_prog10(struct sk_msg_md *msg) bpf_msg_pull_data(msg, *start, *end, 0); start_push = bpf_map_lookup_elem(&sock_bytes, &two); end_push = bpf_map_lookup_elem(&sock_bytes, &three); - if (start_push && end_push) - bpf_msg_push_data(msg, *start_push, *end_push, 0); + if (start_push && end_push) { + err = bpf_msg_push_data(msg, *start_push, *end_push, 0); + if (err) + return SK_PASS; + } start_pop = bpf_map_lookup_elem(&sock_bytes, &four); pop = bpf_map_lookup_elem(&sock_bytes, &five); if (start_pop && pop) diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_progs_query.c b/tools/testing/selftests/bpf/progs/test_sockmap_progs_query.c new file mode 100644 index 000000000000..9d58d61c0dee --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_sockmap_progs_query.c @@ -0,0 +1,24 @@ +// SPDX-License-Identifier: GPL-2.0 +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> + +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u64); +} sock_map SEC(".maps"); + +SEC("sk_skb") +int prog_skb_verdict(struct __sk_buff *skb) +{ + return SK_PASS; +} + +SEC("sk_msg") +int prog_skmsg_verdict(struct sk_msg_md *msg) +{ + return SK_PASS; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_stacktrace_map.c b/tools/testing/selftests/bpf/progs/test_stacktrace_map.c index a8233e7f173b..728dbd39eff0 100644 --- a/tools/testing/selftests/bpf/progs/test_stacktrace_map.c +++ b/tools/testing/selftests/bpf/progs/test_stacktrace_map.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 // Copyright (c) 2018 Facebook -#include <linux/bpf.h> +#include <vmlinux.h> #include <bpf/bpf_helpers.h> #ifndef PERF_MAX_STACK_DEPTH @@ -41,11 +41,11 @@ struct { /* taken from /sys/kernel/debug/tracing/events/sched/sched_switch/format */ struct sched_switch_args { unsigned long long pad; - char prev_comm[16]; + char prev_comm[TASK_COMM_LEN]; int prev_pid; int prev_prio; long long prev_state; - char next_comm[16]; + char next_comm[TASK_COMM_LEN]; int next_pid; int next_prio; }; diff --git a/tools/testing/selftests/bpf/progs/test_subskeleton.c b/tools/testing/selftests/bpf/progs/test_subskeleton.c new file mode 100644 index 000000000000..006417974372 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_subskeleton.c @@ -0,0 +1,28 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) Meta Platforms, Inc. and affiliates. */ + +#include <stdbool.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +/* volatile to force a read, compiler may assume 0 otherwise */ +const volatile int rovar1; +int out1; + +/* Override weak symbol in test_subskeleton_lib */ +int var5 = 5; + +extern volatile bool CONFIG_BPF_SYSCALL __kconfig; + +extern int lib_routine(void); + +SEC("raw_tp/sys_enter") +int handler1(const void *ctx) +{ + (void) CONFIG_BPF_SYSCALL; + + out1 = lib_routine() * rovar1; + return 0; +} + +char LICENSE[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_subskeleton_lib.c b/tools/testing/selftests/bpf/progs/test_subskeleton_lib.c new file mode 100644 index 000000000000..ecfafe812c36 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_subskeleton_lib.c @@ -0,0 +1,61 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) Meta Platforms, Inc. and affiliates. */ + +#include <stdbool.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +/* volatile to force a read */ +const volatile int var1; +volatile int var2 = 1; +struct { + int var3_1; + __s64 var3_2; +} var3; +int libout1; + +extern volatile bool CONFIG_BPF_SYSCALL __kconfig; + +int var4[4]; + +__weak int var5 SEC(".data"); + +/* Fully contained within library extern-and-definition */ +extern int var6; + +int var7 SEC(".data.custom"); + +int (*fn_ptr)(void); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, __u32); + __type(value, __u32); + __uint(max_entries, 16); +} map1 SEC(".maps"); + +extern struct { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, __u32); + __type(value, __u32); + __uint(max_entries, 16); +} map2 SEC(".maps"); + +int lib_routine(void) +{ + __u32 key = 1, value = 2; + + (void) CONFIG_BPF_SYSCALL; + bpf_map_update_elem(&map2, &key, &value, BPF_ANY); + + libout1 = var1 + var2 + var3.var3_1 + var3.var3_2 + var5 + var6; + return libout1; +} + +SEC("perf_event") +int lib_perf_handler(struct pt_regs *ctx) +{ + return 0; +} + +char LICENSE[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_subskeleton_lib2.c b/tools/testing/selftests/bpf/progs/test_subskeleton_lib2.c new file mode 100644 index 000000000000..80238486b7ce --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_subskeleton_lib2.c @@ -0,0 +1,16 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) Meta Platforms, Inc. and affiliates. */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +int var6 = 6; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, __u32); + __type(value, __u32); + __uint(max_entries, 16); +} map2 SEC(".maps"); + +char LICENSE[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_tc_dtime.c b/tools/testing/selftests/bpf/progs/test_tc_dtime.c new file mode 100644 index 000000000000..06f300d06dbd --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_tc_dtime.c @@ -0,0 +1,349 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2022 Meta + +#include <stddef.h> +#include <stdint.h> +#include <stdbool.h> +#include <linux/bpf.h> +#include <linux/stddef.h> +#include <linux/pkt_cls.h> +#include <linux/if_ether.h> +#include <linux/in.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> +#include <sys/socket.h> + +/* veth_src --- veth_src_fwd --- veth_det_fwd --- veth_dst + * | | + * ns_src | ns_fwd | ns_dst + * + * ns_src and ns_dst: ENDHOST namespace + * ns_fwd: Fowarding namespace + */ + +#define ctx_ptr(field) (void *)(long)(field) + +#define ip4_src __bpf_htonl(0xac100164) /* 172.16.1.100 */ +#define ip4_dst __bpf_htonl(0xac100264) /* 172.16.2.100 */ + +#define ip6_src { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, \ + 0x00, 0x01, 0xde, 0xad, 0xbe, 0xef, 0xca, 0xfe } +#define ip6_dst { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, \ + 0x00, 0x02, 0xde, 0xad, 0xbe, 0xef, 0xca, 0xfe } + +#define v6_equal(a, b) (a.s6_addr32[0] == b.s6_addr32[0] && \ + a.s6_addr32[1] == b.s6_addr32[1] && \ + a.s6_addr32[2] == b.s6_addr32[2] && \ + a.s6_addr32[3] == b.s6_addr32[3]) + +volatile const __u32 IFINDEX_SRC; +volatile const __u32 IFINDEX_DST; + +#define EGRESS_ENDHOST_MAGIC 0x0b9fbeef +#define INGRESS_FWDNS_MAGIC 0x1b9fbeef +#define EGRESS_FWDNS_MAGIC 0x2b9fbeef + +enum { + INGRESS_FWDNS_P100, + INGRESS_FWDNS_P101, + EGRESS_FWDNS_P100, + EGRESS_FWDNS_P101, + INGRESS_ENDHOST, + EGRESS_ENDHOST, + SET_DTIME, + __MAX_CNT, +}; + +enum { + TCP_IP6_CLEAR_DTIME, + TCP_IP4, + TCP_IP6, + UDP_IP4, + UDP_IP6, + TCP_IP4_RT_FWD, + TCP_IP6_RT_FWD, + UDP_IP4_RT_FWD, + UDP_IP6_RT_FWD, + UKN_TEST, + __NR_TESTS, +}; + +enum { + SRC_NS = 1, + DST_NS, +}; + +__u32 dtimes[__NR_TESTS][__MAX_CNT] = {}; +__u32 errs[__NR_TESTS][__MAX_CNT] = {}; +__u32 test = 0; + +static void inc_dtimes(__u32 idx) +{ + if (test < __NR_TESTS) + dtimes[test][idx]++; + else + dtimes[UKN_TEST][idx]++; +} + +static void inc_errs(__u32 idx) +{ + if (test < __NR_TESTS) + errs[test][idx]++; + else + errs[UKN_TEST][idx]++; +} + +static int skb_proto(int type) +{ + return type & 0xff; +} + +static int skb_ns(int type) +{ + return (type >> 8) & 0xff; +} + +static bool fwdns_clear_dtime(void) +{ + return test == TCP_IP6_CLEAR_DTIME; +} + +static bool bpf_fwd(void) +{ + return test < TCP_IP4_RT_FWD; +} + +/* -1: parse error: TC_ACT_SHOT + * 0: not testing traffic: TC_ACT_OK + * >0: first byte is the inet_proto, second byte has the netns + * of the sender + */ +static int skb_get_type(struct __sk_buff *skb) +{ + void *data_end = ctx_ptr(skb->data_end); + void *data = ctx_ptr(skb->data); + __u8 inet_proto = 0, ns = 0; + struct ipv6hdr *ip6h; + struct iphdr *iph; + + switch (skb->protocol) { + case __bpf_htons(ETH_P_IP): + iph = data + sizeof(struct ethhdr); + if (iph + 1 > data_end) + return -1; + if (iph->saddr == ip4_src) + ns = SRC_NS; + else if (iph->saddr == ip4_dst) + ns = DST_NS; + inet_proto = iph->protocol; + break; + case __bpf_htons(ETH_P_IPV6): + ip6h = data + sizeof(struct ethhdr); + if (ip6h + 1 > data_end) + return -1; + if (v6_equal(ip6h->saddr, (struct in6_addr)ip6_src)) + ns = SRC_NS; + else if (v6_equal(ip6h->saddr, (struct in6_addr)ip6_dst)) + ns = DST_NS; + inet_proto = ip6h->nexthdr; + break; + default: + return 0; + } + + if ((inet_proto != IPPROTO_TCP && inet_proto != IPPROTO_UDP) || !ns) + return 0; + + return (ns << 8 | inet_proto); +} + +/* format: direction@iface@netns + * egress@veth_(src|dst)@ns_(src|dst) + */ +SEC("tc") +int egress_host(struct __sk_buff *skb) +{ + int skb_type; + + skb_type = skb_get_type(skb); + if (skb_type == -1) + return TC_ACT_SHOT; + if (!skb_type) + return TC_ACT_OK; + + if (skb_proto(skb_type) == IPPROTO_TCP) { + if (skb->tstamp_type == BPF_SKB_TSTAMP_DELIVERY_MONO && + skb->tstamp) + inc_dtimes(EGRESS_ENDHOST); + else + inc_errs(EGRESS_ENDHOST); + } else { + if (skb->tstamp_type == BPF_SKB_TSTAMP_UNSPEC && + skb->tstamp) + inc_dtimes(EGRESS_ENDHOST); + else + inc_errs(EGRESS_ENDHOST); + } + + skb->tstamp = EGRESS_ENDHOST_MAGIC; + + return TC_ACT_OK; +} + +/* ingress@veth_(src|dst)@ns_(src|dst) */ +SEC("tc") +int ingress_host(struct __sk_buff *skb) +{ + int skb_type; + + skb_type = skb_get_type(skb); + if (skb_type == -1) + return TC_ACT_SHOT; + if (!skb_type) + return TC_ACT_OK; + + if (skb->tstamp_type == BPF_SKB_TSTAMP_DELIVERY_MONO && + skb->tstamp == EGRESS_FWDNS_MAGIC) + inc_dtimes(INGRESS_ENDHOST); + else + inc_errs(INGRESS_ENDHOST); + + return TC_ACT_OK; +} + +/* ingress@veth_(src|dst)_fwd@ns_fwd priority 100 */ +SEC("tc") +int ingress_fwdns_prio100(struct __sk_buff *skb) +{ + int skb_type; + + skb_type = skb_get_type(skb); + if (skb_type == -1) + return TC_ACT_SHOT; + if (!skb_type) + return TC_ACT_OK; + + /* delivery_time is only available to the ingress + * if the tc-bpf checks the skb->tstamp_type. + */ + if (skb->tstamp == EGRESS_ENDHOST_MAGIC) + inc_errs(INGRESS_FWDNS_P100); + + if (fwdns_clear_dtime()) + skb->tstamp = 0; + + return TC_ACT_UNSPEC; +} + +/* egress@veth_(src|dst)_fwd@ns_fwd priority 100 */ +SEC("tc") +int egress_fwdns_prio100(struct __sk_buff *skb) +{ + int skb_type; + + skb_type = skb_get_type(skb); + if (skb_type == -1) + return TC_ACT_SHOT; + if (!skb_type) + return TC_ACT_OK; + + /* delivery_time is always available to egress even + * the tc-bpf did not use the tstamp_type. + */ + if (skb->tstamp == INGRESS_FWDNS_MAGIC) + inc_dtimes(EGRESS_FWDNS_P100); + else + inc_errs(EGRESS_FWDNS_P100); + + if (fwdns_clear_dtime()) + skb->tstamp = 0; + + return TC_ACT_UNSPEC; +} + +/* ingress@veth_(src|dst)_fwd@ns_fwd priority 101 */ +SEC("tc") +int ingress_fwdns_prio101(struct __sk_buff *skb) +{ + __u64 expected_dtime = EGRESS_ENDHOST_MAGIC; + int skb_type; + + skb_type = skb_get_type(skb); + if (skb_type == -1 || !skb_type) + /* Should have handled in prio100 */ + return TC_ACT_SHOT; + + if (skb_proto(skb_type) == IPPROTO_UDP) + expected_dtime = 0; + + if (skb->tstamp_type) { + if (fwdns_clear_dtime() || + skb->tstamp_type != BPF_SKB_TSTAMP_DELIVERY_MONO || + skb->tstamp != expected_dtime) + inc_errs(INGRESS_FWDNS_P101); + else + inc_dtimes(INGRESS_FWDNS_P101); + } else { + if (!fwdns_clear_dtime() && expected_dtime) + inc_errs(INGRESS_FWDNS_P101); + } + + if (skb->tstamp_type == BPF_SKB_TSTAMP_DELIVERY_MONO) { + skb->tstamp = INGRESS_FWDNS_MAGIC; + } else { + if (bpf_skb_set_tstamp(skb, INGRESS_FWDNS_MAGIC, + BPF_SKB_TSTAMP_DELIVERY_MONO)) + inc_errs(SET_DTIME); + if (!bpf_skb_set_tstamp(skb, INGRESS_FWDNS_MAGIC, + BPF_SKB_TSTAMP_UNSPEC)) + inc_errs(SET_DTIME); + } + + if (skb_ns(skb_type) == SRC_NS) + return bpf_fwd() ? + bpf_redirect_neigh(IFINDEX_DST, NULL, 0, 0) : TC_ACT_OK; + else + return bpf_fwd() ? + bpf_redirect_neigh(IFINDEX_SRC, NULL, 0, 0) : TC_ACT_OK; +} + +/* egress@veth_(src|dst)_fwd@ns_fwd priority 101 */ +SEC("tc") +int egress_fwdns_prio101(struct __sk_buff *skb) +{ + int skb_type; + + skb_type = skb_get_type(skb); + if (skb_type == -1 || !skb_type) + /* Should have handled in prio100 */ + return TC_ACT_SHOT; + + if (skb->tstamp_type) { + if (fwdns_clear_dtime() || + skb->tstamp_type != BPF_SKB_TSTAMP_DELIVERY_MONO || + skb->tstamp != INGRESS_FWDNS_MAGIC) + inc_errs(EGRESS_FWDNS_P101); + else + inc_dtimes(EGRESS_FWDNS_P101); + } else { + if (!fwdns_clear_dtime()) + inc_errs(EGRESS_FWDNS_P101); + } + + if (skb->tstamp_type == BPF_SKB_TSTAMP_DELIVERY_MONO) { + skb->tstamp = EGRESS_FWDNS_MAGIC; + } else { + if (bpf_skb_set_tstamp(skb, EGRESS_FWDNS_MAGIC, + BPF_SKB_TSTAMP_DELIVERY_MONO)) + inc_errs(SET_DTIME); + if (!bpf_skb_set_tstamp(skb, INGRESS_FWDNS_MAGIC, + BPF_SKB_TSTAMP_UNSPEC)) + inc_errs(SET_DTIME); + } + + return TC_ACT_OK; +} + +char __license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_tc_edt.c b/tools/testing/selftests/bpf/progs/test_tc_edt.c index bf28814bfde5..950a70b61e74 100644 --- a/tools/testing/selftests/bpf/progs/test_tc_edt.c +++ b/tools/testing/selftests/bpf/progs/test_tc_edt.c @@ -17,12 +17,12 @@ #define THROTTLE_RATE_BPS (5 * 1000 * 1000) /* flow_key => last_tstamp timestamp used */ -struct bpf_map_def SEC("maps") flow_map = { - .type = BPF_MAP_TYPE_HASH, - .key_size = sizeof(uint32_t), - .value_size = sizeof(uint64_t), - .max_entries = 1, -}; +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, uint32_t); + __type(value, uint64_t); + __uint(max_entries, 1); +} flow_map SEC(".maps"); static inline int throttle_flow(struct __sk_buff *skb) { diff --git a/tools/testing/selftests/bpf/progs/test_tcp_check_syncookie_kern.c b/tools/testing/selftests/bpf/progs/test_tcp_check_syncookie_kern.c index cd747cd93dbe..6edebce563b5 100644 --- a/tools/testing/selftests/bpf/progs/test_tcp_check_syncookie_kern.c +++ b/tools/testing/selftests/bpf/progs/test_tcp_check_syncookie_kern.c @@ -16,12 +16,12 @@ #include <bpf/bpf_helpers.h> #include <bpf/bpf_endian.h> -struct bpf_map_def SEC("maps") results = { - .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(__u32), - .max_entries = 3, -}; +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, __u32); + __type(value, __u32); + __uint(max_entries, 3); +} results SEC(".maps"); static __always_inline __s64 gen_syncookie(void *data_end, struct bpf_sock *sk, void *iph, __u32 ip_size, diff --git a/tools/testing/selftests/bpf/progs/test_tracepoint.c b/tools/testing/selftests/bpf/progs/test_tracepoint.c index ce6974016f53..43bd7a20cc50 100644 --- a/tools/testing/selftests/bpf/progs/test_tracepoint.c +++ b/tools/testing/selftests/bpf/progs/test_tracepoint.c @@ -1,17 +1,17 @@ // SPDX-License-Identifier: GPL-2.0 // Copyright (c) 2017 Facebook -#include <linux/bpf.h> +#include <vmlinux.h> #include <bpf/bpf_helpers.h> /* taken from /sys/kernel/debug/tracing/events/sched/sched_switch/format */ struct sched_switch_args { unsigned long long pad; - char prev_comm[16]; + char prev_comm[TASK_COMM_LEN]; int prev_pid; int prev_prio; long long prev_state; - char next_comm[16]; + char next_comm[TASK_COMM_LEN]; int next_pid; int next_prio; }; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c b/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c index 199c61b7d062..53b64c999450 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c @@ -7,11 +7,10 @@ int _xdp_adjust_tail_grow(struct xdp_md *xdp) { void *data_end = (void *)(long)xdp->data_end; void *data = (void *)(long)xdp->data; - unsigned int data_len; + int data_len = bpf_xdp_get_buff_len(xdp); int offset = 0; /* Data length determine test case */ - data_len = data_end - data; if (data_len == 54) { /* sizeof(pkt_v4) */ offset = 4096; /* test too large offset */ @@ -20,7 +19,12 @@ int _xdp_adjust_tail_grow(struct xdp_md *xdp) } else if (data_len == 64) { offset = 128; } else if (data_len == 128) { - offset = 4096 - 256 - 320 - data_len; /* Max tail grow 3520 */ + /* Max tail grow 3520 */ + offset = 4096 - 256 - 320 - data_len; + } else if (data_len == 9000) { + offset = 10; + } else if (data_len == 9001) { + offset = 4096; } else { return XDP_ABORTED; /* No matching test */ } diff --git a/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_shrink.c b/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_shrink.c index b7448253d135..ca68c038357c 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_shrink.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_shrink.c @@ -12,14 +12,38 @@ SEC("xdp") int _xdp_adjust_tail_shrink(struct xdp_md *xdp) { - void *data_end = (void *)(long)xdp->data_end; - void *data = (void *)(long)xdp->data; + __u8 *data_end = (void *)(long)xdp->data_end; + __u8 *data = (void *)(long)xdp->data; int offset = 0; - if (data_end - data == 54) /* sizeof(pkt_v4) */ + switch (bpf_xdp_get_buff_len(xdp)) { + case 54: + /* sizeof(pkt_v4) */ offset = 256; /* shrink too much */ - else + break; + case 9000: + /* non-linear buff test cases */ + if (data + 1 > data_end) + return XDP_DROP; + + switch (data[0]) { + case 0: + offset = 10; + break; + case 1: + offset = 4100; + break; + case 2: + offset = 8200; + break; + default: + return XDP_DROP; + } + break; + default: offset = 20; + break; + } if (bpf_xdp_adjust_tail(xdp, 0 - offset)) return XDP_DROP; return XDP_TX; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_bpf2bpf.c b/tools/testing/selftests/bpf/progs/test_xdp_bpf2bpf.c index 58cf4345f5cc..3379d303f41a 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_bpf2bpf.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_bpf2bpf.c @@ -49,7 +49,7 @@ int BPF_PROG(trace_on_entry, struct xdp_buff *xdp) void *data = (void *)(long)xdp->data; meta.ifindex = xdp->rxq->dev->ifindex; - meta.pkt_len = data_end - data; + meta.pkt_len = bpf_xdp_get_buff_len((struct xdp_md *)xdp); bpf_xdp_output(xdp, &perf_buf_map, ((__u64) meta.pkt_len << 32) | BPF_F_CURRENT_CPU, diff --git a/tools/testing/selftests/bpf/progs/test_xdp_do_redirect.c b/tools/testing/selftests/bpf/progs/test_xdp_do_redirect.c new file mode 100644 index 000000000000..77a123071940 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_xdp_do_redirect.c @@ -0,0 +1,100 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <vmlinux.h> +#include <bpf/bpf_helpers.h> + +#define ETH_ALEN 6 +#define HDR_SZ (sizeof(struct ethhdr) + sizeof(struct ipv6hdr) + sizeof(struct udphdr)) +const volatile int ifindex_out; +const volatile int ifindex_in; +const volatile __u8 expect_dst[ETH_ALEN]; +volatile int pkts_seen_xdp = 0; +volatile int pkts_seen_zero = 0; +volatile int pkts_seen_tc = 0; +volatile int retcode = XDP_REDIRECT; + +SEC("xdp") +int xdp_redirect(struct xdp_md *xdp) +{ + __u32 *metadata = (void *)(long)xdp->data_meta; + void *data_end = (void *)(long)xdp->data_end; + void *data = (void *)(long)xdp->data; + + __u8 *payload = data + HDR_SZ; + int ret = retcode; + + if (payload + 1 > data_end) + return XDP_ABORTED; + + if (xdp->ingress_ifindex != ifindex_in) + return XDP_ABORTED; + + if (metadata + 1 > data) + return XDP_ABORTED; + + if (*metadata != 0x42) + return XDP_ABORTED; + + if (*payload == 0) { + *payload = 0x42; + pkts_seen_zero++; + } + + if (bpf_xdp_adjust_meta(xdp, 4)) + return XDP_ABORTED; + + if (retcode > XDP_PASS) + retcode--; + + if (ret == XDP_REDIRECT) + return bpf_redirect(ifindex_out, 0); + + return ret; +} + +static bool check_pkt(void *data, void *data_end) +{ + struct ipv6hdr *iph = data + sizeof(struct ethhdr); + __u8 *payload = data + HDR_SZ; + + if (payload + 1 > data_end) + return false; + + if (iph->nexthdr != IPPROTO_UDP || *payload != 0x42) + return false; + + /* reset the payload so the same packet doesn't get counted twice when + * it cycles back through the kernel path and out the dst veth + */ + *payload = 0; + return true; +} + +SEC("xdp") +int xdp_count_pkts(struct xdp_md *xdp) +{ + void *data = (void *)(long)xdp->data; + void *data_end = (void *)(long)xdp->data_end; + + if (check_pkt(data, data_end)) + pkts_seen_xdp++; + + /* Return XDP_DROP to make sure the data page is recycled, like when it + * exits a physical NIC. Recycled pages will be counted in the + * pkts_seen_zero counter above. + */ + return XDP_DROP; +} + +SEC("tc") +int tc_count_pkts(struct __sk_buff *skb) +{ + void *data = (void *)(long)skb->data; + void *data_end = (void *)(long)skb->data_end; + + if (check_pkt(data, data_end)) + pkts_seen_tc++; + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_link.c b/tools/testing/selftests/bpf/progs/test_xdp_link.c index ee7d6ac0f615..64ff32eaae92 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_link.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_link.c @@ -10,3 +10,9 @@ int xdp_handler(struct xdp_md *xdp) { return 0; } + +SEC("tc") +int tc_handler(struct __sk_buff *skb) +{ + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/test_xdp_update_frags.c b/tools/testing/selftests/bpf/progs/test_xdp_update_frags.c new file mode 100644 index 000000000000..2a3496d8e327 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_xdp_update_frags.c @@ -0,0 +1,42 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#include <linux/bpf.h> +#include <linux/if_ether.h> +#include <bpf/bpf_helpers.h> + +int _version SEC("version") = 1; + +SEC("xdp.frags") +int xdp_adjust_frags(struct xdp_md *xdp) +{ + __u8 *data_end = (void *)(long)xdp->data_end; + __u8 *data = (void *)(long)xdp->data; + __u8 val[16] = {}; + __u32 offset; + int err; + + if (data + sizeof(__u32) > data_end) + return XDP_DROP; + + offset = *(__u32 *)data; + err = bpf_xdp_load_bytes(xdp, offset, val, sizeof(val)); + if (err < 0) + return XDP_DROP; + + if (val[0] != 0xaa || val[15] != 0xaa) /* marker */ + return XDP_DROP; + + val[0] = 0xbb; /* update the marker */ + val[15] = 0xbb; + err = bpf_xdp_store_bytes(xdp, offset, val, sizeof(val)); + if (err < 0) + return XDP_DROP; + + return XDP_PASS; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_with_cpumap_frags_helpers.c b/tools/testing/selftests/bpf/progs/test_xdp_with_cpumap_frags_helpers.c new file mode 100644 index 000000000000..97ed625bb70a --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_xdp_with_cpumap_frags_helpers.c @@ -0,0 +1,27 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +#define IFINDEX_LO 1 + +struct { + __uint(type, BPF_MAP_TYPE_CPUMAP); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(struct bpf_cpumap_val)); + __uint(max_entries, 4); +} cpu_map SEC(".maps"); + +SEC("xdp/cpumap") +int xdp_dummy_cm(struct xdp_md *ctx) +{ + return XDP_PASS; +} + +SEC("xdp.frags/cpumap") +int xdp_dummy_cm_frags(struct xdp_md *ctx) +{ + return XDP_PASS; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_with_cpumap_helpers.c b/tools/testing/selftests/bpf/progs/test_xdp_with_cpumap_helpers.c index 532025057711..20ec6723df18 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_with_cpumap_helpers.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_with_cpumap_helpers.c @@ -24,7 +24,7 @@ int xdp_dummy_prog(struct xdp_md *ctx) return XDP_PASS; } -SEC("xdp_cpumap/dummy_cm") +SEC("xdp/cpumap") int xdp_dummy_cm(struct xdp_md *ctx) { if (ctx->ingress_ifindex == IFINDEX_LO) @@ -33,4 +33,10 @@ int xdp_dummy_cm(struct xdp_md *ctx) return XDP_PASS; } +SEC("xdp.frags/cpumap") +int xdp_dummy_cm_frags(struct xdp_md *ctx) +{ + return XDP_PASS; +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_frags_helpers.c b/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_frags_helpers.c new file mode 100644 index 000000000000..cdcf7de7ec8c --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_frags_helpers.c @@ -0,0 +1,27 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +struct { + __uint(type, BPF_MAP_TYPE_DEVMAP); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(struct bpf_devmap_val)); + __uint(max_entries, 4); +} dm_ports SEC(".maps"); + +/* valid program on DEVMAP entry via SEC name; + * has access to egress and ingress ifindex + */ +SEC("xdp/devmap") +int xdp_dummy_dm(struct xdp_md *ctx) +{ + return XDP_PASS; +} + +SEC("xdp.frags/devmap") +int xdp_dummy_dm_frags(struct xdp_md *ctx) +{ + return XDP_PASS; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_helpers.c b/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_helpers.c index 1e6b9c38ea6d..4139a14f9996 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_helpers.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_helpers.c @@ -27,7 +27,7 @@ int xdp_dummy_prog(struct xdp_md *ctx) /* valid program on DEVMAP entry via SEC name; * has access to egress and ingress ifindex */ -SEC("xdp_devmap/map_prog") +SEC("xdp/devmap") int xdp_dummy_dm(struct xdp_md *ctx) { char fmt[] = "devmap redirect: dev %u -> dev %u len %u\n"; @@ -40,4 +40,11 @@ int xdp_dummy_dm(struct xdp_md *ctx) return XDP_PASS; } + +SEC("xdp.frags/devmap") +int xdp_dummy_dm_frags(struct xdp_md *ctx) +{ + return XDP_PASS; +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/timer_crash.c b/tools/testing/selftests/bpf/progs/timer_crash.c new file mode 100644 index 000000000000..f8f7944e70da --- /dev/null +++ b/tools/testing/selftests/bpf/progs/timer_crash.c @@ -0,0 +1,54 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <vmlinux.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_helpers.h> + +struct map_elem { + struct bpf_timer timer; + struct bpf_spin_lock lock; +}; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, int); + __type(value, struct map_elem); +} amap SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 1); + __type(key, int); + __type(value, struct map_elem); +} hmap SEC(".maps"); + +int pid = 0; +int crash_map = 0; /* 0 for amap, 1 for hmap */ + +SEC("fentry/do_nanosleep") +int sys_enter(void *ctx) +{ + struct map_elem *e, value = {}; + void *map = crash_map ? (void *)&hmap : (void *)&amap; + + if (bpf_get_current_task_btf()->tgid != pid) + return 0; + + *(void **)&value = (void *)0xdeadcaf3; + + bpf_map_update_elem(map, &(int){0}, &value, 0); + /* For array map, doing bpf_map_update_elem will do a + * check_and_free_timer_in_array, which will trigger the crash if timer + * pointer was overwritten, for hmap we need to use bpf_timer_cancel. + */ + if (crash_map == 1) { + e = bpf_map_lookup_elem(map, &(int){0}); + if (!e) + return 0; + bpf_timer_cancel(&e->timer); + } + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/trace_printk.c b/tools/testing/selftests/bpf/progs/trace_printk.c index 119582aa105a..6695478c2b25 100644 --- a/tools/testing/selftests/bpf/progs/trace_printk.c +++ b/tools/testing/selftests/bpf/progs/trace_printk.c @@ -4,6 +4,7 @@ #include "vmlinux.h" #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> +#include "bpf_misc.h" char _license[] SEC("license") = "GPL"; @@ -12,7 +13,7 @@ int trace_printk_ran = 0; const char fmt[] = "Testing,testing %d\n"; -SEC("fentry/__x64_sys_nanosleep") +SEC("fentry/" SYS_PREFIX "sys_nanosleep") int sys_enter(void *ctx) { trace_printk_ret = bpf_trace_printk(fmt, sizeof(fmt), diff --git a/tools/testing/selftests/bpf/progs/trace_vprintk.c b/tools/testing/selftests/bpf/progs/trace_vprintk.c index d327241ba047..969306cd4f33 100644 --- a/tools/testing/selftests/bpf/progs/trace_vprintk.c +++ b/tools/testing/selftests/bpf/progs/trace_vprintk.c @@ -4,6 +4,7 @@ #include "vmlinux.h" #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> +#include "bpf_misc.h" char _license[] SEC("license") = "GPL"; @@ -11,7 +12,7 @@ int null_data_vprintk_ret = 0; int trace_vprintk_ret = 0; int trace_vprintk_ran = 0; -SEC("fentry/__x64_sys_nanosleep") +SEC("fentry/" SYS_PREFIX "sys_nanosleep") int sys_enter(void *ctx) { static const char one[] = "1"; diff --git a/tools/testing/selftests/bpf/progs/trigger_bench.c b/tools/testing/selftests/bpf/progs/trigger_bench.c index 2098f3f27f18..2ab049b54d6c 100644 --- a/tools/testing/selftests/bpf/progs/trigger_bench.c +++ b/tools/testing/selftests/bpf/progs/trigger_bench.c @@ -5,6 +5,7 @@ #include <asm/unistd.h> #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> +#include "bpf_misc.h" char _license[] SEC("license") = "GPL"; @@ -25,28 +26,28 @@ int BPF_PROG(bench_trigger_raw_tp, struct pt_regs *regs, long id) return 0; } -SEC("kprobe/__x64_sys_getpgid") +SEC("kprobe/" SYS_PREFIX "sys_getpgid") int bench_trigger_kprobe(void *ctx) { __sync_add_and_fetch(&hits, 1); return 0; } -SEC("fentry/__x64_sys_getpgid") +SEC("fentry/" SYS_PREFIX "sys_getpgid") int bench_trigger_fentry(void *ctx) { __sync_add_and_fetch(&hits, 1); return 0; } -SEC("fentry.s/__x64_sys_getpgid") +SEC("fentry.s/" SYS_PREFIX "sys_getpgid") int bench_trigger_fentry_sleep(void *ctx) { __sync_add_and_fetch(&hits, 1); return 0; } -SEC("fmod_ret/__x64_sys_getpgid") +SEC("fmod_ret/" SYS_PREFIX "sys_getpgid") int bench_trigger_fmodret(void *ctx) { __sync_add_and_fetch(&hits, 1); diff --git a/tools/testing/selftests/bpf/progs/xdp_redirect_multi_kern.c b/tools/testing/selftests/bpf/progs/xdp_redirect_multi_kern.c index 8395782b6e0a..97b26a30b59a 100644 --- a/tools/testing/selftests/bpf/progs/xdp_redirect_multi_kern.c +++ b/tools/testing/selftests/bpf/progs/xdp_redirect_multi_kern.c @@ -70,7 +70,7 @@ int xdp_redirect_map_all_prog(struct xdp_md *ctx) BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS); } -SEC("xdp_devmap/map_prog") +SEC("xdp/devmap") int xdp_devmap_prog(struct xdp_md *ctx) { void *data_end = (void *)(long)ctx->data_end; diff --git a/tools/testing/selftests/bpf/test_cgroup_storage.c b/tools/testing/selftests/bpf/test_cgroup_storage.c index 5b8314cd77fd..d6a1be4d8020 100644 --- a/tools/testing/selftests/bpf/test_cgroup_storage.c +++ b/tools/testing/selftests/bpf/test_cgroup_storage.c @@ -36,7 +36,7 @@ int main(int argc, char **argv) BPF_MOV64_REG(BPF_REG_0, BPF_REG_1), BPF_EXIT_INSN(), }; - size_t insns_cnt = sizeof(prog) / sizeof(struct bpf_insn); + size_t insns_cnt = ARRAY_SIZE(prog); int error = EXIT_FAILURE; int map_fd, percpu_map_fd, prog_fd, cgroup_fd; struct bpf_cgroup_storage_key key; diff --git a/tools/testing/selftests/bpf/test_cpp.cpp b/tools/testing/selftests/bpf/test_cpp.cpp index e00201de2890..19ad172036da 100644 --- a/tools/testing/selftests/bpf/test_cpp.cpp +++ b/tools/testing/selftests/bpf/test_cpp.cpp @@ -1,22 +1,107 @@ /* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ #include <iostream> +#pragma GCC diagnostic push +#pragma GCC diagnostic ignored "-Wdeprecated-declarations" #include <bpf/libbpf.h> +#pragma GCC diagnostic pop #include <bpf/bpf.h> #include <bpf/btf.h> #include "test_core_extern.skel.h" -/* do nothing, just make sure we can link successfully */ +template <typename T> +class Skeleton { +private: + T *skel; +public: + Skeleton(): skel(nullptr) { } + + ~Skeleton() { if (skel) T::destroy(skel); } + + int open(const struct bpf_object_open_opts *opts = nullptr) + { + int err; + + if (skel) + return -EBUSY; + + skel = T::open(opts); + err = libbpf_get_error(skel); + if (err) { + skel = nullptr; + return err; + } + + return 0; + } + + int load() { return T::load(skel); } + + int attach() { return T::attach(skel); } + + void detach() { return T::detach(skel); } + + const T* operator->() const { return skel; } + + T* operator->() { return skel; } + + const T *get() const { return skel; } +}; static void dump_printf(void *ctx, const char *fmt, va_list args) { } +static void try_skeleton_template() +{ + Skeleton<test_core_extern> skel; + std::string prog_name; + int err; + LIBBPF_OPTS(bpf_object_open_opts, opts); + + err = skel.open(&opts); + if (err) { + fprintf(stderr, "Skeleton open failed: %d\n", err); + return; + } + + skel->data->kern_ver = 123; + skel->data->int_val = skel->data->ushort_val; + + err = skel.load(); + if (err) { + fprintf(stderr, "Skeleton load failed: %d\n", err); + return; + } + + if (!skel->kconfig->CONFIG_BPF_SYSCALL) + fprintf(stderr, "Seems like CONFIG_BPF_SYSCALL isn't set?!\n"); + + err = skel.attach(); + if (err) { + fprintf(stderr, "Skeleton attach failed: %d\n", err); + return; + } + + prog_name = bpf_program__name(skel->progs.handle_sys_enter); + if (prog_name != "handle_sys_enter") + fprintf(stderr, "Unexpected program name: %s\n", prog_name.c_str()); + + bpf_link__destroy(skel->links.handle_sys_enter); + skel->links.handle_sys_enter = bpf_program__attach(skel->progs.handle_sys_enter); + + skel.detach(); + + /* destructor will destory underlying skeleton */ +} + int main(int argc, char *argv[]) { struct btf_dump_opts opts = { }; struct test_core_extern *skel; struct btf *btf; + try_skeleton_template(); + /* libbpf.h */ libbpf_set_print(NULL); @@ -25,7 +110,8 @@ int main(int argc, char *argv[]) /* btf.h */ btf = btf__new(NULL, 0); - btf_dump__new(btf, dump_printf, nullptr, &opts); + if (!libbpf_get_error(btf)) + btf_dump__new(btf, dump_printf, nullptr, &opts); /* BPF skeleton */ skel = test_core_extern__open_and_load(); diff --git a/tools/testing/selftests/bpf/test_lirc_mode2.sh b/tools/testing/selftests/bpf/test_lirc_mode2.sh index ec4e15948e40..5252b91f48a1 100755 --- a/tools/testing/selftests/bpf/test_lirc_mode2.sh +++ b/tools/testing/selftests/bpf/test_lirc_mode2.sh @@ -3,6 +3,7 @@ # Kselftest framework requirement - SKIP code is 4. ksft_skip=4 +ret=$ksft_skip msg="skip all tests:" if [ $UID != 0 ]; then @@ -25,7 +26,7 @@ do fi done -if [ -n $LIRCDEV ]; +if [ -n "$LIRCDEV" ]; then TYPE=lirc_mode2 ./test_lirc_mode2_user $LIRCDEV $INPUTDEV @@ -36,3 +37,5 @@ then echo -e ${GREEN}"PASS: $TYPE"${NC} fi fi + +exit $ret diff --git a/tools/testing/selftests/bpf/test_lirc_mode2_user.c b/tools/testing/selftests/bpf/test_lirc_mode2_user.c index ebf68dce5504..2893e9f2f1e0 100644 --- a/tools/testing/selftests/bpf/test_lirc_mode2_user.c +++ b/tools/testing/selftests/bpf/test_lirc_mode2_user.c @@ -28,7 +28,6 @@ // 5. We can read keycode from same /dev/lirc device #include <linux/bpf.h> -#include <linux/lirc.h> #include <linux/input.h> #include <errno.h> #include <stdio.h> diff --git a/tools/testing/selftests/bpf/test_lru_map.c b/tools/testing/selftests/bpf/test_lru_map.c index b9f1bbbc8aba..563bbe18c172 100644 --- a/tools/testing/selftests/bpf/test_lru_map.c +++ b/tools/testing/selftests/bpf/test_lru_map.c @@ -61,7 +61,11 @@ static int bpf_map_lookup_elem_with_ref_bit(int fd, unsigned long long key, }; __u8 data[64] = {}; int mfd, pfd, ret, zero = 0; - __u32 retval = 0; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = data, + .data_size_in = sizeof(data), + .repeat = 1, + ); mfd = bpf_map_create(BPF_MAP_TYPE_ARRAY, NULL, sizeof(int), sizeof(__u64), 1, NULL); if (mfd < 0) @@ -75,9 +79,8 @@ static int bpf_map_lookup_elem_with_ref_bit(int fd, unsigned long long key, return -1; } - ret = bpf_prog_test_run(pfd, 1, data, sizeof(data), - NULL, NULL, &retval, NULL); - if (ret < 0 || retval != 42) { + ret = bpf_prog_test_run_opts(pfd, &topts); + if (ret < 0 || topts.retval != 42) { ret = -1; } else { assert(!bpf_map_lookup_elem(mfd, &zero, value)); @@ -875,11 +878,11 @@ int main(int argc, char **argv) assert(nr_cpus != -1); printf("nr_cpus:%d\n\n", nr_cpus); - for (f = 0; f < sizeof(map_flags) / sizeof(*map_flags); f++) { + for (f = 0; f < ARRAY_SIZE(map_flags); f++) { unsigned int tgt_free = (map_flags[f] & BPF_F_NO_COMMON_LRU) ? PERCPU_FREE_TARGET : LOCAL_FREE_TARGET; - for (t = 0; t < sizeof(map_types) / sizeof(*map_types); t++) { + for (t = 0; t < ARRAY_SIZE(map_types); t++) { test_lru_sanity0(map_types[t], map_flags[f]); test_lru_sanity1(map_types[t], map_flags[f], tgt_free); test_lru_sanity2(map_types[t], map_flags[f], tgt_free); diff --git a/tools/testing/selftests/bpf/test_lwt_ip_encap.sh b/tools/testing/selftests/bpf/test_lwt_ip_encap.sh index b497bb85b667..6c69c42b1d60 100755 --- a/tools/testing/selftests/bpf/test_lwt_ip_encap.sh +++ b/tools/testing/selftests/bpf/test_lwt_ip_encap.sh @@ -120,6 +120,14 @@ setup() ip netns exec ${NS2} sysctl -wq net.ipv4.conf.default.rp_filter=0 ip netns exec ${NS3} sysctl -wq net.ipv4.conf.default.rp_filter=0 + # disable IPv6 DAD because it sometimes takes too long and fails tests + ip netns exec ${NS1} sysctl -wq net.ipv6.conf.all.accept_dad=0 + ip netns exec ${NS2} sysctl -wq net.ipv6.conf.all.accept_dad=0 + ip netns exec ${NS3} sysctl -wq net.ipv6.conf.all.accept_dad=0 + ip netns exec ${NS1} sysctl -wq net.ipv6.conf.default.accept_dad=0 + ip netns exec ${NS2} sysctl -wq net.ipv6.conf.default.accept_dad=0 + ip netns exec ${NS3} sysctl -wq net.ipv6.conf.default.accept_dad=0 + ip link add veth1 type veth peer name veth2 ip link add veth3 type veth peer name veth4 ip link add veth5 type veth peer name veth6 @@ -289,7 +297,7 @@ test_ping() ip netns exec ${NS1} ping -c 1 -W 1 -I veth1 ${IPv4_DST} 2>&1 > /dev/null RET=$? elif [ "${PROTO}" == "IPv6" ] ; then - ip netns exec ${NS1} ping6 -c 1 -W 6 -I veth1 ${IPv6_DST} 2>&1 > /dev/null + ip netns exec ${NS1} ping6 -c 1 -W 1 -I veth1 ${IPv6_DST} 2>&1 > /dev/null RET=$? else echo " test_ping: unknown PROTO: ${PROTO}" diff --git a/tools/testing/selftests/bpf/test_lwt_seg6local.sh b/tools/testing/selftests/bpf/test_lwt_seg6local.sh index 5620919fde9e..826f4423ce02 100755 --- a/tools/testing/selftests/bpf/test_lwt_seg6local.sh +++ b/tools/testing/selftests/bpf/test_lwt_seg6local.sh @@ -23,6 +23,12 @@ # Kselftest framework requirement - SKIP code is 4. ksft_skip=4 +readonly NS1="ns1-$(mktemp -u XXXXXX)" +readonly NS2="ns2-$(mktemp -u XXXXXX)" +readonly NS3="ns3-$(mktemp -u XXXXXX)" +readonly NS4="ns4-$(mktemp -u XXXXXX)" +readonly NS5="ns5-$(mktemp -u XXXXXX)" +readonly NS6="ns6-$(mktemp -u XXXXXX)" msg="skip all tests:" if [ $UID != 0 ]; then @@ -41,23 +47,23 @@ cleanup() fi set +e - ip netns del ns1 2> /dev/null - ip netns del ns2 2> /dev/null - ip netns del ns3 2> /dev/null - ip netns del ns4 2> /dev/null - ip netns del ns5 2> /dev/null - ip netns del ns6 2> /dev/null + ip netns del ${NS1} 2> /dev/null + ip netns del ${NS2} 2> /dev/null + ip netns del ${NS3} 2> /dev/null + ip netns del ${NS4} 2> /dev/null + ip netns del ${NS5} 2> /dev/null + ip netns del ${NS6} 2> /dev/null rm -f $TMP_FILE } set -e -ip netns add ns1 -ip netns add ns2 -ip netns add ns3 -ip netns add ns4 -ip netns add ns5 -ip netns add ns6 +ip netns add ${NS1} +ip netns add ${NS2} +ip netns add ${NS3} +ip netns add ${NS4} +ip netns add ${NS5} +ip netns add ${NS6} trap cleanup 0 2 3 6 9 @@ -67,78 +73,78 @@ ip link add veth5 type veth peer name veth6 ip link add veth7 type veth peer name veth8 ip link add veth9 type veth peer name veth10 -ip link set veth1 netns ns1 -ip link set veth2 netns ns2 -ip link set veth3 netns ns2 -ip link set veth4 netns ns3 -ip link set veth5 netns ns3 -ip link set veth6 netns ns4 -ip link set veth7 netns ns4 -ip link set veth8 netns ns5 -ip link set veth9 netns ns5 -ip link set veth10 netns ns6 - -ip netns exec ns1 ip link set dev veth1 up -ip netns exec ns2 ip link set dev veth2 up -ip netns exec ns2 ip link set dev veth3 up -ip netns exec ns3 ip link set dev veth4 up -ip netns exec ns3 ip link set dev veth5 up -ip netns exec ns4 ip link set dev veth6 up -ip netns exec ns4 ip link set dev veth7 up -ip netns exec ns5 ip link set dev veth8 up -ip netns exec ns5 ip link set dev veth9 up -ip netns exec ns6 ip link set dev veth10 up -ip netns exec ns6 ip link set dev lo up +ip link set veth1 netns ${NS1} +ip link set veth2 netns ${NS2} +ip link set veth3 netns ${NS2} +ip link set veth4 netns ${NS3} +ip link set veth5 netns ${NS3} +ip link set veth6 netns ${NS4} +ip link set veth7 netns ${NS4} +ip link set veth8 netns ${NS5} +ip link set veth9 netns ${NS5} +ip link set veth10 netns ${NS6} + +ip netns exec ${NS1} ip link set dev veth1 up +ip netns exec ${NS2} ip link set dev veth2 up +ip netns exec ${NS2} ip link set dev veth3 up +ip netns exec ${NS3} ip link set dev veth4 up +ip netns exec ${NS3} ip link set dev veth5 up +ip netns exec ${NS4} ip link set dev veth6 up +ip netns exec ${NS4} ip link set dev veth7 up +ip netns exec ${NS5} ip link set dev veth8 up +ip netns exec ${NS5} ip link set dev veth9 up +ip netns exec ${NS6} ip link set dev veth10 up +ip netns exec ${NS6} ip link set dev lo up # All link scope addresses and routes required between veths -ip netns exec ns1 ip -6 addr add fb00::12/16 dev veth1 scope link -ip netns exec ns1 ip -6 route add fb00::21 dev veth1 scope link -ip netns exec ns2 ip -6 addr add fb00::21/16 dev veth2 scope link -ip netns exec ns2 ip -6 addr add fb00::34/16 dev veth3 scope link -ip netns exec ns2 ip -6 route add fb00::43 dev veth3 scope link -ip netns exec ns3 ip -6 route add fb00::65 dev veth5 scope link -ip netns exec ns3 ip -6 addr add fb00::43/16 dev veth4 scope link -ip netns exec ns3 ip -6 addr add fb00::56/16 dev veth5 scope link -ip netns exec ns4 ip -6 addr add fb00::65/16 dev veth6 scope link -ip netns exec ns4 ip -6 addr add fb00::78/16 dev veth7 scope link -ip netns exec ns4 ip -6 route add fb00::87 dev veth7 scope link -ip netns exec ns5 ip -6 addr add fb00::87/16 dev veth8 scope link -ip netns exec ns5 ip -6 addr add fb00::910/16 dev veth9 scope link -ip netns exec ns5 ip -6 route add fb00::109 dev veth9 scope link -ip netns exec ns5 ip -6 route add fb00::109 table 117 dev veth9 scope link -ip netns exec ns6 ip -6 addr add fb00::109/16 dev veth10 scope link - -ip netns exec ns1 ip -6 addr add fb00::1/16 dev lo -ip netns exec ns1 ip -6 route add fb00::6 dev veth1 via fb00::21 - -ip netns exec ns2 ip -6 route add fb00::6 encap bpf in obj test_lwt_seg6local.o sec encap_srh dev veth2 -ip netns exec ns2 ip -6 route add fd00::1 dev veth3 via fb00::43 scope link - -ip netns exec ns3 ip -6 route add fc42::1 dev veth5 via fb00::65 -ip netns exec ns3 ip -6 route add fd00::1 encap seg6local action End.BPF endpoint obj test_lwt_seg6local.o sec add_egr_x dev veth4 - -ip netns exec ns4 ip -6 route add fd00::2 encap seg6local action End.BPF endpoint obj test_lwt_seg6local.o sec pop_egr dev veth6 -ip netns exec ns4 ip -6 addr add fc42::1 dev lo -ip netns exec ns4 ip -6 route add fd00::3 dev veth7 via fb00::87 - -ip netns exec ns5 ip -6 route add fd00::4 table 117 dev veth9 via fb00::109 -ip netns exec ns5 ip -6 route add fd00::3 encap seg6local action End.BPF endpoint obj test_lwt_seg6local.o sec inspect_t dev veth8 - -ip netns exec ns6 ip -6 addr add fb00::6/16 dev lo -ip netns exec ns6 ip -6 addr add fd00::4/16 dev lo - -ip netns exec ns1 sysctl net.ipv6.conf.all.forwarding=1 > /dev/null -ip netns exec ns2 sysctl net.ipv6.conf.all.forwarding=1 > /dev/null -ip netns exec ns3 sysctl net.ipv6.conf.all.forwarding=1 > /dev/null -ip netns exec ns4 sysctl net.ipv6.conf.all.forwarding=1 > /dev/null -ip netns exec ns5 sysctl net.ipv6.conf.all.forwarding=1 > /dev/null - -ip netns exec ns6 sysctl net.ipv6.conf.all.seg6_enabled=1 > /dev/null -ip netns exec ns6 sysctl net.ipv6.conf.lo.seg6_enabled=1 > /dev/null -ip netns exec ns6 sysctl net.ipv6.conf.veth10.seg6_enabled=1 > /dev/null - -ip netns exec ns6 nc -l -6 -u -d 7330 > $TMP_FILE & -ip netns exec ns1 bash -c "echo 'foobar' | nc -w0 -6 -u -p 2121 -s fb00::1 fb00::6 7330" +ip netns exec ${NS1} ip -6 addr add fb00::12/16 dev veth1 scope link +ip netns exec ${NS1} ip -6 route add fb00::21 dev veth1 scope link +ip netns exec ${NS2} ip -6 addr add fb00::21/16 dev veth2 scope link +ip netns exec ${NS2} ip -6 addr add fb00::34/16 dev veth3 scope link +ip netns exec ${NS2} ip -6 route add fb00::43 dev veth3 scope link +ip netns exec ${NS3} ip -6 route add fb00::65 dev veth5 scope link +ip netns exec ${NS3} ip -6 addr add fb00::43/16 dev veth4 scope link +ip netns exec ${NS3} ip -6 addr add fb00::56/16 dev veth5 scope link +ip netns exec ${NS4} ip -6 addr add fb00::65/16 dev veth6 scope link +ip netns exec ${NS4} ip -6 addr add fb00::78/16 dev veth7 scope link +ip netns exec ${NS4} ip -6 route add fb00::87 dev veth7 scope link +ip netns exec ${NS5} ip -6 addr add fb00::87/16 dev veth8 scope link +ip netns exec ${NS5} ip -6 addr add fb00::910/16 dev veth9 scope link +ip netns exec ${NS5} ip -6 route add fb00::109 dev veth9 scope link +ip netns exec ${NS5} ip -6 route add fb00::109 table 117 dev veth9 scope link +ip netns exec ${NS6} ip -6 addr add fb00::109/16 dev veth10 scope link + +ip netns exec ${NS1} ip -6 addr add fb00::1/16 dev lo +ip netns exec ${NS1} ip -6 route add fb00::6 dev veth1 via fb00::21 + +ip netns exec ${NS2} ip -6 route add fb00::6 encap bpf in obj test_lwt_seg6local.o sec encap_srh dev veth2 +ip netns exec ${NS2} ip -6 route add fd00::1 dev veth3 via fb00::43 scope link + +ip netns exec ${NS3} ip -6 route add fc42::1 dev veth5 via fb00::65 +ip netns exec ${NS3} ip -6 route add fd00::1 encap seg6local action End.BPF endpoint obj test_lwt_seg6local.o sec add_egr_x dev veth4 + +ip netns exec ${NS4} ip -6 route add fd00::2 encap seg6local action End.BPF endpoint obj test_lwt_seg6local.o sec pop_egr dev veth6 +ip netns exec ${NS4} ip -6 addr add fc42::1 dev lo +ip netns exec ${NS4} ip -6 route add fd00::3 dev veth7 via fb00::87 + +ip netns exec ${NS5} ip -6 route add fd00::4 table 117 dev veth9 via fb00::109 +ip netns exec ${NS5} ip -6 route add fd00::3 encap seg6local action End.BPF endpoint obj test_lwt_seg6local.o sec inspect_t dev veth8 + +ip netns exec ${NS6} ip -6 addr add fb00::6/16 dev lo +ip netns exec ${NS6} ip -6 addr add fd00::4/16 dev lo + +ip netns exec ${NS1} sysctl net.ipv6.conf.all.forwarding=1 > /dev/null +ip netns exec ${NS2} sysctl net.ipv6.conf.all.forwarding=1 > /dev/null +ip netns exec ${NS3} sysctl net.ipv6.conf.all.forwarding=1 > /dev/null +ip netns exec ${NS4} sysctl net.ipv6.conf.all.forwarding=1 > /dev/null +ip netns exec ${NS5} sysctl net.ipv6.conf.all.forwarding=1 > /dev/null + +ip netns exec ${NS6} sysctl net.ipv6.conf.all.seg6_enabled=1 > /dev/null +ip netns exec ${NS6} sysctl net.ipv6.conf.lo.seg6_enabled=1 > /dev/null +ip netns exec ${NS6} sysctl net.ipv6.conf.veth10.seg6_enabled=1 > /dev/null + +ip netns exec ${NS6} nc -l -6 -u -d 7330 > $TMP_FILE & +ip netns exec ${NS1} bash -c "echo 'foobar' | nc -w0 -6 -u -p 2121 -s fb00::1 fb00::6 7330" sleep 5 # wait enough time to ensure the UDP datagram arrived to the last segment kill -TERM $! diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c index 50f7e74ca0b9..cbebfaa7c1e8 100644 --- a/tools/testing/selftests/bpf/test_maps.c +++ b/tools/testing/selftests/bpf/test_maps.c @@ -738,7 +738,7 @@ static void test_sockmap(unsigned int tasks, void *data) sizeof(key), sizeof(value), 6, NULL); if (fd < 0) { - if (!bpf_probe_map_type(BPF_MAP_TYPE_SOCKMAP, 0)) { + if (!libbpf_probe_bpf_map_type(BPF_MAP_TYPE_SOCKMAP, NULL)) { printf("%s SKIP (unsupported map type BPF_MAP_TYPE_SOCKMAP)\n", __func__); skips++; diff --git a/tools/testing/selftests/bpf/test_sock_addr.c b/tools/testing/selftests/bpf/test_sock_addr.c index f0c8d05ba6d1..f3d5d7ac6505 100644 --- a/tools/testing/selftests/bpf/test_sock_addr.c +++ b/tools/testing/selftests/bpf/test_sock_addr.c @@ -723,7 +723,7 @@ static int xmsg_ret_only_prog_load(const struct sock_addr_test *test, BPF_MOV64_IMM(BPF_REG_0, rc), BPF_EXIT_INSN(), }; - return load_insns(test, insns, sizeof(insns) / sizeof(struct bpf_insn)); + return load_insns(test, insns, ARRAY_SIZE(insns)); } static int sendmsg_allow_prog_load(const struct sock_addr_test *test) @@ -795,7 +795,7 @@ static int sendmsg4_rw_asm_prog_load(const struct sock_addr_test *test) BPF_EXIT_INSN(), }; - return load_insns(test, insns, sizeof(insns) / sizeof(struct bpf_insn)); + return load_insns(test, insns, ARRAY_SIZE(insns)); } static int recvmsg4_rw_c_prog_load(const struct sock_addr_test *test) @@ -858,7 +858,7 @@ static int sendmsg6_rw_dst_asm_prog_load(const struct sock_addr_test *test, BPF_EXIT_INSN(), }; - return load_insns(test, insns, sizeof(insns) / sizeof(struct bpf_insn)); + return load_insns(test, insns, ARRAY_SIZE(insns)); } static int sendmsg6_rw_asm_prog_load(const struct sock_addr_test *test) diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c index 1ba7e7346afb..dfb4f5c0fcb9 100644 --- a/tools/testing/selftests/bpf/test_sockmap.c +++ b/tools/testing/selftests/bpf/test_sockmap.c @@ -1786,7 +1786,7 @@ static int populate_progs(char *bpf_file) i++; } - for (i = 0; i < sizeof(map_fd)/sizeof(int); i++) { + for (i = 0; i < ARRAY_SIZE(map_fd); i++) { maps[i] = bpf_object__find_map_by_name(obj, map_names[i]); map_fd[i] = bpf_map__fd(maps[i]); if (map_fd[i] < 0) { @@ -1867,7 +1867,7 @@ static int __test_selftests(int cg_fd, struct sockmap_options *opt) } /* Tests basic commands and APIs */ - for (i = 0; i < sizeof(test)/sizeof(struct _test); i++) { + for (i = 0; i < ARRAY_SIZE(test); i++) { struct _test t = test[i]; if (check_whitelist(&t, opt) != 0) diff --git a/tools/testing/selftests/bpf/test_tcp_check_syncookie.sh b/tools/testing/selftests/bpf/test_tcp_check_syncookie.sh index 6413c1472554..102e6588e2fe 100755 --- a/tools/testing/selftests/bpf/test_tcp_check_syncookie.sh +++ b/tools/testing/selftests/bpf/test_tcp_check_syncookie.sh @@ -4,6 +4,7 @@ # Copyright (c) 2019 Cloudflare set -eu +readonly NS1="ns1-$(mktemp -u XXXXXX)" wait_for_ip() { @@ -28,12 +29,12 @@ get_prog_id() ns1_exec() { - ip netns exec ns1 "$@" + ip netns exec ${NS1} "$@" } setup() { - ip netns add ns1 + ip netns add ${NS1} ns1_exec ip link set lo up ns1_exec sysctl -w net.ipv4.tcp_syncookies=2 diff --git a/tools/testing/selftests/bpf/test_tunnel.sh b/tools/testing/selftests/bpf/test_tunnel.sh index ca1372924023..2817d9948d59 100755 --- a/tools/testing/selftests/bpf/test_tunnel.sh +++ b/tools/testing/selftests/bpf/test_tunnel.sh @@ -39,7 +39,7 @@ # from root namespace, the following operations happen: # 1) Route lookup shows 10.1.1.100/24 belongs to tnl dev, fwd to tnl dev. # 2) Tnl device's egress BPF program is triggered and set the tunnel metadata, -# with remote_ip=172.16.1.200 and others. +# with remote_ip=172.16.1.100 and others. # 3) Outer tunnel header is prepended and route the packet to veth1's egress # 4) veth0's ingress queue receive the tunneled packet at namespace at_ns0 # 5) Tunnel protocol handler, ex: vxlan_rcv, decap the packet diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index 76cd903117af..a2cd236c32eb 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -22,8 +22,6 @@ #include <limits.h> #include <assert.h> -#include <sys/capability.h> - #include <linux/unistd.h> #include <linux/filter.h> #include <linux/bpf_perf_event.h> @@ -31,6 +29,7 @@ #include <linux/if_ether.h> #include <linux/btf.h> +#include <bpf/btf.h> #include <bpf/bpf.h> #include <bpf/libbpf.h> @@ -41,6 +40,7 @@ # define CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS 1 # endif #endif +#include "cap_helpers.h" #include "bpf_rand.h" #include "bpf_util.h" #include "test_btf.h" @@ -61,11 +61,20 @@ #define F_NEEDS_EFFICIENT_UNALIGNED_ACCESS (1 << 0) #define F_LOAD_WITH_STRICT_ALIGNMENT (1 << 1) +/* need CAP_BPF, CAP_NET_ADMIN, CAP_PERFMON to load progs */ +#define ADMIN_CAPS (1ULL << CAP_NET_ADMIN | \ + 1ULL << CAP_PERFMON | \ + 1ULL << CAP_BPF) #define UNPRIV_SYSCTL "kernel/unprivileged_bpf_disabled" static bool unpriv_disabled = false; static int skips; static bool verbose = false; +struct kfunc_btf_id_pair { + const char *kfunc; + int insn_idx; +}; + struct bpf_test { const char *descr; struct bpf_insn insns[MAX_INSNS]; @@ -92,6 +101,7 @@ struct bpf_test { int fixup_map_reuseport_array[MAX_FIXUPS]; int fixup_map_ringbuf[MAX_FIXUPS]; int fixup_map_timer[MAX_FIXUPS]; + struct kfunc_btf_id_pair fixup_kfunc_btf_id[MAX_FIXUPS]; /* Expected verifier log output for result REJECT or VERBOSE_ACCEPT. * Can be a tab-separated sequence of expected strings. An empty string * means no log verification. @@ -449,7 +459,7 @@ static int probe_filter_length(const struct bpf_insn *fp) static bool skip_unsupported_map(enum bpf_map_type map_type) { - if (!bpf_probe_map_type(map_type, 0)) { + if (!libbpf_probe_bpf_map_type(map_type, NULL)) { printf("SKIP (unsupported map type %d)\n", map_type); skips++; return true; @@ -744,6 +754,7 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type, int *fixup_map_reuseport_array = test->fixup_map_reuseport_array; int *fixup_map_ringbuf = test->fixup_map_ringbuf; int *fixup_map_timer = test->fixup_map_timer; + struct kfunc_btf_id_pair *fixup_kfunc_btf_id = test->fixup_kfunc_btf_id; if (test->fill_helper) { test->fill_insns = calloc(MAX_TEST_INSNS, sizeof(struct bpf_insn)); @@ -936,6 +947,26 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type, fixup_map_timer++; } while (*fixup_map_timer); } + + /* Patch in kfunc BTF IDs */ + if (fixup_kfunc_btf_id->kfunc) { + struct btf *btf; + int btf_id; + + do { + btf_id = 0; + btf = btf__load_vmlinux_btf(); + if (btf) { + btf_id = btf__find_by_name_kind(btf, + fixup_kfunc_btf_id->kfunc, + BTF_KIND_FUNC); + btf_id = btf_id < 0 ? 0 : btf_id; + } + btf__free(btf); + prog[fixup_kfunc_btf_id->insn_idx].imm = btf_id; + fixup_kfunc_btf_id++; + } while (fixup_kfunc_btf_id->kfunc); + } } struct libcap { @@ -945,47 +976,19 @@ struct libcap { static int set_admin(bool admin) { - cap_t caps; - /* need CAP_BPF, CAP_NET_ADMIN, CAP_PERFMON to load progs */ - const cap_value_t cap_net_admin = CAP_NET_ADMIN; - const cap_value_t cap_sys_admin = CAP_SYS_ADMIN; - struct libcap *cap; - int ret = -1; - - caps = cap_get_proc(); - if (!caps) { - perror("cap_get_proc"); - return -1; - } - cap = (struct libcap *)caps; - if (cap_set_flag(caps, CAP_EFFECTIVE, 1, &cap_sys_admin, CAP_CLEAR)) { - perror("cap_set_flag clear admin"); - goto out; - } - if (cap_set_flag(caps, CAP_EFFECTIVE, 1, &cap_net_admin, - admin ? CAP_SET : CAP_CLEAR)) { - perror("cap_set_flag set_or_clear net"); - goto out; - } - /* libcap is likely old and simply ignores CAP_BPF and CAP_PERFMON, - * so update effective bits manually - */ + int err; + if (admin) { - cap->data[1].effective |= 1 << (38 /* CAP_PERFMON */ - 32); - cap->data[1].effective |= 1 << (39 /* CAP_BPF */ - 32); + err = cap_enable_effective(ADMIN_CAPS, NULL); + if (err) + perror("cap_enable_effective(ADMIN_CAPS)"); } else { - cap->data[1].effective &= ~(1 << (38 - 32)); - cap->data[1].effective &= ~(1 << (39 - 32)); + err = cap_disable_effective(ADMIN_CAPS, NULL); + if (err) + perror("cap_disable_effective(ADMIN_CAPS)"); } - if (cap_set_proc(caps)) { - perror("cap_set_proc"); - goto out; - } - ret = 0; -out: - if (cap_free(caps)) - perror("cap_free"); - return ret; + + return err; } static int do_prog_test_run(int fd_prog, bool unpriv, uint32_t expected_val, @@ -993,13 +996,18 @@ static int do_prog_test_run(int fd_prog, bool unpriv, uint32_t expected_val, { __u8 tmp[TEST_DATA_LEN << 2]; __u32 size_tmp = sizeof(tmp); - uint32_t retval; int err, saved_errno; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = data, + .data_size_in = size_data, + .data_out = tmp, + .data_size_out = size_tmp, + .repeat = 1, + ); if (unpriv) set_admin(true); - err = bpf_prog_test_run(fd_prog, 1, data, size_data, - tmp, &size_tmp, &retval, NULL); + err = bpf_prog_test_run_opts(fd_prog, &topts); saved_errno = errno; if (unpriv) @@ -1023,9 +1031,8 @@ static int do_prog_test_run(int fd_prog, bool unpriv, uint32_t expected_val, } } - if (retval != expected_val && - expected_val != POINTER_VALUE) { - printf("FAIL retval %d != %d ", retval, expected_val); + if (topts.retval != expected_val && expected_val != POINTER_VALUE) { + printf("FAIL retval %d != %d ", topts.retval, expected_val); return 1; } @@ -1148,7 +1155,7 @@ static void do_test_single(struct bpf_test *test, bool unpriv, * bpf_probe_prog_type won't give correct answer */ if (fd_prog < 0 && prog_type != BPF_PROG_TYPE_TRACING && - !bpf_probe_prog_type(prog_type, 0)) { + !libbpf_probe_bpf_prog_type(prog_type, NULL)) { printf("SKIP (unsupported program type %d)\n", prog_type); skips++; goto close_fds; @@ -1259,31 +1266,18 @@ fail_log: static bool is_admin(void) { - cap_flag_value_t net_priv = CAP_CLEAR; - bool perfmon_priv = false; - bool bpf_priv = false; - struct libcap *cap; - cap_t caps; - -#ifdef CAP_IS_SUPPORTED - if (!CAP_IS_SUPPORTED(CAP_SETFCAP)) { - perror("cap_get_flag"); - return false; - } -#endif - caps = cap_get_proc(); - if (!caps) { - perror("cap_get_proc"); + __u64 caps; + + /* The test checks for finer cap as CAP_NET_ADMIN, + * CAP_PERFMON, and CAP_BPF instead of CAP_SYS_ADMIN. + * Thus, disable CAP_SYS_ADMIN at the beginning. + */ + if (cap_disable_effective(1ULL << CAP_SYS_ADMIN, &caps)) { + perror("cap_disable_effective(CAP_SYS_ADMIN)"); return false; } - cap = (struct libcap *)caps; - bpf_priv = cap->data[1].effective & (1 << (39/* CAP_BPF */ - 32)); - perfmon_priv = cap->data[1].effective & (1 << (38/* CAP_PERFMON */ - 32)); - if (cap_get_flag(caps, CAP_NET_ADMIN, CAP_EFFECTIVE, &net_priv)) - perror("cap_get_flag NET"); - if (cap_free(caps)) - perror("cap_free"); - return bpf_priv && perfmon_priv && net_priv == CAP_SET; + + return (caps & ADMIN_CAPS) == ADMIN_CAPS; } static void get_unpriv_disabled() diff --git a/tools/testing/selftests/bpf/test_xdp_meta.sh b/tools/testing/selftests/bpf/test_xdp_meta.sh index d10cefd6eb09..ea69370caae3 100755 --- a/tools/testing/selftests/bpf/test_xdp_meta.sh +++ b/tools/testing/selftests/bpf/test_xdp_meta.sh @@ -2,6 +2,8 @@ # Kselftest framework requirement - SKIP code is 4. readonly KSFT_SKIP=4 +readonly NS1="ns1-$(mktemp -u XXXXXX)" +readonly NS2="ns2-$(mktemp -u XXXXXX)" cleanup() { @@ -13,8 +15,8 @@ cleanup() set +e ip link del veth1 2> /dev/null - ip netns del ns1 2> /dev/null - ip netns del ns2 2> /dev/null + ip netns del ${NS1} 2> /dev/null + ip netns del ${NS2} 2> /dev/null } ip link set dev lo xdp off 2>/dev/null > /dev/null @@ -24,32 +26,32 @@ if [ $? -ne 0 ];then fi set -e -ip netns add ns1 -ip netns add ns2 +ip netns add ${NS1} +ip netns add ${NS2} trap cleanup 0 2 3 6 9 ip link add veth1 type veth peer name veth2 -ip link set veth1 netns ns1 -ip link set veth2 netns ns2 +ip link set veth1 netns ${NS1} +ip link set veth2 netns ${NS2} -ip netns exec ns1 ip addr add 10.1.1.11/24 dev veth1 -ip netns exec ns2 ip addr add 10.1.1.22/24 dev veth2 +ip netns exec ${NS1} ip addr add 10.1.1.11/24 dev veth1 +ip netns exec ${NS2} ip addr add 10.1.1.22/24 dev veth2 -ip netns exec ns1 tc qdisc add dev veth1 clsact -ip netns exec ns2 tc qdisc add dev veth2 clsact +ip netns exec ${NS1} tc qdisc add dev veth1 clsact +ip netns exec ${NS2} tc qdisc add dev veth2 clsact -ip netns exec ns1 tc filter add dev veth1 ingress bpf da obj test_xdp_meta.o sec t -ip netns exec ns2 tc filter add dev veth2 ingress bpf da obj test_xdp_meta.o sec t +ip netns exec ${NS1} tc filter add dev veth1 ingress bpf da obj test_xdp_meta.o sec t +ip netns exec ${NS2} tc filter add dev veth2 ingress bpf da obj test_xdp_meta.o sec t -ip netns exec ns1 ip link set dev veth1 xdp obj test_xdp_meta.o sec x -ip netns exec ns2 ip link set dev veth2 xdp obj test_xdp_meta.o sec x +ip netns exec ${NS1} ip link set dev veth1 xdp obj test_xdp_meta.o sec x +ip netns exec ${NS2} ip link set dev veth2 xdp obj test_xdp_meta.o sec x -ip netns exec ns1 ip link set dev veth1 up -ip netns exec ns2 ip link set dev veth2 up +ip netns exec ${NS1} ip link set dev veth1 up +ip netns exec ${NS2} ip link set dev veth2 up -ip netns exec ns1 ping -c 1 10.1.1.22 -ip netns exec ns2 ping -c 1 10.1.1.11 +ip netns exec ${NS1} ping -c 1 10.1.1.22 +ip netns exec ${NS2} ping -c 1 10.1.1.11 exit 0 diff --git a/tools/testing/selftests/bpf/test_xdp_redirect.sh b/tools/testing/selftests/bpf/test_xdp_redirect.sh index 57c8db9972a6..1d79f31480ad 100755 --- a/tools/testing/selftests/bpf/test_xdp_redirect.sh +++ b/tools/testing/selftests/bpf/test_xdp_redirect.sh @@ -10,6 +10,8 @@ # | xdp forwarding | # ------------------ +readonly NS1="ns1-$(mktemp -u XXXXXX)" +readonly NS2="ns2-$(mktemp -u XXXXXX)" ret=0 setup() @@ -17,27 +19,27 @@ setup() local xdpmode=$1 - ip netns add ns1 - ip netns add ns2 + ip netns add ${NS1} + ip netns add ${NS2} - ip link add veth1 index 111 type veth peer name veth11 netns ns1 - ip link add veth2 index 222 type veth peer name veth22 netns ns2 + ip link add veth1 index 111 type veth peer name veth11 netns ${NS1} + ip link add veth2 index 222 type veth peer name veth22 netns ${NS2} ip link set veth1 up ip link set veth2 up - ip -n ns1 link set dev veth11 up - ip -n ns2 link set dev veth22 up + ip -n ${NS1} link set dev veth11 up + ip -n ${NS2} link set dev veth22 up - ip -n ns1 addr add 10.1.1.11/24 dev veth11 - ip -n ns2 addr add 10.1.1.22/24 dev veth22 + ip -n ${NS1} addr add 10.1.1.11/24 dev veth11 + ip -n ${NS2} addr add 10.1.1.22/24 dev veth22 } cleanup() { ip link del veth1 2> /dev/null ip link del veth2 2> /dev/null - ip netns del ns1 2> /dev/null - ip netns del ns2 2> /dev/null + ip netns del ${NS1} 2> /dev/null + ip netns del ${NS2} 2> /dev/null } test_xdp_redirect() @@ -52,13 +54,13 @@ test_xdp_redirect() return 0 fi - ip -n ns1 link set veth11 $xdpmode obj xdp_dummy.o sec xdp &> /dev/null - ip -n ns2 link set veth22 $xdpmode obj xdp_dummy.o sec xdp &> /dev/null + ip -n ${NS1} link set veth11 $xdpmode obj xdp_dummy.o sec xdp &> /dev/null + ip -n ${NS2} link set veth22 $xdpmode obj xdp_dummy.o sec xdp &> /dev/null ip link set dev veth1 $xdpmode obj test_xdp_redirect.o sec redirect_to_222 &> /dev/null ip link set dev veth2 $xdpmode obj test_xdp_redirect.o sec redirect_to_111 &> /dev/null - if ip netns exec ns1 ping -c 1 10.1.1.22 &> /dev/null && - ip netns exec ns2 ping -c 1 10.1.1.11 &> /dev/null; then + if ip netns exec ${NS1} ping -c 1 10.1.1.22 &> /dev/null && + ip netns exec ${NS2} ping -c 1 10.1.1.11 &> /dev/null; then echo "selftests: test_xdp_redirect $xdpmode [PASS]"; else ret=1 diff --git a/tools/testing/selftests/bpf/test_xdp_redirect_multi.sh b/tools/testing/selftests/bpf/test_xdp_redirect_multi.sh index 05f872740999..cc57cb87e65f 100755 --- a/tools/testing/selftests/bpf/test_xdp_redirect_multi.sh +++ b/tools/testing/selftests/bpf/test_xdp_redirect_multi.sh @@ -32,6 +32,11 @@ DRV_MODE="xdpgeneric xdpdrv xdpegress" PASS=0 FAIL=0 LOG_DIR=$(mktemp -d) +declare -a NS +NS[0]="ns0-$(mktemp -u XXXXXX)" +NS[1]="ns1-$(mktemp -u XXXXXX)" +NS[2]="ns2-$(mktemp -u XXXXXX)" +NS[3]="ns3-$(mktemp -u XXXXXX)" test_pass() { @@ -47,11 +52,9 @@ test_fail() clean_up() { - for i in $(seq $NUM); do - ip link del veth$i 2> /dev/null - ip netns del ns$i 2> /dev/null + for i in $(seq 0 $NUM); do + ip netns del ${NS[$i]} 2> /dev/null done - ip netns del ns0 2> /dev/null } # Kselftest framework requirement - SKIP code is 4. @@ -79,23 +82,22 @@ setup_ns() mode="xdpdrv" fi - ip netns add ns0 + ip netns add ${NS[0]} for i in $(seq $NUM); do - ip netns add ns$i - ip -n ns$i link add veth0 index 2 type veth \ - peer name veth$i netns ns0 index $((1 + $i)) - ip -n ns0 link set veth$i up - ip -n ns$i link set veth0 up - - ip -n ns$i addr add 192.0.2.$i/24 dev veth0 - ip -n ns$i addr add 2001:db8::$i/64 dev veth0 + ip netns add ${NS[$i]} + ip -n ${NS[$i]} link add veth0 type veth peer name veth$i netns ${NS[0]} + ip -n ${NS[$i]} link set veth0 up + ip -n ${NS[0]} link set veth$i up + + ip -n ${NS[$i]} addr add 192.0.2.$i/24 dev veth0 + ip -n ${NS[$i]} addr add 2001:db8::$i/64 dev veth0 # Add a neigh entry for IPv4 ping test - ip -n ns$i neigh add 192.0.2.253 lladdr 00:00:00:00:00:01 dev veth0 - ip -n ns$i link set veth0 $mode obj \ + ip -n ${NS[$i]} neigh add 192.0.2.253 lladdr 00:00:00:00:00:01 dev veth0 + ip -n ${NS[$i]} link set veth0 $mode obj \ xdp_dummy.o sec xdp &> /dev/null || \ { test_fail "Unable to load dummy xdp" && exit 1; } IFACES="$IFACES veth$i" - veth_mac[$i]=$(ip -n ns0 link show veth$i | awk '/link\/ether/ {print $2}') + veth_mac[$i]=$(ip -n ${NS[0]} link show veth$i | awk '/link\/ether/ {print $2}') done } @@ -104,10 +106,10 @@ do_egress_tests() local mode=$1 # mac test - ip netns exec ns2 tcpdump -e -i veth0 -nn -l -e &> ${LOG_DIR}/mac_ns1-2_${mode}.log & - ip netns exec ns3 tcpdump -e -i veth0 -nn -l -e &> ${LOG_DIR}/mac_ns1-3_${mode}.log & + ip netns exec ${NS[2]} tcpdump -e -i veth0 -nn -l -e &> ${LOG_DIR}/mac_ns1-2_${mode}.log & + ip netns exec ${NS[3]} tcpdump -e -i veth0 -nn -l -e &> ${LOG_DIR}/mac_ns1-3_${mode}.log & sleep 0.5 - ip netns exec ns1 ping 192.0.2.254 -i 0.1 -c 4 &> /dev/null + ip netns exec ${NS[1]} ping 192.0.2.254 -i 0.1 -c 4 &> /dev/null sleep 0.5 pkill tcpdump @@ -123,18 +125,18 @@ do_ping_tests() local mode=$1 # ping6 test: echo request should be redirect back to itself, not others - ip netns exec ns1 ip neigh add 2001:db8::2 dev veth0 lladdr 00:00:00:00:00:02 + ip netns exec ${NS[1]} ip neigh add 2001:db8::2 dev veth0 lladdr 00:00:00:00:00:02 - ip netns exec ns1 tcpdump -i veth0 -nn -l -e &> ${LOG_DIR}/ns1-1_${mode}.log & - ip netns exec ns2 tcpdump -i veth0 -nn -l -e &> ${LOG_DIR}/ns1-2_${mode}.log & - ip netns exec ns3 tcpdump -i veth0 -nn -l -e &> ${LOG_DIR}/ns1-3_${mode}.log & + ip netns exec ${NS[1]} tcpdump -i veth0 -nn -l -e &> ${LOG_DIR}/ns1-1_${mode}.log & + ip netns exec ${NS[2]} tcpdump -i veth0 -nn -l -e &> ${LOG_DIR}/ns1-2_${mode}.log & + ip netns exec ${NS[3]} tcpdump -i veth0 -nn -l -e &> ${LOG_DIR}/ns1-3_${mode}.log & sleep 0.5 # ARP test - ip netns exec ns1 arping -q -c 2 -I veth0 192.0.2.254 + ip netns exec ${NS[1]} arping -q -c 2 -I veth0 192.0.2.254 # IPv4 test - ip netns exec ns1 ping 192.0.2.253 -i 0.1 -c 4 &> /dev/null + ip netns exec ${NS[1]} ping 192.0.2.253 -i 0.1 -c 4 &> /dev/null # IPv6 test - ip netns exec ns1 ping6 2001:db8::2 -i 0.1 -c 2 &> /dev/null + ip netns exec ${NS[1]} ping6 2001:db8::2 -i 0.1 -c 2 &> /dev/null sleep 0.5 pkill tcpdump @@ -180,7 +182,7 @@ do_tests() xdpgeneric) drv_p="-S";; esac - ip netns exec ns0 ./xdp_redirect_multi $drv_p $IFACES &> ${LOG_DIR}/xdp_redirect_${mode}.log & + ip netns exec ${NS[0]} ./xdp_redirect_multi $drv_p $IFACES &> ${LOG_DIR}/xdp_redirect_${mode}.log & xdp_pid=$! sleep 1 if ! ps -p $xdp_pid > /dev/null; then @@ -197,10 +199,10 @@ do_tests() kill $xdp_pid } -trap clean_up EXIT - check_env +trap clean_up EXIT + for mode in ${DRV_MODE}; do setup_ns $mode do_tests $mode diff --git a/tools/testing/selftests/bpf/test_xdp_veth.sh b/tools/testing/selftests/bpf/test_xdp_veth.sh index a3a1eaee26ea..392d28cc4e58 100755 --- a/tools/testing/selftests/bpf/test_xdp_veth.sh +++ b/tools/testing/selftests/bpf/test_xdp_veth.sh @@ -22,6 +22,9 @@ ksft_skip=4 TESTNAME=xdp_veth BPF_FS=$(awk '$3 == "bpf" {print $2; exit}' /proc/mounts) BPF_DIR=$BPF_FS/test_$TESTNAME +readonly NS1="ns1-$(mktemp -u XXXXXX)" +readonly NS2="ns2-$(mktemp -u XXXXXX)" +readonly NS3="ns3-$(mktemp -u XXXXXX)" _cleanup() { @@ -29,9 +32,9 @@ _cleanup() ip link del veth1 2> /dev/null ip link del veth2 2> /dev/null ip link del veth3 2> /dev/null - ip netns del ns1 2> /dev/null - ip netns del ns2 2> /dev/null - ip netns del ns3 2> /dev/null + ip netns del ${NS1} 2> /dev/null + ip netns del ${NS2} 2> /dev/null + ip netns del ${NS3} 2> /dev/null rm -rf $BPF_DIR 2> /dev/null } @@ -77,24 +80,24 @@ set -e trap cleanup_skip EXIT -ip netns add ns1 -ip netns add ns2 -ip netns add ns3 +ip netns add ${NS1} +ip netns add ${NS2} +ip netns add ${NS3} -ip link add veth1 index 111 type veth peer name veth11 netns ns1 -ip link add veth2 index 122 type veth peer name veth22 netns ns2 -ip link add veth3 index 133 type veth peer name veth33 netns ns3 +ip link add veth1 index 111 type veth peer name veth11 netns ${NS1} +ip link add veth2 index 122 type veth peer name veth22 netns ${NS2} +ip link add veth3 index 133 type veth peer name veth33 netns ${NS3} ip link set veth1 up ip link set veth2 up ip link set veth3 up -ip -n ns1 addr add 10.1.1.11/24 dev veth11 -ip -n ns3 addr add 10.1.1.33/24 dev veth33 +ip -n ${NS1} addr add 10.1.1.11/24 dev veth11 +ip -n ${NS3} addr add 10.1.1.33/24 dev veth33 -ip -n ns1 link set dev veth11 up -ip -n ns2 link set dev veth22 up -ip -n ns3 link set dev veth33 up +ip -n ${NS1} link set dev veth11 up +ip -n ${NS2} link set dev veth22 up +ip -n ${NS3} link set dev veth33 up mkdir $BPF_DIR bpftool prog loadall \ @@ -107,12 +110,12 @@ ip link set dev veth1 xdp pinned $BPF_DIR/progs/redirect_map_0 ip link set dev veth2 xdp pinned $BPF_DIR/progs/redirect_map_1 ip link set dev veth3 xdp pinned $BPF_DIR/progs/redirect_map_2 -ip -n ns1 link set dev veth11 xdp obj xdp_dummy.o sec xdp -ip -n ns2 link set dev veth22 xdp obj xdp_tx.o sec xdp -ip -n ns3 link set dev veth33 xdp obj xdp_dummy.o sec xdp +ip -n ${NS1} link set dev veth11 xdp obj xdp_dummy.o sec xdp +ip -n ${NS2} link set dev veth22 xdp obj xdp_tx.o sec xdp +ip -n ${NS3} link set dev veth33 xdp obj xdp_dummy.o sec xdp trap cleanup EXIT -ip netns exec ns1 ping -c 1 -W 1 10.1.1.33 +ip netns exec ${NS1} ping -c 1 -W 1 10.1.1.33 exit 0 diff --git a/tools/testing/selftests/bpf/test_xdp_vlan.sh b/tools/testing/selftests/bpf/test_xdp_vlan.sh index 0cbc7604a2f8..810c407e0286 100755 --- a/tools/testing/selftests/bpf/test_xdp_vlan.sh +++ b/tools/testing/selftests/bpf/test_xdp_vlan.sh @@ -4,6 +4,8 @@ # Kselftest framework requirement - SKIP code is 4. readonly KSFT_SKIP=4 +readonly NS1="ns1-$(mktemp -u XXXXXX)" +readonly NS2="ns2-$(mktemp -u XXXXXX)" # Allow wrapper scripts to name test if [ -z "$TESTNAME" ]; then @@ -49,15 +51,15 @@ cleanup() if [ -n "$INTERACTIVE" ]; then echo "Namespace setup still active explore with:" - echo " ip netns exec ns1 bash" - echo " ip netns exec ns2 bash" + echo " ip netns exec ${NS1} bash" + echo " ip netns exec ${NS2} bash" exit $status fi set +e ip link del veth1 2> /dev/null - ip netns del ns1 2> /dev/null - ip netns del ns2 2> /dev/null + ip netns del ${NS1} 2> /dev/null + ip netns del ${NS2} 2> /dev/null } # Using external program "getopt" to get --long-options @@ -126,8 +128,8 @@ fi # Interactive mode likely require us to cleanup netns if [ -n "$INTERACTIVE" ]; then ip link del veth1 2> /dev/null - ip netns del ns1 2> /dev/null - ip netns del ns2 2> /dev/null + ip netns del ${NS1} 2> /dev/null + ip netns del ${NS2} 2> /dev/null fi # Exit on failure @@ -144,8 +146,8 @@ if [ -n "$VERBOSE" ]; then fi # Create two namespaces -ip netns add ns1 -ip netns add ns2 +ip netns add ${NS1} +ip netns add ${NS2} # Run cleanup if failing or on kill trap cleanup 0 2 3 6 9 @@ -154,44 +156,44 @@ trap cleanup 0 2 3 6 9 ip link add veth1 type veth peer name veth2 # Move veth1 and veth2 into the respective namespaces -ip link set veth1 netns ns1 -ip link set veth2 netns ns2 +ip link set veth1 netns ${NS1} +ip link set veth2 netns ${NS2} # NOTICE: XDP require VLAN header inside packet payload # - Thus, disable VLAN offloading driver features # - For veth REMEMBER TX side VLAN-offload # # Disable rx-vlan-offload (mostly needed on ns1) -ip netns exec ns1 ethtool -K veth1 rxvlan off -ip netns exec ns2 ethtool -K veth2 rxvlan off +ip netns exec ${NS1} ethtool -K veth1 rxvlan off +ip netns exec ${NS2} ethtool -K veth2 rxvlan off # # Disable tx-vlan-offload (mostly needed on ns2) -ip netns exec ns2 ethtool -K veth2 txvlan off -ip netns exec ns1 ethtool -K veth1 txvlan off +ip netns exec ${NS2} ethtool -K veth2 txvlan off +ip netns exec ${NS1} ethtool -K veth1 txvlan off export IPADDR1=100.64.41.1 export IPADDR2=100.64.41.2 # In ns1/veth1 add IP-addr on plain net_device -ip netns exec ns1 ip addr add ${IPADDR1}/24 dev veth1 -ip netns exec ns1 ip link set veth1 up +ip netns exec ${NS1} ip addr add ${IPADDR1}/24 dev veth1 +ip netns exec ${NS1} ip link set veth1 up # In ns2/veth2 create VLAN device export VLAN=4011 export DEVNS2=veth2 -ip netns exec ns2 ip link add link $DEVNS2 name $DEVNS2.$VLAN type vlan id $VLAN -ip netns exec ns2 ip addr add ${IPADDR2}/24 dev $DEVNS2.$VLAN -ip netns exec ns2 ip link set $DEVNS2 up -ip netns exec ns2 ip link set $DEVNS2.$VLAN up +ip netns exec ${NS2} ip link add link $DEVNS2 name $DEVNS2.$VLAN type vlan id $VLAN +ip netns exec ${NS2} ip addr add ${IPADDR2}/24 dev $DEVNS2.$VLAN +ip netns exec ${NS2} ip link set $DEVNS2 up +ip netns exec ${NS2} ip link set $DEVNS2.$VLAN up # Bringup lo in netns (to avoids confusing people using --interactive) -ip netns exec ns1 ip link set lo up -ip netns exec ns2 ip link set lo up +ip netns exec ${NS1} ip link set lo up +ip netns exec ${NS2} ip link set lo up # At this point, the hosts cannot reach each-other, # because ns2 are using VLAN tags on the packets. -ip netns exec ns2 sh -c 'ping -W 1 -c 1 100.64.41.1 || echo "Success: First ping must fail"' +ip netns exec ${NS2} sh -c 'ping -W 1 -c 1 100.64.41.1 || echo "Success: First ping must fail"' # Now we can use the test_xdp_vlan.c program to pop/push these VLAN tags @@ -202,19 +204,19 @@ export FILE=test_xdp_vlan.o # First test: Remove VLAN by setting VLAN ID 0, using "xdp_vlan_change" export XDP_PROG=xdp_vlan_change -ip netns exec ns1 ip link set $DEVNS1 $XDP_MODE object $FILE section $XDP_PROG +ip netns exec ${NS1} ip link set $DEVNS1 $XDP_MODE object $FILE section $XDP_PROG # In ns1: egress use TC to add back VLAN tag 4011 # (del cmd) # tc qdisc del dev $DEVNS1 clsact 2> /dev/null # -ip netns exec ns1 tc qdisc add dev $DEVNS1 clsact -ip netns exec ns1 tc filter add dev $DEVNS1 egress \ +ip netns exec ${NS1} tc qdisc add dev $DEVNS1 clsact +ip netns exec ${NS1} tc filter add dev $DEVNS1 egress \ prio 1 handle 1 bpf da obj $FILE sec tc_vlan_push # Now the namespaces can reach each-other, test with ping: -ip netns exec ns2 ping -i 0.2 -W 2 -c 2 $IPADDR1 -ip netns exec ns1 ping -i 0.2 -W 2 -c 2 $IPADDR2 +ip netns exec ${NS2} ping -i 0.2 -W 2 -c 2 $IPADDR1 +ip netns exec ${NS1} ping -i 0.2 -W 2 -c 2 $IPADDR2 # Second test: Replace xdp prog, that fully remove vlan header # @@ -223,9 +225,9 @@ ip netns exec ns1 ping -i 0.2 -W 2 -c 2 $IPADDR2 # ETH_P_8021Q indication, and this cause overwriting of our changes. # export XDP_PROG=xdp_vlan_remove_outer2 -ip netns exec ns1 ip link set $DEVNS1 $XDP_MODE off -ip netns exec ns1 ip link set $DEVNS1 $XDP_MODE object $FILE section $XDP_PROG +ip netns exec ${NS1} ip link set $DEVNS1 $XDP_MODE off +ip netns exec ${NS1} ip link set $DEVNS1 $XDP_MODE object $FILE section $XDP_PROG # Now the namespaces should still be able reach each-other, test with ping: -ip netns exec ns2 ping -i 0.2 -W 2 -c 2 $IPADDR1 -ip netns exec ns1 ping -i 0.2 -W 2 -c 2 $IPADDR2 +ip netns exec ${NS2} ping -i 0.2 -W 2 -c 2 $IPADDR1 +ip netns exec ${NS1} ping -i 0.2 -W 2 -c 2 $IPADDR2 diff --git a/tools/testing/selftests/bpf/trace_helpers.c b/tools/testing/selftests/bpf/trace_helpers.c index 7b7f918eda77..3d6217e3aff7 100644 --- a/tools/testing/selftests/bpf/trace_helpers.c +++ b/tools/testing/selftests/bpf/trace_helpers.c @@ -34,6 +34,13 @@ int load_kallsyms(void) if (!f) return -ENOENT; + /* + * This is called/used from multiplace places, + * load symbols just once. + */ + if (sym_cnt) + return 0; + while (fgets(buf, sizeof(buf), f)) { if (sscanf(buf, "%p %c %s", &addr, &symbol, func) != 3) break; @@ -138,6 +145,29 @@ void read_trace_pipe(void) } } +ssize_t get_uprobe_offset(const void *addr) +{ + size_t start, end, base; + char buf[256]; + bool found = false; + FILE *f; + + f = fopen("/proc/self/maps", "r"); + if (!f) + return -errno; + + while (fscanf(f, "%zx-%zx %s %zx %*[^\n]\n", &start, &end, buf, &base) == 4) { + if (buf[2] == 'x' && (uintptr_t)addr >= start && (uintptr_t)addr < end) { + found = true; + break; + } + } + + fclose(f); + + if (!found) + return -ESRCH; + #if defined(__powerpc64__) && defined(_CALL_ELF) && _CALL_ELF == 2 #define OP_RT_RA_MASK 0xffff0000UL @@ -145,10 +175,6 @@ void read_trace_pipe(void) #define ADDIS_R2_R12 0x3c4c0000UL #define ADDI_R2_R2 0x38420000UL -ssize_t get_uprobe_offset(const void *addr, ssize_t base) -{ - u32 *insn = (u32 *)(uintptr_t)addr; - /* * A PPC64 ABIv2 function may have a local and a global entry * point. We need to use the local entry point when patching @@ -165,43 +191,16 @@ ssize_t get_uprobe_offset(const void *addr, ssize_t base) * lis r2,XXXX * addi r2,r2,XXXX */ - if ((((*insn & OP_RT_RA_MASK) == ADDIS_R2_R12) || - ((*insn & OP_RT_RA_MASK) == LIS_R2)) && - ((*(insn + 1) & OP_RT_RA_MASK) == ADDI_R2_R2)) - return (ssize_t)(insn + 2) - base; - else - return (uintptr_t)addr - base; -} + { + const u32 *insn = (const u32 *)(uintptr_t)addr; -#else - -ssize_t get_uprobe_offset(const void *addr, ssize_t base) -{ - return (uintptr_t)addr - base; -} - -#endif - -ssize_t get_base_addr(void) -{ - size_t start, offset; - char buf[256]; - FILE *f; - - f = fopen("/proc/self/maps", "r"); - if (!f) - return -errno; - - while (fscanf(f, "%zx-%*x %s %zx %*[^\n]\n", - &start, buf, &offset) == 3) { - if (strcmp(buf, "r-xp") == 0) { - fclose(f); - return start - offset; - } + if ((((*insn & OP_RT_RA_MASK) == ADDIS_R2_R12) || + ((*insn & OP_RT_RA_MASK) == LIS_R2)) && + ((*(insn + 1) & OP_RT_RA_MASK) == ADDI_R2_R2)) + return (uintptr_t)(insn + 2) - start + base; } - - fclose(f); - return -EINVAL; +#endif + return (uintptr_t)addr - start + base; } ssize_t get_rel_offset(uintptr_t addr) diff --git a/tools/testing/selftests/bpf/trace_helpers.h b/tools/testing/selftests/bpf/trace_helpers.h index d907b445524d..238a9c98cde2 100644 --- a/tools/testing/selftests/bpf/trace_helpers.h +++ b/tools/testing/selftests/bpf/trace_helpers.h @@ -18,8 +18,7 @@ int kallsyms_find(const char *sym, unsigned long long *addr); void read_trace_pipe(void); -ssize_t get_uprobe_offset(const void *addr, ssize_t base); -ssize_t get_base_addr(void); +ssize_t get_uprobe_offset(const void *addr); ssize_t get_rel_offset(uintptr_t addr); #endif diff --git a/tools/testing/selftests/bpf/verifier/atomic_invalid.c b/tools/testing/selftests/bpf/verifier/atomic_invalid.c index 39272720b2f6..25f4ac1c69ab 100644 --- a/tools/testing/selftests/bpf/verifier/atomic_invalid.c +++ b/tools/testing/selftests/bpf/verifier/atomic_invalid.c @@ -1,6 +1,6 @@ -#define __INVALID_ATOMIC_ACCESS_TEST(op) \ +#define __INVALID_ATOMIC_ACCESS_TEST(op) \ { \ - "atomic " #op " access through non-pointer ", \ + "atomic " #op " access through non-pointer ", \ .insns = { \ BPF_MOV64_IMM(BPF_REG_0, 1), \ BPF_MOV64_IMM(BPF_REG_1, 0), \ @@ -9,7 +9,7 @@ BPF_EXIT_INSN(), \ }, \ .result = REJECT, \ - .errstr = "R1 invalid mem access 'inv'" \ + .errstr = "R1 invalid mem access 'scalar'" \ } __INVALID_ATOMIC_ACCESS_TEST(BPF_ADD), __INVALID_ATOMIC_ACCESS_TEST(BPF_ADD | BPF_FETCH), diff --git a/tools/testing/selftests/bpf/verifier/bounds.c b/tools/testing/selftests/bpf/verifier/bounds.c index e061e8799ce2..33125d5f6772 100644 --- a/tools/testing/selftests/bpf/verifier/bounds.c +++ b/tools/testing/selftests/bpf/verifier/bounds.c @@ -508,7 +508,7 @@ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, -1), BPF_EXIT_INSN(), }, - .errstr_unpriv = "R0 invalid mem access 'inv'", + .errstr_unpriv = "R0 invalid mem access 'scalar'", .result_unpriv = REJECT, .result = ACCEPT }, @@ -530,7 +530,7 @@ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, -1), BPF_EXIT_INSN(), }, - .errstr_unpriv = "R0 invalid mem access 'inv'", + .errstr_unpriv = "R0 invalid mem access 'scalar'", .result_unpriv = REJECT, .result = ACCEPT }, diff --git a/tools/testing/selftests/bpf/verifier/bounds_deduction.c b/tools/testing/selftests/bpf/verifier/bounds_deduction.c index 91869aea6d64..3931c481e30c 100644 --- a/tools/testing/selftests/bpf/verifier/bounds_deduction.c +++ b/tools/testing/selftests/bpf/verifier/bounds_deduction.c @@ -105,7 +105,7 @@ BPF_EXIT_INSN(), }, .errstr_unpriv = "R1 has pointer with unsupported alu operation", - .errstr = "dereference of modified ctx ptr", + .errstr = "negative offset ctx ptr R1 off=-1 disallowed", .result = REJECT, .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, diff --git a/tools/testing/selftests/bpf/verifier/calls.c b/tools/testing/selftests/bpf/verifier/calls.c index d7b74eb28333..2e03decb11b6 100644 --- a/tools/testing/selftests/bpf/verifier/calls.c +++ b/tools/testing/selftests/bpf/verifier/calls.c @@ -22,6 +22,183 @@ .result = ACCEPT, }, { + "calls: invalid kfunc call: ptr_to_mem to struct with non-scalar", + .insns = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, BPF_PSEUDO_KFUNC_CALL, 0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = REJECT, + .errstr = "arg#0 pointer type STRUCT prog_test_fail1 must point to scalar", + .fixup_kfunc_btf_id = { + { "bpf_kfunc_call_test_fail1", 2 }, + }, +}, +{ + "calls: invalid kfunc call: ptr_to_mem to struct with nesting depth > 4", + .insns = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, BPF_PSEUDO_KFUNC_CALL, 0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = REJECT, + .errstr = "max struct nesting depth exceeded\narg#0 pointer type STRUCT prog_test_fail2", + .fixup_kfunc_btf_id = { + { "bpf_kfunc_call_test_fail2", 2 }, + }, +}, +{ + "calls: invalid kfunc call: ptr_to_mem to struct with FAM", + .insns = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, BPF_PSEUDO_KFUNC_CALL, 0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = REJECT, + .errstr = "arg#0 pointer type STRUCT prog_test_fail3 must point to scalar", + .fixup_kfunc_btf_id = { + { "bpf_kfunc_call_test_fail3", 2 }, + }, +}, +{ + "calls: invalid kfunc call: reg->type != PTR_TO_CTX", + .insns = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, BPF_PSEUDO_KFUNC_CALL, 0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = REJECT, + .errstr = "arg#0 expected pointer to ctx, but got PTR", + .fixup_kfunc_btf_id = { + { "bpf_kfunc_call_test_pass_ctx", 2 }, + }, +}, +{ + "calls: invalid kfunc call: void * not allowed in func proto without mem size arg", + .insns = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, BPF_PSEUDO_KFUNC_CALL, 0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = REJECT, + .errstr = "arg#0 pointer type UNKNOWN must point to scalar", + .fixup_kfunc_btf_id = { + { "bpf_kfunc_call_test_mem_len_fail1", 2 }, + }, +}, +{ + "calls: trigger reg2btf_ids[reg->type] for reg->type > __BPF_REG_TYPE_MAX", + .insns = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_1, 0, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, BPF_PSEUDO_KFUNC_CALL, 0, 0), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, BPF_PSEUDO_KFUNC_CALL, 0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = REJECT, + .errstr = "arg#0 pointer type STRUCT prog_test_ref_kfunc must point", + .fixup_kfunc_btf_id = { + { "bpf_kfunc_call_test_acquire", 3 }, + { "bpf_kfunc_call_test_release", 5 }, + }, +}, +{ + "calls: invalid kfunc call: reg->off must be zero when passed to release kfunc", + .insns = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_1, 0, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, BPF_PSEUDO_KFUNC_CALL, 0, 0), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, BPF_PSEUDO_KFUNC_CALL, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = REJECT, + .errstr = "R1 must have zero offset when passed to release func", + .fixup_kfunc_btf_id = { + { "bpf_kfunc_call_test_acquire", 3 }, + { "bpf_kfunc_call_memb_release", 8 }, + }, +}, +{ + "calls: invalid kfunc call: PTR_TO_BTF_ID with negative offset", + .insns = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_1, 0, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, BPF_PSEUDO_KFUNC_CALL, 0, 0), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, 16), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -4), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, BPF_PSEUDO_KFUNC_CALL, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .fixup_kfunc_btf_id = { + { "bpf_kfunc_call_test_acquire", 3 }, + { "bpf_kfunc_call_test_release", 9 }, + }, + .result_unpriv = REJECT, + .result = REJECT, + .errstr = "negative offset ptr_ ptr R1 off=-4 disallowed", +}, +{ + "calls: invalid kfunc call: PTR_TO_BTF_ID with variable offset", + .insns = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_1, 0, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, BPF_PSEUDO_KFUNC_CALL, 0, 0), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_0, 4), + BPF_JMP_IMM(BPF_JLE, BPF_REG_2, 4, 3), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, BPF_PSEUDO_KFUNC_CALL, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_JMP_IMM(BPF_JGE, BPF_REG_2, 0, 3), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, BPF_PSEUDO_KFUNC_CALL, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_2), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, BPF_PSEUDO_KFUNC_CALL, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .fixup_kfunc_btf_id = { + { "bpf_kfunc_call_test_acquire", 3 }, + { "bpf_kfunc_call_test_release", 9 }, + { "bpf_kfunc_call_test_release", 13 }, + { "bpf_kfunc_call_test_release", 17 }, + }, + .result_unpriv = REJECT, + .result = REJECT, + .errstr = "variable ptr_ access var_off=(0x0; 0x7) disallowed", +}, +{ "calls: basic sanity", .insns = { BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2), @@ -94,7 +271,7 @@ }, .prog_type = BPF_PROG_TYPE_SCHED_CLS, .result = REJECT, - .errstr = "R0 invalid mem access 'inv'", + .errstr = "R0 invalid mem access 'scalar'", }, { "calls: multiple ret types in subprog 2", @@ -397,7 +574,7 @@ BPF_EXIT_INSN(), }, .result = REJECT, - .errstr = "R6 invalid mem access 'inv'", + .errstr = "R6 invalid mem access 'scalar'", .prog_type = BPF_PROG_TYPE_XDP, .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, @@ -1603,7 +1780,7 @@ .prog_type = BPF_PROG_TYPE_SCHED_CLS, .fixup_map_hash_8b = { 12, 22 }, .result = REJECT, - .errstr = "R0 invalid mem access 'inv'", + .errstr = "R0 invalid mem access 'scalar'", }, { "calls: pkt_ptr spill into caller stack", diff --git a/tools/testing/selftests/bpf/verifier/ctx.c b/tools/testing/selftests/bpf/verifier/ctx.c index 23080862aafd..c8eaf0536c24 100644 --- a/tools/testing/selftests/bpf/verifier/ctx.c +++ b/tools/testing/selftests/bpf/verifier/ctx.c @@ -58,7 +58,7 @@ }, .prog_type = BPF_PROG_TYPE_SCHED_CLS, .result = REJECT, - .errstr = "dereference of modified ctx ptr", + .errstr = "negative offset ctx ptr R1 off=-612 disallowed", }, { "pass modified ctx pointer to helper, 2", @@ -71,8 +71,8 @@ }, .result_unpriv = REJECT, .result = REJECT, - .errstr_unpriv = "dereference of modified ctx ptr", - .errstr = "dereference of modified ctx ptr", + .errstr_unpriv = "negative offset ctx ptr R1 off=-612 disallowed", + .errstr = "negative offset ctx ptr R1 off=-612 disallowed", }, { "pass modified ctx pointer to helper, 3", @@ -127,7 +127,7 @@ .prog_type = BPF_PROG_TYPE_CGROUP_SOCK_ADDR, .expected_attach_type = BPF_CGROUP_UDP6_SENDMSG, .result = REJECT, - .errstr = "R1 type=inv expected=ctx", + .errstr = "R1 type=scalar expected=ctx", }, { "pass ctx or null check, 4: ctx - const", @@ -141,7 +141,7 @@ .prog_type = BPF_PROG_TYPE_CGROUP_SOCK_ADDR, .expected_attach_type = BPF_CGROUP_UDP6_SENDMSG, .result = REJECT, - .errstr = "dereference of modified ctx ptr", + .errstr = "negative offset ctx ptr R1 off=-612 disallowed", }, { "pass ctx or null check, 5: null (connect)", @@ -193,5 +193,5 @@ .prog_type = BPF_PROG_TYPE_CGROUP_SOCK, .expected_attach_type = BPF_CGROUP_INET4_POST_BIND, .result = REJECT, - .errstr = "R1 type=inv expected=ctx", + .errstr = "R1 type=scalar expected=ctx", }, diff --git a/tools/testing/selftests/bpf/verifier/direct_packet_access.c b/tools/testing/selftests/bpf/verifier/direct_packet_access.c index ac1e19d0f520..11acd1855acf 100644 --- a/tools/testing/selftests/bpf/verifier/direct_packet_access.c +++ b/tools/testing/selftests/bpf/verifier/direct_packet_access.c @@ -339,7 +339,7 @@ BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .errstr = "R2 invalid mem access 'inv'", + .errstr = "R2 invalid mem access 'scalar'", .result = REJECT, .prog_type = BPF_PROG_TYPE_SCHED_CLS, .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, diff --git a/tools/testing/selftests/bpf/verifier/helper_access_var_len.c b/tools/testing/selftests/bpf/verifier/helper_access_var_len.c index 0ab7f1dfc97a..a6c869a7319c 100644 --- a/tools/testing/selftests/bpf/verifier/helper_access_var_len.c +++ b/tools/testing/selftests/bpf/verifier/helper_access_var_len.c @@ -350,7 +350,7 @@ BPF_EMIT_CALL(BPF_FUNC_csum_diff), BPF_EXIT_INSN(), }, - .errstr = "R1 type=inv expected=fp", + .errstr = "R1 type=scalar expected=fp", .result = REJECT, .prog_type = BPF_PROG_TYPE_SCHED_CLS, }, @@ -471,7 +471,7 @@ BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel), BPF_EXIT_INSN(), }, - .errstr = "R1 type=inv expected=fp", + .errstr = "R1 type=scalar expected=fp", .result = REJECT, .prog_type = BPF_PROG_TYPE_TRACEPOINT, }, @@ -484,7 +484,7 @@ BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel), BPF_EXIT_INSN(), }, - .errstr = "R1 type=inv expected=fp", + .errstr = "R1 type=scalar expected=fp", .result = REJECT, .prog_type = BPF_PROG_TYPE_TRACEPOINT, }, diff --git a/tools/testing/selftests/bpf/verifier/jmp32.c b/tools/testing/selftests/bpf/verifier/jmp32.c index 1c857b2fbdf0..6ddc418fdfaf 100644 --- a/tools/testing/selftests/bpf/verifier/jmp32.c +++ b/tools/testing/selftests/bpf/verifier/jmp32.c @@ -286,7 +286,7 @@ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .errstr_unpriv = "R0 invalid mem access 'inv'", + .errstr_unpriv = "R0 invalid mem access 'scalar'", .result_unpriv = REJECT, .result = ACCEPT, .retval = 2, @@ -356,7 +356,7 @@ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .errstr_unpriv = "R0 invalid mem access 'inv'", + .errstr_unpriv = "R0 invalid mem access 'scalar'", .result_unpriv = REJECT, .result = ACCEPT, .retval = 2, @@ -426,7 +426,7 @@ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .errstr_unpriv = "R0 invalid mem access 'inv'", + .errstr_unpriv = "R0 invalid mem access 'scalar'", .result_unpriv = REJECT, .result = ACCEPT, .retval = 2, @@ -496,7 +496,7 @@ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .errstr_unpriv = "R0 invalid mem access 'inv'", + .errstr_unpriv = "R0 invalid mem access 'scalar'", .result_unpriv = REJECT, .result = ACCEPT, .retval = 2, @@ -566,7 +566,7 @@ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .errstr_unpriv = "R0 invalid mem access 'inv'", + .errstr_unpriv = "R0 invalid mem access 'scalar'", .result_unpriv = REJECT, .result = ACCEPT, .retval = 2, @@ -636,7 +636,7 @@ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .errstr_unpriv = "R0 invalid mem access 'inv'", + .errstr_unpriv = "R0 invalid mem access 'scalar'", .result_unpriv = REJECT, .result = ACCEPT, .retval = 2, @@ -706,7 +706,7 @@ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .errstr_unpriv = "R0 invalid mem access 'inv'", + .errstr_unpriv = "R0 invalid mem access 'scalar'", .result_unpriv = REJECT, .result = ACCEPT, .retval = 2, @@ -776,7 +776,7 @@ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .errstr_unpriv = "R0 invalid mem access 'inv'", + .errstr_unpriv = "R0 invalid mem access 'scalar'", .result_unpriv = REJECT, .result = ACCEPT, .retval = 2, diff --git a/tools/testing/selftests/bpf/verifier/precise.c b/tools/testing/selftests/bpf/verifier/precise.c index 6dc8003ffc70..9e754423fa8b 100644 --- a/tools/testing/selftests/bpf/verifier/precise.c +++ b/tools/testing/selftests/bpf/verifier/precise.c @@ -27,7 +27,7 @@ BPF_JMP_IMM(BPF_JLT, BPF_REG_2, 8, 1), BPF_EXIT_INSN(), - BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, 1), /* R2=inv(umin=1, umax=8) */ + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, 1), /* R2=scalar(umin=1, umax=8) */ BPF_MOV64_REG(BPF_REG_1, BPF_REG_FP), BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8), BPF_MOV64_IMM(BPF_REG_3, 0), @@ -87,7 +87,7 @@ BPF_JMP_IMM(BPF_JLT, BPF_REG_2, 8, 1), BPF_EXIT_INSN(), - BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, 1), /* R2=inv(umin=1, umax=8) */ + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, 1), /* R2=scalar(umin=1, umax=8) */ BPF_MOV64_REG(BPF_REG_1, BPF_REG_FP), BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8), BPF_MOV64_IMM(BPF_REG_3, 0), diff --git a/tools/testing/selftests/bpf/verifier/raw_stack.c b/tools/testing/selftests/bpf/verifier/raw_stack.c index cc8e8c3cdc03..eb5ed936580b 100644 --- a/tools/testing/selftests/bpf/verifier/raw_stack.c +++ b/tools/testing/selftests/bpf/verifier/raw_stack.c @@ -132,7 +132,7 @@ BPF_EXIT_INSN(), }, .result = REJECT, - .errstr = "R0 invalid mem access 'inv'", + .errstr = "R0 invalid mem access 'scalar'", .prog_type = BPF_PROG_TYPE_SCHED_CLS, .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, @@ -162,7 +162,7 @@ BPF_EXIT_INSN(), }, .result = REJECT, - .errstr = "R3 invalid mem access 'inv'", + .errstr = "R3 invalid mem access 'scalar'", .prog_type = BPF_PROG_TYPE_SCHED_CLS, .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, diff --git a/tools/testing/selftests/bpf/verifier/ref_tracking.c b/tools/testing/selftests/bpf/verifier/ref_tracking.c index 3b6ee009c00b..fbd682520e47 100644 --- a/tools/testing/selftests/bpf/verifier/ref_tracking.c +++ b/tools/testing/selftests/bpf/verifier/ref_tracking.c @@ -162,7 +162,7 @@ BPF_EXIT_INSN(), }, .prog_type = BPF_PROG_TYPE_SCHED_CLS, - .errstr = "type=inv expected=sock", + .errstr = "type=scalar expected=sock", .result = REJECT, }, { @@ -178,7 +178,7 @@ BPF_EXIT_INSN(), }, .prog_type = BPF_PROG_TYPE_SCHED_CLS, - .errstr = "type=inv expected=sock", + .errstr = "type=scalar expected=sock", .result = REJECT, }, { @@ -274,7 +274,7 @@ BPF_EXIT_INSN(), }, .prog_type = BPF_PROG_TYPE_SCHED_CLS, - .errstr = "type=inv expected=sock", + .errstr = "type=scalar expected=sock", .result = REJECT, }, { diff --git a/tools/testing/selftests/bpf/verifier/ringbuf.c b/tools/testing/selftests/bpf/verifier/ringbuf.c new file mode 100644 index 000000000000..b64d33e4833c --- /dev/null +++ b/tools/testing/selftests/bpf/verifier/ringbuf.c @@ -0,0 +1,95 @@ +{ + "ringbuf: invalid reservation offset 1", + .insns = { + /* reserve 8 byte ringbuf memory */ + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_MOV64_IMM(BPF_REG_2, 8), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_ringbuf_reserve), + /* store a pointer to the reserved memory in R6 */ + BPF_MOV64_REG(BPF_REG_6, BPF_REG_0), + /* check whether the reservation was successful */ + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7), + /* spill R6(mem) into the stack */ + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_6, -8), + /* fill it back in R7 */ + BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_10, -8), + /* should be able to access *(R7) = 0 */ + BPF_ST_MEM(BPF_DW, BPF_REG_7, 0, 0), + /* submit the reserved ringbuf memory */ + BPF_MOV64_REG(BPF_REG_1, BPF_REG_7), + /* add invalid offset to reserved ringbuf memory */ + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 0xcafe), + BPF_MOV64_IMM(BPF_REG_2, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_ringbuf_submit), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_ringbuf = { 1 }, + .result = REJECT, + .errstr = "dereference of modified alloc_mem ptr R1", +}, +{ + "ringbuf: invalid reservation offset 2", + .insns = { + /* reserve 8 byte ringbuf memory */ + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_MOV64_IMM(BPF_REG_2, 8), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_ringbuf_reserve), + /* store a pointer to the reserved memory in R6 */ + BPF_MOV64_REG(BPF_REG_6, BPF_REG_0), + /* check whether the reservation was successful */ + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7), + /* spill R6(mem) into the stack */ + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_6, -8), + /* fill it back in R7 */ + BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_10, -8), + /* add invalid offset to reserved ringbuf memory */ + BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, 0xcafe), + /* should be able to access *(R7) = 0 */ + BPF_ST_MEM(BPF_DW, BPF_REG_7, 0, 0), + /* submit the reserved ringbuf memory */ + BPF_MOV64_REG(BPF_REG_1, BPF_REG_7), + BPF_MOV64_IMM(BPF_REG_2, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_ringbuf_submit), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_ringbuf = { 1 }, + .result = REJECT, + .errstr = "R7 min value is outside of the allowed memory range", +}, +{ + "ringbuf: check passing rb mem to helpers", + .insns = { + BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), + /* reserve 8 byte ringbuf memory */ + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_MOV64_IMM(BPF_REG_2, 8), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_ringbuf_reserve), + BPF_MOV64_REG(BPF_REG_7, BPF_REG_0), + /* check whether the reservation was successful */ + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + /* pass allocated ring buffer memory to fib lookup */ + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_0), + BPF_MOV64_IMM(BPF_REG_3, 8), + BPF_MOV64_IMM(BPF_REG_4, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_fib_lookup), + /* submit the ringbuf memory */ + BPF_MOV64_REG(BPF_REG_1, BPF_REG_7), + BPF_MOV64_IMM(BPF_REG_2, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_ringbuf_submit), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_ringbuf = { 2 }, + .prog_type = BPF_PROG_TYPE_XDP, + .result = ACCEPT, +}, diff --git a/tools/testing/selftests/bpf/verifier/search_pruning.c b/tools/testing/selftests/bpf/verifier/search_pruning.c index 682519769fe3..68b14fdfebdb 100644 --- a/tools/testing/selftests/bpf/verifier/search_pruning.c +++ b/tools/testing/selftests/bpf/verifier/search_pruning.c @@ -104,7 +104,7 @@ BPF_EXIT_INSN(), }, .fixup_map_hash_8b = { 3 }, - .errstr = "R6 invalid mem access 'inv'", + .errstr = "R6 invalid mem access 'scalar'", .result = REJECT, .prog_type = BPF_PROG_TYPE_TRACEPOINT, }, diff --git a/tools/testing/selftests/bpf/verifier/sock.c b/tools/testing/selftests/bpf/verifier/sock.c index ce13ece08d51..86b24cad27a7 100644 --- a/tools/testing/selftests/bpf/verifier/sock.c +++ b/tools/testing/selftests/bpf/verifier/sock.c @@ -121,7 +121,25 @@ .result = ACCEPT, }, { - "sk_fullsock(skb->sk): sk->dst_port [narrow load]", + "sk_fullsock(skb->sk): sk->dst_port [word load] (backward compatibility)", + .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)), + BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_EMIT_CALL(BPF_FUNC_sk_fullsock), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, offsetof(struct bpf_sock, dst_port)), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_CGROUP_SKB, + .result = ACCEPT, +}, +{ + "sk_fullsock(skb->sk): sk->dst_port [half load]", .insns = { BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)), BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2), @@ -139,7 +157,64 @@ .result = ACCEPT, }, { - "sk_fullsock(skb->sk): sk->dst_port [load 2nd byte]", + "sk_fullsock(skb->sk): sk->dst_port [half load] (invalid)", + .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)), + BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_EMIT_CALL(BPF_FUNC_sk_fullsock), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_0, offsetof(struct bpf_sock, dst_port) + 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_CGROUP_SKB, + .result = REJECT, + .errstr = "invalid sock access", +}, +{ + "sk_fullsock(skb->sk): sk->dst_port [byte load]", + .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)), + BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_EMIT_CALL(BPF_FUNC_sk_fullsock), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_LDX_MEM(BPF_B, BPF_REG_2, BPF_REG_0, offsetof(struct bpf_sock, dst_port)), + BPF_LDX_MEM(BPF_B, BPF_REG_2, BPF_REG_0, offsetof(struct bpf_sock, dst_port) + 1), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_CGROUP_SKB, + .result = ACCEPT, +}, +{ + "sk_fullsock(skb->sk): sk->dst_port [byte load] (invalid)", + .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)), + BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_EMIT_CALL(BPF_FUNC_sk_fullsock), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, offsetof(struct bpf_sock, dst_port) + 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_CGROUP_SKB, + .result = REJECT, + .errstr = "invalid sock access", +}, +{ + "sk_fullsock(skb->sk): past sk->dst_port [half load] (invalid)", .insns = { BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)), BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2), @@ -149,7 +224,7 @@ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2), BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), - BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, offsetof(struct bpf_sock, dst_port) + 1), + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_0, offsetofend(struct bpf_sock, dst_port)), BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, @@ -427,7 +502,7 @@ .fixup_sk_storage_map = { 11 }, .prog_type = BPF_PROG_TYPE_SCHED_CLS, .result = REJECT, - .errstr = "R3 type=inv expected=fp", + .errstr = "R3 type=scalar expected=fp", }, { "sk_storage_get(map, skb->sk, &stack_value, 1): stack_value", diff --git a/tools/testing/selftests/bpf/verifier/spill_fill.c b/tools/testing/selftests/bpf/verifier/spill_fill.c index 1a8eb9672bd1..e23f07175e1b 100644 --- a/tools/testing/selftests/bpf/verifier/spill_fill.c +++ b/tools/testing/selftests/bpf/verifier/spill_fill.c @@ -84,7 +84,7 @@ }, .fixup_map_ringbuf = { 1 }, .result = REJECT, - .errstr = "R0 pointer arithmetic on mem_or_null prohibited", + .errstr = "R0 pointer arithmetic on alloc_mem_or_null prohibited", }, { "check corrupted spill/fill", @@ -102,7 +102,7 @@ BPF_EXIT_INSN(), }, .errstr_unpriv = "attempt to corrupt spilled", - .errstr = "R0 invalid mem access 'inv", + .errstr = "R0 invalid mem access 'scalar'", .result = REJECT, .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, @@ -147,11 +147,11 @@ BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_10, -8), /* r0 = r2 */ BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), - /* r0 += r4 R0=pkt R2=pkt R3=pkt_end R4=inv20 */ + /* r0 += r4 R0=pkt R2=pkt R3=pkt_end R4=20 */ BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_4), - /* if (r0 > r3) R0=pkt,off=20 R2=pkt R3=pkt_end R4=inv20 */ + /* if (r0 > r3) R0=pkt,off=20 R2=pkt R3=pkt_end R4=20 */ BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1), - /* r0 = *(u32 *)r2 R0=pkt,off=20,r=20 R2=pkt,r=20 R3=pkt_end R4=inv20 */ + /* r0 = *(u32 *)r2 R0=pkt,off=20,r=20 R2=pkt,r=20 R3=pkt_end R4=20 */ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_2, 0), BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), @@ -190,11 +190,11 @@ BPF_LDX_MEM(BPF_H, BPF_REG_4, BPF_REG_10, -8), /* r0 = r2 */ BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), - /* r0 += r4 R0=pkt R2=pkt R3=pkt_end R4=inv,umax=65535 */ + /* r0 += r4 R0=pkt R2=pkt R3=pkt_end R4=umax=65535 */ BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_4), - /* if (r0 > r3) R0=pkt,umax=65535 R2=pkt R3=pkt_end R4=inv,umax=65535 */ + /* if (r0 > r3) R0=pkt,umax=65535 R2=pkt R3=pkt_end R4=umax=65535 */ BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1), - /* r0 = *(u32 *)r2 R0=pkt,umax=65535 R2=pkt R3=pkt_end R4=inv20 */ + /* r0 = *(u32 *)r2 R0=pkt,umax=65535 R2=pkt R3=pkt_end R4=20 */ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_2, 0), BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), @@ -222,11 +222,11 @@ BPF_LDX_MEM(BPF_H, BPF_REG_4, BPF_REG_10, -8), /* r0 = r2 */ BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), - /* r0 += r4 R0=pkt R2=pkt R3=pkt_end R4=inv,umax=65535 */ + /* r0 += r4 R0=pkt R2=pkt R3=pkt_end R4=umax=65535 */ BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_4), - /* if (r0 > r3) R0=pkt,umax=65535 R2=pkt R3=pkt_end R4=inv,umax=65535 */ + /* if (r0 > r3) R0=pkt,umax=65535 R2=pkt R3=pkt_end R4=umax=65535 */ BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1), - /* r0 = *(u32 *)r2 R0=pkt,umax=65535 R2=pkt R3=pkt_end R4=inv20 */ + /* r0 = *(u32 *)r2 R0=pkt,umax=65535 R2=pkt R3=pkt_end R4=20 */ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_2, 0), BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), @@ -250,11 +250,11 @@ BPF_LDX_MEM(BPF_H, BPF_REG_4, BPF_REG_10, -6), /* r0 = r2 */ BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), - /* r0 += r4 R0=pkt R2=pkt R3=pkt_end R4=inv,umax=65535 */ + /* r0 += r4 R0=pkt R2=pkt R3=pkt_end R4=umax=65535 */ BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_4), - /* if (r0 > r3) R0=pkt,umax=65535 R2=pkt R3=pkt_end R4=inv,umax=65535 */ + /* if (r0 > r3) R0=pkt,umax=65535 R2=pkt R3=pkt_end R4=umax=65535 */ BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1), - /* r0 = *(u32 *)r2 R0=pkt,umax=65535 R2=pkt R3=pkt_end R4=inv20 */ + /* r0 = *(u32 *)r2 R0=pkt,umax=65535 R2=pkt R3=pkt_end R4=20 */ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_2, 0), BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), @@ -280,11 +280,11 @@ BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_10, -4), /* r0 = r2 */ BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), - /* r0 += r4 R0=pkt R2=pkt R3=pkt_end R4=inv,umax=U32_MAX */ + /* r0 += r4 R0=pkt R2=pkt R3=pkt_end R4=umax=U32_MAX */ BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_4), - /* if (r0 > r3) R0=pkt,umax=U32_MAX R2=pkt R3=pkt_end R4=inv */ + /* if (r0 > r3) R0=pkt,umax=U32_MAX R2=pkt R3=pkt_end R4= */ BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1), - /* r0 = *(u32 *)r2 R0=pkt,umax=U32_MAX R2=pkt R3=pkt_end R4=inv */ + /* r0 = *(u32 *)r2 R0=pkt,umax=U32_MAX R2=pkt R3=pkt_end R4= */ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_2, 0), BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), @@ -305,13 +305,13 @@ BPF_JMP_IMM(BPF_JLE, BPF_REG_4, 40, 2), BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), - /* *(u32 *)(r10 -8) = r4 R4=inv,umax=40 */ + /* *(u32 *)(r10 -8) = r4 R4=umax=40 */ BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_4, -8), /* r4 = (*u32 *)(r10 - 8) */ BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_10, -8), - /* r2 += r4 R2=pkt R4=inv,umax=40 */ + /* r2 += r4 R2=pkt R4=umax=40 */ BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_4), - /* r0 = r2 R2=pkt,umax=40 R4=inv,umax=40 */ + /* r0 = r2 R2=pkt,umax=40 R4=umax=40 */ BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), /* r2 += 20 R0=pkt,umax=40 R2=pkt,umax=40 */ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, 20), diff --git a/tools/testing/selftests/bpf/verifier/unpriv.c b/tools/testing/selftests/bpf/verifier/unpriv.c index 111801aea5e3..878ca26c3f0a 100644 --- a/tools/testing/selftests/bpf/verifier/unpriv.c +++ b/tools/testing/selftests/bpf/verifier/unpriv.c @@ -214,7 +214,7 @@ BPF_EXIT_INSN(), }, .result = REJECT, - .errstr = "R1 type=inv expected=ctx", + .errstr = "R1 type=scalar expected=ctx", .prog_type = BPF_PROG_TYPE_SCHED_CLS, }, { @@ -420,7 +420,7 @@ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_7, 0), BPF_EXIT_INSN(), }, - .errstr_unpriv = "R7 invalid mem access 'inv'", + .errstr_unpriv = "R7 invalid mem access 'scalar'", .result_unpriv = REJECT, .result = ACCEPT, .retval = 0, diff --git a/tools/testing/selftests/bpf/verifier/value_illegal_alu.c b/tools/testing/selftests/bpf/verifier/value_illegal_alu.c index 489062867218..d6f29eb4bd57 100644 --- a/tools/testing/selftests/bpf/verifier/value_illegal_alu.c +++ b/tools/testing/selftests/bpf/verifier/value_illegal_alu.c @@ -64,7 +64,7 @@ }, .fixup_map_hash_48b = { 3 }, .errstr_unpriv = "R0 pointer arithmetic prohibited", - .errstr = "invalid mem access 'inv'", + .errstr = "invalid mem access 'scalar'", .result = REJECT, .result_unpriv = REJECT, .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, @@ -89,7 +89,7 @@ }, .fixup_map_hash_48b = { 3 }, .errstr_unpriv = "leaking pointer from stack off -8", - .errstr = "R0 invalid mem access 'inv'", + .errstr = "R0 invalid mem access 'scalar'", .result = REJECT, .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, diff --git a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c index 359f3e8f8b60..249187d3c530 100644 --- a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c +++ b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c @@ -397,7 +397,7 @@ .fixup_map_array_48b = { 1 }, .result = ACCEPT, .result_unpriv = REJECT, - .errstr_unpriv = "R0 invalid mem access 'inv'", + .errstr_unpriv = "R0 invalid mem access 'scalar'", .retval = 0, }, { @@ -1074,7 +1074,7 @@ }, .fixup_map_array_48b = { 3 }, .result = REJECT, - .errstr = "R0 invalid mem access 'inv'", + .errstr = "R0 invalid mem access 'scalar'", .errstr_unpriv = "R0 pointer -= pointer prohibited", }, { diff --git a/tools/testing/selftests/bpf/verifier/var_off.c b/tools/testing/selftests/bpf/verifier/var_off.c index eab1f7f56e2f..187c6f6e32bc 100644 --- a/tools/testing/selftests/bpf/verifier/var_off.c +++ b/tools/testing/selftests/bpf/verifier/var_off.c @@ -131,7 +131,7 @@ * write might have overwritten the spilled pointer (i.e. we lose track * of the spilled register when we analyze the write). */ - .errstr = "R2 invalid mem access 'inv'", + .errstr = "R2 invalid mem access 'scalar'", .result = REJECT, }, { diff --git a/tools/testing/selftests/bpf/vmtest.sh b/tools/testing/selftests/bpf/vmtest.sh index b3afd43549fa..e0bb04a97e10 100755 --- a/tools/testing/selftests/bpf/vmtest.sh +++ b/tools/testing/selftests/bpf/vmtest.sh @@ -241,7 +241,7 @@ EOF -nodefaults \ -display none \ -serial mon:stdio \ - "${qemu_flags[@]}" \ + "${QEMU_FLAGS[@]}" \ -enable-kvm \ -m 4G \ -drive file="${rootfs_img}",format=raw,index=1,media=disk,if=virtio,cache=none \ diff --git a/tools/testing/selftests/bpf/xdp_redirect_multi.c b/tools/testing/selftests/bpf/xdp_redirect_multi.c index 51c8224b4ccc..aaedbf4955c3 100644 --- a/tools/testing/selftests/bpf/xdp_redirect_multi.c +++ b/tools/testing/selftests/bpf/xdp_redirect_multi.c @@ -32,12 +32,12 @@ static void int_exit(int sig) int i; for (i = 0; ifaces[i] > 0; i++) { - if (bpf_get_link_xdp_id(ifaces[i], &prog_id, xdp_flags)) { - printf("bpf_get_link_xdp_id failed\n"); + if (bpf_xdp_query_id(ifaces[i], xdp_flags, &prog_id)) { + printf("bpf_xdp_query_id failed\n"); exit(1); } if (prog_id) - bpf_set_link_xdp_fd(ifaces[i], -1, xdp_flags); + bpf_xdp_detach(ifaces[i], xdp_flags, NULL); } exit(0); @@ -210,7 +210,7 @@ int main(int argc, char **argv) } /* bind prog_fd to each interface */ - ret = bpf_set_link_xdp_fd(ifindex, prog_fd, xdp_flags); + ret = bpf_xdp_attach(ifindex, prog_fd, xdp_flags, NULL); if (ret) { printf("Set xdp fd failed on %d\n", ifindex); goto err_out; diff --git a/tools/testing/selftests/bpf/xdping.c b/tools/testing/selftests/bpf/xdping.c index baa870a759a2..c567856fd1bc 100644 --- a/tools/testing/selftests/bpf/xdping.c +++ b/tools/testing/selftests/bpf/xdping.c @@ -29,7 +29,7 @@ static __u32 xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST; static void cleanup(int sig) { - bpf_set_link_xdp_fd(ifindex, -1, xdp_flags); + bpf_xdp_detach(ifindex, xdp_flags, NULL); if (sig) exit(1); } @@ -203,7 +203,7 @@ int main(int argc, char **argv) printf("XDP setup disrupts network connectivity, hit Ctrl+C to quit\n"); - if (bpf_set_link_xdp_fd(ifindex, prog_fd, xdp_flags) < 0) { + if (bpf_xdp_attach(ifindex, prog_fd, xdp_flags, NULL) < 0) { fprintf(stderr, "Link set xdp fd failed for %s\n", ifname); goto done; } diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c index 0a5d23da486d..5f8296d29e77 100644 --- a/tools/testing/selftests/bpf/xdpxceiver.c +++ b/tools/testing/selftests/bpf/xdpxceiver.c @@ -266,22 +266,24 @@ static int xsk_configure_umem(struct xsk_umem_info *umem, void *buffer, u64 size } static int xsk_configure_socket(struct xsk_socket_info *xsk, struct xsk_umem_info *umem, - struct ifobject *ifobject, u32 qid) + struct ifobject *ifobject, bool shared) { - struct xsk_socket_config cfg; + struct xsk_socket_config cfg = {}; struct xsk_ring_cons *rxr; struct xsk_ring_prod *txr; xsk->umem = umem; cfg.rx_size = xsk->rxqsize; cfg.tx_size = XSK_RING_PROD__DEFAULT_NUM_DESCS; - cfg.libbpf_flags = 0; + cfg.libbpf_flags = XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD; cfg.xdp_flags = ifobject->xdp_flags; cfg.bind_flags = ifobject->bind_flags; + if (shared) + cfg.bind_flags |= XDP_SHARED_UMEM; txr = ifobject->tx_on ? &xsk->tx : NULL; rxr = ifobject->rx_on ? &xsk->rx : NULL; - return xsk_socket__create(&xsk->xsk, ifobject->ifname, qid, umem->umem, rxr, txr, &cfg); + return xsk_socket__create(&xsk->xsk, ifobject->ifname, 0, umem->umem, rxr, txr, &cfg); } static struct option long_options[] = { @@ -387,7 +389,6 @@ static void __test_spec_init(struct test_spec *test, struct ifobject *ifobj_tx, for (i = 0; i < MAX_INTERFACES; i++) { struct ifobject *ifobj = i ? ifobj_rx : ifobj_tx; - ifobj->umem = &ifobj->umem_arr[0]; ifobj->xsk = &ifobj->xsk_arr[0]; ifobj->use_poll = false; ifobj->pacing_on = true; @@ -401,11 +402,12 @@ static void __test_spec_init(struct test_spec *test, struct ifobject *ifobj_tx, ifobj->tx_on = false; } + memset(ifobj->umem, 0, sizeof(*ifobj->umem)); + ifobj->umem->num_frames = DEFAULT_UMEM_BUFFERS; + ifobj->umem->frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE; + for (j = 0; j < MAX_SOCKETS; j++) { - memset(&ifobj->umem_arr[j], 0, sizeof(ifobj->umem_arr[j])); memset(&ifobj->xsk_arr[j], 0, sizeof(ifobj->xsk_arr[j])); - ifobj->umem_arr[j].num_frames = DEFAULT_UMEM_BUFFERS; - ifobj->umem_arr[j].frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE; ifobj->xsk_arr[j].rxqsize = XSK_RING_CONS__DEFAULT_NUM_DESCS; } } @@ -906,7 +908,10 @@ static bool rx_stats_are_valid(struct ifobject *ifobject) return true; case STAT_TEST_RX_FULL: xsk_stat = stats.rx_ring_full; - expected_stat -= RX_FULL_RXQSIZE; + if (ifobject->umem->num_frames < XSK_RING_PROD__DEFAULT_NUM_DESCS) + expected_stat = ifobject->umem->num_frames - RX_FULL_RXQSIZE; + else + expected_stat = XSK_RING_PROD__DEFAULT_NUM_DESCS - RX_FULL_RXQSIZE; break; case STAT_TEST_RX_FILL_EMPTY: xsk_stat = stats.rx_fill_ring_empty_descs; @@ -947,7 +952,10 @@ static void tx_stats_validate(struct ifobject *ifobject) static void thread_common_ops(struct test_spec *test, struct ifobject *ifobject) { + u64 umem_sz = ifobject->umem->num_frames * ifobject->umem->frame_size; int mmap_flags = MAP_PRIVATE | MAP_ANONYMOUS | MAP_NORESERVE; + int ret, ifindex; + void *bufs; u32 i; ifobject->ns_fd = switch_namespace(ifobject->nsname); @@ -955,23 +963,20 @@ static void thread_common_ops(struct test_spec *test, struct ifobject *ifobject) if (ifobject->umem->unaligned_mode) mmap_flags |= MAP_HUGETLB; - for (i = 0; i < test->nb_sockets; i++) { - u64 umem_sz = ifobject->umem->num_frames * ifobject->umem->frame_size; - u32 ctr = 0; - void *bufs; - int ret; + bufs = mmap(NULL, umem_sz, PROT_READ | PROT_WRITE, mmap_flags, -1, 0); + if (bufs == MAP_FAILED) + exit_with_error(errno); - bufs = mmap(NULL, umem_sz, PROT_READ | PROT_WRITE, mmap_flags, -1, 0); - if (bufs == MAP_FAILED) - exit_with_error(errno); + ret = xsk_configure_umem(ifobject->umem, bufs, umem_sz); + if (ret) + exit_with_error(-ret); - ret = xsk_configure_umem(&ifobject->umem_arr[i], bufs, umem_sz); - if (ret) - exit_with_error(-ret); + for (i = 0; i < test->nb_sockets; i++) { + u32 ctr = 0; while (ctr++ < SOCK_RECONF_CTR) { - ret = xsk_configure_socket(&ifobject->xsk_arr[i], &ifobject->umem_arr[i], - ifobject, i); + ret = xsk_configure_socket(&ifobject->xsk_arr[i], ifobject->umem, + ifobject, !!i); if (!ret) break; @@ -982,8 +987,22 @@ static void thread_common_ops(struct test_spec *test, struct ifobject *ifobject) } } - ifobject->umem = &ifobject->umem_arr[0]; ifobject->xsk = &ifobject->xsk_arr[0]; + + if (!ifobject->rx_on) + return; + + ifindex = if_nametoindex(ifobject->ifname); + if (!ifindex) + exit_with_error(errno); + + ret = xsk_setup_xdp_prog(ifindex, &ifobject->xsk_map_fd); + if (ret) + exit_with_error(-ret); + + ret = xsk_socket__update_xskmap(ifobject->xsk->xsk, ifobject->xsk_map_fd); + if (ret) + exit_with_error(-ret); } static void testapp_cleanup_xsk_res(struct ifobject *ifobj) @@ -1139,14 +1158,16 @@ static void testapp_bidi(struct test_spec *test) static void swap_xsk_resources(struct ifobject *ifobj_tx, struct ifobject *ifobj_rx) { + int ret; + xsk_socket__delete(ifobj_tx->xsk->xsk); - xsk_umem__delete(ifobj_tx->umem->umem); xsk_socket__delete(ifobj_rx->xsk->xsk); - xsk_umem__delete(ifobj_rx->umem->umem); - ifobj_tx->umem = &ifobj_tx->umem_arr[1]; ifobj_tx->xsk = &ifobj_tx->xsk_arr[1]; - ifobj_rx->umem = &ifobj_rx->umem_arr[1]; ifobj_rx->xsk = &ifobj_rx->xsk_arr[1]; + + ret = xsk_socket__update_xskmap(ifobj_rx->xsk->xsk, ifobj_rx->xsk_map_fd); + if (ret) + exit_with_error(-ret); } static void testapp_bpf_res(struct test_spec *test) @@ -1405,13 +1426,13 @@ static struct ifobject *ifobject_create(void) if (!ifobj->xsk_arr) goto out_xsk_arr; - ifobj->umem_arr = calloc(MAX_SOCKETS, sizeof(*ifobj->umem_arr)); - if (!ifobj->umem_arr) - goto out_umem_arr; + ifobj->umem = calloc(1, sizeof(*ifobj->umem)); + if (!ifobj->umem) + goto out_umem; return ifobj; -out_umem_arr: +out_umem: free(ifobj->xsk_arr); out_xsk_arr: free(ifobj); @@ -1420,7 +1441,7 @@ out_xsk_arr: static void ifobject_delete(struct ifobject *ifobj) { - free(ifobj->umem_arr); + free(ifobj->umem); free(ifobj->xsk_arr); free(ifobj); } diff --git a/tools/testing/selftests/bpf/xdpxceiver.h b/tools/testing/selftests/bpf/xdpxceiver.h index 2f705f44b748..62a3e6388632 100644 --- a/tools/testing/selftests/bpf/xdpxceiver.h +++ b/tools/testing/selftests/bpf/xdpxceiver.h @@ -125,10 +125,10 @@ struct ifobject { struct xsk_socket_info *xsk; struct xsk_socket_info *xsk_arr; struct xsk_umem_info *umem; - struct xsk_umem_info *umem_arr; thread_func_t func_ptr; struct pkt_stream *pkt_stream; int ns_fd; + int xsk_map_fd; u32 dst_ip; u32 src_ip; u32 xdp_flags; diff --git a/tools/testing/selftests/cgroup/cgroup_util.c b/tools/testing/selftests/cgroup/cgroup_util.c index 0cf7e90c0052..dbaa7aabbb4a 100644 --- a/tools/testing/selftests/cgroup/cgroup_util.c +++ b/tools/testing/selftests/cgroup/cgroup_util.c @@ -583,7 +583,7 @@ int clone_into_cgroup_run_wait(const char *cgroup) return 0; } -int cg_prepare_for_wait(const char *cgroup) +static int __prepare_for_wait(const char *cgroup, const char *filename) { int fd, ret = -1; @@ -591,8 +591,7 @@ int cg_prepare_for_wait(const char *cgroup) if (fd == -1) return fd; - ret = inotify_add_watch(fd, cg_control(cgroup, "cgroup.events"), - IN_MODIFY); + ret = inotify_add_watch(fd, cg_control(cgroup, filename), IN_MODIFY); if (ret == -1) { close(fd); fd = -1; @@ -601,6 +600,16 @@ int cg_prepare_for_wait(const char *cgroup) return fd; } +int cg_prepare_for_wait(const char *cgroup) +{ + return __prepare_for_wait(cgroup, "cgroup.events"); +} + +int memcg_prepare_for_wait(const char *cgroup) +{ + return __prepare_for_wait(cgroup, "memory.events"); +} + int cg_wait_for(int fd) { int ret = -1; diff --git a/tools/testing/selftests/cgroup/cgroup_util.h b/tools/testing/selftests/cgroup/cgroup_util.h index 4f66d10626d2..628738532ac9 100644 --- a/tools/testing/selftests/cgroup/cgroup_util.h +++ b/tools/testing/selftests/cgroup/cgroup_util.h @@ -55,4 +55,5 @@ extern int clone_reap(pid_t pid, int options); extern int clone_into_cgroup_run_wait(const char *cgroup); extern int dirfd_open_opath(const char *dir); extern int cg_prepare_for_wait(const char *cgroup); +extern int memcg_prepare_for_wait(const char *cgroup); extern int cg_wait_for(int fd); diff --git a/tools/testing/selftests/cgroup/test_memcontrol.c b/tools/testing/selftests/cgroup/test_memcontrol.c index c19a97dd02d4..36ccf2322e21 100644 --- a/tools/testing/selftests/cgroup/test_memcontrol.c +++ b/tools/testing/selftests/cgroup/test_memcontrol.c @@ -16,6 +16,7 @@ #include <netinet/in.h> #include <netdb.h> #include <errno.h> +#include <sys/mman.h> #include "../kselftest.h" #include "cgroup_util.h" @@ -628,6 +629,82 @@ cleanup: return ret; } +static int alloc_anon_mlock(const char *cgroup, void *arg) +{ + size_t size = (size_t)arg; + void *buf; + + buf = mmap(NULL, size, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANON, + 0, 0); + if (buf == MAP_FAILED) + return -1; + + mlock(buf, size); + munmap(buf, size); + return 0; +} + +/* + * This test checks that memory.high is able to throttle big single shot + * allocation i.e. large allocation within one kernel entry. + */ +static int test_memcg_high_sync(const char *root) +{ + int ret = KSFT_FAIL, pid, fd = -1; + char *memcg; + long pre_high, pre_max; + long post_high, post_max; + + memcg = cg_name(root, "memcg_test"); + if (!memcg) + goto cleanup; + + if (cg_create(memcg)) + goto cleanup; + + pre_high = cg_read_key_long(memcg, "memory.events", "high "); + pre_max = cg_read_key_long(memcg, "memory.events", "max "); + if (pre_high < 0 || pre_max < 0) + goto cleanup; + + if (cg_write(memcg, "memory.swap.max", "0")) + goto cleanup; + + if (cg_write(memcg, "memory.high", "30M")) + goto cleanup; + + if (cg_write(memcg, "memory.max", "140M")) + goto cleanup; + + fd = memcg_prepare_for_wait(memcg); + if (fd < 0) + goto cleanup; + + pid = cg_run_nowait(memcg, alloc_anon_mlock, (void *)MB(200)); + if (pid < 0) + goto cleanup; + + cg_wait_for(fd); + + post_high = cg_read_key_long(memcg, "memory.events", "high "); + post_max = cg_read_key_long(memcg, "memory.events", "max "); + if (post_high < 0 || post_max < 0) + goto cleanup; + + if (pre_high == post_high || pre_max != post_max) + goto cleanup; + + ret = KSFT_PASS; + +cleanup: + if (fd >= 0) + close(fd); + cg_destroy(memcg); + free(memcg); + + return ret; +} + /* * This test checks that memory.max limits the amount of * memory which can be consumed by either anonymous memory @@ -1180,6 +1257,7 @@ struct memcg_test { T(test_memcg_min), T(test_memcg_low), T(test_memcg_high), + T(test_memcg_high_sync), T(test_memcg_max), T(test_memcg_oom_events), T(test_memcg_swap_max), diff --git a/tools/testing/selftests/clone3/clone3.c b/tools/testing/selftests/clone3/clone3.c index 076cf4325f78..cd4582129c7d 100644 --- a/tools/testing/selftests/clone3/clone3.c +++ b/tools/testing/selftests/clone3/clone3.c @@ -126,8 +126,6 @@ static void test_clone3(uint64_t flags, size_t size, int expected, int main(int argc, char *argv[]) { - pid_t pid; - uid_t uid = getuid(); ksft_print_header(); diff --git a/tools/testing/selftests/cpufreq/main.sh b/tools/testing/selftests/cpufreq/main.sh index 31f8c9a76c5f..60ce18ed0666 100755 --- a/tools/testing/selftests/cpufreq/main.sh +++ b/tools/testing/selftests/cpufreq/main.sh @@ -194,5 +194,5 @@ prerequisite # Run requested functions clear_dumps $OUTFILE -do_test >> $OUTFILE.txt +do_test | tee -a $OUTFILE.txt dmesg_dumps $OUTFILE diff --git a/tools/testing/selftests/damon/Makefile b/tools/testing/selftests/damon/Makefile index 937d36ae9a69..0470c5f3e690 100644 --- a/tools/testing/selftests/damon/Makefile +++ b/tools/testing/selftests/damon/Makefile @@ -6,5 +6,6 @@ TEST_GEN_FILES += huge_count_read_write TEST_FILES = _chk_dependency.sh _debugfs_common.sh TEST_PROGS = debugfs_attrs.sh debugfs_schemes.sh debugfs_target_ids.sh TEST_PROGS += debugfs_empty_targets.sh debugfs_huge_count_read_write.sh +TEST_PROGS += sysfs.sh include ../lib.mk diff --git a/tools/testing/selftests/damon/sysfs.sh b/tools/testing/selftests/damon/sysfs.sh new file mode 100644 index 000000000000..2e3ae77cb6db --- /dev/null +++ b/tools/testing/selftests/damon/sysfs.sh @@ -0,0 +1,306 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# Kselftest frmework requirement - SKIP code is 4. +ksft_skip=4 + +ensure_write_succ() +{ + file=$1 + content=$2 + reason=$3 + + if ! echo "$content" > "$file" + then + echo "writing $content to $file failed" + echo "expected success because $reason" + exit 1 + fi +} + +ensure_write_fail() +{ + file=$1 + content=$2 + reason=$3 + + if echo "$content" > "$file" + then + echo "writing $content to $file succeed ($fail_reason)" + echo "expected failure because $reason" + exit 1 + fi +} + +ensure_dir() +{ + dir=$1 + to_ensure=$2 + if [ "$to_ensure" = "exist" ] && [ ! -d "$dir" ] + then + echo "$dir dir is expected but not found" + exit 1 + elif [ "$to_ensure" = "not_exist" ] && [ -d "$dir" ] + then + echo "$dir dir is not expected but found" + exit 1 + fi +} + +ensure_file() +{ + file=$1 + to_ensure=$2 + permission=$3 + if [ "$to_ensure" = "exist" ] + then + if [ ! -f "$file" ] + then + echo "$file is expected but not found" + exit 1 + fi + perm=$(stat -c "%a" "$file") + if [ ! "$perm" = "$permission" ] + then + echo "$file permission: expected $permission but $perm" + exit 1 + fi + elif [ "$to_ensure" = "not_exist" ] && [ -f "$dir" ] + then + echo "$file is not expected but found" + exit 1 + fi +} + +test_range() +{ + range_dir=$1 + ensure_dir "$range_dir" "exist" + ensure_file "$range_dir/min" "exist" 600 + ensure_file "$range_dir/max" "exist" 600 +} + +test_stats() +{ + stats_dir=$1 + ensure_dir "$stats_dir" "exist" + for f in nr_tried sz_tried nr_applied sz_applied qt_exceeds + do + ensure_file "$stats_dir/$f" "exist" "400" + done +} + +test_watermarks() +{ + watermarks_dir=$1 + ensure_dir "$watermarks_dir" "exist" + ensure_file "$watermarks_dir/metric" "exist" "600" + ensure_file "$watermarks_dir/interval_us" "exist" "600" + ensure_file "$watermarks_dir/high" "exist" "600" + ensure_file "$watermarks_dir/mid" "exist" "600" + ensure_file "$watermarks_dir/low" "exist" "600" +} + +test_weights() +{ + weights_dir=$1 + ensure_dir "$weights_dir" "exist" + ensure_file "$weights_dir/sz_permil" "exist" "600" + ensure_file "$weights_dir/nr_accesses_permil" "exist" "600" + ensure_file "$weights_dir/age_permil" "exist" "600" +} + +test_quotas() +{ + quotas_dir=$1 + ensure_dir "$quotas_dir" "exist" + ensure_file "$quotas_dir/ms" "exist" 600 + ensure_file "$quotas_dir/bytes" "exist" 600 + ensure_file "$quotas_dir/reset_interval_ms" "exist" 600 + test_weights "$quotas_dir/weights" +} + +test_access_pattern() +{ + access_pattern_dir=$1 + ensure_dir "$access_pattern_dir" "exist" + test_range "$access_pattern_dir/age" + test_range "$access_pattern_dir/nr_accesses" + test_range "$access_pattern_dir/sz" +} + +test_scheme() +{ + scheme_dir=$1 + ensure_dir "$scheme_dir" "exist" + ensure_file "$scheme_dir/action" "exist" "600" + test_access_pattern "$scheme_dir/access_pattern" + test_quotas "$scheme_dir/quotas" + test_watermarks "$scheme_dir/watermarks" + test_stats "$scheme_dir/stats" +} + +test_schemes() +{ + schemes_dir=$1 + ensure_dir "$schemes_dir" "exist" + ensure_file "$schemes_dir/nr_schemes" "exist" 600 + + ensure_write_succ "$schemes_dir/nr_schemes" "1" "valid input" + test_scheme "$schemes_dir/0" + + ensure_write_succ "$schemes_dir/nr_schemes" "2" "valid input" + test_scheme "$schemes_dir/0" + test_scheme "$schemes_dir/1" + + ensure_write_succ "$schemes_dir/nr_schemes" "0" "valid input" + ensure_dir "$schemes_dir/0" "not_exist" + ensure_dir "$schemes_dir/1" "not_exist" +} + +test_region() +{ + region_dir=$1 + ensure_dir "$region_dir" "exist" + ensure_file "$region_dir/start" "exist" 600 + ensure_file "$region_dir/end" "exist" 600 +} + +test_regions() +{ + regions_dir=$1 + ensure_dir "$regions_dir" "exist" + ensure_file "$regions_dir/nr_regions" "exist" 600 + + ensure_write_succ "$regions_dir/nr_regions" "1" "valid input" + test_region "$regions_dir/0" + + ensure_write_succ "$regions_dir/nr_regions" "2" "valid input" + test_region "$regions_dir/0" + test_region "$regions_dir/1" + + ensure_write_succ "$regions_dir/nr_regions" "0" "valid input" + ensure_dir "$regions_dir/0" "not_exist" + ensure_dir "$regions_dir/1" "not_exist" +} + +test_target() +{ + target_dir=$1 + ensure_dir "$target_dir" "exist" + ensure_file "$target_dir/pid_target" "exist" "600" + test_regions "$target_dir/regions" +} + +test_targets() +{ + targets_dir=$1 + ensure_dir "$targets_dir" "exist" + ensure_file "$targets_dir/nr_targets" "exist" 600 + + ensure_write_succ "$targets_dir/nr_targets" "1" "valid input" + test_target "$targets_dir/0" + + ensure_write_succ "$targets_dir/nr_targets" "2" "valid input" + test_target "$targets_dir/0" + test_target "$targets_dir/1" + + ensure_write_succ "$targets_dir/nr_targets" "0" "valid input" + ensure_dir "$targets_dir/0" "not_exist" + ensure_dir "$targets_dir/1" "not_exist" +} + +test_intervals() +{ + intervals_dir=$1 + ensure_dir "$intervals_dir" "exist" + ensure_file "$intervals_dir/aggr_us" "exist" "600" + ensure_file "$intervals_dir/sample_us" "exist" "600" + ensure_file "$intervals_dir/update_us" "exist" "600" +} + +test_monitoring_attrs() +{ + monitoring_attrs_dir=$1 + ensure_dir "$monitoring_attrs_dir" "exist" + test_intervals "$monitoring_attrs_dir/intervals" + test_range "$monitoring_attrs_dir/nr_regions" +} + +test_context() +{ + context_dir=$1 + ensure_dir "$context_dir" "exist" + ensure_file "$context_dir/operations" "exist" 600 + test_monitoring_attrs "$context_dir/monitoring_attrs" + test_targets "$context_dir/targets" + test_schemes "$context_dir/schemes" +} + +test_contexts() +{ + contexts_dir=$1 + ensure_dir "$contexts_dir" "exist" + ensure_file "$contexts_dir/nr_contexts" "exist" 600 + + ensure_write_succ "$contexts_dir/nr_contexts" "1" "valid input" + test_context "$contexts_dir/0" + + ensure_write_fail "$contexts_dir/nr_contexts" "2" "only 0/1 are supported" + test_context "$contexts_dir/0" + + ensure_write_succ "$contexts_dir/nr_contexts" "0" "valid input" + ensure_dir "$contexts_dir/0" "not_exist" +} + +test_kdamond() +{ + kdamond_dir=$1 + ensure_dir "$kdamond_dir" "exist" + ensure_file "$kdamond_dir/state" "exist" "600" + ensure_file "$kdamond_dir/pid" "exist" 400 + test_contexts "$kdamond_dir/contexts" +} + +test_kdamonds() +{ + kdamonds_dir=$1 + ensure_dir "$kdamonds_dir" "exist" + + ensure_file "$kdamonds_dir/nr_kdamonds" "exist" "600" + + ensure_write_succ "$kdamonds_dir/nr_kdamonds" "1" "valid input" + test_kdamond "$kdamonds_dir/0" + + ensure_write_succ "$kdamonds_dir/nr_kdamonds" "2" "valid input" + test_kdamond "$kdamonds_dir/0" + test_kdamond "$kdamonds_dir/1" + + ensure_write_succ "$kdamonds_dir/nr_kdamonds" "0" "valid input" + ensure_dir "$kdamonds_dir/0" "not_exist" + ensure_dir "$kdamonds_dir/1" "not_exist" +} + +test_damon_sysfs() +{ + damon_sysfs=$1 + if [ ! -d "$damon_sysfs" ] + then + echo "$damon_sysfs not found" + exit $ksft_skip + fi + + test_kdamonds "$damon_sysfs/kdamonds" +} + +check_dependencies() +{ + if [ $EUID -ne 0 ] + then + echo "Run as root" + exit $ksft_skip + fi +} + +check_dependencies +test_damon_sysfs "/sys/kernel/mm/damon/admin" diff --git a/tools/testing/selftests/drivers/net/mlxsw/hw_stats_l3.sh b/tools/testing/selftests/drivers/net/mlxsw/hw_stats_l3.sh new file mode 100755 index 000000000000..941ba4c485c9 --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/hw_stats_l3.sh @@ -0,0 +1,31 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +lib_dir=$(dirname $0)/../../../net/forwarding + +ALL_TESTS=" + l3_monitor_test +" +NUM_NETIFS=0 +source $lib_dir/lib.sh + +swp=$NETIF_NO_CABLE + +cleanup() +{ + pre_cleanup +} + +l3_monitor_test() +{ + hw_stats_monitor_test $swp l3 \ + "ip addr add dev $swp 192.0.2.1/28" \ + "ip addr del dev $swp 192.0.2.1/28" +} + +trap cleanup EXIT + +setup_wait +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh index bcb110e830ce..dea33dc93790 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh @@ -50,8 +50,8 @@ for current_test in ${TESTS:-$ALL_TESTS}; do else log_test "'$current_test' [$profile] overflow $target" fi + RET_FIN=$(( RET_FIN || RET )) done - RET_FIN=$(( RET_FIN || RET )) done done current_test="" diff --git a/tools/testing/selftests/drivers/net/mlxsw/tc_police_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/tc_police_scale.sh index 3e3e06ea5703..86e787895f78 100644 --- a/tools/testing/selftests/drivers/net/mlxsw/tc_police_scale.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/tc_police_scale.sh @@ -60,7 +60,8 @@ __tc_police_test() tc_police_rules_create $count $should_fail - offload_count=$(tc filter show dev $swp1 ingress | grep in_hw | wc -l) + offload_count=$(tc -j filter show dev $swp1 ingress | + jq "[.[] | select(.options.in_hw == true)] | length") ((offload_count == count)) check_err_fail $should_fail $? "tc police offload count" } diff --git a/tools/testing/selftests/drivers/net/netdevsim/hw_stats_l3.sh b/tools/testing/selftests/drivers/net/netdevsim/hw_stats_l3.sh new file mode 100755 index 000000000000..fe1898402987 --- /dev/null +++ b/tools/testing/selftests/drivers/net/netdevsim/hw_stats_l3.sh @@ -0,0 +1,421 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +lib_dir=$(dirname $0)/../../../net/forwarding + +ALL_TESTS=" + l3_reporting_test + l3_fail_next_test + l3_counter_test + l3_rollback_test + l3_monitor_test +" + +NETDEVSIM_PATH=/sys/bus/netdevsim/ +DEV_ADDR_1=1337 +DEV_ADDR_2=1057 +DEV_ADDR_3=5417 +NUM_NETIFS=0 +source $lib_dir/lib.sh + +DUMMY_IFINDEX= + +DEV_ADDR() +{ + local n=$1; shift + local var=DEV_ADDR_$n + + echo ${!var} +} + +DEV() +{ + echo netdevsim$(DEV_ADDR $1) +} + +DEVLINK_DEV() +{ + echo netdevsim/$(DEV $1) +} + +SYSFS_NET_DIR() +{ + echo /sys/bus/netdevsim/devices/$(DEV $1)/net/ +} + +DEBUGFS_DIR() +{ + echo /sys/kernel/debug/netdevsim/$(DEV $1)/ +} + +nsim_add() +{ + local n=$1; shift + + echo "$(DEV_ADDR $n) 1" > ${NETDEVSIM_PATH}/new_device + while [ ! -d $(SYSFS_NET_DIR $n) ] ; do :; done +} + +nsim_reload() +{ + local n=$1; shift + local ns=$1; shift + + devlink dev reload $(DEVLINK_DEV $n) netns $ns + + if [ $? -ne 0 ]; then + echo "Failed to reload $(DEV $n) into netns \"testns1\"" + exit 1 + fi + +} + +nsim_del() +{ + local n=$1; shift + + echo "$(DEV_ADDR $n)" > ${NETDEVSIM_PATH}/del_device +} + +nsim_hwstats_toggle() +{ + local action=$1; shift + local instance=$1; shift + local netdev=$1; shift + local type=$1; shift + + local ifindex=$($IP -j link show dev $netdev | jq '.[].ifindex') + + echo $ifindex > $(DEBUGFS_DIR $instance)/hwstats/$type/$action +} + +nsim_hwstats_enable() +{ + nsim_hwstats_toggle enable_ifindex "$@" +} + +nsim_hwstats_disable() +{ + nsim_hwstats_toggle disable_ifindex "$@" +} + +nsim_hwstats_fail_next_enable() +{ + nsim_hwstats_toggle fail_next_enable "$@" +} + +setup_prepare() +{ + modprobe netdevsim &> /dev/null + nsim_add 1 + nsim_add 2 + nsim_add 3 + + ip netns add testns1 + + if [ $? -ne 0 ]; then + echo "Failed to add netns \"testns1\"" + exit 1 + fi + + nsim_reload 1 testns1 + nsim_reload 2 testns1 + nsim_reload 3 testns1 + + IP="ip -n testns1" + + $IP link add name dummy1 type dummy + $IP link set dev dummy1 up + DUMMY_IFINDEX=$($IP -j link show dev dummy1 | jq '.[].ifindex') +} + +cleanup() +{ + pre_cleanup + + $IP link del name dummy1 + ip netns del testns1 + nsim_del 3 + nsim_del 2 + nsim_del 1 + modprobe -r netdevsim &> /dev/null +} + +netdev_hwstats_used() +{ + local netdev=$1; shift + local type=$1; shift + + $IP -j stats show dev "$netdev" group offload subgroup hw_stats_info | + jq '.[].info.l3_stats.used' +} + +netdev_check_used() +{ + local netdev=$1; shift + local type=$1; shift + + [[ $(netdev_hwstats_used $netdev $type) == "true" ]] +} + +netdev_check_unused() +{ + local netdev=$1; shift + local type=$1; shift + + [[ $(netdev_hwstats_used $netdev $type) == "false" ]] +} + +netdev_hwstats_request() +{ + local netdev=$1; shift + local type=$1; shift + + $IP -j stats show dev "$netdev" group offload subgroup hw_stats_info | + jq ".[].info.${type}_stats.request" +} + +netdev_check_requested() +{ + local netdev=$1; shift + local type=$1; shift + + [[ $(netdev_hwstats_request $netdev $type) == "true" ]] +} + +netdev_check_unrequested() +{ + local netdev=$1; shift + local type=$1; shift + + [[ $(netdev_hwstats_request $netdev $type) == "false" ]] +} + +reporting_test() +{ + local type=$1; shift + local instance=1 + + RET=0 + + [[ -n $(netdev_hwstats_used dummy1 $type) ]] + check_err $? "$type stats not reported" + + netdev_check_unused dummy1 $type + check_err $? "$type stats reported as used before either device or netdevsim request" + + nsim_hwstats_enable $instance dummy1 $type + netdev_check_unused dummy1 $type + check_err $? "$type stats reported as used before device request" + netdev_check_unrequested dummy1 $type + check_err $? "$type stats reported as requested before device request" + + $IP stats set dev dummy1 ${type}_stats on + netdev_check_used dummy1 $type + check_err $? "$type stats reported as not used after both device and netdevsim request" + netdev_check_requested dummy1 $type + check_err $? "$type stats reported as not requested after device request" + + nsim_hwstats_disable $instance dummy1 $type + netdev_check_unused dummy1 $type + check_err $? "$type stats reported as used after netdevsim request withdrawn" + + nsim_hwstats_enable $instance dummy1 $type + netdev_check_used dummy1 $type + check_err $? "$type stats reported as not used after netdevsim request reenabled" + + $IP stats set dev dummy1 ${type}_stats off + netdev_check_unused dummy1 $type + check_err $? "$type stats reported as used after device request withdrawn" + netdev_check_unrequested dummy1 $type + check_err $? "$type stats reported as requested after device request withdrawn" + + nsim_hwstats_disable $instance dummy1 $type + netdev_check_unused dummy1 $type + check_err $? "$type stats reported as used after both requests withdrawn" + + log_test "Reporting of $type stats usage" +} + +l3_reporting_test() +{ + reporting_test l3 +} + +__fail_next_test() +{ + local instance=$1; shift + local type=$1; shift + + RET=0 + + netdev_check_unused dummy1 $type + check_err $? "$type stats reported as used before either device or netdevsim request" + + nsim_hwstats_enable $instance dummy1 $type + nsim_hwstats_fail_next_enable $instance dummy1 $type + netdev_check_unused dummy1 $type + check_err $? "$type stats reported as used before device request" + netdev_check_unrequested dummy1 $type + check_err $? "$type stats reported as requested before device request" + + $IP stats set dev dummy1 ${type}_stats on 2>/dev/null + check_fail $? "$type stats request not bounced as it should have been" + netdev_check_unused dummy1 $type + check_err $? "$type stats reported as used after bounce" + netdev_check_unrequested dummy1 $type + check_err $? "$type stats reported as requested after bounce" + + $IP stats set dev dummy1 ${type}_stats on + check_err $? "$type stats request failed when it shouldn't have" + netdev_check_used dummy1 $type + check_err $? "$type stats reported as not used after both device and netdevsim request" + netdev_check_requested dummy1 $type + check_err $? "$type stats reported as not requested after device request" + + $IP stats set dev dummy1 ${type}_stats off + nsim_hwstats_disable $instance dummy1 $type + + log_test "Injected failure of $type stats enablement (netdevsim #$instance)" +} + +fail_next_test() +{ + __fail_next_test 1 "$@" + __fail_next_test 2 "$@" + __fail_next_test 3 "$@" +} + +l3_fail_next_test() +{ + fail_next_test l3 +} + +get_hwstat() +{ + local netdev=$1; shift + local type=$1; shift + local selector=$1; shift + + $IP -j stats show dev $netdev group offload subgroup ${type}_stats | + jq ".[0].stats64.${selector}" +} + +counter_test() +{ + local type=$1; shift + local instance=1 + + RET=0 + + nsim_hwstats_enable $instance dummy1 $type + $IP stats set dev dummy1 ${type}_stats on + netdev_check_used dummy1 $type + check_err $? "$type stats reported as not used after both device and netdevsim request" + + # Netdevsim counts 10pps on ingress. We should see maybe a couple + # packets, unless things take a reeealy long time. + local pkts=$(get_hwstat dummy1 l3 rx.packets) + ((pkts < 10)) + check_err $? "$type stats show >= 10 packets after first enablement" + + sleep 2 + + local pkts=$(get_hwstat dummy1 l3 rx.packets) + ((pkts >= 20)) + check_err $? "$type stats show < 20 packets after 2s passed" + + $IP stats set dev dummy1 ${type}_stats off + + sleep 2 + + $IP stats set dev dummy1 ${type}_stats on + local pkts=$(get_hwstat dummy1 l3 rx.packets) + ((pkts < 10)) + check_err $? "$type stats show >= 10 packets after second enablement" + + $IP stats set dev dummy1 ${type}_stats off + nsim_hwstats_fail_next_enable $instance dummy1 $type + $IP stats set dev dummy1 ${type}_stats on 2>/dev/null + check_fail $? "$type stats request not bounced as it should have been" + + sleep 2 + + $IP stats set dev dummy1 ${type}_stats on + local pkts=$(get_hwstat dummy1 l3 rx.packets) + ((pkts < 10)) + check_err $? "$type stats show >= 10 packets after post-fail enablement" + + $IP stats set dev dummy1 ${type}_stats off + + log_test "Counter values in $type stats" +} + +l3_counter_test() +{ + counter_test l3 +} + +rollback_test() +{ + local type=$1; shift + + RET=0 + + nsim_hwstats_enable 1 dummy1 l3 + nsim_hwstats_enable 2 dummy1 l3 + nsim_hwstats_enable 3 dummy1 l3 + + # The three netdevsim instances are registered in order of their number + # one after another. It is reasonable to expect that whatever + # notifications take place hit no. 2 in between hitting nos. 1 and 3, + # whatever the actual order. This allows us to test that a fail caused + # by no. 2 does not leave the system in a partial state, and rolls + # everything back. + + nsim_hwstats_fail_next_enable 2 dummy1 l3 + $IP stats set dev dummy1 ${type}_stats on 2>/dev/null + check_fail $? "$type stats request not bounced as it should have been" + + netdev_check_unused dummy1 $type + check_err $? "$type stats reported as used after bounce" + netdev_check_unrequested dummy1 $type + check_err $? "$type stats reported as requested after bounce" + + sleep 2 + + $IP stats set dev dummy1 ${type}_stats on + check_err $? "$type stats request not upheld as it should have been" + + local pkts=$(get_hwstat dummy1 l3 rx.packets) + ((pkts < 10)) + check_err $? "$type stats show $pkts packets after post-fail enablement" + + $IP stats set dev dummy1 ${type}_stats off + + nsim_hwstats_disable 3 dummy1 l3 + nsim_hwstats_disable 2 dummy1 l3 + nsim_hwstats_disable 1 dummy1 l3 + + log_test "Failure in $type stats enablement rolled back" +} + +l3_rollback_test() +{ + rollback_test l3 +} + +l3_monitor_test() +{ + hw_stats_monitor_test dummy1 l3 \ + "nsim_hwstats_enable 1 dummy1 l3" \ + "nsim_hwstats_disable 1 dummy1 l3" \ + "$IP" +} + +trap cleanup EXIT + +setup_prepare +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/drivers/sdsi/sdsi.sh b/tools/testing/selftests/drivers/sdsi/sdsi.sh new file mode 100755 index 000000000000..9b84b9b82b49 --- /dev/null +++ b/tools/testing/selftests/drivers/sdsi/sdsi.sh @@ -0,0 +1,25 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# Runs tests for the intel_sdsi driver + +if ! command -v python3 > /dev/null 2>&1; then + echo "drivers/sdsi: [SKIP] python3 not installed" + exit 77 +fi + +if ! python3 -c "import pytest" > /dev/null 2>&1; then + echo "drivers/sdsi: [SKIP] pytest module not installed" + exit 77 +fi + +if ! /sbin/modprobe -q -r intel_sdsi; then + echo "drivers/sdsi: [SKIP]" + exit 77 +fi + +if /sbin/modprobe -q intel_sdsi && python3 -m pytest sdsi_test.py; then + echo "drivers/sdsi: [OK]" +else + echo "drivers/sdsi: [FAIL]" + exit 1 +fi diff --git a/tools/testing/selftests/drivers/sdsi/sdsi_test.py b/tools/testing/selftests/drivers/sdsi/sdsi_test.py new file mode 100644 index 000000000000..5efb29feee70 --- /dev/null +++ b/tools/testing/selftests/drivers/sdsi/sdsi_test.py @@ -0,0 +1,226 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 + +from struct import pack +from time import sleep + +import errno +import glob +import os +import subprocess + +try: + import pytest +except ImportError: + print("Unable to import pytest python module.") + print("\nIf not already installed, you may do so with:") + print("\t\tpip3 install pytest") + exit(1) + +SOCKETS = glob.glob('/sys/bus/auxiliary/devices/intel_vsec.sdsi.*') +NUM_SOCKETS = len(SOCKETS) + +MODULE_NAME = 'intel_sdsi' +DEV_PREFIX = 'intel_vsec.sdsi' +CLASS_DIR = '/sys/bus/auxiliary/devices' +GUID = "0x6dd191" + +def read_bin_file(file): + with open(file, mode='rb') as f: + content = f.read() + return content + +def get_dev_file_path(socket, file): + return CLASS_DIR + '/' + DEV_PREFIX + '.' + str(socket) + '/' + file + +def kmemleak_enabled(): + kmemleak = "/sys/kernel/debug/kmemleak" + return os.path.isfile(kmemleak) + +class TestSDSiDriver: + def test_driver_loaded(self): + lsmod_p = subprocess.Popen(('lsmod'), stdout=subprocess.PIPE) + result = subprocess.check_output(('grep', '-q', MODULE_NAME), stdin=lsmod_p.stdout) + +@pytest.mark.parametrize('socket', range(0, NUM_SOCKETS)) +class TestSDSiFilesClass: + + def read_value(self, file): + f = open(file, "r") + value = f.read().strip("\n") + return value + + def get_dev_folder(self, socket): + return CLASS_DIR + '/' + DEV_PREFIX + '.' + str(socket) + '/' + + def test_sysfs_files_exist(self, socket): + folder = self.get_dev_folder(socket) + print (folder) + assert os.path.isfile(folder + "guid") == True + assert os.path.isfile(folder + "provision_akc") == True + assert os.path.isfile(folder + "provision_cap") == True + assert os.path.isfile(folder + "state_certificate") == True + assert os.path.isfile(folder + "registers") == True + + def test_sysfs_file_permissions(self, socket): + folder = self.get_dev_folder(socket) + mode = os.stat(folder + "guid").st_mode & 0o777 + assert mode == 0o444 # Read all + mode = os.stat(folder + "registers").st_mode & 0o777 + assert mode == 0o400 # Read owner + mode = os.stat(folder + "provision_akc").st_mode & 0o777 + assert mode == 0o200 # Read owner + mode = os.stat(folder + "provision_cap").st_mode & 0o777 + assert mode == 0o200 # Read owner + mode = os.stat(folder + "state_certificate").st_mode & 0o777 + assert mode == 0o400 # Read owner + + def test_sysfs_file_ownership(self, socket): + folder = self.get_dev_folder(socket) + + st = os.stat(folder + "guid") + assert st.st_uid == 0 + assert st.st_gid == 0 + + st = os.stat(folder + "registers") + assert st.st_uid == 0 + assert st.st_gid == 0 + + st = os.stat(folder + "provision_akc") + assert st.st_uid == 0 + assert st.st_gid == 0 + + st = os.stat(folder + "provision_cap") + assert st.st_uid == 0 + assert st.st_gid == 0 + + st = os.stat(folder + "state_certificate") + assert st.st_uid == 0 + assert st.st_gid == 0 + + def test_sysfs_file_sizes(self, socket): + folder = self.get_dev_folder(socket) + + if self.read_value(folder + "guid") == GUID: + st = os.stat(folder + "registers") + assert st.st_size == 72 + + st = os.stat(folder + "provision_akc") + assert st.st_size == 1024 + + st = os.stat(folder + "provision_cap") + assert st.st_size == 1024 + + st = os.stat(folder + "state_certificate") + assert st.st_size == 4096 + + def test_no_seek_allowed(self, socket): + folder = self.get_dev_folder(socket) + rand_file = bytes(os.urandom(8)) + + f = open(folder + "provision_cap", "wb", 0) + f.seek(1) + with pytest.raises(OSError) as error: + f.write(rand_file) + assert error.value.errno == errno.ESPIPE + f.close() + + f = open(folder + "provision_akc", "wb", 0) + f.seek(1) + with pytest.raises(OSError) as error: + f.write(rand_file) + assert error.value.errno == errno.ESPIPE + f.close() + + def test_registers_seek(self, socket): + folder = self.get_dev_folder(socket) + + # Check that the value read from an offset of the entire + # file is none-zero and the same as the value read + # from seeking to the same location + f = open(folder + "registers", "rb") + data = f.read() + f.seek(64) + id = f.read() + assert id != bytes(0) + assert data[64:] == id + f.close() + +@pytest.mark.parametrize('socket', range(0, NUM_SOCKETS)) +class TestSDSiMailboxCmdsClass: + def test_provision_akc_eoverflow_1017_bytes(self, socket): + + # The buffer for writes is 1k, of with 8 bytes must be + # reserved for the command, leaving 1016 bytes max. + # Check that we get an overflow error for 1017 bytes. + node = get_dev_file_path(socket, "provision_akc") + rand_file = bytes(os.urandom(1017)) + + f = open(node, 'wb', 0) + with pytest.raises(OSError) as error: + f.write(rand_file) + assert error.value.errno == errno.EOVERFLOW + f.close() + +@pytest.mark.parametrize('socket', range(0, NUM_SOCKETS)) +class TestSdsiDriverLocksClass: + def test_enodev_when_pci_device_removed(self, socket): + node = get_dev_file_path(socket, "provision_akc") + dev_name = DEV_PREFIX + '.' + str(socket) + driver_dir = CLASS_DIR + '/' + dev_name + "/driver/" + rand_file = bytes(os.urandom(8)) + + f = open(node, 'wb', 0) + g = open(node, 'wb', 0) + + with open(driver_dir + 'unbind', 'w') as k: + print(dev_name, file = k) + + with pytest.raises(OSError) as error: + f.write(rand_file) + assert error.value.errno == errno.ENODEV + + with pytest.raises(OSError) as error: + g.write(rand_file) + assert error.value.errno == errno.ENODEV + + f.close() + g.close() + + # Short wait needed to allow file to close before pulling driver + sleep(1) + + p = subprocess.Popen(('modprobe', '-r', 'intel_sdsi')) + p.wait() + p = subprocess.Popen(('modprobe', '-r', 'intel_vsec')) + p.wait() + p = subprocess.Popen(('modprobe', 'intel_vsec')) + p.wait() + + # Short wait needed to allow driver time to get inserted + # before continuing tests + sleep(1) + + def test_memory_leak(self, socket): + if not kmemleak_enabled(): + pytest.skip("kmemleak not enabled in kernel") + + dev_name = DEV_PREFIX + '.' + str(socket) + driver_dir = CLASS_DIR + '/' + dev_name + "/driver/" + + with open(driver_dir + 'unbind', 'w') as k: + print(dev_name, file = k) + + sleep(1) + + subprocess.check_output(('modprobe', '-r', 'intel_sdsi')) + subprocess.check_output(('modprobe', '-r', 'intel_vsec')) + + with open('/sys/kernel/debug/kmemleak', 'w') as f: + print('scan', file = f) + sleep(5) + + assert os.stat('/sys/kernel/debug/kmemleak').st_size == 0 + + subprocess.check_output(('modprobe', 'intel_vsec')) + sleep(1) diff --git a/tools/testing/selftests/exec/.gitignore b/tools/testing/selftests/exec/.gitignore index 9e2f00343f15..90c238ba6a4b 100644 --- a/tools/testing/selftests/exec/.gitignore +++ b/tools/testing/selftests/exec/.gitignore @@ -7,6 +7,8 @@ execveat.moved execveat.path.ephemeral execveat.ephemeral execveat.denatured +non-regular +null-argv /load_address_* /recursion-depth xxxxxxxx* diff --git a/tools/testing/selftests/exec/Makefile b/tools/testing/selftests/exec/Makefile index dd61118df66e..a0b8688b0836 100644 --- a/tools/testing/selftests/exec/Makefile +++ b/tools/testing/selftests/exec/Makefile @@ -3,13 +3,14 @@ CFLAGS = -Wall CFLAGS += -Wno-nonnull CFLAGS += -D_GNU_SOURCE -TEST_PROGS := binfmt_script non-regular -TEST_GEN_PROGS := execveat load_address_4096 load_address_2097152 load_address_16777216 -TEST_GEN_FILES := execveat.symlink execveat.denatured script subdir pipe +TEST_PROGS := binfmt_script.py +TEST_GEN_PROGS := execveat load_address_4096 load_address_2097152 load_address_16777216 non-regular +TEST_GEN_FILES := execveat.symlink execveat.denatured script subdir # Makefile is a run-time dependency, since it's accessed by the execveat test TEST_FILES := Makefile TEST_GEN_PROGS += recursion-depth +TEST_GEN_PROGS += null-argv EXTRA_CLEAN := $(OUTPUT)/subdir.moved $(OUTPUT)/execveat.moved $(OUTPUT)/xxxxx* \ $(OUTPUT)/S_I*.test diff --git a/tools/testing/selftests/exec/binfmt_script b/tools/testing/selftests/exec/binfmt_script.py index 05f94a741c7a..05f94a741c7a 100755 --- a/tools/testing/selftests/exec/binfmt_script +++ b/tools/testing/selftests/exec/binfmt_script.py diff --git a/tools/testing/selftests/exec/null-argv.c b/tools/testing/selftests/exec/null-argv.c new file mode 100644 index 000000000000..c19726e710d1 --- /dev/null +++ b/tools/testing/selftests/exec/null-argv.c @@ -0,0 +1,78 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Test that empty argvs are swapped out for a single empty string. */ +#include <stdio.h> +#include <unistd.h> +#include <sys/types.h> +#include <sys/wait.h> + +#include "../kselftest.h" + +#define FORK(exec) \ +do { \ + pid = fork(); \ + if (pid == 0) { \ + /* Child */ \ + exec; /* Some kind of exec */ \ + perror("# " #exec); \ + return 1; \ + } \ + check_result(pid, #exec); \ +} while (0) + +void check_result(pid_t pid, const char *msg) +{ + int wstatus; + + if (pid == (pid_t)-1) { + perror("# fork"); + ksft_test_result_fail("fork failed: %s\n", msg); + return; + } + if (waitpid(pid, &wstatus, 0) < 0) { + perror("# waitpid"); + ksft_test_result_fail("waitpid failed: %s\n", msg); + return; + } + if (!WIFEXITED(wstatus)) { + ksft_test_result_fail("child did not exit: %s\n", msg); + return; + } + if (WEXITSTATUS(wstatus) != 0) { + ksft_test_result_fail("non-zero exit: %s\n", msg); + return; + } + ksft_test_result_pass("%s\n", msg); +} + +int main(int argc, char *argv[], char *envp[]) +{ + pid_t pid; + static char * const args[] = { NULL }; + static char * const str[] = { "", NULL }; + + /* argc counting checks */ + if (argc < 1) { + fprintf(stderr, "# FAIL: saw argc == 0 (old kernel?)\n"); + return 1; + } + if (argc != 1) { + fprintf(stderr, "# FAIL: unknown argc (%d)\n", argc); + return 1; + } + if (argv[0][0] == '\0') { + /* Good, we found a NULL terminated string at argv[0]! */ + return 0; + } + + /* Test runner. */ + ksft_print_header(); + ksft_set_plan(5); + + FORK(execve(argv[0], str, NULL)); + FORK(execve(argv[0], NULL, NULL)); + FORK(execve(argv[0], NULL, envp)); + FORK(execve(argv[0], args, NULL)); + FORK(execve(argv[0], args, envp)); + + ksft_exit(ksft_cnt.ksft_pass == ksft_plan); +} diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func_set_ftrace_file.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func_set_ftrace_file.tc index e96e279e0533..25432b8cd5bd 100644 --- a/tools/testing/selftests/ftrace/test.d/ftrace/func_set_ftrace_file.tc +++ b/tools/testing/selftests/ftrace/test.d/ftrace/func_set_ftrace_file.tc @@ -19,7 +19,7 @@ fail() { # mesg FILTER=set_ftrace_filter FUNC1="schedule" -FUNC2="do_softirq" +FUNC2="scheduler_tick" ALL_FUNCS="#### all functions enabled ####" diff --git a/tools/testing/selftests/futex/Makefile b/tools/testing/selftests/futex/Makefile index 12631f0076a1..11e157d7533b 100644 --- a/tools/testing/selftests/futex/Makefile +++ b/tools/testing/selftests/futex/Makefile @@ -11,7 +11,7 @@ all: @for DIR in $(SUBDIRS); do \ BUILD_TARGET=$(OUTPUT)/$$DIR; \ mkdir $$BUILD_TARGET -p; \ - make OUTPUT=$$BUILD_TARGET -C $$DIR $@;\ + $(MAKE) OUTPUT=$$BUILD_TARGET -C $$DIR $@;\ if [ -e $$DIR/$(TEST_PROGS) ]; then \ rsync -a $$DIR/$(TEST_PROGS) $$BUILD_TARGET/; \ fi \ @@ -32,6 +32,6 @@ override define CLEAN @for DIR in $(SUBDIRS); do \ BUILD_TARGET=$(OUTPUT)/$$DIR; \ mkdir $$BUILD_TARGET -p; \ - make OUTPUT=$$BUILD_TARGET -C $$DIR $@;\ + $(MAKE) OUTPUT=$$BUILD_TARGET -C $$DIR $@;\ done endef diff --git a/tools/testing/selftests/futex/functional/Makefile b/tools/testing/selftests/futex/functional/Makefile index 5cc38de9d8ea..b8152c573e8a 100644 --- a/tools/testing/selftests/futex/functional/Makefile +++ b/tools/testing/selftests/futex/functional/Makefile @@ -1,7 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 -INCLUDES := -I../include -I../../ -I../../../../../usr/include/ \ - -I$(KBUILD_OUTPUT)/kselftest/usr/include -CFLAGS := $(CFLAGS) -g -O2 -Wall -D_GNU_SOURCE -pthread $(INCLUDES) +INCLUDES := -I../include -I../../ -I../../../../../usr/include/ +CFLAGS := $(CFLAGS) -g -O2 -Wall -D_GNU_SOURCE -pthread $(INCLUDES) $(KHDR_INCLUDES) LDLIBS := -lpthread -lrt HEADERS := \ @@ -24,6 +23,7 @@ TEST_PROGS := run.sh top_srcdir = ../../../../.. KSFT_KHDR_INSTALL := 1 +DEFAULT_INSTALL_HDR_PATH := 1 include ../../lib.mk $(TEST_GEN_FILES): $(HEADERS) diff --git a/tools/testing/selftests/ir/ir_loopback.c b/tools/testing/selftests/ir/ir_loopback.c index 06256c96df12..f4a15cbdd5ea 100644 --- a/tools/testing/selftests/ir/ir_loopback.c +++ b/tools/testing/selftests/ir/ir_loopback.c @@ -29,6 +29,16 @@ #define SYSFS_PATH_MAX 256 #define DNAME_PATH_MAX 256 +/* + * Support ancient lirc.h which does not have these values. Can be removed + * once RHEL 8 is no longer a relevant testing platform. + */ +#if RC_PROTO_MAX < 26 +#define RC_PROTO_RCMM12 24 +#define RC_PROTO_RCMM24 25 +#define RC_PROTO_RCMM32 26 +#endif + static const struct { enum rc_proto proto; const char *name; diff --git a/tools/testing/selftests/kselftest.h b/tools/testing/selftests/kselftest.h index f1180987492c..b8f248018174 100644 --- a/tools/testing/selftests/kselftest.h +++ b/tools/testing/selftests/kselftest.h @@ -28,6 +28,7 @@ * * When all tests are finished, clean up and exit the program with one of: * + * ksft_finished(); * ksft_exit(condition); * ksft_exit_pass(); * ksft_exit_fail(); @@ -235,6 +236,15 @@ static inline int ksft_exit_fail(void) ksft_exit_fail(); \ } while (0) +/** + * ksft_finished() - Exit selftest with success if all tests passed + */ +#define ksft_finished() \ + ksft_exit(ksft_plan == \ + ksft_cnt.ksft_pass + \ + ksft_cnt.ksft_xfail + \ + ksft_cnt.ksft_xskip) + static inline int ksft_exit_fail_msg(const char *msg, ...) { int saved_errno = errno; diff --git a/tools/testing/selftests/kselftest/runner.sh b/tools/testing/selftests/kselftest/runner.sh index a9ba782d8ca0..294619ade49f 100644 --- a/tools/testing/selftests/kselftest/runner.sh +++ b/tools/testing/selftests/kselftest/runner.sh @@ -18,6 +18,8 @@ if [ -z "$BASE_DIR" ]; then exit 1 fi +TR_CMD=$(command -v tr) + # If Perl is unavailable, we must fall back to line-at-a-time prefixing # with sed instead of unbuffered output. tap_prefix() @@ -49,6 +51,31 @@ run_one() # Reset any "settings"-file variables. export kselftest_timeout="$kselftest_default_timeout" + + # Safe default if tr not available + kselftest_cmd_args_ref="KSELFTEST_ARGS" + + # Optional arguments for this command, possibly defined as an + # environment variable built using the test executable in all + # uppercase and sanitized substituting non acceptable shell + # variable name characters with "_" as in: + # + # KSELFTEST_<UPPERCASE_SANITIZED_TESTNAME>_ARGS="<options>" + # + # e.g. + # + # rtctest --> KSELFTEST_RTCTEST_ARGS="/dev/rtc1" + # + # cpu-on-off-test.sh --> KSELFTEST_CPU_ON_OFF_TEST_SH_ARGS="-a -p 10" + # + if [ -n "$TR_CMD" ]; then + BASENAME_SANITIZED=$(echo "$BASENAME_TEST" | \ + $TR_CMD -d "[:blank:][:cntrl:]" | \ + $TR_CMD -c "[:alnum:]_" "_" | \ + $TR_CMD [:lower:] [:upper:]) + kselftest_cmd_args_ref="KSELFTEST_${BASENAME_SANITIZED}_ARGS" + fi + # Load per-test-directory kselftest "settings" file. settings="$BASE_DIR/$DIR/settings" if [ -r "$settings" ] ; then @@ -69,7 +96,8 @@ run_one() echo "# Warning: file $TEST is missing!" echo "not ok $test_num $TEST_HDR_MSG" else - cmd="./$BASENAME_TEST" + eval kselftest_cmd_args="\$${kselftest_cmd_args_ref:-}" + cmd="./$BASENAME_TEST $kselftest_cmd_args" if [ ! -x "$TEST" ]; then echo "# Warning: file $TEST is not executable" diff --git a/tools/testing/selftests/kselftest_harness.h b/tools/testing/selftests/kselftest_harness.h index 471eaa7b3a3f..11779405dc80 100644 --- a/tools/testing/selftests/kselftest_harness.h +++ b/tools/testing/selftests/kselftest_harness.h @@ -877,7 +877,8 @@ static void __timeout_handler(int sig, siginfo_t *info, void *ucontext) } t->timed_out = true; - kill(t->pid, SIGKILL); + // signal process group + kill(-(t->pid), SIGKILL); } void __wait_for_test(struct __test_metadata *t) @@ -987,6 +988,7 @@ void __run_test(struct __fixture_metadata *f, ksft_print_msg("ERROR SPAWNING TEST CHILD\n"); t->passed = 0; } else if (t->pid == 0) { + setpgrp(); t->fn(t, variant); if (t->skip) _exit(255); diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore index 3cb5ac5da087..d1e8f5237469 100644 --- a/tools/testing/selftests/kvm/.gitignore +++ b/tools/testing/selftests/kvm/.gitignore @@ -4,23 +4,28 @@ /aarch64/get-reg-list /aarch64/psci_cpu_on_test /aarch64/vgic_init +/aarch64/vgic_irq /s390x/memop /s390x/resets /s390x/sync_regs_test +/s390x/tprot +/x86_64/amx_test +/x86_64/cpuid_test /x86_64/cr4_cpuid_sync_test /x86_64/debug_regs /x86_64/evmcs_test /x86_64/emulator_error_test -/x86_64/get_cpuid_test /x86_64/get_msr_index_features /x86_64/kvm_clock_test /x86_64/kvm_pv_test /x86_64/hyperv_clock /x86_64/hyperv_cpuid /x86_64/hyperv_features +/x86_64/hyperv_svm_test /x86_64/mmio_warning_test /x86_64/mmu_role_test /x86_64/platform_info_test +/x86_64/pmu_event_filter_test /x86_64/set_boot_cpu_id /x86_64/set_sregs_test /x86_64/sev_migrate_tests @@ -35,12 +40,14 @@ /x86_64/vmx_apic_access_test /x86_64/vmx_close_while_nested_test /x86_64/vmx_dirty_log_test +/x86_64/vmx_exception_with_invalid_guest_state /x86_64/vmx_invalid_nested_guest_state /x86_64/vmx_preemption_timer_test /x86_64/vmx_set_nested_state_test /x86_64/vmx_tsc_adjust_test /x86_64/vmx_nested_tsc_scaling_test /x86_64/xapic_ipi_test +/x86_64/xapic_state_test /x86_64/xen_shinfo_test /x86_64/xen_vmcall_test /x86_64/xss_msr_test @@ -52,6 +59,7 @@ /hardware_disable_test /kvm_create_max_vcpus /kvm_page_table_test +/max_guest_memory_test /memslot_modification_stress_test /memslot_perf_test /rseq_test diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 17342b575e85..21c2dbd21a81 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -32,25 +32,32 @@ endif ifeq ($(ARCH),s390) UNAME_M := s390x endif +# Set UNAME_M riscv compile/install to work +ifeq ($(ARCH),riscv) + UNAME_M := riscv +endif LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/rbtree.c lib/sparsebit.c lib/test_util.c lib/guest_modes.c lib/perf_test_util.c LIBKVM_x86_64 = lib/x86_64/apic.c lib/x86_64/processor.c lib/x86_64/vmx.c lib/x86_64/svm.c lib/x86_64/ucall.c lib/x86_64/handlers.S LIBKVM_aarch64 = lib/aarch64/processor.c lib/aarch64/ucall.c lib/aarch64/handlers.S lib/aarch64/spinlock.c lib/aarch64/gic.c lib/aarch64/gic_v3.c lib/aarch64/vgic.c LIBKVM_s390x = lib/s390x/processor.c lib/s390x/ucall.c lib/s390x/diag318_test_handler.c +LIBKVM_riscv = lib/riscv/processor.c lib/riscv/ucall.c -TEST_GEN_PROGS_x86_64 = x86_64/cr4_cpuid_sync_test +TEST_GEN_PROGS_x86_64 = x86_64/cpuid_test +TEST_GEN_PROGS_x86_64 += x86_64/cr4_cpuid_sync_test TEST_GEN_PROGS_x86_64 += x86_64/get_msr_index_features TEST_GEN_PROGS_x86_64 += x86_64/evmcs_test TEST_GEN_PROGS_x86_64 += x86_64/emulator_error_test -TEST_GEN_PROGS_x86_64 += x86_64/get_cpuid_test TEST_GEN_PROGS_x86_64 += x86_64/hyperv_clock TEST_GEN_PROGS_x86_64 += x86_64/hyperv_cpuid TEST_GEN_PROGS_x86_64 += x86_64/hyperv_features +TEST_GEN_PROGS_x86_64 += x86_64/hyperv_svm_test TEST_GEN_PROGS_x86_64 += x86_64/kvm_clock_test TEST_GEN_PROGS_x86_64 += x86_64/kvm_pv_test TEST_GEN_PROGS_x86_64 += x86_64/mmio_warning_test TEST_GEN_PROGS_x86_64 += x86_64/mmu_role_test TEST_GEN_PROGS_x86_64 += x86_64/platform_info_test +TEST_GEN_PROGS_x86_64 += x86_64/pmu_event_filter_test TEST_GEN_PROGS_x86_64 += x86_64/set_boot_cpu_id TEST_GEN_PROGS_x86_64 += x86_64/set_sregs_test TEST_GEN_PROGS_x86_64 += x86_64/smm_test @@ -64,25 +71,29 @@ TEST_GEN_PROGS_x86_64 += x86_64/userspace_msr_exit_test TEST_GEN_PROGS_x86_64 += x86_64/vmx_apic_access_test TEST_GEN_PROGS_x86_64 += x86_64/vmx_close_while_nested_test TEST_GEN_PROGS_x86_64 += x86_64/vmx_dirty_log_test +TEST_GEN_PROGS_x86_64 += x86_64/vmx_exception_with_invalid_guest_state TEST_GEN_PROGS_x86_64 += x86_64/vmx_invalid_nested_guest_state TEST_GEN_PROGS_x86_64 += x86_64/vmx_set_nested_state_test TEST_GEN_PROGS_x86_64 += x86_64/vmx_tsc_adjust_test TEST_GEN_PROGS_x86_64 += x86_64/vmx_nested_tsc_scaling_test TEST_GEN_PROGS_x86_64 += x86_64/xapic_ipi_test +TEST_GEN_PROGS_x86_64 += x86_64/xapic_state_test TEST_GEN_PROGS_x86_64 += x86_64/xss_msr_test TEST_GEN_PROGS_x86_64 += x86_64/debug_regs TEST_GEN_PROGS_x86_64 += x86_64/tsc_msrs_test TEST_GEN_PROGS_x86_64 += x86_64/vmx_pmu_msrs_test TEST_GEN_PROGS_x86_64 += x86_64/xen_shinfo_test TEST_GEN_PROGS_x86_64 += x86_64/xen_vmcall_test -TEST_GEN_PROGS_x86_64 += x86_64/vmx_pi_mmio_test TEST_GEN_PROGS_x86_64 += x86_64/sev_migrate_tests +TEST_GEN_PROGS_x86_64 += x86_64/amx_test +TEST_GEN_PROGS_x86_64 += access_tracking_perf_test TEST_GEN_PROGS_x86_64 += demand_paging_test TEST_GEN_PROGS_x86_64 += dirty_log_test TEST_GEN_PROGS_x86_64 += dirty_log_perf_test TEST_GEN_PROGS_x86_64 += hardware_disable_test TEST_GEN_PROGS_x86_64 += kvm_create_max_vcpus TEST_GEN_PROGS_x86_64 += kvm_page_table_test +TEST_GEN_PROGS_x86_64 += max_guest_memory_test TEST_GEN_PROGS_x86_64 += memslot_modification_stress_test TEST_GEN_PROGS_x86_64 += memslot_perf_test TEST_GEN_PROGS_x86_64 += rseq_test @@ -96,6 +107,7 @@ TEST_GEN_PROGS_aarch64 += aarch64/debug-exceptions TEST_GEN_PROGS_aarch64 += aarch64/get-reg-list TEST_GEN_PROGS_aarch64 += aarch64/psci_cpu_on_test TEST_GEN_PROGS_aarch64 += aarch64/vgic_init +TEST_GEN_PROGS_aarch64 += aarch64/vgic_irq TEST_GEN_PROGS_aarch64 += demand_paging_test TEST_GEN_PROGS_aarch64 += dirty_log_test TEST_GEN_PROGS_aarch64 += dirty_log_perf_test @@ -111,6 +123,7 @@ TEST_GEN_PROGS_aarch64 += kvm_binary_stats_test TEST_GEN_PROGS_s390x = s390x/memop TEST_GEN_PROGS_s390x += s390x/resets TEST_GEN_PROGS_s390x += s390x/sync_regs_test +TEST_GEN_PROGS_s390x += s390x/tprot TEST_GEN_PROGS_s390x += demand_paging_test TEST_GEN_PROGS_s390x += dirty_log_test TEST_GEN_PROGS_s390x += kvm_create_max_vcpus @@ -119,6 +132,13 @@ TEST_GEN_PROGS_s390x += rseq_test TEST_GEN_PROGS_s390x += set_memory_region_test TEST_GEN_PROGS_s390x += kvm_binary_stats_test +TEST_GEN_PROGS_riscv += demand_paging_test +TEST_GEN_PROGS_riscv += dirty_log_test +TEST_GEN_PROGS_riscv += kvm_create_max_vcpus +TEST_GEN_PROGS_riscv += kvm_page_table_test +TEST_GEN_PROGS_riscv += set_memory_region_test +TEST_GEN_PROGS_riscv += kvm_binary_stats_test + TEST_GEN_PROGS += $(TEST_GEN_PROGS_$(UNAME_M)) LIBKVM += $(LIBKVM_$(UNAME_M)) @@ -133,7 +153,7 @@ endif CFLAGS += -Wall -Wstrict-prototypes -Wuninitialized -O2 -g -std=gnu99 \ -fno-stack-protector -fno-PIE -I$(LINUX_TOOL_INCLUDE) \ -I$(LINUX_TOOL_ARCH_INCLUDE) -I$(LINUX_HDR_PATH) -Iinclude \ - -I$(<D) -Iinclude/$(UNAME_M) -I.. + -I$(<D) -Iinclude/$(UNAME_M) -I.. $(EXTRA_CFLAGS) $(KHDR_INCLUDES) no-pie-option := $(call try-run, echo 'int main() { return 0; }' | \ $(CC) -Werror -no-pie -x c - -o "$$TMP", -no-pie) diff --git a/tools/testing/selftests/kvm/aarch64/arch_timer.c b/tools/testing/selftests/kvm/aarch64/arch_timer.c index bf6a45b0b8dc..b08d30bf71c5 100644 --- a/tools/testing/selftests/kvm/aarch64/arch_timer.c +++ b/tools/testing/selftests/kvm/aarch64/arch_timer.c @@ -366,6 +366,7 @@ static struct kvm_vm *test_vm_create(void) { struct kvm_vm *vm; unsigned int i; + int ret; int nr_vcpus = test_args.nr_vcpus; vm = vm_create_default_with_vcpus(nr_vcpus, 0, 0, guest_code, NULL); @@ -382,7 +383,11 @@ static struct kvm_vm *test_vm_create(void) ucall_init(vm, NULL); test_init_timer_irq(vm); - vgic_v3_setup(vm, nr_vcpus, GICD_BASE_GPA, GICR_BASE_GPA); + ret = vgic_v3_setup(vm, nr_vcpus, 64, GICD_BASE_GPA, GICR_BASE_GPA); + if (ret < 0) { + print_skip("Failed to create vgic-v3"); + exit(KSFT_SKIP); + } /* Make all the test's cmdline args visible to the guest */ sync_global_to_guest(vm, test_args); diff --git a/tools/testing/selftests/kvm/aarch64/debug-exceptions.c b/tools/testing/selftests/kvm/aarch64/debug-exceptions.c index ea189d83abf7..63b2178210c4 100644 --- a/tools/testing/selftests/kvm/aarch64/debug-exceptions.c +++ b/tools/testing/selftests/kvm/aarch64/debug-exceptions.c @@ -23,7 +23,7 @@ #define SPSR_D (1 << 9) #define SPSR_SS (1 << 21) -extern unsigned char sw_bp, hw_bp, bp_svc, bp_brk, hw_wp, ss_start; +extern unsigned char sw_bp, sw_bp2, hw_bp, hw_bp2, bp_svc, bp_brk, hw_wp, ss_start; static volatile uint64_t sw_bp_addr, hw_bp_addr; static volatile uint64_t wp_addr, wp_data_addr; static volatile uint64_t svc_addr; @@ -47,6 +47,14 @@ static void reset_debug_state(void) isb(); } +static void enable_os_lock(void) +{ + write_sysreg(1, oslar_el1); + isb(); + + GUEST_ASSERT(read_sysreg(oslsr_el1) & 2); +} + static void install_wp(uint64_t addr) { uint32_t wcr; @@ -99,6 +107,7 @@ static void guest_code(void) GUEST_SYNC(0); /* Software-breakpoint */ + reset_debug_state(); asm volatile("sw_bp: brk #0"); GUEST_ASSERT_EQ(sw_bp_addr, PC(sw_bp)); @@ -152,6 +161,51 @@ static void guest_code(void) GUEST_ASSERT_EQ(ss_addr[1], PC(ss_start) + 4); GUEST_ASSERT_EQ(ss_addr[2], PC(ss_start) + 8); + GUEST_SYNC(6); + + /* OS Lock does not block software-breakpoint */ + reset_debug_state(); + enable_os_lock(); + sw_bp_addr = 0; + asm volatile("sw_bp2: brk #0"); + GUEST_ASSERT_EQ(sw_bp_addr, PC(sw_bp2)); + + GUEST_SYNC(7); + + /* OS Lock blocking hardware-breakpoint */ + reset_debug_state(); + enable_os_lock(); + install_hw_bp(PC(hw_bp2)); + hw_bp_addr = 0; + asm volatile("hw_bp2: nop"); + GUEST_ASSERT_EQ(hw_bp_addr, 0); + + GUEST_SYNC(8); + + /* OS Lock blocking watchpoint */ + reset_debug_state(); + enable_os_lock(); + write_data = '\0'; + wp_data_addr = 0; + install_wp(PC(write_data)); + write_data = 'x'; + GUEST_ASSERT_EQ(write_data, 'x'); + GUEST_ASSERT_EQ(wp_data_addr, 0); + + GUEST_SYNC(9); + + /* OS Lock blocking single-step */ + reset_debug_state(); + enable_os_lock(); + ss_addr[0] = 0; + install_ss(); + ss_idx = 0; + asm volatile("mrs x0, esr_el1\n\t" + "add x0, x0, #1\n\t" + "msr daifset, #8\n\t" + : : : "x0"); + GUEST_ASSERT_EQ(ss_addr[0], 0); + GUEST_DONE(); } @@ -223,7 +277,7 @@ int main(int argc, char *argv[]) vm_install_sync_handler(vm, VECTOR_SYNC_CURRENT, ESR_EC_SVC64, guest_svc_handler); - for (stage = 0; stage < 7; stage++) { + for (stage = 0; stage < 11; stage++) { vcpu_run(vm, VCPU_ID); switch (get_ucall(vm, VCPU_ID, &uc)) { diff --git a/tools/testing/selftests/kvm/aarch64/get-reg-list.c b/tools/testing/selftests/kvm/aarch64/get-reg-list.c index cc898181faab..f12147c43464 100644 --- a/tools/testing/selftests/kvm/aarch64/get-reg-list.c +++ b/tools/testing/selftests/kvm/aarch64/get-reg-list.c @@ -760,6 +760,7 @@ static __u64 base_regs[] = { ARM64_SYS_REG(2, 0, 0, 15, 5), ARM64_SYS_REG(2, 0, 0, 15, 6), ARM64_SYS_REG(2, 0, 0, 15, 7), + ARM64_SYS_REG(2, 0, 1, 1, 4), /* OSLSR_EL1 */ ARM64_SYS_REG(2, 4, 0, 7, 0), /* DBGVCR32_EL2 */ ARM64_SYS_REG(3, 0, 0, 0, 5), /* MPIDR_EL1 */ ARM64_SYS_REG(3, 0, 0, 1, 0), /* ID_PFR0_EL1 */ @@ -1014,6 +1015,22 @@ static __u64 sve_rejects_set[] = { KVM_REG_ARM64_SVE_VLS, }; +static __u64 pauth_addr_regs[] = { + ARM64_SYS_REG(3, 0, 2, 1, 0), /* APIAKEYLO_EL1 */ + ARM64_SYS_REG(3, 0, 2, 1, 1), /* APIAKEYHI_EL1 */ + ARM64_SYS_REG(3, 0, 2, 1, 2), /* APIBKEYLO_EL1 */ + ARM64_SYS_REG(3, 0, 2, 1, 3), /* APIBKEYHI_EL1 */ + ARM64_SYS_REG(3, 0, 2, 2, 0), /* APDAKEYLO_EL1 */ + ARM64_SYS_REG(3, 0, 2, 2, 1), /* APDAKEYHI_EL1 */ + ARM64_SYS_REG(3, 0, 2, 2, 2), /* APDBKEYLO_EL1 */ + ARM64_SYS_REG(3, 0, 2, 2, 3) /* APDBKEYHI_EL1 */ +}; + +static __u64 pauth_generic_regs[] = { + ARM64_SYS_REG(3, 0, 2, 3, 0), /* APGAKEYLO_EL1 */ + ARM64_SYS_REG(3, 0, 2, 3, 1), /* APGAKEYHI_EL1 */ +}; + #define BASE_SUBLIST \ { "base", .regs = base_regs, .regs_n = ARRAY_SIZE(base_regs), } #define VREGS_SUBLIST \ @@ -1025,6 +1042,21 @@ static __u64 sve_rejects_set[] = { { "sve", .capability = KVM_CAP_ARM_SVE, .feature = KVM_ARM_VCPU_SVE, .finalize = true, \ .regs = sve_regs, .regs_n = ARRAY_SIZE(sve_regs), \ .rejects_set = sve_rejects_set, .rejects_set_n = ARRAY_SIZE(sve_rejects_set), } +#define PAUTH_SUBLIST \ + { \ + .name = "pauth_address", \ + .capability = KVM_CAP_ARM_PTRAUTH_ADDRESS, \ + .feature = KVM_ARM_VCPU_PTRAUTH_ADDRESS, \ + .regs = pauth_addr_regs, \ + .regs_n = ARRAY_SIZE(pauth_addr_regs), \ + }, \ + { \ + .name = "pauth_generic", \ + .capability = KVM_CAP_ARM_PTRAUTH_GENERIC, \ + .feature = KVM_ARM_VCPU_PTRAUTH_GENERIC, \ + .regs = pauth_generic_regs, \ + .regs_n = ARRAY_SIZE(pauth_generic_regs), \ + } static struct vcpu_config vregs_config = { .sublists = { @@ -1056,11 +1088,30 @@ static struct vcpu_config sve_pmu_config = { {0}, }, }; +static struct vcpu_config pauth_config = { + .sublists = { + BASE_SUBLIST, + VREGS_SUBLIST, + PAUTH_SUBLIST, + {0}, + }, +}; +static struct vcpu_config pauth_pmu_config = { + .sublists = { + BASE_SUBLIST, + VREGS_SUBLIST, + PAUTH_SUBLIST, + PMU_SUBLIST, + {0}, + }, +}; static struct vcpu_config *vcpu_configs[] = { &vregs_config, &vregs_pmu_config, &sve_config, &sve_pmu_config, + &pauth_config, + &pauth_pmu_config, }; static int vcpu_configs_n = ARRAY_SIZE(vcpu_configs); diff --git a/tools/testing/selftests/kvm/aarch64/vgic_irq.c b/tools/testing/selftests/kvm/aarch64/vgic_irq.c new file mode 100644 index 000000000000..554ca649d470 --- /dev/null +++ b/tools/testing/selftests/kvm/aarch64/vgic_irq.c @@ -0,0 +1,864 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * vgic_irq.c - Test userspace injection of IRQs + * + * This test validates the injection of IRQs from userspace using various + * methods (e.g., KVM_IRQ_LINE) and modes (e.g., EOI). The guest "asks" the + * host to inject a specific intid via a GUEST_SYNC call, and then checks that + * it received it. + */ + +#include <asm/kvm.h> +#include <asm/kvm_para.h> +#include <sys/eventfd.h> +#include <linux/sizes.h> + +#include "processor.h" +#include "test_util.h" +#include "kvm_util.h" +#include "gic.h" +#include "gic_v3.h" +#include "vgic.h" + +#define GICD_BASE_GPA 0x08000000ULL +#define GICR_BASE_GPA 0x080A0000ULL +#define VCPU_ID 0 + +/* + * Stores the user specified args; it's passed to the guest and to every test + * function. + */ +struct test_args { + uint32_t nr_irqs; /* number of KVM supported IRQs. */ + bool eoi_split; /* 1 is eoir+dir, 0 is eoir only */ + bool level_sensitive; /* 1 is level, 0 is edge */ + int kvm_max_routes; /* output of KVM_CAP_IRQ_ROUTING */ + bool kvm_supports_irqfd; /* output of KVM_CAP_IRQFD */ +}; + +/* + * KVM implements 32 priority levels: + * 0x00 (highest priority) - 0xF8 (lowest priority), in steps of 8 + * + * Note that these macros will still be correct in the case that KVM implements + * more priority levels. Also note that 32 is the minimum for GICv3 and GICv2. + */ +#define KVM_NUM_PRIOS 32 +#define KVM_PRIO_SHIFT 3 /* steps of 8 = 1 << 3 */ +#define KVM_PRIO_STEPS (1 << KVM_PRIO_SHIFT) /* 8 */ +#define LOWEST_PRIO (KVM_NUM_PRIOS - 1) +#define CPU_PRIO_MASK (LOWEST_PRIO << KVM_PRIO_SHIFT) /* 0xf8 */ +#define IRQ_DEFAULT_PRIO (LOWEST_PRIO - 1) +#define IRQ_DEFAULT_PRIO_REG (IRQ_DEFAULT_PRIO << KVM_PRIO_SHIFT) /* 0xf0 */ + +static void *dist = (void *)GICD_BASE_GPA; +static void *redist = (void *)GICR_BASE_GPA; + +/* + * The kvm_inject_* utilities are used by the guest to ask the host to inject + * interrupts (e.g., using the KVM_IRQ_LINE ioctl). + */ + +typedef enum { + KVM_INJECT_EDGE_IRQ_LINE = 1, + KVM_SET_IRQ_LINE, + KVM_SET_IRQ_LINE_HIGH, + KVM_SET_LEVEL_INFO_HIGH, + KVM_INJECT_IRQFD, + KVM_WRITE_ISPENDR, + KVM_WRITE_ISACTIVER, +} kvm_inject_cmd; + +struct kvm_inject_args { + kvm_inject_cmd cmd; + uint32_t first_intid; + uint32_t num; + int level; + bool expect_failure; +}; + +/* Used on the guest side to perform the hypercall. */ +static void kvm_inject_call(kvm_inject_cmd cmd, uint32_t first_intid, + uint32_t num, int level, bool expect_failure); + +/* Used on the host side to get the hypercall info. */ +static void kvm_inject_get_call(struct kvm_vm *vm, struct ucall *uc, + struct kvm_inject_args *args); + +#define _KVM_INJECT_MULTI(cmd, intid, num, expect_failure) \ + kvm_inject_call(cmd, intid, num, -1 /* not used */, expect_failure) + +#define KVM_INJECT_MULTI(cmd, intid, num) \ + _KVM_INJECT_MULTI(cmd, intid, num, false) + +#define _KVM_INJECT(cmd, intid, expect_failure) \ + _KVM_INJECT_MULTI(cmd, intid, 1, expect_failure) + +#define KVM_INJECT(cmd, intid) \ + _KVM_INJECT_MULTI(cmd, intid, 1, false) + +#define KVM_ACTIVATE(cmd, intid) \ + kvm_inject_call(cmd, intid, 1, 1, false); + +struct kvm_inject_desc { + kvm_inject_cmd cmd; + /* can inject PPIs, PPIs, and/or SPIs. */ + bool sgi, ppi, spi; +}; + +static struct kvm_inject_desc inject_edge_fns[] = { + /* sgi ppi spi */ + { KVM_INJECT_EDGE_IRQ_LINE, false, false, true }, + { KVM_INJECT_IRQFD, false, false, true }, + { KVM_WRITE_ISPENDR, true, false, true }, + { 0, }, +}; + +static struct kvm_inject_desc inject_level_fns[] = { + /* sgi ppi spi */ + { KVM_SET_IRQ_LINE_HIGH, false, true, true }, + { KVM_SET_LEVEL_INFO_HIGH, false, true, true }, + { KVM_INJECT_IRQFD, false, false, true }, + { KVM_WRITE_ISPENDR, false, true, true }, + { 0, }, +}; + +static struct kvm_inject_desc set_active_fns[] = { + /* sgi ppi spi */ + { KVM_WRITE_ISACTIVER, true, true, true }, + { 0, }, +}; + +#define for_each_inject_fn(t, f) \ + for ((f) = (t); (f)->cmd; (f)++) + +#define for_each_supported_inject_fn(args, t, f) \ + for_each_inject_fn(t, f) \ + if ((args)->kvm_supports_irqfd || (f)->cmd != KVM_INJECT_IRQFD) + +#define for_each_supported_activate_fn(args, t, f) \ + for_each_supported_inject_fn((args), (t), (f)) + +/* Shared between the guest main thread and the IRQ handlers. */ +volatile uint64_t irq_handled; +volatile uint32_t irqnr_received[MAX_SPI + 1]; + +static void reset_stats(void) +{ + int i; + + irq_handled = 0; + for (i = 0; i <= MAX_SPI; i++) + irqnr_received[i] = 0; +} + +static uint64_t gic_read_ap1r0(void) +{ + uint64_t reg = read_sysreg_s(SYS_ICV_AP1R0_EL1); + + dsb(sy); + return reg; +} + +static void gic_write_ap1r0(uint64_t val) +{ + write_sysreg_s(val, SYS_ICV_AP1R0_EL1); + isb(); +} + +static void guest_set_irq_line(uint32_t intid, uint32_t level); + +static void guest_irq_generic_handler(bool eoi_split, bool level_sensitive) +{ + uint32_t intid = gic_get_and_ack_irq(); + + if (intid == IAR_SPURIOUS) + return; + + GUEST_ASSERT(gic_irq_get_active(intid)); + + if (!level_sensitive) + GUEST_ASSERT(!gic_irq_get_pending(intid)); + + if (level_sensitive) + guest_set_irq_line(intid, 0); + + GUEST_ASSERT(intid < MAX_SPI); + irqnr_received[intid] += 1; + irq_handled += 1; + + gic_set_eoi(intid); + GUEST_ASSERT_EQ(gic_read_ap1r0(), 0); + if (eoi_split) + gic_set_dir(intid); + + GUEST_ASSERT(!gic_irq_get_active(intid)); + GUEST_ASSERT(!gic_irq_get_pending(intid)); +} + +static void kvm_inject_call(kvm_inject_cmd cmd, uint32_t first_intid, + uint32_t num, int level, bool expect_failure) +{ + struct kvm_inject_args args = { + .cmd = cmd, + .first_intid = first_intid, + .num = num, + .level = level, + .expect_failure = expect_failure, + }; + GUEST_SYNC(&args); +} + +#define GUEST_ASSERT_IAR_EMPTY() \ +do { \ + uint32_t _intid; \ + _intid = gic_get_and_ack_irq(); \ + GUEST_ASSERT(_intid == 0 || _intid == IAR_SPURIOUS); \ +} while (0) + +#define CAT_HELPER(a, b) a ## b +#define CAT(a, b) CAT_HELPER(a, b) +#define PREFIX guest_irq_handler_ +#define GUEST_IRQ_HANDLER_NAME(split, lev) CAT(PREFIX, CAT(split, lev)) +#define GENERATE_GUEST_IRQ_HANDLER(split, lev) \ +static void CAT(PREFIX, CAT(split, lev))(struct ex_regs *regs) \ +{ \ + guest_irq_generic_handler(split, lev); \ +} + +GENERATE_GUEST_IRQ_HANDLER(0, 0); +GENERATE_GUEST_IRQ_HANDLER(0, 1); +GENERATE_GUEST_IRQ_HANDLER(1, 0); +GENERATE_GUEST_IRQ_HANDLER(1, 1); + +static void (*guest_irq_handlers[2][2])(struct ex_regs *) = { + {GUEST_IRQ_HANDLER_NAME(0, 0), GUEST_IRQ_HANDLER_NAME(0, 1),}, + {GUEST_IRQ_HANDLER_NAME(1, 0), GUEST_IRQ_HANDLER_NAME(1, 1),}, +}; + +static void reset_priorities(struct test_args *args) +{ + int i; + + for (i = 0; i < args->nr_irqs; i++) + gic_set_priority(i, IRQ_DEFAULT_PRIO_REG); +} + +static void guest_set_irq_line(uint32_t intid, uint32_t level) +{ + kvm_inject_call(KVM_SET_IRQ_LINE, intid, 1, level, false); +} + +static void test_inject_fail(struct test_args *args, + uint32_t intid, kvm_inject_cmd cmd) +{ + reset_stats(); + + _KVM_INJECT(cmd, intid, true); + /* no IRQ to handle on entry */ + + GUEST_ASSERT_EQ(irq_handled, 0); + GUEST_ASSERT_IAR_EMPTY(); +} + +static void guest_inject(struct test_args *args, + uint32_t first_intid, uint32_t num, + kvm_inject_cmd cmd) +{ + uint32_t i; + + reset_stats(); + + /* Cycle over all priorities to make things more interesting. */ + for (i = first_intid; i < num + first_intid; i++) + gic_set_priority(i, (i % (KVM_NUM_PRIOS - 1)) << 3); + + asm volatile("msr daifset, #2" : : : "memory"); + KVM_INJECT_MULTI(cmd, first_intid, num); + + while (irq_handled < num) { + asm volatile("wfi\n" + "msr daifclr, #2\n" + /* handle IRQ */ + "msr daifset, #2\n" + : : : "memory"); + } + asm volatile("msr daifclr, #2" : : : "memory"); + + GUEST_ASSERT_EQ(irq_handled, num); + for (i = first_intid; i < num + first_intid; i++) + GUEST_ASSERT_EQ(irqnr_received[i], 1); + GUEST_ASSERT_IAR_EMPTY(); + + reset_priorities(args); +} + +/* + * Restore the active state of multiple concurrent IRQs (given by + * concurrent_irqs). This does what a live-migration would do on the + * destination side assuming there are some active IRQs that were not + * deactivated yet. + */ +static void guest_restore_active(struct test_args *args, + uint32_t first_intid, uint32_t num, + kvm_inject_cmd cmd) +{ + uint32_t prio, intid, ap1r; + int i; + + /* + * Set the priorities of the first (KVM_NUM_PRIOS - 1) IRQs + * in descending order, so intid+1 can preempt intid. + */ + for (i = 0, prio = (num - 1) * 8; i < num; i++, prio -= 8) { + GUEST_ASSERT(prio >= 0); + intid = i + first_intid; + gic_set_priority(intid, prio); + } + + /* + * In a real migration, KVM would restore all GIC state before running + * guest code. + */ + for (i = 0; i < num; i++) { + intid = i + first_intid; + KVM_ACTIVATE(cmd, intid); + ap1r = gic_read_ap1r0(); + ap1r |= 1U << i; + gic_write_ap1r0(ap1r); + } + + /* This is where the "migration" would occur. */ + + /* finish handling the IRQs starting with the highest priority one. */ + for (i = 0; i < num; i++) { + intid = num - i - 1 + first_intid; + gic_set_eoi(intid); + if (args->eoi_split) + gic_set_dir(intid); + } + + for (i = 0; i < num; i++) + GUEST_ASSERT(!gic_irq_get_active(i + first_intid)); + GUEST_ASSERT_EQ(gic_read_ap1r0(), 0); + GUEST_ASSERT_IAR_EMPTY(); +} + +/* + * Polls the IAR until it's not a spurious interrupt. + * + * This function should only be used in test_inject_preemption (with IRQs + * masked). + */ +static uint32_t wait_for_and_activate_irq(void) +{ + uint32_t intid; + + do { + asm volatile("wfi" : : : "memory"); + intid = gic_get_and_ack_irq(); + } while (intid == IAR_SPURIOUS); + + return intid; +} + +/* + * Inject multiple concurrent IRQs (num IRQs starting at first_intid) and + * handle them without handling the actual exceptions. This is done by masking + * interrupts for the whole test. + */ +static void test_inject_preemption(struct test_args *args, + uint32_t first_intid, int num, + kvm_inject_cmd cmd) +{ + uint32_t intid, prio, step = KVM_PRIO_STEPS; + int i; + + /* Set the priorities of the first (KVM_NUM_PRIOS - 1) IRQs + * in descending order, so intid+1 can preempt intid. + */ + for (i = 0, prio = (num - 1) * step; i < num; i++, prio -= step) { + GUEST_ASSERT(prio >= 0); + intid = i + first_intid; + gic_set_priority(intid, prio); + } + + local_irq_disable(); + + for (i = 0; i < num; i++) { + uint32_t tmp; + intid = i + first_intid; + KVM_INJECT(cmd, intid); + /* Each successive IRQ will preempt the previous one. */ + tmp = wait_for_and_activate_irq(); + GUEST_ASSERT_EQ(tmp, intid); + if (args->level_sensitive) + guest_set_irq_line(intid, 0); + } + + /* finish handling the IRQs starting with the highest priority one. */ + for (i = 0; i < num; i++) { + intid = num - i - 1 + first_intid; + gic_set_eoi(intid); + if (args->eoi_split) + gic_set_dir(intid); + } + + local_irq_enable(); + + for (i = 0; i < num; i++) + GUEST_ASSERT(!gic_irq_get_active(i + first_intid)); + GUEST_ASSERT_EQ(gic_read_ap1r0(), 0); + GUEST_ASSERT_IAR_EMPTY(); + + reset_priorities(args); +} + +static void test_injection(struct test_args *args, struct kvm_inject_desc *f) +{ + uint32_t nr_irqs = args->nr_irqs; + + if (f->sgi) { + guest_inject(args, MIN_SGI, 1, f->cmd); + guest_inject(args, 0, 16, f->cmd); + } + + if (f->ppi) + guest_inject(args, MIN_PPI, 1, f->cmd); + + if (f->spi) { + guest_inject(args, MIN_SPI, 1, f->cmd); + guest_inject(args, nr_irqs - 1, 1, f->cmd); + guest_inject(args, MIN_SPI, nr_irqs - MIN_SPI, f->cmd); + } +} + +static void test_injection_failure(struct test_args *args, + struct kvm_inject_desc *f) +{ + uint32_t bad_intid[] = { args->nr_irqs, 1020, 1024, 1120, 5120, ~0U, }; + int i; + + for (i = 0; i < ARRAY_SIZE(bad_intid); i++) + test_inject_fail(args, bad_intid[i], f->cmd); +} + +static void test_preemption(struct test_args *args, struct kvm_inject_desc *f) +{ + /* + * Test up to 4 levels of preemption. The reason is that KVM doesn't + * currently implement the ability to have more than the number-of-LRs + * number of concurrently active IRQs. The number of LRs implemented is + * IMPLEMENTATION DEFINED, however, it seems that most implement 4. + */ + if (f->sgi) + test_inject_preemption(args, MIN_SGI, 4, f->cmd); + + if (f->ppi) + test_inject_preemption(args, MIN_PPI, 4, f->cmd); + + if (f->spi) + test_inject_preemption(args, MIN_SPI, 4, f->cmd); +} + +static void test_restore_active(struct test_args *args, struct kvm_inject_desc *f) +{ + /* Test up to 4 active IRQs. Same reason as in test_preemption. */ + if (f->sgi) + guest_restore_active(args, MIN_SGI, 4, f->cmd); + + if (f->ppi) + guest_restore_active(args, MIN_PPI, 4, f->cmd); + + if (f->spi) + guest_restore_active(args, MIN_SPI, 4, f->cmd); +} + +static void guest_code(struct test_args *args) +{ + uint32_t i, nr_irqs = args->nr_irqs; + bool level_sensitive = args->level_sensitive; + struct kvm_inject_desc *f, *inject_fns; + + gic_init(GIC_V3, 1, dist, redist); + + for (i = 0; i < nr_irqs; i++) + gic_irq_enable(i); + + for (i = MIN_SPI; i < nr_irqs; i++) + gic_irq_set_config(i, !level_sensitive); + + gic_set_eoi_split(args->eoi_split); + + reset_priorities(args); + gic_set_priority_mask(CPU_PRIO_MASK); + + inject_fns = level_sensitive ? inject_level_fns + : inject_edge_fns; + + local_irq_enable(); + + /* Start the tests. */ + for_each_supported_inject_fn(args, inject_fns, f) { + test_injection(args, f); + test_preemption(args, f); + test_injection_failure(args, f); + } + + /* + * Restore the active state of IRQs. This would happen when live + * migrating IRQs in the middle of being handled. + */ + for_each_supported_activate_fn(args, set_active_fns, f) + test_restore_active(args, f); + + GUEST_DONE(); +} + +static void kvm_irq_line_check(struct kvm_vm *vm, uint32_t intid, int level, + struct test_args *test_args, bool expect_failure) +{ + int ret; + + if (!expect_failure) { + kvm_arm_irq_line(vm, intid, level); + } else { + /* The interface doesn't allow larger intid's. */ + if (intid > KVM_ARM_IRQ_NUM_MASK) + return; + + ret = _kvm_arm_irq_line(vm, intid, level); + TEST_ASSERT(ret != 0 && errno == EINVAL, + "Bad intid %i did not cause KVM_IRQ_LINE " + "error: rc: %i errno: %i", intid, ret, errno); + } +} + +void kvm_irq_set_level_info_check(int gic_fd, uint32_t intid, int level, + bool expect_failure) +{ + if (!expect_failure) { + kvm_irq_set_level_info(gic_fd, intid, level); + } else { + int ret = _kvm_irq_set_level_info(gic_fd, intid, level); + /* + * The kernel silently fails for invalid SPIs and SGIs (which + * are not level-sensitive). It only checks for intid to not + * spill over 1U << 10 (the max reserved SPI). Also, callers + * are supposed to mask the intid with 0x3ff (1023). + */ + if (intid > VGIC_MAX_RESERVED) + TEST_ASSERT(ret != 0 && errno == EINVAL, + "Bad intid %i did not cause VGIC_GRP_LEVEL_INFO " + "error: rc: %i errno: %i", intid, ret, errno); + else + TEST_ASSERT(!ret, "KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO " + "for intid %i failed, rc: %i errno: %i", + intid, ret, errno); + } +} + +static void kvm_set_gsi_routing_irqchip_check(struct kvm_vm *vm, + uint32_t intid, uint32_t num, uint32_t kvm_max_routes, + bool expect_failure) +{ + struct kvm_irq_routing *routing; + int ret; + uint64_t i; + + assert(num <= kvm_max_routes && kvm_max_routes <= KVM_MAX_IRQ_ROUTES); + + routing = kvm_gsi_routing_create(); + for (i = intid; i < (uint64_t)intid + num; i++) + kvm_gsi_routing_irqchip_add(routing, i - MIN_SPI, i - MIN_SPI); + + if (!expect_failure) { + kvm_gsi_routing_write(vm, routing); + } else { + ret = _kvm_gsi_routing_write(vm, routing); + /* The kernel only checks e->irqchip.pin >= KVM_IRQCHIP_NUM_PINS */ + if (((uint64_t)intid + num - 1 - MIN_SPI) >= KVM_IRQCHIP_NUM_PINS) + TEST_ASSERT(ret != 0 && errno == EINVAL, + "Bad intid %u did not cause KVM_SET_GSI_ROUTING " + "error: rc: %i errno: %i", intid, ret, errno); + else + TEST_ASSERT(ret == 0, "KVM_SET_GSI_ROUTING " + "for intid %i failed, rc: %i errno: %i", + intid, ret, errno); + } +} + +static void kvm_irq_write_ispendr_check(int gic_fd, uint32_t intid, + uint32_t vcpu, bool expect_failure) +{ + /* + * Ignore this when expecting failure as invalid intids will lead to + * either trying to inject SGIs when we configured the test to be + * level_sensitive (or the reverse), or inject large intids which + * will lead to writing above the ISPENDR register space (and we + * don't want to do that either). + */ + if (!expect_failure) + kvm_irq_write_ispendr(gic_fd, intid, vcpu); +} + +static void kvm_routing_and_irqfd_check(struct kvm_vm *vm, + uint32_t intid, uint32_t num, uint32_t kvm_max_routes, + bool expect_failure) +{ + int fd[MAX_SPI]; + uint64_t val; + int ret, f; + uint64_t i; + + /* + * There is no way to try injecting an SGI or PPI as the interface + * starts counting from the first SPI (above the private ones), so just + * exit. + */ + if (INTID_IS_SGI(intid) || INTID_IS_PPI(intid)) + return; + + kvm_set_gsi_routing_irqchip_check(vm, intid, num, + kvm_max_routes, expect_failure); + + /* + * If expect_failure, then just to inject anyway. These + * will silently fail. And in any case, the guest will check + * that no actual interrupt was injected for those cases. + */ + + for (f = 0, i = intid; i < (uint64_t)intid + num; i++, f++) { + fd[f] = eventfd(0, 0); + TEST_ASSERT(fd[f] != -1, + "eventfd failed, errno: %i\n", errno); + } + + for (f = 0, i = intid; i < (uint64_t)intid + num; i++, f++) { + struct kvm_irqfd irqfd = { + .fd = fd[f], + .gsi = i - MIN_SPI, + }; + assert(i <= (uint64_t)UINT_MAX); + vm_ioctl(vm, KVM_IRQFD, &irqfd); + } + + for (f = 0, i = intid; i < (uint64_t)intid + num; i++, f++) { + val = 1; + ret = write(fd[f], &val, sizeof(uint64_t)); + TEST_ASSERT(ret == sizeof(uint64_t), + "Write to KVM_IRQFD failed with ret: %d\n", ret); + } + + for (f = 0, i = intid; i < (uint64_t)intid + num; i++, f++) + close(fd[f]); +} + +/* handles the valid case: intid=0xffffffff num=1 */ +#define for_each_intid(first, num, tmp, i) \ + for ((tmp) = (i) = (first); \ + (tmp) < (uint64_t)(first) + (uint64_t)(num); \ + (tmp)++, (i)++) + +static void run_guest_cmd(struct kvm_vm *vm, int gic_fd, + struct kvm_inject_args *inject_args, + struct test_args *test_args) +{ + kvm_inject_cmd cmd = inject_args->cmd; + uint32_t intid = inject_args->first_intid; + uint32_t num = inject_args->num; + int level = inject_args->level; + bool expect_failure = inject_args->expect_failure; + uint64_t tmp; + uint32_t i; + + /* handles the valid case: intid=0xffffffff num=1 */ + assert(intid < UINT_MAX - num || num == 1); + + switch (cmd) { + case KVM_INJECT_EDGE_IRQ_LINE: + for_each_intid(intid, num, tmp, i) + kvm_irq_line_check(vm, i, 1, test_args, + expect_failure); + for_each_intid(intid, num, tmp, i) + kvm_irq_line_check(vm, i, 0, test_args, + expect_failure); + break; + case KVM_SET_IRQ_LINE: + for_each_intid(intid, num, tmp, i) + kvm_irq_line_check(vm, i, level, test_args, + expect_failure); + break; + case KVM_SET_IRQ_LINE_HIGH: + for_each_intid(intid, num, tmp, i) + kvm_irq_line_check(vm, i, 1, test_args, + expect_failure); + break; + case KVM_SET_LEVEL_INFO_HIGH: + for_each_intid(intid, num, tmp, i) + kvm_irq_set_level_info_check(gic_fd, i, 1, + expect_failure); + break; + case KVM_INJECT_IRQFD: + kvm_routing_and_irqfd_check(vm, intid, num, + test_args->kvm_max_routes, + expect_failure); + break; + case KVM_WRITE_ISPENDR: + for (i = intid; i < intid + num; i++) + kvm_irq_write_ispendr_check(gic_fd, i, + VCPU_ID, expect_failure); + break; + case KVM_WRITE_ISACTIVER: + for (i = intid; i < intid + num; i++) + kvm_irq_write_isactiver(gic_fd, i, VCPU_ID); + break; + default: + break; + } +} + +static void kvm_inject_get_call(struct kvm_vm *vm, struct ucall *uc, + struct kvm_inject_args *args) +{ + struct kvm_inject_args *kvm_args_hva; + vm_vaddr_t kvm_args_gva; + + kvm_args_gva = uc->args[1]; + kvm_args_hva = (struct kvm_inject_args *)addr_gva2hva(vm, kvm_args_gva); + memcpy(args, kvm_args_hva, sizeof(struct kvm_inject_args)); +} + +static void print_args(struct test_args *args) +{ + printf("nr-irqs=%d level-sensitive=%d eoi-split=%d\n", + args->nr_irqs, args->level_sensitive, + args->eoi_split); +} + +static void test_vgic(uint32_t nr_irqs, bool level_sensitive, bool eoi_split) +{ + struct ucall uc; + int gic_fd; + struct kvm_vm *vm; + struct kvm_inject_args inject_args; + vm_vaddr_t args_gva; + + struct test_args args = { + .nr_irqs = nr_irqs, + .level_sensitive = level_sensitive, + .eoi_split = eoi_split, + .kvm_max_routes = kvm_check_cap(KVM_CAP_IRQ_ROUTING), + .kvm_supports_irqfd = kvm_check_cap(KVM_CAP_IRQFD), + }; + + print_args(&args); + + vm = vm_create_default(VCPU_ID, 0, guest_code); + ucall_init(vm, NULL); + + vm_init_descriptor_tables(vm); + vcpu_init_descriptor_tables(vm, VCPU_ID); + + /* Setup the guest args page (so it gets the args). */ + args_gva = vm_vaddr_alloc_page(vm); + memcpy(addr_gva2hva(vm, args_gva), &args, sizeof(args)); + vcpu_args_set(vm, 0, 1, args_gva); + + gic_fd = vgic_v3_setup(vm, 1, nr_irqs, + GICD_BASE_GPA, GICR_BASE_GPA); + if (gic_fd < 0) { + print_skip("Failed to create vgic-v3, skipping"); + exit(KSFT_SKIP); + } + + vm_install_exception_handler(vm, VECTOR_IRQ_CURRENT, + guest_irq_handlers[args.eoi_split][args.level_sensitive]); + + while (1) { + vcpu_run(vm, VCPU_ID); + + switch (get_ucall(vm, VCPU_ID, &uc)) { + case UCALL_SYNC: + kvm_inject_get_call(vm, &uc, &inject_args); + run_guest_cmd(vm, gic_fd, &inject_args, &args); + break; + case UCALL_ABORT: + TEST_FAIL("%s at %s:%ld\n\tvalues: %#lx, %#lx", + (const char *)uc.args[0], + __FILE__, uc.args[1], uc.args[2], uc.args[3]); + break; + case UCALL_DONE: + goto done; + default: + TEST_FAIL("Unknown ucall %lu", uc.cmd); + } + } + +done: + close(gic_fd); + kvm_vm_free(vm); +} + +static void help(const char *name) +{ + printf( + "\n" + "usage: %s [-n num_irqs] [-e eoi_split] [-l level_sensitive]\n", name); + printf(" -n: specify number of IRQs to setup the vgic with. " + "It has to be a multiple of 32 and between 64 and 1024.\n"); + printf(" -e: if 1 then EOI is split into a write to DIR on top " + "of writing EOI.\n"); + printf(" -l: specify whether the IRQs are level-sensitive (1) or not (0)."); + puts(""); + exit(1); +} + +int main(int argc, char **argv) +{ + uint32_t nr_irqs = 64; + bool default_args = true; + bool level_sensitive = false; + int opt; + bool eoi_split = false; + + /* Tell stdout not to buffer its content */ + setbuf(stdout, NULL); + + while ((opt = getopt(argc, argv, "hn:e:l:")) != -1) { + switch (opt) { + case 'n': + nr_irqs = atoi(optarg); + if (nr_irqs > 1024 || nr_irqs % 32) + help(argv[0]); + break; + case 'e': + eoi_split = (bool)atoi(optarg); + default_args = false; + break; + case 'l': + level_sensitive = (bool)atoi(optarg); + default_args = false; + break; + case 'h': + default: + help(argv[0]); + break; + } + } + + /* + * If the user just specified nr_irqs and/or gic_version, then run all + * combinations. + */ + if (default_args) { + test_vgic(nr_irqs, false /* level */, false /* eoi_split */); + test_vgic(nr_irqs, false /* level */, true /* eoi_split */); + test_vgic(nr_irqs, true /* level */, false /* eoi_split */); + test_vgic(nr_irqs, true /* level */, true /* eoi_split */); + } else { + test_vgic(nr_irqs, level_sensitive, eoi_split); + } + + return 0; +} diff --git a/tools/testing/selftests/kvm/dirty_log_perf_test.c b/tools/testing/selftests/kvm/dirty_log_perf_test.c index 1954b964d1cf..c9d9e513ca04 100644 --- a/tools/testing/selftests/kvm/dirty_log_perf_test.c +++ b/tools/testing/selftests/kvm/dirty_log_perf_test.c @@ -18,6 +18,12 @@ #include "test_util.h" #include "perf_test_util.h" #include "guest_modes.h" +#ifdef __aarch64__ +#include "aarch64/vgic.h" + +#define GICD_BASE_GPA 0x8000000ULL +#define GICR_BASE_GPA 0x80A0000ULL +#endif /* How many host loops to run by default (one KVM_GET_DIRTY_LOG for each loop)*/ #define TEST_HOST_LOOP_N 2UL @@ -200,6 +206,10 @@ static void run_test(enum vm_guest_mode mode, void *arg) vm_enable_cap(vm, &cap); } +#ifdef __aarch64__ + vgic_v3_setup(vm, nr_vcpus, 64, GICD_BASE_GPA, GICR_BASE_GPA); +#endif + /* Start the iterations */ iteration = 0; host_quit = false; @@ -298,12 +308,18 @@ static void run_test(enum vm_guest_mode mode, void *arg) static void help(char *name) { puts(""); - printf("usage: %s [-h] [-i iterations] [-p offset] " + printf("usage: %s [-h] [-i iterations] [-p offset] [-g]" "[-m mode] [-b vcpu bytes] [-v vcpus] [-o] [-s mem type]" "[-x memslots]\n", name); puts(""); printf(" -i: specify iteration counts (default: %"PRIu64")\n", TEST_HOST_LOOP_N); + printf(" -g: Do not enable KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2. This\n" + " makes KVM_GET_DIRTY_LOG clear the dirty log (i.e.\n" + " KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE is not enabled)\n" + " and writes will be tracked as soon as dirty logging is\n" + " enabled on the memslot (i.e. KVM_DIRTY_LOG_INITIALLY_SET\n" + " is not enabled).\n"); printf(" -p: specify guest physical test memory offset\n" " Warning: a low offset can conflict with the loaded test code.\n"); guest_modes_help(); @@ -343,8 +359,11 @@ int main(int argc, char *argv[]) guest_modes_append_default(); - while ((opt = getopt(argc, argv, "hi:p:m:b:f:v:os:x:")) != -1) { + while ((opt = getopt(argc, argv, "ghi:p:m:b:f:v:os:x:")) != -1) { switch (opt) { + case 'g': + dirty_log_manual_caps = 0; + break; case 'i': p.iterations = atoi(optarg); break; diff --git a/tools/testing/selftests/kvm/include/aarch64/gic.h b/tools/testing/selftests/kvm/include/aarch64/gic.h index 85dd1e53048e..b217ea17cac5 100644 --- a/tools/testing/selftests/kvm/include/aarch64/gic.h +++ b/tools/testing/selftests/kvm/include/aarch64/gic.h @@ -11,11 +11,37 @@ enum gic_type { GIC_TYPE_MAX, }; +#define MIN_SGI 0 +#define MIN_PPI 16 +#define MIN_SPI 32 +#define MAX_SPI 1019 +#define IAR_SPURIOUS 1023 + +#define INTID_IS_SGI(intid) (0 <= (intid) && (intid) < MIN_PPI) +#define INTID_IS_PPI(intid) (MIN_PPI <= (intid) && (intid) < MIN_SPI) +#define INTID_IS_SPI(intid) (MIN_SPI <= (intid) && (intid) <= MAX_SPI) + void gic_init(enum gic_type type, unsigned int nr_cpus, void *dist_base, void *redist_base); void gic_irq_enable(unsigned int intid); void gic_irq_disable(unsigned int intid); unsigned int gic_get_and_ack_irq(void); void gic_set_eoi(unsigned int intid); +void gic_set_dir(unsigned int intid); + +/* + * Sets the EOI mode. When split is false, EOI just drops the priority. When + * split is true, EOI drops the priority and deactivates the interrupt. + */ +void gic_set_eoi_split(bool split); +void gic_set_priority_mask(uint64_t mask); +void gic_set_priority(uint32_t intid, uint32_t prio); +void gic_irq_set_active(unsigned int intid); +void gic_irq_clear_active(unsigned int intid); +bool gic_irq_get_active(unsigned int intid); +void gic_irq_set_pending(unsigned int intid); +void gic_irq_clear_pending(unsigned int intid); +bool gic_irq_get_pending(unsigned int intid); +void gic_irq_set_config(unsigned int intid, bool is_edge); #endif /* SELFTEST_KVM_GIC_H */ diff --git a/tools/testing/selftests/kvm/lib/aarch64/gic_v3.h b/tools/testing/selftests/kvm/include/aarch64/gic_v3.h index b51536d469a6..ba0886e8a2bb 100644 --- a/tools/testing/selftests/kvm/lib/aarch64/gic_v3.h +++ b/tools/testing/selftests/kvm/include/aarch64/gic_v3.h @@ -16,8 +16,12 @@ #define GICD_IGROUPR 0x0080 #define GICD_ISENABLER 0x0100 #define GICD_ICENABLER 0x0180 +#define GICD_ISPENDR 0x0200 +#define GICD_ICPENDR 0x0280 #define GICD_ICACTIVER 0x0380 +#define GICD_ISACTIVER 0x0300 #define GICD_IPRIORITYR 0x0400 +#define GICD_ICFGR 0x0C00 /* * The assumption is that the guest runs in a non-secure mode. @@ -49,16 +53,24 @@ #define GICR_IGROUPR0 GICD_IGROUPR #define GICR_ISENABLER0 GICD_ISENABLER #define GICR_ICENABLER0 GICD_ICENABLER +#define GICR_ISPENDR0 GICD_ISPENDR +#define GICR_ISACTIVER0 GICD_ISACTIVER #define GICR_ICACTIVER0 GICD_ICACTIVER +#define GICR_ICENABLER GICD_ICENABLER +#define GICR_ICACTIVER GICD_ICACTIVER #define GICR_IPRIORITYR0 GICD_IPRIORITYR /* CPU interface registers */ #define SYS_ICC_PMR_EL1 sys_reg(3, 0, 4, 6, 0) #define SYS_ICC_IAR1_EL1 sys_reg(3, 0, 12, 12, 0) #define SYS_ICC_EOIR1_EL1 sys_reg(3, 0, 12, 12, 1) +#define SYS_ICC_DIR_EL1 sys_reg(3, 0, 12, 11, 1) +#define SYS_ICC_CTLR_EL1 sys_reg(3, 0, 12, 12, 4) #define SYS_ICC_SRE_EL1 sys_reg(3, 0, 12, 12, 5) #define SYS_ICC_GRPEN1_EL1 sys_reg(3, 0, 12, 12, 7) +#define SYS_ICV_AP1R0_EL1 sys_reg(3, 0, 12, 9, 0) + #define ICC_PMR_DEF_PRIO 0xf0 #define ICC_SRE_EL1_SRE (1U << 0) diff --git a/tools/testing/selftests/kvm/include/aarch64/processor.h b/tools/testing/selftests/kvm/include/aarch64/processor.h index 27d8e1bb5b36..8f9f46979a00 100644 --- a/tools/testing/selftests/kvm/include/aarch64/processor.h +++ b/tools/testing/selftests/kvm/include/aarch64/processor.h @@ -113,6 +113,9 @@ enum { #define ESR_EC_WP_CURRENT 0x35 #define ESR_EC_BRK_INS 0x3c +void aarch64_get_supported_page_sizes(uint32_t ipa, + bool *ps4k, bool *ps16k, bool *ps64k); + void vm_init_descriptor_tables(struct kvm_vm *vm); void vcpu_init_descriptor_tables(struct kvm_vm *vm, uint32_t vcpuid); diff --git a/tools/testing/selftests/kvm/include/aarch64/vgic.h b/tools/testing/selftests/kvm/include/aarch64/vgic.h index 0ecfb253893c..4442081221a0 100644 --- a/tools/testing/selftests/kvm/include/aarch64/vgic.h +++ b/tools/testing/selftests/kvm/include/aarch64/vgic.h @@ -14,7 +14,21 @@ ((uint64_t)(flags) << 12) | \ index) -int vgic_v3_setup(struct kvm_vm *vm, unsigned int nr_vcpus, +int vgic_v3_setup(struct kvm_vm *vm, unsigned int nr_vcpus, uint32_t nr_irqs, uint64_t gicd_base_gpa, uint64_t gicr_base_gpa); -#endif /* SELFTEST_KVM_VGIC_H */ +#define VGIC_MAX_RESERVED 1023 + +void kvm_irq_set_level_info(int gic_fd, uint32_t intid, int level); +int _kvm_irq_set_level_info(int gic_fd, uint32_t intid, int level); + +void kvm_arm_irq_line(struct kvm_vm *vm, uint32_t intid, int level); +int _kvm_arm_irq_line(struct kvm_vm *vm, uint32_t intid, int level); + +/* The vcpu arg only applies to private interrupts. */ +void kvm_irq_write_ispendr(int gic_fd, uint32_t intid, uint32_t vcpu); +void kvm_irq_write_isactiver(int gic_fd, uint32_t intid, uint32_t vcpu); + +#define KVM_IRQCHIP_NUM_PINS (1020 - 32) + +#endif // SELFTEST_KVM_VGIC_H diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h index 2d62edc49d67..c9286811a4cb 100644 --- a/tools/testing/selftests/kvm/include/kvm_util.h +++ b/tools/testing/selftests/kvm/include/kvm_util.h @@ -7,412 +7,7 @@ #ifndef SELFTEST_KVM_UTIL_H #define SELFTEST_KVM_UTIL_H -#include "test_util.h" - -#include "asm/kvm.h" -#include "linux/list.h" -#include "linux/kvm.h" -#include <sys/ioctl.h> - -#include "sparsebit.h" - -#define KVM_DEV_PATH "/dev/kvm" -#define KVM_MAX_VCPUS 512 - -#define NSEC_PER_SEC 1000000000L - -/* - * Callers of kvm_util only have an incomplete/opaque description of the - * structure kvm_util is using to maintain the state of a VM. - */ -struct kvm_vm; - -typedef uint64_t vm_paddr_t; /* Virtual Machine (Guest) physical address */ -typedef uint64_t vm_vaddr_t; /* Virtual Machine (Guest) virtual address */ - -/* Minimum allocated guest virtual and physical addresses */ -#define KVM_UTIL_MIN_VADDR 0x2000 -#define KVM_GUEST_PAGE_TABLE_MIN_PADDR 0x180000 - -#define DEFAULT_GUEST_PHY_PAGES 512 -#define DEFAULT_GUEST_STACK_VADDR_MIN 0xab6000 -#define DEFAULT_STACK_PGS 5 - -enum vm_guest_mode { - VM_MODE_P52V48_4K, - VM_MODE_P52V48_64K, - VM_MODE_P48V48_4K, - VM_MODE_P48V48_64K, - VM_MODE_P40V48_4K, - VM_MODE_P40V48_64K, - VM_MODE_PXXV48_4K, /* For 48bits VA but ANY bits PA */ - VM_MODE_P47V64_4K, - VM_MODE_P44V64_4K, - NUM_VM_MODES, -}; - -#if defined(__aarch64__) - -#define VM_MODE_DEFAULT VM_MODE_P40V48_4K -#define MIN_PAGE_SHIFT 12U -#define ptes_per_page(page_size) ((page_size) / 8) - -#elif defined(__x86_64__) - -#define VM_MODE_DEFAULT VM_MODE_PXXV48_4K -#define MIN_PAGE_SHIFT 12U -#define ptes_per_page(page_size) ((page_size) / 8) - -#elif defined(__s390x__) - -#define VM_MODE_DEFAULT VM_MODE_P44V64_4K -#define MIN_PAGE_SHIFT 12U -#define ptes_per_page(page_size) ((page_size) / 16) - -#endif - -#define MIN_PAGE_SIZE (1U << MIN_PAGE_SHIFT) -#define PTES_PER_MIN_PAGE ptes_per_page(MIN_PAGE_SIZE) - -struct vm_guest_mode_params { - unsigned int pa_bits; - unsigned int va_bits; - unsigned int page_size; - unsigned int page_shift; -}; -extern const struct vm_guest_mode_params vm_guest_mode_params[]; - -int open_path_or_exit(const char *path, int flags); -int open_kvm_dev_path_or_exit(void); -int kvm_check_cap(long cap); -int vm_enable_cap(struct kvm_vm *vm, struct kvm_enable_cap *cap); -int vcpu_enable_cap(struct kvm_vm *vm, uint32_t vcpu_id, - struct kvm_enable_cap *cap); -void vm_enable_dirty_ring(struct kvm_vm *vm, uint32_t ring_size); -const char *vm_guest_mode_string(uint32_t i); - -struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm); -void kvm_vm_free(struct kvm_vm *vmp); -void kvm_vm_restart(struct kvm_vm *vmp, int perm); -void kvm_vm_release(struct kvm_vm *vmp); -void kvm_vm_get_dirty_log(struct kvm_vm *vm, int slot, void *log); -void kvm_vm_clear_dirty_log(struct kvm_vm *vm, int slot, void *log, - uint64_t first_page, uint32_t num_pages); -uint32_t kvm_vm_reset_dirty_ring(struct kvm_vm *vm); - -int kvm_memcmp_hva_gva(void *hva, struct kvm_vm *vm, const vm_vaddr_t gva, - size_t len); - -void kvm_vm_elf_load(struct kvm_vm *vm, const char *filename); - -void vm_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent); - -/* - * VM VCPU Dump - * - * Input Args: - * stream - Output FILE stream - * vm - Virtual Machine - * vcpuid - VCPU ID - * indent - Left margin indent amount - * - * Output Args: None - * - * Return: None - * - * Dumps the current state of the VCPU specified by @vcpuid, within the VM - * given by @vm, to the FILE stream given by @stream. - */ -void vcpu_dump(FILE *stream, struct kvm_vm *vm, uint32_t vcpuid, - uint8_t indent); - -void vm_create_irqchip(struct kvm_vm *vm); - -void vm_userspace_mem_region_add(struct kvm_vm *vm, - enum vm_mem_backing_src_type src_type, - uint64_t guest_paddr, uint32_t slot, uint64_t npages, - uint32_t flags); - -void vcpu_ioctl(struct kvm_vm *vm, uint32_t vcpuid, unsigned long ioctl, - void *arg); -int _vcpu_ioctl(struct kvm_vm *vm, uint32_t vcpuid, unsigned long ioctl, - void *arg); -void vm_ioctl(struct kvm_vm *vm, unsigned long ioctl, void *arg); -int _vm_ioctl(struct kvm_vm *vm, unsigned long cmd, void *arg); -void kvm_ioctl(struct kvm_vm *vm, unsigned long ioctl, void *arg); -int _kvm_ioctl(struct kvm_vm *vm, unsigned long ioctl, void *arg); -void vm_mem_region_set_flags(struct kvm_vm *vm, uint32_t slot, uint32_t flags); -void vm_mem_region_move(struct kvm_vm *vm, uint32_t slot, uint64_t new_gpa); -void vm_mem_region_delete(struct kvm_vm *vm, uint32_t slot); -void vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpuid); -vm_vaddr_t vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min); -vm_vaddr_t vm_vaddr_alloc_pages(struct kvm_vm *vm, int nr_pages); -vm_vaddr_t vm_vaddr_alloc_page(struct kvm_vm *vm); - -void virt_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, - unsigned int npages); -void *addr_gpa2hva(struct kvm_vm *vm, vm_paddr_t gpa); -void *addr_gva2hva(struct kvm_vm *vm, vm_vaddr_t gva); -vm_paddr_t addr_hva2gpa(struct kvm_vm *vm, void *hva); -void *addr_gpa2alias(struct kvm_vm *vm, vm_paddr_t gpa); - -/* - * Address Guest Virtual to Guest Physical - * - * Input Args: - * vm - Virtual Machine - * gva - VM virtual address - * - * Output Args: None - * - * Return: - * Equivalent VM physical address - * - * Returns the VM physical address of the translated VM virtual - * address given by @gva. - */ -vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva); - -struct kvm_run *vcpu_state(struct kvm_vm *vm, uint32_t vcpuid); -void vcpu_run(struct kvm_vm *vm, uint32_t vcpuid); -int _vcpu_run(struct kvm_vm *vm, uint32_t vcpuid); -int vcpu_get_fd(struct kvm_vm *vm, uint32_t vcpuid); -void vcpu_run_complete_io(struct kvm_vm *vm, uint32_t vcpuid); -void vcpu_set_guest_debug(struct kvm_vm *vm, uint32_t vcpuid, - struct kvm_guest_debug *debug); -void vcpu_set_mp_state(struct kvm_vm *vm, uint32_t vcpuid, - struct kvm_mp_state *mp_state); -struct kvm_reg_list *vcpu_get_reg_list(struct kvm_vm *vm, uint32_t vcpuid); -void vcpu_regs_get(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_regs *regs); -void vcpu_regs_set(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_regs *regs); - -/* - * VM VCPU Args Set - * - * Input Args: - * vm - Virtual Machine - * vcpuid - VCPU ID - * num - number of arguments - * ... - arguments, each of type uint64_t - * - * Output Args: None - * - * Return: None - * - * Sets the first @num function input registers of the VCPU with @vcpuid, - * per the C calling convention of the architecture, to the values given - * as variable args. Each of the variable args is expected to be of type - * uint64_t. The maximum @num can be is specific to the architecture. - */ -void vcpu_args_set(struct kvm_vm *vm, uint32_t vcpuid, unsigned int num, ...); - -void vcpu_sregs_get(struct kvm_vm *vm, uint32_t vcpuid, - struct kvm_sregs *sregs); -void vcpu_sregs_set(struct kvm_vm *vm, uint32_t vcpuid, - struct kvm_sregs *sregs); -int _vcpu_sregs_set(struct kvm_vm *vm, uint32_t vcpuid, - struct kvm_sregs *sregs); -void vcpu_fpu_get(struct kvm_vm *vm, uint32_t vcpuid, - struct kvm_fpu *fpu); -void vcpu_fpu_set(struct kvm_vm *vm, uint32_t vcpuid, - struct kvm_fpu *fpu); -void vcpu_get_reg(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_one_reg *reg); -void vcpu_set_reg(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_one_reg *reg); -#ifdef __KVM_HAVE_VCPU_EVENTS -void vcpu_events_get(struct kvm_vm *vm, uint32_t vcpuid, - struct kvm_vcpu_events *events); -void vcpu_events_set(struct kvm_vm *vm, uint32_t vcpuid, - struct kvm_vcpu_events *events); -#endif -#ifdef __x86_64__ -void vcpu_nested_state_get(struct kvm_vm *vm, uint32_t vcpuid, - struct kvm_nested_state *state); -int vcpu_nested_state_set(struct kvm_vm *vm, uint32_t vcpuid, - struct kvm_nested_state *state, bool ignore_error); -#endif -void *vcpu_map_dirty_ring(struct kvm_vm *vm, uint32_t vcpuid); - -int _kvm_device_check_attr(int dev_fd, uint32_t group, uint64_t attr); -int kvm_device_check_attr(int dev_fd, uint32_t group, uint64_t attr); -int _kvm_create_device(struct kvm_vm *vm, uint64_t type, bool test, int *fd); -int kvm_create_device(struct kvm_vm *vm, uint64_t type, bool test); -int _kvm_device_access(int dev_fd, uint32_t group, uint64_t attr, - void *val, bool write); -int kvm_device_access(int dev_fd, uint32_t group, uint64_t attr, - void *val, bool write); - -int _vcpu_has_device_attr(struct kvm_vm *vm, uint32_t vcpuid, uint32_t group, - uint64_t attr); -int vcpu_has_device_attr(struct kvm_vm *vm, uint32_t vcpuid, uint32_t group, - uint64_t attr); -int _vcpu_access_device_attr(struct kvm_vm *vm, uint32_t vcpuid, uint32_t group, - uint64_t attr, void *val, bool write); -int vcpu_access_device_attr(struct kvm_vm *vm, uint32_t vcpuid, uint32_t group, - uint64_t attr, void *val, bool write); - -const char *exit_reason_str(unsigned int exit_reason); - -void virt_pgd_alloc(struct kvm_vm *vm); - -/* - * VM Virtual Page Map - * - * Input Args: - * vm - Virtual Machine - * vaddr - VM Virtual Address - * paddr - VM Physical Address - * memslot - Memory region slot for new virtual translation tables - * - * Output Args: None - * - * Return: None - * - * Within @vm, creates a virtual translation for the page starting - * at @vaddr to the page starting at @paddr. - */ -void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr); - -vm_paddr_t vm_phy_page_alloc(struct kvm_vm *vm, vm_paddr_t paddr_min, - uint32_t memslot); -vm_paddr_t vm_phy_pages_alloc(struct kvm_vm *vm, size_t num, - vm_paddr_t paddr_min, uint32_t memslot); -vm_paddr_t vm_alloc_page_table(struct kvm_vm *vm); - -/* - * Create a VM with reasonable defaults - * - * Input Args: - * vcpuid - The id of the single VCPU to add to the VM. - * extra_mem_pages - The number of extra pages to add (this will - * decide how much extra space we will need to - * setup the page tables using memslot 0) - * guest_code - The vCPU's entry point - * - * Output Args: None - * - * Return: - * Pointer to opaque structure that describes the created VM. - */ -struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages, - void *guest_code); - -/* Same as vm_create_default, but can be used for more than one vcpu */ -struct kvm_vm *vm_create_default_with_vcpus(uint32_t nr_vcpus, uint64_t extra_mem_pages, - uint32_t num_percpu_pages, void *guest_code, - uint32_t vcpuids[]); - -/* Like vm_create_default_with_vcpus, but accepts mode and slot0 memory as a parameter */ -struct kvm_vm *vm_create_with_vcpus(enum vm_guest_mode mode, uint32_t nr_vcpus, - uint64_t slot0_mem_pages, uint64_t extra_mem_pages, - uint32_t num_percpu_pages, void *guest_code, - uint32_t vcpuids[]); - -/* - * Adds a vCPU with reasonable defaults (e.g. a stack) - * - * Input Args: - * vm - Virtual Machine - * vcpuid - The id of the VCPU to add to the VM. - * guest_code - The vCPU's entry point - */ -void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code); - -bool vm_is_unrestricted_guest(struct kvm_vm *vm); - -unsigned int vm_get_page_size(struct kvm_vm *vm); -unsigned int vm_get_page_shift(struct kvm_vm *vm); -unsigned long vm_compute_max_gfn(struct kvm_vm *vm); -uint64_t vm_get_max_gfn(struct kvm_vm *vm); -int vm_get_fd(struct kvm_vm *vm); - -unsigned int vm_calc_num_guest_pages(enum vm_guest_mode mode, size_t size); -unsigned int vm_num_host_pages(enum vm_guest_mode mode, unsigned int num_guest_pages); -unsigned int vm_num_guest_pages(enum vm_guest_mode mode, unsigned int num_host_pages); -static inline unsigned int -vm_adjust_num_guest_pages(enum vm_guest_mode mode, unsigned int num_guest_pages) -{ - unsigned int n; - n = vm_num_guest_pages(mode, vm_num_host_pages(mode, num_guest_pages)); -#ifdef __s390x__ - /* s390 requires 1M aligned guest sizes */ - n = (n + 255) & ~255; -#endif - return n; -} - -struct kvm_userspace_memory_region * -kvm_userspace_memory_region_find(struct kvm_vm *vm, uint64_t start, - uint64_t end); - -struct kvm_dirty_log * -allocate_kvm_dirty_log(struct kvm_userspace_memory_region *region); - -int vm_create_device(struct kvm_vm *vm, struct kvm_create_device *cd); - -#define sync_global_to_guest(vm, g) ({ \ - typeof(g) *_p = addr_gva2hva(vm, (vm_vaddr_t)&(g)); \ - memcpy(_p, &(g), sizeof(g)); \ -}) - -#define sync_global_from_guest(vm, g) ({ \ - typeof(g) *_p = addr_gva2hva(vm, (vm_vaddr_t)&(g)); \ - memcpy(&(g), _p, sizeof(g)); \ -}) - -void assert_on_unhandled_exception(struct kvm_vm *vm, uint32_t vcpuid); - -/* Common ucalls */ -enum { - UCALL_NONE, - UCALL_SYNC, - UCALL_ABORT, - UCALL_DONE, - UCALL_UNHANDLED, -}; - -#define UCALL_MAX_ARGS 6 - -struct ucall { - uint64_t cmd; - uint64_t args[UCALL_MAX_ARGS]; -}; - -void ucall_init(struct kvm_vm *vm, void *arg); -void ucall_uninit(struct kvm_vm *vm); -void ucall(uint64_t cmd, int nargs, ...); -uint64_t get_ucall(struct kvm_vm *vm, uint32_t vcpu_id, struct ucall *uc); - -#define GUEST_SYNC_ARGS(stage, arg1, arg2, arg3, arg4) \ - ucall(UCALL_SYNC, 6, "hello", stage, arg1, arg2, arg3, arg4) -#define GUEST_SYNC(stage) ucall(UCALL_SYNC, 2, "hello", stage) -#define GUEST_DONE() ucall(UCALL_DONE, 0) -#define __GUEST_ASSERT(_condition, _condstr, _nargs, _args...) do { \ - if (!(_condition)) \ - ucall(UCALL_ABORT, 2 + _nargs, \ - "Failed guest assert: " \ - _condstr, __LINE__, _args); \ -} while (0) - -#define GUEST_ASSERT(_condition) \ - __GUEST_ASSERT(_condition, #_condition, 0, 0) - -#define GUEST_ASSERT_1(_condition, arg1) \ - __GUEST_ASSERT(_condition, #_condition, 1, (arg1)) - -#define GUEST_ASSERT_2(_condition, arg1, arg2) \ - __GUEST_ASSERT(_condition, #_condition, 2, (arg1), (arg2)) - -#define GUEST_ASSERT_3(_condition, arg1, arg2, arg3) \ - __GUEST_ASSERT(_condition, #_condition, 3, (arg1), (arg2), (arg3)) - -#define GUEST_ASSERT_4(_condition, arg1, arg2, arg3, arg4) \ - __GUEST_ASSERT(_condition, #_condition, 4, (arg1), (arg2), (arg3), (arg4)) - -#define GUEST_ASSERT_EQ(a, b) __GUEST_ASSERT((a) == (b), #a " == " #b, 2, a, b) - -int vm_get_stats_fd(struct kvm_vm *vm); -int vcpu_get_stats_fd(struct kvm_vm *vm, uint32_t vcpuid); - -uint32_t guest_get_vcpuid(void); +#include "kvm_util_base.h" +#include "ucall_common.h" #endif /* SELFTEST_KVM_UTIL_H */ diff --git a/tools/testing/selftests/kvm/include/kvm_util_base.h b/tools/testing/selftests/kvm/include/kvm_util_base.h new file mode 100644 index 000000000000..92cef0ffb19e --- /dev/null +++ b/tools/testing/selftests/kvm/include/kvm_util_base.h @@ -0,0 +1,406 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * tools/testing/selftests/kvm/include/kvm_util_base.h + * + * Copyright (C) 2018, Google LLC. + */ +#ifndef SELFTEST_KVM_UTIL_BASE_H +#define SELFTEST_KVM_UTIL_BASE_H + +#include "test_util.h" + +#include "asm/kvm.h" +#include "linux/list.h" +#include "linux/kvm.h" +#include <sys/ioctl.h> + +#include "sparsebit.h" + +#define KVM_DEV_PATH "/dev/kvm" +#define KVM_MAX_VCPUS 512 + +#define NSEC_PER_SEC 1000000000L + +/* + * Callers of kvm_util only have an incomplete/opaque description of the + * structure kvm_util is using to maintain the state of a VM. + */ +struct kvm_vm; + +typedef uint64_t vm_paddr_t; /* Virtual Machine (Guest) physical address */ +typedef uint64_t vm_vaddr_t; /* Virtual Machine (Guest) virtual address */ + +/* Minimum allocated guest virtual and physical addresses */ +#define KVM_UTIL_MIN_VADDR 0x2000 +#define KVM_GUEST_PAGE_TABLE_MIN_PADDR 0x180000 + +#define DEFAULT_GUEST_PHY_PAGES 512 +#define DEFAULT_GUEST_STACK_VADDR_MIN 0xab6000 +#define DEFAULT_STACK_PGS 5 + +enum vm_guest_mode { + VM_MODE_P52V48_4K, + VM_MODE_P52V48_64K, + VM_MODE_P48V48_4K, + VM_MODE_P48V48_16K, + VM_MODE_P48V48_64K, + VM_MODE_P40V48_4K, + VM_MODE_P40V48_16K, + VM_MODE_P40V48_64K, + VM_MODE_PXXV48_4K, /* For 48bits VA but ANY bits PA */ + VM_MODE_P47V64_4K, + VM_MODE_P44V64_4K, + VM_MODE_P36V48_4K, + VM_MODE_P36V48_16K, + VM_MODE_P36V48_64K, + VM_MODE_P36V47_16K, + NUM_VM_MODES, +}; + +#if defined(__aarch64__) + +extern enum vm_guest_mode vm_mode_default; + +#define VM_MODE_DEFAULT vm_mode_default +#define MIN_PAGE_SHIFT 12U +#define ptes_per_page(page_size) ((page_size) / 8) + +#elif defined(__x86_64__) + +#define VM_MODE_DEFAULT VM_MODE_PXXV48_4K +#define MIN_PAGE_SHIFT 12U +#define ptes_per_page(page_size) ((page_size) / 8) + +#elif defined(__s390x__) + +#define VM_MODE_DEFAULT VM_MODE_P44V64_4K +#define MIN_PAGE_SHIFT 12U +#define ptes_per_page(page_size) ((page_size) / 16) + +#elif defined(__riscv) + +#if __riscv_xlen == 32 +#error "RISC-V 32-bit kvm selftests not supported" +#endif + +#define VM_MODE_DEFAULT VM_MODE_P40V48_4K +#define MIN_PAGE_SHIFT 12U +#define ptes_per_page(page_size) ((page_size) / 8) + +#endif + +#define MIN_PAGE_SIZE (1U << MIN_PAGE_SHIFT) +#define PTES_PER_MIN_PAGE ptes_per_page(MIN_PAGE_SIZE) + +struct vm_guest_mode_params { + unsigned int pa_bits; + unsigned int va_bits; + unsigned int page_size; + unsigned int page_shift; +}; +extern const struct vm_guest_mode_params vm_guest_mode_params[]; + +int open_path_or_exit(const char *path, int flags); +int open_kvm_dev_path_or_exit(void); +int kvm_check_cap(long cap); +int vm_check_cap(struct kvm_vm *vm, long cap); +int vm_enable_cap(struct kvm_vm *vm, struct kvm_enable_cap *cap); +int vcpu_enable_cap(struct kvm_vm *vm, uint32_t vcpu_id, + struct kvm_enable_cap *cap); +void vm_enable_dirty_ring(struct kvm_vm *vm, uint32_t ring_size); +const char *vm_guest_mode_string(uint32_t i); + +struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm); +void kvm_vm_free(struct kvm_vm *vmp); +void kvm_vm_restart(struct kvm_vm *vmp, int perm); +void kvm_vm_release(struct kvm_vm *vmp); +void kvm_vm_get_dirty_log(struct kvm_vm *vm, int slot, void *log); +void kvm_vm_clear_dirty_log(struct kvm_vm *vm, int slot, void *log, + uint64_t first_page, uint32_t num_pages); +uint32_t kvm_vm_reset_dirty_ring(struct kvm_vm *vm); + +int kvm_memcmp_hva_gva(void *hva, struct kvm_vm *vm, const vm_vaddr_t gva, + size_t len); + +void kvm_vm_elf_load(struct kvm_vm *vm, const char *filename); +int kvm_memfd_alloc(size_t size, bool hugepages); + +void vm_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent); + +/* + * VM VCPU Dump + * + * Input Args: + * stream - Output FILE stream + * vm - Virtual Machine + * vcpuid - VCPU ID + * indent - Left margin indent amount + * + * Output Args: None + * + * Return: None + * + * Dumps the current state of the VCPU specified by @vcpuid, within the VM + * given by @vm, to the FILE stream given by @stream. + */ +void vcpu_dump(FILE *stream, struct kvm_vm *vm, uint32_t vcpuid, + uint8_t indent); + +void vm_create_irqchip(struct kvm_vm *vm); + +void vm_set_user_memory_region(struct kvm_vm *vm, uint32_t slot, uint32_t flags, + uint64_t gpa, uint64_t size, void *hva); +int __vm_set_user_memory_region(struct kvm_vm *vm, uint32_t slot, uint32_t flags, + uint64_t gpa, uint64_t size, void *hva); +void vm_userspace_mem_region_add(struct kvm_vm *vm, + enum vm_mem_backing_src_type src_type, + uint64_t guest_paddr, uint32_t slot, uint64_t npages, + uint32_t flags); + +void vcpu_ioctl(struct kvm_vm *vm, uint32_t vcpuid, unsigned long ioctl, + void *arg); +int _vcpu_ioctl(struct kvm_vm *vm, uint32_t vcpuid, unsigned long ioctl, + void *arg); +void vm_ioctl(struct kvm_vm *vm, unsigned long ioctl, void *arg); +int _vm_ioctl(struct kvm_vm *vm, unsigned long cmd, void *arg); +void kvm_ioctl(struct kvm_vm *vm, unsigned long ioctl, void *arg); +int _kvm_ioctl(struct kvm_vm *vm, unsigned long ioctl, void *arg); +void vm_mem_region_set_flags(struct kvm_vm *vm, uint32_t slot, uint32_t flags); +void vm_mem_region_move(struct kvm_vm *vm, uint32_t slot, uint64_t new_gpa); +void vm_mem_region_delete(struct kvm_vm *vm, uint32_t slot); +void vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpuid); +vm_vaddr_t vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min); +vm_vaddr_t vm_vaddr_alloc_pages(struct kvm_vm *vm, int nr_pages); +vm_vaddr_t vm_vaddr_alloc_page(struct kvm_vm *vm); + +void virt_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, + unsigned int npages); +void *addr_gpa2hva(struct kvm_vm *vm, vm_paddr_t gpa); +void *addr_gva2hva(struct kvm_vm *vm, vm_vaddr_t gva); +vm_paddr_t addr_hva2gpa(struct kvm_vm *vm, void *hva); +void *addr_gpa2alias(struct kvm_vm *vm, vm_paddr_t gpa); + +/* + * Address Guest Virtual to Guest Physical + * + * Input Args: + * vm - Virtual Machine + * gva - VM virtual address + * + * Output Args: None + * + * Return: + * Equivalent VM physical address + * + * Returns the VM physical address of the translated VM virtual + * address given by @gva. + */ +vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva); + +struct kvm_run *vcpu_state(struct kvm_vm *vm, uint32_t vcpuid); +void vcpu_run(struct kvm_vm *vm, uint32_t vcpuid); +int _vcpu_run(struct kvm_vm *vm, uint32_t vcpuid); +int vcpu_get_fd(struct kvm_vm *vm, uint32_t vcpuid); +void vcpu_run_complete_io(struct kvm_vm *vm, uint32_t vcpuid); +void vcpu_set_guest_debug(struct kvm_vm *vm, uint32_t vcpuid, + struct kvm_guest_debug *debug); +void vcpu_set_mp_state(struct kvm_vm *vm, uint32_t vcpuid, + struct kvm_mp_state *mp_state); +struct kvm_reg_list *vcpu_get_reg_list(struct kvm_vm *vm, uint32_t vcpuid); +void vcpu_regs_get(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_regs *regs); +void vcpu_regs_set(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_regs *regs); + +/* + * VM VCPU Args Set + * + * Input Args: + * vm - Virtual Machine + * vcpuid - VCPU ID + * num - number of arguments + * ... - arguments, each of type uint64_t + * + * Output Args: None + * + * Return: None + * + * Sets the first @num function input registers of the VCPU with @vcpuid, + * per the C calling convention of the architecture, to the values given + * as variable args. Each of the variable args is expected to be of type + * uint64_t. The maximum @num can be is specific to the architecture. + */ +void vcpu_args_set(struct kvm_vm *vm, uint32_t vcpuid, unsigned int num, ...); + +void vcpu_sregs_get(struct kvm_vm *vm, uint32_t vcpuid, + struct kvm_sregs *sregs); +void vcpu_sregs_set(struct kvm_vm *vm, uint32_t vcpuid, + struct kvm_sregs *sregs); +int _vcpu_sregs_set(struct kvm_vm *vm, uint32_t vcpuid, + struct kvm_sregs *sregs); +void vcpu_fpu_get(struct kvm_vm *vm, uint32_t vcpuid, + struct kvm_fpu *fpu); +void vcpu_fpu_set(struct kvm_vm *vm, uint32_t vcpuid, + struct kvm_fpu *fpu); +void vcpu_get_reg(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_one_reg *reg); +void vcpu_set_reg(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_one_reg *reg); +#ifdef __KVM_HAVE_VCPU_EVENTS +void vcpu_events_get(struct kvm_vm *vm, uint32_t vcpuid, + struct kvm_vcpu_events *events); +void vcpu_events_set(struct kvm_vm *vm, uint32_t vcpuid, + struct kvm_vcpu_events *events); +#endif +#ifdef __x86_64__ +void vcpu_nested_state_get(struct kvm_vm *vm, uint32_t vcpuid, + struct kvm_nested_state *state); +int vcpu_nested_state_set(struct kvm_vm *vm, uint32_t vcpuid, + struct kvm_nested_state *state, bool ignore_error); +#endif +void *vcpu_map_dirty_ring(struct kvm_vm *vm, uint32_t vcpuid); + +int _kvm_device_check_attr(int dev_fd, uint32_t group, uint64_t attr); +int kvm_device_check_attr(int dev_fd, uint32_t group, uint64_t attr); +int _kvm_create_device(struct kvm_vm *vm, uint64_t type, bool test, int *fd); +int kvm_create_device(struct kvm_vm *vm, uint64_t type, bool test); +int _kvm_device_access(int dev_fd, uint32_t group, uint64_t attr, + void *val, bool write); +int kvm_device_access(int dev_fd, uint32_t group, uint64_t attr, + void *val, bool write); +void kvm_irq_line(struct kvm_vm *vm, uint32_t irq, int level); +int _kvm_irq_line(struct kvm_vm *vm, uint32_t irq, int level); + +int _vcpu_has_device_attr(struct kvm_vm *vm, uint32_t vcpuid, uint32_t group, + uint64_t attr); +int vcpu_has_device_attr(struct kvm_vm *vm, uint32_t vcpuid, uint32_t group, + uint64_t attr); +int _vcpu_access_device_attr(struct kvm_vm *vm, uint32_t vcpuid, uint32_t group, + uint64_t attr, void *val, bool write); +int vcpu_access_device_attr(struct kvm_vm *vm, uint32_t vcpuid, uint32_t group, + uint64_t attr, void *val, bool write); + +#define KVM_MAX_IRQ_ROUTES 4096 + +struct kvm_irq_routing *kvm_gsi_routing_create(void); +void kvm_gsi_routing_irqchip_add(struct kvm_irq_routing *routing, + uint32_t gsi, uint32_t pin); +int _kvm_gsi_routing_write(struct kvm_vm *vm, struct kvm_irq_routing *routing); +void kvm_gsi_routing_write(struct kvm_vm *vm, struct kvm_irq_routing *routing); + +const char *exit_reason_str(unsigned int exit_reason); + +void virt_pgd_alloc(struct kvm_vm *vm); + +/* + * VM Virtual Page Map + * + * Input Args: + * vm - Virtual Machine + * vaddr - VM Virtual Address + * paddr - VM Physical Address + * memslot - Memory region slot for new virtual translation tables + * + * Output Args: None + * + * Return: None + * + * Within @vm, creates a virtual translation for the page starting + * at @vaddr to the page starting at @paddr. + */ +void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr); + +vm_paddr_t vm_phy_page_alloc(struct kvm_vm *vm, vm_paddr_t paddr_min, + uint32_t memslot); +vm_paddr_t vm_phy_pages_alloc(struct kvm_vm *vm, size_t num, + vm_paddr_t paddr_min, uint32_t memslot); +vm_paddr_t vm_alloc_page_table(struct kvm_vm *vm); + +/* + * Create a VM with reasonable defaults + * + * Input Args: + * vcpuid - The id of the single VCPU to add to the VM. + * extra_mem_pages - The number of extra pages to add (this will + * decide how much extra space we will need to + * setup the page tables using memslot 0) + * guest_code - The vCPU's entry point + * + * Output Args: None + * + * Return: + * Pointer to opaque structure that describes the created VM. + */ +struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages, + void *guest_code); + +/* Same as vm_create_default, but can be used for more than one vcpu */ +struct kvm_vm *vm_create_default_with_vcpus(uint32_t nr_vcpus, uint64_t extra_mem_pages, + uint32_t num_percpu_pages, void *guest_code, + uint32_t vcpuids[]); + +/* Like vm_create_default_with_vcpus, but accepts mode and slot0 memory as a parameter */ +struct kvm_vm *vm_create_with_vcpus(enum vm_guest_mode mode, uint32_t nr_vcpus, + uint64_t slot0_mem_pages, uint64_t extra_mem_pages, + uint32_t num_percpu_pages, void *guest_code, + uint32_t vcpuids[]); + +/* Create a default VM without any vcpus. */ +struct kvm_vm *vm_create_without_vcpus(enum vm_guest_mode mode, uint64_t pages); + +/* + * Adds a vCPU with reasonable defaults (e.g. a stack) + * + * Input Args: + * vm - Virtual Machine + * vcpuid - The id of the VCPU to add to the VM. + * guest_code - The vCPU's entry point + */ +void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code); + +bool vm_is_unrestricted_guest(struct kvm_vm *vm); + +unsigned int vm_get_page_size(struct kvm_vm *vm); +unsigned int vm_get_page_shift(struct kvm_vm *vm); +unsigned long vm_compute_max_gfn(struct kvm_vm *vm); +uint64_t vm_get_max_gfn(struct kvm_vm *vm); +int vm_get_fd(struct kvm_vm *vm); + +unsigned int vm_calc_num_guest_pages(enum vm_guest_mode mode, size_t size); +unsigned int vm_num_host_pages(enum vm_guest_mode mode, unsigned int num_guest_pages); +unsigned int vm_num_guest_pages(enum vm_guest_mode mode, unsigned int num_host_pages); +static inline unsigned int +vm_adjust_num_guest_pages(enum vm_guest_mode mode, unsigned int num_guest_pages) +{ + unsigned int n; + n = vm_num_guest_pages(mode, vm_num_host_pages(mode, num_guest_pages)); +#ifdef __s390x__ + /* s390 requires 1M aligned guest sizes */ + n = (n + 255) & ~255; +#endif + return n; +} + +struct kvm_userspace_memory_region * +kvm_userspace_memory_region_find(struct kvm_vm *vm, uint64_t start, + uint64_t end); + +struct kvm_dirty_log * +allocate_kvm_dirty_log(struct kvm_userspace_memory_region *region); + +int vm_create_device(struct kvm_vm *vm, struct kvm_create_device *cd); + +#define sync_global_to_guest(vm, g) ({ \ + typeof(g) *_p = addr_gva2hva(vm, (vm_vaddr_t)&(g)); \ + memcpy(_p, &(g), sizeof(g)); \ +}) + +#define sync_global_from_guest(vm, g) ({ \ + typeof(g) *_p = addr_gva2hva(vm, (vm_vaddr_t)&(g)); \ + memcpy(&(g), _p, sizeof(g)); \ +}) + +void assert_on_unhandled_exception(struct kvm_vm *vm, uint32_t vcpuid); + +int vm_get_stats_fd(struct kvm_vm *vm); +int vcpu_get_stats_fd(struct kvm_vm *vm, uint32_t vcpuid); + +uint32_t guest_get_vcpuid(void); + +#endif /* SELFTEST_KVM_UTIL_BASE_H */ diff --git a/tools/testing/selftests/kvm/include/riscv/processor.h b/tools/testing/selftests/kvm/include/riscv/processor.h new file mode 100644 index 000000000000..dc284c6bdbc3 --- /dev/null +++ b/tools/testing/selftests/kvm/include/riscv/processor.h @@ -0,0 +1,135 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * RISC-V processor specific defines + * + * Copyright (C) 2021 Western Digital Corporation or its affiliates. + */ +#ifndef SELFTEST_KVM_PROCESSOR_H +#define SELFTEST_KVM_PROCESSOR_H + +#include "kvm_util.h" +#include <linux/stringify.h> + +static inline uint64_t __kvm_reg_id(uint64_t type, uint64_t idx, + uint64_t size) +{ + return KVM_REG_RISCV | type | idx | size; +} + +#if __riscv_xlen == 64 +#define KVM_REG_SIZE_ULONG KVM_REG_SIZE_U64 +#else +#define KVM_REG_SIZE_ULONG KVM_REG_SIZE_U32 +#endif + +#define RISCV_CONFIG_REG(name) __kvm_reg_id(KVM_REG_RISCV_CONFIG, \ + KVM_REG_RISCV_CONFIG_REG(name), \ + KVM_REG_SIZE_ULONG) + +#define RISCV_CORE_REG(name) __kvm_reg_id(KVM_REG_RISCV_CORE, \ + KVM_REG_RISCV_CORE_REG(name), \ + KVM_REG_SIZE_ULONG) + +#define RISCV_CSR_REG(name) __kvm_reg_id(KVM_REG_RISCV_CSR, \ + KVM_REG_RISCV_CSR_REG(name), \ + KVM_REG_SIZE_ULONG) + +#define RISCV_TIMER_REG(name) __kvm_reg_id(KVM_REG_RISCV_TIMER, \ + KVM_REG_RISCV_TIMER_REG(name), \ + KVM_REG_SIZE_U64) + +static inline void get_reg(struct kvm_vm *vm, uint32_t vcpuid, uint64_t id, + unsigned long *addr) +{ + struct kvm_one_reg reg; + + reg.id = id; + reg.addr = (unsigned long)addr; + vcpu_get_reg(vm, vcpuid, ®); +} + +static inline void set_reg(struct kvm_vm *vm, uint32_t vcpuid, uint64_t id, + unsigned long val) +{ + struct kvm_one_reg reg; + + reg.id = id; + reg.addr = (unsigned long)&val; + vcpu_set_reg(vm, vcpuid, ®); +} + +/* L3 index Bit[47:39] */ +#define PGTBL_L3_INDEX_MASK 0x0000FF8000000000ULL +#define PGTBL_L3_INDEX_SHIFT 39 +#define PGTBL_L3_BLOCK_SHIFT 39 +#define PGTBL_L3_BLOCK_SIZE 0x0000008000000000ULL +#define PGTBL_L3_MAP_MASK (~(PGTBL_L3_BLOCK_SIZE - 1)) +/* L2 index Bit[38:30] */ +#define PGTBL_L2_INDEX_MASK 0x0000007FC0000000ULL +#define PGTBL_L2_INDEX_SHIFT 30 +#define PGTBL_L2_BLOCK_SHIFT 30 +#define PGTBL_L2_BLOCK_SIZE 0x0000000040000000ULL +#define PGTBL_L2_MAP_MASK (~(PGTBL_L2_BLOCK_SIZE - 1)) +/* L1 index Bit[29:21] */ +#define PGTBL_L1_INDEX_MASK 0x000000003FE00000ULL +#define PGTBL_L1_INDEX_SHIFT 21 +#define PGTBL_L1_BLOCK_SHIFT 21 +#define PGTBL_L1_BLOCK_SIZE 0x0000000000200000ULL +#define PGTBL_L1_MAP_MASK (~(PGTBL_L1_BLOCK_SIZE - 1)) +/* L0 index Bit[20:12] */ +#define PGTBL_L0_INDEX_MASK 0x00000000001FF000ULL +#define PGTBL_L0_INDEX_SHIFT 12 +#define PGTBL_L0_BLOCK_SHIFT 12 +#define PGTBL_L0_BLOCK_SIZE 0x0000000000001000ULL +#define PGTBL_L0_MAP_MASK (~(PGTBL_L0_BLOCK_SIZE - 1)) + +#define PGTBL_PTE_ADDR_MASK 0x003FFFFFFFFFFC00ULL +#define PGTBL_PTE_ADDR_SHIFT 10 +#define PGTBL_PTE_RSW_MASK 0x0000000000000300ULL +#define PGTBL_PTE_RSW_SHIFT 8 +#define PGTBL_PTE_DIRTY_MASK 0x0000000000000080ULL +#define PGTBL_PTE_DIRTY_SHIFT 7 +#define PGTBL_PTE_ACCESSED_MASK 0x0000000000000040ULL +#define PGTBL_PTE_ACCESSED_SHIFT 6 +#define PGTBL_PTE_GLOBAL_MASK 0x0000000000000020ULL +#define PGTBL_PTE_GLOBAL_SHIFT 5 +#define PGTBL_PTE_USER_MASK 0x0000000000000010ULL +#define PGTBL_PTE_USER_SHIFT 4 +#define PGTBL_PTE_EXECUTE_MASK 0x0000000000000008ULL +#define PGTBL_PTE_EXECUTE_SHIFT 3 +#define PGTBL_PTE_WRITE_MASK 0x0000000000000004ULL +#define PGTBL_PTE_WRITE_SHIFT 2 +#define PGTBL_PTE_READ_MASK 0x0000000000000002ULL +#define PGTBL_PTE_READ_SHIFT 1 +#define PGTBL_PTE_PERM_MASK (PGTBL_PTE_EXECUTE_MASK | \ + PGTBL_PTE_WRITE_MASK | \ + PGTBL_PTE_READ_MASK) +#define PGTBL_PTE_VALID_MASK 0x0000000000000001ULL +#define PGTBL_PTE_VALID_SHIFT 0 + +#define PGTBL_PAGE_SIZE PGTBL_L0_BLOCK_SIZE +#define PGTBL_PAGE_SIZE_SHIFT PGTBL_L0_BLOCK_SHIFT + +#define SATP_PPN _AC(0x00000FFFFFFFFFFF, UL) +#define SATP_MODE_39 _AC(0x8000000000000000, UL) +#define SATP_MODE_48 _AC(0x9000000000000000, UL) +#define SATP_ASID_BITS 16 +#define SATP_ASID_SHIFT 44 +#define SATP_ASID_MASK _AC(0xFFFF, UL) + +#define SBI_EXT_EXPERIMENTAL_START 0x08000000 +#define SBI_EXT_EXPERIMENTAL_END 0x08FFFFFF + +#define KVM_RISCV_SELFTESTS_SBI_EXT SBI_EXT_EXPERIMENTAL_END + +struct sbiret { + long error; + long value; +}; + +struct sbiret sbi_ecall(int ext, int fid, unsigned long arg0, + unsigned long arg1, unsigned long arg2, + unsigned long arg3, unsigned long arg4, + unsigned long arg5); + +#endif /* SELFTEST_KVM_PROCESSOR_H */ diff --git a/tools/testing/selftests/kvm/include/s390x/processor.h b/tools/testing/selftests/kvm/include/s390x/processor.h index e0e96a5f608c..255c9b990f4c 100644 --- a/tools/testing/selftests/kvm/include/s390x/processor.h +++ b/tools/testing/selftests/kvm/include/s390x/processor.h @@ -5,6 +5,8 @@ #ifndef SELFTEST_KVM_PROCESSOR_H #define SELFTEST_KVM_PROCESSOR_H +#include <linux/compiler.h> + /* Bits in the region/segment table entry */ #define REGION_ENTRY_ORIGIN ~0xfffUL /* region/segment table origin */ #define REGION_ENTRY_PROTECT 0x200 /* region protection bit */ @@ -19,4 +21,10 @@ #define PAGE_PROTECT 0x200 /* HW read-only bit */ #define PAGE_NOEXEC 0x100 /* HW no-execute bit */ +/* Is there a portable way to do this? */ +static inline void cpu_relax(void) +{ + barrier(); +} + #endif diff --git a/tools/testing/selftests/kvm/include/ucall_common.h b/tools/testing/selftests/kvm/include/ucall_common.h new file mode 100644 index 000000000000..9eecc9d40b79 --- /dev/null +++ b/tools/testing/selftests/kvm/include/ucall_common.h @@ -0,0 +1,59 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * tools/testing/selftests/kvm/include/kvm_util.h + * + * Copyright (C) 2018, Google LLC. + */ +#ifndef SELFTEST_KVM_UCALL_COMMON_H +#define SELFTEST_KVM_UCALL_COMMON_H + +/* Common ucalls */ +enum { + UCALL_NONE, + UCALL_SYNC, + UCALL_ABORT, + UCALL_DONE, + UCALL_UNHANDLED, +}; + +#define UCALL_MAX_ARGS 6 + +struct ucall { + uint64_t cmd; + uint64_t args[UCALL_MAX_ARGS]; +}; + +void ucall_init(struct kvm_vm *vm, void *arg); +void ucall_uninit(struct kvm_vm *vm); +void ucall(uint64_t cmd, int nargs, ...); +uint64_t get_ucall(struct kvm_vm *vm, uint32_t vcpu_id, struct ucall *uc); + +#define GUEST_SYNC_ARGS(stage, arg1, arg2, arg3, arg4) \ + ucall(UCALL_SYNC, 6, "hello", stage, arg1, arg2, arg3, arg4) +#define GUEST_SYNC(stage) ucall(UCALL_SYNC, 2, "hello", stage) +#define GUEST_DONE() ucall(UCALL_DONE, 0) +#define __GUEST_ASSERT(_condition, _condstr, _nargs, _args...) do { \ + if (!(_condition)) \ + ucall(UCALL_ABORT, 2 + _nargs, \ + "Failed guest assert: " \ + _condstr, __LINE__, _args); \ +} while (0) + +#define GUEST_ASSERT(_condition) \ + __GUEST_ASSERT(_condition, #_condition, 0, 0) + +#define GUEST_ASSERT_1(_condition, arg1) \ + __GUEST_ASSERT(_condition, #_condition, 1, (arg1)) + +#define GUEST_ASSERT_2(_condition, arg1, arg2) \ + __GUEST_ASSERT(_condition, #_condition, 2, (arg1), (arg2)) + +#define GUEST_ASSERT_3(_condition, arg1, arg2, arg3) \ + __GUEST_ASSERT(_condition, #_condition, 3, (arg1), (arg2), (arg3)) + +#define GUEST_ASSERT_4(_condition, arg1, arg2, arg3, arg4) \ + __GUEST_ASSERT(_condition, #_condition, 4, (arg1), (arg2), (arg3), (arg4)) + +#define GUEST_ASSERT_EQ(a, b) __GUEST_ASSERT((a) == (b), #a " == " #b, 2, a, b) + +#endif /* SELFTEST_KVM_UCALL_COMMON_H */ diff --git a/tools/testing/selftests/kvm/include/x86_64/apic.h b/tools/testing/selftests/kvm/include/x86_64/apic.h index 0be4757f1f20..ac88557dcc9a 100644 --- a/tools/testing/selftests/kvm/include/x86_64/apic.h +++ b/tools/testing/selftests/kvm/include/x86_64/apic.h @@ -33,6 +33,7 @@ #define APIC_SPIV 0xF0 #define APIC_SPIV_FOCUS_DISABLED (1 << 9) #define APIC_SPIV_APIC_ENABLED (1 << 8) +#define APIC_IRR 0x200 #define APIC_ICR 0x300 #define APIC_DEST_SELF 0x40000 #define APIC_DEST_ALLINC 0x80000 diff --git a/tools/testing/selftests/kvm/include/x86_64/evmcs.h b/tools/testing/selftests/kvm/include/x86_64/evmcs.h index c9af97abd622..cc5d14a45702 100644 --- a/tools/testing/selftests/kvm/include/x86_64/evmcs.h +++ b/tools/testing/selftests/kvm/include/x86_64/evmcs.h @@ -213,6 +213,25 @@ struct hv_enlightened_vmcs { u64 padding64_6[7]; }; +#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE 0 +#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_IO_BITMAP BIT(0) +#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP BIT(1) +#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2 BIT(2) +#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP1 BIT(3) +#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_PROC BIT(4) +#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EVENT BIT(5) +#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_ENTRY BIT(6) +#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EXCPN BIT(7) +#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR BIT(8) +#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_XLAT BIT(9) +#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC BIT(10) +#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1 BIT(11) +#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2 BIT(12) +#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER BIT(13) +#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1 BIT(14) +#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_ENLIGHTENMENTSCONTROL BIT(15) +#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL 0xFFFF + #define HV_X64_MSR_VP_ASSIST_PAGE 0x40000073 #define HV_X64_MSR_VP_ASSIST_PAGE_ENABLE 0x00000001 #define HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_SHIFT 12 @@ -648,381 +667,507 @@ static inline int evmcs_vmwrite(uint64_t encoding, uint64_t value) switch (encoding) { case GUEST_RIP: current_evmcs->guest_rip = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE; break; case GUEST_RSP: current_evmcs->guest_rsp = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC; break; case GUEST_RFLAGS: current_evmcs->guest_rflags = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC; break; case HOST_IA32_PAT: current_evmcs->host_ia32_pat = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1; break; case HOST_IA32_EFER: current_evmcs->host_ia32_efer = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1; break; case HOST_CR0: current_evmcs->host_cr0 = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1; break; case HOST_CR3: current_evmcs->host_cr3 = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1; break; case HOST_CR4: current_evmcs->host_cr4 = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1; break; case HOST_IA32_SYSENTER_ESP: current_evmcs->host_ia32_sysenter_esp = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1; break; case HOST_IA32_SYSENTER_EIP: current_evmcs->host_ia32_sysenter_eip = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1; break; case HOST_RIP: current_evmcs->host_rip = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1; break; case IO_BITMAP_A: current_evmcs->io_bitmap_a = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_IO_BITMAP; break; case IO_BITMAP_B: current_evmcs->io_bitmap_b = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_IO_BITMAP; break; case MSR_BITMAP: current_evmcs->msr_bitmap = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP; break; case GUEST_ES_BASE: current_evmcs->guest_es_base = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2; break; case GUEST_CS_BASE: current_evmcs->guest_cs_base = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2; break; case GUEST_SS_BASE: current_evmcs->guest_ss_base = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2; break; case GUEST_DS_BASE: current_evmcs->guest_ds_base = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2; break; case GUEST_FS_BASE: current_evmcs->guest_fs_base = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2; break; case GUEST_GS_BASE: current_evmcs->guest_gs_base = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2; break; case GUEST_LDTR_BASE: current_evmcs->guest_ldtr_base = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2; break; case GUEST_TR_BASE: current_evmcs->guest_tr_base = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2; break; case GUEST_GDTR_BASE: current_evmcs->guest_gdtr_base = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2; break; case GUEST_IDTR_BASE: current_evmcs->guest_idtr_base = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2; break; case TSC_OFFSET: current_evmcs->tsc_offset = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2; break; case VIRTUAL_APIC_PAGE_ADDR: current_evmcs->virtual_apic_page_addr = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2; break; case VMCS_LINK_POINTER: current_evmcs->vmcs_link_pointer = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1; break; case GUEST_IA32_DEBUGCTL: current_evmcs->guest_ia32_debugctl = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1; break; case GUEST_IA32_PAT: current_evmcs->guest_ia32_pat = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1; break; case GUEST_IA32_EFER: current_evmcs->guest_ia32_efer = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1; break; case GUEST_PDPTR0: current_evmcs->guest_pdptr0 = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1; break; case GUEST_PDPTR1: current_evmcs->guest_pdptr1 = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1; break; case GUEST_PDPTR2: current_evmcs->guest_pdptr2 = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1; break; case GUEST_PDPTR3: current_evmcs->guest_pdptr3 = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1; break; case GUEST_PENDING_DBG_EXCEPTIONS: current_evmcs->guest_pending_dbg_exceptions = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1; break; case GUEST_SYSENTER_ESP: current_evmcs->guest_sysenter_esp = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1; break; case GUEST_SYSENTER_EIP: current_evmcs->guest_sysenter_eip = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1; break; case CR0_GUEST_HOST_MASK: current_evmcs->cr0_guest_host_mask = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR; break; case CR4_GUEST_HOST_MASK: current_evmcs->cr4_guest_host_mask = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR; break; case CR0_READ_SHADOW: current_evmcs->cr0_read_shadow = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR; break; case CR4_READ_SHADOW: current_evmcs->cr4_read_shadow = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR; break; case GUEST_CR0: current_evmcs->guest_cr0 = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR; break; case GUEST_CR3: current_evmcs->guest_cr3 = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR; break; case GUEST_CR4: current_evmcs->guest_cr4 = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR; break; case GUEST_DR7: current_evmcs->guest_dr7 = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR; break; case HOST_FS_BASE: current_evmcs->host_fs_base = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER; break; case HOST_GS_BASE: current_evmcs->host_gs_base = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER; break; case HOST_TR_BASE: current_evmcs->host_tr_base = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER; break; case HOST_GDTR_BASE: current_evmcs->host_gdtr_base = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER; break; case HOST_IDTR_BASE: current_evmcs->host_idtr_base = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER; break; case HOST_RSP: current_evmcs->host_rsp = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER; break; case EPT_POINTER: current_evmcs->ept_pointer = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_XLAT; break; case GUEST_BNDCFGS: current_evmcs->guest_bndcfgs = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1; break; case XSS_EXIT_BITMAP: current_evmcs->xss_exit_bitmap = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2; break; case GUEST_PHYSICAL_ADDRESS: current_evmcs->guest_physical_address = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE; break; case EXIT_QUALIFICATION: current_evmcs->exit_qualification = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE; break; case GUEST_LINEAR_ADDRESS: current_evmcs->guest_linear_address = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE; break; case VM_EXIT_MSR_STORE_ADDR: current_evmcs->vm_exit_msr_store_addr = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL; break; case VM_EXIT_MSR_LOAD_ADDR: current_evmcs->vm_exit_msr_load_addr = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL; break; case VM_ENTRY_MSR_LOAD_ADDR: current_evmcs->vm_entry_msr_load_addr = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL; break; case CR3_TARGET_VALUE0: current_evmcs->cr3_target_value0 = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL; break; case CR3_TARGET_VALUE1: current_evmcs->cr3_target_value1 = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL; break; case CR3_TARGET_VALUE2: current_evmcs->cr3_target_value2 = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL; break; case CR3_TARGET_VALUE3: current_evmcs->cr3_target_value3 = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL; break; case TPR_THRESHOLD: current_evmcs->tpr_threshold = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE; break; case GUEST_INTERRUPTIBILITY_INFO: current_evmcs->guest_interruptibility_info = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC; break; case CPU_BASED_VM_EXEC_CONTROL: current_evmcs->cpu_based_vm_exec_control = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_PROC; break; case EXCEPTION_BITMAP: current_evmcs->exception_bitmap = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EXCPN; break; case VM_ENTRY_CONTROLS: current_evmcs->vm_entry_controls = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_ENTRY; break; case VM_ENTRY_INTR_INFO_FIELD: current_evmcs->vm_entry_intr_info_field = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EVENT; break; case VM_ENTRY_EXCEPTION_ERROR_CODE: current_evmcs->vm_entry_exception_error_code = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EVENT; break; case VM_ENTRY_INSTRUCTION_LEN: current_evmcs->vm_entry_instruction_len = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EVENT; break; case HOST_IA32_SYSENTER_CS: current_evmcs->host_ia32_sysenter_cs = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1; break; case PIN_BASED_VM_EXEC_CONTROL: current_evmcs->pin_based_vm_exec_control = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP1; break; case VM_EXIT_CONTROLS: current_evmcs->vm_exit_controls = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP1; break; case SECONDARY_VM_EXEC_CONTROL: current_evmcs->secondary_vm_exec_control = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP1; break; case GUEST_ES_LIMIT: current_evmcs->guest_es_limit = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2; break; case GUEST_CS_LIMIT: current_evmcs->guest_cs_limit = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2; break; case GUEST_SS_LIMIT: current_evmcs->guest_ss_limit = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2; break; case GUEST_DS_LIMIT: current_evmcs->guest_ds_limit = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2; break; case GUEST_FS_LIMIT: current_evmcs->guest_fs_limit = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2; break; case GUEST_GS_LIMIT: current_evmcs->guest_gs_limit = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2; break; case GUEST_LDTR_LIMIT: current_evmcs->guest_ldtr_limit = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2; break; case GUEST_TR_LIMIT: current_evmcs->guest_tr_limit = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2; break; case GUEST_GDTR_LIMIT: current_evmcs->guest_gdtr_limit = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2; break; case GUEST_IDTR_LIMIT: current_evmcs->guest_idtr_limit = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2; break; case GUEST_ES_AR_BYTES: current_evmcs->guest_es_ar_bytes = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2; break; case GUEST_CS_AR_BYTES: current_evmcs->guest_cs_ar_bytes = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2; break; case GUEST_SS_AR_BYTES: current_evmcs->guest_ss_ar_bytes = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2; break; case GUEST_DS_AR_BYTES: current_evmcs->guest_ds_ar_bytes = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2; break; case GUEST_FS_AR_BYTES: current_evmcs->guest_fs_ar_bytes = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2; break; case GUEST_GS_AR_BYTES: current_evmcs->guest_gs_ar_bytes = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2; break; case GUEST_LDTR_AR_BYTES: current_evmcs->guest_ldtr_ar_bytes = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2; break; case GUEST_TR_AR_BYTES: current_evmcs->guest_tr_ar_bytes = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2; break; case GUEST_ACTIVITY_STATE: current_evmcs->guest_activity_state = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1; break; case GUEST_SYSENTER_CS: current_evmcs->guest_sysenter_cs = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1; break; case VM_INSTRUCTION_ERROR: current_evmcs->vm_instruction_error = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE; break; case VM_EXIT_REASON: current_evmcs->vm_exit_reason = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE; break; case VM_EXIT_INTR_INFO: current_evmcs->vm_exit_intr_info = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE; break; case VM_EXIT_INTR_ERROR_CODE: current_evmcs->vm_exit_intr_error_code = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE; break; case IDT_VECTORING_INFO_FIELD: current_evmcs->idt_vectoring_info_field = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE; break; case IDT_VECTORING_ERROR_CODE: current_evmcs->idt_vectoring_error_code = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE; break; case VM_EXIT_INSTRUCTION_LEN: current_evmcs->vm_exit_instruction_len = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE; break; case VMX_INSTRUCTION_INFO: current_evmcs->vmx_instruction_info = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE; break; case PAGE_FAULT_ERROR_CODE_MASK: current_evmcs->page_fault_error_code_mask = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL; break; case PAGE_FAULT_ERROR_CODE_MATCH: current_evmcs->page_fault_error_code_match = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL; break; case CR3_TARGET_COUNT: current_evmcs->cr3_target_count = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL; break; case VM_EXIT_MSR_STORE_COUNT: current_evmcs->vm_exit_msr_store_count = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL; break; case VM_EXIT_MSR_LOAD_COUNT: current_evmcs->vm_exit_msr_load_count = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL; break; case VM_ENTRY_MSR_LOAD_COUNT: current_evmcs->vm_entry_msr_load_count = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL; break; case HOST_ES_SELECTOR: current_evmcs->host_es_selector = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1; break; case HOST_CS_SELECTOR: current_evmcs->host_cs_selector = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1; break; case HOST_SS_SELECTOR: current_evmcs->host_ss_selector = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1; break; case HOST_DS_SELECTOR: current_evmcs->host_ds_selector = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1; break; case HOST_FS_SELECTOR: current_evmcs->host_fs_selector = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1; break; case HOST_GS_SELECTOR: current_evmcs->host_gs_selector = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1; break; case HOST_TR_SELECTOR: current_evmcs->host_tr_selector = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1; break; case GUEST_ES_SELECTOR: current_evmcs->guest_es_selector = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2; break; case GUEST_CS_SELECTOR: current_evmcs->guest_cs_selector = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2; break; case GUEST_SS_SELECTOR: current_evmcs->guest_ss_selector = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2; break; case GUEST_DS_SELECTOR: current_evmcs->guest_ds_selector = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2; break; case GUEST_FS_SELECTOR: current_evmcs->guest_fs_selector = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2; break; case GUEST_GS_SELECTOR: current_evmcs->guest_gs_selector = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2; break; case GUEST_LDTR_SELECTOR: current_evmcs->guest_ldtr_selector = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2; break; case GUEST_TR_SELECTOR: current_evmcs->guest_tr_selector = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2; break; case VIRTUAL_PROCESSOR_ID: current_evmcs->virtual_processor_id = value; + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_XLAT; break; default: return 1; } @@ -1070,7 +1215,10 @@ static inline int evmcs_vmresume(void) { int ret; - current_evmcs->hv_clean_fields = 0; + /* HOST_RIP */ + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1; + /* HOST_RSP */ + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER; __asm__ __volatile__("push %%rbp;" "push %%rcx;" diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h index 05e65ca1c30c..37db341d4cc5 100644 --- a/tools/testing/selftests/kvm/include/x86_64/processor.h +++ b/tools/testing/selftests/kvm/include/x86_64/processor.h @@ -10,8 +10,10 @@ #include <assert.h> #include <stdint.h> +#include <syscall.h> #include <asm/msr-index.h> +#include <asm/prctl.h> #include "../kvm_util.h" @@ -92,6 +94,21 @@ struct desc_ptr { uint64_t address; } __attribute__((packed)); +struct kvm_x86_state { + struct kvm_xsave *xsave; + struct kvm_vcpu_events events; + struct kvm_mp_state mp_state; + struct kvm_regs regs; + struct kvm_xcrs xcrs; + struct kvm_sregs sregs; + struct kvm_debugregs debugregs; + union { + struct kvm_nested_state nested; + char nested_[16384]; + }; + struct kvm_msrs msrs; +}; + static inline uint64_t get_desc64_base(const struct desc64 *desc) { return ((uint64_t)desc->base3 << 32) | @@ -346,18 +363,43 @@ static inline unsigned long get_xmm(int n) return 0; } +static inline void cpu_relax(void) +{ + asm volatile("rep; nop" ::: "memory"); +} + bool is_intel_cpu(void); +bool is_amd_cpu(void); + +static inline unsigned int x86_family(unsigned int eax) +{ + unsigned int x86; + + x86 = (eax >> 8) & 0xf; + + if (x86 == 0xf) + x86 += (eax >> 20) & 0xff; + + return x86; +} + +static inline unsigned int x86_model(unsigned int eax) +{ + return ((eax >> 12) & 0xf0) | ((eax >> 4) & 0x0f); +} -struct kvm_x86_state; struct kvm_x86_state *vcpu_save_state(struct kvm_vm *vm, uint32_t vcpuid); void vcpu_load_state(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_x86_state *state); +void kvm_x86_state_cleanup(struct kvm_x86_state *state); struct kvm_msr_list *kvm_get_msr_index_list(void); uint64_t kvm_get_feature_msr(uint64_t msr_index); struct kvm_cpuid2 *kvm_get_supported_cpuid(void); struct kvm_cpuid2 *vcpu_get_cpuid(struct kvm_vm *vm, uint32_t vcpuid); +int __vcpu_set_cpuid(struct kvm_vm *vm, uint32_t vcpuid, + struct kvm_cpuid2 *cpuid); void vcpu_set_cpuid(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_cpuid2 *cpuid); @@ -402,6 +444,11 @@ void vm_set_page_table_entry(struct kvm_vm *vm, int vcpuid, uint64_t vaddr, uint64_t pte); /* + * get_cpuid() - find matching CPUID entry and return pointer to it. + */ +struct kvm_cpuid_entry2 *get_cpuid(struct kvm_cpuid2 *cpuid, uint32_t function, + uint32_t index); +/* * set_cpuid() - overwrites a matching cpuid entry with the provided value. * matches based on ent->function && ent->index. returns true * if a match was found and successfully overwritten. @@ -416,6 +463,7 @@ uint64_t kvm_hypercall(uint64_t nr, uint64_t a0, uint64_t a1, uint64_t a2, struct kvm_cpuid2 *kvm_get_supported_hv_cpuid(void); void vcpu_set_hv_cpuid(struct kvm_vm *vm, uint32_t vcpuid); struct kvm_cpuid2 *vcpu_get_supported_hv_cpuid(struct kvm_vm *vm, uint32_t vcpuid); +void vm_xsave_req_perm(int bit); enum x86_page_size { X86_PAGE_SIZE_4K = 0, @@ -443,4 +491,11 @@ void __virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, /* VMX_EPT_VPID_CAP bits */ #define VMX_EPT_VPID_CAP_AD_BITS (1ULL << 21) +#define XSTATE_XTILE_CFG_BIT 17 +#define XSTATE_XTILE_DATA_BIT 18 + +#define XSTATE_XTILE_CFG_MASK (1ULL << XSTATE_XTILE_CFG_BIT) +#define XSTATE_XTILE_DATA_MASK (1ULL << XSTATE_XTILE_DATA_BIT) +#define XFEATURE_XTILE_MASK (XSTATE_XTILE_CFG_MASK | \ + XSTATE_XTILE_DATA_MASK) #endif /* SELFTEST_KVM_PROCESSOR_H */ diff --git a/tools/testing/selftests/kvm/include/x86_64/svm.h b/tools/testing/selftests/kvm/include/x86_64/svm.h index f4ea2355dbc2..2225e5077350 100644 --- a/tools/testing/selftests/kvm/include/x86_64/svm.h +++ b/tools/testing/selftests/kvm/include/x86_64/svm.h @@ -99,7 +99,14 @@ struct __attribute__ ((__packed__)) vmcb_control_area { u8 reserved_6[8]; /* Offset 0xe8 */ u64 avic_logical_id; /* Offset 0xf0 */ u64 avic_physical_id; /* Offset 0xf8 */ - u8 reserved_7[768]; + u8 reserved_7[8]; + u64 vmsa_pa; /* Used for an SEV-ES guest */ + u8 reserved_8[720]; + /* + * Offset 0x3e0, 32 bytes reserved + * for use by hypervisor/software. + */ + u8 reserved_sw[32]; }; diff --git a/tools/testing/selftests/kvm/include/x86_64/svm_util.h b/tools/testing/selftests/kvm/include/x86_64/svm_util.h index 587fbe408b99..a25aabd8f5e7 100644 --- a/tools/testing/selftests/kvm/include/x86_64/svm_util.h +++ b/tools/testing/selftests/kvm/include/x86_64/svm_util.h @@ -16,6 +16,7 @@ #define CPUID_SVM_BIT 2 #define CPUID_SVM BIT_ULL(CPUID_SVM_BIT) +#define SVM_EXIT_MSR 0x07c #define SVM_EXIT_VMMCALL 0x081 struct svm_test_data { @@ -28,6 +29,11 @@ struct svm_test_data { struct vmcb_save_area *save_area; /* gva */ void *save_area_hva; uint64_t save_area_gpa; + + /* MSR-Bitmap */ + void *msr; /* gva */ + void *msr_hva; + uint64_t msr_gpa; }; struct svm_test_data *vcpu_alloc_svm(struct kvm_vm *vm, vm_vaddr_t *p_svm_gva); diff --git a/tools/testing/selftests/kvm/lib/aarch64/gic.c b/tools/testing/selftests/kvm/lib/aarch64/gic.c index fff4fc27504d..55668631d546 100644 --- a/tools/testing/selftests/kvm/lib/aarch64/gic.c +++ b/tools/testing/selftests/kvm/lib/aarch64/gic.c @@ -93,3 +93,69 @@ void gic_set_eoi(unsigned int intid) GUEST_ASSERT(gic_common_ops); gic_common_ops->gic_write_eoir(intid); } + +void gic_set_dir(unsigned int intid) +{ + GUEST_ASSERT(gic_common_ops); + gic_common_ops->gic_write_dir(intid); +} + +void gic_set_eoi_split(bool split) +{ + GUEST_ASSERT(gic_common_ops); + gic_common_ops->gic_set_eoi_split(split); +} + +void gic_set_priority_mask(uint64_t pmr) +{ + GUEST_ASSERT(gic_common_ops); + gic_common_ops->gic_set_priority_mask(pmr); +} + +void gic_set_priority(unsigned int intid, unsigned int prio) +{ + GUEST_ASSERT(gic_common_ops); + gic_common_ops->gic_set_priority(intid, prio); +} + +void gic_irq_set_active(unsigned int intid) +{ + GUEST_ASSERT(gic_common_ops); + gic_common_ops->gic_irq_set_active(intid); +} + +void gic_irq_clear_active(unsigned int intid) +{ + GUEST_ASSERT(gic_common_ops); + gic_common_ops->gic_irq_clear_active(intid); +} + +bool gic_irq_get_active(unsigned int intid) +{ + GUEST_ASSERT(gic_common_ops); + return gic_common_ops->gic_irq_get_active(intid); +} + +void gic_irq_set_pending(unsigned int intid) +{ + GUEST_ASSERT(gic_common_ops); + gic_common_ops->gic_irq_set_pending(intid); +} + +void gic_irq_clear_pending(unsigned int intid) +{ + GUEST_ASSERT(gic_common_ops); + gic_common_ops->gic_irq_clear_pending(intid); +} + +bool gic_irq_get_pending(unsigned int intid) +{ + GUEST_ASSERT(gic_common_ops); + return gic_common_ops->gic_irq_get_pending(intid); +} + +void gic_irq_set_config(unsigned int intid, bool is_edge) +{ + GUEST_ASSERT(gic_common_ops); + gic_common_ops->gic_irq_set_config(intid, is_edge); +} diff --git a/tools/testing/selftests/kvm/lib/aarch64/gic_private.h b/tools/testing/selftests/kvm/lib/aarch64/gic_private.h index d81d739433dc..75d07313c893 100644 --- a/tools/testing/selftests/kvm/lib/aarch64/gic_private.h +++ b/tools/testing/selftests/kvm/lib/aarch64/gic_private.h @@ -14,6 +14,17 @@ struct gic_common_ops { void (*gic_irq_disable)(unsigned int intid); uint64_t (*gic_read_iar)(void); void (*gic_write_eoir)(uint32_t irq); + void (*gic_write_dir)(uint32_t irq); + void (*gic_set_eoi_split)(bool split); + void (*gic_set_priority_mask)(uint64_t mask); + void (*gic_set_priority)(uint32_t intid, uint32_t prio); + void (*gic_irq_set_active)(uint32_t intid); + void (*gic_irq_clear_active)(uint32_t intid); + bool (*gic_irq_get_active)(uint32_t intid); + void (*gic_irq_set_pending)(uint32_t intid); + void (*gic_irq_clear_pending)(uint32_t intid); + bool (*gic_irq_get_pending)(uint32_t intid); + void (*gic_irq_set_config)(uint32_t intid, bool is_edge); }; extern const struct gic_common_ops gicv3_ops; diff --git a/tools/testing/selftests/kvm/lib/aarch64/gic_v3.c b/tools/testing/selftests/kvm/lib/aarch64/gic_v3.c index 2dbf3339b62e..263bf3ed8fd5 100644 --- a/tools/testing/selftests/kvm/lib/aarch64/gic_v3.c +++ b/tools/testing/selftests/kvm/lib/aarch64/gic_v3.c @@ -19,7 +19,8 @@ struct gicv3_data { unsigned int nr_spis; }; -#define sgi_base_from_redist(redist_base) (redist_base + SZ_64K) +#define sgi_base_from_redist(redist_base) (redist_base + SZ_64K) +#define DIST_BIT (1U << 31) enum gicv3_intid_range { SGI_RANGE, @@ -50,6 +51,14 @@ static void gicv3_gicr_wait_for_rwp(void *redist_base) } } +static void gicv3_wait_for_rwp(uint32_t cpu_or_dist) +{ + if (cpu_or_dist & DIST_BIT) + gicv3_gicd_wait_for_rwp(); + else + gicv3_gicr_wait_for_rwp(gicv3_data.redist_base[cpu_or_dist]); +} + static enum gicv3_intid_range get_intid_range(unsigned int intid) { switch (intid) { @@ -81,39 +90,177 @@ static void gicv3_write_eoir(uint32_t irq) isb(); } -static void -gicv3_config_irq(unsigned int intid, unsigned int offset) +static void gicv3_write_dir(uint32_t irq) +{ + write_sysreg_s(irq, SYS_ICC_DIR_EL1); + isb(); +} + +static void gicv3_set_priority_mask(uint64_t mask) +{ + write_sysreg_s(mask, SYS_ICC_PMR_EL1); +} + +static void gicv3_set_eoi_split(bool split) +{ + uint32_t val; + + /* + * All other fields are read-only, so no need to read CTLR first. In + * fact, the kernel does the same. + */ + val = split ? (1U << 1) : 0; + write_sysreg_s(val, SYS_ICC_CTLR_EL1); + isb(); +} + +uint32_t gicv3_reg_readl(uint32_t cpu_or_dist, uint64_t offset) +{ + void *base = cpu_or_dist & DIST_BIT ? gicv3_data.dist_base + : sgi_base_from_redist(gicv3_data.redist_base[cpu_or_dist]); + return readl(base + offset); +} + +void gicv3_reg_writel(uint32_t cpu_or_dist, uint64_t offset, uint32_t reg_val) +{ + void *base = cpu_or_dist & DIST_BIT ? gicv3_data.dist_base + : sgi_base_from_redist(gicv3_data.redist_base[cpu_or_dist]); + writel(reg_val, base + offset); +} + +uint32_t gicv3_getl_fields(uint32_t cpu_or_dist, uint64_t offset, uint32_t mask) +{ + return gicv3_reg_readl(cpu_or_dist, offset) & mask; +} + +void gicv3_setl_fields(uint32_t cpu_or_dist, uint64_t offset, + uint32_t mask, uint32_t reg_val) +{ + uint32_t tmp = gicv3_reg_readl(cpu_or_dist, offset) & ~mask; + + tmp |= (reg_val & mask); + gicv3_reg_writel(cpu_or_dist, offset, tmp); +} + +/* + * We use a single offset for the distributor and redistributor maps as they + * have the same value in both. The only exceptions are registers that only + * exist in one and not the other, like GICR_WAKER that doesn't exist in the + * distributor map. Such registers are conveniently marked as reserved in the + * map that doesn't implement it; like GICR_WAKER's offset of 0x0014 being + * marked as "Reserved" in the Distributor map. + */ +static void gicv3_access_reg(uint32_t intid, uint64_t offset, + uint32_t reg_bits, uint32_t bits_per_field, + bool write, uint32_t *val) { uint32_t cpu = guest_get_vcpuid(); - uint32_t mask = 1 << (intid % 32); enum gicv3_intid_range intid_range = get_intid_range(intid); - void *reg; - - /* We care about 'cpu' only for SGIs or PPIs */ - if (intid_range == SGI_RANGE || intid_range == PPI_RANGE) { - GUEST_ASSERT(cpu < gicv3_data.nr_cpus); - - reg = sgi_base_from_redist(gicv3_data.redist_base[cpu]) + - offset; - writel(mask, reg); - gicv3_gicr_wait_for_rwp(gicv3_data.redist_base[cpu]); - } else if (intid_range == SPI_RANGE) { - reg = gicv3_data.dist_base + offset + (intid / 32) * 4; - writel(mask, reg); - gicv3_gicd_wait_for_rwp(); - } else { - GUEST_ASSERT(0); - } + uint32_t fields_per_reg, index, mask, shift; + uint32_t cpu_or_dist; + + GUEST_ASSERT(bits_per_field <= reg_bits); + GUEST_ASSERT(!write || *val < (1U << bits_per_field)); + /* + * This function does not support 64 bit accesses. Just asserting here + * until we implement readq/writeq. + */ + GUEST_ASSERT(reg_bits == 32); + + fields_per_reg = reg_bits / bits_per_field; + index = intid % fields_per_reg; + shift = index * bits_per_field; + mask = ((1U << bits_per_field) - 1) << shift; + + /* Set offset to the actual register holding intid's config. */ + offset += (intid / fields_per_reg) * (reg_bits / 8); + + cpu_or_dist = (intid_range == SPI_RANGE) ? DIST_BIT : cpu; + + if (write) + gicv3_setl_fields(cpu_or_dist, offset, mask, *val << shift); + *val = gicv3_getl_fields(cpu_or_dist, offset, mask) >> shift; +} + +static void gicv3_write_reg(uint32_t intid, uint64_t offset, + uint32_t reg_bits, uint32_t bits_per_field, uint32_t val) +{ + gicv3_access_reg(intid, offset, reg_bits, + bits_per_field, true, &val); +} + +static uint32_t gicv3_read_reg(uint32_t intid, uint64_t offset, + uint32_t reg_bits, uint32_t bits_per_field) +{ + uint32_t val; + + gicv3_access_reg(intid, offset, reg_bits, + bits_per_field, false, &val); + return val; +} + +static void gicv3_set_priority(uint32_t intid, uint32_t prio) +{ + gicv3_write_reg(intid, GICD_IPRIORITYR, 32, 8, prio); +} + +/* Sets the intid to be level-sensitive or edge-triggered. */ +static void gicv3_irq_set_config(uint32_t intid, bool is_edge) +{ + uint32_t val; + + /* N/A for private interrupts. */ + GUEST_ASSERT(get_intid_range(intid) == SPI_RANGE); + val = is_edge ? 2 : 0; + gicv3_write_reg(intid, GICD_ICFGR, 32, 2, val); +} + +static void gicv3_irq_enable(uint32_t intid) +{ + bool is_spi = get_intid_range(intid) == SPI_RANGE; + uint32_t cpu = guest_get_vcpuid(); + + gicv3_write_reg(intid, GICD_ISENABLER, 32, 1, 1); + gicv3_wait_for_rwp(is_spi ? DIST_BIT : cpu); +} + +static void gicv3_irq_disable(uint32_t intid) +{ + bool is_spi = get_intid_range(intid) == SPI_RANGE; + uint32_t cpu = guest_get_vcpuid(); + + gicv3_write_reg(intid, GICD_ICENABLER, 32, 1, 1); + gicv3_wait_for_rwp(is_spi ? DIST_BIT : cpu); +} + +static void gicv3_irq_set_active(uint32_t intid) +{ + gicv3_write_reg(intid, GICD_ISACTIVER, 32, 1, 1); +} + +static void gicv3_irq_clear_active(uint32_t intid) +{ + gicv3_write_reg(intid, GICD_ICACTIVER, 32, 1, 1); +} + +static bool gicv3_irq_get_active(uint32_t intid) +{ + return gicv3_read_reg(intid, GICD_ISACTIVER, 32, 1); +} + +static void gicv3_irq_set_pending(uint32_t intid) +{ + gicv3_write_reg(intid, GICD_ISPENDR, 32, 1, 1); } -static void gicv3_irq_enable(unsigned int intid) +static void gicv3_irq_clear_pending(uint32_t intid) { - gicv3_config_irq(intid, GICD_ISENABLER); + gicv3_write_reg(intid, GICD_ICPENDR, 32, 1, 1); } -static void gicv3_irq_disable(unsigned int intid) +static bool gicv3_irq_get_pending(uint32_t intid) { - gicv3_config_irq(intid, GICD_ICENABLER); + return gicv3_read_reg(intid, GICD_ISPENDR, 32, 1); } static void gicv3_enable_redist(void *redist_base) @@ -237,4 +384,15 @@ const struct gic_common_ops gicv3_ops = { .gic_irq_disable = gicv3_irq_disable, .gic_read_iar = gicv3_read_iar, .gic_write_eoir = gicv3_write_eoir, + .gic_write_dir = gicv3_write_dir, + .gic_set_priority_mask = gicv3_set_priority_mask, + .gic_set_eoi_split = gicv3_set_eoi_split, + .gic_set_priority = gicv3_set_priority, + .gic_irq_set_active = gicv3_irq_set_active, + .gic_irq_clear_active = gicv3_irq_clear_active, + .gic_irq_get_active = gicv3_irq_get_active, + .gic_irq_set_pending = gicv3_irq_set_pending, + .gic_irq_clear_pending = gicv3_irq_clear_pending, + .gic_irq_get_pending = gicv3_irq_get_pending, + .gic_irq_set_config = gicv3_irq_set_config, }; diff --git a/tools/testing/selftests/kvm/lib/aarch64/processor.c b/tools/testing/selftests/kvm/lib/aarch64/processor.c index b4eeeafd2a70..9343d82519b4 100644 --- a/tools/testing/selftests/kvm/lib/aarch64/processor.c +++ b/tools/testing/selftests/kvm/lib/aarch64/processor.c @@ -8,6 +8,7 @@ #include <linux/compiler.h> #include <assert.h> +#include "guest_modes.h" #include "kvm_util.h" #include "../kvm_util_internal.h" #include "processor.h" @@ -237,6 +238,7 @@ void aarch64_vcpu_setup(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_vcpu_init get_reg(vm, vcpuid, KVM_ARM64_SYS_REG(SYS_SCTLR_EL1), &sctlr_el1); get_reg(vm, vcpuid, KVM_ARM64_SYS_REG(SYS_TCR_EL1), &tcr_el1); + /* Configure base granule size */ switch (vm->mode) { case VM_MODE_P52V48_4K: TEST_FAIL("AArch64 does not support 4K sized pages " @@ -245,25 +247,47 @@ void aarch64_vcpu_setup(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_vcpu_init TEST_FAIL("AArch64 does not support 4K sized pages " "with ANY-bit physical address ranges"); case VM_MODE_P52V48_64K: + case VM_MODE_P48V48_64K: + case VM_MODE_P40V48_64K: + case VM_MODE_P36V48_64K: tcr_el1 |= 1ul << 14; /* TG0 = 64KB */ - tcr_el1 |= 6ul << 32; /* IPS = 52 bits */ + break; + case VM_MODE_P48V48_16K: + case VM_MODE_P40V48_16K: + case VM_MODE_P36V48_16K: + case VM_MODE_P36V47_16K: + tcr_el1 |= 2ul << 14; /* TG0 = 16KB */ break; case VM_MODE_P48V48_4K: + case VM_MODE_P40V48_4K: + case VM_MODE_P36V48_4K: tcr_el1 |= 0ul << 14; /* TG0 = 4KB */ - tcr_el1 |= 5ul << 32; /* IPS = 48 bits */ break; + default: + TEST_FAIL("Unknown guest mode, mode: 0x%x", vm->mode); + } + + /* Configure output size */ + switch (vm->mode) { + case VM_MODE_P52V48_64K: + tcr_el1 |= 6ul << 32; /* IPS = 52 bits */ + break; + case VM_MODE_P48V48_4K: + case VM_MODE_P48V48_16K: case VM_MODE_P48V48_64K: - tcr_el1 |= 1ul << 14; /* TG0 = 64KB */ tcr_el1 |= 5ul << 32; /* IPS = 48 bits */ break; case VM_MODE_P40V48_4K: - tcr_el1 |= 0ul << 14; /* TG0 = 4KB */ - tcr_el1 |= 2ul << 32; /* IPS = 40 bits */ - break; + case VM_MODE_P40V48_16K: case VM_MODE_P40V48_64K: - tcr_el1 |= 1ul << 14; /* TG0 = 64KB */ tcr_el1 |= 2ul << 32; /* IPS = 40 bits */ break; + case VM_MODE_P36V48_4K: + case VM_MODE_P36V48_16K: + case VM_MODE_P36V48_64K: + case VM_MODE_P36V47_16K: + tcr_el1 |= 1ul << 32; /* IPS = 36 bits */ + break; default: TEST_FAIL("Unknown guest mode, mode: 0x%x", vm->mode); } @@ -432,3 +456,47 @@ uint32_t guest_get_vcpuid(void) { return read_sysreg(tpidr_el1); } + +void aarch64_get_supported_page_sizes(uint32_t ipa, + bool *ps4k, bool *ps16k, bool *ps64k) +{ + struct kvm_vcpu_init preferred_init; + int kvm_fd, vm_fd, vcpu_fd, err; + uint64_t val; + struct kvm_one_reg reg = { + .id = KVM_ARM64_SYS_REG(SYS_ID_AA64MMFR0_EL1), + .addr = (uint64_t)&val, + }; + + kvm_fd = open_kvm_dev_path_or_exit(); + vm_fd = ioctl(kvm_fd, KVM_CREATE_VM, ipa); + TEST_ASSERT(vm_fd >= 0, "Can't create VM"); + + vcpu_fd = ioctl(vm_fd, KVM_CREATE_VCPU, 0); + TEST_ASSERT(vcpu_fd >= 0, "Can't create vcpu"); + + err = ioctl(vm_fd, KVM_ARM_PREFERRED_TARGET, &preferred_init); + TEST_ASSERT(err == 0, "Can't get target"); + err = ioctl(vcpu_fd, KVM_ARM_VCPU_INIT, &preferred_init); + TEST_ASSERT(err == 0, "Can't get init vcpu"); + + err = ioctl(vcpu_fd, KVM_GET_ONE_REG, ®); + TEST_ASSERT(err == 0, "Can't get MMFR0"); + + *ps4k = ((val >> 28) & 0xf) != 0xf; + *ps64k = ((val >> 24) & 0xf) == 0; + *ps16k = ((val >> 20) & 0xf) != 0; + + close(vcpu_fd); + close(vm_fd); + close(kvm_fd); +} + +/* + * arm64 doesn't have a true default mode, so start by computing the + * available IPA space and page sizes early. + */ +void __attribute__((constructor)) init_guest_modes(void) +{ + guest_modes_append_default(); +} diff --git a/tools/testing/selftests/kvm/lib/aarch64/vgic.c b/tools/testing/selftests/kvm/lib/aarch64/vgic.c index b9b271ff520d..5d45046c1b80 100644 --- a/tools/testing/selftests/kvm/lib/aarch64/vgic.c +++ b/tools/testing/selftests/kvm/lib/aarch64/vgic.c @@ -5,11 +5,14 @@ #include <linux/kvm.h> #include <linux/sizes.h> +#include <asm/kvm_para.h> #include <asm/kvm.h> #include "kvm_util.h" #include "../kvm_util_internal.h" #include "vgic.h" +#include "gic.h" +#include "gic_v3.h" /* * vGIC-v3 default host setup @@ -28,7 +31,7 @@ * 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, +int vgic_v3_setup(struct kvm_vm *vm, unsigned int nr_vcpus, uint32_t nr_irqs, uint64_t gicd_base_gpa, uint64_t gicr_base_gpa) { int gic_fd; @@ -49,7 +52,16 @@ int vgic_v3_setup(struct kvm_vm *vm, unsigned int nr_vcpus, nr_vcpus, nr_vcpus_created); /* Distributor setup */ - gic_fd = kvm_create_device(vm, KVM_DEV_TYPE_ARM_VGIC_V3, false); + if (_kvm_create_device(vm, KVM_DEV_TYPE_ARM_VGIC_V3, + false, &gic_fd) != 0) + return -1; + + kvm_device_access(gic_fd, KVM_DEV_ARM_VGIC_GRP_NR_IRQS, + 0, &nr_irqs, true); + + kvm_device_access(gic_fd, KVM_DEV_ARM_VGIC_GRP_CTRL, + KVM_DEV_ARM_VGIC_CTRL_INIT, NULL, true); + kvm_device_access(gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, KVM_VGIC_V3_ADDR_TYPE_DIST, &gicd_base_gpa, true); nr_gic_pages = vm_calc_num_guest_pages(vm->mode, KVM_VGIC_V3_DIST_SIZE); @@ -68,3 +80,95 @@ int vgic_v3_setup(struct kvm_vm *vm, unsigned int nr_vcpus, return gic_fd; } + +/* should only work for level sensitive interrupts */ +int _kvm_irq_set_level_info(int gic_fd, uint32_t intid, int level) +{ + uint64_t attr = 32 * (intid / 32); + uint64_t index = intid % 32; + uint64_t val; + int ret; + + ret = _kvm_device_access(gic_fd, KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO, + attr, &val, false); + if (ret != 0) + return ret; + + val |= 1U << index; + ret = _kvm_device_access(gic_fd, KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO, + attr, &val, true); + return ret; +} + +void kvm_irq_set_level_info(int gic_fd, uint32_t intid, int level) +{ + int ret = _kvm_irq_set_level_info(gic_fd, intid, level); + + TEST_ASSERT(ret == 0, "KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO failed, " + "rc: %i errno: %i", ret, errno); +} + +int _kvm_arm_irq_line(struct kvm_vm *vm, uint32_t intid, int level) +{ + uint32_t irq = intid & KVM_ARM_IRQ_NUM_MASK; + + TEST_ASSERT(!INTID_IS_SGI(intid), "KVM_IRQ_LINE's interface itself " + "doesn't allow injecting SGIs. There's no mask for it."); + + if (INTID_IS_PPI(intid)) + irq |= KVM_ARM_IRQ_TYPE_PPI << KVM_ARM_IRQ_TYPE_SHIFT; + else + irq |= KVM_ARM_IRQ_TYPE_SPI << KVM_ARM_IRQ_TYPE_SHIFT; + + return _kvm_irq_line(vm, irq, level); +} + +void kvm_arm_irq_line(struct kvm_vm *vm, uint32_t intid, int level) +{ + int ret = _kvm_arm_irq_line(vm, intid, level); + + TEST_ASSERT(ret == 0, "KVM_IRQ_LINE failed, rc: %i errno: %i", + ret, errno); +} + +static void vgic_poke_irq(int gic_fd, uint32_t intid, + uint32_t vcpu, uint64_t reg_off) +{ + uint64_t reg = intid / 32; + uint64_t index = intid % 32; + uint64_t attr = reg_off + reg * 4; + uint64_t val; + bool intid_is_private = INTID_IS_SGI(intid) || INTID_IS_PPI(intid); + + uint32_t group = intid_is_private ? KVM_DEV_ARM_VGIC_GRP_REDIST_REGS + : KVM_DEV_ARM_VGIC_GRP_DIST_REGS; + + if (intid_is_private) { + /* TODO: only vcpu 0 implemented for now. */ + assert(vcpu == 0); + attr += SZ_64K; + } + + /* Check that the addr part of the attr is within 32 bits. */ + assert((attr & ~KVM_DEV_ARM_VGIC_OFFSET_MASK) == 0); + + /* + * All calls will succeed, even with invalid intid's, as long as the + * addr part of the attr is within 32 bits (checked above). An invalid + * intid will just make the read/writes point to above the intended + * register space (i.e., ICPENDR after ISPENDR). + */ + kvm_device_access(gic_fd, group, attr, &val, false); + val |= 1ULL << index; + kvm_device_access(gic_fd, group, attr, &val, true); +} + +void kvm_irq_write_ispendr(int gic_fd, uint32_t intid, uint32_t vcpu) +{ + vgic_poke_irq(gic_fd, intid, vcpu, GICD_ISPENDR); +} + +void kvm_irq_write_isactiver(int gic_fd, uint32_t intid, uint32_t vcpu) +{ + vgic_poke_irq(gic_fd, intid, vcpu, GICD_ISACTIVER); +} diff --git a/tools/testing/selftests/kvm/lib/guest_modes.c b/tools/testing/selftests/kvm/lib/guest_modes.c index c330f414ef96..8784013b747c 100644 --- a/tools/testing/selftests/kvm/lib/guest_modes.c +++ b/tools/testing/selftests/kvm/lib/guest_modes.c @@ -4,22 +4,59 @@ */ #include "guest_modes.h" +#ifdef __aarch64__ +#include "processor.h" +enum vm_guest_mode vm_mode_default; +#endif + struct guest_mode guest_modes[NUM_VM_MODES]; void guest_modes_append_default(void) { +#ifndef __aarch64__ guest_mode_append(VM_MODE_DEFAULT, true, true); - -#ifdef __aarch64__ - guest_mode_append(VM_MODE_P40V48_64K, true, true); +#else { unsigned int limit = kvm_check_cap(KVM_CAP_ARM_VM_IPA_SIZE); + bool ps4k, ps16k, ps64k; + int i; + + aarch64_get_supported_page_sizes(limit, &ps4k, &ps16k, &ps64k); + + vm_mode_default = NUM_VM_MODES; + if (limit >= 52) - guest_mode_append(VM_MODE_P52V48_64K, true, true); + guest_mode_append(VM_MODE_P52V48_64K, ps64k, ps64k); if (limit >= 48) { - guest_mode_append(VM_MODE_P48V48_4K, true, true); - guest_mode_append(VM_MODE_P48V48_64K, true, true); + guest_mode_append(VM_MODE_P48V48_4K, ps4k, ps4k); + guest_mode_append(VM_MODE_P48V48_16K, ps16k, ps16k); + guest_mode_append(VM_MODE_P48V48_64K, ps64k, ps64k); + } + if (limit >= 40) { + guest_mode_append(VM_MODE_P40V48_4K, ps4k, ps4k); + guest_mode_append(VM_MODE_P40V48_16K, ps16k, ps16k); + guest_mode_append(VM_MODE_P40V48_64K, ps64k, ps64k); + if (ps4k) + vm_mode_default = VM_MODE_P40V48_4K; } + if (limit >= 36) { + guest_mode_append(VM_MODE_P36V48_4K, ps4k, ps4k); + guest_mode_append(VM_MODE_P36V48_16K, ps16k, ps16k); + guest_mode_append(VM_MODE_P36V48_64K, ps64k, ps64k); + guest_mode_append(VM_MODE_P36V47_16K, ps16k, ps16k); + } + + /* + * Pick the first supported IPA size if the default + * isn't available. + */ + for (i = 0; vm_mode_default == NUM_VM_MODES && i < NUM_VM_MODES; i++) { + if (guest_modes[i].supported && guest_modes[i].enabled) + vm_mode_default = i; + } + + TEST_ASSERT(vm_mode_default != NUM_VM_MODES, + "No supported mode!"); } #endif #ifdef __s390x__ @@ -38,6 +75,16 @@ void guest_modes_append_default(void) guest_mode_append(VM_MODE_P47V64_4K, true, true); } #endif +#ifdef __riscv + { + unsigned int sz = kvm_check_cap(KVM_CAP_VM_GPA_BITS); + + if (sz >= 52) + guest_mode_append(VM_MODE_P52V48_4K, true, true); + if (sz >= 48) + guest_mode_append(VM_MODE_P48V48_4K, true, true); + } +#endif } void for_each_guest_mode(void (*func)(enum vm_guest_mode, void *), void *arg) diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index 53d2b5d04b82..1665a220abcb 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -85,6 +85,33 @@ int kvm_check_cap(long cap) return ret; } +/* VM Check Capability + * + * Input Args: + * vm - Virtual Machine + * cap - Capability + * + * Output Args: None + * + * Return: + * On success, the Value corresponding to the capability (KVM_CAP_*) + * specified by the value of cap. On failure a TEST_ASSERT failure + * is produced. + * + * Looks up and returns the value corresponding to the capability + * (KVM_CAP_*) given by cap. + */ +int vm_check_cap(struct kvm_vm *vm, long cap) +{ + int ret; + + ret = ioctl(vm->fd, KVM_CHECK_EXTENSION, cap); + TEST_ASSERT(ret >= 0, "KVM_CHECK_EXTENSION VM IOCTL failed,\n" + " rc: %i errno: %i", ret, errno); + + return ret; +} + /* VM Enable Capability * * Input Args: @@ -166,12 +193,18 @@ const char *vm_guest_mode_string(uint32_t i) [VM_MODE_P52V48_4K] = "PA-bits:52, VA-bits:48, 4K pages", [VM_MODE_P52V48_64K] = "PA-bits:52, VA-bits:48, 64K pages", [VM_MODE_P48V48_4K] = "PA-bits:48, VA-bits:48, 4K pages", + [VM_MODE_P48V48_16K] = "PA-bits:48, VA-bits:48, 16K pages", [VM_MODE_P48V48_64K] = "PA-bits:48, VA-bits:48, 64K pages", [VM_MODE_P40V48_4K] = "PA-bits:40, VA-bits:48, 4K pages", + [VM_MODE_P40V48_16K] = "PA-bits:40, VA-bits:48, 16K pages", [VM_MODE_P40V48_64K] = "PA-bits:40, VA-bits:48, 64K pages", [VM_MODE_PXXV48_4K] = "PA-bits:ANY, VA-bits:48, 4K pages", [VM_MODE_P47V64_4K] = "PA-bits:47, VA-bits:64, 4K pages", [VM_MODE_P44V64_4K] = "PA-bits:44, VA-bits:64, 4K pages", + [VM_MODE_P36V48_4K] = "PA-bits:36, VA-bits:48, 4K pages", + [VM_MODE_P36V48_16K] = "PA-bits:36, VA-bits:48, 16K pages", + [VM_MODE_P36V48_64K] = "PA-bits:36, VA-bits:48, 64K pages", + [VM_MODE_P36V47_16K] = "PA-bits:36, VA-bits:47, 16K pages", }; _Static_assert(sizeof(strings)/sizeof(char *) == NUM_VM_MODES, "Missing new mode strings?"); @@ -185,12 +218,18 @@ const struct vm_guest_mode_params vm_guest_mode_params[] = { [VM_MODE_P52V48_4K] = { 52, 48, 0x1000, 12 }, [VM_MODE_P52V48_64K] = { 52, 48, 0x10000, 16 }, [VM_MODE_P48V48_4K] = { 48, 48, 0x1000, 12 }, + [VM_MODE_P48V48_16K] = { 48, 48, 0x4000, 14 }, [VM_MODE_P48V48_64K] = { 48, 48, 0x10000, 16 }, [VM_MODE_P40V48_4K] = { 40, 48, 0x1000, 12 }, + [VM_MODE_P40V48_16K] = { 40, 48, 0x4000, 14 }, [VM_MODE_P40V48_64K] = { 40, 48, 0x10000, 16 }, [VM_MODE_PXXV48_4K] = { 0, 0, 0x1000, 12 }, [VM_MODE_P47V64_4K] = { 47, 64, 0x1000, 12 }, [VM_MODE_P44V64_4K] = { 44, 64, 0x1000, 12 }, + [VM_MODE_P36V48_4K] = { 36, 48, 0x1000, 12 }, + [VM_MODE_P36V48_16K] = { 36, 48, 0x4000, 14 }, + [VM_MODE_P36V48_64K] = { 36, 48, 0x10000, 16 }, + [VM_MODE_P36V47_16K] = { 36, 47, 0x4000, 14 }, }; _Static_assert(sizeof(vm_guest_mode_params)/sizeof(struct vm_guest_mode_params) == NUM_VM_MODES, "Missing new mode params?"); @@ -252,9 +291,19 @@ struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm) vm->pgtable_levels = 3; break; case VM_MODE_P40V48_4K: + case VM_MODE_P36V48_4K: vm->pgtable_levels = 4; break; case VM_MODE_P40V48_64K: + case VM_MODE_P36V48_64K: + vm->pgtable_levels = 3; + break; + case VM_MODE_P48V48_16K: + case VM_MODE_P40V48_16K: + case VM_MODE_P36V48_16K: + vm->pgtable_levels = 4; + break; + case VM_MODE_P36V47_16K: vm->pgtable_levels = 3; break; case VM_MODE_PXXV48_4K: @@ -313,6 +362,20 @@ struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm) return vm; } +struct kvm_vm *vm_create_without_vcpus(enum vm_guest_mode mode, uint64_t pages) +{ + struct kvm_vm *vm; + + vm = vm_create(mode, pages, O_RDWR); + + kvm_vm_elf_load(vm, program_invocation_name); + +#ifdef __x86_64__ + vm_create_irqchip(vm); +#endif + return vm; +} + /* * VM Create with customized parameters * @@ -363,13 +426,8 @@ struct kvm_vm *vm_create_with_vcpus(enum vm_guest_mode mode, uint32_t nr_vcpus, nr_vcpus, kvm_check_cap(KVM_CAP_MAX_VCPUS)); pages = vm_adjust_num_guest_pages(mode, pages); - vm = vm_create(mode, pages, O_RDWR); - kvm_vm_elf_load(vm, program_invocation_name); - -#ifdef __x86_64__ - vm_create_irqchip(vm); -#endif + vm = vm_create_without_vcpus(mode, pages); for (i = 0; i < nr_vcpus; ++i) { uint32_t vcpuid = vcpuids ? vcpuids[i] : i; @@ -443,9 +501,11 @@ void kvm_vm_get_dirty_log(struct kvm_vm *vm, int slot, void *log) void kvm_vm_clear_dirty_log(struct kvm_vm *vm, int slot, void *log, uint64_t first_page, uint32_t num_pages) { - struct kvm_clear_dirty_log args = { .dirty_bitmap = log, .slot = slot, - .first_page = first_page, - .num_pages = num_pages }; + struct kvm_clear_dirty_log args = { + .dirty_bitmap = log, .slot = slot, + .first_page = first_page, + .num_pages = num_pages + }; int ret; ret = ioctl(vm->fd, KVM_CLEAR_DIRTY_LOG, &args); @@ -658,6 +718,27 @@ void kvm_vm_free(struct kvm_vm *vmp) free(vmp); } +int kvm_memfd_alloc(size_t size, bool hugepages) +{ + int memfd_flags = MFD_CLOEXEC; + int fd, r; + + if (hugepages) + memfd_flags |= MFD_HUGETLB; + + fd = memfd_create("kvm_selftest", memfd_flags); + TEST_ASSERT(fd != -1, "memfd_create() failed, errno: %i (%s)", + errno, strerror(errno)); + + r = ftruncate(fd, size); + TEST_ASSERT(!r, "ftruncate() failed, errno: %i (%s)", errno, strerror(errno)); + + r = fallocate(fd, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, 0, size); + TEST_ASSERT(!r, "fallocate() failed, errno: %i (%s)", errno, strerror(errno)); + + return fd; +} + /* * Memory Compare, host virtual to guest virtual * @@ -779,6 +860,30 @@ static void vm_userspace_mem_region_hva_insert(struct rb_root *hva_tree, rb_insert_color(®ion->hva_node, hva_tree); } + +int __vm_set_user_memory_region(struct kvm_vm *vm, uint32_t slot, uint32_t flags, + uint64_t gpa, uint64_t size, void *hva) +{ + struct kvm_userspace_memory_region region = { + .slot = slot, + .flags = flags, + .guest_phys_addr = gpa, + .memory_size = size, + .userspace_addr = (uintptr_t)hva, + }; + + return ioctl(vm->fd, KVM_SET_USER_MEMORY_REGION, ®ion); +} + +void vm_set_user_memory_region(struct kvm_vm *vm, uint32_t slot, uint32_t flags, + uint64_t gpa, uint64_t size, void *hva) +{ + int ret = __vm_set_user_memory_region(vm, slot, flags, gpa, size, hva); + + TEST_ASSERT(!ret, "KVM_SET_USER_MEMORY_REGION failed, errno = %d (%s)", + errno, strerror(errno)); +} + /* * VM Userspace Memory Region Add * @@ -886,24 +991,9 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm, region->mmap_size += alignment; region->fd = -1; - if (backing_src_is_shared(src_type)) { - int memfd_flags = MFD_CLOEXEC; - - if (src_type == VM_MEM_SRC_SHARED_HUGETLB) - memfd_flags |= MFD_HUGETLB; - - region->fd = memfd_create("kvm_selftest", memfd_flags); - TEST_ASSERT(region->fd != -1, - "memfd_create failed, errno: %i", errno); - - ret = ftruncate(region->fd, region->mmap_size); - TEST_ASSERT(ret == 0, "ftruncate failed, errno: %i", errno); - - ret = fallocate(region->fd, - FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, 0, - region->mmap_size); - TEST_ASSERT(ret == 0, "fallocate failed, errno: %i", errno); - } + if (backing_src_is_shared(src_type)) + region->fd = kvm_memfd_alloc(region->mmap_size, + src_type == VM_MEM_SRC_SHARED_HUGETLB); region->mmap_start = mmap(NULL, region->mmap_size, PROT_READ | PROT_WRITE, @@ -2087,6 +2177,78 @@ int vcpu_access_device_attr(struct kvm_vm *vm, uint32_t vcpuid, uint32_t group, } /* + * IRQ related functions. + */ + +int _kvm_irq_line(struct kvm_vm *vm, uint32_t irq, int level) +{ + struct kvm_irq_level irq_level = { + .irq = irq, + .level = level, + }; + + return _vm_ioctl(vm, KVM_IRQ_LINE, &irq_level); +} + +void kvm_irq_line(struct kvm_vm *vm, uint32_t irq, int level) +{ + int ret = _kvm_irq_line(vm, irq, level); + + TEST_ASSERT(ret >= 0, "KVM_IRQ_LINE failed, rc: %i errno: %i", ret, errno); +} + +struct kvm_irq_routing *kvm_gsi_routing_create(void) +{ + struct kvm_irq_routing *routing; + size_t size; + + size = sizeof(struct kvm_irq_routing); + /* Allocate space for the max number of entries: this wastes 196 KBs. */ + size += KVM_MAX_IRQ_ROUTES * sizeof(struct kvm_irq_routing_entry); + routing = calloc(1, size); + assert(routing); + + return routing; +} + +void kvm_gsi_routing_irqchip_add(struct kvm_irq_routing *routing, + uint32_t gsi, uint32_t pin) +{ + int i; + + assert(routing); + assert(routing->nr < KVM_MAX_IRQ_ROUTES); + + i = routing->nr; + routing->entries[i].gsi = gsi; + routing->entries[i].type = KVM_IRQ_ROUTING_IRQCHIP; + routing->entries[i].flags = 0; + routing->entries[i].u.irqchip.irqchip = 0; + routing->entries[i].u.irqchip.pin = pin; + routing->nr++; +} + +int _kvm_gsi_routing_write(struct kvm_vm *vm, struct kvm_irq_routing *routing) +{ + int ret; + + assert(routing); + ret = ioctl(vm_get_fd(vm), KVM_SET_GSI_ROUTING, routing); + free(routing); + + return ret; +} + +void kvm_gsi_routing_write(struct kvm_vm *vm, struct kvm_irq_routing *routing) +{ + int ret; + + ret = _kvm_gsi_routing_write(vm, routing); + TEST_ASSERT(ret == 0, "KVM_SET_GSI_ROUTING failed, rc: %i errno: %i", + ret, errno); +} + +/* * VM Dump * * Input Args: diff --git a/tools/testing/selftests/kvm/lib/riscv/processor.c b/tools/testing/selftests/kvm/lib/riscv/processor.c new file mode 100644 index 000000000000..d377f2603d98 --- /dev/null +++ b/tools/testing/selftests/kvm/lib/riscv/processor.c @@ -0,0 +1,362 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * RISC-V code + * + * Copyright (C) 2021 Western Digital Corporation or its affiliates. + */ + +#include <linux/compiler.h> +#include <assert.h> + +#include "kvm_util.h" +#include "../kvm_util_internal.h" +#include "processor.h" + +#define DEFAULT_RISCV_GUEST_STACK_VADDR_MIN 0xac0000 + +static uint64_t page_align(struct kvm_vm *vm, uint64_t v) +{ + return (v + vm->page_size) & ~(vm->page_size - 1); +} + +static uint64_t pte_addr(struct kvm_vm *vm, uint64_t entry) +{ + return ((entry & PGTBL_PTE_ADDR_MASK) >> PGTBL_PTE_ADDR_SHIFT) << + PGTBL_PAGE_SIZE_SHIFT; +} + +static uint64_t ptrs_per_pte(struct kvm_vm *vm) +{ + return PGTBL_PAGE_SIZE / sizeof(uint64_t); +} + +static uint64_t pte_index_mask[] = { + PGTBL_L0_INDEX_MASK, + PGTBL_L1_INDEX_MASK, + PGTBL_L2_INDEX_MASK, + PGTBL_L3_INDEX_MASK, +}; + +static uint32_t pte_index_shift[] = { + PGTBL_L0_INDEX_SHIFT, + PGTBL_L1_INDEX_SHIFT, + PGTBL_L2_INDEX_SHIFT, + PGTBL_L3_INDEX_SHIFT, +}; + +static uint64_t pte_index(struct kvm_vm *vm, vm_vaddr_t gva, int level) +{ + TEST_ASSERT(level > -1, + "Negative page table level (%d) not possible", level); + TEST_ASSERT(level < vm->pgtable_levels, + "Invalid page table level (%d)", level); + + return (gva & pte_index_mask[level]) >> pte_index_shift[level]; +} + +void virt_pgd_alloc(struct kvm_vm *vm) +{ + if (!vm->pgd_created) { + vm_paddr_t paddr = vm_phy_pages_alloc(vm, + page_align(vm, ptrs_per_pte(vm) * 8) / vm->page_size, + KVM_GUEST_PAGE_TABLE_MIN_PADDR, 0); + vm->pgd = paddr; + vm->pgd_created = true; + } +} + +void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr) +{ + uint64_t *ptep, next_ppn; + int level = vm->pgtable_levels - 1; + + TEST_ASSERT((vaddr % vm->page_size) == 0, + "Virtual address not on page boundary,\n" + " vaddr: 0x%lx vm->page_size: 0x%x", vaddr, vm->page_size); + TEST_ASSERT(sparsebit_is_set(vm->vpages_valid, + (vaddr >> vm->page_shift)), + "Invalid virtual address, vaddr: 0x%lx", vaddr); + TEST_ASSERT((paddr % vm->page_size) == 0, + "Physical address not on page boundary,\n" + " paddr: 0x%lx vm->page_size: 0x%x", paddr, vm->page_size); + TEST_ASSERT((paddr >> vm->page_shift) <= vm->max_gfn, + "Physical address beyond maximum supported,\n" + " paddr: 0x%lx vm->max_gfn: 0x%lx vm->page_size: 0x%x", + paddr, vm->max_gfn, vm->page_size); + + ptep = addr_gpa2hva(vm, vm->pgd) + pte_index(vm, vaddr, level) * 8; + if (!*ptep) { + next_ppn = vm_alloc_page_table(vm) >> PGTBL_PAGE_SIZE_SHIFT; + *ptep = (next_ppn << PGTBL_PTE_ADDR_SHIFT) | + PGTBL_PTE_VALID_MASK; + } + level--; + + while (level > -1) { + ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) + + pte_index(vm, vaddr, level) * 8; + if (!*ptep && level > 0) { + next_ppn = vm_alloc_page_table(vm) >> + PGTBL_PAGE_SIZE_SHIFT; + *ptep = (next_ppn << PGTBL_PTE_ADDR_SHIFT) | + PGTBL_PTE_VALID_MASK; + } + level--; + } + + paddr = paddr >> PGTBL_PAGE_SIZE_SHIFT; + *ptep = (paddr << PGTBL_PTE_ADDR_SHIFT) | + PGTBL_PTE_PERM_MASK | PGTBL_PTE_VALID_MASK; +} + +vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva) +{ + uint64_t *ptep; + int level = vm->pgtable_levels - 1; + + if (!vm->pgd_created) + goto unmapped_gva; + + ptep = addr_gpa2hva(vm, vm->pgd) + pte_index(vm, gva, level) * 8; + if (!ptep) + goto unmapped_gva; + level--; + + while (level > -1) { + ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) + + pte_index(vm, gva, level) * 8; + if (!ptep) + goto unmapped_gva; + level--; + } + + return pte_addr(vm, *ptep) + (gva & (vm->page_size - 1)); + +unmapped_gva: + TEST_FAIL("No mapping for vm virtual address gva: 0x%lx level: %d", + gva, level); + exit(1); +} + +static void pte_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent, + uint64_t page, int level) +{ +#ifdef DEBUG + static const char *const type[] = { "pte", "pmd", "pud", "p4d"}; + uint64_t pte, *ptep; + + if (level < 0) + return; + + for (pte = page; pte < page + ptrs_per_pte(vm) * 8; pte += 8) { + ptep = addr_gpa2hva(vm, pte); + if (!*ptep) + continue; + fprintf(stream, "%*s%s: %lx: %lx at %p\n", indent, "", + type[level], pte, *ptep, ptep); + pte_dump(stream, vm, indent + 1, + pte_addr(vm, *ptep), level - 1); + } +#endif +} + +void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) +{ + int level = vm->pgtable_levels - 1; + uint64_t pgd, *ptep; + + if (!vm->pgd_created) + return; + + for (pgd = vm->pgd; pgd < vm->pgd + ptrs_per_pte(vm) * 8; pgd += 8) { + ptep = addr_gpa2hva(vm, pgd); + if (!*ptep) + continue; + fprintf(stream, "%*spgd: %lx: %lx at %p\n", indent, "", + pgd, *ptep, ptep); + pte_dump(stream, vm, indent + 1, + pte_addr(vm, *ptep), level - 1); + } +} + +void riscv_vcpu_mmu_setup(struct kvm_vm *vm, int vcpuid) +{ + unsigned long satp; + + /* + * The RISC-V Sv48 MMU mode supports 56-bit physical address + * for 48-bit virtual address with 4KB last level page size. + */ + switch (vm->mode) { + case VM_MODE_P52V48_4K: + case VM_MODE_P48V48_4K: + case VM_MODE_P40V48_4K: + break; + default: + TEST_FAIL("Unknown guest mode, mode: 0x%x", vm->mode); + } + + satp = (vm->pgd >> PGTBL_PAGE_SIZE_SHIFT) & SATP_PPN; + satp |= SATP_MODE_48; + + set_reg(vm, vcpuid, RISCV_CSR_REG(satp), satp); +} + +void vcpu_dump(FILE *stream, struct kvm_vm *vm, uint32_t vcpuid, uint8_t indent) +{ + struct kvm_riscv_core core; + + get_reg(vm, vcpuid, RISCV_CORE_REG(mode), &core.mode); + get_reg(vm, vcpuid, RISCV_CORE_REG(regs.pc), &core.regs.pc); + get_reg(vm, vcpuid, RISCV_CORE_REG(regs.ra), &core.regs.ra); + get_reg(vm, vcpuid, RISCV_CORE_REG(regs.sp), &core.regs.sp); + get_reg(vm, vcpuid, RISCV_CORE_REG(regs.gp), &core.regs.gp); + get_reg(vm, vcpuid, RISCV_CORE_REG(regs.tp), &core.regs.tp); + get_reg(vm, vcpuid, RISCV_CORE_REG(regs.t0), &core.regs.t0); + get_reg(vm, vcpuid, RISCV_CORE_REG(regs.t1), &core.regs.t1); + get_reg(vm, vcpuid, RISCV_CORE_REG(regs.t2), &core.regs.t2); + get_reg(vm, vcpuid, RISCV_CORE_REG(regs.s0), &core.regs.s0); + get_reg(vm, vcpuid, RISCV_CORE_REG(regs.s1), &core.regs.s1); + get_reg(vm, vcpuid, RISCV_CORE_REG(regs.a0), &core.regs.a0); + get_reg(vm, vcpuid, RISCV_CORE_REG(regs.a1), &core.regs.a1); + get_reg(vm, vcpuid, RISCV_CORE_REG(regs.a2), &core.regs.a2); + get_reg(vm, vcpuid, RISCV_CORE_REG(regs.a3), &core.regs.a3); + get_reg(vm, vcpuid, RISCV_CORE_REG(regs.a4), &core.regs.a4); + get_reg(vm, vcpuid, RISCV_CORE_REG(regs.a5), &core.regs.a5); + get_reg(vm, vcpuid, RISCV_CORE_REG(regs.a6), &core.regs.a6); + get_reg(vm, vcpuid, RISCV_CORE_REG(regs.a7), &core.regs.a7); + get_reg(vm, vcpuid, RISCV_CORE_REG(regs.s2), &core.regs.s2); + get_reg(vm, vcpuid, RISCV_CORE_REG(regs.s3), &core.regs.s3); + get_reg(vm, vcpuid, RISCV_CORE_REG(regs.s4), &core.regs.s4); + get_reg(vm, vcpuid, RISCV_CORE_REG(regs.s5), &core.regs.s5); + get_reg(vm, vcpuid, RISCV_CORE_REG(regs.s6), &core.regs.s6); + get_reg(vm, vcpuid, RISCV_CORE_REG(regs.s7), &core.regs.s7); + get_reg(vm, vcpuid, RISCV_CORE_REG(regs.s8), &core.regs.s8); + get_reg(vm, vcpuid, RISCV_CORE_REG(regs.s9), &core.regs.s9); + get_reg(vm, vcpuid, RISCV_CORE_REG(regs.s10), &core.regs.s10); + get_reg(vm, vcpuid, RISCV_CORE_REG(regs.s11), &core.regs.s11); + get_reg(vm, vcpuid, RISCV_CORE_REG(regs.t3), &core.regs.t3); + get_reg(vm, vcpuid, RISCV_CORE_REG(regs.t4), &core.regs.t4); + get_reg(vm, vcpuid, RISCV_CORE_REG(regs.t5), &core.regs.t5); + get_reg(vm, vcpuid, RISCV_CORE_REG(regs.t6), &core.regs.t6); + + fprintf(stream, + " MODE: 0x%lx\n", core.mode); + fprintf(stream, + " PC: 0x%016lx RA: 0x%016lx SP: 0x%016lx GP: 0x%016lx\n", + core.regs.pc, core.regs.ra, core.regs.sp, core.regs.gp); + fprintf(stream, + " TP: 0x%016lx T0: 0x%016lx T1: 0x%016lx T2: 0x%016lx\n", + core.regs.tp, core.regs.t0, core.regs.t1, core.regs.t2); + fprintf(stream, + " S0: 0x%016lx S1: 0x%016lx A0: 0x%016lx A1: 0x%016lx\n", + core.regs.s0, core.regs.s1, core.regs.a0, core.regs.a1); + fprintf(stream, + " A2: 0x%016lx A3: 0x%016lx A4: 0x%016lx A5: 0x%016lx\n", + core.regs.a2, core.regs.a3, core.regs.a4, core.regs.a5); + fprintf(stream, + " A6: 0x%016lx A7: 0x%016lx S2: 0x%016lx S3: 0x%016lx\n", + core.regs.a6, core.regs.a7, core.regs.s2, core.regs.s3); + fprintf(stream, + " S4: 0x%016lx S5: 0x%016lx S6: 0x%016lx S7: 0x%016lx\n", + core.regs.s4, core.regs.s5, core.regs.s6, core.regs.s7); + fprintf(stream, + " S8: 0x%016lx S9: 0x%016lx S10: 0x%016lx S11: 0x%016lx\n", + core.regs.s8, core.regs.s9, core.regs.s10, core.regs.s11); + fprintf(stream, + " T3: 0x%016lx T4: 0x%016lx T5: 0x%016lx T6: 0x%016lx\n", + core.regs.t3, core.regs.t4, core.regs.t5, core.regs.t6); +} + +static void guest_hang(void) +{ + while (1) + ; +} + +void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code) +{ + int r; + size_t stack_size = vm->page_size == 4096 ? + DEFAULT_STACK_PGS * vm->page_size : + vm->page_size; + unsigned long stack_vaddr = vm_vaddr_alloc(vm, stack_size, + DEFAULT_RISCV_GUEST_STACK_VADDR_MIN); + unsigned long current_gp = 0; + struct kvm_mp_state mps; + + vm_vcpu_add(vm, vcpuid); + riscv_vcpu_mmu_setup(vm, vcpuid); + + /* + * With SBI HSM support in KVM RISC-V, all secondary VCPUs are + * powered-off by default so we ensure that all secondary VCPUs + * are powered-on using KVM_SET_MP_STATE ioctl(). + */ + mps.mp_state = KVM_MP_STATE_RUNNABLE; + r = _vcpu_ioctl(vm, vcpuid, KVM_SET_MP_STATE, &mps); + TEST_ASSERT(!r, "IOCTL KVM_SET_MP_STATE failed (error %d)", r); + + /* Setup global pointer of guest to be same as the host */ + asm volatile ( + "add %0, gp, zero" : "=r" (current_gp) : : "memory"); + set_reg(vm, vcpuid, RISCV_CORE_REG(regs.gp), current_gp); + + /* Setup stack pointer and program counter of guest */ + set_reg(vm, vcpuid, RISCV_CORE_REG(regs.sp), + stack_vaddr + stack_size); + set_reg(vm, vcpuid, RISCV_CORE_REG(regs.pc), + (unsigned long)guest_code); + + /* Setup default exception vector of guest */ + set_reg(vm, vcpuid, RISCV_CSR_REG(stvec), + (unsigned long)guest_hang); +} + +void vcpu_args_set(struct kvm_vm *vm, uint32_t vcpuid, unsigned int num, ...) +{ + va_list ap; + uint64_t id = RISCV_CORE_REG(regs.a0); + int i; + + TEST_ASSERT(num >= 1 && num <= 8, "Unsupported number of args,\n" + " num: %u\n", num); + + va_start(ap, num); + + for (i = 0; i < num; i++) { + switch (i) { + case 0: + id = RISCV_CORE_REG(regs.a0); + break; + case 1: + id = RISCV_CORE_REG(regs.a1); + break; + case 2: + id = RISCV_CORE_REG(regs.a2); + break; + case 3: + id = RISCV_CORE_REG(regs.a3); + break; + case 4: + id = RISCV_CORE_REG(regs.a4); + break; + case 5: + id = RISCV_CORE_REG(regs.a5); + break; + case 6: + id = RISCV_CORE_REG(regs.a6); + break; + case 7: + id = RISCV_CORE_REG(regs.a7); + break; + }; + set_reg(vm, vcpuid, id, va_arg(ap, uint64_t)); + } + + va_end(ap); +} + +void assert_on_unhandled_exception(struct kvm_vm *vm, uint32_t vcpuid) +{ +} diff --git a/tools/testing/selftests/kvm/lib/riscv/ucall.c b/tools/testing/selftests/kvm/lib/riscv/ucall.c new file mode 100644 index 000000000000..9e42d8248fa6 --- /dev/null +++ b/tools/testing/selftests/kvm/lib/riscv/ucall.c @@ -0,0 +1,87 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * ucall support. A ucall is a "hypercall to userspace". + * + * Copyright (C) 2021 Western Digital Corporation or its affiliates. + */ + +#include <linux/kvm.h> + +#include "kvm_util.h" +#include "../kvm_util_internal.h" +#include "processor.h" + +void ucall_init(struct kvm_vm *vm, void *arg) +{ +} + +void ucall_uninit(struct kvm_vm *vm) +{ +} + +struct sbiret sbi_ecall(int ext, int fid, unsigned long arg0, + unsigned long arg1, unsigned long arg2, + unsigned long arg3, unsigned long arg4, + unsigned long arg5) +{ + register uintptr_t a0 asm ("a0") = (uintptr_t)(arg0); + register uintptr_t a1 asm ("a1") = (uintptr_t)(arg1); + register uintptr_t a2 asm ("a2") = (uintptr_t)(arg2); + register uintptr_t a3 asm ("a3") = (uintptr_t)(arg3); + register uintptr_t a4 asm ("a4") = (uintptr_t)(arg4); + register uintptr_t a5 asm ("a5") = (uintptr_t)(arg5); + register uintptr_t a6 asm ("a6") = (uintptr_t)(fid); + register uintptr_t a7 asm ("a7") = (uintptr_t)(ext); + struct sbiret ret; + + asm volatile ( + "ecall" + : "+r" (a0), "+r" (a1) + : "r" (a2), "r" (a3), "r" (a4), "r" (a5), "r" (a6), "r" (a7) + : "memory"); + ret.error = a0; + ret.value = a1; + + return ret; +} + +void ucall(uint64_t cmd, int nargs, ...) +{ + struct ucall uc = { + .cmd = cmd, + }; + va_list va; + int i; + + nargs = nargs <= UCALL_MAX_ARGS ? nargs : UCALL_MAX_ARGS; + + va_start(va, nargs); + for (i = 0; i < nargs; ++i) + uc.args[i] = va_arg(va, uint64_t); + va_end(va); + + sbi_ecall(KVM_RISCV_SELFTESTS_SBI_EXT, 0, (vm_vaddr_t)&uc, + 0, 0, 0, 0, 0); +} + +uint64_t get_ucall(struct kvm_vm *vm, uint32_t vcpu_id, struct ucall *uc) +{ + struct kvm_run *run = vcpu_state(vm, vcpu_id); + struct ucall ucall = {}; + + if (uc) + memset(uc, 0, sizeof(*uc)); + + if (run->exit_reason == KVM_EXIT_RISCV_SBI && + run->riscv_sbi.extension_id == KVM_RISCV_SELFTESTS_SBI_EXT && + run->riscv_sbi.function_id == 0) { + memcpy(&ucall, addr_gva2hva(vm, run->riscv_sbi.args[0]), + sizeof(ucall)); + + vcpu_run_complete_io(vm, vcpu_id); + if (uc) + memcpy(uc, &ucall, sizeof(ucall)); + } + + return ucall.cmd; +} diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c index eef7b34756d5..9f000dfb5594 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/processor.c +++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c @@ -650,6 +650,60 @@ static void vcpu_setup(struct kvm_vm *vm, int vcpuid) vcpu_sregs_set(vm, vcpuid, &sregs); } +#define CPUID_XFD_BIT (1 << 4) +static bool is_xfd_supported(void) +{ + int eax, ebx, ecx, edx; + const int leaf = 0xd, subleaf = 0x1; + + __asm__ __volatile__( + "cpuid" + : /* output */ "=a"(eax), "=b"(ebx), + "=c"(ecx), "=d"(edx) + : /* input */ "0"(leaf), "2"(subleaf)); + + return !!(eax & CPUID_XFD_BIT); +} + +void vm_xsave_req_perm(int bit) +{ + int kvm_fd; + u64 bitmask; + long rc; + struct kvm_device_attr attr = { + .group = 0, + .attr = KVM_X86_XCOMP_GUEST_SUPP, + .addr = (unsigned long) &bitmask + }; + + kvm_fd = open_kvm_dev_path_or_exit(); + rc = ioctl(kvm_fd, KVM_GET_DEVICE_ATTR, &attr); + close(kvm_fd); + if (rc == -1 && (errno == ENXIO || errno == EINVAL)) + exit(KSFT_SKIP); + TEST_ASSERT(rc == 0, "KVM_GET_DEVICE_ATTR(0, KVM_X86_XCOMP_GUEST_SUPP) error: %ld", rc); + if (!(bitmask & (1ULL << bit))) + exit(KSFT_SKIP); + + if (!is_xfd_supported()) + exit(KSFT_SKIP); + + rc = syscall(SYS_arch_prctl, ARCH_REQ_XCOMP_GUEST_PERM, bit); + + /* + * The older kernel version(<5.15) can't support + * ARCH_REQ_XCOMP_GUEST_PERM and directly return. + */ + if (rc) + return; + + rc = syscall(SYS_arch_prctl, ARCH_GET_XCOMP_GUEST_PERM, &bitmask); + TEST_ASSERT(rc == 0, "prctl(ARCH_GET_XCOMP_GUEST_PERM) error: %ld", rc); + TEST_ASSERT(bitmask & (1ULL << bit), + "prctl(ARCH_REQ_XCOMP_GUEST_PERM) failure bitmask=0x%lx", + bitmask); +} + void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code) { struct kvm_mp_state mp_state; @@ -847,6 +901,17 @@ kvm_get_supported_cpuid_index(uint32_t function, uint32_t index) return entry; } + +int __vcpu_set_cpuid(struct kvm_vm *vm, uint32_t vcpuid, + struct kvm_cpuid2 *cpuid) +{ + struct vcpu *vcpu = vcpu_find(vm, vcpuid); + + TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid); + + return ioctl(vcpu->fd, KVM_SET_CPUID2, cpuid); +} + /* * VM VCPU CPUID Set * @@ -864,12 +929,9 @@ kvm_get_supported_cpuid_index(uint32_t function, uint32_t index) void vcpu_set_cpuid(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_cpuid2 *cpuid) { - struct vcpu *vcpu = vcpu_find(vm, vcpuid); int rc; - TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid); - - rc = ioctl(vcpu->fd, KVM_SET_CPUID2, cpuid); + rc = __vcpu_set_cpuid(vm, vcpuid, cpuid); TEST_ASSERT(rc == 0, "KVM_SET_CPUID2 failed, rc: %i errno: %i", rc, errno); @@ -1017,21 +1079,6 @@ void vcpu_dump(FILE *stream, struct kvm_vm *vm, uint32_t vcpuid, uint8_t indent) sregs_dump(stream, &sregs, indent + 4); } -struct kvm_x86_state { - struct kvm_vcpu_events events; - struct kvm_mp_state mp_state; - struct kvm_regs regs; - struct kvm_xsave xsave; - struct kvm_xcrs xcrs; - struct kvm_sregs sregs; - struct kvm_debugregs debugregs; - union { - struct kvm_nested_state nested; - char nested_[16384]; - }; - struct kvm_msrs msrs; -}; - static int kvm_get_num_msrs_fd(int kvm_fd) { struct kvm_msr_list nmsrs; @@ -1069,6 +1116,22 @@ struct kvm_msr_list *kvm_get_msr_index_list(void) return list; } +static int vcpu_save_xsave_state(struct kvm_vm *vm, struct vcpu *vcpu, + struct kvm_x86_state *state) +{ + int size; + + size = vm_check_cap(vm, KVM_CAP_XSAVE2); + if (!size) + size = sizeof(struct kvm_xsave); + + state->xsave = malloc(size); + if (size == sizeof(struct kvm_xsave)) + return ioctl(vcpu->fd, KVM_GET_XSAVE, state->xsave); + else + return ioctl(vcpu->fd, KVM_GET_XSAVE2, state->xsave); +} + struct kvm_x86_state *vcpu_save_state(struct kvm_vm *vm, uint32_t vcpuid) { struct vcpu *vcpu = vcpu_find(vm, vcpuid); @@ -1096,25 +1159,25 @@ struct kvm_x86_state *vcpu_save_state(struct kvm_vm *vm, uint32_t vcpuid) list = malloc(sizeof(*list) + nmsrs * sizeof(list->indices[0])); list->nmsrs = nmsrs; r = ioctl(vm->kvm_fd, KVM_GET_MSR_INDEX_LIST, list); - TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_MSR_INDEX_LIST, r: %i", - r); + TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_MSR_INDEX_LIST, r: %i", + r); state = malloc(sizeof(*state) + nmsrs * sizeof(state->msrs.entries[0])); r = ioctl(vcpu->fd, KVM_GET_VCPU_EVENTS, &state->events); - TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_VCPU_EVENTS, r: %i", - r); + TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_VCPU_EVENTS, r: %i", + r); r = ioctl(vcpu->fd, KVM_GET_MP_STATE, &state->mp_state); - TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_MP_STATE, r: %i", - r); + TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_MP_STATE, r: %i", + r); r = ioctl(vcpu->fd, KVM_GET_REGS, &state->regs); - TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_REGS, r: %i", - r); + TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_REGS, r: %i", + r); - r = ioctl(vcpu->fd, KVM_GET_XSAVE, &state->xsave); - TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_XSAVE, r: %i", - r); + r = vcpu_save_xsave_state(vm, vcpu, state); + TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_XSAVE, r: %i", + r); if (kvm_check_cap(KVM_CAP_XCRS)) { r = ioctl(vcpu->fd, KVM_GET_XCRS, &state->xcrs); @@ -1123,17 +1186,17 @@ struct kvm_x86_state *vcpu_save_state(struct kvm_vm *vm, uint32_t vcpuid) } r = ioctl(vcpu->fd, KVM_GET_SREGS, &state->sregs); - TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_SREGS, r: %i", - r); + TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_SREGS, r: %i", + r); if (nested_size) { state->nested.size = sizeof(state->nested_); r = ioctl(vcpu->fd, KVM_GET_NESTED_STATE, &state->nested); TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_NESTED_STATE, r: %i", - r); + r); TEST_ASSERT(state->nested.size <= nested_size, - "Nested state size too big, %i (KVM_CHECK_CAP gave %i)", - state->nested.size, nested_size); + "Nested state size too big, %i (KVM_CHECK_CAP gave %i)", + state->nested.size, nested_size); } else state->nested.size = 0; @@ -1141,12 +1204,12 @@ struct kvm_x86_state *vcpu_save_state(struct kvm_vm *vm, uint32_t vcpuid) for (i = 0; i < nmsrs; i++) state->msrs.entries[i].index = list->indices[i]; r = ioctl(vcpu->fd, KVM_GET_MSRS, &state->msrs); - TEST_ASSERT(r == nmsrs, "Unexpected result from KVM_GET_MSRS, r: %i (failed MSR was 0x%x)", - r, r == nmsrs ? -1 : list->indices[r]); + TEST_ASSERT(r == nmsrs, "Unexpected result from KVM_GET_MSRS, r: %i (failed MSR was 0x%x)", + r, r == nmsrs ? -1 : list->indices[r]); r = ioctl(vcpu->fd, KVM_GET_DEBUGREGS, &state->debugregs); - TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_DEBUGREGS, r: %i", - r); + TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_DEBUGREGS, r: %i", + r); free(list); return state; @@ -1157,9 +1220,14 @@ void vcpu_load_state(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_x86_state *s struct vcpu *vcpu = vcpu_find(vm, vcpuid); int r; - r = ioctl(vcpu->fd, KVM_SET_XSAVE, &state->xsave); - TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_XSAVE, r: %i", - r); + r = ioctl(vcpu->fd, KVM_SET_SREGS, &state->sregs); + TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_SREGS, r: %i", + r); + + r = ioctl(vcpu->fd, KVM_SET_MSRS, &state->msrs); + TEST_ASSERT(r == state->msrs.nmsrs, + "Unexpected result from KVM_SET_MSRS, r: %i (failed at %x)", + r, r == state->msrs.nmsrs ? -1 : state->msrs.entries[r].index); if (kvm_check_cap(KVM_CAP_XCRS)) { r = ioctl(vcpu->fd, KVM_SET_XCRS, &state->xcrs); @@ -1167,41 +1235,43 @@ void vcpu_load_state(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_x86_state *s r); } - r = ioctl(vcpu->fd, KVM_SET_SREGS, &state->sregs); - TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_SREGS, r: %i", - r); - - r = ioctl(vcpu->fd, KVM_SET_MSRS, &state->msrs); - TEST_ASSERT(r == state->msrs.nmsrs, "Unexpected result from KVM_SET_MSRS, r: %i (failed at %x)", - r, r == state->msrs.nmsrs ? -1 : state->msrs.entries[r].index); + r = ioctl(vcpu->fd, KVM_SET_XSAVE, state->xsave); + TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_XSAVE, r: %i", + r); r = ioctl(vcpu->fd, KVM_SET_VCPU_EVENTS, &state->events); - TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_VCPU_EVENTS, r: %i", - r); + TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_VCPU_EVENTS, r: %i", + r); r = ioctl(vcpu->fd, KVM_SET_MP_STATE, &state->mp_state); - TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_MP_STATE, r: %i", - r); + TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_MP_STATE, r: %i", + r); r = ioctl(vcpu->fd, KVM_SET_DEBUGREGS, &state->debugregs); - TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_DEBUGREGS, r: %i", - r); + TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_DEBUGREGS, r: %i", + r); r = ioctl(vcpu->fd, KVM_SET_REGS, &state->regs); - TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_REGS, r: %i", - r); + TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_REGS, r: %i", + r); if (state->nested.size) { r = ioctl(vcpu->fd, KVM_SET_NESTED_STATE, &state->nested); TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_NESTED_STATE, r: %i", - r); + r); } } -bool is_intel_cpu(void) +void kvm_x86_state_cleanup(struct kvm_x86_state *state) +{ + free(state->xsave); + free(state); +} + +static bool cpu_vendor_string_is(const char *vendor) { + const uint32_t *chunk = (const uint32_t *)vendor; int eax, ebx, ecx, edx; - const uint32_t *chunk; const int leaf = 0; __asm__ __volatile__( @@ -1210,10 +1280,22 @@ bool is_intel_cpu(void) "=c"(ecx), "=d"(edx) : /* input */ "0"(leaf), "2"(0)); - chunk = (const uint32_t *)("GenuineIntel"); return (ebx == chunk[0] && edx == chunk[1] && ecx == chunk[2]); } +bool is_intel_cpu(void) +{ + return cpu_vendor_string_is("GenuineIntel"); +} + +/* + * Exclude early K5 samples with a vendor string of "AMDisbetter!" + */ +bool is_amd_cpu(void) +{ + return cpu_vendor_string_is("AuthenticAMD"); +} + uint32_t kvm_get_cpuid_max_basic(void) { return kvm_get_supported_cpuid_entry(0)->eax; @@ -1337,6 +1419,23 @@ void assert_on_unhandled_exception(struct kvm_vm *vm, uint32_t vcpuid) } } +struct kvm_cpuid_entry2 *get_cpuid(struct kvm_cpuid2 *cpuid, uint32_t function, + uint32_t index) +{ + int i; + + for (i = 0; i < cpuid->nent; i++) { + struct kvm_cpuid_entry2 *cur = &cpuid->entries[i]; + + if (cur->function == function && cur->index == index) + return cur; + } + + TEST_FAIL("CPUID function 0x%x index 0x%x not found ", function, index); + + return NULL; +} + bool set_cpuid(struct kvm_cpuid2 *cpuid, struct kvm_cpuid_entry2 *ent) { @@ -1432,22 +1531,6 @@ struct kvm_cpuid2 *vcpu_get_supported_hv_cpuid(struct kvm_vm *vm, uint32_t vcpui return cpuid; } -#define X86EMUL_CPUID_VENDOR_AuthenticAMD_ebx 0x68747541 -#define X86EMUL_CPUID_VENDOR_AuthenticAMD_ecx 0x444d4163 -#define X86EMUL_CPUID_VENDOR_AuthenticAMD_edx 0x69746e65 - -static inline unsigned x86_family(unsigned int eax) -{ - unsigned int x86; - - x86 = (eax >> 8) & 0xf; - - if (x86 == 0xf) - x86 += (eax >> 20) & 0xff; - - return x86; -} - unsigned long vm_compute_max_gfn(struct kvm_vm *vm) { const unsigned long num_ht_pages = 12 << (30 - vm->page_shift); /* 12 GiB */ @@ -1457,11 +1540,7 @@ unsigned long vm_compute_max_gfn(struct kvm_vm *vm) max_gfn = (1ULL << (vm->pa_bits - vm->page_shift)) - 1; /* Avoid reserved HyperTransport region on AMD processors. */ - eax = ecx = 0; - cpuid(&eax, &ebx, &ecx, &edx); - if (ebx != X86EMUL_CPUID_VENDOR_AuthenticAMD_ebx || - ecx != X86EMUL_CPUID_VENDOR_AuthenticAMD_ecx || - edx != X86EMUL_CPUID_VENDOR_AuthenticAMD_edx) + if (!is_amd_cpu()) return max_gfn; /* On parts with <40 physical address bits, the area is fully hidden */ @@ -1471,6 +1550,7 @@ unsigned long vm_compute_max_gfn(struct kvm_vm *vm) /* Before family 17h, the HyperTransport area is just below 1T. */ ht_gfn = (1 << 28) - num_ht_pages; eax = 1; + ecx = 0; cpuid(&eax, &ebx, &ecx, &edx); if (x86_family(eax) < 0x17) goto done; diff --git a/tools/testing/selftests/kvm/lib/x86_64/svm.c b/tools/testing/selftests/kvm/lib/x86_64/svm.c index 0ebc03ce079c..736ee4a23df6 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/svm.c +++ b/tools/testing/selftests/kvm/lib/x86_64/svm.c @@ -43,6 +43,11 @@ vcpu_alloc_svm(struct kvm_vm *vm, vm_vaddr_t *p_svm_gva) svm->save_area_hva = addr_gva2hva(vm, (uintptr_t)svm->save_area); svm->save_area_gpa = addr_gva2gpa(vm, (uintptr_t)svm->save_area); + svm->msr = (void *)vm_vaddr_alloc_page(vm); + svm->msr_hva = addr_gva2hva(vm, (uintptr_t)svm->msr); + svm->msr_gpa = addr_gva2gpa(vm, (uintptr_t)svm->msr); + memset(svm->msr_hva, 0, getpagesize()); + *p_svm_gva = svm_gva; return svm; } @@ -106,6 +111,7 @@ void generic_svm_setup(struct svm_test_data *svm, void *guest_rip, void *guest_r save->dbgctl = rdmsr(MSR_IA32_DEBUGCTLMSR); ctrl->intercept = (1ULL << INTERCEPT_VMRUN) | (1ULL << INTERCEPT_VMMCALL); + ctrl->msrpm_base_pa = svm->msr_gpa; vmcb->save.rip = (u64)guest_rip; vmcb->save.rsp = (u64)guest_rsp; diff --git a/tools/testing/selftests/kvm/max_guest_memory_test.c b/tools/testing/selftests/kvm/max_guest_memory_test.c new file mode 100644 index 000000000000..3875c4b23a04 --- /dev/null +++ b/tools/testing/selftests/kvm/max_guest_memory_test.c @@ -0,0 +1,292 @@ +// SPDX-License-Identifier: GPL-2.0 +#define _GNU_SOURCE + +#include <stdio.h> +#include <stdlib.h> +#include <pthread.h> +#include <semaphore.h> +#include <sys/types.h> +#include <signal.h> +#include <errno.h> +#include <linux/bitmap.h> +#include <linux/bitops.h> +#include <linux/atomic.h> + +#include "kvm_util.h" +#include "test_util.h" +#include "guest_modes.h" +#include "processor.h" + +static void guest_code(uint64_t start_gpa, uint64_t end_gpa, uint64_t stride) +{ + uint64_t gpa; + + for (gpa = start_gpa; gpa < end_gpa; gpa += stride) + *((volatile uint64_t *)gpa) = gpa; + + GUEST_DONE(); +} + +struct vcpu_info { + struct kvm_vm *vm; + uint32_t id; + uint64_t start_gpa; + uint64_t end_gpa; +}; + +static int nr_vcpus; +static atomic_t rendezvous; + +static void rendezvous_with_boss(void) +{ + int orig = atomic_read(&rendezvous); + + if (orig > 0) { + atomic_dec_and_test(&rendezvous); + while (atomic_read(&rendezvous) > 0) + cpu_relax(); + } else { + atomic_inc(&rendezvous); + while (atomic_read(&rendezvous) < 0) + cpu_relax(); + } +} + +static void run_vcpu(struct kvm_vm *vm, uint32_t vcpu_id) +{ + vcpu_run(vm, vcpu_id); + ASSERT_EQ(get_ucall(vm, vcpu_id, NULL), UCALL_DONE); +} + +static void *vcpu_worker(void *data) +{ + struct vcpu_info *vcpu = data; + struct kvm_vm *vm = vcpu->vm; + struct kvm_sregs sregs; + struct kvm_regs regs; + + vcpu_args_set(vm, vcpu->id, 3, vcpu->start_gpa, vcpu->end_gpa, + vm_get_page_size(vm)); + + /* Snapshot regs before the first run. */ + vcpu_regs_get(vm, vcpu->id, ®s); + rendezvous_with_boss(); + + run_vcpu(vm, vcpu->id); + rendezvous_with_boss(); + vcpu_regs_set(vm, vcpu->id, ®s); + vcpu_sregs_get(vm, vcpu->id, &sregs); +#ifdef __x86_64__ + /* Toggle CR0.WP to trigger a MMU context reset. */ + sregs.cr0 ^= X86_CR0_WP; +#endif + vcpu_sregs_set(vm, vcpu->id, &sregs); + rendezvous_with_boss(); + + run_vcpu(vm, vcpu->id); + rendezvous_with_boss(); + + return NULL; +} + +static pthread_t *spawn_workers(struct kvm_vm *vm, uint64_t start_gpa, + uint64_t end_gpa) +{ + struct vcpu_info *info; + uint64_t gpa, nr_bytes; + pthread_t *threads; + int i; + + threads = malloc(nr_vcpus * sizeof(*threads)); + TEST_ASSERT(threads, "Failed to allocate vCPU threads"); + + info = malloc(nr_vcpus * sizeof(*info)); + TEST_ASSERT(info, "Failed to allocate vCPU gpa ranges"); + + nr_bytes = ((end_gpa - start_gpa) / nr_vcpus) & + ~((uint64_t)vm_get_page_size(vm) - 1); + TEST_ASSERT(nr_bytes, "C'mon, no way you have %d CPUs", nr_vcpus); + + for (i = 0, gpa = start_gpa; i < nr_vcpus; i++, gpa += nr_bytes) { + info[i].vm = vm; + info[i].id = i; + info[i].start_gpa = gpa; + info[i].end_gpa = gpa + nr_bytes; + pthread_create(&threads[i], NULL, vcpu_worker, &info[i]); + } + return threads; +} + +static void rendezvous_with_vcpus(struct timespec *time, const char *name) +{ + int i, rendezvoused; + + pr_info("Waiting for vCPUs to finish %s...\n", name); + + rendezvoused = atomic_read(&rendezvous); + for (i = 0; abs(rendezvoused) != 1; i++) { + usleep(100); + if (!(i & 0x3f)) + pr_info("\r%d vCPUs haven't rendezvoused...", + abs(rendezvoused) - 1); + rendezvoused = atomic_read(&rendezvous); + } + + clock_gettime(CLOCK_MONOTONIC, time); + + /* Release the vCPUs after getting the time of the previous action. */ + pr_info("\rAll vCPUs finished %s, releasing...\n", name); + if (rendezvoused > 0) + atomic_set(&rendezvous, -nr_vcpus - 1); + else + atomic_set(&rendezvous, nr_vcpus + 1); +} + +static void calc_default_nr_vcpus(void) +{ + cpu_set_t possible_mask; + int r; + + r = sched_getaffinity(0, sizeof(possible_mask), &possible_mask); + TEST_ASSERT(!r, "sched_getaffinity failed, errno = %d (%s)", + errno, strerror(errno)); + + nr_vcpus = CPU_COUNT(&possible_mask) * 3/4; + TEST_ASSERT(nr_vcpus > 0, "Uh, no CPUs?"); +} + +int main(int argc, char *argv[]) +{ + /* + * Skip the first 4gb and slot0. slot0 maps <1gb and is used to back + * the guest's code, stack, and page tables. Because selftests creates + * an IRQCHIP, a.k.a. a local APIC, KVM creates an internal memslot + * just below the 4gb boundary. This test could create memory at + * 1gb-3gb,but it's simpler to skip straight to 4gb. + */ + const uint64_t size_1gb = (1 << 30); + const uint64_t start_gpa = (4ull * size_1gb); + const int first_slot = 1; + + struct timespec time_start, time_run1, time_reset, time_run2; + uint64_t max_gpa, gpa, slot_size, max_mem, i; + int max_slots, slot, opt, fd; + bool hugepages = false; + pthread_t *threads; + struct kvm_vm *vm; + void *mem; + + /* + * Default to 2gb so that maxing out systems with MAXPHADDR=46, which + * are quite common for x86, requires changing only max_mem (KVM allows + * 32k memslots, 32k * 2gb == ~64tb of guest memory). + */ + slot_size = 2 * size_1gb; + + max_slots = kvm_check_cap(KVM_CAP_NR_MEMSLOTS); + TEST_ASSERT(max_slots > first_slot, "KVM is broken"); + + /* All KVM MMUs should be able to survive a 128gb guest. */ + max_mem = 128 * size_1gb; + + calc_default_nr_vcpus(); + + while ((opt = getopt(argc, argv, "c:h:m:s:H")) != -1) { + switch (opt) { + case 'c': + nr_vcpus = atoi(optarg); + TEST_ASSERT(nr_vcpus > 0, "number of vcpus must be >0"); + break; + case 'm': + max_mem = atoi(optarg) * size_1gb; + TEST_ASSERT(max_mem > 0, "memory size must be >0"); + break; + case 's': + slot_size = atoi(optarg) * size_1gb; + TEST_ASSERT(slot_size > 0, "slot size must be >0"); + break; + case 'H': + hugepages = true; + break; + case 'h': + default: + printf("usage: %s [-c nr_vcpus] [-m max_mem_in_gb] [-s slot_size_in_gb] [-H]\n", argv[0]); + exit(1); + } + } + + vm = vm_create_default_with_vcpus(nr_vcpus, 0, 0, guest_code, NULL); + + max_gpa = vm_get_max_gfn(vm) << vm_get_page_shift(vm); + TEST_ASSERT(max_gpa > (4 * slot_size), "MAXPHYADDR <4gb "); + + fd = kvm_memfd_alloc(slot_size, hugepages); + mem = mmap(NULL, slot_size, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0); + TEST_ASSERT(mem != MAP_FAILED, "mmap() failed"); + + TEST_ASSERT(!madvise(mem, slot_size, MADV_NOHUGEPAGE), "madvise() failed"); + + /* Pre-fault the memory to avoid taking mmap_sem on guest page faults. */ + for (i = 0; i < slot_size; i += vm_get_page_size(vm)) + ((uint8_t *)mem)[i] = 0xaa; + + gpa = 0; + for (slot = first_slot; slot < max_slots; slot++) { + gpa = start_gpa + ((slot - first_slot) * slot_size); + if (gpa + slot_size > max_gpa) + break; + + if ((gpa - start_gpa) >= max_mem) + break; + + vm_set_user_memory_region(vm, slot, 0, gpa, slot_size, mem); + +#ifdef __x86_64__ + /* Identity map memory in the guest using 1gb pages. */ + for (i = 0; i < slot_size; i += size_1gb) + __virt_pg_map(vm, gpa + i, gpa + i, X86_PAGE_SIZE_1G); +#else + for (i = 0; i < slot_size; i += vm_get_page_size(vm)) + virt_pg_map(vm, gpa + i, gpa + i); +#endif + } + + atomic_set(&rendezvous, nr_vcpus + 1); + threads = spawn_workers(vm, start_gpa, gpa); + + pr_info("Running with %lugb of guest memory and %u vCPUs\n", + (gpa - start_gpa) / size_1gb, nr_vcpus); + + rendezvous_with_vcpus(&time_start, "spawning"); + rendezvous_with_vcpus(&time_run1, "run 1"); + rendezvous_with_vcpus(&time_reset, "reset"); + rendezvous_with_vcpus(&time_run2, "run 2"); + + time_run2 = timespec_sub(time_run2, time_reset); + time_reset = timespec_sub(time_reset, time_run1); + time_run1 = timespec_sub(time_run1, time_start); + + pr_info("run1 = %ld.%.9lds, reset = %ld.%.9lds, run2 = %ld.%.9lds\n", + time_run1.tv_sec, time_run1.tv_nsec, + time_reset.tv_sec, time_reset.tv_nsec, + time_run2.tv_sec, time_run2.tv_nsec); + + /* + * Delete even numbered slots (arbitrary) and unmap the first half of + * the backing (also arbitrary) to verify KVM correctly drops all + * references to the removed regions. + */ + for (slot = (slot - 1) & ~1ull; slot >= first_slot; slot -= 2) + vm_set_user_memory_region(vm, slot, 0, 0, 0, NULL); + + munmap(mem, slot_size / 2); + + /* Sanity check that the vCPUs actually ran. */ + for (i = 0; i < nr_vcpus; i++) + pthread_join(threads[i], NULL); + + /* + * Deliberately exit without deleting the remaining memslots or closing + * kvm_fd to test cleanup via mmu_notifier.release. + */ +} diff --git a/tools/testing/selftests/kvm/s390x/memop.c b/tools/testing/selftests/kvm/s390x/memop.c index 9f49ead380ab..b04c2c1b3c30 100644 --- a/tools/testing/selftests/kvm/s390x/memop.c +++ b/tools/testing/selftests/kvm/s390x/memop.c @@ -13,154 +13,668 @@ #include "test_util.h" #include "kvm_util.h" +enum mop_target { + LOGICAL, + SIDA, + ABSOLUTE, + INVALID, +}; + +enum mop_access_mode { + READ, + WRITE, +}; + +struct mop_desc { + uintptr_t gaddr; + uintptr_t gaddr_v; + uint64_t set_flags; + unsigned int f_check : 1; + unsigned int f_inject : 1; + unsigned int f_key : 1; + unsigned int _gaddr_v : 1; + unsigned int _set_flags : 1; + unsigned int _sida_offset : 1; + unsigned int _ar : 1; + uint32_t size; + enum mop_target target; + enum mop_access_mode mode; + void *buf; + uint32_t sida_offset; + uint8_t ar; + uint8_t key; +}; + +static struct kvm_s390_mem_op ksmo_from_desc(struct mop_desc desc) +{ + struct kvm_s390_mem_op ksmo = { + .gaddr = (uintptr_t)desc.gaddr, + .size = desc.size, + .buf = ((uintptr_t)desc.buf), + .reserved = "ignored_ignored_ignored_ignored" + }; + + switch (desc.target) { + case LOGICAL: + if (desc.mode == READ) + ksmo.op = KVM_S390_MEMOP_LOGICAL_READ; + if (desc.mode == WRITE) + ksmo.op = KVM_S390_MEMOP_LOGICAL_WRITE; + break; + case SIDA: + if (desc.mode == READ) + ksmo.op = KVM_S390_MEMOP_SIDA_READ; + if (desc.mode == WRITE) + ksmo.op = KVM_S390_MEMOP_SIDA_WRITE; + break; + case ABSOLUTE: + if (desc.mode == READ) + ksmo.op = KVM_S390_MEMOP_ABSOLUTE_READ; + if (desc.mode == WRITE) + ksmo.op = KVM_S390_MEMOP_ABSOLUTE_WRITE; + break; + case INVALID: + ksmo.op = -1; + } + if (desc.f_check) + ksmo.flags |= KVM_S390_MEMOP_F_CHECK_ONLY; + if (desc.f_inject) + ksmo.flags |= KVM_S390_MEMOP_F_INJECT_EXCEPTION; + if (desc._set_flags) + ksmo.flags = desc.set_flags; + if (desc.f_key) { + ksmo.flags |= KVM_S390_MEMOP_F_SKEY_PROTECTION; + ksmo.key = desc.key; + } + if (desc._ar) + ksmo.ar = desc.ar; + else + ksmo.ar = 0; + if (desc._sida_offset) + ksmo.sida_offset = desc.sida_offset; + + return ksmo; +} + +/* vcpu dummy id signifying that vm instead of vcpu ioctl is to occur */ +const uint32_t VM_VCPU_ID = (uint32_t)-1; + +struct test_vcpu { + struct kvm_vm *vm; + uint32_t id; +}; + +#define PRINT_MEMOP false +static void print_memop(uint32_t vcpu_id, const struct kvm_s390_mem_op *ksmo) +{ + if (!PRINT_MEMOP) + return; + + if (vcpu_id == VM_VCPU_ID) + printf("vm memop("); + else + printf("vcpu memop("); + switch (ksmo->op) { + case KVM_S390_MEMOP_LOGICAL_READ: + printf("LOGICAL, READ, "); + break; + case KVM_S390_MEMOP_LOGICAL_WRITE: + printf("LOGICAL, WRITE, "); + break; + case KVM_S390_MEMOP_SIDA_READ: + printf("SIDA, READ, "); + break; + case KVM_S390_MEMOP_SIDA_WRITE: + printf("SIDA, WRITE, "); + break; + case KVM_S390_MEMOP_ABSOLUTE_READ: + printf("ABSOLUTE, READ, "); + break; + case KVM_S390_MEMOP_ABSOLUTE_WRITE: + printf("ABSOLUTE, WRITE, "); + break; + } + printf("gaddr=%llu, size=%u, buf=%llu, ar=%u, key=%u", + ksmo->gaddr, ksmo->size, ksmo->buf, ksmo->ar, ksmo->key); + if (ksmo->flags & KVM_S390_MEMOP_F_CHECK_ONLY) + printf(", CHECK_ONLY"); + if (ksmo->flags & KVM_S390_MEMOP_F_INJECT_EXCEPTION) + printf(", INJECT_EXCEPTION"); + if (ksmo->flags & KVM_S390_MEMOP_F_SKEY_PROTECTION) + printf(", SKEY_PROTECTION"); + puts(")"); +} + +static void memop_ioctl(struct test_vcpu vcpu, struct kvm_s390_mem_op *ksmo) +{ + if (vcpu.id == VM_VCPU_ID) + vm_ioctl(vcpu.vm, KVM_S390_MEM_OP, ksmo); + else + vcpu_ioctl(vcpu.vm, vcpu.id, KVM_S390_MEM_OP, ksmo); +} + +static int err_memop_ioctl(struct test_vcpu vcpu, struct kvm_s390_mem_op *ksmo) +{ + if (vcpu.id == VM_VCPU_ID) + return _vm_ioctl(vcpu.vm, KVM_S390_MEM_OP, ksmo); + else + return _vcpu_ioctl(vcpu.vm, vcpu.id, KVM_S390_MEM_OP, ksmo); +} + +#define MEMOP(err, vcpu_p, mop_target_p, access_mode_p, buf_p, size_p, ...) \ +({ \ + struct test_vcpu __vcpu = (vcpu_p); \ + struct mop_desc __desc = { \ + .target = (mop_target_p), \ + .mode = (access_mode_p), \ + .buf = (buf_p), \ + .size = (size_p), \ + __VA_ARGS__ \ + }; \ + struct kvm_s390_mem_op __ksmo; \ + \ + if (__desc._gaddr_v) { \ + if (__desc.target == ABSOLUTE) \ + __desc.gaddr = addr_gva2gpa(__vcpu.vm, __desc.gaddr_v); \ + else \ + __desc.gaddr = __desc.gaddr_v; \ + } \ + __ksmo = ksmo_from_desc(__desc); \ + print_memop(__vcpu.id, &__ksmo); \ + err##memop_ioctl(__vcpu, &__ksmo); \ +}) + +#define MOP(...) MEMOP(, __VA_ARGS__) +#define ERR_MOP(...) MEMOP(err_, __VA_ARGS__) + +#define GADDR(a) .gaddr = ((uintptr_t)a) +#define GADDR_V(v) ._gaddr_v = 1, .gaddr_v = ((uintptr_t)v) +#define CHECK_ONLY .f_check = 1 +#define SET_FLAGS(f) ._set_flags = 1, .set_flags = (f) +#define SIDA_OFFSET(o) ._sida_offset = 1, .sida_offset = (o) +#define AR(a) ._ar = 1, .ar = (a) +#define KEY(a) .f_key = 1, .key = (a) + +#define CHECK_N_DO(f, ...) ({ f(__VA_ARGS__, CHECK_ONLY); f(__VA_ARGS__); }) + #define VCPU_ID 1 +#define PAGE_SHIFT 12 +#define PAGE_SIZE (1ULL << PAGE_SHIFT) +#define PAGE_MASK (~(PAGE_SIZE - 1)) +#define CR0_FETCH_PROTECTION_OVERRIDE (1UL << (63 - 38)) +#define CR0_STORAGE_PROTECTION_OVERRIDE (1UL << (63 - 39)) static uint8_t mem1[65536]; static uint8_t mem2[65536]; -static void guest_code(void) +struct test_default { + struct kvm_vm *kvm_vm; + struct test_vcpu vm; + struct test_vcpu vcpu; + struct kvm_run *run; + int size; +}; + +static struct test_default test_default_init(void *guest_code) +{ + struct test_default t; + + t.size = min((size_t)kvm_check_cap(KVM_CAP_S390_MEM_OP), sizeof(mem1)); + t.kvm_vm = vm_create_default(VCPU_ID, 0, guest_code); + t.vm = (struct test_vcpu) { t.kvm_vm, VM_VCPU_ID }; + t.vcpu = (struct test_vcpu) { t.kvm_vm, VCPU_ID }; + t.run = vcpu_state(t.kvm_vm, VCPU_ID); + return t; +} + +enum stage { + /* Synced state set by host, e.g. DAT */ + STAGE_INITED, + /* Guest did nothing */ + STAGE_IDLED, + /* Guest set storage keys (specifics up to test case) */ + STAGE_SKEYS_SET, + /* Guest copied memory (locations up to test case) */ + STAGE_COPIED, +}; + +#define HOST_SYNC(vcpu_p, stage) \ +({ \ + struct test_vcpu __vcpu = (vcpu_p); \ + struct ucall uc; \ + int __stage = (stage); \ + \ + vcpu_run(__vcpu.vm, __vcpu.id); \ + get_ucall(__vcpu.vm, __vcpu.id, &uc); \ + ASSERT_EQ(uc.cmd, UCALL_SYNC); \ + ASSERT_EQ(uc.args[1], __stage); \ +}) \ + +static void prepare_mem12(void) { int i; + for (i = 0; i < sizeof(mem1); i++) + mem1[i] = rand(); + memset(mem2, 0xaa, sizeof(mem2)); +} + +#define ASSERT_MEM_EQ(p1, p2, size) \ + TEST_ASSERT(!memcmp(p1, p2, size), "Memory contents do not match!") + +#define DEFAULT_WRITE_READ(copy_cpu, mop_cpu, mop_target_p, size, ...) \ +({ \ + struct test_vcpu __copy_cpu = (copy_cpu), __mop_cpu = (mop_cpu); \ + enum mop_target __target = (mop_target_p); \ + uint32_t __size = (size); \ + \ + prepare_mem12(); \ + CHECK_N_DO(MOP, __mop_cpu, __target, WRITE, mem1, __size, \ + GADDR_V(mem1), ##__VA_ARGS__); \ + HOST_SYNC(__copy_cpu, STAGE_COPIED); \ + CHECK_N_DO(MOP, __mop_cpu, __target, READ, mem2, __size, \ + GADDR_V(mem2), ##__VA_ARGS__); \ + ASSERT_MEM_EQ(mem1, mem2, __size); \ +}) + +#define DEFAULT_READ(copy_cpu, mop_cpu, mop_target_p, size, ...) \ +({ \ + struct test_vcpu __copy_cpu = (copy_cpu), __mop_cpu = (mop_cpu); \ + enum mop_target __target = (mop_target_p); \ + uint32_t __size = (size); \ + \ + prepare_mem12(); \ + CHECK_N_DO(MOP, __mop_cpu, __target, WRITE, mem1, __size, \ + GADDR_V(mem1)); \ + HOST_SYNC(__copy_cpu, STAGE_COPIED); \ + CHECK_N_DO(MOP, __mop_cpu, __target, READ, mem2, __size, ##__VA_ARGS__);\ + ASSERT_MEM_EQ(mem1, mem2, __size); \ +}) + +static void guest_copy(void) +{ + GUEST_SYNC(STAGE_INITED); + memcpy(&mem2, &mem1, sizeof(mem2)); + GUEST_SYNC(STAGE_COPIED); +} + +static void test_copy(void) +{ + struct test_default t = test_default_init(guest_copy); + + HOST_SYNC(t.vcpu, STAGE_INITED); + + DEFAULT_WRITE_READ(t.vcpu, t.vcpu, LOGICAL, t.size); + + kvm_vm_free(t.kvm_vm); +} + +static void set_storage_key_range(void *addr, size_t len, uint8_t key) +{ + uintptr_t _addr, abs, i; + int not_mapped = 0; + + _addr = (uintptr_t)addr; + for (i = _addr & PAGE_MASK; i < _addr + len; i += PAGE_SIZE) { + abs = i; + asm volatile ( + "lra %[abs], 0(0,%[abs])\n" + " jz 0f\n" + " llill %[not_mapped],1\n" + " j 1f\n" + "0: sske %[key], %[abs]\n" + "1:" + : [abs] "+&a" (abs), [not_mapped] "+r" (not_mapped) + : [key] "r" (key) + : "cc" + ); + GUEST_ASSERT_EQ(not_mapped, 0); + } +} + +static void guest_copy_key(void) +{ + set_storage_key_range(mem1, sizeof(mem1), 0x90); + set_storage_key_range(mem2, sizeof(mem2), 0x90); + GUEST_SYNC(STAGE_SKEYS_SET); + for (;;) { - for (i = 0; i < sizeof(mem2); i++) - mem2[i] = mem1[i]; - GUEST_SYNC(0); + memcpy(&mem2, &mem1, sizeof(mem2)); + GUEST_SYNC(STAGE_COPIED); } } -int main(int argc, char *argv[]) +static void test_copy_key(void) { - struct kvm_vm *vm; - struct kvm_run *run; - struct kvm_s390_mem_op ksmo; - int rv, i, maxsize; + struct test_default t = test_default_init(guest_copy_key); - setbuf(stdout, NULL); /* Tell stdout not to buffer its content */ + HOST_SYNC(t.vcpu, STAGE_SKEYS_SET); - maxsize = kvm_check_cap(KVM_CAP_S390_MEM_OP); - if (!maxsize) { - print_skip("CAP_S390_MEM_OP not supported"); - exit(KSFT_SKIP); + /* vm, no key */ + DEFAULT_WRITE_READ(t.vcpu, t.vm, ABSOLUTE, t.size); + + /* vm/vcpu, machting key or key 0 */ + DEFAULT_WRITE_READ(t.vcpu, t.vcpu, LOGICAL, t.size, KEY(0)); + DEFAULT_WRITE_READ(t.vcpu, t.vcpu, LOGICAL, t.size, KEY(9)); + DEFAULT_WRITE_READ(t.vcpu, t.vm, ABSOLUTE, t.size, KEY(0)); + DEFAULT_WRITE_READ(t.vcpu, t.vm, ABSOLUTE, t.size, KEY(9)); + /* + * There used to be different code paths for key handling depending on + * if the region crossed a page boundary. + * There currently are not, but the more tests the merrier. + */ + DEFAULT_WRITE_READ(t.vcpu, t.vcpu, LOGICAL, 1, KEY(0)); + DEFAULT_WRITE_READ(t.vcpu, t.vcpu, LOGICAL, 1, KEY(9)); + DEFAULT_WRITE_READ(t.vcpu, t.vm, ABSOLUTE, 1, KEY(0)); + DEFAULT_WRITE_READ(t.vcpu, t.vm, ABSOLUTE, 1, KEY(9)); + + /* vm/vcpu, mismatching keys on read, but no fetch protection */ + DEFAULT_READ(t.vcpu, t.vcpu, LOGICAL, t.size, GADDR_V(mem2), KEY(2)); + DEFAULT_READ(t.vcpu, t.vm, ABSOLUTE, t.size, GADDR_V(mem1), KEY(2)); + + kvm_vm_free(t.kvm_vm); +} + +static void guest_copy_key_fetch_prot(void) +{ + /* + * For some reason combining the first sync with override enablement + * results in an exception when calling HOST_SYNC. + */ + GUEST_SYNC(STAGE_INITED); + /* Storage protection override applies to both store and fetch. */ + set_storage_key_range(mem1, sizeof(mem1), 0x98); + set_storage_key_range(mem2, sizeof(mem2), 0x98); + GUEST_SYNC(STAGE_SKEYS_SET); + + for (;;) { + memcpy(&mem2, &mem1, sizeof(mem2)); + GUEST_SYNC(STAGE_COPIED); } - if (maxsize > sizeof(mem1)) - maxsize = sizeof(mem1); +} - /* Create VM */ - vm = vm_create_default(VCPU_ID, 0, guest_code); - run = vcpu_state(vm, VCPU_ID); +static void test_copy_key_storage_prot_override(void) +{ + struct test_default t = test_default_init(guest_copy_key_fetch_prot); - for (i = 0; i < sizeof(mem1); i++) - mem1[i] = i * i + i; - - /* Set the first array */ - ksmo.gaddr = addr_gva2gpa(vm, (uintptr_t)mem1); - ksmo.flags = 0; - ksmo.size = maxsize; - ksmo.op = KVM_S390_MEMOP_LOGICAL_WRITE; - ksmo.buf = (uintptr_t)mem1; - ksmo.ar = 0; - vcpu_ioctl(vm, VCPU_ID, KVM_S390_MEM_OP, &ksmo); - - /* Let the guest code copy the first array to the second */ - vcpu_run(vm, VCPU_ID); - TEST_ASSERT(run->exit_reason == KVM_EXIT_S390_SIEIC, - "Unexpected exit reason: %u (%s)\n", - run->exit_reason, - exit_reason_str(run->exit_reason)); + HOST_SYNC(t.vcpu, STAGE_INITED); + t.run->s.regs.crs[0] |= CR0_STORAGE_PROTECTION_OVERRIDE; + t.run->kvm_dirty_regs = KVM_SYNC_CRS; + HOST_SYNC(t.vcpu, STAGE_SKEYS_SET); - memset(mem2, 0xaa, sizeof(mem2)); + /* vcpu, mismatching keys, storage protection override in effect */ + DEFAULT_WRITE_READ(t.vcpu, t.vcpu, LOGICAL, t.size, KEY(2)); + + kvm_vm_free(t.kvm_vm); +} + +static void test_copy_key_fetch_prot(void) +{ + struct test_default t = test_default_init(guest_copy_key_fetch_prot); - /* Get the second array */ - ksmo.gaddr = (uintptr_t)mem2; - ksmo.flags = 0; - ksmo.size = maxsize; - ksmo.op = KVM_S390_MEMOP_LOGICAL_READ; - ksmo.buf = (uintptr_t)mem2; - ksmo.ar = 0; - vcpu_ioctl(vm, VCPU_ID, KVM_S390_MEM_OP, &ksmo); - - TEST_ASSERT(!memcmp(mem1, mem2, maxsize), - "Memory contents do not match!"); - - /* Check error conditions - first bad size: */ - ksmo.gaddr = (uintptr_t)mem1; - ksmo.flags = 0; - ksmo.size = -1; - ksmo.op = KVM_S390_MEMOP_LOGICAL_WRITE; - ksmo.buf = (uintptr_t)mem1; - ksmo.ar = 0; - rv = _vcpu_ioctl(vm, VCPU_ID, KVM_S390_MEM_OP, &ksmo); + HOST_SYNC(t.vcpu, STAGE_INITED); + HOST_SYNC(t.vcpu, STAGE_SKEYS_SET); + + /* vm/vcpu, matching key, fetch protection in effect */ + DEFAULT_READ(t.vcpu, t.vcpu, LOGICAL, t.size, GADDR_V(mem2), KEY(9)); + DEFAULT_READ(t.vcpu, t.vm, ABSOLUTE, t.size, GADDR_V(mem2), KEY(9)); + + kvm_vm_free(t.kvm_vm); +} + +#define ERR_PROT_MOP(...) \ +({ \ + int rv; \ + \ + rv = ERR_MOP(__VA_ARGS__); \ + TEST_ASSERT(rv == 4, "Should result in protection exception"); \ +}) + +static void test_errors_key(void) +{ + struct test_default t = test_default_init(guest_copy_key_fetch_prot); + + HOST_SYNC(t.vcpu, STAGE_INITED); + HOST_SYNC(t.vcpu, STAGE_SKEYS_SET); + + /* vm/vcpu, mismatching keys, fetch protection in effect */ + CHECK_N_DO(ERR_PROT_MOP, t.vcpu, LOGICAL, WRITE, mem1, t.size, GADDR_V(mem1), KEY(2)); + CHECK_N_DO(ERR_PROT_MOP, t.vcpu, LOGICAL, READ, mem2, t.size, GADDR_V(mem2), KEY(2)); + CHECK_N_DO(ERR_PROT_MOP, t.vm, ABSOLUTE, WRITE, mem1, t.size, GADDR_V(mem1), KEY(2)); + CHECK_N_DO(ERR_PROT_MOP, t.vm, ABSOLUTE, READ, mem2, t.size, GADDR_V(mem2), KEY(2)); + + kvm_vm_free(t.kvm_vm); +} + +static void test_errors_key_storage_prot_override(void) +{ + struct test_default t = test_default_init(guest_copy_key_fetch_prot); + + HOST_SYNC(t.vcpu, STAGE_INITED); + t.run->s.regs.crs[0] |= CR0_STORAGE_PROTECTION_OVERRIDE; + t.run->kvm_dirty_regs = KVM_SYNC_CRS; + HOST_SYNC(t.vcpu, STAGE_SKEYS_SET); + + /* vm, mismatching keys, storage protection override not applicable to vm */ + CHECK_N_DO(ERR_PROT_MOP, t.vm, ABSOLUTE, WRITE, mem1, t.size, GADDR_V(mem1), KEY(2)); + CHECK_N_DO(ERR_PROT_MOP, t.vm, ABSOLUTE, READ, mem2, t.size, GADDR_V(mem2), KEY(2)); + + kvm_vm_free(t.kvm_vm); +} + +const uint64_t last_page_addr = -PAGE_SIZE; + +static void guest_copy_key_fetch_prot_override(void) +{ + int i; + char *page_0 = 0; + + GUEST_SYNC(STAGE_INITED); + set_storage_key_range(0, PAGE_SIZE, 0x18); + set_storage_key_range((void *)last_page_addr, PAGE_SIZE, 0x0); + asm volatile ("sske %[key],%[addr]\n" :: [addr] "r"(0), [key] "r"(0x18) : "cc"); + GUEST_SYNC(STAGE_SKEYS_SET); + + for (;;) { + for (i = 0; i < PAGE_SIZE; i++) + page_0[i] = mem1[i]; + GUEST_SYNC(STAGE_COPIED); + } +} + +static void test_copy_key_fetch_prot_override(void) +{ + struct test_default t = test_default_init(guest_copy_key_fetch_prot_override); + vm_vaddr_t guest_0_page, guest_last_page; + + guest_0_page = vm_vaddr_alloc(t.kvm_vm, PAGE_SIZE, 0); + guest_last_page = vm_vaddr_alloc(t.kvm_vm, PAGE_SIZE, last_page_addr); + if (guest_0_page != 0 || guest_last_page != last_page_addr) { + print_skip("did not allocate guest pages at required positions"); + goto out; + } + + HOST_SYNC(t.vcpu, STAGE_INITED); + t.run->s.regs.crs[0] |= CR0_FETCH_PROTECTION_OVERRIDE; + t.run->kvm_dirty_regs = KVM_SYNC_CRS; + HOST_SYNC(t.vcpu, STAGE_SKEYS_SET); + + /* vcpu, mismatching keys on fetch, fetch protection override applies */ + prepare_mem12(); + MOP(t.vcpu, LOGICAL, WRITE, mem1, PAGE_SIZE, GADDR_V(mem1)); + HOST_SYNC(t.vcpu, STAGE_COPIED); + CHECK_N_DO(MOP, t.vcpu, LOGICAL, READ, mem2, 2048, GADDR_V(guest_0_page), KEY(2)); + ASSERT_MEM_EQ(mem1, mem2, 2048); + + /* + * vcpu, mismatching keys on fetch, fetch protection override applies, + * wraparound + */ + prepare_mem12(); + MOP(t.vcpu, LOGICAL, WRITE, mem1, 2 * PAGE_SIZE, GADDR_V(guest_last_page)); + HOST_SYNC(t.vcpu, STAGE_COPIED); + CHECK_N_DO(MOP, t.vcpu, LOGICAL, READ, mem2, PAGE_SIZE + 2048, + GADDR_V(guest_last_page), KEY(2)); + ASSERT_MEM_EQ(mem1, mem2, 2048); + +out: + kvm_vm_free(t.kvm_vm); +} + +static void test_errors_key_fetch_prot_override_not_enabled(void) +{ + struct test_default t = test_default_init(guest_copy_key_fetch_prot_override); + vm_vaddr_t guest_0_page, guest_last_page; + + guest_0_page = vm_vaddr_alloc(t.kvm_vm, PAGE_SIZE, 0); + guest_last_page = vm_vaddr_alloc(t.kvm_vm, PAGE_SIZE, last_page_addr); + if (guest_0_page != 0 || guest_last_page != last_page_addr) { + print_skip("did not allocate guest pages at required positions"); + goto out; + } + HOST_SYNC(t.vcpu, STAGE_INITED); + HOST_SYNC(t.vcpu, STAGE_SKEYS_SET); + + /* vcpu, mismatching keys on fetch, fetch protection override not enabled */ + CHECK_N_DO(ERR_PROT_MOP, t.vcpu, LOGICAL, READ, mem2, 2048, GADDR_V(0), KEY(2)); + +out: + kvm_vm_free(t.kvm_vm); +} + +static void test_errors_key_fetch_prot_override_enabled(void) +{ + struct test_default t = test_default_init(guest_copy_key_fetch_prot_override); + vm_vaddr_t guest_0_page, guest_last_page; + + guest_0_page = vm_vaddr_alloc(t.kvm_vm, PAGE_SIZE, 0); + guest_last_page = vm_vaddr_alloc(t.kvm_vm, PAGE_SIZE, last_page_addr); + if (guest_0_page != 0 || guest_last_page != last_page_addr) { + print_skip("did not allocate guest pages at required positions"); + goto out; + } + HOST_SYNC(t.vcpu, STAGE_INITED); + t.run->s.regs.crs[0] |= CR0_FETCH_PROTECTION_OVERRIDE; + t.run->kvm_dirty_regs = KVM_SYNC_CRS; + HOST_SYNC(t.vcpu, STAGE_SKEYS_SET); + + /* + * vcpu, mismatching keys on fetch, + * fetch protection override does not apply because memory range acceeded + */ + CHECK_N_DO(ERR_PROT_MOP, t.vcpu, LOGICAL, READ, mem2, 2048 + 1, GADDR_V(0), KEY(2)); + CHECK_N_DO(ERR_PROT_MOP, t.vcpu, LOGICAL, READ, mem2, PAGE_SIZE + 2048 + 1, + GADDR_V(guest_last_page), KEY(2)); + /* vm, fetch protected override does not apply */ + CHECK_N_DO(ERR_PROT_MOP, t.vm, ABSOLUTE, READ, mem2, 2048, GADDR(0), KEY(2)); + CHECK_N_DO(ERR_PROT_MOP, t.vm, ABSOLUTE, READ, mem2, 2048, GADDR_V(guest_0_page), KEY(2)); + +out: + kvm_vm_free(t.kvm_vm); +} + +static void guest_idle(void) +{ + GUEST_SYNC(STAGE_INITED); /* for consistency's sake */ + for (;;) + GUEST_SYNC(STAGE_IDLED); +} + +static void _test_errors_common(struct test_vcpu vcpu, enum mop_target target, int size) +{ + int rv; + + /* Bad size: */ + rv = ERR_MOP(vcpu, target, WRITE, mem1, -1, GADDR_V(mem1)); TEST_ASSERT(rv == -1 && errno == E2BIG, "ioctl allows insane sizes"); /* Zero size: */ - ksmo.gaddr = (uintptr_t)mem1; - ksmo.flags = 0; - ksmo.size = 0; - ksmo.op = KVM_S390_MEMOP_LOGICAL_WRITE; - ksmo.buf = (uintptr_t)mem1; - ksmo.ar = 0; - rv = _vcpu_ioctl(vm, VCPU_ID, KVM_S390_MEM_OP, &ksmo); + rv = ERR_MOP(vcpu, target, WRITE, mem1, 0, GADDR_V(mem1)); TEST_ASSERT(rv == -1 && (errno == EINVAL || errno == ENOMEM), "ioctl allows 0 as size"); /* Bad flags: */ - ksmo.gaddr = (uintptr_t)mem1; - ksmo.flags = -1; - ksmo.size = maxsize; - ksmo.op = KVM_S390_MEMOP_LOGICAL_WRITE; - ksmo.buf = (uintptr_t)mem1; - ksmo.ar = 0; - rv = _vcpu_ioctl(vm, VCPU_ID, KVM_S390_MEM_OP, &ksmo); + rv = ERR_MOP(vcpu, target, WRITE, mem1, size, GADDR_V(mem1), SET_FLAGS(-1)); TEST_ASSERT(rv == -1 && errno == EINVAL, "ioctl allows all flags"); - /* Bad operation: */ - ksmo.gaddr = (uintptr_t)mem1; - ksmo.flags = 0; - ksmo.size = maxsize; - ksmo.op = -1; - ksmo.buf = (uintptr_t)mem1; - ksmo.ar = 0; - rv = _vcpu_ioctl(vm, VCPU_ID, KVM_S390_MEM_OP, &ksmo); - TEST_ASSERT(rv == -1 && errno == EINVAL, "ioctl allows bad operations"); - /* Bad guest address: */ - ksmo.gaddr = ~0xfffUL; - ksmo.flags = KVM_S390_MEMOP_F_CHECK_ONLY; - ksmo.size = maxsize; - ksmo.op = KVM_S390_MEMOP_LOGICAL_WRITE; - ksmo.buf = (uintptr_t)mem1; - ksmo.ar = 0; - rv = _vcpu_ioctl(vm, VCPU_ID, KVM_S390_MEM_OP, &ksmo); + rv = ERR_MOP(vcpu, target, WRITE, mem1, size, GADDR((void *)~0xfffUL), CHECK_ONLY); TEST_ASSERT(rv > 0, "ioctl does not report bad guest memory access"); /* Bad host address: */ - ksmo.gaddr = (uintptr_t)mem1; - ksmo.flags = 0; - ksmo.size = maxsize; - ksmo.op = KVM_S390_MEMOP_LOGICAL_WRITE; - ksmo.buf = 0; - ksmo.ar = 0; - rv = _vcpu_ioctl(vm, VCPU_ID, KVM_S390_MEM_OP, &ksmo); + rv = ERR_MOP(vcpu, target, WRITE, 0, size, GADDR_V(mem1)); TEST_ASSERT(rv == -1 && errno == EFAULT, "ioctl does not report bad host memory address"); + /* Bad key: */ + rv = ERR_MOP(vcpu, target, WRITE, mem1, size, GADDR_V(mem1), KEY(17)); + TEST_ASSERT(rv == -1 && errno == EINVAL, "ioctl allows invalid key"); +} + +static void test_errors(void) +{ + struct test_default t = test_default_init(guest_idle); + int rv; + + HOST_SYNC(t.vcpu, STAGE_INITED); + + _test_errors_common(t.vcpu, LOGICAL, t.size); + _test_errors_common(t.vm, ABSOLUTE, t.size); + + /* Bad operation: */ + rv = ERR_MOP(t.vcpu, INVALID, WRITE, mem1, t.size, GADDR_V(mem1)); + TEST_ASSERT(rv == -1 && errno == EINVAL, "ioctl allows bad operations"); + /* virtual addresses are not translated when passing INVALID */ + rv = ERR_MOP(t.vm, INVALID, WRITE, mem1, PAGE_SIZE, GADDR(0)); + TEST_ASSERT(rv == -1 && errno == EINVAL, "ioctl allows bad operations"); + /* Bad access register: */ - run->psw_mask &= ~(3UL << (63 - 17)); - run->psw_mask |= 1UL << (63 - 17); /* Enable AR mode */ - vcpu_run(vm, VCPU_ID); /* To sync new state to SIE block */ - ksmo.gaddr = (uintptr_t)mem1; - ksmo.flags = 0; - ksmo.size = maxsize; - ksmo.op = KVM_S390_MEMOP_LOGICAL_WRITE; - ksmo.buf = (uintptr_t)mem1; - ksmo.ar = 17; - rv = _vcpu_ioctl(vm, VCPU_ID, KVM_S390_MEM_OP, &ksmo); + t.run->psw_mask &= ~(3UL << (63 - 17)); + t.run->psw_mask |= 1UL << (63 - 17); /* Enable AR mode */ + HOST_SYNC(t.vcpu, STAGE_IDLED); /* To sync new state to SIE block */ + rv = ERR_MOP(t.vcpu, LOGICAL, WRITE, mem1, t.size, GADDR_V(mem1), AR(17)); TEST_ASSERT(rv == -1 && errno == EINVAL, "ioctl allows ARs > 15"); - run->psw_mask &= ~(3UL << (63 - 17)); /* Disable AR mode */ - vcpu_run(vm, VCPU_ID); /* Run to sync new state */ + t.run->psw_mask &= ~(3UL << (63 - 17)); /* Disable AR mode */ + HOST_SYNC(t.vcpu, STAGE_IDLED); /* Run to sync new state */ + + /* Check that the SIDA calls are rejected for non-protected guests */ + rv = ERR_MOP(t.vcpu, SIDA, READ, mem1, 8, GADDR(0), SIDA_OFFSET(0x1c0)); + TEST_ASSERT(rv == -1 && errno == EINVAL, + "ioctl does not reject SIDA_READ in non-protected mode"); + rv = ERR_MOP(t.vcpu, SIDA, WRITE, mem1, 8, GADDR(0), SIDA_OFFSET(0x1c0)); + TEST_ASSERT(rv == -1 && errno == EINVAL, + "ioctl does not reject SIDA_WRITE in non-protected mode"); + + kvm_vm_free(t.kvm_vm); +} - kvm_vm_free(vm); +int main(int argc, char *argv[]) +{ + int memop_cap, extension_cap; + + setbuf(stdout, NULL); /* Tell stdout not to buffer its content */ + + memop_cap = kvm_check_cap(KVM_CAP_S390_MEM_OP); + extension_cap = kvm_check_cap(KVM_CAP_S390_MEM_OP_EXTENSION); + if (!memop_cap) { + print_skip("CAP_S390_MEM_OP not supported"); + exit(KSFT_SKIP); + } + + test_copy(); + if (extension_cap > 0) { + test_copy_key(); + test_copy_key_storage_prot_override(); + test_copy_key_fetch_prot(); + test_copy_key_fetch_prot_override(); + test_errors_key(); + test_errors_key_storage_prot_override(); + test_errors_key_fetch_prot_override_not_enabled(); + test_errors_key_fetch_prot_override_enabled(); + } else { + print_skip("storage key memop extension not supported"); + } + test_errors(); return 0; } diff --git a/tools/testing/selftests/kvm/s390x/tprot.c b/tools/testing/selftests/kvm/s390x/tprot.c new file mode 100644 index 000000000000..c097b9db495e --- /dev/null +++ b/tools/testing/selftests/kvm/s390x/tprot.c @@ -0,0 +1,227 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Test TEST PROTECTION emulation. + * + * Copyright IBM Corp. 2021 + */ + +#include <sys/mman.h> +#include "test_util.h" +#include "kvm_util.h" + +#define PAGE_SHIFT 12 +#define PAGE_SIZE (1 << PAGE_SHIFT) +#define CR0_FETCH_PROTECTION_OVERRIDE (1UL << (63 - 38)) +#define CR0_STORAGE_PROTECTION_OVERRIDE (1UL << (63 - 39)) + +#define VCPU_ID 1 + +static __aligned(PAGE_SIZE) uint8_t pages[2][PAGE_SIZE]; +static uint8_t *const page_store_prot = pages[0]; +static uint8_t *const page_fetch_prot = pages[1]; + +/* Nonzero return value indicates that address not mapped */ +static int set_storage_key(void *addr, uint8_t key) +{ + int not_mapped = 0; + + asm volatile ( + "lra %[addr], 0(0,%[addr])\n" + " jz 0f\n" + " llill %[not_mapped],1\n" + " j 1f\n" + "0: sske %[key], %[addr]\n" + "1:" + : [addr] "+&a" (addr), [not_mapped] "+r" (not_mapped) + : [key] "r" (key) + : "cc" + ); + return -not_mapped; +} + +enum permission { + READ_WRITE = 0, + READ = 1, + RW_PROTECTED = 2, + TRANSL_UNAVAIL = 3, +}; + +static enum permission test_protection(void *addr, uint8_t key) +{ + uint64_t mask; + + asm volatile ( + "tprot %[addr], 0(%[key])\n" + " ipm %[mask]\n" + : [mask] "=r" (mask) + : [addr] "Q" (*(char *)addr), + [key] "a" (key) + : "cc" + ); + + return (enum permission)(mask >> 28); +} + +enum stage { + STAGE_END, + STAGE_INIT_SIMPLE, + TEST_SIMPLE, + STAGE_INIT_FETCH_PROT_OVERRIDE, + TEST_FETCH_PROT_OVERRIDE, + TEST_STORAGE_PROT_OVERRIDE, +}; + +struct test { + enum stage stage; + void *addr; + uint8_t key; + enum permission expected; +} tests[] = { + /* + * We perform each test in the array by executing TEST PROTECTION on + * the specified addr with the specified key and checking if the returned + * permissions match the expected value. + * Both guest and host cooperate to set up the required test conditions. + * A central condition is that the page targeted by addr has to be DAT + * protected in the host mappings, in order for KVM to emulate the + * TEST PROTECTION instruction. + * Since the page tables are shared, the host uses mprotect to achieve + * this. + * + * Test resulting in RW_PROTECTED/TRANSL_UNAVAIL will be interpreted + * by SIE, not KVM, but there is no harm in testing them also. + * See Enhanced Suppression-on-Protection Facilities in the + * Interpretive-Execution Mode + */ + /* + * guest: set storage key of page_store_prot to 1 + * storage key of page_fetch_prot to 9 and enable + * protection for it + * STAGE_INIT_SIMPLE + * host: write protect both via mprotect + */ + /* access key 0 matches any storage key -> RW */ + { TEST_SIMPLE, page_store_prot, 0x00, READ_WRITE }, + /* access key matches storage key -> RW */ + { TEST_SIMPLE, page_store_prot, 0x10, READ_WRITE }, + /* mismatched keys, but no fetch protection -> RO */ + { TEST_SIMPLE, page_store_prot, 0x20, READ }, + /* access key 0 matches any storage key -> RW */ + { TEST_SIMPLE, page_fetch_prot, 0x00, READ_WRITE }, + /* access key matches storage key -> RW */ + { TEST_SIMPLE, page_fetch_prot, 0x90, READ_WRITE }, + /* mismatched keys, fetch protection -> inaccessible */ + { TEST_SIMPLE, page_fetch_prot, 0x10, RW_PROTECTED }, + /* page 0 not mapped yet -> translation not available */ + { TEST_SIMPLE, (void *)0x00, 0x10, TRANSL_UNAVAIL }, + /* + * host: try to map page 0 + * guest: set storage key of page 0 to 9 and enable fetch protection + * STAGE_INIT_FETCH_PROT_OVERRIDE + * host: write protect page 0 + * enable fetch protection override + */ + /* mismatched keys, fetch protection, but override applies -> RO */ + { TEST_FETCH_PROT_OVERRIDE, (void *)0x00, 0x10, READ }, + /* mismatched keys, fetch protection, override applies to 0-2048 only -> inaccessible */ + { TEST_FETCH_PROT_OVERRIDE, (void *)2049, 0x10, RW_PROTECTED }, + /* + * host: enable storage protection override + */ + /* mismatched keys, but override applies (storage key 9) -> RW */ + { TEST_STORAGE_PROT_OVERRIDE, page_fetch_prot, 0x10, READ_WRITE }, + /* mismatched keys, no fetch protection, override doesn't apply -> RO */ + { TEST_STORAGE_PROT_OVERRIDE, page_store_prot, 0x20, READ }, + /* mismatched keys, but override applies (storage key 9) -> RW */ + { TEST_STORAGE_PROT_OVERRIDE, (void *)2049, 0x10, READ_WRITE }, + /* end marker */ + { STAGE_END, 0, 0, 0 }, +}; + +static enum stage perform_next_stage(int *i, bool mapped_0) +{ + enum stage stage = tests[*i].stage; + enum permission result; + bool skip; + + for (; tests[*i].stage == stage; (*i)++) { + /* + * Some fetch protection override tests require that page 0 + * be mapped, however, when the hosts tries to map that page via + * vm_vaddr_alloc, it may happen that some other page gets mapped + * instead. + * In order to skip these tests we detect this inside the guest + */ + skip = tests[*i].addr < (void *)4096 && + tests[*i].expected != TRANSL_UNAVAIL && + !mapped_0; + if (!skip) { + result = test_protection(tests[*i].addr, tests[*i].key); + GUEST_ASSERT_2(result == tests[*i].expected, *i, result); + } + } + return stage; +} + +static void guest_code(void) +{ + bool mapped_0; + int i = 0; + + GUEST_ASSERT_EQ(set_storage_key(page_store_prot, 0x10), 0); + GUEST_ASSERT_EQ(set_storage_key(page_fetch_prot, 0x98), 0); + GUEST_SYNC(STAGE_INIT_SIMPLE); + GUEST_SYNC(perform_next_stage(&i, false)); + + /* Fetch-protection override */ + mapped_0 = !set_storage_key((void *)0, 0x98); + GUEST_SYNC(STAGE_INIT_FETCH_PROT_OVERRIDE); + GUEST_SYNC(perform_next_stage(&i, mapped_0)); + + /* Storage-protection override */ + GUEST_SYNC(perform_next_stage(&i, mapped_0)); +} + +#define HOST_SYNC(vmp, stage) \ +({ \ + struct kvm_vm *__vm = (vmp); \ + struct ucall uc; \ + int __stage = (stage); \ + \ + vcpu_run(__vm, VCPU_ID); \ + get_ucall(__vm, VCPU_ID, &uc); \ + if (uc.cmd == UCALL_ABORT) { \ + TEST_FAIL("line %lu: %s, hints: %lu, %lu", uc.args[1], \ + (const char *)uc.args[0], uc.args[2], uc.args[3]); \ + } \ + ASSERT_EQ(uc.cmd, UCALL_SYNC); \ + ASSERT_EQ(uc.args[1], __stage); \ +}) + +int main(int argc, char *argv[]) +{ + struct kvm_vm *vm; + struct kvm_run *run; + vm_vaddr_t guest_0_page; + + vm = vm_create_default(VCPU_ID, 0, guest_code); + run = vcpu_state(vm, VCPU_ID); + + HOST_SYNC(vm, STAGE_INIT_SIMPLE); + mprotect(addr_gva2hva(vm, (vm_vaddr_t)pages), PAGE_SIZE * 2, PROT_READ); + HOST_SYNC(vm, TEST_SIMPLE); + + guest_0_page = vm_vaddr_alloc(vm, PAGE_SIZE, 0); + if (guest_0_page != 0) + print_skip("Did not allocate page at 0 for fetch protection override tests"); + HOST_SYNC(vm, STAGE_INIT_FETCH_PROT_OVERRIDE); + if (guest_0_page == 0) + mprotect(addr_gva2hva(vm, (vm_vaddr_t)0), PAGE_SIZE, PROT_READ); + run->s.regs.crs[0] |= CR0_FETCH_PROTECTION_OVERRIDE; + run->kvm_dirty_regs = KVM_SYNC_CRS; + HOST_SYNC(vm, TEST_FETCH_PROT_OVERRIDE); + + run->s.regs.crs[0] |= CR0_STORAGE_PROTECTION_OVERRIDE; + run->kvm_dirty_regs = KVM_SYNC_CRS; + HOST_SYNC(vm, TEST_STORAGE_PROT_OVERRIDE); +} diff --git a/tools/testing/selftests/kvm/set_memory_region_test.c b/tools/testing/selftests/kvm/set_memory_region_test.c index 72a1c9b4882c..73bc297dabe6 100644 --- a/tools/testing/selftests/kvm/set_memory_region_test.c +++ b/tools/testing/selftests/kvm/set_memory_region_test.c @@ -329,22 +329,6 @@ static void test_zero_memory_regions(void) } #endif /* __x86_64__ */ -static int test_memory_region_add(struct kvm_vm *vm, void *mem, uint32_t slot, - uint32_t size, uint64_t guest_addr) -{ - struct kvm_userspace_memory_region region; - int ret; - - region.slot = slot; - region.flags = 0; - region.guest_phys_addr = guest_addr; - region.memory_size = size; - region.userspace_addr = (uintptr_t) mem; - ret = ioctl(vm_get_fd(vm), KVM_SET_USER_MEMORY_REGION, ®ion); - - return ret; -} - /* * Test it can be added memory slots up to KVM_CAP_NR_MEMSLOTS, then any * tentative to add further slots should fail. @@ -382,23 +366,20 @@ static void test_add_max_memory_regions(void) TEST_ASSERT(mem != MAP_FAILED, "Failed to mmap() host"); mem_aligned = (void *)(((size_t) mem + alignment - 1) & ~(alignment - 1)); - for (slot = 0; slot < max_mem_slots; slot++) { - ret = test_memory_region_add(vm, mem_aligned + - ((uint64_t)slot * MEM_REGION_SIZE), - slot, MEM_REGION_SIZE, - (uint64_t)slot * MEM_REGION_SIZE); - TEST_ASSERT(ret == 0, "KVM_SET_USER_MEMORY_REGION IOCTL failed,\n" - " rc: %i errno: %i slot: %i\n", - ret, errno, slot); - } + for (slot = 0; slot < max_mem_slots; slot++) + vm_set_user_memory_region(vm, slot, 0, + ((uint64_t)slot * MEM_REGION_SIZE), + MEM_REGION_SIZE, + mem_aligned + (uint64_t)slot * MEM_REGION_SIZE); /* Check it cannot be added memory slots beyond the limit */ mem_extra = mmap(NULL, MEM_REGION_SIZE, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); TEST_ASSERT(mem_extra != MAP_FAILED, "Failed to mmap() host"); - ret = test_memory_region_add(vm, mem_extra, max_mem_slots, MEM_REGION_SIZE, - (uint64_t)max_mem_slots * MEM_REGION_SIZE); + ret = __vm_set_user_memory_region(vm, max_mem_slots, 0, + (uint64_t)max_mem_slots * MEM_REGION_SIZE, + MEM_REGION_SIZE, mem_extra); TEST_ASSERT(ret == -1 && errno == EINVAL, "Adding one more memory slot should fail with EINVAL"); diff --git a/tools/testing/selftests/kvm/x86_64/amx_test.c b/tools/testing/selftests/kvm/x86_64/amx_test.c new file mode 100644 index 000000000000..52a3ef6629e8 --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/amx_test.c @@ -0,0 +1,450 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * amx tests + * + * Copyright (C) 2021, Intel, Inc. + * + * Tests for amx #NM exception and save/restore. + */ + +#define _GNU_SOURCE /* for program_invocation_short_name */ +#include <fcntl.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/ioctl.h> +#include <sys/syscall.h> + +#include "test_util.h" + +#include "kvm_util.h" +#include "processor.h" +#include "vmx.h" + +#ifndef __x86_64__ +# error This test is 64-bit only +#endif + +#define VCPU_ID 0 +#define X86_FEATURE_XSAVE (1 << 26) +#define X86_FEATURE_OSXSAVE (1 << 27) + +#define PAGE_SIZE (1 << 12) +#define NUM_TILES 8 +#define TILE_SIZE 1024 +#define XSAVE_SIZE ((NUM_TILES * TILE_SIZE) + PAGE_SIZE) + +/* Tile configuration associated: */ +#define MAX_TILES 16 +#define RESERVED_BYTES 14 + +#define XFEATURE_XTILECFG 17 +#define XFEATURE_XTILEDATA 18 +#define XFEATURE_MASK_XTILECFG (1 << XFEATURE_XTILECFG) +#define XFEATURE_MASK_XTILEDATA (1 << XFEATURE_XTILEDATA) +#define XFEATURE_MASK_XTILE (XFEATURE_MASK_XTILECFG | XFEATURE_MASK_XTILEDATA) + +#define TILE_CPUID 0x1d +#define XSTATE_CPUID 0xd +#define TILE_PALETTE_CPUID_SUBLEAVE 0x1 +#define XSTATE_USER_STATE_SUBLEAVE 0x0 + +#define XSAVE_HDR_OFFSET 512 + +struct xsave_data { + u8 area[XSAVE_SIZE]; +} __aligned(64); + +struct tile_config { + u8 palette_id; + u8 start_row; + u8 reserved[RESERVED_BYTES]; + u16 colsb[MAX_TILES]; + u8 rows[MAX_TILES]; +}; + +struct tile_data { + u8 data[NUM_TILES * TILE_SIZE]; +}; + +struct xtile_info { + u16 bytes_per_tile; + u16 bytes_per_row; + u16 max_names; + u16 max_rows; + u32 xsave_offset; + u32 xsave_size; +}; + +static struct xtile_info xtile; + +static inline u64 __xgetbv(u32 index) +{ + u32 eax, edx; + + asm volatile("xgetbv;" + : "=a" (eax), "=d" (edx) + : "c" (index)); + return eax + ((u64)edx << 32); +} + +static inline void __xsetbv(u32 index, u64 value) +{ + u32 eax = value; + u32 edx = value >> 32; + + asm volatile("xsetbv" :: "a" (eax), "d" (edx), "c" (index)); +} + +static inline void __ldtilecfg(void *cfg) +{ + asm volatile(".byte 0xc4,0xe2,0x78,0x49,0x00" + : : "a"(cfg)); +} + +static inline void __tileloadd(void *tile) +{ + asm volatile(".byte 0xc4,0xe2,0x7b,0x4b,0x04,0x10" + : : "a"(tile), "d"(0)); +} + +static inline void __tilerelease(void) +{ + asm volatile(".byte 0xc4, 0xe2, 0x78, 0x49, 0xc0" ::); +} + +static inline void __xsavec(struct xsave_data *data, uint64_t rfbm) +{ + uint32_t rfbm_lo = rfbm; + uint32_t rfbm_hi = rfbm >> 32; + + asm volatile("xsavec (%%rdi)" + : : "D" (data), "a" (rfbm_lo), "d" (rfbm_hi) + : "memory"); +} + +static inline void check_cpuid_xsave(void) +{ + uint32_t eax, ebx, ecx, edx; + + eax = 1; + ecx = 0; + cpuid(&eax, &ebx, &ecx, &edx); + if (!(ecx & X86_FEATURE_XSAVE)) + GUEST_ASSERT(!"cpuid: no CPU xsave support!"); + if (!(ecx & X86_FEATURE_OSXSAVE)) + GUEST_ASSERT(!"cpuid: no OS xsave support!"); +} + +static bool check_xsave_supports_xtile(void) +{ + return __xgetbv(0) & XFEATURE_MASK_XTILE; +} + +static bool enum_xtile_config(void) +{ + u32 eax, ebx, ecx, edx; + + eax = TILE_CPUID; + ecx = TILE_PALETTE_CPUID_SUBLEAVE; + + cpuid(&eax, &ebx, &ecx, &edx); + if (!eax || !ebx || !ecx) + return false; + + xtile.max_names = ebx >> 16; + if (xtile.max_names < NUM_TILES) + return false; + + xtile.bytes_per_tile = eax >> 16; + if (xtile.bytes_per_tile < TILE_SIZE) + return false; + + xtile.bytes_per_row = ebx; + xtile.max_rows = ecx; + + return true; +} + +static bool enum_xsave_tile(void) +{ + u32 eax, ebx, ecx, edx; + + eax = XSTATE_CPUID; + ecx = XFEATURE_XTILEDATA; + + cpuid(&eax, &ebx, &ecx, &edx); + if (!eax || !ebx) + return false; + + xtile.xsave_offset = ebx; + xtile.xsave_size = eax; + + return true; +} + +static bool check_xsave_size(void) +{ + u32 eax, ebx, ecx, edx; + bool valid = false; + + eax = XSTATE_CPUID; + ecx = XSTATE_USER_STATE_SUBLEAVE; + + cpuid(&eax, &ebx, &ecx, &edx); + if (ebx && ebx <= XSAVE_SIZE) + valid = true; + + return valid; +} + +static bool check_xtile_info(void) +{ + bool ret = false; + + if (!check_xsave_size()) + return ret; + + if (!enum_xsave_tile()) + return ret; + + if (!enum_xtile_config()) + return ret; + + if (sizeof(struct tile_data) >= xtile.xsave_size) + ret = true; + + return ret; +} + +static void set_tilecfg(struct tile_config *cfg) +{ + int i; + + /* Only palette id 1 */ + cfg->palette_id = 1; + for (i = 0; i < xtile.max_names; i++) { + cfg->colsb[i] = xtile.bytes_per_row; + cfg->rows[i] = xtile.max_rows; + } +} + +static void set_xstatebv(void *data, uint64_t bv) +{ + *(uint64_t *)(data + XSAVE_HDR_OFFSET) = bv; +} + +static u64 get_xstatebv(void *data) +{ + return *(u64 *)(data + XSAVE_HDR_OFFSET); +} + +static void init_regs(void) +{ + uint64_t cr4, xcr0; + + /* turn on CR4.OSXSAVE */ + cr4 = get_cr4(); + cr4 |= X86_CR4_OSXSAVE; + set_cr4(cr4); + + xcr0 = __xgetbv(0); + xcr0 |= XFEATURE_MASK_XTILE; + __xsetbv(0x0, xcr0); +} + +static void __attribute__((__flatten__)) guest_code(struct tile_config *amx_cfg, + struct tile_data *tiledata, + struct xsave_data *xsave_data) +{ + init_regs(); + check_cpuid_xsave(); + GUEST_ASSERT(check_xsave_supports_xtile()); + GUEST_ASSERT(check_xtile_info()); + + /* check xtile configs */ + GUEST_ASSERT(xtile.xsave_offset == 2816); + GUEST_ASSERT(xtile.xsave_size == 8192); + GUEST_ASSERT(xtile.max_names == 8); + GUEST_ASSERT(xtile.bytes_per_tile == 1024); + GUEST_ASSERT(xtile.bytes_per_row == 64); + GUEST_ASSERT(xtile.max_rows == 16); + GUEST_SYNC(1); + + /* xfd=0, enable amx */ + wrmsr(MSR_IA32_XFD, 0); + GUEST_SYNC(2); + GUEST_ASSERT(rdmsr(MSR_IA32_XFD) == 0); + set_tilecfg(amx_cfg); + __ldtilecfg(amx_cfg); + GUEST_SYNC(3); + /* Check save/restore when trap to userspace */ + __tileloadd(tiledata); + GUEST_SYNC(4); + __tilerelease(); + GUEST_SYNC(5); + /* bit 18 not in the XCOMP_BV after xsavec() */ + set_xstatebv(xsave_data, XFEATURE_MASK_XTILEDATA); + __xsavec(xsave_data, XFEATURE_MASK_XTILEDATA); + GUEST_ASSERT((get_xstatebv(xsave_data) & XFEATURE_MASK_XTILEDATA) == 0); + + /* xfd=0x40000, disable amx tiledata */ + wrmsr(MSR_IA32_XFD, XFEATURE_MASK_XTILEDATA); + GUEST_SYNC(6); + GUEST_ASSERT(rdmsr(MSR_IA32_XFD) == XFEATURE_MASK_XTILEDATA); + set_tilecfg(amx_cfg); + __ldtilecfg(amx_cfg); + /* Trigger #NM exception */ + __tileloadd(tiledata); + GUEST_SYNC(10); + + GUEST_DONE(); +} + +void guest_nm_handler(struct ex_regs *regs) +{ + /* Check if #NM is triggered by XFEATURE_MASK_XTILEDATA */ + GUEST_SYNC(7); + GUEST_ASSERT(rdmsr(MSR_IA32_XFD_ERR) == XFEATURE_MASK_XTILEDATA); + GUEST_SYNC(8); + GUEST_ASSERT(rdmsr(MSR_IA32_XFD_ERR) == XFEATURE_MASK_XTILEDATA); + /* Clear xfd_err */ + wrmsr(MSR_IA32_XFD_ERR, 0); + /* xfd=0, enable amx */ + wrmsr(MSR_IA32_XFD, 0); + GUEST_SYNC(9); +} + +int main(int argc, char *argv[]) +{ + struct kvm_cpuid_entry2 *entry; + struct kvm_regs regs1, regs2; + bool amx_supported = false; + struct kvm_vm *vm; + struct kvm_run *run; + struct kvm_x86_state *state; + int xsave_restore_size = 0; + vm_vaddr_t amx_cfg, tiledata, xsavedata; + struct ucall uc; + u32 amx_offset; + int stage, ret; + + vm_xsave_req_perm(XSTATE_XTILE_DATA_BIT); + + /* Create VM */ + vm = vm_create_default(VCPU_ID, 0, guest_code); + + entry = kvm_get_supported_cpuid_entry(1); + if (!(entry->ecx & X86_FEATURE_XSAVE)) { + print_skip("XSAVE feature not supported"); + exit(KSFT_SKIP); + } + + if (kvm_get_cpuid_max_basic() >= 0xd) { + entry = kvm_get_supported_cpuid_index(0xd, 0); + amx_supported = entry && !!(entry->eax & XFEATURE_MASK_XTILE); + if (!amx_supported) { + print_skip("AMX is not supported by the vCPU (eax=0x%x)", entry->eax); + exit(KSFT_SKIP); + } + /* Get xsave/restore max size */ + xsave_restore_size = entry->ecx; + } + + run = vcpu_state(vm, VCPU_ID); + vcpu_regs_get(vm, VCPU_ID, ®s1); + + /* Register #NM handler */ + vm_init_descriptor_tables(vm); + vcpu_init_descriptor_tables(vm, VCPU_ID); + vm_install_exception_handler(vm, NM_VECTOR, guest_nm_handler); + + /* amx cfg for guest_code */ + amx_cfg = vm_vaddr_alloc_page(vm); + memset(addr_gva2hva(vm, amx_cfg), 0x0, getpagesize()); + + /* amx tiledata for guest_code */ + tiledata = vm_vaddr_alloc_pages(vm, 2); + memset(addr_gva2hva(vm, tiledata), rand() | 1, 2 * getpagesize()); + + /* xsave data for guest_code */ + xsavedata = vm_vaddr_alloc_pages(vm, 3); + memset(addr_gva2hva(vm, xsavedata), 0, 3 * getpagesize()); + vcpu_args_set(vm, VCPU_ID, 3, amx_cfg, tiledata, xsavedata); + + for (stage = 1; ; stage++) { + _vcpu_run(vm, VCPU_ID); + TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, + "Stage %d: unexpected exit reason: %u (%s),\n", + stage, run->exit_reason, + exit_reason_str(run->exit_reason)); + + switch (get_ucall(vm, VCPU_ID, &uc)) { + case UCALL_ABORT: + TEST_FAIL("%s at %s:%ld", (const char *)uc.args[0], + __FILE__, uc.args[1]); + /* NOT REACHED */ + case UCALL_SYNC: + switch (uc.args[1]) { + case 1: + case 2: + case 3: + case 5: + case 6: + case 7: + case 8: + fprintf(stderr, "GUEST_SYNC(%ld)\n", uc.args[1]); + break; + case 4: + case 10: + fprintf(stderr, + "GUEST_SYNC(%ld), check save/restore status\n", uc.args[1]); + + /* Compacted mode, get amx offset by xsave area + * size subtract 8K amx size. + */ + amx_offset = xsave_restore_size - NUM_TILES*TILE_SIZE; + state = vcpu_save_state(vm, VCPU_ID); + void *amx_start = (void *)state->xsave + amx_offset; + void *tiles_data = (void *)addr_gva2hva(vm, tiledata); + /* Only check TMM0 register, 1 tile */ + ret = memcmp(amx_start, tiles_data, TILE_SIZE); + TEST_ASSERT(ret == 0, "memcmp failed, ret=%d\n", ret); + kvm_x86_state_cleanup(state); + break; + case 9: + fprintf(stderr, + "GUEST_SYNC(%ld), #NM exception and enable amx\n", uc.args[1]); + break; + } + break; + case UCALL_DONE: + fprintf(stderr, "UCALL_DONE\n"); + goto done; + default: + TEST_FAIL("Unknown ucall %lu", uc.cmd); + } + + state = vcpu_save_state(vm, VCPU_ID); + memset(®s1, 0, sizeof(regs1)); + vcpu_regs_get(vm, VCPU_ID, ®s1); + + kvm_vm_release(vm); + + /* Restore state in a new VM. */ + kvm_vm_restart(vm, O_RDWR); + vm_vcpu_add(vm, VCPU_ID); + vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); + vcpu_load_state(vm, VCPU_ID, state); + run = vcpu_state(vm, VCPU_ID); + kvm_x86_state_cleanup(state); + + memset(®s2, 0, sizeof(regs2)); + vcpu_regs_get(vm, VCPU_ID, ®s2); + TEST_ASSERT(!memcmp(®s1, ®s2, sizeof(regs2)), + "Unexpected register values after vcpu_load_state; rdi: %lx rsi: %lx", + (ulong) regs2.rdi, (ulong) regs2.rsi); + } +done: + kvm_vm_free(vm); +} diff --git a/tools/testing/selftests/kvm/x86_64/get_cpuid_test.c b/tools/testing/selftests/kvm/x86_64/cpuid_test.c index a711f83749ea..16d2465c5634 100644 --- a/tools/testing/selftests/kvm/x86_64/get_cpuid_test.c +++ b/tools/testing/selftests/kvm/x86_64/cpuid_test.c @@ -154,6 +154,34 @@ struct kvm_cpuid2 *vcpu_alloc_cpuid(struct kvm_vm *vm, vm_vaddr_t *p_gva, struct return guest_cpuids; } +static void set_cpuid_after_run(struct kvm_vm *vm, struct kvm_cpuid2 *cpuid) +{ + struct kvm_cpuid_entry2 *ent; + int rc; + u32 eax, ebx, x; + + /* Setting unmodified CPUID is allowed */ + rc = __vcpu_set_cpuid(vm, VCPU_ID, cpuid); + TEST_ASSERT(!rc, "Setting unmodified CPUID after KVM_RUN failed: %d", rc); + + /* Changing CPU features is forbidden */ + ent = get_cpuid(cpuid, 0x7, 0); + ebx = ent->ebx; + ent->ebx--; + rc = __vcpu_set_cpuid(vm, VCPU_ID, cpuid); + TEST_ASSERT(rc, "Changing CPU features should fail"); + ent->ebx = ebx; + + /* Changing MAXPHYADDR is forbidden */ + ent = get_cpuid(cpuid, 0x80000008, 0); + eax = ent->eax; + x = eax & 0xff; + ent->eax = (eax & ~0xffu) | (x - 1); + rc = __vcpu_set_cpuid(vm, VCPU_ID, cpuid); + TEST_ASSERT(rc, "Changing MAXPHYADDR should fail"); + ent->eax = eax; +} + int main(void) { struct kvm_cpuid2 *supp_cpuid, *cpuid2; @@ -175,5 +203,7 @@ int main(void) for (stage = 0; stage < 3; stage++) run_vcpu(vm, VCPU_ID, stage); + set_cpuid_after_run(vm, cpuid2); + kvm_vm_free(vm); } diff --git a/tools/testing/selftests/kvm/x86_64/evmcs_test.c b/tools/testing/selftests/kvm/x86_64/evmcs_test.c index 2b46dcca86a8..d12e043aa2ee 100644 --- a/tools/testing/selftests/kvm/x86_64/evmcs_test.c +++ b/tools/testing/selftests/kvm/x86_64/evmcs_test.c @@ -10,6 +10,7 @@ #include <stdlib.h> #include <string.h> #include <sys/ioctl.h> +#include <linux/bitmap.h> #include "test_util.h" @@ -32,6 +33,22 @@ static void guest_nmi_handler(struct ex_regs *regs) { } +/* Exits to L1 destroy GRPs! */ +static inline void rdmsr_fs_base(void) +{ + __asm__ __volatile__ ("mov $0xc0000100, %%rcx; rdmsr" : : : + "rax", "rbx", "rcx", "rdx", + "rsi", "rdi", "r8", "r9", "r10", "r11", "r12", + "r13", "r14", "r15"); +} +static inline void rdmsr_gs_base(void) +{ + __asm__ __volatile__ ("mov $0xc0000101, %%rcx; rdmsr" : : : + "rax", "rbx", "rcx", "rdx", + "rsi", "rdi", "r8", "r9", "r10", "r11", "r12", + "r13", "r14", "r15"); +} + void l2_guest_code(void) { GUEST_SYNC(7); @@ -41,6 +58,15 @@ void l2_guest_code(void) /* Forced exit to L1 upon restore */ GUEST_SYNC(9); + vmcall(); + + /* MSR-Bitmap tests */ + rdmsr_fs_base(); /* intercepted */ + rdmsr_fs_base(); /* intercepted */ + rdmsr_gs_base(); /* not intercepted */ + vmcall(); + rdmsr_gs_base(); /* intercepted */ + /* Done, exit to L1 and never come back. */ vmcall(); } @@ -76,8 +102,9 @@ void guest_code(struct vmx_pages *vmx_pages) current_evmcs->revision_id = EVMCS_VERSION; GUEST_SYNC(6); - current_evmcs->pin_based_vm_exec_control |= - PIN_BASED_NMI_EXITING; + vmwrite(PIN_BASED_VM_EXEC_CONTROL, vmreadz(PIN_BASED_VM_EXEC_CONTROL) | + PIN_BASED_NMI_EXITING); + GUEST_ASSERT(!vmlaunch()); GUEST_ASSERT(vmptrstz() == vmx_pages->enlightened_vmcs_gpa); @@ -91,6 +118,39 @@ void guest_code(struct vmx_pages *vmx_pages) GUEST_SYNC(10); GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL); + current_evmcs->guest_rip += 3; /* vmcall */ + + /* Intercept RDMSR 0xc0000100 */ + vmwrite(CPU_BASED_VM_EXEC_CONTROL, vmreadz(CPU_BASED_VM_EXEC_CONTROL) | + CPU_BASED_USE_MSR_BITMAPS); + set_bit(MSR_FS_BASE & 0x1fff, vmx_pages->msr + 0x400); + GUEST_ASSERT(!vmresume()); + GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_MSR_READ); + current_evmcs->guest_rip += 2; /* rdmsr */ + + /* Enable enlightened MSR bitmap */ + current_evmcs->hv_enlightenments_control.msr_bitmap = 1; + GUEST_ASSERT(!vmresume()); + GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_MSR_READ); + current_evmcs->guest_rip += 2; /* rdmsr */ + + /* Intercept RDMSR 0xc0000101 without telling KVM about it */ + set_bit(MSR_GS_BASE & 0x1fff, vmx_pages->msr + 0x400); + /* Make sure HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP is set */ + current_evmcs->hv_clean_fields |= HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP; + GUEST_ASSERT(!vmresume()); + /* Make sure we don't see EXIT_REASON_MSR_READ here so eMSR bitmap works */ + GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL); + current_evmcs->guest_rip += 3; /* vmcall */ + + /* Now tell KVM we've changed MSR-Bitmap */ + current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP; + GUEST_ASSERT(!vmresume()); + GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_MSR_READ); + current_evmcs->guest_rip += 2; /* rdmsr */ + + GUEST_ASSERT(!vmresume()); + GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL); GUEST_SYNC(11); /* Try enlightened vmptrld with an incorrect GPA */ @@ -129,7 +189,7 @@ static void save_restore_vm(struct kvm_vm *vm) vcpu_set_hv_cpuid(vm, VCPU_ID); vcpu_enable_evmcs(vm, VCPU_ID); vcpu_load_state(vm, VCPU_ID, state); - free(state); + kvm_x86_state_cleanup(state); memset(®s2, 0, sizeof(regs2)); vcpu_regs_get(vm, VCPU_ID, ®s2); diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c b/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c index 7e2d2d17d2ed..8c245ab2d98a 100644 --- a/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c +++ b/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c @@ -49,16 +49,13 @@ static void test_hv_cpuid(struct kvm_cpuid2 *hv_cpuid_entries, bool evmcs_expected) { int i; - int nent = 9; + int nent_expected = 10; u32 test_val; - if (evmcs_expected) - nent += 1; /* 0x4000000A */ - - TEST_ASSERT(hv_cpuid_entries->nent == nent, + TEST_ASSERT(hv_cpuid_entries->nent == nent_expected, "KVM_GET_SUPPORTED_HV_CPUID should return %d entries" - " with evmcs=%d (returned %d)", - nent, evmcs_expected, hv_cpuid_entries->nent); + " (returned %d)", + nent_expected, hv_cpuid_entries->nent); for (i = 0; i < hv_cpuid_entries->nent; i++) { struct kvm_cpuid_entry2 *entry = &hv_cpuid_entries->entries[i]; @@ -68,9 +65,6 @@ static void test_hv_cpuid(struct kvm_cpuid2 *hv_cpuid_entries, "function %x is our of supported range", entry->function); - TEST_ASSERT(evmcs_expected || (entry->function != 0x4000000A), - "0x4000000A leaf should not be reported"); - TEST_ASSERT(entry->index == 0, ".index field should be zero"); @@ -97,8 +91,20 @@ static void test_hv_cpuid(struct kvm_cpuid2 *hv_cpuid_entries, "NoNonArchitecturalCoreSharing bit" " doesn't reflect SMT setting"); break; - } + case 0x4000000A: + TEST_ASSERT(entry->eax & (1UL << 19), + "Enlightened MSR-Bitmap should always be supported" + " 0x40000000.EAX: %x", entry->eax); + if (evmcs_expected) + TEST_ASSERT((entry->eax & 0xffff) == 0x101, + "Supported Enlightened VMCS version range is supposed to be 1:1" + " 0x40000000.EAX: %x", entry->eax); + + break; + default: + break; + } /* * If needed for debug: * fprintf(stdout, @@ -107,7 +113,6 @@ static void test_hv_cpuid(struct kvm_cpuid2 *hv_cpuid_entries, * entry->edx); */ } - } void test_hv_cpuid_e2big(struct kvm_vm *vm, bool system) diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_svm_test.c b/tools/testing/selftests/kvm/x86_64/hyperv_svm_test.c new file mode 100644 index 000000000000..21f5ca9197da --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/hyperv_svm_test.c @@ -0,0 +1,175 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * KVM_GET/SET_* tests + * + * Copyright (C) 2022, Red Hat, Inc. + * + * Tests for Hyper-V extensions to SVM. + */ +#define _GNU_SOURCE /* for program_invocation_short_name */ +#include <fcntl.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/ioctl.h> +#include <linux/bitmap.h> + +#include "test_util.h" + +#include "kvm_util.h" +#include "processor.h" +#include "svm_util.h" +#include "hyperv.h" + +#define VCPU_ID 1 +#define L2_GUEST_STACK_SIZE 256 + +struct hv_enlightenments { + struct __packed hv_enlightenments_control { + u32 nested_flush_hypercall:1; + u32 msr_bitmap:1; + u32 enlightened_npt_tlb: 1; + u32 reserved:29; + } __packed hv_enlightenments_control; + u32 hv_vp_id; + u64 hv_vm_id; + u64 partition_assist_page; + u64 reserved; +} __packed; + +/* + * Hyper-V uses the software reserved clean bit in VMCB + */ +#define VMCB_HV_NESTED_ENLIGHTENMENTS (1U << 31) + +static inline void vmmcall(void) +{ + __asm__ __volatile__("vmmcall"); +} + +void l2_guest_code(void) +{ + GUEST_SYNC(3); + /* Exit to L1 */ + vmmcall(); + + /* MSR-Bitmap tests */ + rdmsr(MSR_FS_BASE); /* intercepted */ + rdmsr(MSR_FS_BASE); /* intercepted */ + rdmsr(MSR_GS_BASE); /* not intercepted */ + vmmcall(); + rdmsr(MSR_GS_BASE); /* intercepted */ + + GUEST_SYNC(5); + + /* Done, exit to L1 and never come back. */ + vmmcall(); +} + +static void __attribute__((__flatten__)) guest_code(struct svm_test_data *svm) +{ + unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; + struct vmcb *vmcb = svm->vmcb; + struct hv_enlightenments *hve = + (struct hv_enlightenments *)vmcb->control.reserved_sw; + + GUEST_SYNC(1); + + wrmsr(HV_X64_MSR_GUEST_OS_ID, (u64)0x8100 << 48); + + GUEST_ASSERT(svm->vmcb_gpa); + /* Prepare for L2 execution. */ + generic_svm_setup(svm, l2_guest_code, + &l2_guest_stack[L2_GUEST_STACK_SIZE]); + + GUEST_SYNC(2); + run_guest(vmcb, svm->vmcb_gpa); + GUEST_ASSERT(vmcb->control.exit_code == SVM_EXIT_VMMCALL); + GUEST_SYNC(4); + vmcb->save.rip += 3; + + /* Intercept RDMSR 0xc0000100 */ + vmcb->control.intercept |= 1ULL << INTERCEPT_MSR_PROT; + set_bit(2 * (MSR_FS_BASE & 0x1fff), svm->msr + 0x800); + run_guest(vmcb, svm->vmcb_gpa); + GUEST_ASSERT(vmcb->control.exit_code == SVM_EXIT_MSR); + vmcb->save.rip += 2; /* rdmsr */ + + /* Enable enlightened MSR bitmap */ + hve->hv_enlightenments_control.msr_bitmap = 1; + run_guest(vmcb, svm->vmcb_gpa); + GUEST_ASSERT(vmcb->control.exit_code == SVM_EXIT_MSR); + vmcb->save.rip += 2; /* rdmsr */ + + /* Intercept RDMSR 0xc0000101 without telling KVM about it */ + set_bit(2 * (MSR_GS_BASE & 0x1fff), svm->msr + 0x800); + /* Make sure HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP is set */ + vmcb->control.clean |= VMCB_HV_NESTED_ENLIGHTENMENTS; + run_guest(vmcb, svm->vmcb_gpa); + /* Make sure we don't see SVM_EXIT_MSR here so eMSR bitmap works */ + GUEST_ASSERT(vmcb->control.exit_code == SVM_EXIT_VMMCALL); + vmcb->save.rip += 3; /* vmcall */ + + /* Now tell KVM we've changed MSR-Bitmap */ + vmcb->control.clean &= ~VMCB_HV_NESTED_ENLIGHTENMENTS; + run_guest(vmcb, svm->vmcb_gpa); + GUEST_ASSERT(vmcb->control.exit_code == SVM_EXIT_MSR); + vmcb->save.rip += 2; /* rdmsr */ + + run_guest(vmcb, svm->vmcb_gpa); + GUEST_ASSERT(vmcb->control.exit_code == SVM_EXIT_VMMCALL); + GUEST_SYNC(6); + + GUEST_DONE(); +} + +int main(int argc, char *argv[]) +{ + vm_vaddr_t nested_gva = 0; + + struct kvm_vm *vm; + struct kvm_run *run; + struct ucall uc; + int stage; + + if (!nested_svm_supported()) { + print_skip("Nested SVM not supported"); + exit(KSFT_SKIP); + } + /* Create VM */ + vm = vm_create_default(VCPU_ID, 0, guest_code); + vcpu_set_hv_cpuid(vm, VCPU_ID); + run = vcpu_state(vm, VCPU_ID); + vcpu_alloc_svm(vm, &nested_gva); + vcpu_args_set(vm, VCPU_ID, 1, nested_gva); + + for (stage = 1;; stage++) { + _vcpu_run(vm, VCPU_ID); + TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, + "Stage %d: unexpected exit reason: %u (%s),\n", + stage, run->exit_reason, + exit_reason_str(run->exit_reason)); + + switch (get_ucall(vm, VCPU_ID, &uc)) { + case UCALL_ABORT: + TEST_FAIL("%s at %s:%ld", (const char *)uc.args[0], + __FILE__, uc.args[1]); + /* NOT REACHED */ + case UCALL_SYNC: + break; + case UCALL_DONE: + goto done; + default: + TEST_FAIL("Unknown ucall %lu", uc.cmd); + } + + /* UCALL_SYNC is handled here. */ + TEST_ASSERT(!strcmp((const char *)uc.args[0], "hello") && + uc.args[1] == stage, "Stage %d: Unexpected register values vmexit, got %lx", + stage, (ulong)uc.args[1]); + + } + +done: + kvm_vm_free(vm); +} diff --git a/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c b/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c new file mode 100644 index 000000000000..0d06ffa95d9d --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c @@ -0,0 +1,467 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Test for x86 KVM_SET_PMU_EVENT_FILTER. + * + * Copyright (C) 2022, Google LLC. + * + * This work is licensed under the terms of the GNU GPL, version 2. + * + * Verifies the expected behavior of allow lists and deny lists for + * virtual PMU events. + */ + +#define _GNU_SOURCE /* for program_invocation_short_name */ +#include "test_util.h" +#include "kvm_util.h" +#include "processor.h" + +/* + * In lieu of copying perf_event.h into tools... + */ +#define ARCH_PERFMON_EVENTSEL_OS (1ULL << 17) +#define ARCH_PERFMON_EVENTSEL_ENABLE (1ULL << 22) + +union cpuid10_eax { + struct { + unsigned int version_id:8; + unsigned int num_counters:8; + unsigned int bit_width:8; + unsigned int mask_length:8; + } split; + unsigned int full; +}; + +union cpuid10_ebx { + struct { + unsigned int no_unhalted_core_cycles:1; + unsigned int no_instructions_retired:1; + unsigned int no_unhalted_reference_cycles:1; + unsigned int no_llc_reference:1; + unsigned int no_llc_misses:1; + unsigned int no_branch_instruction_retired:1; + unsigned int no_branch_misses_retired:1; + } split; + unsigned int full; +}; + +/* End of stuff taken from perf_event.h. */ + +/* Oddly, this isn't in perf_event.h. */ +#define ARCH_PERFMON_BRANCHES_RETIRED 5 + +#define VCPU_ID 0 +#define NUM_BRANCHES 42 + +/* + * This is how the event selector and unit mask are stored in an AMD + * core performance event-select register. Intel's format is similar, + * but the event selector is only 8 bits. + */ +#define EVENT(select, umask) ((select & 0xf00UL) << 24 | (select & 0xff) | \ + (umask & 0xff) << 8) + +/* + * "Branch instructions retired", from the Intel SDM, volume 3, + * "Pre-defined Architectural Performance Events." + */ + +#define INTEL_BR_RETIRED EVENT(0xc4, 0) + +/* + * "Retired branch instructions", from Processor Programming Reference + * (PPR) for AMD Family 17h Model 01h, Revision B1 Processors, + * Preliminary Processor Programming Reference (PPR) for AMD Family + * 17h Model 31h, Revision B0 Processors, and Preliminary Processor + * Programming Reference (PPR) for AMD Family 19h Model 01h, Revision + * B1 Processors Volume 1 of 2. + */ + +#define AMD_ZEN_BR_RETIRED EVENT(0xc2, 0) + +/* + * This event list comprises Intel's eight architectural events plus + * AMD's "retired branch instructions" for Zen[123] (and possibly + * other AMD CPUs). + */ +static const uint64_t event_list[] = { + EVENT(0x3c, 0), + EVENT(0xc0, 0), + EVENT(0x3c, 1), + EVENT(0x2e, 0x4f), + EVENT(0x2e, 0x41), + EVENT(0xc4, 0), + EVENT(0xc5, 0), + EVENT(0xa4, 1), + AMD_ZEN_BR_RETIRED, +}; + +/* + * If we encounter a #GP during the guest PMU sanity check, then the guest + * PMU is not functional. Inform the hypervisor via GUEST_SYNC(0). + */ +static void guest_gp_handler(struct ex_regs *regs) +{ + GUEST_SYNC(0); +} + +/* + * Check that we can write a new value to the given MSR and read it back. + * The caller should provide a non-empty set of bits that are safe to flip. + * + * Return on success. GUEST_SYNC(0) on error. + */ +static void check_msr(uint32_t msr, uint64_t bits_to_flip) +{ + uint64_t v = rdmsr(msr) ^ bits_to_flip; + + wrmsr(msr, v); + if (rdmsr(msr) != v) + GUEST_SYNC(0); + + v ^= bits_to_flip; + wrmsr(msr, v); + if (rdmsr(msr) != v) + GUEST_SYNC(0); +} + +static void intel_guest_code(void) +{ + check_msr(MSR_CORE_PERF_GLOBAL_CTRL, 1); + check_msr(MSR_P6_EVNTSEL0, 0xffff); + check_msr(MSR_IA32_PMC0, 0xffff); + GUEST_SYNC(1); + + for (;;) { + uint64_t br0, br1; + + wrmsr(MSR_CORE_PERF_GLOBAL_CTRL, 0); + wrmsr(MSR_P6_EVNTSEL0, ARCH_PERFMON_EVENTSEL_ENABLE | + ARCH_PERFMON_EVENTSEL_OS | INTEL_BR_RETIRED); + wrmsr(MSR_CORE_PERF_GLOBAL_CTRL, 1); + br0 = rdmsr(MSR_IA32_PMC0); + __asm__ __volatile__("loop ." : "+c"((int){NUM_BRANCHES})); + br1 = rdmsr(MSR_IA32_PMC0); + GUEST_SYNC(br1 - br0); + } +} + +/* + * To avoid needing a check for CPUID.80000001:ECX.PerfCtrExtCore[bit 23], + * this code uses the always-available, legacy K7 PMU MSRs, which alias to + * the first four of the six extended core PMU MSRs. + */ +static void amd_guest_code(void) +{ + check_msr(MSR_K7_EVNTSEL0, 0xffff); + check_msr(MSR_K7_PERFCTR0, 0xffff); + GUEST_SYNC(1); + + for (;;) { + uint64_t br0, br1; + + wrmsr(MSR_K7_EVNTSEL0, 0); + wrmsr(MSR_K7_EVNTSEL0, ARCH_PERFMON_EVENTSEL_ENABLE | + ARCH_PERFMON_EVENTSEL_OS | AMD_ZEN_BR_RETIRED); + br0 = rdmsr(MSR_K7_PERFCTR0); + __asm__ __volatile__("loop ." : "+c"((int){NUM_BRANCHES})); + br1 = rdmsr(MSR_K7_PERFCTR0); + GUEST_SYNC(br1 - br0); + } +} + +/* + * Run the VM to the next GUEST_SYNC(value), and return the value passed + * to the sync. Any other exit from the guest is fatal. + */ +static uint64_t run_vm_to_sync(struct kvm_vm *vm) +{ + struct kvm_run *run = vcpu_state(vm, VCPU_ID); + struct ucall uc; + + vcpu_run(vm, VCPU_ID); + TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, + "Exit_reason other than KVM_EXIT_IO: %u (%s)\n", + run->exit_reason, + exit_reason_str(run->exit_reason)); + get_ucall(vm, VCPU_ID, &uc); + TEST_ASSERT(uc.cmd == UCALL_SYNC, + "Received ucall other than UCALL_SYNC: %lu", uc.cmd); + return uc.args[1]; +} + +/* + * In a nested environment or if the vPMU is disabled, the guest PMU + * might not work as architected (accessing the PMU MSRs may raise + * #GP, or writes could simply be discarded). In those situations, + * there is no point in running these tests. The guest code will perform + * a sanity check and then GUEST_SYNC(success). In the case of failure, + * the behavior of the guest on resumption is undefined. + */ +static bool sanity_check_pmu(struct kvm_vm *vm) +{ + bool success; + + vm_install_exception_handler(vm, GP_VECTOR, guest_gp_handler); + success = run_vm_to_sync(vm); + vm_install_exception_handler(vm, GP_VECTOR, NULL); + + return success; +} + +static struct kvm_pmu_event_filter *make_pmu_event_filter(uint32_t nevents) +{ + struct kvm_pmu_event_filter *f; + int size = sizeof(*f) + nevents * sizeof(f->events[0]); + + f = malloc(size); + TEST_ASSERT(f, "Out of memory"); + memset(f, 0, size); + f->nevents = nevents; + return f; +} + +static struct kvm_pmu_event_filter *event_filter(uint32_t action) +{ + struct kvm_pmu_event_filter *f; + int i; + + f = make_pmu_event_filter(ARRAY_SIZE(event_list)); + f->action = action; + for (i = 0; i < ARRAY_SIZE(event_list); i++) + f->events[i] = event_list[i]; + + return f; +} + +/* + * Remove the first occurrence of 'event' (if any) from the filter's + * event list. + */ +static struct kvm_pmu_event_filter *remove_event(struct kvm_pmu_event_filter *f, + uint64_t event) +{ + bool found = false; + int i; + + for (i = 0; i < f->nevents; i++) { + if (found) + f->events[i - 1] = f->events[i]; + else + found = f->events[i] == event; + } + if (found) + f->nevents--; + return f; +} + +static void test_without_filter(struct kvm_vm *vm) +{ + uint64_t count = run_vm_to_sync(vm); + + if (count != NUM_BRANCHES) + pr_info("%s: Branch instructions retired = %lu (expected %u)\n", + __func__, count, NUM_BRANCHES); + TEST_ASSERT(count, "Allowed PMU event is not counting"); +} + +static uint64_t test_with_filter(struct kvm_vm *vm, + struct kvm_pmu_event_filter *f) +{ + vm_ioctl(vm, KVM_SET_PMU_EVENT_FILTER, (void *)f); + return run_vm_to_sync(vm); +} + +static void test_member_deny_list(struct kvm_vm *vm) +{ + struct kvm_pmu_event_filter *f = event_filter(KVM_PMU_EVENT_DENY); + uint64_t count = test_with_filter(vm, f); + + free(f); + if (count) + pr_info("%s: Branch instructions retired = %lu (expected 0)\n", + __func__, count); + TEST_ASSERT(!count, "Disallowed PMU Event is counting"); +} + +static void test_member_allow_list(struct kvm_vm *vm) +{ + struct kvm_pmu_event_filter *f = event_filter(KVM_PMU_EVENT_ALLOW); + uint64_t count = test_with_filter(vm, f); + + free(f); + if (count != NUM_BRANCHES) + pr_info("%s: Branch instructions retired = %lu (expected %u)\n", + __func__, count, NUM_BRANCHES); + TEST_ASSERT(count, "Allowed PMU event is not counting"); +} + +static void test_not_member_deny_list(struct kvm_vm *vm) +{ + struct kvm_pmu_event_filter *f = event_filter(KVM_PMU_EVENT_DENY); + uint64_t count; + + remove_event(f, INTEL_BR_RETIRED); + remove_event(f, AMD_ZEN_BR_RETIRED); + count = test_with_filter(vm, f); + free(f); + if (count != NUM_BRANCHES) + pr_info("%s: Branch instructions retired = %lu (expected %u)\n", + __func__, count, NUM_BRANCHES); + TEST_ASSERT(count, "Allowed PMU event is not counting"); +} + +static void test_not_member_allow_list(struct kvm_vm *vm) +{ + struct kvm_pmu_event_filter *f = event_filter(KVM_PMU_EVENT_ALLOW); + uint64_t count; + + remove_event(f, INTEL_BR_RETIRED); + remove_event(f, AMD_ZEN_BR_RETIRED); + count = test_with_filter(vm, f); + free(f); + if (count) + pr_info("%s: Branch instructions retired = %lu (expected 0)\n", + __func__, count); + TEST_ASSERT(!count, "Disallowed PMU Event is counting"); +} + +/* + * Verify that setting KVM_PMU_CAP_DISABLE prevents the use of the PMU. + * + * Note that KVM_CAP_PMU_CAPABILITY must be invoked prior to creating VCPUs. + */ +static void test_pmu_config_disable(void (*guest_code)(void)) +{ + int r; + struct kvm_vm *vm; + struct kvm_enable_cap cap = { 0 }; + + r = kvm_check_cap(KVM_CAP_PMU_CAPABILITY); + if (!(r & KVM_PMU_CAP_DISABLE)) + return; + + vm = vm_create_without_vcpus(VM_MODE_DEFAULT, DEFAULT_GUEST_PHY_PAGES); + + cap.cap = KVM_CAP_PMU_CAPABILITY; + cap.args[0] = KVM_PMU_CAP_DISABLE; + TEST_ASSERT(!vm_enable_cap(vm, &cap), "Failed to set KVM_PMU_CAP_DISABLE."); + + vm_vcpu_add_default(vm, VCPU_ID, guest_code); + vm_init_descriptor_tables(vm); + vcpu_init_descriptor_tables(vm, VCPU_ID); + + TEST_ASSERT(!sanity_check_pmu(vm), + "Guest should not be able to use disabled PMU."); + + kvm_vm_free(vm); +} + +/* + * Check for a non-zero PMU version, at least one general-purpose + * counter per logical processor, an EBX bit vector of length greater + * than 5, and EBX[5] clear. + */ +static bool check_intel_pmu_leaf(struct kvm_cpuid_entry2 *entry) +{ + union cpuid10_eax eax = { .full = entry->eax }; + union cpuid10_ebx ebx = { .full = entry->ebx }; + + return eax.split.version_id && eax.split.num_counters > 0 && + eax.split.mask_length > ARCH_PERFMON_BRANCHES_RETIRED && + !ebx.split.no_branch_instruction_retired; +} + +/* + * Note that CPUID leaf 0xa is Intel-specific. This leaf should be + * clear on AMD hardware. + */ +static bool use_intel_pmu(void) +{ + struct kvm_cpuid_entry2 *entry; + + entry = kvm_get_supported_cpuid_index(0xa, 0); + return is_intel_cpu() && entry && check_intel_pmu_leaf(entry); +} + +static bool is_zen1(uint32_t eax) +{ + return x86_family(eax) == 0x17 && x86_model(eax) <= 0x0f; +} + +static bool is_zen2(uint32_t eax) +{ + return x86_family(eax) == 0x17 && + x86_model(eax) >= 0x30 && x86_model(eax) <= 0x3f; +} + +static bool is_zen3(uint32_t eax) +{ + return x86_family(eax) == 0x19 && x86_model(eax) <= 0x0f; +} + +/* + * Determining AMD support for a PMU event requires consulting the AMD + * PPR for the CPU or reference material derived therefrom. The AMD + * test code herein has been verified to work on Zen1, Zen2, and Zen3. + * + * Feel free to add more AMD CPUs that are documented to support event + * select 0xc2 umask 0 as "retired branch instructions." + */ +static bool use_amd_pmu(void) +{ + struct kvm_cpuid_entry2 *entry; + + entry = kvm_get_supported_cpuid_index(1, 0); + return is_amd_cpu() && entry && + (is_zen1(entry->eax) || + is_zen2(entry->eax) || + is_zen3(entry->eax)); +} + +int main(int argc, char *argv[]) +{ + void (*guest_code)(void) = NULL; + struct kvm_vm *vm; + int r; + + /* Tell stdout not to buffer its content */ + setbuf(stdout, NULL); + + r = kvm_check_cap(KVM_CAP_PMU_EVENT_FILTER); + if (!r) { + print_skip("KVM_CAP_PMU_EVENT_FILTER not supported"); + exit(KSFT_SKIP); + } + + if (use_intel_pmu()) + guest_code = intel_guest_code; + else if (use_amd_pmu()) + guest_code = amd_guest_code; + + if (!guest_code) { + print_skip("Don't know how to test this guest PMU"); + exit(KSFT_SKIP); + } + + vm = vm_create_default(VCPU_ID, 0, guest_code); + + vm_init_descriptor_tables(vm); + vcpu_init_descriptor_tables(vm, VCPU_ID); + + if (!sanity_check_pmu(vm)) { + print_skip("Guest PMU is not functional"); + exit(KSFT_SKIP); + } + + test_without_filter(vm); + test_member_deny_list(vm); + test_member_allow_list(vm); + test_not_member_deny_list(vm); + test_not_member_allow_list(vm); + + kvm_vm_free(vm); + + test_pmu_config_disable(guest_code); + + return 0; +} diff --git a/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c b/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c index 29b18d565cf4..d1dc1acf997c 100644 --- a/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c +++ b/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c @@ -21,7 +21,9 @@ #define NR_LOCK_TESTING_THREADS 3 #define NR_LOCK_TESTING_ITERATIONS 10000 -static void sev_ioctl(int vm_fd, int cmd_id, void *data) +bool have_sev_es; + +static int __sev_ioctl(int vm_fd, int cmd_id, void *data, __u32 *fw_error) { struct kvm_sev_cmd cmd = { .id = cmd_id, @@ -31,9 +33,19 @@ static void sev_ioctl(int vm_fd, int cmd_id, void *data) int ret; ret = ioctl(vm_fd, KVM_MEMORY_ENCRYPT_OP, &cmd); - TEST_ASSERT((ret == 0 || cmd.error == SEV_RET_SUCCESS), + *fw_error = cmd.error; + return ret; +} + +static void sev_ioctl(int vm_fd, int cmd_id, void *data) +{ + int ret; + __u32 fw_error; + + ret = __sev_ioctl(vm_fd, cmd_id, data, &fw_error); + TEST_ASSERT(ret == 0 && fw_error == SEV_RET_SUCCESS, "%d failed: return code: %d, errno: %d, fw error: %d", - cmd_id, ret, errno, cmd.error); + cmd_id, ret, errno, fw_error); } static struct kvm_vm *sev_vm_create(bool es) @@ -162,10 +174,18 @@ static void test_sev_migrate_parameters(void) *sev_es_vm_no_vmsa; int ret; - sev_vm = sev_vm_create(/* es= */ false); - sev_es_vm = sev_vm_create(/* es= */ true); vm_no_vcpu = vm_create(VM_MODE_DEFAULT, 0, O_RDWR); vm_no_sev = aux_vm_create(true); + ret = __sev_migrate_from(vm_no_vcpu->fd, vm_no_sev->fd); + TEST_ASSERT(ret == -1 && errno == EINVAL, + "Migrations require SEV enabled. ret %d, errno: %d\n", ret, + errno); + + if (!have_sev_es) + goto out; + + sev_vm = sev_vm_create(/* es= */ false); + sev_es_vm = sev_vm_create(/* es= */ true); sev_es_vm_no_vmsa = vm_create(VM_MODE_DEFAULT, 0, O_RDWR); sev_ioctl(sev_es_vm_no_vmsa->fd, KVM_SEV_ES_INIT, NULL); vm_vcpu_add(sev_es_vm_no_vmsa, 1); @@ -194,14 +214,10 @@ static void test_sev_migrate_parameters(void) "SEV-ES migrations require UPDATE_VMSA. ret %d, errno: %d\n", ret, errno); - ret = __sev_migrate_from(vm_no_vcpu->fd, vm_no_sev->fd); - TEST_ASSERT(ret == -1 && errno == EINVAL, - "Migrations require SEV enabled. ret %d, errno: %d\n", ret, - errno); - kvm_vm_free(sev_vm); kvm_vm_free(sev_es_vm); kvm_vm_free(sev_es_vm_no_vmsa); +out: kvm_vm_free(vm_no_vcpu); kvm_vm_free(vm_no_sev); } @@ -225,12 +241,45 @@ static void sev_mirror_create(int dst_fd, int src_fd) TEST_ASSERT(!ret, "Copying context failed, ret: %d, errno: %d\n", ret, errno); } +static void verify_mirror_allowed_cmds(int vm_fd) +{ + struct kvm_sev_guest_status status; + + for (int cmd_id = KVM_SEV_INIT; cmd_id < KVM_SEV_NR_MAX; ++cmd_id) { + int ret; + __u32 fw_error; + + /* + * These commands are allowed for mirror VMs, all others are + * not. + */ + switch (cmd_id) { + case KVM_SEV_LAUNCH_UPDATE_VMSA: + case KVM_SEV_GUEST_STATUS: + case KVM_SEV_DBG_DECRYPT: + case KVM_SEV_DBG_ENCRYPT: + continue; + default: + break; + } + + /* + * These commands should be disallowed before the data + * parameter is examined so NULL is OK here. + */ + ret = __sev_ioctl(vm_fd, cmd_id, NULL, &fw_error); + TEST_ASSERT( + ret == -1 && errno == EINVAL, + "Should not be able call command: %d. ret: %d, errno: %d\n", + cmd_id, ret, errno); + } + + sev_ioctl(vm_fd, KVM_SEV_GUEST_STATUS, &status); +} + static void test_sev_mirror(bool es) { struct kvm_vm *src_vm, *dst_vm; - struct kvm_sev_launch_start start = { - .policy = es ? SEV_POLICY_ES : 0 - }; int i; src_vm = sev_vm_create(es); @@ -241,10 +290,12 @@ static void test_sev_mirror(bool es) /* Check that we can complete creation of the mirror VM. */ for (i = 0; i < NR_MIGRATE_TEST_VCPUS; ++i) vm_vcpu_add(dst_vm, i); - sev_ioctl(dst_vm->fd, KVM_SEV_LAUNCH_START, &start); + if (es) sev_ioctl(dst_vm->fd, KVM_SEV_LAUNCH_UPDATE_VMSA, NULL); + verify_mirror_allowed_cmds(dst_vm->fd); + kvm_vm_free(src_vm); kvm_vm_free(dst_vm); } @@ -255,7 +306,6 @@ static void test_sev_mirror_parameters(void) int ret; sev_vm = sev_vm_create(/* es= */ false); - sev_es_vm = sev_vm_create(/* es= */ true); vm_with_vcpu = aux_vm_create(true); vm_no_vcpu = aux_vm_create(false); @@ -265,6 +315,21 @@ static void test_sev_mirror_parameters(void) "Should not be able copy context to self. ret: %d, errno: %d\n", ret, errno); + ret = __sev_mirror_create(vm_no_vcpu->fd, vm_with_vcpu->fd); + TEST_ASSERT(ret == -1 && errno == EINVAL, + "Copy context requires SEV enabled. ret %d, errno: %d\n", ret, + errno); + + ret = __sev_mirror_create(vm_with_vcpu->fd, sev_vm->fd); + TEST_ASSERT( + ret == -1 && errno == EINVAL, + "SEV copy context requires no vCPUS on the destination. ret: %d, errno: %d\n", + ret, errno); + + if (!have_sev_es) + goto out; + + sev_es_vm = sev_vm_create(/* es= */ true); ret = __sev_mirror_create(sev_vm->fd, sev_es_vm->fd); TEST_ASSERT( ret == -1 && errno == EINVAL, @@ -277,63 +342,97 @@ static void test_sev_mirror_parameters(void) "Should not be able copy context to SEV-ES enabled VM. ret: %d, errno: %d\n", ret, errno); - ret = __sev_mirror_create(vm_no_vcpu->fd, vm_with_vcpu->fd); - TEST_ASSERT(ret == -1 && errno == EINVAL, - "Copy context requires SEV enabled. ret %d, errno: %d\n", ret, - errno); - - ret = __sev_mirror_create(vm_with_vcpu->fd, sev_vm->fd); - TEST_ASSERT( - ret == -1 && errno == EINVAL, - "SEV copy context requires no vCPUS on the destination. ret: %d, errno: %d\n", - ret, errno); + kvm_vm_free(sev_es_vm); +out: kvm_vm_free(sev_vm); - kvm_vm_free(sev_es_vm); kvm_vm_free(vm_with_vcpu); kvm_vm_free(vm_no_vcpu); } static void test_sev_move_copy(void) { - struct kvm_vm *dst_vm, *sev_vm, *mirror_vm, *dst_mirror_vm; - int ret; + struct kvm_vm *dst_vm, *dst2_vm, *dst3_vm, *sev_vm, *mirror_vm, + *dst_mirror_vm, *dst2_mirror_vm, *dst3_mirror_vm; sev_vm = sev_vm_create(/* es= */ false); dst_vm = aux_vm_create(true); + dst2_vm = aux_vm_create(true); + dst3_vm = aux_vm_create(true); mirror_vm = aux_vm_create(false); dst_mirror_vm = aux_vm_create(false); + dst2_mirror_vm = aux_vm_create(false); + dst3_mirror_vm = aux_vm_create(false); sev_mirror_create(mirror_vm->fd, sev_vm->fd); - ret = __sev_migrate_from(dst_vm->fd, sev_vm->fd); - TEST_ASSERT(ret == -1 && errno == EBUSY, - "Cannot migrate VM that has mirrors. ret %d, errno: %d\n", ret, - errno); - /* The mirror itself can be migrated. */ sev_migrate_from(dst_mirror_vm->fd, mirror_vm->fd); - ret = __sev_migrate_from(dst_vm->fd, sev_vm->fd); - TEST_ASSERT(ret == -1 && errno == EBUSY, - "Cannot migrate VM that has mirrors. ret %d, errno: %d\n", ret, - errno); + sev_migrate_from(dst_vm->fd, sev_vm->fd); + + sev_migrate_from(dst2_vm->fd, dst_vm->fd); + sev_migrate_from(dst2_mirror_vm->fd, dst_mirror_vm->fd); + + sev_migrate_from(dst3_mirror_vm->fd, dst2_mirror_vm->fd); + sev_migrate_from(dst3_vm->fd, dst2_vm->fd); + + kvm_vm_free(dst_vm); + kvm_vm_free(sev_vm); + kvm_vm_free(dst2_vm); + kvm_vm_free(dst3_vm); + kvm_vm_free(mirror_vm); + kvm_vm_free(dst_mirror_vm); + kvm_vm_free(dst2_mirror_vm); + kvm_vm_free(dst3_mirror_vm); /* - * mirror_vm is not a mirror anymore, dst_mirror_vm is. Thus, - * the owner can be copied as soon as dst_mirror_vm is gone. + * Run similar test be destroy mirrors before mirrored VMs to ensure + * destruction is done safely. */ - kvm_vm_free(dst_mirror_vm); + sev_vm = sev_vm_create(/* es= */ false); + dst_vm = aux_vm_create(true); + mirror_vm = aux_vm_create(false); + dst_mirror_vm = aux_vm_create(false); + + sev_mirror_create(mirror_vm->fd, sev_vm->fd); + + sev_migrate_from(dst_mirror_vm->fd, mirror_vm->fd); sev_migrate_from(dst_vm->fd, sev_vm->fd); kvm_vm_free(mirror_vm); + kvm_vm_free(dst_mirror_vm); kvm_vm_free(dst_vm); kvm_vm_free(sev_vm); } +#define X86_FEATURE_SEV (1 << 1) +#define X86_FEATURE_SEV_ES (1 << 3) + int main(int argc, char *argv[]) { + struct kvm_cpuid_entry2 *cpuid; + + if (!kvm_check_cap(KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM) && + !kvm_check_cap(KVM_CAP_VM_COPY_ENC_CONTEXT_FROM)) { + print_skip("Capabilities not available"); + exit(KSFT_SKIP); + } + + cpuid = kvm_get_supported_cpuid_entry(0x80000000); + if (cpuid->eax < 0x8000001f) { + print_skip("AMD memory encryption not available"); + exit(KSFT_SKIP); + } + cpuid = kvm_get_supported_cpuid_entry(0x8000001f); + if (!(cpuid->eax & X86_FEATURE_SEV)) { + print_skip("AMD SEV not available"); + exit(KSFT_SKIP); + } + have_sev_es = !!(cpuid->eax & X86_FEATURE_SEV_ES); + if (kvm_check_cap(KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM)) { test_sev_migrate_from(/* es= */ false); - test_sev_migrate_from(/* es= */ true); + if (have_sev_es) + test_sev_migrate_from(/* es= */ true); test_sev_migrate_locking(); test_sev_migrate_parameters(); if (kvm_check_cap(KVM_CAP_VM_COPY_ENC_CONTEXT_FROM)) @@ -341,7 +440,8 @@ int main(int argc, char *argv[]) } if (kvm_check_cap(KVM_CAP_VM_COPY_ENC_CONTEXT_FROM)) { test_sev_mirror(/* es= */ false); - test_sev_mirror(/* es= */ true); + if (have_sev_es) + test_sev_mirror(/* es= */ true); test_sev_mirror_parameters(); } return 0; diff --git a/tools/testing/selftests/kvm/x86_64/smm_test.c b/tools/testing/selftests/kvm/x86_64/smm_test.c index d0fe2fdce58c..a626d40fdb48 100644 --- a/tools/testing/selftests/kvm/x86_64/smm_test.c +++ b/tools/testing/selftests/kvm/x86_64/smm_test.c @@ -105,7 +105,6 @@ static void guest_code(void *arg) if (cpu_has_svm()) { run_guest(svm->vmcb, svm->vmcb_gpa); - svm->vmcb->save.rip += 3; run_guest(svm->vmcb, svm->vmcb_gpa); } else { vmlaunch(); @@ -212,7 +211,7 @@ int main(int argc, char *argv[]) vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); vcpu_load_state(vm, VCPU_ID, state); run = vcpu_state(vm, VCPU_ID); - free(state); + kvm_x86_state_cleanup(state); } done: diff --git a/tools/testing/selftests/kvm/x86_64/state_test.c b/tools/testing/selftests/kvm/x86_64/state_test.c index 32854c1462ad..2e0a92da8ff5 100644 --- a/tools/testing/selftests/kvm/x86_64/state_test.c +++ b/tools/testing/selftests/kvm/x86_64/state_test.c @@ -218,7 +218,7 @@ int main(int argc, char *argv[]) vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); vcpu_load_state(vm, VCPU_ID, state); run = vcpu_state(vm, VCPU_ID); - free(state); + kvm_x86_state_cleanup(state); memset(®s2, 0, sizeof(regs2)); vcpu_regs_get(vm, VCPU_ID, ®s2); diff --git a/tools/testing/selftests/kvm/x86_64/tsc_msrs_test.c b/tools/testing/selftests/kvm/x86_64/tsc_msrs_test.c index 5a6a662f2e59..a426078b16a3 100644 --- a/tools/testing/selftests/kvm/x86_64/tsc_msrs_test.c +++ b/tools/testing/selftests/kvm/x86_64/tsc_msrs_test.c @@ -77,8 +77,8 @@ static void run_vcpu(struct kvm_vm *vm, uint32_t vcpuid, int stage) switch (get_ucall(vm, vcpuid, &uc)) { case UCALL_SYNC: TEST_ASSERT(!strcmp((const char *)uc.args[0], "hello") && - uc.args[1] == stage + 1, "Stage %d: Unexpected register values vmexit, got %lx", - stage + 1, (ulong)uc.args[1]); + uc.args[1] == stage + 1, "Stage %d: Unexpected register values vmexit, got %lx", + stage + 1, (ulong)uc.args[1]); return; case UCALL_DONE: return; diff --git a/tools/testing/selftests/kvm/x86_64/vmx_close_while_nested_test.c b/tools/testing/selftests/kvm/x86_64/vmx_close_while_nested_test.c index 2835a17f1b7a..edac8839e717 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_close_while_nested_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_close_while_nested_test.c @@ -30,8 +30,8 @@ static struct kvm_vm *vm; static void l2_guest_code(void) { /* Exit to L0 */ - asm volatile("inb %%dx, %%al" - : : [port] "d" (PORT_L0_EXIT) : "rax"); + asm volatile("inb %%dx, %%al" + : : [port] "d" (PORT_L0_EXIT) : "rax"); } static void l1_guest_code(struct vmx_pages *vmx_pages) diff --git a/tools/testing/selftests/kvm/x86_64/vmx_exception_with_invalid_guest_state.c b/tools/testing/selftests/kvm/x86_64/vmx_exception_with_invalid_guest_state.c new file mode 100644 index 000000000000..27a850f3d7ce --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/vmx_exception_with_invalid_guest_state.c @@ -0,0 +1,139 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include "test_util.h" +#include "kvm_util.h" +#include "processor.h" + +#include <signal.h> +#include <string.h> +#include <sys/ioctl.h> +#include <sys/time.h> + +#include "kselftest.h" + +#define VCPU_ID 0 + +static struct kvm_vm *vm; + +static void guest_ud_handler(struct ex_regs *regs) +{ + /* Loop on the ud2 until guest state is made invalid. */ +} + +static void guest_code(void) +{ + asm volatile("ud2"); +} + +static void __run_vcpu_with_invalid_state(void) +{ + struct kvm_run *run = vcpu_state(vm, VCPU_ID); + + vcpu_run(vm, VCPU_ID); + + TEST_ASSERT(run->exit_reason == KVM_EXIT_INTERNAL_ERROR, + "Expected KVM_EXIT_INTERNAL_ERROR, got %d (%s)\n", + run->exit_reason, exit_reason_str(run->exit_reason)); + TEST_ASSERT(run->emulation_failure.suberror == KVM_INTERNAL_ERROR_EMULATION, + "Expected emulation failure, got %d\n", + run->emulation_failure.suberror); +} + +static void run_vcpu_with_invalid_state(void) +{ + /* + * Always run twice to verify KVM handles the case where _KVM_ queues + * an exception with invalid state and then exits to userspace, i.e. + * that KVM doesn't explode if userspace ignores the initial error. + */ + __run_vcpu_with_invalid_state(); + __run_vcpu_with_invalid_state(); +} + +static void set_timer(void) +{ + struct itimerval timer; + + timer.it_value.tv_sec = 0; + timer.it_value.tv_usec = 200; + timer.it_interval = timer.it_value; + ASSERT_EQ(setitimer(ITIMER_REAL, &timer, NULL), 0); +} + +static void set_or_clear_invalid_guest_state(bool set) +{ + static struct kvm_sregs sregs; + + if (!sregs.cr0) + vcpu_sregs_get(vm, VCPU_ID, &sregs); + sregs.tr.unusable = !!set; + vcpu_sregs_set(vm, VCPU_ID, &sregs); +} + +static void set_invalid_guest_state(void) +{ + set_or_clear_invalid_guest_state(true); +} + +static void clear_invalid_guest_state(void) +{ + set_or_clear_invalid_guest_state(false); +} + +static void sigalrm_handler(int sig) +{ + struct kvm_vcpu_events events; + + TEST_ASSERT(sig == SIGALRM, "Unexpected signal = %d", sig); + + vcpu_events_get(vm, VCPU_ID, &events); + + /* + * If an exception is pending, attempt KVM_RUN with invalid guest, + * otherwise rearm the timer and keep doing so until the timer fires + * between KVM queueing an exception and re-entering the guest. + */ + if (events.exception.pending) { + set_invalid_guest_state(); + run_vcpu_with_invalid_state(); + } else { + set_timer(); + } +} + +int main(int argc, char *argv[]) +{ + if (!is_intel_cpu() || vm_is_unrestricted_guest(NULL)) { + print_skip("Must be run with kvm_intel.unrestricted_guest=0"); + exit(KSFT_SKIP); + } + + vm = vm_create_default(VCPU_ID, 0, (void *)guest_code); + + vm_init_descriptor_tables(vm); + vcpu_init_descriptor_tables(vm, VCPU_ID); + + vm_install_exception_handler(vm, UD_VECTOR, guest_ud_handler); + + /* + * Stuff invalid guest state for L2 by making TR unusuable. The next + * KVM_RUN should induce a TRIPLE_FAULT in L2 as KVM doesn't support + * emulating invalid guest state for L2. + */ + set_invalid_guest_state(); + run_vcpu_with_invalid_state(); + + /* + * Verify KVM also handles the case where userspace gains control while + * an exception is pending and stuffs invalid state. Run with valid + * guest state and a timer firing every 200us, and attempt to enter the + * guest with invalid state when the handler interrupts KVM with an + * exception pending. + */ + clear_invalid_guest_state(); + TEST_ASSERT(signal(SIGALRM, sigalrm_handler) != SIG_ERR, + "Failed to register SIGALRM handler, errno = %d (%s)", + errno, strerror(errno)); + + set_timer(); + run_vcpu_with_invalid_state(); +} diff --git a/tools/testing/selftests/kvm/x86_64/vmx_preemption_timer_test.c b/tools/testing/selftests/kvm/x86_64/vmx_preemption_timer_test.c index a07480aed397..ff92e25b6f1e 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_preemption_timer_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_preemption_timer_test.c @@ -244,7 +244,7 @@ int main(int argc, char *argv[]) vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); vcpu_load_state(vm, VCPU_ID, state); run = vcpu_state(vm, VCPU_ID); - free(state); + kvm_x86_state_cleanup(state); memset(®s2, 0, sizeof(regs2)); vcpu_regs_get(vm, VCPU_ID, ®s2); diff --git a/tools/testing/selftests/kvm/x86_64/xapic_state_test.c b/tools/testing/selftests/kvm/x86_64/xapic_state_test.c new file mode 100644 index 000000000000..0792334ba243 --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/xapic_state_test.c @@ -0,0 +1,150 @@ +// SPDX-License-Identifier: GPL-2.0-only +#define _GNU_SOURCE /* for program_invocation_short_name */ +#include <fcntl.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/ioctl.h> + +#include "apic.h" +#include "kvm_util.h" +#include "processor.h" +#include "test_util.h" + +struct kvm_vcpu { + uint32_t id; + bool is_x2apic; +}; + +static void xapic_guest_code(void) +{ + asm volatile("cli"); + + xapic_enable(); + + while (1) { + uint64_t val = (u64)xapic_read_reg(APIC_IRR) | + (u64)xapic_read_reg(APIC_IRR + 0x10) << 32; + + xapic_write_reg(APIC_ICR2, val >> 32); + xapic_write_reg(APIC_ICR, val); + GUEST_SYNC(val); + } +} + +static void x2apic_guest_code(void) +{ + asm volatile("cli"); + + x2apic_enable(); + + do { + uint64_t val = x2apic_read_reg(APIC_IRR) | + x2apic_read_reg(APIC_IRR + 0x10) << 32; + + x2apic_write_reg(APIC_ICR, val); + GUEST_SYNC(val); + } while (1); +} + +static void ____test_icr(struct kvm_vm *vm, struct kvm_vcpu *vcpu, uint64_t val) +{ + struct kvm_lapic_state xapic; + struct ucall uc; + uint64_t icr; + + /* + * Tell the guest what ICR value to write. Use the IRR to pass info, + * all bits are valid and should not be modified by KVM (ignoring the + * fact that vectors 0-15 are technically illegal). + */ + vcpu_ioctl(vm, vcpu->id, KVM_GET_LAPIC, &xapic); + *((u32 *)&xapic.regs[APIC_IRR]) = val; + *((u32 *)&xapic.regs[APIC_IRR + 0x10]) = val >> 32; + vcpu_ioctl(vm, vcpu->id, KVM_SET_LAPIC, &xapic); + + vcpu_run(vm, vcpu->id); + ASSERT_EQ(get_ucall(vm, vcpu->id, &uc), UCALL_SYNC); + ASSERT_EQ(uc.args[1], val); + + vcpu_ioctl(vm, vcpu->id, KVM_GET_LAPIC, &xapic); + icr = (u64)(*((u32 *)&xapic.regs[APIC_ICR])) | + (u64)(*((u32 *)&xapic.regs[APIC_ICR2])) << 32; + if (!vcpu->is_x2apic) + val &= (-1u | (0xffull << (32 + 24))); + ASSERT_EQ(icr, val & ~APIC_ICR_BUSY); +} + +static void __test_icr(struct kvm_vm *vm, struct kvm_vcpu *vcpu, uint64_t val) +{ + ____test_icr(vm, vcpu, val | APIC_ICR_BUSY); + ____test_icr(vm, vcpu, val & ~(u64)APIC_ICR_BUSY); +} + +static void test_icr(struct kvm_vm *vm, struct kvm_vcpu *vcpu) +{ + uint64_t icr, i, j; + + icr = APIC_DEST_SELF | APIC_INT_ASSERT | APIC_DM_FIXED; + for (i = 0; i <= 0xff; i++) + __test_icr(vm, vcpu, icr | i); + + icr = APIC_INT_ASSERT | APIC_DM_FIXED; + for (i = 0; i <= 0xff; i++) + __test_icr(vm, vcpu, icr | i); + + /* + * Send all flavors of IPIs to non-existent vCPUs. TODO: use number of + * vCPUs, not vcpu.id + 1. Arbitrarily use vector 0xff. + */ + icr = APIC_INT_ASSERT | 0xff; + for (i = vcpu->id + 1; i < 0xff; i++) { + for (j = 0; j < 8; j++) + __test_icr(vm, vcpu, i << (32 + 24) | APIC_INT_ASSERT | (j << 8)); + } + + /* And again with a shorthand destination for all types of IPIs. */ + icr = APIC_DEST_ALLBUT | APIC_INT_ASSERT; + for (i = 0; i < 8; i++) + __test_icr(vm, vcpu, icr | (i << 8)); + + /* And a few garbage value, just make sure it's an IRQ (blocked). */ + __test_icr(vm, vcpu, 0xa5a5a5a5a5a5a5a5 & ~APIC_DM_FIXED_MASK); + __test_icr(vm, vcpu, 0x5a5a5a5a5a5a5a5a & ~APIC_DM_FIXED_MASK); + __test_icr(vm, vcpu, -1ull & ~APIC_DM_FIXED_MASK); +} + +int main(int argc, char *argv[]) +{ + struct kvm_vcpu vcpu = { + .id = 0, + .is_x2apic = true, + }; + struct kvm_cpuid2 *cpuid; + struct kvm_vm *vm; + int i; + + vm = vm_create_default(vcpu.id, 0, x2apic_guest_code); + test_icr(vm, &vcpu); + kvm_vm_free(vm); + + /* + * Use a second VM for the xAPIC test so that x2APIC can be hidden from + * the guest in order to test AVIC. KVM disallows changing CPUID after + * KVM_RUN and AVIC is disabled if _any_ vCPU is allowed to use x2APIC. + */ + vm = vm_create_default(vcpu.id, 0, xapic_guest_code); + vcpu.is_x2apic = false; + + cpuid = vcpu_get_cpuid(vm, vcpu.id); + for (i = 0; i < cpuid->nent; i++) { + if (cpuid->entries[i].function == 1) + break; + } + cpuid->entries[i].ecx &= ~BIT(21); + vcpu_set_cpuid(vm, vcpu.id, cpuid); + + virt_pg_map(vm, APIC_DEFAULT_GPA, APIC_DEFAULT_GPA); + test_icr(vm, &vcpu); + kvm_vm_free(vm); +} diff --git a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c index a0699f00b3d6..865e17146815 100644 --- a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c +++ b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c @@ -14,6 +14,9 @@ #include <stdint.h> #include <time.h> #include <sched.h> +#include <signal.h> + +#include <sys/eventfd.h> #define VCPU_ID 5 @@ -22,10 +25,15 @@ #define SHINFO_REGION_SLOT 10 #define PAGE_SIZE 4096 +#define DUMMY_REGION_GPA (SHINFO_REGION_GPA + (2 * PAGE_SIZE)) +#define DUMMY_REGION_SLOT 11 + +#define SHINFO_ADDR (SHINFO_REGION_GPA) #define PVTIME_ADDR (SHINFO_REGION_GPA + PAGE_SIZE) #define RUNSTATE_ADDR (SHINFO_REGION_GPA + PAGE_SIZE + 0x20) #define VCPU_INFO_ADDR (SHINFO_REGION_GPA + 0x40) +#define SHINFO_VADDR (SHINFO_REGION_GVA) #define RUNSTATE_VADDR (SHINFO_REGION_GVA + PAGE_SIZE + 0x20) #define VCPU_INFO_VADDR (SHINFO_REGION_GVA + 0x40) @@ -38,20 +46,20 @@ static struct kvm_vm *vm; #define MIN_STEAL_TIME 50000 struct pvclock_vcpu_time_info { - u32 version; - u32 pad0; - u64 tsc_timestamp; - u64 system_time; - u32 tsc_to_system_mul; - s8 tsc_shift; - u8 flags; - u8 pad[2]; + u32 version; + u32 pad0; + u64 tsc_timestamp; + u64 system_time; + u32 tsc_to_system_mul; + s8 tsc_shift; + u8 flags; + u8 pad[2]; } __attribute__((__packed__)); /* 32 bytes */ struct pvclock_wall_clock { - u32 version; - u32 sec; - u32 nsec; + u32 version; + u32 sec; + u32 nsec; } __attribute__((__packed__)); struct vcpu_runstate_info { @@ -66,22 +74,44 @@ struct arch_vcpu_info { }; struct vcpu_info { - uint8_t evtchn_upcall_pending; - uint8_t evtchn_upcall_mask; - unsigned long evtchn_pending_sel; - struct arch_vcpu_info arch; - struct pvclock_vcpu_time_info time; + uint8_t evtchn_upcall_pending; + uint8_t evtchn_upcall_mask; + unsigned long evtchn_pending_sel; + struct arch_vcpu_info arch; + struct pvclock_vcpu_time_info time; }; /* 64 bytes (x86) */ +struct shared_info { + struct vcpu_info vcpu_info[32]; + unsigned long evtchn_pending[64]; + unsigned long evtchn_mask[64]; + struct pvclock_wall_clock wc; + uint32_t wc_sec_hi; + /* arch_shared_info here */ +}; + #define RUNSTATE_running 0 #define RUNSTATE_runnable 1 #define RUNSTATE_blocked 2 #define RUNSTATE_offline 3 +static const char *runstate_names[] = { + "running", + "runnable", + "blocked", + "offline" +}; + +struct { + struct kvm_irq_routing info; + struct kvm_irq_routing_entry entries[2]; +} irq_routes; + static void evtchn_handler(struct ex_regs *regs) { struct vcpu_info *vi = (void *)VCPU_INFO_VADDR; vi->evtchn_upcall_pending = 0; + vi->evtchn_pending_sel = 0; GUEST_SYNC(0x20); } @@ -127,7 +157,25 @@ static void guest_code(void) GUEST_SYNC(6); GUEST_ASSERT(rs->time[RUNSTATE_runnable] >= MIN_STEAL_TIME); - GUEST_DONE(); + /* Attempt to deliver a *masked* interrupt */ + GUEST_SYNC(7); + + /* Wait until we see the bit set */ + struct shared_info *si = (void *)SHINFO_VADDR; + while (!si->evtchn_pending[0]) + __asm__ __volatile__ ("rep nop" : : : "memory"); + + /* Now deliver an *unmasked* interrupt */ + GUEST_SYNC(8); + + while (!si->evtchn_pending[1]) + __asm__ __volatile__ ("rep nop" : : : "memory"); + + /* Change memslots and deliver an interrupt */ + GUEST_SYNC(9); + + for (;;) + __asm__ __volatile__ ("rep nop" : : : "memory"); } static int cmp_timespec(struct timespec *a, struct timespec *b) @@ -144,9 +192,18 @@ static int cmp_timespec(struct timespec *a, struct timespec *b) return 0; } +static void handle_alrm(int sig) +{ + TEST_FAIL("IRQ delivery timed out"); +} + int main(int argc, char *argv[]) { struct timespec min_ts, max_ts, vm_ts; + bool verbose; + + verbose = argc > 1 && (!strncmp(argv[1], "-v", 3) || + !strncmp(argv[1], "--verbose", 10)); int xen_caps = kvm_check_cap(KVM_CAP_XEN_HVM); if (!(xen_caps & KVM_XEN_HVM_CONFIG_SHARED_INFO) ) { @@ -155,6 +212,7 @@ int main(int argc, char *argv[]) } bool do_runstate_tests = !!(xen_caps & KVM_XEN_HVM_CONFIG_RUNSTATE); + bool do_eventfd_tests = !!(xen_caps & KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL); clock_gettime(CLOCK_REALTIME, &min_ts); @@ -166,6 +224,11 @@ int main(int argc, char *argv[]) SHINFO_REGION_GPA, SHINFO_REGION_SLOT, 2, 0); virt_map(vm, SHINFO_REGION_GVA, SHINFO_REGION_GPA, 2); + struct shared_info *shinfo = addr_gpa2hva(vm, SHINFO_VADDR); + + int zero_fd = open("/dev/zero", O_RDONLY); + TEST_ASSERT(zero_fd != -1, "Failed to open /dev/zero"); + struct kvm_xen_hvm_config hvmc = { .flags = KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL, .msr = XEN_HYPERCALL_MSR, @@ -184,6 +247,16 @@ int main(int argc, char *argv[]) }; vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &ha); + /* + * Test what happens when the HVA of the shinfo page is remapped after + * the kernel has a reference to it. But make sure we copy the clock + * info over since that's only set at setup time, and we test it later. + */ + struct pvclock_wall_clock wc_copy = shinfo->wc; + void *m = mmap(shinfo, PAGE_SIZE, PROT_READ|PROT_WRITE, MAP_FIXED|MAP_PRIVATE, zero_fd, 0); + TEST_ASSERT(m == shinfo, "Failed to map /dev/zero over shared info"); + shinfo->wc = wc_copy; + struct kvm_xen_vcpu_attr vi = { .type = KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO, .u.gpa = VCPU_INFO_ADDR, @@ -214,6 +287,49 @@ int main(int argc, char *argv[]) vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &st); } + int irq_fd[2] = { -1, -1 }; + + if (do_eventfd_tests) { + irq_fd[0] = eventfd(0, 0); + irq_fd[1] = eventfd(0, 0); + + /* Unexpected, but not a KVM failure */ + if (irq_fd[0] == -1 || irq_fd[1] == -1) + do_eventfd_tests = false; + } + + if (do_eventfd_tests) { + irq_routes.info.nr = 2; + + irq_routes.entries[0].gsi = 32; + irq_routes.entries[0].type = KVM_IRQ_ROUTING_XEN_EVTCHN; + irq_routes.entries[0].u.xen_evtchn.port = 15; + irq_routes.entries[0].u.xen_evtchn.vcpu = VCPU_ID; + irq_routes.entries[0].u.xen_evtchn.priority = KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL; + + irq_routes.entries[1].gsi = 33; + irq_routes.entries[1].type = KVM_IRQ_ROUTING_XEN_EVTCHN; + irq_routes.entries[1].u.xen_evtchn.port = 66; + irq_routes.entries[1].u.xen_evtchn.vcpu = VCPU_ID; + irq_routes.entries[1].u.xen_evtchn.priority = KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL; + + vm_ioctl(vm, KVM_SET_GSI_ROUTING, &irq_routes); + + struct kvm_irqfd ifd = { }; + + ifd.fd = irq_fd[0]; + ifd.gsi = 32; + vm_ioctl(vm, KVM_IRQFD, &ifd); + + ifd.fd = irq_fd[1]; + ifd.gsi = 33; + vm_ioctl(vm, KVM_IRQFD, &ifd); + + struct sigaction sa = { }; + sa.sa_handler = handle_alrm; + sigaction(SIGALRM, &sa, NULL); + } + struct vcpu_info *vinfo = addr_gpa2hva(vm, VCPU_INFO_VADDR); vinfo->evtchn_upcall_pending = 0; @@ -248,6 +364,8 @@ int main(int argc, char *argv[]) switch (uc.args[1]) { case 0: + if (verbose) + printf("Delivering evtchn upcall\n"); evtchn_irq_expected = true; vinfo->evtchn_upcall_pending = 1; break; @@ -256,11 +374,16 @@ int main(int argc, char *argv[]) TEST_ASSERT(!evtchn_irq_expected, "Event channel IRQ not seen"); if (!do_runstate_tests) goto done; + if (verbose) + printf("Testing runstate %s\n", runstate_names[uc.args[1]]); rst.type = KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_CURRENT; rst.u.runstate.state = uc.args[1]; vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &rst); break; + case 4: + if (verbose) + printf("Testing RUNSTATE_ADJUST\n"); rst.type = KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADJUST; memset(&rst.u, 0, sizeof(rst.u)); rst.u.runstate.state = (uint64_t)-1; @@ -274,6 +397,8 @@ int main(int argc, char *argv[]) break; case 5: + if (verbose) + printf("Testing RUNSTATE_DATA\n"); rst.type = KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_DATA; memset(&rst.u, 0, sizeof(rst.u)); rst.u.runstate.state = RUNSTATE_running; @@ -282,16 +407,54 @@ int main(int argc, char *argv[]) rst.u.runstate.time_offline = 0x5a; vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &rst); break; + case 6: + if (verbose) + printf("Testing steal time\n"); /* Yield until scheduler delay exceeds target */ rundelay = get_run_delay() + MIN_STEAL_TIME; do { sched_yield(); } while (get_run_delay() < rundelay); break; + + case 7: + if (!do_eventfd_tests) + goto done; + if (verbose) + printf("Testing masked event channel\n"); + shinfo->evtchn_mask[0] = 0x8000; + eventfd_write(irq_fd[0], 1UL); + alarm(1); + break; + + case 8: + if (verbose) + printf("Testing unmasked event channel\n"); + /* Unmask that, but deliver the other one */ + shinfo->evtchn_pending[0] = 0; + shinfo->evtchn_mask[0] = 0; + eventfd_write(irq_fd[1], 1UL); + evtchn_irq_expected = true; + alarm(1); + break; + + case 9: + if (verbose) + printf("Testing event channel after memslot change\n"); + vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, + DUMMY_REGION_GPA, DUMMY_REGION_SLOT, 1, 0); + eventfd_write(irq_fd[0], 1UL); + evtchn_irq_expected = true; + alarm(1); + break; + case 0x20: TEST_ASSERT(evtchn_irq_expected, "Unexpected event channel IRQ"); evtchn_irq_expected = false; + if (shinfo->evtchn_pending[1] && + shinfo->evtchn_pending[0]) + goto done; break; } break; @@ -318,9 +481,19 @@ int main(int argc, char *argv[]) ti = addr_gpa2hva(vm, SHINFO_REGION_GPA + 0x40 + 0x20); ti2 = addr_gpa2hva(vm, PVTIME_ADDR); + if (verbose) { + printf("Wall clock (v %d) %d.%09d\n", wc->version, wc->sec, wc->nsec); + printf("Time info 1: v %u tsc %" PRIu64 " time %" PRIu64 " mul %u shift %u flags %x\n", + ti->version, ti->tsc_timestamp, ti->system_time, ti->tsc_to_system_mul, + ti->tsc_shift, ti->flags); + printf("Time info 2: v %u tsc %" PRIu64 " time %" PRIu64 " mul %u shift %u flags %x\n", + ti2->version, ti2->tsc_timestamp, ti2->system_time, ti2->tsc_to_system_mul, + ti2->tsc_shift, ti2->flags); + } + vm_ts.tv_sec = wc->sec; vm_ts.tv_nsec = wc->nsec; - TEST_ASSERT(wc->version && !(wc->version & 1), + TEST_ASSERT(wc->version && !(wc->version & 1), "Bad wallclock version %x", wc->version); TEST_ASSERT(cmp_timespec(&min_ts, &vm_ts) <= 0, "VM time too old"); TEST_ASSERT(cmp_timespec(&max_ts, &vm_ts) >= 0, "VM time too new"); @@ -341,6 +514,15 @@ int main(int argc, char *argv[]) }; vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_GET_ATTR, &rst); + if (verbose) { + printf("Runstate: %s(%d), entry %" PRIu64 " ns\n", + rs->state <= RUNSTATE_offline ? runstate_names[rs->state] : "unknown", + rs->state, rs->state_entry_time); + for (int i = RUNSTATE_running; i <= RUNSTATE_offline; i++) { + printf("State %s: %" PRIu64 " ns\n", + runstate_names[i], rs->time[i]); + } + } TEST_ASSERT(rs->state == rst.u.runstate.state, "Runstate mismatch"); TEST_ASSERT(rs->state_entry_time == rst.u.runstate.state_entry_time, "State entry time mismatch"); diff --git a/tools/testing/selftests/landlock/Makefile b/tools/testing/selftests/landlock/Makefile index a99596ca9882..0b0049e133bb 100644 --- a/tools/testing/selftests/landlock/Makefile +++ b/tools/testing/selftests/landlock/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 -CFLAGS += -Wall -O2 +CFLAGS += -Wall -O2 $(KHDR_INCLUDES) src_test := $(wildcard *_test.c) diff --git a/tools/testing/selftests/lkdtm/config b/tools/testing/selftests/lkdtm/config index a26a3fa9e925..46f39ee76208 100644 --- a/tools/testing/selftests/lkdtm/config +++ b/tools/testing/selftests/lkdtm/config @@ -3,9 +3,9 @@ CONFIG_DEBUG_LIST=y CONFIG_SLAB_FREELIST_HARDENED=y CONFIG_FORTIFY_SOURCE=y CONFIG_HARDENED_USERCOPY=y -# CONFIG_HARDENED_USERCOPY_FALLBACK is not set CONFIG_RANDOMIZE_KSTACK_OFFSET_DEFAULT=y CONFIG_INIT_ON_ALLOC_DEFAULT_ON=y +CONFIG_UBSAN=y CONFIG_UBSAN_BOUNDS=y CONFIG_UBSAN_TRAP=y CONFIG_STACKPROTECTOR_STRONG=y diff --git a/tools/testing/selftests/lkdtm/tests.txt b/tools/testing/selftests/lkdtm/tests.txt index 6b36b7f5dcf9..243c781f0780 100644 --- a/tools/testing/selftests/lkdtm/tests.txt +++ b/tools/testing/selftests/lkdtm/tests.txt @@ -44,6 +44,7 @@ ACCESS_NULL WRITE_RO WRITE_RO_AFTER_INIT WRITE_KERN +WRITE_OPD REFCOUNT_INC_OVERFLOW REFCOUNT_ADD_OVERFLOW REFCOUNT_INC_NOT_ZERO_OVERFLOW diff --git a/tools/testing/selftests/memfd/memfd_test.c b/tools/testing/selftests/memfd/memfd_test.c index 192a2899bae8..94df2692e6e4 100644 --- a/tools/testing/selftests/memfd/memfd_test.c +++ b/tools/testing/selftests/memfd/memfd_test.c @@ -455,6 +455,7 @@ static void mfd_fail_write(int fd) printf("mmap()+mprotect() didn't fail as expected\n"); abort(); } + munmap(p, mfd_def_size); } /* verify PUNCH_HOLE fails */ diff --git a/tools/testing/selftests/mincore/mincore_selftest.c b/tools/testing/selftests/mincore/mincore_selftest.c index e54106643337..4c88238fc8f0 100644 --- a/tools/testing/selftests/mincore/mincore_selftest.c +++ b/tools/testing/selftests/mincore/mincore_selftest.c @@ -207,15 +207,21 @@ TEST(check_file_mmap) errno = 0; fd = open(".", O_TMPFILE | O_RDWR, 0600); - ASSERT_NE(-1, fd) { - TH_LOG("Can't create temporary file: %s", - strerror(errno)); + if (fd < 0) { + ASSERT_EQ(errno, EOPNOTSUPP) { + TH_LOG("Can't create temporary file: %s", + strerror(errno)); + } + SKIP(goto out_free, "O_TMPFILE not supported by filesystem."); } errno = 0; retval = fallocate(fd, 0, 0, FILE_SIZE); - ASSERT_EQ(0, retval) { - TH_LOG("Error allocating space for the temporary file: %s", - strerror(errno)); + if (retval) { + ASSERT_EQ(errno, EOPNOTSUPP) { + TH_LOG("Error allocating space for the temporary file: %s", + strerror(errno)); + } + SKIP(goto out_close, "fallocate not supported by filesystem."); } /* @@ -271,7 +277,9 @@ TEST(check_file_mmap) } munmap(addr, FILE_SIZE); +out_close: close(fd); +out_free: free(vec); } diff --git a/tools/testing/selftests/mount_setattr/mount_setattr_test.c b/tools/testing/selftests/mount_setattr/mount_setattr_test.c index f31205f04ee0..8c5fea68ae67 100644 --- a/tools/testing/selftests/mount_setattr/mount_setattr_test.c +++ b/tools/testing/selftests/mount_setattr/mount_setattr_test.c @@ -1236,7 +1236,7 @@ static int get_userns_fd(unsigned long nsid, unsigned long hostid, unsigned long } /** - * Validate that an attached mount in our mount namespace can be idmapped. + * Validate that an attached mount in our mount namespace cannot be idmapped. * (The kernel enforces that the mount's mount namespace and the caller's mount * namespace match.) */ @@ -1259,7 +1259,7 @@ TEST_F(mount_setattr_idmapped, attached_mount_inside_current_mount_namespace) attr.userns_fd = get_userns_fd(0, 10000, 10000); ASSERT_GE(attr.userns_fd, 0); - ASSERT_EQ(sys_mount_setattr(open_tree_fd, "", AT_EMPTY_PATH, &attr, sizeof(attr)), 0); + ASSERT_NE(sys_mount_setattr(open_tree_fd, "", AT_EMPTY_PATH, &attr, sizeof(attr)), 0); ASSERT_EQ(close(attr.userns_fd), 0); ASSERT_EQ(close(open_tree_fd), 0); } diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore index 7581a7348e1b..21a411b04890 100644 --- a/tools/testing/selftests/net/.gitignore +++ b/tools/testing/selftests/net/.gitignore @@ -35,4 +35,4 @@ test_unix_oob gro ioam6_parser toeplitz -cmsg_so_mark +cmsg_sender diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 9897fa9ab953..3fe2515aa616 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -2,7 +2,7 @@ # Makefile for net selftests CFLAGS = -Wall -Wl,--no-as-needed -O2 -g -CFLAGS += -I../../../../usr/include/ +CFLAGS += -I../../../../usr/include/ $(KHDR_INCLUDES) TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh netdevice.sh \ rtnetlink.sh xfrm_policy.sh test_blackhole_dev.sh @@ -30,6 +30,7 @@ TEST_PROGS += ioam6.sh TEST_PROGS += gro.sh TEST_PROGS += gre_gso.sh TEST_PROGS += cmsg_so_mark.sh +TEST_PROGS += cmsg_time.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 @@ -52,7 +53,7 @@ TEST_GEN_FILES += gro TEST_GEN_PROGS = reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa TEST_GEN_PROGS += reuseport_dualstack reuseaddr_conflict tls TEST_GEN_FILES += toeplitz -TEST_GEN_FILES += cmsg_so_mark +TEST_GEN_FILES += cmsg_sender TEST_FILES := settings diff --git a/tools/testing/selftests/net/af_unix/test_unix_oob.c b/tools/testing/selftests/net/af_unix/test_unix_oob.c index 3dece8b29253..b57e91e1c3f2 100644 --- a/tools/testing/selftests/net/af_unix/test_unix_oob.c +++ b/tools/testing/selftests/net/af_unix/test_unix_oob.c @@ -218,10 +218,10 @@ main(int argc, char **argv) /* Test 1: * veriyf that SIGURG is - * delivered and 63 bytes are - * read and oob is '@' + * delivered, 63 bytes are + * read, oob is '@', and POLLPRI works. */ - wait_for_data(pfd, POLLIN | POLLPRI); + wait_for_data(pfd, POLLPRI); read_oob(pfd, &oob); len = read_data(pfd, buf, 1024); if (!signal_recvd || len != 63 || oob != '@') { diff --git a/tools/testing/selftests/net/cmsg_ipv6.sh b/tools/testing/selftests/net/cmsg_ipv6.sh new file mode 100755 index 000000000000..2d89cb0ad288 --- /dev/null +++ b/tools/testing/selftests/net/cmsg_ipv6.sh @@ -0,0 +1,156 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +ksft_skip=4 + +NS=ns +IP6=2001:db8:1::1/64 +TGT6=2001:db8:1::2 +TMPF=`mktemp` + +cleanup() +{ + rm -f $TMPF + ip netns del $NS +} + +trap cleanup EXIT + +NSEXE="ip netns exec $NS" + +tcpdump -h | grep immediate-mode >> /dev/null +if [ $? -ne 0 ]; then + echo "SKIP - tcpdump with --immediate-mode option required" + exit $ksft_skip +fi + +# Namespaces +ip netns add $NS + +$NSEXE sysctl -w net.ipv4.ping_group_range='0 2147483647' > /dev/null + +# Connectivity +ip -netns $NS link add type dummy +ip -netns $NS link set dev dummy0 up +ip -netns $NS addr add $IP6 dev dummy0 + +# Test +BAD=0 +TOTAL=0 + +check_result() { + ((TOTAL++)) + if [ $1 -ne $2 ]; then + echo " Case $3 returned $1, expected $2" + ((BAD++)) + fi +} + +# IPV6_DONTFRAG +for ovr in setsock cmsg both diff; do + for df in 0 1; do + for p in u i r; do + [ $p == "u" ] && prot=UDP + [ $p == "i" ] && prot=ICMP + [ $p == "r" ] && prot=RAW + + [ $ovr == "setsock" ] && m="-F $df" + [ $ovr == "cmsg" ] && m="-f $df" + [ $ovr == "both" ] && m="-F $df -f $df" + [ $ovr == "diff" ] && m="-F $((1 - df)) -f $df" + + $NSEXE ./cmsg_sender -s -S 2000 -6 -p $p $m $TGT6 1234 + check_result $? $df "DONTFRAG $prot $ovr" + done + done +done + +# IPV6_TCLASS +TOS=0x10 +TOS2=0x20 + +ip -6 -netns $NS rule add tos $TOS lookup 300 +ip -6 -netns $NS route add table 300 prohibit any + +for ovr in setsock cmsg both diff; do + for p in u i r; do + [ $p == "u" ] && prot=UDP + [ $p == "i" ] && prot=ICMP + [ $p == "r" ] && prot=RAW + + [ $ovr == "setsock" ] && m="-C" + [ $ovr == "cmsg" ] && m="-c" + [ $ovr == "both" ] && m="-C $((TOS2)) -c" + [ $ovr == "diff" ] && m="-C $((TOS )) -c" + + $NSEXE nohup tcpdump --immediate-mode -p -ni dummy0 -w $TMPF -c 4 2> /dev/null & + BG=$! + sleep 0.05 + + $NSEXE ./cmsg_sender -6 -p $p $m $((TOS2)) $TGT6 1234 + check_result $? 0 "TCLASS $prot $ovr - pass" + + while [ -d /proc/$BG ]; do + $NSEXE ./cmsg_sender -6 -p u $TGT6 1234 + done + + tcpdump -r $TMPF -v 2>&1 | grep "class $TOS2" >> /dev/null + check_result $? 0 "TCLASS $prot $ovr - packet data" + rm $TMPF + + [ $ovr == "both" ] && m="-C $((TOS )) -c" + [ $ovr == "diff" ] && m="-C $((TOS2)) -c" + + $NSEXE ./cmsg_sender -6 -p $p $m $((TOS)) -s $TGT6 1234 + check_result $? 1 "TCLASS $prot $ovr - rejection" + done +done + +# IPV6_HOPLIMIT +LIM=4 + +for ovr in setsock cmsg both diff; do + for p in u i r; do + [ $p == "u" ] && prot=UDP + [ $p == "i" ] && prot=ICMP + [ $p == "r" ] && prot=RAW + + [ $ovr == "setsock" ] && m="-L" + [ $ovr == "cmsg" ] && m="-l" + [ $ovr == "both" ] && m="-L $LIM -l" + [ $ovr == "diff" ] && m="-L $((LIM + 1)) -l" + + $NSEXE nohup tcpdump --immediate-mode -p -ni dummy0 -w $TMPF -c 4 2> /dev/null & + BG=$! + sleep 0.05 + + $NSEXE ./cmsg_sender -6 -p $p $m $LIM $TGT6 1234 + check_result $? 0 "HOPLIMIT $prot $ovr - pass" + + while [ -d /proc/$BG ]; do + $NSEXE ./cmsg_sender -6 -p u $TGT6 1234 + done + + tcpdump -r $TMPF -v 2>&1 | grep "hlim $LIM[^0-9]" >> /dev/null + check_result $? 0 "HOPLIMIT $prot $ovr - packet data" + rm $TMPF + done +done + +# IPV6 exthdr +for p in u i r; do + # Very basic "does it crash" test + for h in h d r; do + $NSEXE ./cmsg_sender -p $p -6 -H $h $TGT6 1234 + check_result $? 0 "ExtHdr $prot $ovr - pass" + done +done + +# Summary +if [ $BAD -ne 0 ]; then + echo "FAIL - $BAD/$TOTAL cases failed" + exit 1 +else + echo "OK" + exit 0 +fi diff --git a/tools/testing/selftests/net/cmsg_sender.c b/tools/testing/selftests/net/cmsg_sender.c new file mode 100644 index 000000000000..bc2162909a1a --- /dev/null +++ b/tools/testing/selftests/net/cmsg_sender.c @@ -0,0 +1,506 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +#include <errno.h> +#include <error.h> +#include <netdb.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <time.h> +#include <unistd.h> +#include <linux/errqueue.h> +#include <linux/icmp.h> +#include <linux/icmpv6.h> +#include <linux/net_tstamp.h> +#include <linux/types.h> +#include <linux/udp.h> +#include <sys/socket.h> + +#include "../kselftest.h" + +enum { + ERN_SUCCESS = 0, + /* Well defined errors, callers may depend on these */ + ERN_SEND = 1, + /* Informational, can reorder */ + ERN_HELP, + ERN_SEND_SHORT, + ERN_SOCK_CREATE, + ERN_RESOLVE, + ERN_CMSG_WR, + ERN_SOCKOPT, + ERN_GETTIME, + ERN_RECVERR, + ERN_CMSG_RD, + ERN_CMSG_RCV, +}; + +struct option_cmsg_u32 { + bool ena; + unsigned int val; +}; + +struct options { + bool silent_send; + const char *host; + const char *service; + unsigned int size; + struct { + unsigned int mark; + unsigned int dontfrag; + unsigned int tclass; + unsigned int hlimit; + } sockopt; + struct { + unsigned int family; + unsigned int type; + unsigned int proto; + } sock; + struct option_cmsg_u32 mark; + struct { + bool ena; + unsigned int delay; + } txtime; + struct { + bool ena; + } ts; + struct { + struct option_cmsg_u32 dontfrag; + struct option_cmsg_u32 tclass; + struct option_cmsg_u32 hlimit; + struct option_cmsg_u32 exthdr; + } v6; +} opt = { + .size = 13, + .sock = { + .family = AF_UNSPEC, + .type = SOCK_DGRAM, + .proto = IPPROTO_UDP, + }, +}; + +static struct timespec time_start_real; +static struct timespec time_start_mono; + +static void __attribute__((noreturn)) cs_usage(const char *bin) +{ + printf("Usage: %s [opts] <dst host> <dst port / service>\n", bin); + printf("Options:\n" + "\t\t-s Silent send() failures\n" + "\t\t-S send() size\n" + "\t\t-4/-6 Force IPv4 / IPv6 only\n" + "\t\t-p prot Socket protocol\n" + "\t\t (u = UDP (default); i = ICMP; r = RAW)\n" + "\n" + "\t\t-m val Set SO_MARK with given value\n" + "\t\t-M val Set SO_MARK via setsockopt\n" + "\t\t-d val Set SO_TXTIME with given delay (usec)\n" + "\t\t-t Enable time stamp reporting\n" + "\t\t-f val Set don't fragment via cmsg\n" + "\t\t-F val Set don't fragment via setsockopt\n" + "\t\t-c val Set TCLASS via cmsg\n" + "\t\t-C val Set TCLASS via setsockopt\n" + "\t\t-l val Set HOPLIMIT via cmsg\n" + "\t\t-L val Set HOPLIMIT via setsockopt\n" + "\t\t-H type Add an IPv6 header option\n" + "\t\t (h = HOP; d = DST; r = RTDST)" + ""); + exit(ERN_HELP); +} + +static void cs_parse_args(int argc, char *argv[]) +{ + char o; + + while ((o = getopt(argc, argv, "46sS:p:m:M:d:tf:F:c:C:l:L:H:")) != -1) { + switch (o) { + case 's': + opt.silent_send = true; + break; + case 'S': + opt.size = atoi(optarg); + break; + case '4': + opt.sock.family = AF_INET; + break; + case '6': + opt.sock.family = AF_INET6; + break; + case 'p': + if (*optarg == 'u' || *optarg == 'U') { + opt.sock.proto = IPPROTO_UDP; + } else if (*optarg == 'i' || *optarg == 'I') { + opt.sock.proto = IPPROTO_ICMP; + } else if (*optarg == 'r') { + opt.sock.type = SOCK_RAW; + } else { + printf("Error: unknown protocol: %s\n", optarg); + cs_usage(argv[0]); + } + break; + + case 'm': + opt.mark.ena = true; + opt.mark.val = atoi(optarg); + break; + case 'M': + opt.sockopt.mark = atoi(optarg); + break; + case 'd': + opt.txtime.ena = true; + opt.txtime.delay = atoi(optarg); + break; + case 't': + opt.ts.ena = true; + break; + case 'f': + opt.v6.dontfrag.ena = true; + opt.v6.dontfrag.val = atoi(optarg); + break; + case 'F': + opt.sockopt.dontfrag = atoi(optarg); + break; + case 'c': + opt.v6.tclass.ena = true; + opt.v6.tclass.val = atoi(optarg); + break; + case 'C': + opt.sockopt.tclass = atoi(optarg); + break; + case 'l': + opt.v6.hlimit.ena = true; + opt.v6.hlimit.val = atoi(optarg); + break; + case 'L': + opt.sockopt.hlimit = atoi(optarg); + break; + case 'H': + opt.v6.exthdr.ena = true; + switch (optarg[0]) { + case 'h': + opt.v6.exthdr.val = IPV6_HOPOPTS; + break; + case 'd': + opt.v6.exthdr.val = IPV6_DSTOPTS; + break; + case 'r': + opt.v6.exthdr.val = IPV6_RTHDRDSTOPTS; + break; + default: + printf("Error: hdr type: %s\n", optarg); + break; + } + break; + } + } + + if (optind != argc - 2) + cs_usage(argv[0]); + + opt.host = argv[optind]; + opt.service = argv[optind + 1]; +} + +static void memrnd(void *s, size_t n) +{ + int *dword = s; + char *byte; + + for (; n >= 4; n -= 4) + *dword++ = rand(); + byte = (void *)dword; + while (n--) + *byte++ = rand(); +} + +static void +ca_write_cmsg_u32(char *cbuf, size_t cbuf_sz, size_t *cmsg_len, + int level, int optname, struct option_cmsg_u32 *uopt) +{ + struct cmsghdr *cmsg; + + if (!uopt->ena) + return; + + cmsg = (struct cmsghdr *)(cbuf + *cmsg_len); + *cmsg_len += CMSG_SPACE(sizeof(__u32)); + if (cbuf_sz < *cmsg_len) + error(ERN_CMSG_WR, EFAULT, "cmsg buffer too small"); + + cmsg->cmsg_level = level; + cmsg->cmsg_type = optname; + cmsg->cmsg_len = CMSG_LEN(sizeof(__u32)); + *(__u32 *)CMSG_DATA(cmsg) = uopt->val; +} + +static void +cs_write_cmsg(int fd, struct msghdr *msg, char *cbuf, size_t cbuf_sz) +{ + struct cmsghdr *cmsg; + size_t cmsg_len; + + msg->msg_control = cbuf; + cmsg_len = 0; + + ca_write_cmsg_u32(cbuf, cbuf_sz, &cmsg_len, + SOL_SOCKET, SO_MARK, &opt.mark); + ca_write_cmsg_u32(cbuf, cbuf_sz, &cmsg_len, + SOL_IPV6, IPV6_DONTFRAG, &opt.v6.dontfrag); + ca_write_cmsg_u32(cbuf, cbuf_sz, &cmsg_len, + SOL_IPV6, IPV6_TCLASS, &opt.v6.tclass); + ca_write_cmsg_u32(cbuf, cbuf_sz, &cmsg_len, + SOL_IPV6, IPV6_HOPLIMIT, &opt.v6.hlimit); + + if (opt.txtime.ena) { + struct sock_txtime so_txtime = { + .clockid = CLOCK_MONOTONIC, + }; + __u64 txtime; + + if (setsockopt(fd, SOL_SOCKET, SO_TXTIME, + &so_txtime, sizeof(so_txtime))) + error(ERN_SOCKOPT, errno, "setsockopt TXTIME"); + + txtime = time_start_mono.tv_sec * (1000ULL * 1000 * 1000) + + time_start_mono.tv_nsec + + opt.txtime.delay * 1000; + + cmsg = (struct cmsghdr *)(cbuf + cmsg_len); + cmsg_len += CMSG_SPACE(sizeof(txtime)); + if (cbuf_sz < cmsg_len) + error(ERN_CMSG_WR, EFAULT, "cmsg buffer too small"); + + cmsg->cmsg_level = SOL_SOCKET; + cmsg->cmsg_type = SCM_TXTIME; + cmsg->cmsg_len = CMSG_LEN(sizeof(txtime)); + memcpy(CMSG_DATA(cmsg), &txtime, sizeof(txtime)); + } + if (opt.ts.ena) { + __u32 val = SOF_TIMESTAMPING_SOFTWARE | + SOF_TIMESTAMPING_OPT_TSONLY; + + if (setsockopt(fd, SOL_SOCKET, SO_TIMESTAMPING, + &val, sizeof(val))) + error(ERN_SOCKOPT, errno, "setsockopt TIMESTAMPING"); + + cmsg = (struct cmsghdr *)(cbuf + cmsg_len); + cmsg_len += CMSG_SPACE(sizeof(__u32)); + if (cbuf_sz < cmsg_len) + error(ERN_CMSG_WR, EFAULT, "cmsg buffer too small"); + + cmsg->cmsg_level = SOL_SOCKET; + cmsg->cmsg_type = SO_TIMESTAMPING; + cmsg->cmsg_len = CMSG_LEN(sizeof(__u32)); + *(__u32 *)CMSG_DATA(cmsg) = SOF_TIMESTAMPING_TX_SCHED | + SOF_TIMESTAMPING_TX_SOFTWARE; + } + if (opt.v6.exthdr.ena) { + cmsg = (struct cmsghdr *)(cbuf + cmsg_len); + cmsg_len += CMSG_SPACE(8); + if (cbuf_sz < cmsg_len) + error(ERN_CMSG_WR, EFAULT, "cmsg buffer too small"); + + cmsg->cmsg_level = SOL_IPV6; + cmsg->cmsg_type = opt.v6.exthdr.val; + cmsg->cmsg_len = CMSG_LEN(8); + *(__u64 *)CMSG_DATA(cmsg) = 0; + } + + if (cmsg_len) + msg->msg_controllen = cmsg_len; + else + msg->msg_control = NULL; +} + +static const char *cs_ts_info2str(unsigned int info) +{ + static const char *names[] = { + [SCM_TSTAMP_SND] = "SND", + [SCM_TSTAMP_SCHED] = "SCHED", + [SCM_TSTAMP_ACK] = "ACK", + }; + + if (info < ARRAY_SIZE(names)) + return names[info]; + return "unknown"; +} + +static void +cs_read_cmsg(int fd, struct msghdr *msg, char *cbuf, size_t cbuf_sz) +{ + struct sock_extended_err *see; + struct scm_timestamping *ts; + struct cmsghdr *cmsg; + int i, err; + + if (!opt.ts.ena) + return; + msg->msg_control = cbuf; + msg->msg_controllen = cbuf_sz; + + while (true) { + ts = NULL; + see = NULL; + memset(cbuf, 0, cbuf_sz); + + err = recvmsg(fd, msg, MSG_ERRQUEUE); + if (err < 0) { + if (errno == EAGAIN) + break; + error(ERN_RECVERR, errno, "recvmsg ERRQ"); + } + + for (cmsg = CMSG_FIRSTHDR(msg); cmsg != NULL; + cmsg = CMSG_NXTHDR(msg, cmsg)) { + if (cmsg->cmsg_level == SOL_SOCKET && + cmsg->cmsg_type == SO_TIMESTAMPING_OLD) { + if (cmsg->cmsg_len < sizeof(*ts)) + error(ERN_CMSG_RD, EINVAL, "TS cmsg"); + + ts = (void *)CMSG_DATA(cmsg); + } + if ((cmsg->cmsg_level == SOL_IP && + cmsg->cmsg_type == IP_RECVERR) || + (cmsg->cmsg_level == SOL_IPV6 && + cmsg->cmsg_type == IPV6_RECVERR)) { + if (cmsg->cmsg_len < sizeof(*see)) + error(ERN_CMSG_RD, EINVAL, "sock_err cmsg"); + + see = (void *)CMSG_DATA(cmsg); + } + } + + if (!ts) + error(ERN_CMSG_RCV, ENOENT, "TS cmsg not found"); + if (!see) + error(ERN_CMSG_RCV, ENOENT, "sock_err cmsg not found"); + + for (i = 0; i < 3; i++) { + unsigned long long rel_time; + + if (!ts->ts[i].tv_sec && !ts->ts[i].tv_nsec) + continue; + + rel_time = (ts->ts[i].tv_sec - time_start_real.tv_sec) * + (1000ULL * 1000) + + (ts->ts[i].tv_nsec - time_start_real.tv_nsec) / + 1000; + printf(" %5s ts%d %lluus\n", + cs_ts_info2str(see->ee_info), + i, rel_time); + } + } +} + +static void ca_set_sockopts(int fd) +{ + if (opt.sockopt.mark && + setsockopt(fd, SOL_SOCKET, SO_MARK, + &opt.sockopt.mark, sizeof(opt.sockopt.mark))) + error(ERN_SOCKOPT, errno, "setsockopt SO_MARK"); + if (opt.sockopt.dontfrag && + setsockopt(fd, SOL_IPV6, IPV6_DONTFRAG, + &opt.sockopt.dontfrag, sizeof(opt.sockopt.dontfrag))) + error(ERN_SOCKOPT, errno, "setsockopt IPV6_DONTFRAG"); + if (opt.sockopt.tclass && + setsockopt(fd, SOL_IPV6, IPV6_TCLASS, + &opt.sockopt.tclass, sizeof(opt.sockopt.tclass))) + error(ERN_SOCKOPT, errno, "setsockopt IPV6_TCLASS"); + if (opt.sockopt.hlimit && + setsockopt(fd, SOL_IPV6, IPV6_UNICAST_HOPS, + &opt.sockopt.hlimit, sizeof(opt.sockopt.hlimit))) + error(ERN_SOCKOPT, errno, "setsockopt IPV6_HOPLIMIT"); +} + +int main(int argc, char *argv[]) +{ + struct addrinfo hints, *ai; + struct iovec iov[1]; + struct msghdr msg; + char cbuf[1024]; + char *buf; + int err; + int fd; + + cs_parse_args(argc, argv); + + buf = malloc(opt.size); + memrnd(buf, opt.size); + + memset(&hints, 0, sizeof(hints)); + hints.ai_family = opt.sock.family; + + ai = NULL; + err = getaddrinfo(opt.host, opt.service, &hints, &ai); + if (err) { + fprintf(stderr, "Can't resolve address [%s]:%s\n", + opt.host, opt.service); + return ERN_SOCK_CREATE; + } + + if (ai->ai_family == AF_INET6 && opt.sock.proto == IPPROTO_ICMP) + opt.sock.proto = IPPROTO_ICMPV6; + + fd = socket(ai->ai_family, opt.sock.type, opt.sock.proto); + if (fd < 0) { + fprintf(stderr, "Can't open socket: %s\n", strerror(errno)); + freeaddrinfo(ai); + return ERN_RESOLVE; + } + + if (opt.sock.proto == IPPROTO_ICMP) { + buf[0] = ICMP_ECHO; + buf[1] = 0; + } else if (opt.sock.proto == IPPROTO_ICMPV6) { + buf[0] = ICMPV6_ECHO_REQUEST; + buf[1] = 0; + } else if (opt.sock.type == SOCK_RAW) { + struct udphdr hdr = { 1, 2, htons(opt.size), 0 }; + struct sockaddr_in6 *sin6 = (void *)ai->ai_addr;; + + memcpy(buf, &hdr, sizeof(hdr)); + sin6->sin6_port = htons(opt.sock.proto); + } + + ca_set_sockopts(fd); + + if (clock_gettime(CLOCK_REALTIME, &time_start_real)) + error(ERN_GETTIME, errno, "gettime REALTIME"); + if (clock_gettime(CLOCK_MONOTONIC, &time_start_mono)) + error(ERN_GETTIME, errno, "gettime MONOTONIC"); + + iov[0].iov_base = buf; + iov[0].iov_len = opt.size; + + memset(&msg, 0, sizeof(msg)); + msg.msg_name = ai->ai_addr; + msg.msg_namelen = ai->ai_addrlen; + msg.msg_iov = iov; + msg.msg_iovlen = 1; + + cs_write_cmsg(fd, &msg, cbuf, sizeof(cbuf)); + + err = sendmsg(fd, &msg, 0); + if (err < 0) { + if (!opt.silent_send) + fprintf(stderr, "send failed: %s\n", strerror(errno)); + err = ERN_SEND; + goto err_out; + } else if (err != (int)opt.size) { + fprintf(stderr, "short send\n"); + err = ERN_SEND_SHORT; + goto err_out; + } else { + err = ERN_SUCCESS; + } + + /* Make sure all timestamps have time to loop back */ + usleep(opt.txtime.delay); + + cs_read_cmsg(fd, &msg, cbuf, sizeof(cbuf)); + +err_out: + close(fd); + freeaddrinfo(ai); + return err; +} diff --git a/tools/testing/selftests/net/cmsg_so_mark.c b/tools/testing/selftests/net/cmsg_so_mark.c deleted file mode 100644 index 27f2804892a7..000000000000 --- a/tools/testing/selftests/net/cmsg_so_mark.c +++ /dev/null @@ -1,67 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -#include <errno.h> -#include <netdb.h> -#include <stdio.h> -#include <stdlib.h> -#include <string.h> -#include <unistd.h> -#include <linux/types.h> -#include <sys/socket.h> - -int main(int argc, const char **argv) -{ - char cbuf[CMSG_SPACE(sizeof(__u32))]; - struct addrinfo hints, *ai; - struct cmsghdr *cmsg; - struct iovec iov[1]; - struct msghdr msg; - int mark; - int err; - int fd; - - if (argc != 4) { - fprintf(stderr, "Usage: %s <dst_ip> <port> <mark>\n", argv[0]); - return 1; - } - mark = atoi(argv[3]); - - memset(&hints, 0, sizeof(hints)); - hints.ai_family = AF_UNSPEC; - hints.ai_socktype = SOCK_DGRAM; - - ai = NULL; - err = getaddrinfo(argv[1], argv[2], &hints, &ai); - if (err) { - fprintf(stderr, "Can't resolve address: %s\n", strerror(errno)); - return 1; - } - - fd = socket(ai->ai_family, SOCK_DGRAM, IPPROTO_UDP); - if (fd < 0) { - fprintf(stderr, "Can't open socket: %s\n", strerror(errno)); - freeaddrinfo(ai); - return 1; - } - - iov[0].iov_base = "bla"; - iov[0].iov_len = 4; - - msg.msg_name = ai->ai_addr; - msg.msg_namelen = ai->ai_addrlen; - msg.msg_iov = iov; - msg.msg_iovlen = 1; - msg.msg_control = cbuf; - msg.msg_controllen = sizeof(cbuf); - - cmsg = CMSG_FIRSTHDR(&msg); - cmsg->cmsg_level = SOL_SOCKET; - cmsg->cmsg_type = SO_MARK; - cmsg->cmsg_len = CMSG_LEN(sizeof(__u32)); - *(__u32 *)CMSG_DATA(cmsg) = mark; - - err = sendmsg(fd, &msg, 0); - - close(fd); - freeaddrinfo(ai); - return err != 4; -} diff --git a/tools/testing/selftests/net/cmsg_so_mark.sh b/tools/testing/selftests/net/cmsg_so_mark.sh index 19c6aab8d0e9..1650b8622f2f 100755 --- a/tools/testing/selftests/net/cmsg_so_mark.sh +++ b/tools/testing/selftests/net/cmsg_so_mark.sh @@ -18,6 +18,8 @@ trap cleanup EXIT # Namespaces ip netns add $NS +ip netns exec $NS sysctl -w net.ipv4.ping_group_range='0 2147483647' > /dev/null + # Connectivity ip -netns $NS link add type dummy ip -netns $NS link set dev dummy0 up @@ -41,15 +43,29 @@ check_result() { fi } -ip netns exec $NS ./cmsg_so_mark $TGT4 1234 $((MARK + 1)) -check_result $? 0 "IPv4 pass" -ip netns exec $NS ./cmsg_so_mark $TGT6 1234 $((MARK + 1)) -check_result $? 0 "IPv6 pass" +for ovr in setsock cmsg both; do + for i in 4 6; do + [ $i == 4 ] && TGT=$TGT4 || TGT=$TGT6 + + for p in u i r; do + [ $p == "u" ] && prot=UDP + [ $p == "i" ] && prot=ICMP + [ $p == "r" ] && prot=RAW + + [ $ovr == "setsock" ] && m="-M" + [ $ovr == "cmsg" ] && m="-m" + [ $ovr == "both" ] && m="-M $MARK -m" + + ip netns exec $NS ./cmsg_sender -$i -p $p $m $((MARK + 1)) $TGT 1234 + check_result $? 0 "$prot $ovr - pass" + + [ $ovr == "diff" ] && m="-M $((MARK + 1)) -m" -ip netns exec $NS ./cmsg_so_mark $TGT4 1234 $MARK -check_result $? 1 "IPv4 rejection" -ip netns exec $NS ./cmsg_so_mark $TGT6 1234 $MARK -check_result $? 1 "IPv6 rejection" + ip netns exec $NS ./cmsg_sender -$i -p $p $m $MARK -s $TGT 1234 + check_result $? 1 "$prot $ovr - rejection" + done + done +done # Summary if [ $BAD -ne 0 ]; then diff --git a/tools/testing/selftests/net/cmsg_time.sh b/tools/testing/selftests/net/cmsg_time.sh new file mode 100755 index 000000000000..91161e1da734 --- /dev/null +++ b/tools/testing/selftests/net/cmsg_time.sh @@ -0,0 +1,83 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +NS=ns +IP4=172.16.0.1/24 +TGT4=172.16.0.2 +IP6=2001:db8:1::1/64 +TGT6=2001:db8:1::2 + +cleanup() +{ + ip netns del $NS +} + +trap cleanup EXIT + +# Namespaces +ip netns add $NS + +ip netns exec $NS sysctl -w net.ipv4.ping_group_range='0 2147483647' > /dev/null + +# Connectivity +ip -netns $NS link add type dummy +ip -netns $NS link set dev dummy0 up +ip -netns $NS addr add $IP4 dev dummy0 +ip -netns $NS addr add $IP6 dev dummy0 + +# Need FQ for TXTIME +ip netns exec $NS tc qdisc replace dev dummy0 root fq + +# Test +BAD=0 +TOTAL=0 + +check_result() { + ((TOTAL++)) + if [ $1 -ne 0 ]; then + echo " Case $4 returned $1, expected 0" + ((BAD++)) + elif [ "$2" != "$3" ]; then + echo " Case $4 returned '$2', expected '$3'" + ((BAD++)) + fi +} + +for i in "-4 $TGT4" "-6 $TGT6"; do + for p in u i r; do + [ $p == "u" ] && prot=UDPv${i:1:2} + [ $p == "i" ] && prot=ICMPv${i:1:2} + [ $p == "r" ] && prot=RAWv${i:1:2} + + ts=$(ip netns exec $NS ./cmsg_sender -p $p $i 1234) + check_result $? "$ts" "" "$prot - no options" + + ts=$(ip netns exec $NS ./cmsg_sender -p $p $i 1234 -t | wc -l) + check_result $? "$ts" "2" "$prot - ts cnt" + ts=$(ip netns exec $NS ./cmsg_sender -p $p $i 1234 -t | + sed -n "s/.*SCHED ts0 [0-9].*/OK/p") + check_result $? "$ts" "OK" "$prot - ts0 SCHED" + ts=$(ip netns exec $NS ./cmsg_sender -p $p $i 1234 -t | + sed -n "s/.*SND ts0 [0-9].*/OK/p") + check_result $? "$ts" "OK" "$prot - ts0 SND" + + ts=$(ip netns exec $NS ./cmsg_sender -p $p $i 1234 -t -d 1000 | + awk '/SND/ { if ($3 > 1000) print "OK"; }') + check_result $? "$ts" "OK" "$prot - TXTIME abs" + + ts=$(ip netns exec $NS ./cmsg_sender -p $p $i 1234 -t -d 1000 | + awk '/SND/ {snd=$3} + /SCHED/ {sch=$3} + END { if (snd - sch > 500) print "OK"; }') + check_result $? "$ts" "OK" "$prot - TXTIME rel" + done +done + +# Summary +if [ $BAD -ne 0 ]; then + echo "FAIL - $BAD/$TOTAL cases failed" + exit 1 +else + echo "OK" + exit 0 +fi diff --git a/tools/testing/selftests/net/fcnal-test.sh b/tools/testing/selftests/net/fcnal-test.sh index 412d85205546..47c4d4b4a44a 100755 --- a/tools/testing/selftests/net/fcnal-test.sh +++ b/tools/testing/selftests/net/fcnal-test.sh @@ -750,7 +750,7 @@ ipv4_ping_vrf() log_start show_hint "Fails since address on vrf device is out of device scope" run_cmd ping -c1 -w1 -I ${NSA_DEV} ${a} - log_test_addr ${a} $? 1 "ping local, device bind" + log_test_addr ${a} $? 2 "ping local, device bind" done # @@ -4059,6 +4059,9 @@ usage: ${0##*/} OPTS -p Pause on fail -P Pause after each test -v Be verbose + +Tests: + $TESTS_IPV4 $TESTS_IPV6 $TESTS_OTHER EOF } diff --git a/tools/testing/selftests/net/fib_rule_tests.sh b/tools/testing/selftests/net/fib_rule_tests.sh index 43ea8407a82e..4f70baad867d 100755 --- a/tools/testing/selftests/net/fib_rule_tests.sh +++ b/tools/testing/selftests/net/fib_rule_tests.sh @@ -96,7 +96,7 @@ fib_rule6_del() fib_rule6_del_by_pref() { - pref=$($IP -6 rule show | grep "$1 lookup $TABLE" | cut -d ":" -f 1) + pref=$($IP -6 rule show $1 table $RTABLE | cut -d ":" -f 1) $IP -6 rule del pref $pref } @@ -104,17 +104,36 @@ fib_rule6_test_match_n_redirect() { local match="$1" local getmatch="$2" + local description="$3" $IP -6 rule add $match table $RTABLE $IP -6 route get $GW_IP6 $getmatch | grep -q "table $RTABLE" - log_test $? 0 "rule6 check: $1" + log_test $? 0 "rule6 check: $description" fib_rule6_del_by_pref "$match" - log_test $? 0 "rule6 del by pref: $match" + log_test $? 0 "rule6 del by pref: $description" +} + +fib_rule6_test_reject() +{ + local match="$1" + local rc + + $IP -6 rule add $match table $RTABLE 2>/dev/null + rc=$? + log_test $rc 2 "rule6 check: $match" + + if [ $rc -eq 0 ]; then + $IP -6 rule del $match table $RTABLE + fi } fib_rule6_test() { + local getmatch + local match + local cnt + # setup the fib rule redirect route $IP -6 route add table $RTABLE default via $GW_IP6 dev $DEV onlink @@ -124,8 +143,21 @@ fib_rule6_test() match="from $SRC_IP6 iif $DEV" fib_rule6_test_match_n_redirect "$match" "$match" "iif redirect to table" + # Reject dsfield (tos) options which have ECN bits set + for cnt in $(seq 1 3); do + match="dsfield $cnt" + fib_rule6_test_reject "$match" + done + + # Don't take ECN bits into account when matching on dsfield match="tos 0x10" - fib_rule6_test_match_n_redirect "$match" "$match" "tos redirect to table" + for cnt in "0x10" "0x11" "0x12" "0x13"; do + # Using option 'tos' instead of 'dsfield' as old iproute2 + # versions don't support 'dsfield' in ip rule show. + getmatch="tos $cnt" + fib_rule6_test_match_n_redirect "$match" "$getmatch" \ + "$getmatch redirect to table" + done match="fwmark 0x64" getmatch="mark 0x64" @@ -165,7 +197,7 @@ fib_rule4_del() fib_rule4_del_by_pref() { - pref=$($IP rule show | grep "$1 lookup $TABLE" | cut -d ":" -f 1) + pref=$($IP rule show $1 table $RTABLE | cut -d ":" -f 1) $IP rule del pref $pref } @@ -173,17 +205,36 @@ fib_rule4_test_match_n_redirect() { local match="$1" local getmatch="$2" + local description="$3" $IP rule add $match table $RTABLE $IP route get $GW_IP4 $getmatch | grep -q "table $RTABLE" - log_test $? 0 "rule4 check: $1" + log_test $? 0 "rule4 check: $description" fib_rule4_del_by_pref "$match" - log_test $? 0 "rule4 del by pref: $match" + log_test $? 0 "rule4 del by pref: $description" +} + +fib_rule4_test_reject() +{ + local match="$1" + local rc + + $IP rule add $match table $RTABLE 2>/dev/null + rc=$? + log_test $rc 2 "rule4 check: $match" + + if [ $rc -eq 0 ]; then + $IP rule del $match table $RTABLE + fi } fib_rule4_test() { + local getmatch + local match + local cnt + # setup the fib rule redirect route $IP route add table $RTABLE default via $GW_IP4 dev $DEV onlink @@ -192,14 +243,27 @@ fib_rule4_test() # need enable forwarding and disable rp_filter temporarily as all the # addresses are in the same subnet and egress device == ingress device. - ip netns exec testns sysctl -w net.ipv4.ip_forward=1 - ip netns exec testns sysctl -w net.ipv4.conf.$DEV.rp_filter=0 + ip netns exec testns sysctl -qw net.ipv4.ip_forward=1 + ip netns exec testns sysctl -qw net.ipv4.conf.$DEV.rp_filter=0 match="from $SRC_IP iif $DEV" fib_rule4_test_match_n_redirect "$match" "$match" "iif redirect to table" - ip netns exec testns sysctl -w net.ipv4.ip_forward=0 + ip netns exec testns sysctl -qw net.ipv4.ip_forward=0 + + # Reject dsfield (tos) options which have ECN bits set + for cnt in $(seq 1 3); do + match="dsfield $cnt" + fib_rule4_test_reject "$match" + done + # Don't take ECN bits into account when matching on dsfield match="tos 0x10" - fib_rule4_test_match_n_redirect "$match" "$match" "tos redirect to table" + for cnt in "0x10" "0x11" "0x12" "0x13"; do + # Using option 'tos' instead of 'dsfield' as old iproute2 + # versions don't support 'dsfield' in ip rule show. + getmatch="tos $cnt" + fib_rule4_test_match_n_redirect "$match" "$getmatch" \ + "$getmatch redirect to table" + done match="fwmark 0x64" getmatch="mark 0x64" diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh index 996af1ae3d3d..2271a8727f62 100755 --- a/tools/testing/selftests/net/fib_tests.sh +++ b/tools/testing/selftests/net/fib_tests.sh @@ -9,7 +9,7 @@ ret=0 ksft_skip=4 # all tests in this script. Can be overridden with -t option -TESTS="unregister down carrier nexthop suppress ipv6_rt ipv4_rt ipv6_addr_metric ipv4_addr_metric ipv6_route_metrics ipv4_route_metrics ipv4_route_v6_gw rp_filter ipv4_del_addr ipv4_mangle ipv6_mangle" +TESTS="unregister down carrier nexthop suppress ipv6_rt ipv4_rt ipv6_addr_metric ipv4_addr_metric ipv6_route_metrics ipv4_route_metrics ipv4_route_v6_gw rp_filter ipv4_del_addr ipv4_mangle ipv6_mangle ipv4_bcast_neigh" VERBOSE=0 PAUSE_ON_FAIL=no @@ -988,12 +988,25 @@ ipv6_rt_replace() ipv6_rt_replace_mpath } +ipv6_rt_dsfield() +{ + echo + echo "IPv6 route with dsfield tests" + + run_cmd "$IP -6 route flush 2001:db8:102::/64" + + # IPv6 doesn't support routing based on dsfield + run_cmd "$IP -6 route add 2001:db8:102::/64 dsfield 0x04 via 2001:db8:101::2" + log_test $? 2 "Reject route with dsfield" +} + ipv6_route_test() { route_setup ipv6_rt_add ipv6_rt_replace + ipv6_rt_dsfield route_cleanup } @@ -1447,6 +1460,81 @@ ipv4_local_rt_cache() log_test $? 0 "Cached route removed from VRF port device" } +ipv4_rt_dsfield() +{ + echo + echo "IPv4 route with dsfield tests" + + run_cmd "$IP route flush 172.16.102.0/24" + + # New routes should reject dsfield options that interfere with ECN + run_cmd "$IP route add 172.16.102.0/24 dsfield 0x01 via 172.16.101.2" + log_test $? 2 "Reject route with dsfield 0x01" + + run_cmd "$IP route add 172.16.102.0/24 dsfield 0x02 via 172.16.101.2" + log_test $? 2 "Reject route with dsfield 0x02" + + run_cmd "$IP route add 172.16.102.0/24 dsfield 0x03 via 172.16.101.2" + log_test $? 2 "Reject route with dsfield 0x03" + + # A generic route that doesn't take DSCP into account + run_cmd "$IP route add 172.16.102.0/24 via 172.16.101.2" + + # A more specific route for DSCP 0x10 + run_cmd "$IP route add 172.16.102.0/24 dsfield 0x10 via 172.16.103.2" + + # DSCP 0x10 should match the specific route, no matter the ECN bits + $IP route get fibmatch 172.16.102.1 dsfield 0x10 | \ + grep -q "via 172.16.103.2" + log_test $? 0 "IPv4 route with DSCP and ECN:Not-ECT" + + $IP route get fibmatch 172.16.102.1 dsfield 0x11 | \ + grep -q "via 172.16.103.2" + log_test $? 0 "IPv4 route with DSCP and ECN:ECT(1)" + + $IP route get fibmatch 172.16.102.1 dsfield 0x12 | \ + grep -q "via 172.16.103.2" + log_test $? 0 "IPv4 route with DSCP and ECN:ECT(0)" + + $IP route get fibmatch 172.16.102.1 dsfield 0x13 | \ + grep -q "via 172.16.103.2" + log_test $? 0 "IPv4 route with DSCP and ECN:CE" + + # Unknown DSCP should match the generic route, no matter the ECN bits + $IP route get fibmatch 172.16.102.1 dsfield 0x14 | \ + grep -q "via 172.16.101.2" + log_test $? 0 "IPv4 route with unknown DSCP and ECN:Not-ECT" + + $IP route get fibmatch 172.16.102.1 dsfield 0x15 | \ + grep -q "via 172.16.101.2" + log_test $? 0 "IPv4 route with unknown DSCP and ECN:ECT(1)" + + $IP route get fibmatch 172.16.102.1 dsfield 0x16 | \ + grep -q "via 172.16.101.2" + log_test $? 0 "IPv4 route with unknown DSCP and ECN:ECT(0)" + + $IP route get fibmatch 172.16.102.1 dsfield 0x17 | \ + grep -q "via 172.16.101.2" + log_test $? 0 "IPv4 route with unknown DSCP and ECN:CE" + + # Null DSCP should match the generic route, no matter the ECN bits + $IP route get fibmatch 172.16.102.1 dsfield 0x00 | \ + grep -q "via 172.16.101.2" + log_test $? 0 "IPv4 route with no DSCP and ECN:Not-ECT" + + $IP route get fibmatch 172.16.102.1 dsfield 0x01 | \ + grep -q "via 172.16.101.2" + log_test $? 0 "IPv4 route with no DSCP and ECN:ECT(1)" + + $IP route get fibmatch 172.16.102.1 dsfield 0x02 | \ + grep -q "via 172.16.101.2" + log_test $? 0 "IPv4 route with no DSCP and ECN:ECT(0)" + + $IP route get fibmatch 172.16.102.1 dsfield 0x03 | \ + grep -q "via 172.16.101.2" + log_test $? 0 "IPv4 route with no DSCP and ECN:CE" +} + ipv4_route_test() { route_setup @@ -1454,6 +1542,7 @@ ipv4_route_test() ipv4_rt_add ipv4_rt_replace ipv4_local_rt_cache + ipv4_rt_dsfield route_cleanup } @@ -1865,6 +1954,61 @@ ipv6_mangle_test() route_cleanup } +ip_neigh_get_check() +{ + ip neigh help 2>&1 | grep -q 'ip neigh get' + if [ $? -ne 0 ]; then + echo "iproute2 command does not support neigh get. Skipping test" + return 1 + fi + + return 0 +} + +ipv4_bcast_neigh_test() +{ + local rc + + echo + echo "IPv4 broadcast neighbour tests" + + ip_neigh_get_check || return 1 + + setup + + set -e + run_cmd "$IP neigh add 192.0.2.111 lladdr 00:11:22:33:44:55 nud perm dev dummy0" + run_cmd "$IP neigh add 192.0.2.255 lladdr 00:11:22:33:44:55 nud perm dev dummy0" + + run_cmd "$IP neigh get 192.0.2.111 dev dummy0" + run_cmd "$IP neigh get 192.0.2.255 dev dummy0" + + run_cmd "$IP address add 192.0.2.1/24 broadcast 192.0.2.111 dev dummy0" + + run_cmd "$IP neigh add 203.0.113.111 nud failed dev dummy0" + run_cmd "$IP neigh add 203.0.113.255 nud failed dev dummy0" + + run_cmd "$IP neigh get 203.0.113.111 dev dummy0" + run_cmd "$IP neigh get 203.0.113.255 dev dummy0" + + run_cmd "$IP address add 203.0.113.1/24 broadcast 203.0.113.111 dev dummy0" + set +e + + run_cmd "$IP neigh get 192.0.2.111 dev dummy0" + log_test $? 0 "Resolved neighbour for broadcast address" + + run_cmd "$IP neigh get 192.0.2.255 dev dummy0" + log_test $? 0 "Resolved neighbour for network broadcast address" + + run_cmd "$IP neigh get 203.0.113.111 dev dummy0" + log_test $? 2 "Unresolved neighbour for broadcast address" + + run_cmd "$IP neigh get 203.0.113.255 dev dummy0" + log_test $? 2 "Unresolved neighbour for network broadcast address" + + cleanup +} + ################################################################################ # usage @@ -1939,6 +2083,7 @@ do ipv4_route_v6_gw) ipv4_route_v6_gw_test;; ipv4_mangle) ipv4_mangle_test;; ipv6_mangle) ipv6_mangle_test;; + ipv4_bcast_neigh) ipv4_bcast_neigh_test;; help) echo "Test names: $TESTS"; exit 0;; esac diff --git a/tools/testing/selftests/net/forwarding/Makefile b/tools/testing/selftests/net/forwarding/Makefile index 72ee644d47bf..8fa97ae9af9e 100644 --- a/tools/testing/selftests/net/forwarding/Makefile +++ b/tools/testing/selftests/net/forwarding/Makefile @@ -1,6 +1,7 @@ # SPDX-License-Identifier: GPL-2.0+ OR MIT TEST_PROGS = bridge_igmp.sh \ + bridge_locked_port.sh \ bridge_port_isolation.sh \ bridge_sticky_fdb.sh \ bridge_vlan_aware.sh \ diff --git a/tools/testing/selftests/net/forwarding/bridge_locked_port.sh b/tools/testing/selftests/net/forwarding/bridge_locked_port.sh new file mode 100755 index 000000000000..5b02b6b60ce7 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/bridge_locked_port.sh @@ -0,0 +1,176 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +ALL_TESTS="locked_port_ipv4 locked_port_ipv6 locked_port_vlan" +NUM_NETIFS=4 +CHECK_TC="no" +source lib.sh + +h1_create() +{ + simple_if_init $h1 192.0.2.1/24 2001:db8:1::1/64 + vlan_create $h1 100 v$h1 198.51.100.1/24 +} + +h1_destroy() +{ + vlan_destroy $h1 100 + simple_if_fini $h1 192.0.2.1/24 2001:db8:1::1/64 +} + +h2_create() +{ + simple_if_init $h2 192.0.2.2/24 2001:db8:1::2/64 + vlan_create $h2 100 v$h2 198.51.100.2/24 +} + +h2_destroy() +{ + vlan_destroy $h2 100 + simple_if_fini $h2 192.0.2.2/24 2001:db8:1::2/64 +} + +switch_create() +{ + ip link add dev br0 type bridge vlan_filtering 1 + + ip link set dev $swp1 master br0 + ip link set dev $swp2 master br0 + + bridge link set dev $swp1 learning off + + ip link set dev br0 up + ip link set dev $swp1 up + ip link set dev $swp2 up +} + +switch_destroy() +{ + ip link set dev $swp2 down + ip link set dev $swp1 down + + ip link del dev br0 +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + vrf_prepare + + h1_create + h2_create + + switch_create +} + +cleanup() +{ + pre_cleanup + + switch_destroy + + h2_destroy + h1_destroy + + vrf_cleanup +} + +locked_port_ipv4() +{ + RET=0 + + check_locked_port_support || return 0 + + ping_do $h1 192.0.2.2 + check_err $? "Ping did not work before locking port" + + bridge link set dev $swp1 locked on + + ping_do $h1 192.0.2.2 + check_fail $? "Ping worked after locking port, but before adding FDB entry" + + bridge fdb add `mac_get $h1` dev $swp1 master static + + ping_do $h1 192.0.2.2 + check_err $? "Ping did not work after locking port and adding FDB entry" + + bridge link set dev $swp1 locked off + bridge fdb del `mac_get $h1` dev $swp1 master static + + ping_do $h1 192.0.2.2 + check_err $? "Ping did not work after unlocking port and removing FDB entry." + + log_test "Locked port ipv4" +} + +locked_port_vlan() +{ + RET=0 + + check_locked_port_support || return 0 + + bridge vlan add vid 100 dev $swp1 + bridge vlan add vid 100 dev $swp2 + + ping_do $h1.100 198.51.100.2 + check_err $? "Ping through vlan did not work before locking port" + + bridge link set dev $swp1 locked on + ping_do $h1.100 198.51.100.2 + check_fail $? "Ping through vlan worked after locking port, but before adding FDB entry" + + bridge fdb add `mac_get $h1` dev $swp1 vlan 100 master static + + ping_do $h1.100 198.51.100.2 + check_err $? "Ping through vlan did not work after locking port and adding FDB entry" + + bridge link set dev $swp1 locked off + bridge fdb del `mac_get $h1` dev $swp1 vlan 100 master static + + ping_do $h1.100 198.51.100.2 + check_err $? "Ping through vlan did not work after unlocking port and removing FDB entry" + + bridge vlan del vid 100 dev $swp1 + bridge vlan del vid 100 dev $swp2 + log_test "Locked port vlan" +} + +locked_port_ipv6() +{ + RET=0 + check_locked_port_support || return 0 + + ping6_do $h1 2001:db8:1::2 + check_err $? "Ping6 did not work before locking port" + + bridge link set dev $swp1 locked on + + ping6_do $h1 2001:db8:1::2 + check_fail $? "Ping6 worked after locking port, but before adding FDB entry" + + bridge fdb add `mac_get $h1` dev $swp1 master static + ping6_do $h1 2001:db8:1::2 + check_err $? "Ping6 did not work after locking port and adding FDB entry" + + bridge link set dev $swp1 locked off + bridge fdb del `mac_get $h1` dev $swp1 master static + + ping6_do $h1 2001:db8:1::2 + check_err $? "Ping6 did not work after unlocking port and removing FDB entry" + + log_test "Locked port ipv6" +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh b/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh index b90dff8d3a94..64bd00fe9a4f 100755 --- a/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh +++ b/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh @@ -28,8 +28,9 @@ h2_destroy() switch_create() { - # 10 Seconds ageing time. - ip link add dev br0 type bridge vlan_filtering 1 ageing_time 1000 \ + ip link add dev br0 type bridge \ + vlan_filtering 1 \ + ageing_time $LOW_AGEING_TIME \ mcast_snooping 0 ip link set dev $swp1 master br0 diff --git a/tools/testing/selftests/net/forwarding/bridge_vlan_unaware.sh b/tools/testing/selftests/net/forwarding/bridge_vlan_unaware.sh index c15c6c85c984..1c8a26046589 100755 --- a/tools/testing/selftests/net/forwarding/bridge_vlan_unaware.sh +++ b/tools/testing/selftests/net/forwarding/bridge_vlan_unaware.sh @@ -27,8 +27,9 @@ h2_destroy() switch_create() { - # 10 Seconds ageing time. - ip link add dev br0 type bridge ageing_time 1000 mcast_snooping 0 + ip link add dev br0 type bridge \ + ageing_time $LOW_AGEING_TIME \ + mcast_snooping 0 ip link set dev $swp1 master br0 ip link set dev $swp2 master br0 diff --git a/tools/testing/selftests/net/forwarding/fib_offload_lib.sh b/tools/testing/selftests/net/forwarding/fib_offload_lib.sh index e134a5f529c9..1b3b46292179 100644 --- a/tools/testing/selftests/net/forwarding/fib_offload_lib.sh +++ b/tools/testing/selftests/net/forwarding/fib_offload_lib.sh @@ -99,15 +99,15 @@ fib_ipv4_tos_test() fib4_trap_check $ns "192.0.2.0/24 dev dummy1 tos 0 metric 1024" false check_err $? "Route not in hardware when should" - ip -n $ns route add 192.0.2.0/24 dev dummy1 tos 2 metric 1024 - fib4_trap_check $ns "192.0.2.0/24 dev dummy1 tos 2 metric 1024" false + ip -n $ns route add 192.0.2.0/24 dev dummy1 tos 8 metric 1024 + fib4_trap_check $ns "192.0.2.0/24 dev dummy1 tos 8 metric 1024" false check_err $? "Highest TOS route not in hardware when should" fib4_trap_check $ns "192.0.2.0/24 dev dummy1 tos 0 metric 1024" true check_err $? "Lowest TOS route still in hardware when should not" - ip -n $ns route add 192.0.2.0/24 dev dummy1 tos 1 metric 1024 - fib4_trap_check $ns "192.0.2.0/24 dev dummy1 tos 1 metric 1024" true + ip -n $ns route add 192.0.2.0/24 dev dummy1 tos 4 metric 1024 + fib4_trap_check $ns "192.0.2.0/24 dev dummy1 tos 4 metric 1024" true check_err $? "Middle TOS route in hardware when should not" log_test "IPv4 routes with TOS" @@ -277,11 +277,11 @@ fib_ipv4_replay_tos_test() ip -n $ns link set dev dummy1 up ip -n $ns route add 192.0.2.0/24 dev dummy1 tos 0 - ip -n $ns route add 192.0.2.0/24 dev dummy1 tos 1 + ip -n $ns route add 192.0.2.0/24 dev dummy1 tos 4 devlink -N $ns dev reload $devlink_dev - fib4_trap_check $ns "192.0.2.0/24 dev dummy1 tos 1" false + fib4_trap_check $ns "192.0.2.0/24 dev dummy1 tos 4" false check_err $? "Highest TOS route not in hardware when should" fib4_trap_check $ns "192.0.2.0/24 dev dummy1 tos 0" true diff --git a/tools/testing/selftests/net/forwarding/forwarding.config.sample b/tools/testing/selftests/net/forwarding/forwarding.config.sample index b0980a2efa31..4a546509de90 100644 --- a/tools/testing/selftests/net/forwarding/forwarding.config.sample +++ b/tools/testing/selftests/net/forwarding/forwarding.config.sample @@ -41,6 +41,8 @@ NETIF_CREATE=yes # Timeout (in seconds) before ping exits regardless of how many packets have # been sent or received PING_TIMEOUT=5 +# Minimum ageing_time (in centiseconds) supported by hardware +LOW_AGEING_TIME=1000 # Flag for tc match, supposed to be skip_sw/skip_hw which means do not process # filter by software/hardware TC_FLAG=skip_hw diff --git a/tools/testing/selftests/net/forwarding/hw_stats_l3.sh b/tools/testing/selftests/net/forwarding/hw_stats_l3.sh new file mode 100755 index 000000000000..1c11c4256d06 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/hw_stats_l3.sh @@ -0,0 +1,332 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# +--------------------+ +----------------------+ +# | H1 | | H2 | +# | | | | +# | $h1.200 + | | + $h2.200 | +# | 192.0.2.1/28 | | | | 192.0.2.18/28 | +# | 2001:db8:1::1/64 | | | | 2001:db8:2::1/64 | +# | | | | | | +# | $h1 + | | + $h2 | +# | | | | | | +# +------------------|-+ +-|--------------------+ +# | | +# +------------------|-------------------------|--------------------+ +# | SW | | | +# | | | | +# | $rp1 + + $rp2 | +# | | | | +# | $rp1.200 + + $rp2.200 | +# | 192.0.2.2/28 192.0.2.17/28 | +# | 2001:db8:1::2/64 2001:db8:2::2/64 | +# | | +# +-----------------------------------------------------------------+ + +ALL_TESTS=" + ping_ipv4 + ping_ipv6 + test_stats_rx_ipv4 + test_stats_tx_ipv4 + test_stats_rx_ipv6 + test_stats_tx_ipv6 + respin_enablement + test_stats_rx_ipv4 + test_stats_tx_ipv4 + test_stats_rx_ipv6 + test_stats_tx_ipv6 + reapply_config + ping_ipv4 + ping_ipv6 + test_stats_rx_ipv4 + test_stats_tx_ipv4 + test_stats_rx_ipv6 + test_stats_tx_ipv6 + test_stats_report_rx + test_stats_report_tx + test_destroy_enabled + test_double_enable +" +NUM_NETIFS=4 +source lib.sh + +h1_create() +{ + simple_if_init $h1 + vlan_create $h1 200 v$h1 192.0.2.1/28 2001:db8:1::1/64 + ip route add 192.0.2.16/28 vrf v$h1 nexthop via 192.0.2.2 + ip -6 route add 2001:db8:2::/64 vrf v$h1 nexthop via 2001:db8:1::2 +} + +h1_destroy() +{ + ip -6 route del 2001:db8:2::/64 vrf v$h1 nexthop via 2001:db8:1::2 + ip route del 192.0.2.16/28 vrf v$h1 nexthop via 192.0.2.2 + vlan_destroy $h1 200 + simple_if_fini $h1 +} + +h2_create() +{ + simple_if_init $h2 + vlan_create $h2 200 v$h2 192.0.2.18/28 2001:db8:2::1/64 + ip route add 192.0.2.0/28 vrf v$h2 nexthop via 192.0.2.17 + ip -6 route add 2001:db8:1::/64 vrf v$h2 nexthop via 2001:db8:2::2 +} + +h2_destroy() +{ + ip -6 route del 2001:db8:1::/64 vrf v$h2 nexthop via 2001:db8:2::2 + ip route del 192.0.2.0/28 vrf v$h2 nexthop via 192.0.2.17 + vlan_destroy $h2 200 + simple_if_fini $h2 +} + +router_rp1_200_create() +{ + ip link add name $rp1.200 up \ + link $rp1 addrgenmode eui64 type vlan id 200 + ip address add dev $rp1.200 192.0.2.2/28 + ip address add dev $rp1.200 2001:db8:1::2/64 + ip stats set dev $rp1.200 l3_stats on +} + +router_rp1_200_destroy() +{ + ip stats set dev $rp1.200 l3_stats off + ip address del dev $rp1.200 2001:db8:1::2/64 + ip address del dev $rp1.200 192.0.2.2/28 + ip link del dev $rp1.200 +} + +router_create() +{ + ip link set dev $rp1 up + router_rp1_200_create + + ip link set dev $rp2 up + vlan_create $rp2 200 "" 192.0.2.17/28 2001:db8:2::2/64 +} + +router_destroy() +{ + vlan_destroy $rp2 200 + ip link set dev $rp2 down + + router_rp1_200_destroy + ip link set dev $rp1 down +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + rp1=${NETIFS[p2]} + + rp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + rp1mac=$(mac_get $rp1) + rp2mac=$(mac_get $rp2) + + vrf_prepare + + h1_create + h2_create + + router_create + + forwarding_enable +} + +cleanup() +{ + pre_cleanup + + forwarding_restore + + router_destroy + + h2_destroy + h1_destroy + + vrf_cleanup +} + +ping_ipv4() +{ + ping_test $h1.200 192.0.2.18 " IPv4" +} + +ping_ipv6() +{ + ping_test $h1.200 2001:db8:2::1 " IPv6" +} + +get_l3_stat() +{ + local selector=$1; shift + + ip -j stats show dev $rp1.200 group offload subgroup l3_stats | + jq '.[0].stats64.'$selector +} + +send_packets_rx_ipv4() +{ + # Send 21 packets instead of 20, because the first one might trap and go + # through the SW datapath, which might not bump the HW counter. + $MZ $h1.200 -c 21 -d 20msec -p 100 \ + -a own -b $rp1mac -A 192.0.2.1 -B 192.0.2.18 \ + -q -t udp sp=54321,dp=12345 +} + +send_packets_rx_ipv6() +{ + $MZ $h1.200 -6 -c 21 -d 20msec -p 100 \ + -a own -b $rp1mac -A 2001:db8:1::1 -B 2001:db8:2::1 \ + -q -t udp sp=54321,dp=12345 +} + +send_packets_tx_ipv4() +{ + $MZ $h2.200 -c 21 -d 20msec -p 100 \ + -a own -b $rp2mac -A 192.0.2.18 -B 192.0.2.1 \ + -q -t udp sp=54321,dp=12345 +} + +send_packets_tx_ipv6() +{ + $MZ $h2.200 -6 -c 21 -d 20msec -p 100 \ + -a own -b $rp2mac -A 2001:db8:2::1 -B 2001:db8:1::1 \ + -q -t udp sp=54321,dp=12345 +} + +___test_stats() +{ + local dir=$1; shift + local prot=$1; shift + + local a + local b + + a=$(get_l3_stat ${dir}.packets) + send_packets_${dir}_${prot} + "$@" + b=$(busywait "$TC_HIT_TIMEOUT" until_counter_is ">= $a + 20" \ + get_l3_stat ${dir}.packets) + check_err $? "Traffic not reflected in the counter: $a -> $b" +} + +__test_stats() +{ + local dir=$1; shift + local prot=$1; shift + + RET=0 + ___test_stats "$dir" "$prot" + log_test "Test $dir packets: $prot" +} + +test_stats_rx_ipv4() +{ + __test_stats rx ipv4 +} + +test_stats_tx_ipv4() +{ + __test_stats tx ipv4 +} + +test_stats_rx_ipv6() +{ + __test_stats rx ipv6 +} + +test_stats_tx_ipv6() +{ + __test_stats tx ipv6 +} + +# Make sure everything works well even after stats have been disabled and +# reenabled on the same device without touching the L3 configuration. +respin_enablement() +{ + log_info "Turning stats off and on again" + ip stats set dev $rp1.200 l3_stats off + ip stats set dev $rp1.200 l3_stats on +} + +# For the initial run, l3_stats is enabled on a completely set up netdevice. Now +# do it the other way around: enabling the L3 stats on an L2 netdevice, and only +# then apply the L3 configuration. +reapply_config() +{ + log_info "Reapplying configuration" + + router_rp1_200_destroy + + ip link add name $rp1.200 link $rp1 addrgenmode none type vlan id 200 + ip stats set dev $rp1.200 l3_stats on + ip link set dev $rp1.200 up addrgenmode eui64 + ip address add dev $rp1.200 192.0.2.2/28 + ip address add dev $rp1.200 2001:db8:1::2/64 +} + +__test_stats_report() +{ + local dir=$1; shift + local prot=$1; shift + + local a + local b + + RET=0 + + a=$(get_l3_stat ${dir}.packets) + send_packets_${dir}_${prot} + ip address flush dev $rp1.200 + b=$(busywait "$TC_HIT_TIMEOUT" until_counter_is ">= $a + 20" \ + get_l3_stat ${dir}.packets) + check_err $? "Traffic not reflected in the counter: $a -> $b" + log_test "Test ${dir} packets: stats pushed on loss of L3" + + ip stats set dev $rp1.200 l3_stats off + ip link del dev $rp1.200 + router_rp1_200_create +} + +test_stats_report_rx() +{ + __test_stats_report rx ipv4 +} + +test_stats_report_tx() +{ + __test_stats_report tx ipv4 +} + +test_destroy_enabled() +{ + RET=0 + + ip link del dev $rp1.200 + router_rp1_200_create + + log_test "Destroy l3_stats-enabled netdev" +} + +test_double_enable() +{ + RET=0 + ___test_stats rx ipv4 \ + ip stats set dev $rp1.200 l3_stats on + log_test "Test stat retention across a spurious enablement" +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index 7da783d6f453..664b9ecaf228 100644 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -24,6 +24,7 @@ PING_COUNT=${PING_COUNT:=10} PING_TIMEOUT=${PING_TIMEOUT:=5} WAIT_TIMEOUT=${WAIT_TIMEOUT:=20} INTERFACE_TIMEOUT=${INTERFACE_TIMEOUT:=600} +LOW_AGEING_TIME=${LOW_AGEING_TIME:=1000} REQUIRE_JQ=${REQUIRE_JQ:=yes} REQUIRE_MZ=${REQUIRE_MZ:=yes} @@ -125,6 +126,14 @@ check_ethtool_lanes_support() fi } +check_locked_port_support() +{ + if ! bridge -d link show | grep -q " locked"; then + echo "SKIP: iproute2 too old; Locked port feature not supported." + return $ksft_skip + fi +} + if [[ "$(id -u)" -ne 0 ]]; then echo "SKIP: need root privileges" exit $ksft_skip @@ -1489,3 +1498,63 @@ brmcast_check_sg_state() check_err_fail $should_fail $? "Entry $src has blocked flag" done } + +start_ip_monitor() +{ + local mtype=$1; shift + local ip=${1-ip}; shift + + # start the monitor in the background + tmpfile=`mktemp /var/run/nexthoptestXXX` + mpid=`($ip monitor $mtype > $tmpfile & echo $!) 2>/dev/null` + sleep 0.2 + echo "$mpid $tmpfile" +} + +stop_ip_monitor() +{ + local mpid=$1; shift + local tmpfile=$1; shift + local el=$1; shift + local what=$1; shift + + sleep 0.2 + kill $mpid + local lines=`grep '^\w' $tmpfile | wc -l` + test $lines -eq $el + check_err $? "$what: $lines lines of events, expected $el" + rm -rf $tmpfile +} + +hw_stats_monitor_test() +{ + local dev=$1; shift + local type=$1; shift + local make_suitable=$1; shift + local make_unsuitable=$1; shift + local ip=${1-ip}; shift + + RET=0 + + # Expect a notification about enablement. + local ipmout=$(start_ip_monitor stats "$ip") + $ip stats set dev $dev ${type}_stats on + stop_ip_monitor $ipmout 1 "${type}_stats enablement" + + # Expect a notification about offload. + local ipmout=$(start_ip_monitor stats "$ip") + $make_suitable + stop_ip_monitor $ipmout 1 "${type}_stats installation" + + # Expect a notification about loss of offload. + local ipmout=$(start_ip_monitor stats "$ip") + $make_unsuitable + stop_ip_monitor $ipmout 1 "${type}_stats deinstallation" + + # Expect a notification about disablement + local ipmout=$(start_ip_monitor stats "$ip") + $ip stats set dev $dev ${type}_stats off + stop_ip_monitor $ipmout 1 "${type}_stats disablement" + + log_test "${type}_stats notifications" +} diff --git a/tools/testing/selftests/net/forwarding/pedit_ip.sh b/tools/testing/selftests/net/forwarding/pedit_ip.sh new file mode 100755 index 000000000000..d14efb2d23b2 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/pedit_ip.sh @@ -0,0 +1,201 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# This test sends traffic from H1 to H2. Either on ingress of $swp1, or on +# egress of $swp2, the traffic is acted upon by a pedit action. An ingress +# filter installed on $h2 verifies that the packet looks like expected. +# +# +----------------------+ +----------------------+ +# | H1 | | H2 | +# | + $h1 | | $h2 + | +# | | 192.0.2.1/28 | | 192.0.2.2/28 | | +# +----|-----------------+ +----------------|-----+ +# | | +# +----|----------------------------------------------------------------|-----+ +# | SW | | | +# | +-|----------------------------------------------------------------|-+ | +# | | + $swp1 BR $swp2 + | | +# | +--------------------------------------------------------------------+ | +# +---------------------------------------------------------------------------+ + +ALL_TESTS=" + ping_ipv4 + ping_ipv6 + test_ip4_src + test_ip4_dst + test_ip6_src + test_ip6_dst +" + +NUM_NETIFS=4 +source lib.sh +source tc_common.sh + +h1_create() +{ + simple_if_init $h1 192.0.2.1/28 2001:db8:1::1/64 +} + +h1_destroy() +{ + simple_if_fini $h1 192.0.2.1/28 2001:db8:1::1/64 +} + +h2_create() +{ + simple_if_init $h2 192.0.2.2/28 2001:db8:1::2/64 + tc qdisc add dev $h2 clsact +} + +h2_destroy() +{ + tc qdisc del dev $h2 clsact + simple_if_fini $h2 192.0.2.2/28 2001:db8:1::2/64 +} + +switch_create() +{ + ip link add name br1 up type bridge vlan_filtering 1 + ip link set dev $swp1 master br1 + ip link set dev $swp1 up + ip link set dev $swp2 master br1 + ip link set dev $swp2 up + + tc qdisc add dev $swp1 clsact + tc qdisc add dev $swp2 clsact +} + +switch_destroy() +{ + tc qdisc del dev $swp2 clsact + tc qdisc del dev $swp1 clsact + + ip link set dev $swp2 down + ip link set dev $swp2 nomaster + ip link set dev $swp1 down + ip link set dev $swp1 nomaster + ip link del dev br1 +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + h2mac=$(mac_get $h2) + + vrf_prepare + h1_create + h2_create + switch_create +} + +cleanup() +{ + pre_cleanup + + switch_destroy + h2_destroy + h1_destroy + vrf_cleanup +} + +ping_ipv4() +{ + ping_test $h1 192.0.2.2 +} + +ping_ipv6() +{ + ping6_test $h1 2001:db8:1::2 +} + +do_test_pedit_ip() +{ + local pedit_locus=$1; shift + local pedit_action=$1; shift + local match_prot=$1; shift + local match_flower=$1; shift + local mz_flags=$1; shift + + tc filter add $pedit_locus handle 101 pref 1 \ + flower action pedit ex munge $pedit_action + tc filter add dev $h2 ingress handle 101 pref 1 prot $match_prot \ + flower skip_hw $match_flower action pass + + RET=0 + + $MZ $mz_flags $h1 -c 10 -d 20msec -p 100 -a own -b $h2mac -q -t ip + + local pkts + pkts=$(busywait "$TC_HIT_TIMEOUT" until_counter_is ">= 10" \ + tc_rule_handle_stats_get "dev $h2 ingress" 101) + check_err $? "Expected to get 10 packets, but got $pkts." + + pkts=$(tc_rule_handle_stats_get "$pedit_locus" 101) + ((pkts >= 10)) + check_err $? "Expected to get 10 packets on pedit rule, but got $pkts." + + log_test "$pedit_locus pedit $pedit_action" + + tc filter del dev $h2 ingress pref 1 + tc filter del $pedit_locus pref 1 +} + +do_test_pedit_ip6() +{ + local locus=$1; shift + local pedit_addr=$1; shift + local flower_addr=$1; shift + + do_test_pedit_ip "$locus" "$pedit_addr set 2001:db8:2::1" ipv6 \ + "$flower_addr 2001:db8:2::1" \ + "-6 -A 2001:db8:1::1 -B 2001:db8:1::2" +} + +do_test_pedit_ip4() +{ + local locus=$1; shift + local pedit_addr=$1; shift + local flower_addr=$1; shift + + do_test_pedit_ip "$locus" "$pedit_addr set 198.51.100.1" ip \ + "$flower_addr 198.51.100.1" \ + "-A 192.0.2.1 -B 192.0.2.2" +} + +test_ip4_src() +{ + do_test_pedit_ip4 "dev $swp1 ingress" "ip src" src_ip + do_test_pedit_ip4 "dev $swp2 egress" "ip src" src_ip +} + +test_ip4_dst() +{ + do_test_pedit_ip4 "dev $swp1 ingress" "ip dst" dst_ip + do_test_pedit_ip4 "dev $swp2 egress" "ip dst" dst_ip +} + +test_ip6_src() +{ + do_test_pedit_ip6 "dev $swp1 ingress" "ip6 src" src_ip + do_test_pedit_ip6 "dev $swp2 egress" "ip6 src" src_ip +} + +test_ip6_dst() +{ + do_test_pedit_ip6 "dev $swp1 ingress" "ip6 dst" dst_ip + do_test_pedit_ip6 "dev $swp2 egress" "ip6 dst" dst_ip +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/tc_police.sh b/tools/testing/selftests/net/forwarding/tc_police.sh index 4f9f17cb45d6..0a51eef21b9e 100755 --- a/tools/testing/selftests/net/forwarding/tc_police.sh +++ b/tools/testing/selftests/net/forwarding/tc_police.sh @@ -37,6 +37,8 @@ ALL_TESTS=" police_tx_mirror_test police_pps_rx_test police_pps_tx_test + police_mtu_rx_test + police_mtu_tx_test " NUM_NETIFS=6 source tc_common.sh @@ -346,6 +348,56 @@ police_pps_tx_test() tc filter del dev $rp2 egress protocol ip pref 1 handle 101 flower } +police_mtu_common_test() { + RET=0 + + local test_name=$1; shift + local dev=$1; shift + local direction=$1; shift + + tc filter add dev $dev $direction protocol ip pref 1 handle 101 flower \ + dst_ip 198.51.100.1 ip_proto udp dst_port 54321 \ + action police mtu 1042 conform-exceed drop/ok + + # to count "conform" packets + tc filter add dev $h2 ingress protocol ip pref 1 handle 101 flower \ + dst_ip 198.51.100.1 ip_proto udp dst_port 54321 \ + action drop + + mausezahn $h1 -a own -b $(mac_get $rp1) -A 192.0.2.1 -B 198.51.100.1 \ + -t udp sp=12345,dp=54321 -p 1001 -c 10 -q + + mausezahn $h1 -a own -b $(mac_get $rp1) -A 192.0.2.1 -B 198.51.100.1 \ + -t udp sp=12345,dp=54321 -p 1000 -c 3 -q + + tc_check_packets "dev $dev $direction" 101 13 + check_err $? "wrong packet counter" + + # "exceed" packets + local overlimits_t0=$(tc_rule_stats_get ${dev} 1 ${direction} .overlimits) + test ${overlimits_t0} = 10 + check_err $? "wrong overlimits, expected 10 got ${overlimits_t0}" + + # "conform" packets + tc_check_packets "dev $h2 ingress" 101 3 + check_err $? "forwarding error" + + tc filter del dev $h2 ingress protocol ip pref 1 handle 101 flower + tc filter del dev $dev $direction protocol ip pref 1 handle 101 flower + + log_test "$test_name" +} + +police_mtu_rx_test() +{ + police_mtu_common_test "police mtu (rx)" $rp1 ingress +} + +police_mtu_tx_test() +{ + police_mtu_common_test "police mtu (tx)" $rp2 egress +} + setup_prepare() { h1=${NETIFS[p1]} diff --git a/tools/testing/selftests/net/ioam6_parser.c b/tools/testing/selftests/net/ioam6_parser.c index 8f6997d35816..d9d1d4190126 100644 --- a/tools/testing/selftests/net/ioam6_parser.c +++ b/tools/testing/selftests/net/ioam6_parser.c @@ -240,11 +240,8 @@ static int check_ioam6_data(__u8 **p, struct ioam6_trace_hdr *ioam6h, *p += sizeof(__u32); } - if (ioam6h->type.bit6) { - if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff) - return 1; + if (ioam6h->type.bit6) *p += sizeof(__u32); - } if (ioam6h->type.bit7) { if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff) diff --git a/tools/testing/selftests/net/mptcp/Makefile b/tools/testing/selftests/net/mptcp/Makefile index 0356c4501c99..f905d5358e68 100644 --- a/tools/testing/selftests/net/mptcp/Makefile +++ b/tools/testing/selftests/net/mptcp/Makefile @@ -3,7 +3,7 @@ top_srcdir = ../../../../.. KSFT_KHDR_INSTALL := 1 -CFLAGS = -Wall -Wl,--no-as-needed -O2 -g -I$(top_srcdir)/usr/include +CFLAGS = -Wall -Wl,--no-as-needed -O2 -g -I$(top_srcdir)/usr/include $(KHDR_INCLUDES) TEST_PROGS := mptcp_connect.sh pm_netlink.sh mptcp_join.sh diag.sh \ simult_flows.sh mptcp_sockopt.sh diff --git a/tools/testing/selftests/net/mptcp/diag.sh b/tools/testing/selftests/net/mptcp/diag.sh index 2674ba20d524..ff821025d309 100755 --- a/tools/testing/selftests/net/mptcp/diag.sh +++ b/tools/testing/selftests/net/mptcp/diag.sh @@ -71,6 +71,36 @@ chk_msk_remote_key_nr() __chk_nr "grep -c remote_key" $* } +# $1: ns, $2: port +wait_local_port_listen() +{ + local listener_ns="${1}" + local port="${2}" + + local port_hex i + + port_hex="$(printf "%04X" "${port}")" + for i in $(seq 10); do + ip netns exec "${listener_ns}" cat /proc/net/tcp | \ + awk "BEGIN {rc=1} {if (\$2 ~ /:${port_hex}\$/ && \$4 ~ /0A/) {rc=0; exit}} END {exit rc}" && + break + sleep 0.1 + done +} + +wait_connected() +{ + local listener_ns="${1}" + local port="${2}" + + local port_hex i + + port_hex="$(printf "%04X" "${port}")" + for i in $(seq 10); do + ip netns exec ${listener_ns} grep -q " 0100007F:${port_hex} " /proc/net/tcp && break + sleep 0.1 + done +} trap cleanup EXIT ip netns add $ns @@ -81,15 +111,15 @@ echo "a" | \ ip netns exec $ns \ ./mptcp_connect -p 10000 -l -t ${timeout_poll} \ 0.0.0.0 >/dev/null & -sleep 0.1 +wait_local_port_listen $ns 10000 chk_msk_nr 0 "no msk on netns creation" echo "b" | \ timeout ${timeout_test} \ ip netns exec $ns \ - ./mptcp_connect -p 10000 -j -t ${timeout_poll} \ + ./mptcp_connect -p 10000 -r 0 -t ${timeout_poll} \ 127.0.0.1 >/dev/null & -sleep 0.1 +wait_connected $ns 10000 chk_msk_nr 2 "after MPC handshake " chk_msk_remote_key_nr 2 "....chk remote_key" chk_msk_fallback_nr 0 "....chk no fallback" @@ -101,13 +131,13 @@ echo "a" | \ ip netns exec $ns \ ./mptcp_connect -p 10001 -l -s TCP -t ${timeout_poll} \ 0.0.0.0 >/dev/null & -sleep 0.1 +wait_local_port_listen $ns 10001 echo "b" | \ timeout ${timeout_test} \ ip netns exec $ns \ - ./mptcp_connect -p 10001 -j -t ${timeout_poll} \ + ./mptcp_connect -p 10001 -r 0 -t ${timeout_poll} \ 127.0.0.1 >/dev/null & -sleep 0.1 +wait_connected $ns 10001 chk_msk_fallback_nr 1 "check fallback" flush_pids @@ -119,7 +149,7 @@ for I in `seq 1 $NR_CLIENTS`; do ./mptcp_connect -p $((I+10001)) -l -w 10 \ -t ${timeout_poll} 0.0.0.0 >/dev/null & done -sleep 0.1 +wait_local_port_listen $ns $((NR_CLIENTS + 10001)) for I in `seq 1 $NR_CLIENTS`; do echo "b" | \ diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh index cb5809b89081..621af6895f4d 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh @@ -432,6 +432,8 @@ do_transfer() local stat_ackrx_last_l=$(get_mib_counter "${listener_ns}" "MPTcpExtMPCapableACKRX") local stat_cookietx_last=$(get_mib_counter "${listener_ns}" "TcpExtSyncookiesSent") local stat_cookierx_last=$(get_mib_counter "${listener_ns}" "TcpExtSyncookiesRecv") + local stat_csum_err_s=$(get_mib_counter "${listener_ns}" "MPTcpExtDataCsumErr") + local stat_csum_err_c=$(get_mib_counter "${connector_ns}" "MPTcpExtDataCsumErr") timeout ${timeout_test} \ ip netns exec ${listener_ns} \ @@ -524,6 +526,23 @@ do_transfer() fi fi + if $checksum; then + local csum_err_s=$(get_mib_counter "${listener_ns}" "MPTcpExtDataCsumErr") + local csum_err_c=$(get_mib_counter "${connector_ns}" "MPTcpExtDataCsumErr") + + local csum_err_s_nr=$((csum_err_s - stat_csum_err_s)) + if [ $csum_err_s_nr -gt 0 ]; then + printf "[ FAIL ]\nserver got $csum_err_s_nr data checksum error[s]" + rets=1 + fi + + local csum_err_c_nr=$((csum_err_c - stat_csum_err_c)) + if [ $csum_err_c_nr -gt 0 ]; then + printf "[ FAIL ]\nclient got $csum_err_c_nr data checksum error[s]" + retc=1 + fi + fi + if [ $retc -eq 0 ] && [ $rets -eq 0 ]; then printf "[ OK ]" fi @@ -763,8 +782,8 @@ run_tests_disconnect() run_tests_lo "$ns1" "$ns1" dead:beef:1::1 1 "-I 3 -i $old_cin" # restore previous status - cout=$old_cout - cout_disconnect="$cout".disconnect + sin=$old_sin + sin_disconnect="$cout".disconnect cin=$old_cin cin_disconnect="$cin".disconnect connect_per_transfer=1 diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index 27d0eb9afdca..7314257d248a 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -1,6 +1,11 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +# Double quotes to prevent globbing and word splitting is recommended in new +# code but we accept it, especially because there were too many before having +# address all other issues detected by shellcheck. +#shellcheck disable=SC2086 + ret=0 sin="" sinfail="" @@ -9,15 +14,28 @@ cin="" cinfail="" cinsent="" cout="" +capout="" +ns1="" +ns2="" ksft_skip=4 timeout_poll=30 timeout_test=$((timeout_poll * 2 + 1)) -mptcp_connect="" capture=0 checksum=0 -do_all_tests=1 - +ip_mptcp=0 +check_invert=0 +validate_checksum=0 +init=0 + +declare -A all_tests +declare -a only_tests_ids +declare -a only_tests_names +declare -A failed_tests TEST_COUNT=0 +TEST_NAME="" +nr_blank=40 + +export FAILING_LINKS="" # generated using "nfbpf_compile '(ip && (ip[54] & 0xf0) == 0x30) || # (ip6 && (ip6[74] & 0xf0) == 0x30)'" @@ -37,16 +55,18 @@ CBPF_MPTCP_SUBOPTION_ADD_ADDR="14, 6 0 0 65535, 6 0 0 0" -init() +init_partial() { capout=$(mktemp) - rndh=$(printf %x $sec)-$(mktemp -u XXXXXX) + local rndh + rndh=$(mktemp -u XXXXXX) ns1="ns1-$rndh" ns2="ns2-$rndh" - for netns in "$ns1" "$ns2";do + local netns + for netns in "$ns1" "$ns2"; do ip netns add $netns || exit $ksft_skip ip -net $netns link set lo up ip netns exec $netns sysctl -q net.mptcp.enabled=1 @@ -57,13 +77,18 @@ init() fi done - # ns1 ns2 + check_invert=0 + validate_checksum=$checksum + FAILING_LINKS="" + + # ns1 ns2 # ns1eth1 ns2eth1 # ns1eth2 ns2eth2 # ns1eth3 ns2eth3 # ns1eth4 ns2eth4 - for i in `seq 1 4`; do + local i + for i in $(seq 1 4); do ip link add ns1eth$i netns "$ns1" type veth peer name ns2eth$i netns "$ns2" ip -net "$ns1" addr add 10.0.$i.1/24 dev ns1eth$i ip -net "$ns1" addr add dead:beef:$i::1/64 dev ns1eth$i nodad @@ -75,12 +100,14 @@ init() # let $ns2 reach any $ns1 address from any interface ip -net "$ns2" route add default via 10.0.$i.1 dev ns2eth$i metric 10$i + ip -net "$ns2" route add default via dead:beef:$i::1 dev ns2eth$i metric 10$i done } init_shapers() { - for i in `seq 1 4`; do + local i + for i in $(seq 1 4); do tc -n $ns1 qdisc add dev ns1eth$i root netem rate 20mbit delay 1 tc -n $ns2 qdisc add dev ns2eth$i root netem rate 20mbit delay 1 done @@ -90,12 +117,48 @@ cleanup_partial() { rm -f "$capout" + local netns for netns in "$ns1" "$ns2"; do ip netns del $netns rm -f /tmp/$netns.{nstat,out} done } +check_tools() +{ + if ! ip -Version &> /dev/null; then + echo "SKIP: Could not run test without ip tool" + exit $ksft_skip + fi + + if ! iptables -V &> /dev/null; then + echo "SKIP: Could not run all tests without iptables tool" + exit $ksft_skip + fi + + if ! ip6tables -V &> /dev/null; then + echo "SKIP: Could not run all tests without ip6tables tool" + exit $ksft_skip + fi +} + +init() { + init=1 + + check_tools + + sin=$(mktemp) + sout=$(mktemp) + cin=$(mktemp) + cinsent=$(mktemp) + cout=$(mktemp) + + trap cleanup EXIT + + make_file "$cin" "client" 1 + make_file "$sin" "server" 1 +} + cleanup() { rm -f "$cin" "$cout" "$sinfail" @@ -103,33 +166,73 @@ cleanup() cleanup_partial } +skip_test() +{ + if [ "${#only_tests_ids[@]}" -eq 0 ] && [ "${#only_tests_names[@]}" -eq 0 ]; then + return 1 + fi + + local i + for i in "${only_tests_ids[@]}"; do + if [ "${TEST_COUNT}" -eq "${i}" ]; then + return 1 + fi + done + for i in "${only_tests_names[@]}"; do + if [ "${TEST_NAME}" = "${i}" ]; then + return 1 + fi + done + + return 0 +} + +# $1: test name reset() { - cleanup_partial - init + TEST_NAME="${1}" + + TEST_COUNT=$((TEST_COUNT+1)) + + if skip_test; then + return 1 + fi + + if [ "${init}" != "1" ]; then + init + else + cleanup_partial + fi + + init_partial + + return 0 } +# $1: test name reset_with_cookies() { - reset + reset "${1}" || return 1 - for netns in "$ns1" "$ns2";do + local netns + for netns in "$ns1" "$ns2"; do ip netns exec $netns sysctl -q net.ipv4.tcp_syncookies=2 done } +# $1: test name reset_with_add_addr_timeout() { - local ip="${1:-4}" + local ip="${2:-4}" local tables + reset "${1}" || return 1 + tables="iptables" if [ $ip -eq 6 ]; then tables="ip6tables" fi - reset - ip netns exec $ns1 sysctl -q net.mptcp.add_addr_timeout=1 ip netns exec $ns2 $tables -A OUTPUT -p tcp \ -m tcp --tcp-option 30 \ @@ -138,45 +241,45 @@ reset_with_add_addr_timeout() -j DROP } +# $1: test name reset_with_checksum() { local ns1_enable=$1 local ns2_enable=$2 - reset + reset "checksum test ${1} ${2}" || return 1 ip netns exec $ns1 sysctl -q net.mptcp.checksum_enabled=$ns1_enable ip netns exec $ns2 sysctl -q net.mptcp.checksum_enabled=$ns2_enable + + validate_checksum=1 } reset_with_allow_join_id0() { - local ns1_enable=$1 - local ns2_enable=$2 + local ns1_enable=$2 + local ns2_enable=$3 - reset + reset "${1}" || return 1 ip netns exec $ns1 sysctl -q net.mptcp.allow_join_initial_addr_port=$ns1_enable ip netns exec $ns2 sysctl -q net.mptcp.allow_join_initial_addr_port=$ns2_enable } -ip -Version > /dev/null 2>&1 -if [ $? -ne 0 ];then - echo "SKIP: Could not run test without ip tool" - exit $ksft_skip -fi - -iptables -V > /dev/null 2>&1 -if [ $? -ne 0 ];then - echo "SKIP: Could not run all tests without iptables tool" - exit $ksft_skip -fi +fail_test() +{ + ret=1 + failed_tests[${TEST_COUNT}]="${TEST_NAME}" +} -ip6tables -V > /dev/null 2>&1 -if [ $? -ne 0 ];then - echo "SKIP: Could not run all tests without ip6tables tool" - exit $ksft_skip -fi +get_failed_tests_ids() +{ + # sorted + local i + for i in "${!failed_tests[@]}"; do + echo "${i}" + done | sort -n +} print_file_err() { @@ -187,47 +290,53 @@ print_file_err() check_transfer() { - in=$1 - out=$2 - what=$3 - - cmp "$in" "$out" > /dev/null 2>&1 - if [ $? -ne 0 ] ;then - echo "[ FAIL ] $what does not match (in, out):" - print_file_err "$in" - print_file_err "$out" - ret=1 - - return 1 - fi + local in=$1 + local out=$2 + local what=$3 + local i a b + + local line + cmp -l "$in" "$out" | while read -r i a b; do + local sum=$((0${a} + 0${b})) + if [ $check_invert -eq 0 ] || [ $sum -ne $((0xff)) ]; then + echo "[ FAIL ] $what does not match (in, out):" + print_file_err "$in" + print_file_err "$out" + fail_test + + return 1 + else + echo "$what has inverted byte at ${i}" + fi + done return 0 } do_ping() { - listener_ns="$1" - connector_ns="$2" - connect_addr="$3" + local listener_ns="$1" + local connector_ns="$2" + local connect_addr="$3" - ip netns exec ${connector_ns} ping -q -c 1 $connect_addr >/dev/null - if [ $? -ne 0 ] ; then + if ! ip netns exec ${connector_ns} ping -q -c 1 $connect_addr >/dev/null; then echo "$listener_ns -> $connect_addr connectivity [ FAIL ]" 1>&2 - ret=1 + fail_test fi } link_failure() { - ns="$1" + local ns="$1" if [ -z "$FAILING_LINKS" ]; then l=$((RANDOM%4)) FAILING_LINKS=$((l+1)) fi + local l for l in $FAILING_LINKS; do - veth="ns1eth$l" + local veth="ns1eth$l" ip -net "$ns" link set "$veth" down done } @@ -244,9 +353,10 @@ wait_local_port_listen() local listener_ns="${1}" local port="${2}" - local port_hex i - + local port_hex port_hex="$(printf "%04X" "${port}")" + + local i for i in $(seq 10); do ip netns exec "${listener_ns}" cat /proc/net/tcp* | \ awk "BEGIN {rc=1} {if (\$2 ~ /:${port_hex}\$/ && \$4 ~ /0A/) {rc=0; exit}} END {exit rc}" && @@ -257,7 +367,7 @@ wait_local_port_listen() rm_addr_count() { - ns=${1} + local ns=${1} ip netns exec ${ns} nstat -as | grep MPTcpExtRmAddr | awk '{print $2}' } @@ -268,8 +378,8 @@ wait_rm_addr() local ns="${1}" local old_cnt="${2}" local cnt - local i + local i for i in $(seq 10); do cnt=$(rm_addr_count ${ns}) [ "$cnt" = "${old_cnt}" ] || break @@ -277,27 +387,227 @@ wait_rm_addr() done } +wait_mpj() +{ + local ns="${1}" + local cnt old_cnt + + old_cnt=$(ip netns exec ${ns} nstat -as | grep MPJoinAckRx | awk '{print $2}') + + local i + for i in $(seq 10); do + cnt=$(ip netns exec ${ns} nstat -as | grep MPJoinAckRx | awk '{print $2}') + [ "$cnt" = "${old_cnt}" ] || break + sleep 0.1 + done +} + +pm_nl_set_limits() +{ + local ns=$1 + local addrs=$2 + local subflows=$3 + + if [ $ip_mptcp -eq 1 ]; then + ip -n $ns mptcp limits set add_addr_accepted $addrs subflows $subflows + else + ip netns exec $ns ./pm_nl_ctl limits $addrs $subflows + fi +} + +pm_nl_add_endpoint() +{ + local ns=$1 + local addr=$2 + local flags _flags + local port _port + local dev _dev + local id _id + local nr=2 + + local p + for p in "${@}" + do + if [ $p = "flags" ]; then + eval _flags=\$"$nr" + [ -n "$_flags" ]; flags="flags $_flags" + fi + if [ $p = "dev" ]; then + eval _dev=\$"$nr" + [ -n "$_dev" ]; dev="dev $_dev" + fi + if [ $p = "id" ]; then + eval _id=\$"$nr" + [ -n "$_id" ]; id="id $_id" + fi + if [ $p = "port" ]; then + eval _port=\$"$nr" + [ -n "$_port" ]; port="port $_port" + fi + + nr=$((nr + 1)) + done + + if [ $ip_mptcp -eq 1 ]; then + ip -n $ns mptcp endpoint add $addr ${_flags//","/" "} $dev $id $port + else + ip netns exec $ns ./pm_nl_ctl add $addr $flags $dev $id $port + fi +} + +pm_nl_del_endpoint() +{ + local ns=$1 + local id=$2 + local addr=$3 + + if [ $ip_mptcp -eq 1 ]; then + ip -n $ns mptcp endpoint delete id $id $addr + else + ip netns exec $ns ./pm_nl_ctl del $id $addr + fi +} + +pm_nl_flush_endpoint() +{ + local ns=$1 + + if [ $ip_mptcp -eq 1 ]; then + ip -n $ns mptcp endpoint flush + else + ip netns exec $ns ./pm_nl_ctl flush + fi +} + +pm_nl_show_endpoints() +{ + local ns=$1 + + if [ $ip_mptcp -eq 1 ]; then + ip -n $ns mptcp endpoint show + else + ip netns exec $ns ./pm_nl_ctl dump + fi +} + +pm_nl_change_endpoint() +{ + local ns=$1 + local id=$2 + local flags=$3 + + if [ $ip_mptcp -eq 1 ]; then + ip -n $ns mptcp endpoint change id $id ${flags//","/" "} + else + ip netns exec $ns ./pm_nl_ctl set id $id flags $flags + fi +} + +pm_nl_check_endpoint() +{ + local line expected_line + local need_title=$1 + local msg="$2" + local ns=$3 + local addr=$4 + local _flags="" + local flags + local _port + local port + local dev + local _id + local id + + if [ "${need_title}" = 1 ]; then + printf "%03u %-36s %s" "${TEST_COUNT}" "${TEST_NAME}" "${msg}" + else + printf "%-${nr_blank}s %s" " " "${msg}" + fi + + shift 4 + while [ -n "$1" ]; do + if [ $1 = "flags" ]; then + _flags=$2 + [ -n "$_flags" ]; flags="flags $_flags" + shift + elif [ $1 = "dev" ]; then + [ -n "$2" ]; dev="dev $1" + shift + elif [ $1 = "id" ]; then + _id=$2 + [ -n "$_id" ]; id="id $_id" + shift + elif [ $1 = "port" ]; then + _port=$2 + [ -n "$_port" ]; port=" port $_port" + shift + fi + + shift + done + + if [ -z "$id" ]; then + echo "[skip] bad test - missing endpoint id" + return + fi + + if [ $ip_mptcp -eq 1 ]; then + line=$(ip -n $ns mptcp endpoint show $id) + # the dump order is: address id flags port dev + expected_line="$addr" + [ -n "$addr" ] && expected_line="$expected_line $addr" + expected_line="$expected_line $id" + [ -n "$_flags" ] && expected_line="$expected_line ${_flags//","/" "}" + [ -n "$dev" ] && expected_line="$expected_line $dev" + [ -n "$port" ] && expected_line="$expected_line $port" + else + line=$(ip netns exec $ns ./pm_nl_ctl get $_id) + # the dump order is: id flags dev address port + expected_line="$id" + [ -n "$flags" ] && expected_line="$expected_line $flags" + [ -n "$dev" ] && expected_line="$expected_line $dev" + [ -n "$addr" ] && expected_line="$expected_line $addr" + [ -n "$_port" ] && expected_line="$expected_line $_port" + fi + if [ "$line" = "$expected_line" ]; then + echo "[ ok ]" + else + echo "[fail] expected '$expected_line' found '$line'" + fail_test + fi +} + +filter_tcp_from() +{ + local ns="${1}" + local src="${2}" + local target="${3}" + + ip netns exec "${ns}" iptables -A INPUT -s "${src}" -p tcp -j "${target}" +} + do_transfer() { - listener_ns="$1" - connector_ns="$2" - cl_proto="$3" - srv_proto="$4" - connect_addr="$5" - test_link_fail="$6" - addr_nr_ns1="$7" - addr_nr_ns2="$8" - speed="$9" - bkup="${10}" - - port=$((10000+$TEST_COUNT)) - TEST_COUNT=$((TEST_COUNT+1)) + local listener_ns="$1" + local connector_ns="$2" + local cl_proto="$3" + local srv_proto="$4" + local connect_addr="$5" + local test_link_fail="$6" + local addr_nr_ns1="$7" + local addr_nr_ns2="$8" + local speed="$9" + local sflags="${10}" + + local port=$((10000 + TEST_COUNT - 1)) + local cappid :> "$cout" :> "$sout" :> "$capout" if [ $capture -eq 1 ]; then + local capuser if [ -z $SUDO_USER ] ; then capuser="" else @@ -318,12 +628,19 @@ do_transfer() NSTAT_HISTORY=/tmp/${connector_ns}.nstat ip netns exec ${connector_ns} \ nstat -n + local extra_args if [ $speed = "fast" ]; then - mptcp_connect="./mptcp_connect -j" + extra_args="-j" elif [ $speed = "slow" ]; then - mptcp_connect="./mptcp_connect -r 50" - elif [ $speed = "least" ]; then - mptcp_connect="./mptcp_connect -r 10" + extra_args="-r 50" + elif [[ $speed = "speed_"* ]]; then + extra_args="-r ${speed:6}" + fi + + if [[ "${addr_nr_ns2}" = "fastclose_"* ]]; then + # disconnect + extra_args="$extra_args -I ${addr_nr_ns2:10}" + addr_nr_ns2=0 fi local local_addr @@ -333,43 +650,51 @@ do_transfer() local_addr="0.0.0.0" fi - if [ "$test_link_fail" -eq 2 ];then + if [ "$test_link_fail" -gt 1 ];then timeout ${timeout_test} \ ip netns exec ${listener_ns} \ - $mptcp_connect -t ${timeout_poll} -l -p $port -s ${srv_proto} \ - ${local_addr} < "$sinfail" > "$sout" & + ./mptcp_connect -t ${timeout_poll} -l -p $port -s ${srv_proto} \ + $extra_args ${local_addr} < "$sinfail" > "$sout" & else timeout ${timeout_test} \ ip netns exec ${listener_ns} \ - $mptcp_connect -t ${timeout_poll} -l -p $port -s ${srv_proto} \ - ${local_addr} < "$sin" > "$sout" & + ./mptcp_connect -t ${timeout_poll} -l -p $port -s ${srv_proto} \ + $extra_args ${local_addr} < "$sin" > "$sout" & fi - spid=$! + local spid=$! wait_local_port_listen "${listener_ns}" "${port}" if [ "$test_link_fail" -eq 0 ];then timeout ${timeout_test} \ ip netns exec ${connector_ns} \ - $mptcp_connect -t ${timeout_poll} -p $port -s ${cl_proto} \ - $connect_addr < "$cin" > "$cout" & - else + ./mptcp_connect -t ${timeout_poll} -p $port -s ${cl_proto} \ + $extra_args $connect_addr < "$cin" > "$cout" & + elif [ "$test_link_fail" -eq 1 ] || [ "$test_link_fail" -eq 2 ];then ( cat "$cinfail" ; sleep 2; link_failure $listener_ns ; cat "$cinfail" ) | \ tee "$cinsent" | \ timeout ${timeout_test} \ ip netns exec ${connector_ns} \ - $mptcp_connect -t ${timeout_poll} -p $port -s ${cl_proto} \ - $connect_addr > "$cout" & + ./mptcp_connect -t ${timeout_poll} -p $port -s ${cl_proto} \ + $extra_args $connect_addr > "$cout" & + else + tee "$cinsent" < "$cinfail" | \ + timeout ${timeout_test} \ + ip netns exec ${connector_ns} \ + ./mptcp_connect -t ${timeout_poll} -p $port -s ${cl_proto} \ + $extra_args $connect_addr > "$cout" & fi - cpid=$! + local cpid=$! # let the mptcp subflow be established in background before # do endpoint manipulation - [ $addr_nr_ns1 = "0" -a $addr_nr_ns2 = "0" ] || sleep 1 + if [ $addr_nr_ns1 != "0" ] || [ $addr_nr_ns2 != "0" ]; then + sleep 1 + fi if [ $addr_nr_ns1 -gt 0 ]; then - let add_nr_ns1=addr_nr_ns1 - counter=2 + local counter=2 + local add_nr_ns1=${addr_nr_ns1} while [ $add_nr_ns1 -gt 0 ]; do local addr if is_v6 "${connect_addr}"; then @@ -377,35 +702,43 @@ do_transfer() else addr="10.0.$counter.1" fi - ip netns exec $ns1 ./pm_nl_ctl add $addr flags signal - let counter+=1 - let add_nr_ns1-=1 + pm_nl_add_endpoint $ns1 $addr flags signal + counter=$((counter + 1)) + add_nr_ns1=$((add_nr_ns1 - 1)) done elif [ $addr_nr_ns1 -lt 0 ]; then - let rm_nr_ns1=-addr_nr_ns1 + local rm_nr_ns1=$((-addr_nr_ns1)) if [ $rm_nr_ns1 -lt 8 ]; then - counter=1 - pos=1 - dump=(`ip netns exec ${listener_ns} ./pm_nl_ctl dump`) - if [ ${#dump[@]} -gt 0 ]; then - while [ $counter -le $rm_nr_ns1 ] - do - id=${dump[$pos]} - rm_addr=$(rm_addr_count ${connector_ns}) - ip netns exec ${listener_ns} ./pm_nl_ctl del $id - wait_rm_addr ${connector_ns} ${rm_addr} - let counter+=1 - let pos+=5 + local counter=0 + local line + pm_nl_show_endpoints ${listener_ns} | while read -r line; do + # shellcheck disable=SC2206 # we do want to split per word + local arr=($line) + local nr=0 + + local i + for i in "${arr[@]}"; do + if [ $i = "id" ]; then + if [ $counter -eq $rm_nr_ns1 ]; then + break + fi + id=${arr[$nr+1]} + rm_addr=$(rm_addr_count ${connector_ns}) + pm_nl_del_endpoint ${listener_ns} $id + wait_rm_addr ${connector_ns} ${rm_addr} + counter=$((counter + 1)) + fi + nr=$((nr + 1)) done - fi + done elif [ $rm_nr_ns1 -eq 8 ]; then - ip netns exec ${listener_ns} ./pm_nl_ctl flush + pm_nl_flush_endpoint ${listener_ns} elif [ $rm_nr_ns1 -eq 9 ]; then - ip netns exec ${listener_ns} ./pm_nl_ctl del 0 ${connect_addr} + pm_nl_del_endpoint ${listener_ns} 0 ${connect_addr} fi fi - flags="subflow" + local flags="subflow" if [[ "${addr_nr_ns2}" = "fullmesh_"* ]]; then flags="${flags},fullmesh" addr_nr_ns2=${addr_nr_ns2:9} @@ -413,11 +746,11 @@ do_transfer() # if newly added endpoints must be deleted, give the background msk # some time to created them - [ $addr_nr_ns1 -gt 0 -a $addr_nr_ns2 -lt 0 ] && sleep 1 + [ $addr_nr_ns1 -gt 0 ] && [ $addr_nr_ns2 -lt 0 ] && sleep 1 if [ $addr_nr_ns2 -gt 0 ]; then - let add_nr_ns2=addr_nr_ns2 - counter=3 + local add_nr_ns2=${addr_nr_ns2} + local counter=3 while [ $add_nr_ns2 -gt 0 ]; do local addr if is_v6 "${connect_addr}"; then @@ -425,30 +758,40 @@ do_transfer() else addr="10.0.$counter.2" fi - ip netns exec $ns2 ./pm_nl_ctl add $addr flags $flags - let counter+=1 - let add_nr_ns2-=1 + pm_nl_add_endpoint $ns2 $addr flags $flags + counter=$((counter + 1)) + add_nr_ns2=$((add_nr_ns2 - 1)) done elif [ $addr_nr_ns2 -lt 0 ]; then - let rm_nr_ns2=-addr_nr_ns2 + local rm_nr_ns2=$((-addr_nr_ns2)) if [ $rm_nr_ns2 -lt 8 ]; then - counter=1 - pos=1 - dump=(`ip netns exec ${connector_ns} ./pm_nl_ctl dump`) - if [ ${#dump[@]} -gt 0 ]; then - while [ $counter -le $rm_nr_ns2 ] - do - # rm_addr are serialized, allow the previous one to complete - id=${dump[$pos]} - rm_addr=$(rm_addr_count ${listener_ns}) - ip netns exec ${connector_ns} ./pm_nl_ctl del $id - wait_rm_addr ${listener_ns} ${rm_addr} - let counter+=1 - let pos+=5 + local counter=0 + local line + pm_nl_show_endpoints ${connector_ns} | while read -r line; do + # shellcheck disable=SC2206 # we do want to split per word + local arr=($line) + local nr=0 + + local i + for i in "${arr[@]}"; do + if [ $i = "id" ]; then + if [ $counter -eq $rm_nr_ns2 ]; then + break + fi + local id rm_addr + # rm_addr are serialized, allow the previous one to + # complete + id=${arr[$nr+1]} + rm_addr=$(rm_addr_count ${listener_ns}) + pm_nl_del_endpoint ${connector_ns} $id + wait_rm_addr ${listener_ns} ${rm_addr} + counter=$((counter + 1)) + fi + nr=$((nr + 1)) done - fi + done elif [ $rm_nr_ns2 -eq 8 ]; then - ip netns exec ${connector_ns} ./pm_nl_ctl flush + pm_nl_flush_endpoint ${connector_ns} elif [ $rm_nr_ns2 -eq 9 ]; then local addr if is_v6 "${connect_addr}"; then @@ -456,26 +799,38 @@ do_transfer() else addr="10.0.1.2" fi - ip netns exec ${connector_ns} ./pm_nl_ctl del 0 $addr + pm_nl_del_endpoint ${connector_ns} 0 $addr fi fi - if [ ! -z $bkup ]; then + if [ -n "${sflags}" ]; then sleep 1 + + local netns for netns in "$ns1" "$ns2"; do - dump=(`ip netns exec $netns ./pm_nl_ctl dump`) - if [ ${#dump[@]} -gt 0 ]; then - addr=${dump[${#dump[@]} - 1]} - backup="ip netns exec $netns ./pm_nl_ctl set $addr flags $bkup" - $backup - fi + local line + pm_nl_show_endpoints $netns | while read -r line; do + # shellcheck disable=SC2206 # we do want to split per word + local arr=($line) + local nr=0 + local id + + local i + for i in "${arr[@]}"; do + if [ $i = "id" ]; then + id=${arr[$nr+1]} + fi + nr=$((nr + 1)) + done + pm_nl_change_endpoint $netns $id $sflags + done done fi wait $cpid - retc=$? + local retc=$? wait $spid - rets=$? + local rets=$? if [ $capture -eq 1 ]; then sleep 1 @@ -497,11 +852,11 @@ do_transfer() cat /tmp/${connector_ns}.out cat "$capout" - ret=1 + fail_test return 1 fi - if [ "$test_link_fail" -eq 2 ];then + if [ "$test_link_fail" -gt 1 ];then check_transfer $sinfail $cout "file received by client" else check_transfer $sin $cout "file received by client" @@ -525,9 +880,9 @@ do_transfer() make_file() { - name=$1 - who=$2 - size=$3 + local name=$1 + local who=$2 + local size=$3 dd if=/dev/urandom of="$name" bs=1024 count=$size 2> /dev/null echo -e "\nMPTCP_TEST_FILE_END_MARKER" >> "$name" @@ -537,33 +892,49 @@ make_file() run_tests() { - listener_ns="$1" - connector_ns="$2" - connect_addr="$3" - test_linkfail="${4:-0}" - addr_nr_ns1="${5:-0}" - addr_nr_ns2="${6:-0}" - speed="${7:-fast}" - bkup="${8:-""}" - lret=0 - oldin="" - + local listener_ns="$1" + local connector_ns="$2" + local connect_addr="$3" + local test_linkfail="${4:-0}" + local addr_nr_ns1="${5:-0}" + local addr_nr_ns2="${6:-0}" + local speed="${7:-fast}" + local sflags="${8:-""}" + + local size + + # The values above 2 are reused to make test files + # with the given sizes (KB) + if [ "$test_linkfail" -gt 2 ]; then + size=$test_linkfail + + if [ -z "$cinfail" ]; then + cinfail=$(mktemp) + fi + make_file "$cinfail" "client" $size # create the input file for the failure test when # the first failure test run - if [ "$test_linkfail" -ne 0 -a -z "$cinfail" ]; then + elif [ "$test_linkfail" -ne 0 ] && [ -z "$cinfail" ]; then # the client file must be considerably larger # of the maximum expected cwin value, or the # link utilization will be not predicable size=$((RANDOM%2)) size=$((size+1)) size=$((size*8192)) - size=$((size + ( $RANDOM % 8192) )) + size=$((size + ( RANDOM % 8192) )) cinfail=$(mktemp) make_file "$cinfail" "client" $size fi - if [ "$test_linkfail" -eq 2 -a -z "$sinfail" ]; then + if [ "$test_linkfail" -gt 2 ]; then + size=$test_linkfail + + if [ -z "$sinfail" ]; then + sinfail=$(mktemp) + fi + make_file "$sinfail" "server" $size + elif [ "$test_linkfail" -eq 2 ] && [ -z "$sinfail" ]; then size=$((RANDOM%16)) size=$((size+1)) size=$((size*2048)) @@ -573,8 +944,7 @@ run_tests() fi do_transfer ${listener_ns} ${connector_ns} MPTCP MPTCP ${connect_addr} \ - ${test_linkfail} ${addr_nr_ns1} ${addr_nr_ns2} ${speed} ${bkup} - lret=$? + ${test_linkfail} ${addr_nr_ns1} ${addr_nr_ns2} ${speed} ${sflags} } dump_stats() @@ -587,31 +957,40 @@ dump_stats() chk_csum_nr() { - local msg=${1:-""} + local csum_ns1=${1:-0} + local csum_ns2=${2:-0} local count local dump_stats + local allow_multi_errors_ns1=0 + local allow_multi_errors_ns2=0 - if [ ! -z "$msg" ]; then - printf "%02u" "$TEST_COUNT" - else - echo -n " " + if [[ "${csum_ns1}" = "+"* ]]; then + allow_multi_errors_ns1=1 + csum_ns1=${csum_ns1:1} fi - printf " %-36s %s" "$msg" "sum" - count=`ip netns exec $ns1 nstat -as | grep MPTcpExtDataCsumErr | awk '{print $2}'` + if [[ "${csum_ns2}" = "+"* ]]; then + allow_multi_errors_ns2=1 + csum_ns2=${csum_ns2:1} + fi + + printf "%-${nr_blank}s %s" " " "sum" + count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtDataCsumErr | awk '{print $2}') [ -z "$count" ] && count=0 - if [ "$count" != 0 ]; then - echo "[fail] got $count data checksum error[s] expected 0" - ret=1 + if { [ "$count" != $csum_ns1 ] && [ $allow_multi_errors_ns1 -eq 0 ]; } || + { [ "$count" -lt $csum_ns1 ] && [ $allow_multi_errors_ns1 -eq 1 ]; }; then + echo "[fail] got $count data checksum error[s] expected $csum_ns1" + fail_test dump_stats=1 else echo -n "[ ok ]" fi echo -n " - csum " - count=`ip netns exec $ns2 nstat -as | grep MPTcpExtDataCsumErr | awk '{print $2}'` + count=$(ip netns exec $ns2 nstat -as | grep MPTcpExtDataCsumErr | awk '{print $2}') [ -z "$count" ] && count=0 - if [ "$count" != 0 ]; then - echo "[fail] got $count data checksum error[s] expected 0" - ret=1 + if { [ "$count" != $csum_ns2 ] && [ $allow_multi_errors_ns2 -eq 0 ]; } || + { [ "$count" -lt $csum_ns2 ] && [ $allow_multi_errors_ns2 -eq 1 ]; }; then + echo "[fail] got $count data checksum error[s] expected $csum_ns2" + fail_test dump_stats=1 else echo "[ ok ]" @@ -621,28 +1000,28 @@ chk_csum_nr() chk_fail_nr() { - local mp_fail_nr_tx=$1 - local mp_fail_nr_rx=$2 + local fail_tx=$1 + local fail_rx=$2 local count local dump_stats - printf "%-39s %s" " " "ftx" - count=`ip netns exec $ns1 nstat -as | grep MPTcpExtMPFailTx | awk '{print $2}'` + printf "%-${nr_blank}s %s" " " "ftx" + count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtMPFailTx | awk '{print $2}') [ -z "$count" ] && count=0 - if [ "$count" != "$mp_fail_nr_tx" ]; then - echo "[fail] got $count MP_FAIL[s] TX expected $mp_fail_nr_tx" - ret=1 + if [ "$count" != "$fail_tx" ]; then + echo "[fail] got $count MP_FAIL[s] TX expected $fail_tx" + fail_test dump_stats=1 else echo -n "[ ok ]" fi - echo -n " - frx " - count=`ip netns exec $ns2 nstat -as | grep MPTcpExtMPFailRx | awk '{print $2}'` + echo -n " - failrx" + count=$(ip netns exec $ns2 nstat -as | grep MPTcpExtMPFailRx | awk '{print $2}') [ -z "$count" ] && count=0 - if [ "$count" != "$mp_fail_nr_rx" ]; then - echo "[fail] got $count MP_FAIL[s] RX expected $mp_fail_nr_rx" - ret=1 + if [ "$count" != "$fail_rx" ]; then + echo "[fail] got $count MP_FAIL[s] RX expected $fail_rx" + fail_test dump_stats=1 else echo "[ ok ]" @@ -651,51 +1030,146 @@ chk_fail_nr() [ "${dump_stats}" = 1 ] && dump_stats } +chk_fclose_nr() +{ + local fclose_tx=$1 + local fclose_rx=$2 + local count + local dump_stats + + printf "%-${nr_blank}s %s" " " "ctx" + count=$(ip netns exec $ns2 nstat -as | grep MPTcpExtMPFastcloseTx | awk '{print $2}') + [ -z "$count" ] && count=0 + if [ "$count" != "$fclose_tx" ]; then + echo "[fail] got $count MP_FASTCLOSE[s] TX expected $fclose_tx" + fail_test + dump_stats=1 + else + echo -n "[ ok ]" + fi + + echo -n " - fclzrx" + count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtMPFastcloseRx | awk '{print $2}') + [ -z "$count" ] && count=0 + if [ "$count" != "$fclose_rx" ]; then + echo "[fail] got $count MP_FASTCLOSE[s] RX expected $fclose_rx" + fail_test + dump_stats=1 + else + echo "[ ok ]" + fi + + [ "${dump_stats}" = 1 ] && dump_stats +} + +chk_rst_nr() +{ + local rst_tx=$1 + local rst_rx=$2 + local ns_invert=${3:-""} + local count + local dump_stats + local ns_tx=$ns1 + local ns_rx=$ns2 + local extra_msg="" + + if [[ $ns_invert = "invert" ]]; then + ns_tx=$ns2 + ns_rx=$ns1 + extra_msg=" invert" + fi + + printf "%-${nr_blank}s %s" " " "rtx" + count=$(ip netns exec $ns_tx nstat -as | grep MPTcpExtMPRstTx | awk '{print $2}') + [ -z "$count" ] && count=0 + if [ "$count" != "$rst_tx" ]; then + echo "[fail] got $count MP_RST[s] TX expected $rst_tx" + fail_test + dump_stats=1 + else + echo -n "[ ok ]" + fi + + echo -n " - rstrx " + count=$(ip netns exec $ns_rx nstat -as | grep MPTcpExtMPRstRx | awk '{print $2}') + [ -z "$count" ] && count=0 + if [ "$count" != "$rst_rx" ]; then + echo "[fail] got $count MP_RST[s] RX expected $rst_rx" + fail_test + dump_stats=1 + else + echo -n "[ ok ]" + fi + + [ "${dump_stats}" = 1 ] && dump_stats + + echo "$extra_msg" +} + chk_join_nr() { - local msg="$1" - local syn_nr=$2 - local syn_ack_nr=$3 - local ack_nr=$4 + local syn_nr=$1 + local syn_ack_nr=$2 + local ack_nr=$3 + local csum_ns1=${4:-0} + local csum_ns2=${5:-0} + local fail_nr=${6:-0} + local rst_nr=${7:-0} + local corrupted_pkts=${8:-0} local count local dump_stats + local with_cookie + local title="${TEST_NAME}" - printf "%02u %-36s %s" "$TEST_COUNT" "$msg" "syn" - count=`ip netns exec $ns1 nstat -as | grep MPTcpExtMPJoinSynRx | awk '{print $2}'` + if [ "${corrupted_pkts}" -gt 0 ]; then + title+=": ${corrupted_pkts} corrupted pkts" + fi + + printf "%03u %-36s %s" "${TEST_COUNT}" "${title}" "syn" + count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtMPJoinSynRx | awk '{print $2}') [ -z "$count" ] && count=0 if [ "$count" != "$syn_nr" ]; then echo "[fail] got $count JOIN[s] syn expected $syn_nr" - ret=1 + fail_test dump_stats=1 else echo -n "[ ok ]" fi echo -n " - synack" - count=`ip netns exec $ns2 nstat -as | grep MPTcpExtMPJoinSynAckRx | awk '{print $2}'` + with_cookie=$(ip netns exec $ns2 sysctl -n net.ipv4.tcp_syncookies) + count=$(ip netns exec $ns2 nstat -as | grep MPTcpExtMPJoinSynAckRx | awk '{print $2}') [ -z "$count" ] && count=0 if [ "$count" != "$syn_ack_nr" ]; then - echo "[fail] got $count JOIN[s] synack expected $syn_ack_nr" - ret=1 - dump_stats=1 + # simult connections exceeding the limit with cookie enabled could go up to + # synack validation as the conn limit can be enforced reliably only after + # the subflow creation + if [ "$with_cookie" = 2 ] && [ "$count" -gt "$syn_ack_nr" ] && [ "$count" -le "$syn_nr" ]; then + echo -n "[ ok ]" + else + echo "[fail] got $count JOIN[s] synack expected $syn_ack_nr" + fail_test + dump_stats=1 + fi else echo -n "[ ok ]" fi echo -n " - ack" - count=`ip netns exec $ns1 nstat -as | grep MPTcpExtMPJoinAckRx | awk '{print $2}'` + count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtMPJoinAckRx | awk '{print $2}') [ -z "$count" ] && count=0 if [ "$count" != "$ack_nr" ]; then echo "[fail] got $count JOIN[s] ack expected $ack_nr" - ret=1 + fail_test dump_stats=1 else echo "[ ok ]" fi [ "${dump_stats}" = 1 ] && dump_stats if [ $checksum -eq 1 ]; then - chk_csum_nr - chk_fail_nr 0 0 + chk_csum_nr $csum_ns1 $csum_ns2 + chk_fail_nr $fail_nr $fail_nr + chk_rst_nr $rst_nr $rst_nr fi } @@ -714,19 +1188,19 @@ chk_stale_nr() local stale_nr local recover_nr - printf "%-39s %-18s" " " "stale" - stale_nr=`ip netns exec $ns nstat -as | grep MPTcpExtSubflowStale | awk '{print $2}'` + printf "%-${nr_blank}s %-18s" " " "stale" + stale_nr=$(ip netns exec $ns nstat -as | grep MPTcpExtSubflowStale | awk '{print $2}') [ -z "$stale_nr" ] && stale_nr=0 - recover_nr=`ip netns exec $ns nstat -as | grep MPTcpExtSubflowRecover | awk '{print $2}'` + recover_nr=$(ip netns exec $ns nstat -as | grep MPTcpExtSubflowRecover | awk '{print $2}') [ -z "$recover_nr" ] && recover_nr=0 if [ $stale_nr -lt $stale_min ] || - [ $stale_max -gt 0 -a $stale_nr -gt $stale_max ] || - [ $((stale_nr - $recover_nr)) -ne $stale_delta ]; then + { [ $stale_max -gt 0 ] && [ $stale_nr -gt $stale_max ]; } || + [ $((stale_nr - recover_nr)) -ne $stale_delta ]; then echo "[fail] got $stale_nr stale[s] $recover_nr recover[s], " \ " expected stale in range [$stale_min..$stale_max]," \ " stale-recover delta $stale_delta " - ret=1 + fail_test dump_stats=1 else echo "[ ok ]" @@ -751,24 +1225,30 @@ chk_add_nr() local mis_ack_nr=${8:-0} local count local dump_stats + local timeout + + timeout=$(ip netns exec $ns1 sysctl -n net.mptcp.add_addr_timeout) - printf "%-39s %s" " " "add" - count=`ip netns exec $ns2 nstat -as | grep MPTcpExtAddAddr | awk '{print $2}'` + printf "%-${nr_blank}s %s" " " "add" + count=$(ip netns exec $ns2 nstat -as MPTcpExtAddAddr | grep MPTcpExtAddAddr | awk '{print $2}') [ -z "$count" ] && count=0 - if [ "$count" != "$add_nr" ]; then + + # if the test configured a short timeout tolerate greater then expected + # add addrs options, due to retransmissions + if [ "$count" != "$add_nr" ] && { [ "$timeout" -gt 1 ] || [ "$count" -lt "$add_nr" ]; }; then echo "[fail] got $count ADD_ADDR[s] expected $add_nr" - ret=1 + fail_test dump_stats=1 else echo -n "[ ok ]" fi echo -n " - echo " - count=`ip netns exec $ns1 nstat -as | grep MPTcpExtEchoAdd | awk '{print $2}'` + count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtEchoAdd | awk '{print $2}') [ -z "$count" ] && count=0 if [ "$count" != "$echo_nr" ]; then echo "[fail] got $count ADD_ADDR echo[s] expected $echo_nr" - ret=1 + fail_test dump_stats=1 else echo -n "[ ok ]" @@ -776,76 +1256,76 @@ chk_add_nr() if [ $port_nr -gt 0 ]; then echo -n " - pt " - count=`ip netns exec $ns2 nstat -as | grep MPTcpExtPortAdd | awk '{print $2}'` + count=$(ip netns exec $ns2 nstat -as | grep MPTcpExtPortAdd | awk '{print $2}') [ -z "$count" ] && count=0 if [ "$count" != "$port_nr" ]; then echo "[fail] got $count ADD_ADDR[s] with a port-number expected $port_nr" - ret=1 + fail_test dump_stats=1 else echo "[ ok ]" fi - printf "%-39s %s" " " "syn" - count=`ip netns exec $ns1 nstat -as | grep MPTcpExtMPJoinPortSynRx | - awk '{print $2}'` + printf "%-${nr_blank}s %s" " " "syn" + count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtMPJoinPortSynRx | + awk '{print $2}') [ -z "$count" ] && count=0 if [ "$count" != "$syn_nr" ]; then echo "[fail] got $count JOIN[s] syn with a different \ port-number expected $syn_nr" - ret=1 + fail_test dump_stats=1 else echo -n "[ ok ]" fi echo -n " - synack" - count=`ip netns exec $ns2 nstat -as | grep MPTcpExtMPJoinPortSynAckRx | - awk '{print $2}'` + count=$(ip netns exec $ns2 nstat -as | grep MPTcpExtMPJoinPortSynAckRx | + awk '{print $2}') [ -z "$count" ] && count=0 if [ "$count" != "$syn_ack_nr" ]; then echo "[fail] got $count JOIN[s] synack with a different \ port-number expected $syn_ack_nr" - ret=1 + fail_test dump_stats=1 else echo -n "[ ok ]" fi echo -n " - ack" - count=`ip netns exec $ns1 nstat -as | grep MPTcpExtMPJoinPortAckRx | - awk '{print $2}'` + count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtMPJoinPortAckRx | + awk '{print $2}') [ -z "$count" ] && count=0 if [ "$count" != "$ack_nr" ]; then echo "[fail] got $count JOIN[s] ack with a different \ port-number expected $ack_nr" - ret=1 + fail_test dump_stats=1 else echo "[ ok ]" fi - printf "%-39s %s" " " "syn" - count=`ip netns exec $ns1 nstat -as | grep MPTcpExtMismatchPortSynRx | - awk '{print $2}'` + printf "%-${nr_blank}s %s" " " "syn" + count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtMismatchPortSynRx | + awk '{print $2}') [ -z "$count" ] && count=0 if [ "$count" != "$mis_syn_nr" ]; then echo "[fail] got $count JOIN[s] syn with a mismatched \ port-number expected $mis_syn_nr" - ret=1 + fail_test dump_stats=1 else echo -n "[ ok ]" fi echo -n " - ack " - count=`ip netns exec $ns1 nstat -as | grep MPTcpExtMismatchPortAckRx | - awk '{print $2}'` + count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtMismatchPortAckRx | + awk '{print $2}') [ -z "$count" ] && count=0 if [ "$count" != "$mis_ack_nr" ]; then echo "[fail] got $count JOIN[s] ack with a mismatched \ port-number expected $mis_ack_nr" - ret=1 + fail_test dump_stats=1 else echo "[ ok ]" @@ -861,43 +1341,75 @@ chk_rm_nr() { local rm_addr_nr=$1 local rm_subflow_nr=$2 - local invert=${3:-""} + local invert + local simult local count local dump_stats - local addr_ns - local subflow_ns + local addr_ns=$ns1 + local subflow_ns=$ns2 + local extra_msg="" + + shift 2 + while [ -n "$1" ]; do + [ "$1" = "invert" ] && invert=true + [ "$1" = "simult" ] && simult=true + shift + done if [ -z $invert ]; then addr_ns=$ns1 subflow_ns=$ns2 - elif [ $invert = "invert" ]; then + elif [ $invert = "true" ]; then addr_ns=$ns2 subflow_ns=$ns1 + extra_msg=" invert" fi - printf "%-39s %s" " " "rm " - count=`ip netns exec $addr_ns nstat -as | grep MPTcpExtRmAddr | awk '{print $2}'` + printf "%-${nr_blank}s %s" " " "rm " + count=$(ip netns exec $addr_ns nstat -as | grep MPTcpExtRmAddr | awk '{print $2}') [ -z "$count" ] && count=0 if [ "$count" != "$rm_addr_nr" ]; then echo "[fail] got $count RM_ADDR[s] expected $rm_addr_nr" - ret=1 + fail_test dump_stats=1 else echo -n "[ ok ]" fi - echo -n " - sf " - count=`ip netns exec $subflow_ns nstat -as | grep MPTcpExtRmSubflow | awk '{print $2}'` + echo -n " - rmsf " + count=$(ip netns exec $subflow_ns nstat -as | grep MPTcpExtRmSubflow | awk '{print $2}') [ -z "$count" ] && count=0 + if [ -n "$simult" ]; then + local cnt suffix + + cnt=$(ip netns exec $addr_ns nstat -as | grep MPTcpExtRmSubflow | awk '{print $2}') + + # in case of simult flush, the subflow removal count on each side is + # unreliable + [ -z "$cnt" ] && cnt=0 + count=$((count + cnt)) + [ "$count" != "$rm_subflow_nr" ] && suffix="$count in [$rm_subflow_nr:$((rm_subflow_nr*2))]" + if [ $count -ge "$rm_subflow_nr" ] && \ + [ "$count" -le "$((rm_subflow_nr *2 ))" ]; then + echo "[ ok ] $suffix" + else + echo "[fail] got $count RM_SUBFLOW[s] expected in range [$rm_subflow_nr:$((rm_subflow_nr*2))]" + fail_test + dump_stats=1 + fi + return + fi if [ "$count" != "$rm_subflow_nr" ]; then echo "[fail] got $count RM_SUBFLOW[s] expected $rm_subflow_nr" - ret=1 + fail_test dump_stats=1 else - echo "[ ok ]" + echo -n "[ ok ]" fi [ "${dump_stats}" = 1 ] && dump_stats + + echo "$extra_msg" } chk_prio_nr() @@ -907,23 +1419,23 @@ chk_prio_nr() local count local dump_stats - printf "%-39s %s" " " "ptx" - count=`ip netns exec $ns1 nstat -as | grep MPTcpExtMPPrioTx | awk '{print $2}'` + printf "%-${nr_blank}s %s" " " "ptx" + count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtMPPrioTx | awk '{print $2}') [ -z "$count" ] && count=0 if [ "$count" != "$mp_prio_nr_tx" ]; then echo "[fail] got $count MP_PRIO[s] TX expected $mp_prio_nr_tx" - ret=1 + fail_test dump_stats=1 else echo -n "[ ok ]" fi echo -n " - prx " - count=`ip netns exec $ns1 nstat -as | grep MPTcpExtMPPrioRx | awk '{print $2}'` + count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtMPPrioRx | awk '{print $2}') [ -z "$count" ] && count=0 if [ "$count" != "$mp_prio_nr_rx" ]; then echo "[fail] got $count MP_PRIO[s] RX expected $mp_prio_nr_rx" - ret=1 + fail_test dump_stats=1 else echo "[ ok ]" @@ -938,29 +1450,33 @@ chk_link_usage() local link=$2 local out=$3 local expected_rate=$4 - local tx_link=`ip netns exec $ns cat /sys/class/net/$link/statistics/tx_bytes` - local tx_total=`ls -l $out | awk '{print $5}'` - local tx_rate=$((tx_link * 100 / $tx_total)) + + local tx_link tx_total + tx_link=$(ip netns exec $ns cat /sys/class/net/$link/statistics/tx_bytes) + tx_total=$(stat --format=%s $out) + local tx_rate=$((tx_link * 100 / tx_total)) local tolerance=5 - printf "%-39s %-18s" " " "link usage" - if [ $tx_rate -lt $((expected_rate - $tolerance)) -o \ - $tx_rate -gt $((expected_rate + $tolerance)) ]; then + printf "%-${nr_blank}s %-18s" " " "link usage" + if [ $tx_rate -lt $((expected_rate - tolerance)) ] || \ + [ $tx_rate -gt $((expected_rate + tolerance)) ]; then echo "[fail] got $tx_rate% usage, expected $expected_rate%" - ret=1 + fail_test else echo "[ ok ]" fi } -wait_for_tw() +wait_attempt_fail() { local timeout_ms=$((timeout_poll * 1000)) local time=0 local ns=$1 while [ $time -lt $timeout_ms ]; do - local cnt=$(ip netns exec $ns ss -t state time-wait |wc -l) + local cnt + + cnt=$(ip netns exec $ns nstat -as TcpAttemptFails | grep TcpAttemptFails | awk '{print $2}') [ "$cnt" = 1 ] && return 1 time=$((time + 100)) @@ -971,873 +1487,968 @@ wait_for_tw() subflows_tests() { - reset - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "no JOIN" "0" "0" "0" + if reset "no JOIN"; then + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 0 0 0 + fi # subflow limited by client - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 0 - ip netns exec $ns2 ./pm_nl_ctl limits 0 0 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "single subflow, limited by client" 0 0 0 + if reset "single subflow, limited by client"; then + pm_nl_set_limits $ns1 0 0 + pm_nl_set_limits $ns2 0 0 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 0 0 0 + fi # subflow limited by server - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 0 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "single subflow, limited by server" 1 1 0 + if reset "single subflow, limited by server"; then + pm_nl_set_limits $ns1 0 0 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 1 1 0 + fi # subflow - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "single subflow" 1 1 1 + if reset "single subflow"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 1 1 1 + fi # multiple subflows - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 2 - ip netns exec $ns2 ./pm_nl_ctl limits 0 2 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "multiple subflows" 2 2 2 + if reset "multiple subflows"; then + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 0 2 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 2 2 2 + fi # multiple subflows limited by server - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 2 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "multiple subflows, limited by server" 2 2 1 + if reset "multiple subflows, limited by server"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 2 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 2 2 1 + fi # single subflow, dev - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow dev ns2eth3 - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "single subflow, dev" 1 1 1 + if reset "single subflow, dev"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow dev ns2eth3 + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 1 1 1 + fi } subflows_error_tests() { # If a single subflow is configured, and matches the MPC src # address, no additional subflow should be created - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.1.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow - chk_join_nr "no MPC reuse with single endpoint" 0 0 0 + if reset "no MPC reuse with single endpoint"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 10.0.1.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow + chk_join_nr 0 0 0 + fi # multiple subflows, with subflow creation error - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 2 - ip netns exec $ns2 ./pm_nl_ctl limits 0 2 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags subflow - ip netns exec $ns1 iptables -A INPUT -s 10.0.3.2 -p tcp -j REJECT - run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow - chk_join_nr "multi subflows, with failing subflow" 1 1 1 + if reset "multi subflows, with failing subflow"; then + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 0 2 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow + filter_tcp_from $ns1 10.0.3.2 REJECT + run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow + chk_join_nr 1 1 1 + fi # multiple subflows, with subflow timeout on MPJ - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 2 - ip netns exec $ns2 ./pm_nl_ctl limits 0 2 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags subflow - ip netns exec $ns1 iptables -A INPUT -s 10.0.3.2 -p tcp -j DROP - run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow - chk_join_nr "multi subflows, with subflow timeout" 1 1 1 + if reset "multi subflows, with subflow timeout"; then + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 0 2 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow + filter_tcp_from $ns1 10.0.3.2 DROP + run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow + chk_join_nr 1 1 1 + fi # multiple subflows, check that the endpoint corresponding to # closed subflow (due to reset) is not reused if additional # subflows are added later - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - ip netns exec $ns1 iptables -A INPUT -s 10.0.3.2 -p tcp -j REJECT - run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow & - - # updates in the child shell do not have any effect here, we - # need to bump the test counter for the above case - TEST_COUNT=$((TEST_COUNT+1)) - - # mpj subflow will be in TW after the reset - wait_for_tw $ns2 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags subflow - wait - - # additional subflow could be created only if the PM select - # the later endpoint, skipping the already used one - chk_join_nr "multi subflows, fair usage on close" 1 1 1 + if reset "multi subflows, fair usage on close"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + filter_tcp_from $ns1 10.0.3.2 REJECT + run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow & + + # mpj subflow will be in TW after the reset + wait_attempt_fail $ns2 + pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow + wait + + # additional subflow could be created only if the PM select + # the later endpoint, skipping the already used one + chk_join_nr 1 1 1 + fi } signal_address_tests() { # add_address, unused - reset - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "unused signal address" 0 0 0 - chk_add_nr 1 1 + if reset "unused signal address"; then + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 0 0 0 + chk_add_nr 1 1 + fi # accept and use add_addr - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 1 1 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "signal address" 1 1 1 - chk_add_nr 1 1 + if reset "signal address"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 1 1 1 + chk_add_nr 1 1 + fi # accept and use add_addr with an additional subflow # note: signal address in server ns and local addresses in client ns must # belong to different subnets or one of the listed local address could be # used for 'add_addr' subflow - reset - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal - ip netns exec $ns1 ./pm_nl_ctl limits 0 2 - ip netns exec $ns2 ./pm_nl_ctl limits 1 2 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "subflow and signal" 2 2 2 - chk_add_nr 1 1 + if reset "subflow and signal"; then + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 1 2 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 2 2 2 + chk_add_nr 1 1 + fi # accept and use add_addr with additional subflows - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 3 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 1 3 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - ip netns exec $ns2 ./pm_nl_ctl add 10.0.4.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "multiple subflows and signal" 3 3 3 - chk_add_nr 1 1 + if reset "multiple subflows and signal"; then + pm_nl_set_limits $ns1 0 3 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_set_limits $ns2 1 3 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.4.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 3 3 3 + chk_add_nr 1 1 + fi # signal addresses - reset - ip netns exec $ns1 ./pm_nl_ctl limits 3 3 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal - ip netns exec $ns1 ./pm_nl_ctl add 10.0.3.1 flags signal - ip netns exec $ns1 ./pm_nl_ctl add 10.0.4.1 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 3 3 - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "signal addresses" 3 3 3 - chk_add_nr 3 3 + if reset "signal addresses"; then + pm_nl_set_limits $ns1 3 3 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_add_endpoint $ns1 10.0.3.1 flags signal + pm_nl_add_endpoint $ns1 10.0.4.1 flags signal + pm_nl_set_limits $ns2 3 3 + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 3 3 3 + chk_add_nr 3 3 + fi # signal invalid addresses - reset - ip netns exec $ns1 ./pm_nl_ctl limits 3 3 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.12.1 flags signal - ip netns exec $ns1 ./pm_nl_ctl add 10.0.3.1 flags signal - ip netns exec $ns1 ./pm_nl_ctl add 10.0.14.1 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 3 3 - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "signal invalid addresses" 1 1 1 - chk_add_nr 3 3 + if reset "signal invalid addresses"; then + pm_nl_set_limits $ns1 3 3 + pm_nl_add_endpoint $ns1 10.0.12.1 flags signal + pm_nl_add_endpoint $ns1 10.0.3.1 flags signal + pm_nl_add_endpoint $ns1 10.0.14.1 flags signal + pm_nl_set_limits $ns2 3 3 + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 1 1 1 + chk_add_nr 3 3 + fi # signal addresses race test - reset - ip netns exec $ns1 ./pm_nl_ctl limits 4 4 - ip netns exec $ns2 ./pm_nl_ctl limits 4 4 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.1.1 flags signal - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal - ip netns exec $ns1 ./pm_nl_ctl add 10.0.3.1 flags signal - ip netns exec $ns1 ./pm_nl_ctl add 10.0.4.1 flags signal - ip netns exec $ns2 ./pm_nl_ctl add 10.0.1.2 flags signal - ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags signal - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags signal - ip netns exec $ns2 ./pm_nl_ctl add 10.0.4.2 flags signal - run_tests $ns1 $ns2 10.0.1.1 - - # the server will not signal the address terminating - # the MPC subflow - chk_add_nr 3 3 + if reset "signal addresses race test"; then + pm_nl_set_limits $ns1 4 4 + pm_nl_set_limits $ns2 4 4 + pm_nl_add_endpoint $ns1 10.0.1.1 flags signal + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_add_endpoint $ns1 10.0.3.1 flags signal + pm_nl_add_endpoint $ns1 10.0.4.1 flags signal + pm_nl_add_endpoint $ns2 10.0.1.2 flags signal + pm_nl_add_endpoint $ns2 10.0.2.2 flags signal + pm_nl_add_endpoint $ns2 10.0.3.2 flags signal + pm_nl_add_endpoint $ns2 10.0.4.2 flags signal + + # the peer could possibly miss some addr notification, allow retransmission + ip netns exec $ns1 sysctl -q net.mptcp.add_addr_timeout=1 + run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow + chk_join_nr 3 3 3 + + # the server will not signal the address terminating + # the MPC subflow + chk_add_nr 3 3 + fi } link_failure_tests() { # accept and use add_addr with additional subflows and link loss - reset - - # without any b/w limit each veth could spool the packets and get - # them acked at xmit time, so that the corresponding subflow will - # have almost always no outstanding pkts, the scheduler will pick - # always the first subflow and we will have hard time testing - # active backup and link switch-over. - # Let's set some arbitrary (low) virtual link limits. - init_shapers - ip netns exec $ns1 ./pm_nl_ctl limits 0 3 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 dev ns1eth2 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 1 3 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 dev ns2eth3 flags subflow - ip netns exec $ns2 ./pm_nl_ctl add 10.0.4.2 dev ns2eth4 flags subflow - run_tests $ns1 $ns2 10.0.1.1 1 - chk_join_nr "multiple flows, signal, link failure" 3 3 3 - chk_add_nr 1 1 - chk_stale_nr $ns2 1 5 1 + if reset "multiple flows, signal, link failure"; then + # without any b/w limit each veth could spool the packets and get + # them acked at xmit time, so that the corresponding subflow will + # have almost always no outstanding pkts, the scheduler will pick + # always the first subflow and we will have hard time testing + # active backup and link switch-over. + # Let's set some arbitrary (low) virtual link limits. + init_shapers + pm_nl_set_limits $ns1 0 3 + pm_nl_add_endpoint $ns1 10.0.2.1 dev ns1eth2 flags signal + pm_nl_set_limits $ns2 1 3 + pm_nl_add_endpoint $ns2 10.0.3.2 dev ns2eth3 flags subflow + pm_nl_add_endpoint $ns2 10.0.4.2 dev ns2eth4 flags subflow + run_tests $ns1 $ns2 10.0.1.1 1 + chk_join_nr 3 3 3 + chk_add_nr 1 1 + chk_stale_nr $ns2 1 5 1 + fi # accept and use add_addr with additional subflows and link loss # for bidirectional transfer - reset - init_shapers - ip netns exec $ns1 ./pm_nl_ctl limits 0 3 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 dev ns1eth2 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 1 3 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 dev ns2eth3 flags subflow - ip netns exec $ns2 ./pm_nl_ctl add 10.0.4.2 dev ns2eth4 flags subflow - run_tests $ns1 $ns2 10.0.1.1 2 - chk_join_nr "multi flows, signal, bidi, link fail" 3 3 3 - chk_add_nr 1 1 - chk_stale_nr $ns2 1 -1 1 + if reset "multi flows, signal, bidi, link fail"; then + init_shapers + pm_nl_set_limits $ns1 0 3 + pm_nl_add_endpoint $ns1 10.0.2.1 dev ns1eth2 flags signal + pm_nl_set_limits $ns2 1 3 + pm_nl_add_endpoint $ns2 10.0.3.2 dev ns2eth3 flags subflow + pm_nl_add_endpoint $ns2 10.0.4.2 dev ns2eth4 flags subflow + run_tests $ns1 $ns2 10.0.1.1 2 + chk_join_nr 3 3 3 + chk_add_nr 1 1 + chk_stale_nr $ns2 1 -1 1 + fi # 2 subflows plus 1 backup subflow with a lossy link, backup # will never be used - reset - init_shapers - ip netns exec $ns1 ./pm_nl_ctl limits 0 2 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 dev ns1eth2 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 1 2 - export FAILING_LINKS="1" - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 dev ns2eth3 flags subflow,backup - run_tests $ns1 $ns2 10.0.1.1 1 - chk_join_nr "backup subflow unused, link failure" 2 2 2 - chk_add_nr 1 1 - chk_link_usage $ns2 ns2eth3 $cinsent 0 + if reset "backup subflow unused, link failure"; then + init_shapers + pm_nl_set_limits $ns1 0 2 + pm_nl_add_endpoint $ns1 10.0.2.1 dev ns1eth2 flags signal + pm_nl_set_limits $ns2 1 2 + FAILING_LINKS="1" + pm_nl_add_endpoint $ns2 10.0.3.2 dev ns2eth3 flags subflow,backup + run_tests $ns1 $ns2 10.0.1.1 1 + chk_join_nr 2 2 2 + chk_add_nr 1 1 + chk_link_usage $ns2 ns2eth3 $cinsent 0 + fi # 2 lossy links after half transfer, backup will get half of # the traffic - reset - init_shapers - ip netns exec $ns1 ./pm_nl_ctl limits 0 2 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 dev ns1eth2 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 1 2 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 dev ns2eth3 flags subflow,backup - export FAILING_LINKS="1 2" - run_tests $ns1 $ns2 10.0.1.1 1 - chk_join_nr "backup flow used, multi links fail" 2 2 2 - chk_add_nr 1 1 - chk_stale_nr $ns2 2 4 2 - chk_link_usage $ns2 ns2eth3 $cinsent 50 + if reset "backup flow used, multi links fail"; then + init_shapers + pm_nl_set_limits $ns1 0 2 + pm_nl_add_endpoint $ns1 10.0.2.1 dev ns1eth2 flags signal + pm_nl_set_limits $ns2 1 2 + pm_nl_add_endpoint $ns2 10.0.3.2 dev ns2eth3 flags subflow,backup + FAILING_LINKS="1 2" + run_tests $ns1 $ns2 10.0.1.1 1 + chk_join_nr 2 2 2 + chk_add_nr 1 1 + chk_stale_nr $ns2 2 4 2 + chk_link_usage $ns2 ns2eth3 $cinsent 50 + fi # use a backup subflow with the first subflow on a lossy link # for bidirectional transfer - reset - init_shapers - ip netns exec $ns1 ./pm_nl_ctl limits 0 2 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 dev ns1eth2 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 1 3 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 dev ns2eth3 flags subflow,backup - run_tests $ns1 $ns2 10.0.1.1 2 - chk_join_nr "backup flow used, bidi, link failure" 2 2 2 - chk_add_nr 1 1 - chk_stale_nr $ns2 1 -1 2 - chk_link_usage $ns2 ns2eth3 $cinsent 50 + if reset "backup flow used, bidi, link failure"; then + init_shapers + pm_nl_set_limits $ns1 0 2 + pm_nl_add_endpoint $ns1 10.0.2.1 dev ns1eth2 flags signal + pm_nl_set_limits $ns2 1 3 + pm_nl_add_endpoint $ns2 10.0.3.2 dev ns2eth3 flags subflow,backup + FAILING_LINKS="1 2" + run_tests $ns1 $ns2 10.0.1.1 2 + chk_join_nr 2 2 2 + chk_add_nr 1 1 + chk_stale_nr $ns2 1 -1 2 + chk_link_usage $ns2 ns2eth3 $cinsent 50 + fi } add_addr_timeout_tests() { # add_addr timeout - reset_with_add_addr_timeout - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 1 1 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal - run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow - chk_join_nr "signal address, ADD_ADDR timeout" 1 1 1 - chk_add_nr 4 0 + if reset_with_add_addr_timeout "signal address, ADD_ADDR timeout"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow + chk_join_nr 1 1 1 + chk_add_nr 4 0 + fi # add_addr timeout IPv6 - reset_with_add_addr_timeout 6 - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 1 1 - ip netns exec $ns1 ./pm_nl_ctl add dead:beef:2::1 flags signal - run_tests $ns1 $ns2 dead:beef:1::1 0 0 0 slow - chk_join_nr "signal address, ADD_ADDR6 timeout" 1 1 1 - chk_add_nr 4 0 + if reset_with_add_addr_timeout "signal address, ADD_ADDR6 timeout" 6; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns1 dead:beef:2::1 flags signal + run_tests $ns1 $ns2 dead:beef:1::1 0 0 0 slow + chk_join_nr 1 1 1 + chk_add_nr 4 0 + fi # signal addresses timeout - reset_with_add_addr_timeout - ip netns exec $ns1 ./pm_nl_ctl limits 2 2 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal - ip netns exec $ns1 ./pm_nl_ctl add 10.0.3.1 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 2 2 - run_tests $ns1 $ns2 10.0.1.1 0 0 0 least - chk_join_nr "signal addresses, ADD_ADDR timeout" 2 2 2 - chk_add_nr 8 0 + if reset_with_add_addr_timeout "signal addresses, ADD_ADDR timeout"; then + pm_nl_set_limits $ns1 2 2 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_add_endpoint $ns1 10.0.3.1 flags signal + pm_nl_set_limits $ns2 2 2 + run_tests $ns1 $ns2 10.0.1.1 0 0 0 speed_10 + chk_join_nr 2 2 2 + chk_add_nr 8 0 + fi # signal invalid addresses timeout - reset_with_add_addr_timeout - ip netns exec $ns1 ./pm_nl_ctl limits 2 2 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.12.1 flags signal - ip netns exec $ns1 ./pm_nl_ctl add 10.0.3.1 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 2 2 - run_tests $ns1 $ns2 10.0.1.1 0 0 0 least - chk_join_nr "invalid address, ADD_ADDR timeout" 1 1 1 - chk_add_nr 8 0 + if reset_with_add_addr_timeout "invalid address, ADD_ADDR timeout"; then + pm_nl_set_limits $ns1 2 2 + pm_nl_add_endpoint $ns1 10.0.12.1 flags signal + pm_nl_add_endpoint $ns1 10.0.3.1 flags signal + pm_nl_set_limits $ns2 2 2 + run_tests $ns1 $ns2 10.0.1.1 0 0 0 speed_10 + chk_join_nr 1 1 1 + chk_add_nr 8 0 + fi } remove_tests() { # single subflow, remove - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 0 0 -1 slow - chk_join_nr "remove single subflow" 1 1 1 - chk_rm_nr 1 1 + if reset "remove single subflow"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 0 0 -1 slow + chk_join_nr 1 1 1 + chk_rm_nr 1 1 + fi # multiple subflows, remove - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 2 - ip netns exec $ns2 ./pm_nl_ctl limits 0 2 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags subflow - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 0 0 -2 slow - chk_join_nr "remove multiple subflows" 2 2 2 - chk_rm_nr 2 2 + if reset "remove multiple subflows"; then + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 0 2 + pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 0 0 -2 slow + chk_join_nr 2 2 2 + chk_rm_nr 2 2 + fi # single address, remove - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 1 1 - run_tests $ns1 $ns2 10.0.1.1 0 -1 0 slow - chk_join_nr "remove single address" 1 1 1 - chk_add_nr 1 1 - chk_rm_nr 1 1 invert + if reset "remove single address"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_set_limits $ns2 1 1 + run_tests $ns1 $ns2 10.0.1.1 0 -1 0 slow + chk_join_nr 1 1 1 + chk_add_nr 1 1 + chk_rm_nr 1 1 invert + fi # subflow and signal, remove - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 2 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 1 2 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 0 -1 -1 slow - chk_join_nr "remove subflow and signal" 2 2 2 - chk_add_nr 1 1 - chk_rm_nr 1 1 + if reset "remove subflow and signal"; then + pm_nl_set_limits $ns1 0 2 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_set_limits $ns2 1 2 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 0 -1 -1 slow + chk_join_nr 2 2 2 + chk_add_nr 1 1 + chk_rm_nr 1 1 + fi # subflows and signal, remove - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 3 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 1 3 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - ip netns exec $ns2 ./pm_nl_ctl add 10.0.4.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 0 -1 -2 slow - chk_join_nr "remove subflows and signal" 3 3 3 - chk_add_nr 1 1 - chk_rm_nr 2 2 + if reset "remove subflows and signal"; then + pm_nl_set_limits $ns1 0 3 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_set_limits $ns2 1 3 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.4.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 0 -1 -2 slow + chk_join_nr 3 3 3 + chk_add_nr 1 1 + chk_rm_nr 2 2 + fi # addresses remove - reset - ip netns exec $ns1 ./pm_nl_ctl limits 3 3 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal id 250 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.3.1 flags signal - ip netns exec $ns1 ./pm_nl_ctl add 10.0.4.1 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 3 3 - run_tests $ns1 $ns2 10.0.1.1 0 -3 0 slow - chk_join_nr "remove addresses" 3 3 3 - chk_add_nr 3 3 - chk_rm_nr 3 3 invert + if reset "remove addresses"; then + pm_nl_set_limits $ns1 3 3 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal id 250 + pm_nl_add_endpoint $ns1 10.0.3.1 flags signal + pm_nl_add_endpoint $ns1 10.0.4.1 flags signal + pm_nl_set_limits $ns2 3 3 + run_tests $ns1 $ns2 10.0.1.1 0 -3 0 slow + chk_join_nr 3 3 3 + chk_add_nr 3 3 + chk_rm_nr 3 3 invert + fi # invalid addresses remove - reset - ip netns exec $ns1 ./pm_nl_ctl limits 3 3 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.12.1 flags signal - ip netns exec $ns1 ./pm_nl_ctl add 10.0.3.1 flags signal - ip netns exec $ns1 ./pm_nl_ctl add 10.0.14.1 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 3 3 - run_tests $ns1 $ns2 10.0.1.1 0 -3 0 slow - chk_join_nr "remove invalid addresses" 1 1 1 - chk_add_nr 3 3 - chk_rm_nr 3 1 invert + if reset "remove invalid addresses"; then + pm_nl_set_limits $ns1 3 3 + pm_nl_add_endpoint $ns1 10.0.12.1 flags signal + pm_nl_add_endpoint $ns1 10.0.3.1 flags signal + pm_nl_add_endpoint $ns1 10.0.14.1 flags signal + pm_nl_set_limits $ns2 3 3 + run_tests $ns1 $ns2 10.0.1.1 0 -3 0 slow + chk_join_nr 1 1 1 + chk_add_nr 3 3 + chk_rm_nr 3 1 invert + fi # subflows and signal, flush - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 3 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 1 3 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - ip netns exec $ns2 ./pm_nl_ctl add 10.0.4.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 0 -8 -8 slow - chk_join_nr "flush subflows and signal" 3 3 3 - chk_add_nr 1 1 - chk_rm_nr 2 2 + if reset "flush subflows and signal"; then + pm_nl_set_limits $ns1 0 3 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_set_limits $ns2 1 3 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.4.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 0 -8 -8 slow + chk_join_nr 3 3 3 + chk_add_nr 1 1 + chk_rm_nr 1 3 invert simult + fi # subflows flush - reset - ip netns exec $ns1 ./pm_nl_ctl limits 3 3 - ip netns exec $ns2 ./pm_nl_ctl limits 3 3 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags subflow id 150 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - ip netns exec $ns2 ./pm_nl_ctl add 10.0.4.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 0 -8 -8 slow - chk_join_nr "flush subflows" 3 3 3 - chk_rm_nr 3 3 + if reset "flush subflows"; then + pm_nl_set_limits $ns1 3 3 + pm_nl_set_limits $ns2 3 3 + pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow id 150 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.4.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 0 -8 -8 slow + chk_join_nr 3 3 3 + chk_rm_nr 0 3 simult + fi # addresses flush - reset - ip netns exec $ns1 ./pm_nl_ctl limits 3 3 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal id 250 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.3.1 flags signal - ip netns exec $ns1 ./pm_nl_ctl add 10.0.4.1 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 3 3 - run_tests $ns1 $ns2 10.0.1.1 0 -8 -8 slow - chk_join_nr "flush addresses" 3 3 3 - chk_add_nr 3 3 - chk_rm_nr 3 3 invert + if reset "flush addresses"; then + pm_nl_set_limits $ns1 3 3 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal id 250 + pm_nl_add_endpoint $ns1 10.0.3.1 flags signal + pm_nl_add_endpoint $ns1 10.0.4.1 flags signal + pm_nl_set_limits $ns2 3 3 + run_tests $ns1 $ns2 10.0.1.1 0 -8 -8 slow + chk_join_nr 3 3 3 + chk_add_nr 3 3 + chk_rm_nr 3 3 invert simult + fi # invalid addresses flush - reset - ip netns exec $ns1 ./pm_nl_ctl limits 3 3 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.12.1 flags signal - ip netns exec $ns1 ./pm_nl_ctl add 10.0.3.1 flags signal - ip netns exec $ns1 ./pm_nl_ctl add 10.0.14.1 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 3 3 - run_tests $ns1 $ns2 10.0.1.1 0 -8 0 slow - chk_join_nr "flush invalid addresses" 1 1 1 - chk_add_nr 3 3 - chk_rm_nr 3 1 invert + if reset "flush invalid addresses"; then + pm_nl_set_limits $ns1 3 3 + pm_nl_add_endpoint $ns1 10.0.12.1 flags signal + pm_nl_add_endpoint $ns1 10.0.3.1 flags signal + pm_nl_add_endpoint $ns1 10.0.14.1 flags signal + pm_nl_set_limits $ns2 3 3 + run_tests $ns1 $ns2 10.0.1.1 0 -8 0 slow + chk_join_nr 1 1 1 + chk_add_nr 3 3 + chk_rm_nr 3 1 invert + fi # remove id 0 subflow - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 0 0 -9 slow - chk_join_nr "remove id 0 subflow" 1 1 1 - chk_rm_nr 1 1 + if reset "remove id 0 subflow"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 0 0 -9 slow + chk_join_nr 1 1 1 + chk_rm_nr 1 1 + fi # remove id 0 address - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 1 1 - run_tests $ns1 $ns2 10.0.1.1 0 -9 0 slow - chk_join_nr "remove id 0 address" 1 1 1 - chk_add_nr 1 1 - chk_rm_nr 1 1 invert + if reset "remove id 0 address"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_set_limits $ns2 1 1 + run_tests $ns1 $ns2 10.0.1.1 0 -9 0 slow + chk_join_nr 1 1 1 + chk_add_nr 1 1 + chk_rm_nr 1 1 invert + fi } add_tests() { # add single subflow - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 - run_tests $ns1 $ns2 10.0.1.1 0 0 1 slow - chk_join_nr "add single subflow" 1 1 1 + if reset "add single subflow"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + run_tests $ns1 $ns2 10.0.1.1 0 0 1 slow + chk_join_nr 1 1 1 + fi # add signal address - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 1 1 - run_tests $ns1 $ns2 10.0.1.1 0 1 0 slow - chk_join_nr "add signal address" 1 1 1 - chk_add_nr 1 1 + if reset "add signal address"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 1 1 + run_tests $ns1 $ns2 10.0.1.1 0 1 0 slow + chk_join_nr 1 1 1 + chk_add_nr 1 1 + fi # add multiple subflows - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 2 - ip netns exec $ns2 ./pm_nl_ctl limits 0 2 - run_tests $ns1 $ns2 10.0.1.1 0 0 2 slow - chk_join_nr "add multiple subflows" 2 2 2 + if reset "add multiple subflows"; then + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 0 2 + run_tests $ns1 $ns2 10.0.1.1 0 0 2 slow + chk_join_nr 2 2 2 + fi # add multiple subflows IPv6 - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 2 - ip netns exec $ns2 ./pm_nl_ctl limits 0 2 - run_tests $ns1 $ns2 dead:beef:1::1 0 0 2 slow - chk_join_nr "add multiple subflows IPv6" 2 2 2 + if reset "add multiple subflows IPv6"; then + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 0 2 + run_tests $ns1 $ns2 dead:beef:1::1 0 0 2 slow + chk_join_nr 2 2 2 + fi # add multiple addresses IPv6 - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 2 - ip netns exec $ns2 ./pm_nl_ctl limits 2 2 - run_tests $ns1 $ns2 dead:beef:1::1 0 2 0 slow - chk_join_nr "add multiple addresses IPv6" 2 2 2 - chk_add_nr 2 2 + if reset "add multiple addresses IPv6"; then + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 2 2 + run_tests $ns1 $ns2 dead:beef:1::1 0 2 0 slow + chk_join_nr 2 2 2 + chk_add_nr 2 2 + fi } ipv6_tests() { # subflow IPv6 - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl add dead:beef:3::2 flags subflow - run_tests $ns1 $ns2 dead:beef:1::1 0 0 0 slow - chk_join_nr "single subflow IPv6" 1 1 1 + if reset "single subflow IPv6"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 dead:beef:3::2 dev ns2eth3 flags subflow + run_tests $ns1 $ns2 dead:beef:1::1 0 0 0 slow + chk_join_nr 1 1 1 + fi # add_address, unused IPv6 - reset - ip netns exec $ns1 ./pm_nl_ctl add dead:beef:2::1 flags signal - run_tests $ns1 $ns2 dead:beef:1::1 0 0 0 slow - chk_join_nr "unused signal address IPv6" 0 0 0 - chk_add_nr 1 1 + if reset "unused signal address IPv6"; then + pm_nl_add_endpoint $ns1 dead:beef:2::1 flags signal + run_tests $ns1 $ns2 dead:beef:1::1 0 0 0 slow + chk_join_nr 0 0 0 + chk_add_nr 1 1 + fi # signal address IPv6 - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns1 ./pm_nl_ctl add dead:beef:2::1 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 1 1 - run_tests $ns1 $ns2 dead:beef:1::1 0 0 0 slow - chk_join_nr "single address IPv6" 1 1 1 - chk_add_nr 1 1 + if reset "single address IPv6"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_add_endpoint $ns1 dead:beef:2::1 flags signal + pm_nl_set_limits $ns2 1 1 + run_tests $ns1 $ns2 dead:beef:1::1 0 0 0 slow + chk_join_nr 1 1 1 + chk_add_nr 1 1 + fi # single address IPv6, remove - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns1 ./pm_nl_ctl add dead:beef:2::1 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 1 1 - run_tests $ns1 $ns2 dead:beef:1::1 0 -1 0 slow - chk_join_nr "remove single address IPv6" 1 1 1 - chk_add_nr 1 1 - chk_rm_nr 1 1 invert + if reset "remove single address IPv6"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_add_endpoint $ns1 dead:beef:2::1 flags signal + pm_nl_set_limits $ns2 1 1 + run_tests $ns1 $ns2 dead:beef:1::1 0 -1 0 slow + chk_join_nr 1 1 1 + chk_add_nr 1 1 + chk_rm_nr 1 1 invert + fi # subflow and signal IPv6, remove - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 2 - ip netns exec $ns1 ./pm_nl_ctl add dead:beef:2::1 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 1 2 - ip netns exec $ns2 ./pm_nl_ctl add dead:beef:3::2 flags subflow - run_tests $ns1 $ns2 dead:beef:1::1 0 -1 -1 slow - chk_join_nr "remove subflow and signal IPv6" 2 2 2 - chk_add_nr 1 1 - chk_rm_nr 1 1 + if reset "remove subflow and signal IPv6"; then + pm_nl_set_limits $ns1 0 2 + pm_nl_add_endpoint $ns1 dead:beef:2::1 flags signal + pm_nl_set_limits $ns2 1 2 + pm_nl_add_endpoint $ns2 dead:beef:3::2 dev ns2eth3 flags subflow + run_tests $ns1 $ns2 dead:beef:1::1 0 -1 -1 slow + chk_join_nr 2 2 2 + chk_add_nr 1 1 + chk_rm_nr 1 1 + fi } v4mapped_tests() { # subflow IPv4-mapped to IPv4-mapped - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl add "::ffff:10.0.3.2" flags subflow - run_tests $ns1 $ns2 "::ffff:10.0.1.1" - chk_join_nr "single subflow IPv4-mapped" 1 1 1 + if reset "single subflow IPv4-mapped"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 "::ffff:10.0.3.2" flags subflow + run_tests $ns1 $ns2 "::ffff:10.0.1.1" + chk_join_nr 1 1 1 + fi # signal address IPv4-mapped with IPv4-mapped sk - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 1 1 - ip netns exec $ns1 ./pm_nl_ctl add "::ffff:10.0.2.1" flags signal - run_tests $ns1 $ns2 "::ffff:10.0.1.1" - chk_join_nr "signal address IPv4-mapped" 1 1 1 - chk_add_nr 1 1 + if reset "signal address IPv4-mapped"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns1 "::ffff:10.0.2.1" flags signal + run_tests $ns1 $ns2 "::ffff:10.0.1.1" + chk_join_nr 1 1 1 + chk_add_nr 1 1 + fi # subflow v4-map-v6 - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - run_tests $ns1 $ns2 "::ffff:10.0.1.1" - chk_join_nr "single subflow v4-map-v6" 1 1 1 + if reset "single subflow v4-map-v6"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + run_tests $ns1 $ns2 "::ffff:10.0.1.1" + chk_join_nr 1 1 1 + fi # signal address v4-map-v6 - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 1 1 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal - run_tests $ns1 $ns2 "::ffff:10.0.1.1" - chk_join_nr "signal address v4-map-v6" 1 1 1 - chk_add_nr 1 1 + if reset "signal address v4-map-v6"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + run_tests $ns1 $ns2 "::ffff:10.0.1.1" + chk_join_nr 1 1 1 + chk_add_nr 1 1 + fi # subflow v6-map-v4 - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl add "::ffff:10.0.3.2" flags subflow - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "single subflow v6-map-v4" 1 1 1 + if reset "single subflow v6-map-v4"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 "::ffff:10.0.3.2" flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 1 1 1 + fi # signal address v6-map-v4 - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 1 1 - ip netns exec $ns1 ./pm_nl_ctl add "::ffff:10.0.2.1" flags signal - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "signal address v6-map-v4" 1 1 1 - chk_add_nr 1 1 + if reset "signal address v6-map-v4"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns1 "::ffff:10.0.2.1" flags signal + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 1 1 1 + chk_add_nr 1 1 + fi # no subflow IPv6 to v4 address - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl add dead:beef:2::2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "no JOIN with diff families v4-v6" 0 0 0 + if reset "no JOIN with diff families v4-v6"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 dead:beef:2::2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 0 0 0 + fi # no subflow IPv6 to v4 address even if v6 has a valid v4 at the end - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl add dead:beef:2::10.0.3.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "no JOIN with diff families v4-v6-2" 0 0 0 + if reset "no JOIN with diff families v4-v6-2"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 dead:beef:2::10.0.3.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 0 0 0 + fi # no subflow IPv4 to v6 address, no need to slow down too then - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - run_tests $ns1 $ns2 dead:beef:1::1 - chk_join_nr "no JOIN with diff families v6-v4" 0 0 0 + if reset "no JOIN with diff families v6-v4"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + run_tests $ns1 $ns2 dead:beef:1::1 + chk_join_nr 0 0 0 + fi } backup_tests() { # single subflow, backup - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow,backup - run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow nobackup - chk_join_nr "single subflow, backup" 1 1 1 - chk_prio_nr 0 1 + if reset "single subflow, backup"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow,backup + run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow nobackup + chk_join_nr 1 1 1 + chk_prio_nr 0 1 + fi # single address, backup - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 1 1 - run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow backup - chk_join_nr "single address, backup" 1 1 1 - chk_add_nr 1 1 - chk_prio_nr 1 0 + if reset "single address, backup"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_set_limits $ns2 1 1 + run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow backup + chk_join_nr 1 1 1 + chk_add_nr 1 1 + chk_prio_nr 1 1 + fi + + # single address with port, backup + if reset "single address with port, backup"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal port 10100 + pm_nl_set_limits $ns2 1 1 + run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow backup + chk_join_nr 1 1 1 + chk_add_nr 1 1 + chk_prio_nr 1 1 + fi } add_addr_ports_tests() { # signal address with port - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 1 1 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal port 10100 - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "signal address with port" 1 1 1 - chk_add_nr 1 1 1 + if reset "signal address with port"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal port 10100 + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 1 1 1 + chk_add_nr 1 1 1 + fi # subflow and signal with port - reset - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal port 10100 - ip netns exec $ns1 ./pm_nl_ctl limits 0 2 - ip netns exec $ns2 ./pm_nl_ctl limits 1 2 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "subflow and signal with port" 2 2 2 - chk_add_nr 1 1 1 + if reset "subflow and signal with port"; then + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal port 10100 + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 1 2 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 2 2 2 + chk_add_nr 1 1 1 + fi # single address with port, remove - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal port 10100 - ip netns exec $ns2 ./pm_nl_ctl limits 1 1 - run_tests $ns1 $ns2 10.0.1.1 0 -1 0 slow - chk_join_nr "remove single address with port" 1 1 1 - chk_add_nr 1 1 1 - chk_rm_nr 1 1 invert + if reset "remove single address with port"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal port 10100 + pm_nl_set_limits $ns2 1 1 + run_tests $ns1 $ns2 10.0.1.1 0 -1 0 slow + chk_join_nr 1 1 1 + chk_add_nr 1 1 1 + chk_rm_nr 1 1 invert + fi # subflow and signal with port, remove - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 2 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal port 10100 - ip netns exec $ns2 ./pm_nl_ctl limits 1 2 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 0 -1 -1 slow - chk_join_nr "remove subflow and signal with port" 2 2 2 - chk_add_nr 1 1 1 - chk_rm_nr 1 1 + if reset "remove subflow and signal with port"; then + pm_nl_set_limits $ns1 0 2 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal port 10100 + pm_nl_set_limits $ns2 1 2 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 0 -1 -1 slow + chk_join_nr 2 2 2 + chk_add_nr 1 1 1 + chk_rm_nr 1 1 + fi # subflows and signal with port, flush - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 3 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal port 10100 - ip netns exec $ns2 ./pm_nl_ctl limits 1 3 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - ip netns exec $ns2 ./pm_nl_ctl add 10.0.4.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 0 -8 -2 slow - chk_join_nr "flush subflows and signal with port" 3 3 3 - chk_add_nr 1 1 - chk_rm_nr 2 2 + if reset "flush subflows and signal with port"; then + pm_nl_set_limits $ns1 0 3 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal port 10100 + pm_nl_set_limits $ns2 1 3 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.4.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 0 -8 -2 slow + chk_join_nr 3 3 3 + chk_add_nr 1 1 + chk_rm_nr 1 3 invert simult + fi # multiple addresses with port - reset - ip netns exec $ns1 ./pm_nl_ctl limits 2 2 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal port 10100 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.3.1 flags signal port 10100 - ip netns exec $ns2 ./pm_nl_ctl limits 2 2 - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "multiple addresses with port" 2 2 2 - chk_add_nr 2 2 2 + if reset "multiple addresses with port"; then + pm_nl_set_limits $ns1 2 2 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal port 10100 + pm_nl_add_endpoint $ns1 10.0.3.1 flags signal port 10100 + pm_nl_set_limits $ns2 2 2 + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 2 2 2 + chk_add_nr 2 2 2 + fi # multiple addresses with ports - reset - ip netns exec $ns1 ./pm_nl_ctl limits 2 2 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal port 10100 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.3.1 flags signal port 10101 - ip netns exec $ns2 ./pm_nl_ctl limits 2 2 - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "multiple addresses with ports" 2 2 2 - chk_add_nr 2 2 2 + if reset "multiple addresses with ports"; then + pm_nl_set_limits $ns1 2 2 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal port 10100 + pm_nl_add_endpoint $ns1 10.0.3.1 flags signal port 10101 + pm_nl_set_limits $ns2 2 2 + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 2 2 2 + chk_add_nr 2 2 2 + fi } syncookies_tests() { # single subflow, syncookies - reset_with_cookies - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "single subflow with syn cookies" 1 1 1 + if reset_with_cookies "single subflow with syn cookies"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 1 1 1 + fi # multiple subflows with syn cookies - reset_with_cookies - ip netns exec $ns1 ./pm_nl_ctl limits 0 2 - ip netns exec $ns2 ./pm_nl_ctl limits 0 2 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "multiple subflows with syn cookies" 2 2 2 + if reset_with_cookies "multiple subflows with syn cookies"; then + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 0 2 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 2 2 2 + fi # multiple subflows limited by server - reset_with_cookies - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 2 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "subflows limited by server w cookies" 2 1 1 + if reset_with_cookies "subflows limited by server w cookies"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 2 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 2 1 1 + fi # test signal address with cookies - reset_with_cookies - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 1 1 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "signal address with syn cookies" 1 1 1 - chk_add_nr 1 1 + if reset_with_cookies "signal address with syn cookies"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 1 1 1 + chk_add_nr 1 1 + fi # test cookie with subflow and signal - reset_with_cookies - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal - ip netns exec $ns1 ./pm_nl_ctl limits 0 2 - ip netns exec $ns2 ./pm_nl_ctl limits 1 2 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "subflow and signal w cookies" 2 2 2 - chk_add_nr 1 1 + if reset_with_cookies "subflow and signal w cookies"; then + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 1 2 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 2 2 2 + chk_add_nr 1 1 + fi # accept and use add_addr with additional subflows - reset_with_cookies - ip netns exec $ns1 ./pm_nl_ctl limits 0 3 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 1 3 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - ip netns exec $ns2 ./pm_nl_ctl add 10.0.4.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "subflows and signal w. cookies" 3 3 3 - chk_add_nr 1 1 + if reset_with_cookies "subflows and signal w. cookies"; then + pm_nl_set_limits $ns1 0 3 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_set_limits $ns2 1 3 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.4.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 3 3 3 + chk_add_nr 1 1 + fi } checksum_tests() { # checksum test 0 0 - reset_with_checksum 0 0 - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 - run_tests $ns1 $ns2 10.0.1.1 - chk_csum_nr "checksum test 0 0" + if reset_with_checksum 0 0; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 0 0 0 + fi # checksum test 1 1 - reset_with_checksum 1 1 - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 - run_tests $ns1 $ns2 10.0.1.1 - chk_csum_nr "checksum test 1 1" + if reset_with_checksum 1 1; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 0 0 0 + fi # checksum test 0 1 - reset_with_checksum 0 1 - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 - run_tests $ns1 $ns2 10.0.1.1 - chk_csum_nr "checksum test 0 1" + if reset_with_checksum 0 1; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 0 0 0 + fi # checksum test 1 0 - reset_with_checksum 1 0 - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 - run_tests $ns1 $ns2 10.0.1.1 - chk_csum_nr "checksum test 1 0" + if reset_with_checksum 1 0; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 0 0 0 + fi } deny_join_id0_tests() { # subflow allow join id0 ns1 - reset_with_allow_join_id0 1 0 - ip netns exec $ns1 ./pm_nl_ctl limits 1 1 - ip netns exec $ns2 ./pm_nl_ctl limits 1 1 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "single subflow allow join id0 ns1" 1 1 1 + if reset_with_allow_join_id0 "single subflow allow join id0 ns1" 1 0; then + pm_nl_set_limits $ns1 1 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 1 1 1 + fi # subflow allow join id0 ns2 - reset_with_allow_join_id0 0 1 - ip netns exec $ns1 ./pm_nl_ctl limits 1 1 - ip netns exec $ns2 ./pm_nl_ctl limits 1 1 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "single subflow allow join id0 ns2" 0 0 0 + if reset_with_allow_join_id0 "single subflow allow join id0 ns2" 0 1; then + pm_nl_set_limits $ns1 1 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 0 0 0 + fi # signal address allow join id0 ns1 # ADD_ADDRs are not affected by allow_join_id0 value. - reset_with_allow_join_id0 1 0 - ip netns exec $ns1 ./pm_nl_ctl limits 1 1 - ip netns exec $ns2 ./pm_nl_ctl limits 1 1 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "signal address allow join id0 ns1" 1 1 1 - chk_add_nr 1 1 + if reset_with_allow_join_id0 "signal address allow join id0 ns1" 1 0; then + pm_nl_set_limits $ns1 1 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 1 1 1 + chk_add_nr 1 1 + fi # signal address allow join id0 ns2 # ADD_ADDRs are not affected by allow_join_id0 value. - reset_with_allow_join_id0 0 1 - ip netns exec $ns1 ./pm_nl_ctl limits 1 1 - ip netns exec $ns2 ./pm_nl_ctl limits 1 1 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "signal address allow join id0 ns2" 1 1 1 - chk_add_nr 1 1 + if reset_with_allow_join_id0 "signal address allow join id0 ns2" 0 1; then + pm_nl_set_limits $ns1 1 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 1 1 1 + chk_add_nr 1 1 + fi # subflow and address allow join id0 ns1 - reset_with_allow_join_id0 1 0 - ip netns exec $ns1 ./pm_nl_ctl limits 2 2 - ip netns exec $ns2 ./pm_nl_ctl limits 2 2 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "subflow and address allow join id0 1" 2 2 2 + if reset_with_allow_join_id0 "subflow and address allow join id0 1" 1 0; then + pm_nl_set_limits $ns1 2 2 + pm_nl_set_limits $ns2 2 2 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 2 2 2 + fi # subflow and address allow join id0 ns2 - reset_with_allow_join_id0 0 1 - ip netns exec $ns1 ./pm_nl_ctl limits 2 2 - ip netns exec $ns2 ./pm_nl_ctl limits 2 2 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "subflow and address allow join id0 2" 1 1 1 + if reset_with_allow_join_id0 "subflow and address allow join id0 2" 0 1; then + pm_nl_set_limits $ns1 2 2 + pm_nl_set_limits $ns2 2 2 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 1 1 1 + fi } fullmesh_tests() @@ -1845,177 +2456,237 @@ fullmesh_tests() # fullmesh 1 # 2 fullmesh addrs in ns2, added before the connection, # 1 non-fullmesh addr in ns1, added during the connection. - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 4 - ip netns exec $ns2 ./pm_nl_ctl limits 1 4 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags subflow,fullmesh - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow,fullmesh - run_tests $ns1 $ns2 10.0.1.1 0 1 0 slow - chk_join_nr "fullmesh test 2x1" 4 4 4 - chk_add_nr 1 1 + if reset "fullmesh test 2x1"; then + pm_nl_set_limits $ns1 0 4 + pm_nl_set_limits $ns2 1 4 + pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow,fullmesh + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow,fullmesh + run_tests $ns1 $ns2 10.0.1.1 0 1 0 slow + chk_join_nr 4 4 4 + chk_add_nr 1 1 + fi # fullmesh 2 # 1 non-fullmesh addr in ns1, added before the connection, # 1 fullmesh addr in ns2, added during the connection. - reset - ip netns exec $ns1 ./pm_nl_ctl limits 1 3 - ip netns exec $ns2 ./pm_nl_ctl limits 1 3 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal - run_tests $ns1 $ns2 10.0.1.1 0 0 fullmesh_1 slow - chk_join_nr "fullmesh test 1x1" 3 3 3 - chk_add_nr 1 1 + if reset "fullmesh test 1x1"; then + pm_nl_set_limits $ns1 1 3 + pm_nl_set_limits $ns2 1 3 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + run_tests $ns1 $ns2 10.0.1.1 0 0 fullmesh_1 slow + chk_join_nr 3 3 3 + chk_add_nr 1 1 + fi # fullmesh 3 # 1 non-fullmesh addr in ns1, added before the connection, # 2 fullmesh addrs in ns2, added during the connection. - reset - ip netns exec $ns1 ./pm_nl_ctl limits 2 5 - ip netns exec $ns2 ./pm_nl_ctl limits 1 5 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal - run_tests $ns1 $ns2 10.0.1.1 0 0 fullmesh_2 slow - chk_join_nr "fullmesh test 1x2" 5 5 5 - chk_add_nr 1 1 + if reset "fullmesh test 1x2"; then + pm_nl_set_limits $ns1 2 5 + pm_nl_set_limits $ns2 1 5 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + run_tests $ns1 $ns2 10.0.1.1 0 0 fullmesh_2 slow + chk_join_nr 5 5 5 + chk_add_nr 1 1 + fi # fullmesh 4 # 1 non-fullmesh addr in ns1, added before the connection, # 2 fullmesh addrs in ns2, added during the connection, # limit max_subflows to 4. - reset - ip netns exec $ns1 ./pm_nl_ctl limits 2 4 - ip netns exec $ns2 ./pm_nl_ctl limits 1 4 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal - run_tests $ns1 $ns2 10.0.1.1 0 0 fullmesh_2 slow - chk_join_nr "fullmesh test 1x2, limited" 4 4 4 - chk_add_nr 1 1 + if reset "fullmesh test 1x2, limited"; then + pm_nl_set_limits $ns1 2 4 + pm_nl_set_limits $ns2 1 4 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + run_tests $ns1 $ns2 10.0.1.1 0 0 fullmesh_2 slow + chk_join_nr 4 4 4 + chk_add_nr 1 1 + fi + + # set fullmesh flag + if reset "set fullmesh flag test"; then + pm_nl_set_limits $ns1 4 4 + pm_nl_add_endpoint $ns1 10.0.2.1 flags subflow + pm_nl_set_limits $ns2 4 4 + run_tests $ns1 $ns2 10.0.1.1 0 0 1 slow fullmesh + chk_join_nr 2 2 2 + chk_rm_nr 0 1 + fi + + # set nofullmesh flag + if reset "set nofullmesh flag test"; then + pm_nl_set_limits $ns1 4 4 + pm_nl_add_endpoint $ns1 10.0.2.1 flags subflow,fullmesh + pm_nl_set_limits $ns2 4 4 + run_tests $ns1 $ns2 10.0.1.1 0 0 fullmesh_1 slow nofullmesh + chk_join_nr 2 2 2 + chk_rm_nr 0 1 + fi + + # set backup,fullmesh flags + if reset "set backup,fullmesh flags test"; then + pm_nl_set_limits $ns1 4 4 + pm_nl_add_endpoint $ns1 10.0.2.1 flags subflow + pm_nl_set_limits $ns2 4 4 + run_tests $ns1 $ns2 10.0.1.1 0 0 1 slow backup,fullmesh + chk_join_nr 2 2 2 + chk_prio_nr 0 1 + chk_rm_nr 0 1 + fi + + # set nobackup,nofullmesh flags + if reset "set nobackup,nofullmesh flags test"; then + pm_nl_set_limits $ns1 4 4 + pm_nl_set_limits $ns2 4 4 + pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow,backup,fullmesh + run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow nobackup,nofullmesh + chk_join_nr 2 2 2 + chk_prio_nr 0 1 + chk_rm_nr 0 1 + fi } -all_tests() +fastclose_tests() { - subflows_tests - subflows_error_tests - signal_address_tests - link_failure_tests - add_addr_timeout_tests - remove_tests - add_tests - ipv6_tests - v4mapped_tests - backup_tests - add_addr_ports_tests - syncookies_tests - checksum_tests - deny_join_id0_tests - fullmesh_tests + if reset "fastclose test"; then + run_tests $ns1 $ns2 10.0.1.1 1024 0 fastclose_2 + chk_join_nr 0 0 0 + chk_fclose_nr 1 1 + chk_rst_nr 1 1 invert + fi } +implicit_tests() +{ + # userspace pm type prevents add_addr + if reset "implicit EP"; then + pm_nl_set_limits $ns1 2 2 + pm_nl_set_limits $ns2 2 2 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow & + + wait_mpj $ns1 + pm_nl_check_endpoint 1 "creation" \ + $ns2 10.0.2.2 id 1 flags implicit + + pm_nl_add_endpoint $ns2 10.0.2.2 id 33 + pm_nl_check_endpoint 0 "ID change is prevented" \ + $ns2 10.0.2.2 id 1 flags implicit + + pm_nl_add_endpoint $ns2 10.0.2.2 flags signal + pm_nl_check_endpoint 0 "modif is allowed" \ + $ns2 10.0.2.2 id 1 flags signal + wait + fi +} + +# [$1: error message] usage() { + if [ -n "${1}" ]; then + echo "${1}" + ret=1 + fi + echo "mptcp_join usage:" - echo " -f subflows_tests" - echo " -e subflows_error_tests" - echo " -s signal_address_tests" - echo " -l link_failure_tests" - echo " -t add_addr_timeout_tests" - echo " -r remove_tests" - echo " -a add_tests" - echo " -6 ipv6_tests" - echo " -4 v4mapped_tests" - echo " -b backup_tests" - echo " -p add_addr_ports_tests" - echo " -k syncookies_tests" - echo " -S checksum_tests" - echo " -d deny_join_id0_tests" - echo " -m fullmesh_tests" + + local key + for key in "${!all_tests[@]}"; do + echo " -${key} ${all_tests[${key}]}" + done + echo " -c capture pcap files" echo " -C enable data checksum" + echo " -i use ip mptcp" echo " -h help" -} -sin=$(mktemp) -sout=$(mktemp) -cin=$(mktemp) -cinsent=$(mktemp) -cout=$(mktemp) -init -make_file "$cin" "client" 1 -make_file "$sin" "server" 1 -trap cleanup EXIT + echo "[test ids|names]" -for arg in "$@"; do - # check for "capture/checksum" args before launching tests - if [[ "${arg}" =~ ^"-"[0-9a-zA-Z]*"c"[0-9a-zA-Z]*$ ]]; then - capture=1 - fi - if [[ "${arg}" =~ ^"-"[0-9a-zA-Z]*"C"[0-9a-zA-Z]*$ ]]; then - checksum=1 - fi + exit ${ret} +} - # exception for the capture/checksum options, the rest means: a part of the tests - if [ "${arg}" != "-c" ] && [ "${arg}" != "-C" ]; then - do_all_tests=0 - fi -done -if [ $do_all_tests -eq 1 ]; then - all_tests - exit $ret -fi +# Use a "simple" array to force an specific order we cannot have with an associative one +all_tests_sorted=( + f@subflows_tests + e@subflows_error_tests + s@signal_address_tests + l@link_failure_tests + t@add_addr_timeout_tests + r@remove_tests + a@add_tests + 6@ipv6_tests + 4@v4mapped_tests + b@backup_tests + p@add_addr_ports_tests + k@syncookies_tests + S@checksum_tests + d@deny_join_id0_tests + m@fullmesh_tests + z@fastclose_tests + I@implicit_tests +) + +all_tests_args="" +all_tests_names=() +for subtests in "${all_tests_sorted[@]}"; do + key="${subtests%@*}" + value="${subtests#*@}" + + all_tests_args+="${key}" + all_tests_names+=("${value}") + all_tests[${key}]="${value}" +done -while getopts 'fesltra64bpkdmchCS' opt; do +tests=() +while getopts "${all_tests_args}cCih" opt; do case $opt in - f) - subflows_tests - ;; - e) - subflows_error_tests - ;; - s) - signal_address_tests - ;; - l) - link_failure_tests - ;; - t) - add_addr_timeout_tests - ;; - r) - remove_tests - ;; - a) - add_tests - ;; - 6) - ipv6_tests - ;; - 4) - v4mapped_tests - ;; - b) - backup_tests - ;; - p) - add_addr_ports_tests - ;; - k) - syncookies_tests - ;; - S) - checksum_tests - ;; - d) - deny_join_id0_tests - ;; - m) - fullmesh_tests + ["${all_tests_args}"]) + tests+=("${all_tests[${opt}]}") ;; c) + capture=1 ;; C) + checksum=1 + ;; + i) + ip_mptcp=1 ;; - h | *) + h) usage ;; + *) + usage "Unknown option: -${opt}" + ;; esac done +shift $((OPTIND - 1)) + +for arg in "${@}"; do + if [[ "${arg}" =~ ^[0-9]+$ ]]; then + only_tests_ids+=("${arg}") + else + only_tests_names+=("${arg}") + fi +done + +if [ ${#tests[@]} -eq 0 ]; then + tests=("${all_tests_names[@]}") +fi + +for subtests in "${tests[@]}"; do + "${subtests}" +done + +if [ ${ret} -ne 0 ]; then + echo + echo "${#failed_tests[@]} failure(s) has(ve) been detected:" + for i in $(get_failed_tests_ids); do + echo -e "\t- ${i}: ${failed_tests[${i}]}" + done + echo +fi + exit $ret diff --git a/tools/testing/selftests/net/mptcp/pm_netlink.sh b/tools/testing/selftests/net/mptcp/pm_netlink.sh index cbacf9f6538b..89839d1ff9d8 100755 --- a/tools/testing/selftests/net/mptcp/pm_netlink.sh +++ b/tools/testing/selftests/net/mptcp/pm_netlink.sh @@ -164,4 +164,22 @@ id 253 flags 10.0.0.5 id 254 flags 10.0.0.2 id 255 flags 10.0.0.3" "wrap-around ids" +ip netns exec $ns1 ./pm_nl_ctl flush +ip netns exec $ns1 ./pm_nl_ctl add 10.0.1.1 flags subflow +ip netns exec $ns1 ./pm_nl_ctl set 10.0.1.1 flags backup +check "ip netns exec $ns1 ./pm_nl_ctl dump" "id 1 flags \ +subflow,backup 10.0.1.1" "set flags (backup)" +ip netns exec $ns1 ./pm_nl_ctl set 10.0.1.1 flags nobackup +check "ip netns exec $ns1 ./pm_nl_ctl dump" "id 1 flags \ +subflow 10.0.1.1" " (nobackup)" +ip netns exec $ns1 ./pm_nl_ctl set id 1 flags fullmesh +check "ip netns exec $ns1 ./pm_nl_ctl dump" "id 1 flags \ +subflow,fullmesh 10.0.1.1" " (fullmesh)" +ip netns exec $ns1 ./pm_nl_ctl set id 1 flags nofullmesh +check "ip netns exec $ns1 ./pm_nl_ctl dump" "id 1 flags \ +subflow 10.0.1.1" " (nofullmesh)" +ip netns exec $ns1 ./pm_nl_ctl set id 1 flags backup,fullmesh +check "ip netns exec $ns1 ./pm_nl_ctl dump" "id 1 flags \ +subflow,backup,fullmesh 10.0.1.1" " (backup,fullmesh)" + exit $ret diff --git a/tools/testing/selftests/net/mptcp/pm_nl_ctl.c b/tools/testing/selftests/net/mptcp/pm_nl_ctl.c index 354784512748..a75a68ad652e 100644 --- a/tools/testing/selftests/net/mptcp/pm_nl_ctl.c +++ b/tools/testing/selftests/net/mptcp/pm_nl_ctl.c @@ -28,7 +28,7 @@ static void syntax(char *argv[]) fprintf(stderr, "\tadd [flags signal|subflow|backup|fullmesh] [id <nr>] [dev <name>] <ip>\n"); fprintf(stderr, "\tdel <id> [<ip>]\n"); fprintf(stderr, "\tget <id>\n"); - fprintf(stderr, "\tset <ip> [flags backup|nobackup]\n"); + fprintf(stderr, "\tset [<ip>] [id <nr>] flags [no]backup|[no]fullmesh [port <nr>]\n"); fprintf(stderr, "\tflush\n"); fprintf(stderr, "\tdump\n"); fprintf(stderr, "\tlimits [<rcv addr max> <subflow max>]\n"); @@ -436,6 +436,13 @@ static void print_addr(struct rtattr *attrs, int len) printf(","); } + if (flags & MPTCP_PM_ADDR_FLAG_IMPLICIT) { + printf("implicit"); + flags &= ~MPTCP_PM_ADDR_FLAG_IMPLICIT; + if (flags) + printf(","); + } + /* bump unknown flags, if any */ if (flags) printf("0x%x", flags); @@ -657,8 +664,10 @@ int set_flags(int fd, int pm_family, int argc, char *argv[]) u_int32_t flags = 0; u_int16_t family; int nest_start; + int use_id = 0; + u_int8_t id; int off = 0; - int arg; + int arg = 2; memset(data, 0, sizeof(data)); nh = (void *)data; @@ -674,29 +683,45 @@ int set_flags(int fd, int pm_family, int argc, char *argv[]) nest->rta_len = RTA_LENGTH(0); off += NLMSG_ALIGN(nest->rta_len); - /* addr data */ - rta = (void *)(data + off); - if (inet_pton(AF_INET, argv[2], RTA_DATA(rta))) { - family = AF_INET; - rta->rta_type = MPTCP_PM_ADDR_ATTR_ADDR4; - rta->rta_len = RTA_LENGTH(4); - } else if (inet_pton(AF_INET6, argv[2], RTA_DATA(rta))) { - family = AF_INET6; - rta->rta_type = MPTCP_PM_ADDR_ATTR_ADDR6; - rta->rta_len = RTA_LENGTH(16); + if (!strcmp(argv[arg], "id")) { + if (++arg >= argc) + error(1, 0, " missing id value"); + + use_id = 1; + id = atoi(argv[arg]); + rta = (void *)(data + off); + rta->rta_type = MPTCP_PM_ADDR_ATTR_ID; + rta->rta_len = RTA_LENGTH(1); + memcpy(RTA_DATA(rta), &id, 1); + off += NLMSG_ALIGN(rta->rta_len); } else { - error(1, errno, "can't parse ip %s", argv[2]); + /* addr data */ + rta = (void *)(data + off); + if (inet_pton(AF_INET, argv[arg], RTA_DATA(rta))) { + family = AF_INET; + rta->rta_type = MPTCP_PM_ADDR_ATTR_ADDR4; + rta->rta_len = RTA_LENGTH(4); + } else if (inet_pton(AF_INET6, argv[arg], RTA_DATA(rta))) { + family = AF_INET6; + rta->rta_type = MPTCP_PM_ADDR_ATTR_ADDR6; + rta->rta_len = RTA_LENGTH(16); + } else { + error(1, errno, "can't parse ip %s", argv[arg]); + } + off += NLMSG_ALIGN(rta->rta_len); + + /* family */ + rta = (void *)(data + off); + rta->rta_type = MPTCP_PM_ADDR_ATTR_FAMILY; + rta->rta_len = RTA_LENGTH(2); + memcpy(RTA_DATA(rta), &family, 2); + off += NLMSG_ALIGN(rta->rta_len); } - off += NLMSG_ALIGN(rta->rta_len); - /* family */ - rta = (void *)(data + off); - rta->rta_type = MPTCP_PM_ADDR_ATTR_FAMILY; - rta->rta_len = RTA_LENGTH(2); - memcpy(RTA_DATA(rta), &family, 2); - off += NLMSG_ALIGN(rta->rta_len); + if (++arg >= argc) + error(1, 0, " missing flags keyword"); - for (arg = 3; arg < argc; arg++) { + for (; arg < argc; arg++) { if (!strcmp(argv[arg], "flags")) { char *tok, *str; @@ -704,12 +729,14 @@ int set_flags(int fd, int pm_family, int argc, char *argv[]) if (++arg >= argc) error(1, 0, " missing flags value"); - /* do not support flag list yet */ for (str = argv[arg]; (tok = strtok(str, ",")); str = NULL) { if (!strcmp(tok, "backup")) flags |= MPTCP_PM_ADDR_FLAG_BACKUP; - else if (strcmp(tok, "nobackup")) + else if (!strcmp(tok, "fullmesh")) + flags |= MPTCP_PM_ADDR_FLAG_FULLMESH; + else if (strcmp(tok, "nobackup") && + strcmp(tok, "nofullmesh")) error(1, errno, "unknown flag %s", argv[arg]); } @@ -719,6 +746,21 @@ int set_flags(int fd, int pm_family, int argc, char *argv[]) rta->rta_len = RTA_LENGTH(4); memcpy(RTA_DATA(rta), &flags, 4); off += NLMSG_ALIGN(rta->rta_len); + } else if (!strcmp(argv[arg], "port")) { + u_int16_t port; + + if (use_id) + error(1, 0, " port can't be used with id"); + + if (++arg >= argc) + error(1, 0, " missing port value"); + + port = atoi(argv[arg]); + rta = (void *)(data + off); + rta->rta_type = MPTCP_PM_ADDR_ATTR_PORT; + rta->rta_len = RTA_LENGTH(2); + memcpy(RTA_DATA(rta), &port, 2); + off += NLMSG_ALIGN(rta->rta_len); } else { error(1, 0, "unknown keyword %s", argv[arg]); } diff --git a/tools/testing/selftests/net/mptcp/settings b/tools/testing/selftests/net/mptcp/settings index a62d2fa1275c..79b65bdf05db 100644 --- a/tools/testing/selftests/net/mptcp/settings +++ b/tools/testing/selftests/net/mptcp/settings @@ -1 +1 @@ -timeout=600 +timeout=1200 diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh index 543ad7513a8e..736e358dc549 100755 --- a/tools/testing/selftests/net/pmtu.sh +++ b/tools/testing/selftests/net/pmtu.sh @@ -26,6 +26,15 @@ # - pmtu_ipv6 # Same as pmtu_ipv4, except for locked PMTU tests, using IPv6 # +# - pmtu_ipv4_dscp_icmp_exception +# Set up the same network topology as pmtu_ipv4, but use non-default +# routing table in A. A fib-rule is used to jump to this routing table +# based on DSCP. Send ICMPv4 packets with the expected DSCP value and +# verify that ECN doesn't interfere with the creation of PMTU exceptions. +# +# - pmtu_ipv4_dscp_udp_exception +# Same as pmtu_ipv4_dscp_icmp_exception, but use UDP instead of ICMP. +# # - pmtu_ipv4_vxlan4_exception # Set up the same network topology as pmtu_ipv4, create a VXLAN tunnel # over IPv4 between A and B, routed via R1. On the link between R1 and B, @@ -203,6 +212,8 @@ which ping6 > /dev/null 2>&1 && ping6=$(which ping6) || ping6=$(which ping) tests=" pmtu_ipv4_exception ipv4: PMTU exceptions 1 pmtu_ipv6_exception ipv6: PMTU exceptions 1 + pmtu_ipv4_dscp_icmp_exception ICMPv4 with DSCP and ECN: PMTU exceptions 1 + pmtu_ipv4_dscp_udp_exception UDPv4 with DSCP and ECN: PMTU exceptions 1 pmtu_ipv4_vxlan4_exception IPv4 over vxlan4: PMTU exceptions 1 pmtu_ipv6_vxlan4_exception IPv6 over vxlan4: PMTU exceptions 1 pmtu_ipv4_vxlan6_exception IPv4 over vxlan6: PMTU exceptions 1 @@ -323,6 +334,9 @@ routes_nh=" B 6 default 61 " +policy_mark=0x04 +rt_table=main + veth4_a_addr="192.168.1.1" veth4_b_addr="192.168.1.2" veth4_c_addr="192.168.2.10" @@ -346,6 +360,7 @@ dummy6_mask="64" err_buf= tcpdump_pids= nettest_pids= +socat_pids= err() { err_buf="${err_buf}${1} @@ -374,6 +389,16 @@ run_cmd() { return $rc } +run_cmd_bg() { + cmd="$*" + + if [ "$VERBOSE" = "1" ]; then + printf " COMMAND: %s &\n" "${cmd}" + fi + + $cmd 2>&1 & +} + # Find the auto-generated name for this namespace nsname() { eval echo \$NS_$1 @@ -670,10 +695,10 @@ setup_nettest_xfrm() { [ ${1} -eq 6 ] && proto="-6" || proto="" port=${2} - run_cmd ${ns_a} nettest ${proto} -q -D -s -x -p ${port} -t 5 & + run_cmd_bg "${ns_a}" nettest "${proto}" -q -D -s -x -p "${port}" -t 5 nettest_pids="${nettest_pids} $!" - run_cmd ${ns_b} nettest ${proto} -q -D -s -x -p ${port} -t 5 & + run_cmd_bg "${ns_b}" nettest "${proto}" -q -D -s -x -p "${port}" -t 5 nettest_pids="${nettest_pids} $!" } @@ -713,7 +738,7 @@ setup_routing_old() { ns_name="$(nsname ${ns})" - ip -n ${ns_name} route add ${addr} via ${gw} + ip -n "${ns_name}" route add "${addr}" table "${rt_table}" via "${gw}" ns=""; addr=""; gw="" done @@ -743,7 +768,7 @@ setup_routing_new() { ns_name="$(nsname ${ns})" - ip -n ${ns_name} -${fam} route add ${addr} nhid ${nhid} + ip -n "${ns_name}" -"${fam}" route add "${addr}" table "${rt_table}" nhid "${nhid}" ns=""; fam=""; addr=""; nhid="" done @@ -788,6 +813,24 @@ setup_routing() { return 0 } +setup_policy_routing() { + setup_routing + + ip -netns "${NS_A}" -4 rule add dsfield "${policy_mark}" \ + table "${rt_table}" + + # Set the IPv4 Don't Fragment bit with tc, since socat doesn't seem to + # have an option do to it. + tc -netns "${NS_A}" qdisc replace dev veth_A-R1 root prio + tc -netns "${NS_A}" qdisc replace dev veth_A-R2 root prio + tc -netns "${NS_A}" filter add dev veth_A-R1 \ + protocol ipv4 flower ip_proto udp \ + action pedit ex munge ip df set 0x40 pipe csum ip and udp + tc -netns "${NS_A}" filter add dev veth_A-R2 \ + protocol ipv4 flower ip_proto udp \ + action pedit ex munge ip df set 0x40 pipe csum ip and udp +} + setup_bridge() { run_cmd ${ns_a} ip link add br0 type bridge || return $ksft_skip run_cmd ${ns_a} ip link set br0 up @@ -865,7 +908,6 @@ setup_ovs_bridge() { setup() { [ "$(id -u)" -ne 0 ] && echo " need to run as root" && return $ksft_skip - cleanup for arg do eval setup_${arg} || { echo " ${arg} not supported"; return 1; } done @@ -876,7 +918,7 @@ trace() { for arg do [ "${ns_cmd}" = "" ] && ns_cmd="${arg}" && continue - ${ns_cmd} tcpdump -s 0 -i "${arg}" -w "${name}_${arg}.pcap" 2> /dev/null & + ${ns_cmd} tcpdump --immediate-mode -s 0 -i "${arg}" -w "${name}_${arg}.pcap" 2> /dev/null & tcpdump_pids="${tcpdump_pids} $!" ns_cmd= done @@ -894,6 +936,11 @@ cleanup() { done nettest_pids= + for pid in ${socat_pids}; do + kill "${pid}" + done + socat_pids= + for n in ${NS_A} ${NS_B} ${NS_C} ${NS_R1} ${NS_R2}; do ip netns del ${n} 2> /dev/null done @@ -941,15 +988,21 @@ link_get_mtu() { route_get_dst_exception() { ns_cmd="${1}" dst="${2}" + dsfield="${3}" + + if [ -z "${dsfield}" ]; then + dsfield=0 + fi - ${ns_cmd} ip route get "${dst}" + ${ns_cmd} ip route get "${dst}" dsfield "${dsfield}" } route_get_dst_pmtu_from_exception() { ns_cmd="${1}" dst="${2}" + dsfield="${3}" - mtu_parse "$(route_get_dst_exception "${ns_cmd}" ${dst})" + mtu_parse "$(route_get_dst_exception "${ns_cmd}" "${dst}" "${dsfield}")" } check_pmtu_value() { @@ -1059,6 +1112,95 @@ test_pmtu_ipv6_exception() { test_pmtu_ipvX 6 } +test_pmtu_ipv4_dscp_icmp_exception() { + rt_table=100 + + setup namespaces policy_routing || return $ksft_skip + trace "${ns_a}" veth_A-R1 "${ns_r1}" veth_R1-A \ + "${ns_r1}" veth_R1-B "${ns_b}" veth_B-R1 \ + "${ns_a}" veth_A-R2 "${ns_r2}" veth_R2-A \ + "${ns_r2}" veth_R2-B "${ns_b}" veth_B-R2 + + # Set up initial MTU values + mtu "${ns_a}" veth_A-R1 2000 + mtu "${ns_r1}" veth_R1-A 2000 + mtu "${ns_r1}" veth_R1-B 1400 + mtu "${ns_b}" veth_B-R1 1400 + + mtu "${ns_a}" veth_A-R2 2000 + mtu "${ns_r2}" veth_R2-A 2000 + mtu "${ns_r2}" veth_R2-B 1500 + mtu "${ns_b}" veth_B-R2 1500 + + len=$((2000 - 20 - 8)) # Fills MTU of veth_A-R1 + + dst1="${prefix4}.${b_r1}.1" + dst2="${prefix4}.${b_r2}.1" + + # Create route exceptions + dsfield=${policy_mark} # No ECN bit set (Not-ECT) + run_cmd "${ns_a}" ping -q -M want -Q "${dsfield}" -c 1 -w 1 -s "${len}" "${dst1}" + + dsfield=$(printf "%#x" $((policy_mark + 0x02))) # ECN=2 (ECT(0)) + run_cmd "${ns_a}" ping -q -M want -Q "${dsfield}" -c 1 -w 1 -s "${len}" "${dst2}" + + # Check that exceptions have been created with the correct PMTU + pmtu_1="$(route_get_dst_pmtu_from_exception "${ns_a}" "${dst1}" "${policy_mark}")" + check_pmtu_value "1400" "${pmtu_1}" "exceeding MTU" || return 1 + + pmtu_2="$(route_get_dst_pmtu_from_exception "${ns_a}" "${dst2}" "${policy_mark}")" + check_pmtu_value "1500" "${pmtu_2}" "exceeding MTU" || return 1 +} + +test_pmtu_ipv4_dscp_udp_exception() { + rt_table=100 + + if ! which socat > /dev/null 2>&1; then + echo "'socat' command not found; skipping tests" + return $ksft_skip + fi + + setup namespaces policy_routing || return $ksft_skip + trace "${ns_a}" veth_A-R1 "${ns_r1}" veth_R1-A \ + "${ns_r1}" veth_R1-B "${ns_b}" veth_B-R1 \ + "${ns_a}" veth_A-R2 "${ns_r2}" veth_R2-A \ + "${ns_r2}" veth_R2-B "${ns_b}" veth_B-R2 + + # Set up initial MTU values + mtu "${ns_a}" veth_A-R1 2000 + mtu "${ns_r1}" veth_R1-A 2000 + mtu "${ns_r1}" veth_R1-B 1400 + mtu "${ns_b}" veth_B-R1 1400 + + mtu "${ns_a}" veth_A-R2 2000 + mtu "${ns_r2}" veth_R2-A 2000 + mtu "${ns_r2}" veth_R2-B 1500 + mtu "${ns_b}" veth_B-R2 1500 + + len=$((2000 - 20 - 8)) # Fills MTU of veth_A-R1 + + dst1="${prefix4}.${b_r1}.1" + dst2="${prefix4}.${b_r2}.1" + + # Create route exceptions + run_cmd_bg "${ns_b}" socat UDP-LISTEN:50000 OPEN:/dev/null,wronly=1 + socat_pids="${socat_pids} $!" + + dsfield=${policy_mark} # No ECN bit set (Not-ECT) + run_cmd "${ns_a}" socat OPEN:/dev/zero,rdonly=1,readbytes="${len}" \ + UDP:"${dst1}":50000,tos="${dsfield}" + + dsfield=$(printf "%#x" $((policy_mark + 0x02))) # ECN=2 (ECT(0)) + run_cmd "${ns_a}" socat OPEN:/dev/zero,rdonly=1,readbytes="${len}" \ + UDP:"${dst2}":50000,tos="${dsfield}" + + # Check that exceptions have been created with the correct PMTU + pmtu_1="$(route_get_dst_pmtu_from_exception "${ns_a}" "${dst1}" "${policy_mark}")" + check_pmtu_value "1400" "${pmtu_1}" "exceeding MTU" || return 1 + pmtu_2="$(route_get_dst_pmtu_from_exception "${ns_a}" "${dst2}" "${policy_mark}")" + check_pmtu_value "1500" "${pmtu_2}" "exceeding MTU" || return 1 +} + test_pmtu_ipvX_over_vxlanY_or_geneveY_exception() { type=${1} family=${2} @@ -1836,6 +1978,10 @@ run_test() { unset IFS + # Since cleanup() relies on variables modified by this subshell, it + # has to run in this context. + trap cleanup EXIT + if [ "$VERBOSE" = "1" ]; then printf "\n##########################################################################\n\n" fi diff --git a/tools/testing/selftests/net/psock_fanout.c b/tools/testing/selftests/net/psock_fanout.c index 3653d6468c67..1a736f700be4 100644 --- a/tools/testing/selftests/net/psock_fanout.c +++ b/tools/testing/selftests/net/psock_fanout.c @@ -53,6 +53,7 @@ #include <unistd.h> #include "psock_lib.h" +#include "../kselftest.h" #define RING_NUM_FRAMES 20 @@ -117,7 +118,7 @@ static void sock_fanout_set_cbpf(int fd) struct sock_fprog bpf_prog; bpf_prog.filter = bpf_filter; - bpf_prog.len = sizeof(bpf_filter) / sizeof(struct sock_filter); + bpf_prog.len = ARRAY_SIZE(bpf_filter); if (setsockopt(fd, SOL_PACKET, PACKET_FANOUT_DATA, &bpf_prog, sizeof(bpf_prog))) { @@ -162,7 +163,7 @@ static void sock_fanout_set_ebpf(int fd) memset(&attr, 0, sizeof(attr)); attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER; attr.insns = (unsigned long) prog; - attr.insn_cnt = sizeof(prog) / sizeof(prog[0]); + attr.insn_cnt = ARRAY_SIZE(prog); attr.license = (unsigned long) "GPL"; attr.log_buf = (unsigned long) log_buf, attr.log_size = sizeof(log_buf), diff --git a/tools/testing/selftests/net/reuseport_bpf_numa.c b/tools/testing/selftests/net/reuseport_bpf_numa.c index b2eebf669b8c..c9ba36aa688e 100644 --- a/tools/testing/selftests/net/reuseport_bpf_numa.c +++ b/tools/testing/selftests/net/reuseport_bpf_numa.c @@ -86,7 +86,7 @@ static void attach_bpf(int fd) memset(&attr, 0, sizeof(attr)); attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER; - attr.insn_cnt = sizeof(prog) / sizeof(prog[0]); + attr.insn_cnt = ARRAY_SIZE(prog); attr.insns = (unsigned long) &prog; attr.license = (unsigned long) &bpf_license; attr.log_buf = (unsigned long) &bpf_log_buf; diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh index c9ce3dfa42ee..0900c5438fbb 100755 --- a/tools/testing/selftests/net/rtnetlink.sh +++ b/tools/testing/selftests/net/rtnetlink.sh @@ -216,9 +216,9 @@ kci_test_route_get() check_err $? ip route get fe80::1 dev "$devdummy" > /dev/null check_err $? - ip route get 127.0.0.1 from 127.0.0.1 oif lo tos 0x1 mark 0x1 > /dev/null + ip route get 127.0.0.1 from 127.0.0.1 oif lo tos 0x10 mark 0x1 > /dev/null check_err $? - ip route get ::1 from ::1 iif lo oif lo tos 0x1 mark 0x1 > /dev/null + ip route get ::1 from ::1 iif lo oif lo tos 0x10 mark 0x1 > /dev/null check_err $? ip addr add dev "$devdummy" 10.23.7.11/24 check_err $? diff --git a/tools/testing/selftests/net/settings b/tools/testing/selftests/net/settings index 694d70710ff0..dfc27cdc6c05 100644 --- a/tools/testing/selftests/net/settings +++ b/tools/testing/selftests/net/settings @@ -1 +1 @@ -timeout=300 +timeout=1500 diff --git a/tools/testing/selftests/net/test_vxlan_vnifiltering.sh b/tools/testing/selftests/net/test_vxlan_vnifiltering.sh new file mode 100755 index 000000000000..704997ffc244 --- /dev/null +++ b/tools/testing/selftests/net/test_vxlan_vnifiltering.sh @@ -0,0 +1,579 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# This test is for checking the VXLAN vni filtering api and +# datapath. +# It simulates two hypervisors running two VMs each using four network +# six namespaces: two for the HVs, four for the VMs. Each VM is +# connected to a separate bridge. The VM's use overlapping vlans and +# hence the separate bridge domain. Each vxlan device is a collect +# metadata device with vni filtering and hence has the ability to +# terminate configured vni's only. + +# +--------------------------------+ +------------------------------------+ +# | vm-11 netns | | vm-21 netns | +# | | | | +# |+------------+ +-------------+ | |+-------------+ +----------------+ | +# ||veth-11.10 | |veth-11.20 | | ||veth-21.10 | | veth-21.20 | | +# ||10.0.10.11/24 |10.0.20.11/24| | ||10.0.10.21/24| | 10.0.20.21/24 | | +# |+------|-----+ +|------------+ | |+-----------|-+ +---|------------+ | +# | | | | | | | | +# | | | | | +------------+ | +# | +------------+ | | | veth-21 | | +# | | veth-11 | | | | | | +# | | | | | +-----|------+ | +# | +-----|------+ | | | | +# | | | | | | +# +------------|-------------------+ +---------------|--------------------+ +# +------------|-----------------------------------------|-------------------+ +# | +-----|------+ +-----|------+ | +# | |vethhv-11 | |vethhv-21 | | +# | +----|-------+ +-----|------+ | +# | +---|---+ +---|--+ | +# | | br1 | | br2 | | +# | +---|---+ +---|--+ | +# | +---|----+ +---|--+ | +# | | vxlan1| |vxlan2| | +# | +--|-----+ +--|---+ | +# | | | | +# | | +---------------------+ | | +# | | |veth0 | | | +# | +---------|172.16.0.1/24 -----------+ | +# | |2002:fee1::1/64 | | +# | hv-1 netns +--------|------------+ | +# +-----------------------------|--------------------------------------------+ +# | +# +-----------------------------|--------------------------------------------+ +# | hv-2 netns +--------|-------------+ | +# | | veth0 | | +# | +------| 172.16.0.2/24 |---+ | +# | | | 2002:fee1::2/64 | | | +# | | | | | | +# | | +----------------------+ | - | +# | | | | +# | +-|-------+ +--------|-+ | +# | | vxlan1 | | vxlan2 | | +# | +----|----+ +---|------+ | +# | +--|--+ +-|---+ | +# | | br1 | | br2 | | +# | +--|--+ +--|--+ | +# | +-----|-------+ +----|-------+ | +# | | vethhv-12 | |vethhv-22 | | +# | +------|------+ +-------|----+ | +# +-----------------|----------------------------|---------------------------+ +# | | +# +-----------------|-----------------+ +--------|---------------------------+ +# | +-------|---+ | | +--|---------+ | +# | | veth-12 | | | |veth-22 | | +# | +-|--------|+ | | +--|--------|+ | +# | | | | | | | | +# |+----------|--+ +---|-----------+ | |+-------|-----+ +|---------------+ | +# ||veth-12.10 | |veth-12.20 | | ||veth-22.10 | |veth-22.20 | | +# ||10.0.10.12/24| |10.0.20.12/24 | | ||10.0.10.22/24| |10.0.20.22/24 | | +# |+-------------+ +---------------+ | |+-------------+ +----------------+ | +# | | | | +# | | | | +# | vm-12 netns | |vm-22 netns | +# +-----------------------------------+ +------------------------------------+ +# +# +# This test tests the new vxlan vnifiltering api + +ret=0 +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + +# all tests in this script. Can be overridden with -t option +TESTS=" + vxlan_vnifilter_api + vxlan_vnifilter_datapath + vxlan_vnifilter_datapath_pervni + vxlan_vnifilter_datapath_mgroup + vxlan_vnifilter_datapath_mgroup_pervni + vxlan_vnifilter_metadata_and_traditional_mix +" +VERBOSE=0 +PAUSE_ON_FAIL=no +PAUSE=no + +which ping6 > /dev/null 2>&1 && ping6=$(which ping6) || ping6=$(which ping) + +log_test() +{ + local rc=$1 + local expected=$2 + local msg="$3" + + if [ ${rc} -eq ${expected} ]; then + printf " TEST: %-60s [ OK ]\n" "${msg}" + nsuccess=$((nsuccess+1)) + else + ret=1 + nfail=$((nfail+1)) + printf " TEST: %-60s [FAIL]\n" "${msg}" + if [ "${PAUSE_ON_FAIL}" = "yes" ]; then + echo + echo "hit enter to continue, 'q' to quit" + read a + [ "$a" = "q" ] && exit 1 + fi + fi + + if [ "${PAUSE}" = "yes" ]; then + echo + echo "hit enter to continue, 'q' to quit" + read a + [ "$a" = "q" ] && exit 1 + fi +} + +run_cmd() +{ + local cmd="$1" + local out + local stderr="2>/dev/null" + + if [ "$VERBOSE" = "1" ]; then + printf "COMMAND: $cmd\n" + stderr= + fi + + out=$(eval $cmd $stderr) + rc=$? + if [ "$VERBOSE" = "1" -a -n "$out" ]; then + echo " $out" + fi + + return $rc +} + +check_hv_connectivity() { + ip netns exec hv-1 ping -c 1 -W 1 $1 &>/dev/null + sleep 1 + ip netns exec hv-1 ping -c 1 -W 1 $2 &>/dev/null + + return $? +} + +check_vm_connectivity() { + run_cmd "ip netns exec vm-11 ping -c 1 -W 1 10.0.10.12" + log_test $? 0 "VM connectivity over $1 (ipv4 default rdst)" + + run_cmd "ip netns exec vm-21 ping -c 1 -W 1 10.0.10.22" + log_test $? 0 "VM connectivity over $1 (ipv6 default rdst)" +} + +cleanup() { + ip link del veth-hv-1 2>/dev/null || true + ip link del vethhv-11 vethhv-12 vethhv-21 vethhv-22 2>/dev/null || true + + for ns in hv-1 hv-2 vm-11 vm-21 vm-12 vm-22 vm-31 vm-32; do + ip netns del $ns 2>/dev/null || true + done +} + +trap cleanup EXIT + +setup-hv-networking() { + hv=$1 + local1=$2 + mask1=$3 + local2=$4 + mask2=$5 + + ip netns add hv-$hv + ip link set veth-hv-$hv netns hv-$hv + ip -netns hv-$hv link set veth-hv-$hv name veth0 + ip -netns hv-$hv addr add $local1/$mask1 dev veth0 + ip -netns hv-$hv addr add $local2/$mask2 dev veth0 + ip -netns hv-$hv link set veth0 up +} + +# Setups a "VM" simulated by a netns an a veth pair +# example: setup-vm <hvid> <vmid> <brid> <VATTRS> <mcast_for_bum> +# VATTRS = comma separated "<vlan>-<v[46]>-<localip>-<remoteip>-<VTYPE>-<vxlandstport>" +# VTYPE = vxlan device type. "default = traditional device, metadata = metadata device +# vnifilter = vnifiltering device, +# vnifilterg = vnifiltering device with per vni group/remote" +# example: +# setup-vm 1 11 1 \ +# 10-v4-172.16.0.1-239.1.1.100-vnifilterg,20-v4-172.16.0.1-239.1.1.100-vnifilterg 1 +# +setup-vm() { + hvid=$1 + vmid=$2 + brid=$3 + vattrs=$4 + mcast=$5 + lastvxlandev="" + + # create bridge + ip -netns hv-$hvid link add br$brid type bridge vlan_filtering 1 vlan_default_pvid 0 \ + mcast_snooping 0 + ip -netns hv-$hvid link set br$brid up + + # create vm namespace and interfaces and connect to hypervisor + # namespace + ip netns add vm-$vmid + hvvethif="vethhv-$vmid" + vmvethif="veth-$vmid" + ip link add $hvvethif type veth peer name $vmvethif + ip link set $hvvethif netns hv-$hvid + ip link set $vmvethif netns vm-$vmid + ip -netns hv-$hvid link set $hvvethif up + ip -netns vm-$vmid link set $vmvethif up + ip -netns hv-$hvid link set $hvvethif master br$brid + + # configure VM vlan/vni filtering on hypervisor + for vmap in $(echo $vattrs | cut -d "," -f1- --output-delimiter=' ') + do + local vid=$(echo $vmap | awk -F'-' '{print ($1)}') + local family=$(echo $vmap | awk -F'-' '{print ($2)}') + local localip=$(echo $vmap | awk -F'-' '{print ($3)}') + local group=$(echo $vmap | awk -F'-' '{print ($4)}') + local vtype=$(echo $vmap | awk -F'-' '{print ($5)}') + local port=$(echo $vmap | awk -F'-' '{print ($6)}') + + ip -netns vm-$vmid link add name $vmvethif.$vid link $vmvethif type vlan id $vid + ip -netns vm-$vmid addr add 10.0.$vid.$vmid/24 dev $vmvethif.$vid + ip -netns vm-$vmid link set $vmvethif.$vid up + + tid=$vid + vxlandev="vxlan$brid" + vxlandevflags="" + + if [[ -n $vtype && $vtype == "metadata" ]]; then + vxlandevflags="$vxlandevflags external" + elif [[ -n $vtype && $vtype == "vnifilter" || $vtype == "vnifilterg" ]]; then + vxlandevflags="$vxlandevflags external vnifilter" + tid=$((vid+brid)) + else + vxlandevflags="$vxlandevflags id $tid" + vxlandev="vxlan$tid" + fi + + if [[ -n $vtype && $vtype != "vnifilterg" ]]; then + if [[ -n "$group" && "$group" != "null" ]]; then + if [ $mcast -eq 1 ]; then + vxlandevflags="$vxlandevflags group $group" + else + vxlandevflags="$vxlandevflags remote $group" + fi + fi + fi + + if [[ -n "$port" && "$port" != "default" ]]; then + vxlandevflags="$vxlandevflags dstport $port" + fi + + # create vxlan device + if [ "$vxlandev" != "$lastvxlandev" ]; then + ip -netns hv-$hvid link add $vxlandev type vxlan local $localip $vxlandevflags dev veth0 2>/dev/null + ip -netns hv-$hvid link set $vxlandev master br$brid + ip -netns hv-$hvid link set $vxlandev up + lastvxlandev=$vxlandev + fi + + # add vlan + bridge -netns hv-$hvid vlan add vid $vid dev $hvvethif + bridge -netns hv-$hvid vlan add vid $vid pvid dev $vxlandev + + # Add bridge vni filter for tx + if [[ -n $vtype && $vtype == "metadata" || $vtype == "vnifilter" || $vtype == "vnifilterg" ]]; then + bridge -netns hv-$hvid link set dev $vxlandev vlan_tunnel on + bridge -netns hv-$hvid vlan add dev $vxlandev vid $vid tunnel_info id $tid + fi + + if [[ -n $vtype && $vtype == "metadata" ]]; then + bridge -netns hv-$hvid fdb add 00:00:00:00:00:00 dev $vxlandev \ + src_vni $tid vni $tid dst $group self + elif [[ -n $vtype && $vtype == "vnifilter" ]]; then + # Add per vni rx filter with 'bridge vni' api + bridge -netns hv-$hvid vni add dev $vxlandev vni $tid + elif [[ -n $vtype && $vtype == "vnifilterg" ]]; then + # Add per vni group config with 'bridge vni' api + if [ -n "$group" ]; then + if [ "$family" == "v4" ]; then + if [ $mcast -eq 1 ]; then + bridge -netns hv-$hvid vni add dev $vxlandev vni $tid group $group + else + bridge -netns hv-$hvid vni add dev $vxlandev vni $tid remote $group + fi + else + if [ $mcast -eq 1 ]; then + bridge -netns hv-$hvid vni add dev $vxlandev vni $tid group6 $group + else + bridge -netns hv-$hvid vni add dev $vxlandev vni $tid remote6 $group + fi + fi + fi + fi + done +} + +setup_vnifilter_api() +{ + ip link add veth-host type veth peer name veth-testns + ip netns add testns + ip link set veth-testns netns testns +} + +cleanup_vnifilter_api() +{ + ip link del veth-host 2>/dev/null || true + ip netns del testns 2>/dev/null || true +} + +# tests vxlan filtering api +vxlan_vnifilter_api() +{ + hv1addr1="172.16.0.1" + hv2addr1="172.16.0.2" + hv1addr2="2002:fee1::1" + hv2addr2="2002:fee1::2" + localip="172.16.0.1" + group="239.1.1.101" + + cleanup_vnifilter_api &>/dev/null + setup_vnifilter_api + + # Duplicate vni test + # create non-vnifiltering traditional vni device + run_cmd "ip -netns testns link add vxlan100 type vxlan id 100 local $localip dev veth-testns dstport 4789" + log_test $? 0 "Create traditional vxlan device" + + # create vni filtering device + run_cmd "ip -netns testns link add vxlan-ext1 type vxlan vnifilter local $localip dev veth-testns dstport 4789" + log_test $? 1 "Cannot create vnifilter device without external flag" + + run_cmd "ip -netns testns link add vxlan-ext1 type vxlan external vnifilter local $localip dev veth-testns dstport 4789" + log_test $? 0 "Creating external vxlan device with vnifilter flag" + + run_cmd "bridge -netns testns vni add dev vxlan-ext1 vni 100" + log_test $? 0 "Cannot set in-use vni id on vnifiltering device" + + run_cmd "bridge -netns testns vni add dev vxlan-ext1 vni 200" + log_test $? 0 "Set new vni id on vnifiltering device" + + run_cmd "ip -netns testns link add vxlan-ext2 type vxlan external vnifilter local $localip dev veth-testns dstport 4789" + log_test $? 0 "Create second external vxlan device with vnifilter flag" + + run_cmd "bridge -netns testns vni add dev vxlan-ext2 vni 200" + log_test $? 255 "Cannot set in-use vni id on vnifiltering device" + + run_cmd "bridge -netns testns vni add dev vxlan-ext2 vni 300" + log_test $? 0 "Set new vni id on vnifiltering device" + + # check in bridge vni show + run_cmd "bridge -netns testns vni add dev vxlan-ext2 vni 300" + log_test $? 0 "Update vni id on vnifiltering device" + + run_cmd "bridge -netns testns vni add dev vxlan-ext2 vni 400" + log_test $? 0 "Add new vni id on vnifiltering device" + + # add multicast group per vni + run_cmd "bridge -netns testns vni add dev vxlan-ext1 vni 200 group $group" + log_test $? 0 "Set multicast group on existing vni" + + # add multicast group per vni + run_cmd "bridge -netns testns vni add dev vxlan-ext2 vni 300 group $group" + log_test $? 0 "Set multicast group on existing vni" + + # set vnifilter on an existing external vxlan device + run_cmd "ip -netns testns link set dev vxlan-ext1 type vxlan external vnifilter" + log_test $? 2 "Cannot set vnifilter flag on a device" + + # change vxlan vnifilter flag + run_cmd "ip -netns testns link set dev vxlan-ext1 type vxlan external novnifilter" + log_test $? 2 "Cannot unset vnifilter flag on a device" +} + +# Sanity test vnifilter datapath +# vnifilter vnis inherit BUM group from +# vxlan device +vxlan_vnifilter_datapath() +{ + hv1addr1="172.16.0.1" + hv2addr1="172.16.0.2" + hv1addr2="2002:fee1::1" + hv2addr2="2002:fee1::2" + + ip link add veth-hv-1 type veth peer name veth-hv-2 + setup-hv-networking 1 $hv1addr1 24 $hv1addr2 64 $hv2addr1 $hv2addr2 + setup-hv-networking 2 $hv2addr1 24 $hv2addr2 64 $hv1addr1 $hv1addr2 + + check_hv_connectivity hv2addr1 hv2addr2 + + setup-vm 1 11 1 10-v4-$hv1addr1-$hv2addr1-vnifilter,20-v4-$hv1addr1-$hv2addr1-vnifilter 0 + setup-vm 1 21 2 10-v6-$hv1addr2-$hv2addr2-vnifilter,20-v6-$hv1addr2-$hv2addr2-vnifilter 0 + + setup-vm 2 12 1 10-v4-$hv2addr1-$hv1addr1-vnifilter,20-v4-$hv2addr1-$hv1addr1-vnifilter 0 + setup-vm 2 22 2 10-v6-$hv2addr2-$hv1addr2-vnifilter,20-v6-$hv2addr2-$hv1addr2-vnifilter 0 + + check_vm_connectivity "vnifiltering vxlan" +} + +# Sanity test vnifilter datapath +# with vnifilter per vni configured BUM +# group/remote +vxlan_vnifilter_datapath_pervni() +{ + hv1addr1="172.16.0.1" + hv2addr1="172.16.0.2" + hv1addr2="2002:fee1::1" + hv2addr2="2002:fee1::2" + + ip link add veth-hv-1 type veth peer name veth-hv-2 + setup-hv-networking 1 $hv1addr1 24 $hv1addr2 64 + setup-hv-networking 2 $hv2addr1 24 $hv2addr2 64 + + check_hv_connectivity hv2addr1 hv2addr2 + + setup-vm 1 11 1 10-v4-$hv1addr1-$hv2addr1-vnifilterg,20-v4-$hv1addr1-$hv2addr1-vnifilterg 0 + setup-vm 1 21 2 10-v6-$hv1addr2-$hv2addr2-vnifilterg,20-v6-$hv1addr2-$hv2addr2-vnifilterg 0 + + setup-vm 2 12 1 10-v4-$hv2addr1-$hv1addr1-vnifilterg,20-v4-$hv2addr1-$hv1addr1-vnifilterg 0 + setup-vm 2 22 2 10-v6-$hv2addr2-$hv1addr2-vnifilterg,20-v6-$hv2addr2-$hv1addr2-vnifilterg 0 + + check_vm_connectivity "vnifiltering vxlan pervni remote" +} + + +vxlan_vnifilter_datapath_mgroup() +{ + hv1addr1="172.16.0.1" + hv2addr1="172.16.0.2" + hv1addr2="2002:fee1::1" + hv2addr2="2002:fee1::2" + group="239.1.1.100" + group6="ff07::1" + + ip link add veth-hv-1 type veth peer name veth-hv-2 + setup-hv-networking 1 $hv1addr1 24 $hv1addr2 64 + setup-hv-networking 2 $hv2addr1 24 $hv2addr2 64 + + check_hv_connectivity hv2addr1 hv2addr2 + + setup-vm 1 11 1 10-v4-$hv1addr1-$group-vnifilter,20-v4-$hv1addr1-$group-vnifilter 1 + setup-vm 1 21 2 "10-v6-$hv1addr2-$group6-vnifilter,20-v6-$hv1addr2-$group6-vnifilter" 1 + + setup-vm 2 12 1 10-v4-$hv2addr1-$group-vnifilter,20-v4-$hv2addr1-$group-vnifilter 1 + setup-vm 2 22 2 10-v6-$hv2addr2-$group6-vnifilter,20-v6-$hv2addr2-$group6-vnifilter 1 + + check_vm_connectivity "vnifiltering vxlan mgroup" +} + +vxlan_vnifilter_datapath_mgroup_pervni() +{ + hv1addr1="172.16.0.1" + hv2addr1="172.16.0.2" + hv1addr2="2002:fee1::1" + hv2addr2="2002:fee1::2" + group="239.1.1.100" + group6="ff07::1" + + ip link add veth-hv-1 type veth peer name veth-hv-2 + setup-hv-networking 1 $hv1addr1 24 $hv1addr2 64 + setup-hv-networking 2 $hv2addr1 24 $hv2addr2 64 + + check_hv_connectivity hv2addr1 hv2addr2 + + setup-vm 1 11 1 10-v4-$hv1addr1-$group-vnifilterg,20-v4-$hv1addr1-$group-vnifilterg 1 + setup-vm 1 21 2 10-v6-$hv1addr2-$group6-vnifilterg,20-v6-$hv1addr2-$group6-vnifilterg 1 + + setup-vm 2 12 1 10-v4-$hv2addr1-$group-vnifilterg,20-v4-$hv2addr1-$group-vnifilterg 1 + setup-vm 2 22 2 10-v6-$hv2addr2-$group6-vnifilterg,20-v6-$hv2addr2-$group6-vnifilterg 1 + + check_vm_connectivity "vnifiltering vxlan pervni mgroup" +} + +vxlan_vnifilter_metadata_and_traditional_mix() +{ + hv1addr1="172.16.0.1" + hv2addr1="172.16.0.2" + hv1addr2="2002:fee1::1" + hv2addr2="2002:fee1::2" + + ip link add veth-hv-1 type veth peer name veth-hv-2 + setup-hv-networking 1 $hv1addr1 24 $hv1addr2 64 + setup-hv-networking 2 $hv2addr1 24 $hv2addr2 64 + + check_hv_connectivity hv2addr1 hv2addr2 + + setup-vm 1 11 1 10-v4-$hv1addr1-$hv2addr1-vnifilter,20-v4-$hv1addr1-$hv2addr1-vnifilter 0 + setup-vm 1 21 2 10-v6-$hv1addr2-$hv2addr2-vnifilter,20-v6-$hv1addr2-$hv2addr2-vnifilter 0 + setup-vm 1 31 3 30-v4-$hv1addr1-$hv2addr1-default-4790,40-v6-$hv1addr2-$hv2addr2-default-4790,50-v4-$hv1addr1-$hv2addr1-metadata-4791 0 + + + setup-vm 2 12 1 10-v4-$hv2addr1-$hv1addr1-vnifilter,20-v4-$hv2addr1-$hv1addr1-vnifilter 0 + setup-vm 2 22 2 10-v6-$hv2addr2-$hv1addr2-vnifilter,20-v6-$hv2addr2-$hv1addr2-vnifilter 0 + setup-vm 2 32 3 30-v4-$hv2addr1-$hv1addr1-default-4790,40-v6-$hv2addr2-$hv1addr2-default-4790,50-v4-$hv2addr1-$hv1addr1-metadata-4791 0 + + check_vm_connectivity "vnifiltering vxlan pervni remote mix" + + # check VM connectivity over traditional/non-vxlan filtering vxlan devices + run_cmd "ip netns exec vm-31 ping -c 1 -W 1 10.0.30.32" + log_test $? 0 "VM connectivity over traditional vxlan (ipv4 default rdst)" + + run_cmd "ip netns exec vm-31 ping -c 1 -W 1 10.0.40.32" + log_test $? 0 "VM connectivity over traditional vxlan (ipv6 default rdst)" + + run_cmd "ip netns exec vm-31 ping -c 1 -W 1 10.0.50.32" + log_test $? 0 "VM connectivity over metadata nonfiltering vxlan (ipv4 default rdst)" +} + +while getopts :t:pP46hv o +do + case $o in + t) TESTS=$OPTARG;; + p) PAUSE_ON_FAIL=yes;; + P) PAUSE=yes;; + v) VERBOSE=$(($VERBOSE + 1));; + h) usage; exit 0;; + *) usage; exit 1;; + esac +done + +# make sure we don't pause twice +[ "${PAUSE}" = "yes" ] && PAUSE_ON_FAIL=no + +if [ "$(id -u)" -ne 0 ];then + echo "SKIP: Need root privileges" + exit $ksft_skip; +fi + +if [ ! -x "$(command -v ip)" ]; then + echo "SKIP: Could not run test without ip tool" + exit $ksft_skip +fi + +ip link help vxlan 2>&1 | grep -q "vnifilter" +if [ $? -ne 0 ]; then + echo "SKIP: iproute2 too old, missing vxlan dev vnifilter setting" + sync + exit $ksft_skip +fi + +bridge vni help 2>&1 | grep -q "Usage: bridge vni" +if [ $? -ne 0 ]; then + echo "SKIP: iproute2 bridge lacks vxlan vnifiltering support" + exit $ksft_skip +fi + +# start clean +cleanup &> /dev/null + +for t in $TESTS +do + case $t in + none) setup; exit 0;; + *) $t; cleanup;; + esac +done + +if [ "$TESTS" != "none" ]; then + printf "\nTests passed: %3d\n" ${nsuccess} + printf "Tests failed: %3d\n" ${nfail} +fi + +exit $ret diff --git a/tools/testing/selftests/net/timestamping.c b/tools/testing/selftests/net/timestamping.c index aee631c5284e..044bc0e9ed81 100644 --- a/tools/testing/selftests/net/timestamping.c +++ b/tools/testing/selftests/net/timestamping.c @@ -325,8 +325,8 @@ int main(int argc, char **argv) struct ifreq device; struct ifreq hwtstamp; struct hwtstamp_config hwconfig, hwconfig_requested; - struct so_timestamping so_timestamping_get = { 0, -1 }; - struct so_timestamping so_timestamping = { 0, -1 }; + struct so_timestamping so_timestamping_get = { 0, 0 }; + struct so_timestamping so_timestamping = { 0, 0 }; struct sockaddr_in addr; struct ip_mreq imr; struct in_addr iaddr; diff --git a/tools/testing/selftests/net/toeplitz.c b/tools/testing/selftests/net/toeplitz.c index c5489341cfb8..90026a27eac0 100644 --- a/tools/testing/selftests/net/toeplitz.c +++ b/tools/testing/selftests/net/toeplitz.c @@ -52,6 +52,8 @@ #include <sys/types.h> #include <unistd.h> +#include "../kselftest.h" + #define TOEPLITZ_KEY_MIN_LEN 40 #define TOEPLITZ_KEY_MAX_LEN 60 @@ -295,7 +297,7 @@ static void __set_filter(int fd, int off_proto, uint8_t proto, int off_dport) struct sock_fprog prog = {}; prog.filter = filter; - prog.len = sizeof(filter) / sizeof(struct sock_filter); + prog.len = ARRAY_SIZE(filter); if (setsockopt(fd, SOL_SOCKET, SO_ATTACH_FILTER, &prog, sizeof(prog))) error(1, errno, "setsockopt filter"); } @@ -324,7 +326,7 @@ static void set_filter_null(int fd) struct sock_fprog prog = {}; prog.filter = filter; - prog.len = sizeof(filter) / sizeof(struct sock_filter); + prog.len = ARRAY_SIZE(filter); if (setsockopt(fd, SOL_SOCKET, SO_ATTACH_FILTER, &prog, sizeof(prog))) error(1, errno, "setsockopt filter"); } diff --git a/tools/testing/selftests/net/txtimestamp.c b/tools/testing/selftests/net/txtimestamp.c index fabb1d555ee5..10f2fde3686b 100644 --- a/tools/testing/selftests/net/txtimestamp.c +++ b/tools/testing/selftests/net/txtimestamp.c @@ -161,7 +161,7 @@ static void validate_timestamp(struct timespec *cur, int min_delay) max_delay = min_delay + cfg_delay_tolerance_usec; if (cur64 < start64 + min_delay || cur64 > start64 + max_delay) { - fprintf(stderr, "ERROR: %lu us expected between %d and %d\n", + fprintf(stderr, "ERROR: %" PRId64 " us expected between %d and %d\n", cur64 - start64, min_delay, max_delay); test_failed = true; } @@ -170,9 +170,9 @@ static void validate_timestamp(struct timespec *cur, int min_delay) static void __print_ts_delta_formatted(int64_t ts_delta) { if (cfg_print_nsec) - fprintf(stderr, "%lu ns", ts_delta); + fprintf(stderr, "%" PRId64 " ns", ts_delta); else - fprintf(stderr, "%lu us", ts_delta / NSEC_PER_USEC); + fprintf(stderr, "%" PRId64 " us", ts_delta / NSEC_PER_USEC); } static void __print_timestamp(const char *name, struct timespec *cur, diff --git a/tools/testing/selftests/netfilter/.gitignore b/tools/testing/selftests/netfilter/.gitignore index 8448f74adfec..4cb887b57413 100644 --- a/tools/testing/selftests/netfilter/.gitignore +++ b/tools/testing/selftests/netfilter/.gitignore @@ -1,2 +1,3 @@ # SPDX-License-Identifier: GPL-2.0-only nf-queue +connect_close diff --git a/tools/testing/selftests/netfilter/Makefile b/tools/testing/selftests/netfilter/Makefile index ffca314897c4..600e3a19d5e2 100644 --- a/tools/testing/selftests/netfilter/Makefile +++ b/tools/testing/selftests/netfilter/Makefile @@ -6,9 +6,10 @@ TEST_PROGS := nft_trans_stress.sh nft_fib.sh nft_nat.sh bridge_brouter.sh \ nft_concat_range.sh nft_conntrack_helper.sh \ nft_queue.sh nft_meta.sh nf_nat_edemux.sh \ ipip-conntrack-mtu.sh conntrack_tcp_unreplied.sh \ - conntrack_vrf.sh + conntrack_vrf.sh nft_synproxy.sh +CFLAGS += $(shell pkg-config --cflags libmnl 2>/dev/null || echo "-I/usr/include/libmnl") LDLIBS = -lmnl -TEST_GEN_FILES = nf-queue +TEST_GEN_FILES = nf-queue connect_close include ../lib.mk diff --git a/tools/testing/selftests/netfilter/connect_close.c b/tools/testing/selftests/netfilter/connect_close.c new file mode 100644 index 000000000000..1c3b0add54c4 --- /dev/null +++ b/tools/testing/selftests/netfilter/connect_close.c @@ -0,0 +1,136 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <stdio.h> +#include <stdlib.h> +#include <fcntl.h> +#include <string.h> +#include <unistd.h> +#include <signal.h> + +#include <arpa/inet.h> +#include <sys/socket.h> + +#define PORT 12345 +#define RUNTIME 10 + +static struct { + unsigned int timeout; + unsigned int port; +} opts = { + .timeout = RUNTIME, + .port = PORT, +}; + +static void handler(int sig) +{ + _exit(sig == SIGALRM ? 0 : 1); +} + +static void set_timeout(void) +{ + struct sigaction action = { + .sa_handler = handler, + }; + + sigaction(SIGALRM, &action, NULL); + + alarm(opts.timeout); +} + +static void do_connect(const struct sockaddr_in *dst) +{ + int s = socket(AF_INET, SOCK_STREAM, IPPROTO_TCP); + + if (s >= 0) + fcntl(s, F_SETFL, O_NONBLOCK); + + connect(s, (struct sockaddr *)dst, sizeof(*dst)); + close(s); +} + +static void do_accept(const struct sockaddr_in *src) +{ + int c, one = 1, s = socket(AF_INET, SOCK_STREAM, IPPROTO_TCP); + + if (s < 0) + return; + + setsockopt(s, SOL_SOCKET, SO_REUSEADDR, &one, sizeof(one)); + setsockopt(s, SOL_SOCKET, SO_REUSEPORT, &one, sizeof(one)); + + bind(s, (struct sockaddr *)src, sizeof(*src)); + + listen(s, 16); + + c = accept(s, NULL, NULL); + if (c >= 0) + close(c); + + close(s); +} + +static int accept_loop(void) +{ + struct sockaddr_in src = { + .sin_family = AF_INET, + .sin_port = htons(opts.port), + }; + + inet_pton(AF_INET, "127.0.0.1", &src.sin_addr); + + set_timeout(); + + for (;;) + do_accept(&src); + + return 1; +} + +static int connect_loop(void) +{ + struct sockaddr_in dst = { + .sin_family = AF_INET, + .sin_port = htons(opts.port), + }; + + inet_pton(AF_INET, "127.0.0.1", &dst.sin_addr); + + set_timeout(); + + for (;;) + do_connect(&dst); + + return 1; +} + +static void parse_opts(int argc, char **argv) +{ + int c; + + while ((c = getopt(argc, argv, "t:p:")) != -1) { + switch (c) { + case 't': + opts.timeout = atoi(optarg); + break; + case 'p': + opts.port = atoi(optarg); + break; + } + } +} + +int main(int argc, char *argv[]) +{ + pid_t p; + + parse_opts(argc, argv); + + p = fork(); + if (p < 0) + return 111; + + if (p > 0) + return accept_loop(); + + return connect_loop(); +} diff --git a/tools/testing/selftests/netfilter/nft_concat_range.sh b/tools/testing/selftests/netfilter/nft_concat_range.sh index ed61f6cab60f..b35010cc7f6a 100755 --- a/tools/testing/selftests/netfilter/nft_concat_range.sh +++ b/tools/testing/selftests/netfilter/nft_concat_range.sh @@ -27,7 +27,7 @@ TYPES="net_port port_net net6_port port_proto net6_port_mac net6_port_mac_proto net6_port_net6_port net_port_mac_proto_net" # Reported bugs, also described by TYPE_ variables below -BUGS="flush_remove_add" +BUGS="flush_remove_add reload" # List of possible paths to pktgen script from kernel tree for performance tests PKTGEN_SCRIPT_PATHS=" @@ -354,6 +354,23 @@ TYPE_flush_remove_add=" display Add two elements, flush, re-add " +TYPE_reload=" +display net,mac with reload +type_spec ipv4_addr . ether_addr +chain_spec ip daddr . ether saddr +dst addr4 +src mac +start 1 +count 1 +src_delta 2000 +tools sendip nc bash +proto udp + +race_repeat 0 + +perf_duration 0 +" + # Set template for all tests, types and rules are filled in depending on test set_template=' flush ruleset @@ -1473,6 +1490,59 @@ test_bug_flush_remove_add() { nft flush ruleset } +# - add ranged element, check that packets match it +# - reload the set, check packets still match +test_bug_reload() { + setup veth send_"${proto}" set || return ${KSELFTEST_SKIP} + rstart=${start} + + range_size=1 + for i in $(seq "${start}" $((start + count))); do + end=$((start + range_size)) + + # Avoid negative or zero-sized port ranges + if [ $((end / 65534)) -gt $((start / 65534)) ]; then + start=${end} + end=$((end + 1)) + fi + srcstart=$((start + src_delta)) + srcend=$((end + src_delta)) + + add "$(format)" || return 1 + range_size=$((range_size + 1)) + start=$((end + range_size)) + done + + # check kernel does allocate pcpu sctrach map + # for reload with no elemet add/delete + ( echo flush set inet filter test ; + nft list set inet filter test ) | nft -f - + + start=${rstart} + range_size=1 + + for i in $(seq "${start}" $((start + count))); do + end=$((start + range_size)) + + # Avoid negative or zero-sized port ranges + if [ $((end / 65534)) -gt $((start / 65534)) ]; then + start=${end} + end=$((end + 1)) + fi + srcstart=$((start + src_delta)) + srcend=$((end + src_delta)) + + for j in $(seq ${start} $((range_size / 2 + 1)) ${end}); do + send_match "${j}" $((j + src_delta)) || return 1 + done + + range_size=$((range_size + 1)) + start=$((end + range_size)) + done + + nft flush ruleset +} + test_reported_issues() { eval test_bug_"${subtest}" } @@ -1531,4 +1601,4 @@ for name in ${TESTS}; do done done -[ ${passed} -eq 0 ] && exit ${KSELFTEST_SKIP} +[ ${passed} -eq 0 ] && exit ${KSELFTEST_SKIP} || exit 0 diff --git a/tools/testing/selftests/netfilter/nft_fib.sh b/tools/testing/selftests/netfilter/nft_fib.sh index 6caf6ac8c285..695a1958723f 100755 --- a/tools/testing/selftests/netfilter/nft_fib.sh +++ b/tools/testing/selftests/netfilter/nft_fib.sh @@ -174,6 +174,7 @@ test_ping() { ip netns exec ${nsrouter} sysctl net.ipv6.conf.all.forwarding=1 > /dev/null ip netns exec ${nsrouter} sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null ip netns exec ${nsrouter} sysctl net.ipv4.conf.veth1.forwarding=1 > /dev/null +ip netns exec ${nsrouter} sysctl net.ipv4.conf.veth0.rp_filter=0 > /dev/null sleep 3 diff --git a/tools/testing/selftests/netfilter/nft_nat.sh b/tools/testing/selftests/netfilter/nft_nat.sh index 349a319a9e51..eb8543b9a5c4 100755 --- a/tools/testing/selftests/netfilter/nft_nat.sh +++ b/tools/testing/selftests/netfilter/nft_nat.sh @@ -880,9 +880,8 @@ EOF return $ksft_skip fi - # test default behaviour. Packet from ns1 to ns0 is not redirected - # due to automatic port translation. - test_port_shadow "default" "ROUTER" + # test default behaviour. Packet from ns1 to ns0 is redirected to ns2. + test_port_shadow "default" "CLIENT" # test packet filter based mitigation: prevent forwarding of # packets claiming to come from the service port. @@ -899,6 +898,144 @@ EOF ip netns exec "$ns0" nft delete table $family nat } +test_stateless_nat_ip() +{ + local lret=0 + + ip netns exec "$ns0" sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null + ip netns exec "$ns0" sysctl net.ipv4.conf.veth1.forwarding=1 > /dev/null + + ip netns exec "$ns2" ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1 + if [ $? -ne 0 ] ; then + echo "ERROR: cannot ping $ns1 from $ns2 before loading stateless rules" + return 1 + fi + +ip netns exec "$ns0" nft -f /dev/stdin <<EOF +table ip stateless { + map xlate_in { + typeof meta iifname . ip saddr . ip daddr : ip daddr + elements = { + "veth1" . 10.0.2.99 . 10.0.1.99 : 10.0.2.2, + } + } + map xlate_out { + typeof meta iifname . ip saddr . ip daddr : ip daddr + elements = { + "veth0" . 10.0.1.99 . 10.0.2.2 : 10.0.2.99 + } + } + + chain prerouting { + type filter hook prerouting priority -400; policy accept; + ip saddr set meta iifname . ip saddr . ip daddr map @xlate_in + ip daddr set meta iifname . ip saddr . ip daddr map @xlate_out + } +} +EOF + if [ $? -ne 0 ]; then + echo "SKIP: Could not add ip statless rules" + return $ksft_skip + fi + + reset_counters + + ip netns exec "$ns2" ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1 + if [ $? -ne 0 ] ; then + echo "ERROR: cannot ping $ns1 from $ns2 with stateless rules" + lret=1 + fi + + # ns1 should have seen packets from .2.2, due to stateless rewrite. + expect="packets 1 bytes 84" + cnt=$(ip netns exec "$ns1" nft list counter inet filter ns0insl | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter "$ns1" ns0insl "$expect" "test_stateless 1" + lret=1 + fi + + for dir in "in" "out" ; do + cnt=$(ip netns exec "$ns2" nft list counter inet filter ns1${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter "$ns2" ns1$dir "$expect" "test_stateless 2" + lret=1 + fi + done + + # ns1 should not have seen packets from ns2, due to masquerade + expect="packets 0 bytes 0" + for dir in "in" "out" ; do + cnt=$(ip netns exec "$ns1" nft list counter inet filter ns2${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter "$ns1" ns0$dir "$expect" "test_stateless 3" + lret=1 + fi + + cnt=$(ip netns exec "$ns0" nft list counter inet filter ns1${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter "$ns0" ns1$dir "$expect" "test_stateless 4" + lret=1 + fi + done + + reset_counters + + socat -h > /dev/null 2>&1 + if [ $? -ne 0 ];then + echo "SKIP: Could not run stateless nat frag test without socat tool" + if [ $lret -eq 0 ]; then + return $ksft_skip + fi + + ip netns exec "$ns0" nft delete table ip stateless + return $lret + fi + + local tmpfile=$(mktemp) + dd if=/dev/urandom of=$tmpfile bs=4096 count=1 2>/dev/null + + local outfile=$(mktemp) + ip netns exec "$ns1" timeout 3 socat -u UDP4-RECV:4233 OPEN:$outfile < /dev/null & + sc_r=$! + + sleep 1 + # re-do with large ping -> ip fragmentation + ip netns exec "$ns2" timeout 3 socat - UDP4-SENDTO:"10.0.1.99:4233" < "$tmpfile" > /dev/null + if [ $? -ne 0 ] ; then + echo "ERROR: failed to test udp $ns1 to $ns2 with stateless ip nat" 1>&2 + lret=1 + fi + + wait + + cmp "$tmpfile" "$outfile" + if [ $? -ne 0 ]; then + ls -l "$tmpfile" "$outfile" + echo "ERROR: in and output file mismatch when checking udp with stateless nat" 1>&2 + lret=1 + fi + + rm -f "$tmpfile" "$outfile" + + # ns1 should have seen packets from 2.2, due to stateless rewrite. + expect="packets 3 bytes 4164" + cnt=$(ip netns exec "$ns1" nft list counter inet filter ns0insl | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter "$ns1" ns0insl "$expect" "test_stateless 5" + lret=1 + fi + + ip netns exec "$ns0" nft delete table ip stateless + if [ $? -ne 0 ]; then + echo "ERROR: Could not delete table ip stateless" 1>&2 + lret=1 + fi + + test $lret -eq 0 && echo "PASS: IP statless for $ns2" + + return $lret +} + # ip netns exec "$ns0" ping -c 1 -q 10.0.$i.99 for i in 0 1 2; do ip netns exec ns$i-$sfx nft -f /dev/stdin <<EOF @@ -965,6 +1102,19 @@ table inet filter { EOF done +# special case for stateless nat check, counter needs to +# be done before (input) ip defragmentation +ip netns exec ns1-$sfx nft -f /dev/stdin <<EOF +table inet filter { + counter ns0insl {} + + chain pre { + type filter hook prerouting priority -400; policy accept; + ip saddr 10.0.2.2 counter name "ns0insl" + } +} +EOF + sleep 3 # test basic connectivity for i in 1 2; do @@ -1019,6 +1169,7 @@ $test_inet_nat && test_redirect inet $test_inet_nat && test_redirect6 inet test_port_shadowing +test_stateless_nat_ip if [ $ret -ne 0 ];then echo -n "FAIL: " diff --git a/tools/testing/selftests/netfilter/nft_queue.sh b/tools/testing/selftests/netfilter/nft_queue.sh index 7d27f1f3bc01..e12729753351 100755 --- a/tools/testing/selftests/netfilter/nft_queue.sh +++ b/tools/testing/selftests/netfilter/nft_queue.sh @@ -113,6 +113,7 @@ table inet $name { chain output { type filter hook output priority $prio; policy accept; tcp dport 12345 queue num 3 + tcp sport 23456 queue num 3 jump nfq } chain post { @@ -296,6 +297,23 @@ test_tcp_localhost() wait 2>/dev/null } +test_tcp_localhost_connectclose() +{ + tmpfile=$(mktemp) || exit 1 + + ip netns exec ${nsrouter} ./connect_close -p 23456 -t $timeout & + + ip netns exec ${nsrouter} ./nf-queue -q 3 -t $timeout & + local nfqpid=$! + + sleep 1 + rm -f "$tmpfile" + + wait $rpid + [ $? -eq 0 ] && echo "PASS: tcp via loopback with connect/close" + wait 2>/dev/null +} + test_tcp_localhost_requeue() { ip netns exec ${nsrouter} nft -f /dev/stdin <<EOF @@ -424,6 +442,7 @@ test_queue 20 test_tcp_forward test_tcp_localhost +test_tcp_localhost_connectclose test_tcp_localhost_requeue test_icmp_vrf diff --git a/tools/testing/selftests/netfilter/nft_synproxy.sh b/tools/testing/selftests/netfilter/nft_synproxy.sh new file mode 100755 index 000000000000..b62933b680d6 --- /dev/null +++ b/tools/testing/selftests/netfilter/nft_synproxy.sh @@ -0,0 +1,117 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# + +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 +ret=0 + +rnd=$(mktemp -u XXXXXXXX) +nsr="nsr-$rnd" # synproxy machine +ns1="ns1-$rnd" # iperf client +ns2="ns2-$rnd" # iperf server + +checktool (){ + if ! $1 > /dev/null 2>&1; then + echo "SKIP: Could not $2" + exit $ksft_skip + fi +} + +checktool "nft --version" "run test without nft tool" +checktool "ip -Version" "run test without ip tool" +checktool "iperf3 --version" "run test without iperf3" +checktool "ip netns add $nsr" "create net namespace" + +modprobe -q nf_conntrack + +ip netns add $ns1 +ip netns add $ns2 + +cleanup() { + ip netns pids $ns1 | xargs kill 2>/dev/null + ip netns pids $ns2 | xargs kill 2>/dev/null + ip netns del $ns1 + ip netns del $ns2 + + ip netns del $nsr +} + +trap cleanup EXIT + +ip link add veth0 netns $nsr type veth peer name eth0 netns $ns1 +ip link add veth1 netns $nsr type veth peer name eth0 netns $ns2 + +for dev in lo veth0 veth1; do +ip -net $nsr link set $dev up +done + +ip -net $nsr addr add 10.0.1.1/24 dev veth0 +ip -net $nsr addr add 10.0.2.1/24 dev veth1 + +ip netns exec $nsr sysctl -q net.ipv4.conf.veth0.forwarding=1 +ip netns exec $nsr sysctl -q net.ipv4.conf.veth1.forwarding=1 +ip netns exec $nsr sysctl -q net.netfilter.nf_conntrack_tcp_loose=0 + +for n in $ns1 $ns2; do + ip -net $n link set lo up + ip -net $n link set eth0 up +done +ip -net $ns1 addr add 10.0.1.99/24 dev eth0 +ip -net $ns2 addr add 10.0.2.99/24 dev eth0 +ip -net $ns1 route add default via 10.0.1.1 +ip -net $ns2 route add default via 10.0.2.1 + +# test basic connectivity +if ! ip netns exec $ns1 ping -c 1 -q 10.0.2.99 > /dev/null; then + echo "ERROR: $ns1 cannot reach $ns2" 1>&2 + exit 1 +fi + +if ! ip netns exec $ns2 ping -c 1 -q 10.0.1.99 > /dev/null; then + echo "ERROR: $ns2 cannot reach $ns1" 1>&2 + exit 1 +fi + +ip netns exec $ns2 iperf3 -s > /dev/null 2>&1 & +# ip netns exec $nsr tcpdump -vvv -n -i veth1 tcp | head -n 10 & + +sleep 1 + +ip netns exec $nsr nft -f - <<EOF +table inet filter { + chain prerouting { + type filter hook prerouting priority -300; policy accept; + meta iif veth0 tcp flags syn counter notrack + } + + chain forward { + type filter hook forward priority 0; policy accept; + + ct state new,established counter accept + + meta iif veth0 meta l4proto tcp ct state untracked,invalid synproxy mss 1460 sack-perm timestamp + + ct state invalid counter drop + + # make ns2 unreachable w.o. tcp synproxy + tcp flags syn counter drop + } +} +EOF +if [ $? -ne 0 ]; then + echo "SKIP: Cannot add nft synproxy" + exit $ksft_skip +fi + +ip netns exec $ns1 timeout 5 iperf3 -c 10.0.2.99 -n $((1 * 1024 * 1024)) > /dev/null + +if [ $? -ne 0 ]; then + echo "FAIL: iperf3 returned an error" 1>&2 + ret=$? + ip netns exec $nsr nft list ruleset +else + echo "PASS: synproxy connection successful" +fi + +exit $ret diff --git a/tools/testing/selftests/netfilter/nft_zones_many.sh b/tools/testing/selftests/netfilter/nft_zones_many.sh index 04633119b29a..5a8db0b48928 100755 --- a/tools/testing/selftests/netfilter/nft_zones_many.sh +++ b/tools/testing/selftests/netfilter/nft_zones_many.sh @@ -9,7 +9,7 @@ ns="ns-$sfx" # Kselftest framework requirement - SKIP code is 4. ksft_skip=4 -zones=20000 +zones=2000 have_ct_tool=0 ret=0 @@ -75,10 +75,10 @@ EOF while [ $i -lt $max_zones ]; do local start=$(date +%s%3N) - i=$((i + 10000)) + i=$((i + 1000)) j=$((j + 1)) # nft rule in output places each packet in a different zone. - dd if=/dev/zero of=/dev/stdout bs=8k count=10000 2>/dev/null | ip netns exec "$ns" socat STDIN UDP:127.0.0.1:12345,sourceport=12345 + dd if=/dev/zero of=/dev/stdout bs=8k count=1000 2>/dev/null | ip netns exec "$ns" socat STDIN UDP:127.0.0.1:12345,sourceport=12345 if [ $? -ne 0 ] ;then ret=1 break @@ -86,7 +86,7 @@ EOF stop=$(date +%s%3N) local duration=$((stop-start)) - echo "PASS: added 10000 entries in $duration ms (now $i total, loop $j)" + echo "PASS: added 1000 entries in $duration ms (now $i total, loop $j)" done if [ $have_ct_tool -eq 1 ]; then @@ -128,11 +128,11 @@ test_conntrack_tool() { break fi - if [ $((i%10000)) -eq 0 ];then + if [ $((i%1000)) -eq 0 ];then stop=$(date +%s%3N) local duration=$((stop-start)) - echo "PASS: added 10000 entries in $duration ms (now $i total)" + echo "PASS: added 1000 entries in $duration ms (now $i total)" start=$stop fi done diff --git a/tools/testing/selftests/openat2/Makefile b/tools/testing/selftests/openat2/Makefile index 4b93b1417b86..843ba56d8e49 100644 --- a/tools/testing/selftests/openat2/Makefile +++ b/tools/testing/selftests/openat2/Makefile @@ -5,4 +5,4 @@ TEST_GEN_PROGS := openat2_test resolve_test rename_attack_test include ../lib.mk -$(TEST_GEN_PROGS): helpers.c +$(TEST_GEN_PROGS): helpers.c helpers.h diff --git a/tools/testing/selftests/openat2/helpers.h b/tools/testing/selftests/openat2/helpers.h index a6ea27344db2..7056340b9339 100644 --- a/tools/testing/selftests/openat2/helpers.h +++ b/tools/testing/selftests/openat2/helpers.h @@ -9,6 +9,7 @@ #define _GNU_SOURCE #include <stdint.h> +#include <stdbool.h> #include <errno.h> #include <linux/types.h> #include "../kselftest.h" @@ -62,11 +63,12 @@ bool needs_openat2(const struct open_how *how); (similar to chroot(2)). */ #endif /* RESOLVE_IN_ROOT */ -#define E_func(func, ...) \ - do { \ - if (func(__VA_ARGS__) < 0) \ - ksft_exit_fail_msg("%s:%d %s failed\n", \ - __FILE__, __LINE__, #func);\ +#define E_func(func, ...) \ + do { \ + errno = 0; \ + if (func(__VA_ARGS__) < 0) \ + ksft_exit_fail_msg("%s:%d %s failed - errno:%d\n", \ + __FILE__, __LINE__, #func, errno); \ } while (0) #define E_asprintf(...) E_func(asprintf, __VA_ARGS__) diff --git a/tools/testing/selftests/openat2/openat2_test.c b/tools/testing/selftests/openat2/openat2_test.c index 1bddbe934204..7fb902099de4 100644 --- a/tools/testing/selftests/openat2/openat2_test.c +++ b/tools/testing/selftests/openat2/openat2_test.c @@ -259,6 +259,16 @@ void test_openat2_flags(void) unlink(path); fd = sys_openat2(AT_FDCWD, path, &test->how); + if (fd < 0 && fd == -EOPNOTSUPP) { + /* + * Skip the testcase if it failed because not supported + * by FS. (e.g. a valid O_TMPFILE combination on NFS) + */ + ksft_test_result_skip("openat2 with %s fails with %d (%s)\n", + test->name, fd, strerror(-fd)); + goto next; + } + if (test->err >= 0) failed = (fd < 0); else @@ -303,7 +313,7 @@ skip: else resultfn("openat2 with %s fails with %d (%s)\n", test->name, test->err, strerror(-test->err)); - +next: free(fdpath); fflush(stdout); } diff --git a/tools/testing/selftests/perf_events/sigtrap_threads.c b/tools/testing/selftests/perf_events/sigtrap_threads.c index 8e83cf91513a..6d849dc2bee0 100644 --- a/tools/testing/selftests/perf_events/sigtrap_threads.c +++ b/tools/testing/selftests/perf_events/sigtrap_threads.c @@ -44,9 +44,10 @@ static struct { } ctx; /* Unique value to check si_perf_data is correctly set from perf_event_attr::sig_data. */ -#define TEST_SIG_DATA(addr) (~(unsigned long)(addr)) +#define TEST_SIG_DATA(addr, id) (~(unsigned long)(addr) + id) -static struct perf_event_attr make_event_attr(bool enabled, volatile void *addr) +static struct perf_event_attr make_event_attr(bool enabled, volatile void *addr, + unsigned long id) { struct perf_event_attr attr = { .type = PERF_TYPE_BREAKPOINT, @@ -60,7 +61,7 @@ static struct perf_event_attr make_event_attr(bool enabled, volatile void *addr) .inherit_thread = 1, /* ... but only cloned with CLONE_THREAD. */ .remove_on_exec = 1, /* Required by sigtrap. */ .sigtrap = 1, /* Request synchronous SIGTRAP on event. */ - .sig_data = TEST_SIG_DATA(addr), + .sig_data = TEST_SIG_DATA(addr, id), }; return attr; } @@ -110,7 +111,7 @@ FIXTURE(sigtrap_threads) FIXTURE_SETUP(sigtrap_threads) { - struct perf_event_attr attr = make_event_attr(false, &ctx.iterate_on); + struct perf_event_attr attr = make_event_attr(false, &ctx.iterate_on, 0); struct sigaction action = {}; int i; @@ -165,7 +166,7 @@ TEST_F(sigtrap_threads, enable_event) EXPECT_EQ(ctx.tids_want_signal, 0); EXPECT_EQ(ctx.first_siginfo.si_addr, &ctx.iterate_on); EXPECT_EQ(ctx.first_siginfo.si_perf_type, PERF_TYPE_BREAKPOINT); - EXPECT_EQ(ctx.first_siginfo.si_perf_data, TEST_SIG_DATA(&ctx.iterate_on)); + EXPECT_EQ(ctx.first_siginfo.si_perf_data, TEST_SIG_DATA(&ctx.iterate_on, 0)); /* Check enabled for parent. */ ctx.iterate_on = 0; @@ -175,7 +176,7 @@ TEST_F(sigtrap_threads, enable_event) /* Test that modification propagates to all inherited events. */ TEST_F(sigtrap_threads, modify_and_enable_event) { - struct perf_event_attr new_attr = make_event_attr(true, &ctx.iterate_on); + struct perf_event_attr new_attr = make_event_attr(true, &ctx.iterate_on, 42); EXPECT_EQ(ioctl(self->fd, PERF_EVENT_IOC_MODIFY_ATTRIBUTES, &new_attr), 0); run_test_threads(_metadata, self); @@ -184,7 +185,7 @@ TEST_F(sigtrap_threads, modify_and_enable_event) EXPECT_EQ(ctx.tids_want_signal, 0); EXPECT_EQ(ctx.first_siginfo.si_addr, &ctx.iterate_on); EXPECT_EQ(ctx.first_siginfo.si_perf_type, PERF_TYPE_BREAKPOINT); - EXPECT_EQ(ctx.first_siginfo.si_perf_data, TEST_SIG_DATA(&ctx.iterate_on)); + EXPECT_EQ(ctx.first_siginfo.si_perf_data, TEST_SIG_DATA(&ctx.iterate_on, 42)); /* Check enabled for parent. */ ctx.iterate_on = 0; @@ -204,7 +205,7 @@ TEST_F(sigtrap_threads, signal_stress) EXPECT_EQ(ctx.tids_want_signal, 0); EXPECT_EQ(ctx.first_siginfo.si_addr, &ctx.iterate_on); EXPECT_EQ(ctx.first_siginfo.si_perf_type, PERF_TYPE_BREAKPOINT); - EXPECT_EQ(ctx.first_siginfo.si_perf_data, TEST_SIG_DATA(&ctx.iterate_on)); + EXPECT_EQ(ctx.first_siginfo.si_perf_data, TEST_SIG_DATA(&ctx.iterate_on, 0)); } TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/pidfd/pidfd.h b/tools/testing/selftests/pidfd/pidfd.h index 01f8d3c0cf2c..6922d6417e1c 100644 --- a/tools/testing/selftests/pidfd/pidfd.h +++ b/tools/testing/selftests/pidfd/pidfd.h @@ -68,7 +68,7 @@ #define PIDFD_SKIP 3 #define PIDFD_XFAIL 4 -int wait_for_pid(pid_t pid) +static inline int wait_for_pid(pid_t pid) { int status, ret; @@ -78,13 +78,20 @@ again: if (errno == EINTR) goto again; + ksft_print_msg("waitpid returned -1, errno=%d\n", errno); return -1; } - if (!WIFEXITED(status)) + if (!WIFEXITED(status)) { + ksft_print_msg( + "waitpid !WIFEXITED, WIFSIGNALED=%d, WTERMSIG=%d\n", + WIFSIGNALED(status), WTERMSIG(status)); return -1; + } - return WEXITSTATUS(status); + ret = WEXITSTATUS(status); + ksft_print_msg("waitpid WEXITSTATUS=%d\n", ret); + return ret; } static inline int sys_pidfd_open(pid_t pid, unsigned int flags) diff --git a/tools/testing/selftests/pidfd/pidfd_fdinfo_test.c b/tools/testing/selftests/pidfd/pidfd_fdinfo_test.c index 22558524f71c..3fd8e903118f 100644 --- a/tools/testing/selftests/pidfd/pidfd_fdinfo_test.c +++ b/tools/testing/selftests/pidfd/pidfd_fdinfo_test.c @@ -12,6 +12,7 @@ #include <string.h> #include <syscall.h> #include <sys/wait.h> +#include <sys/mman.h> #include "pidfd.h" #include "../kselftest.h" @@ -80,7 +81,10 @@ static inline int error_check(struct error *err, const char *test_name) return err->code; } +#define CHILD_STACK_SIZE 8192 + struct child { + char *stack; pid_t pid; int fd; }; @@ -89,17 +93,22 @@ static struct child clone_newns(int (*fn)(void *), void *args, struct error *err) { static int flags = CLONE_PIDFD | CLONE_NEWPID | CLONE_NEWNS | SIGCHLD; - size_t stack_size = 1024; - char *stack[1024] = { 0 }; struct child ret; if (!(flags & CLONE_NEWUSER) && geteuid() != 0) flags |= CLONE_NEWUSER; + ret.stack = mmap(NULL, CHILD_STACK_SIZE, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS | MAP_STACK, -1, 0); + if (ret.stack == MAP_FAILED) { + error_set(err, -1, "mmap of stack failed (errno %d)", errno); + return ret; + } + #ifdef __ia64__ - ret.pid = __clone2(fn, stack, stack_size, flags, args, &ret.fd); + ret.pid = __clone2(fn, ret.stack, CHILD_STACK_SIZE, flags, args, &ret.fd); #else - ret.pid = clone(fn, stack + stack_size, flags, args, &ret.fd); + ret.pid = clone(fn, ret.stack + CHILD_STACK_SIZE, flags, args, &ret.fd); #endif if (ret.pid < 0) { @@ -129,6 +138,11 @@ static inline int child_join(struct child *child, struct error *err) else if (r > 0) error_set(err, r, "child %d reported: %d", child->pid, r); + if (munmap(child->stack, CHILD_STACK_SIZE)) { + error_set(err, -1, "munmap of child stack failed (errno %d)", errno); + r = -1; + } + return r; } diff --git a/tools/testing/selftests/pidfd/pidfd_test.c b/tools/testing/selftests/pidfd/pidfd_test.c index 529eb700ac26..9a2d64901d59 100644 --- a/tools/testing/selftests/pidfd/pidfd_test.c +++ b/tools/testing/selftests/pidfd/pidfd_test.c @@ -441,7 +441,6 @@ static void test_pidfd_poll_exec(int use_waitpid) { int pid, pidfd = 0; int status, ret; - pthread_t t1; time_t prog_start = time(NULL); const char *test_name = "pidfd_poll check for premature notification on child thread exec"; @@ -500,13 +499,14 @@ static int child_poll_leader_exit_test(void *args) */ *child_exit_secs = time(NULL); syscall(SYS_exit, 0); + /* Never reached, but appeases compiler thinking we should return. */ + exit(0); } static void test_pidfd_poll_leader_exit(int use_waitpid) { int pid, pidfd = 0; - int status, ret; - time_t prog_start = time(NULL); + int status, ret = 0; const char *test_name = "pidfd_poll check for premature notification on non-empty" "group leader exit"; diff --git a/tools/testing/selftests/pidfd/pidfd_wait.c b/tools/testing/selftests/pidfd/pidfd_wait.c index be2943f072f6..17999e082aa7 100644 --- a/tools/testing/selftests/pidfd/pidfd_wait.c +++ b/tools/testing/selftests/pidfd/pidfd_wait.c @@ -39,7 +39,7 @@ static int sys_waitid(int which, pid_t pid, siginfo_t *info, int options, TEST(wait_simple) { - int pidfd = -1, status = 0; + int pidfd = -1; pid_t parent_tid = -1; struct clone_args args = { .parent_tid = ptr_to_u64(&parent_tid), @@ -47,7 +47,6 @@ TEST(wait_simple) .flags = CLONE_PIDFD | CLONE_PARENT_SETTID, .exit_signal = SIGCHLD, }; - int ret; pid_t pid; siginfo_t info = { .si_signo = 0, @@ -88,7 +87,7 @@ TEST(wait_simple) TEST(wait_states) { - int pidfd = -1, status = 0; + int pidfd = -1; pid_t parent_tid = -1; struct clone_args args = { .parent_tid = ptr_to_u64(&parent_tid), diff --git a/tools/testing/selftests/powerpc/Makefile b/tools/testing/selftests/powerpc/Makefile index 0830e63818c1..6ba95cd19e42 100644 --- a/tools/testing/selftests/powerpc/Makefile +++ b/tools/testing/selftests/powerpc/Makefile @@ -30,8 +30,10 @@ SUB_DIRS = alignment \ eeh \ vphn \ math \ + papr_attributes \ ptrace \ - security + security \ + mce endif diff --git a/tools/testing/selftests/powerpc/copyloops/.gitignore b/tools/testing/selftests/powerpc/copyloops/.gitignore index 994b11af765c..7283e8b07b75 100644 --- a/tools/testing/selftests/powerpc/copyloops/.gitignore +++ b/tools/testing/selftests/powerpc/copyloops/.gitignore @@ -13,3 +13,4 @@ copyuser_64_exc_t0 copyuser_64_exc_t1 copyuser_64_exc_t2 copy_mc_64 +memmove_64 diff --git a/tools/testing/selftests/powerpc/copyloops/Makefile b/tools/testing/selftests/powerpc/copyloops/Makefile index 3095b1f1c02b..77594e697f2f 100644 --- a/tools/testing/selftests/powerpc/copyloops/Makefile +++ b/tools/testing/selftests/powerpc/copyloops/Makefile @@ -13,7 +13,8 @@ TEST_GEN_PROGS := copyuser_64_t0 copyuser_64_t1 copyuser_64_t2 \ copyuser_p7_t0 copyuser_p7_t1 \ memcpy_64_t0 memcpy_64_t1 memcpy_64_t2 \ memcpy_p7_t0 memcpy_p7_t1 copy_mc_64 \ - copyuser_64_exc_t0 copyuser_64_exc_t1 copyuser_64_exc_t2 + copyuser_64_exc_t0 copyuser_64_exc_t1 copyuser_64_exc_t2 \ + memmove_64 EXTRA_SOURCES := validate.c ../harness.c stubs.S @@ -56,3 +57,9 @@ $(OUTPUT)/copyuser_64_exc_t%: copyuser_64.S exc_validate.c ../harness.c \ -D COPY_LOOP=test___copy_tofrom_user_base \ -D SELFTEST_CASE=$(subst copyuser_64_exc_t,,$(notdir $@)) \ -o $@ $^ + +$(OUTPUT)/memmove_64: mem_64.S memcpy_64.S memmove_validate.c ../harness.c \ + memcpy_stubs.S + $(CC) $(CPPFLAGS) $(CFLAGS) \ + -D TEST_MEMMOVE=test_memmove \ + -o $@ $^ diff --git a/tools/testing/selftests/powerpc/copyloops/asm/ppc_asm.h b/tools/testing/selftests/powerpc/copyloops/asm/ppc_asm.h index 58c1cef3e399..003e1b3d9300 100644 --- a/tools/testing/selftests/powerpc/copyloops/asm/ppc_asm.h +++ b/tools/testing/selftests/powerpc/copyloops/asm/ppc_asm.h @@ -26,6 +26,7 @@ #define _GLOBAL(A) FUNC_START(test_ ## A) #define _GLOBAL_TOC(A) _GLOBAL(A) #define _GLOBAL_TOC_KASAN(A) _GLOBAL(A) +#define _GLOBAL_KASAN(A) _GLOBAL(A) #define PPC_MTOCRF(A, B) mtocrf A, B diff --git a/tools/testing/selftests/powerpc/copyloops/mem_64.S b/tools/testing/selftests/powerpc/copyloops/mem_64.S new file mode 120000 index 000000000000..db254c9a5f5c --- /dev/null +++ b/tools/testing/selftests/powerpc/copyloops/mem_64.S @@ -0,0 +1 @@ +../../../../../arch/powerpc/lib/mem_64.S
\ No newline at end of file diff --git a/tools/testing/selftests/powerpc/copyloops/memcpy_stubs.S b/tools/testing/selftests/powerpc/copyloops/memcpy_stubs.S new file mode 100644 index 000000000000..d9baa832fa49 --- /dev/null +++ b/tools/testing/selftests/powerpc/copyloops/memcpy_stubs.S @@ -0,0 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include <asm/ppc_asm.h> + +FUNC_START(memcpy) + b test_memcpy + +FUNC_START(backwards_memcpy) + b test_backwards_memcpy diff --git a/tools/testing/selftests/powerpc/copyloops/memmove_validate.c b/tools/testing/selftests/powerpc/copyloops/memmove_validate.c new file mode 100644 index 000000000000..1a23218b5757 --- /dev/null +++ b/tools/testing/selftests/powerpc/copyloops/memmove_validate.c @@ -0,0 +1,58 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <malloc.h> +#include <stdlib.h> +#include <string.h> +#include <assert.h> +#include "utils.h" + +void *TEST_MEMMOVE(const void *s1, const void *s2, size_t n); + +#define BUF_LEN 65536 +#define MAX_OFFSET 512 + +size_t max(size_t a, size_t b) +{ + if (a >= b) + return a; + return b; +} + +static int testcase_run(void) +{ + size_t i, src_off, dst_off, len; + + char *usermap = memalign(BUF_LEN, BUF_LEN); + char *kernelmap = memalign(BUF_LEN, BUF_LEN); + + assert(usermap != NULL); + assert(kernelmap != NULL); + + memset(usermap, 0, BUF_LEN); + memset(kernelmap, 0, BUF_LEN); + + for (i = 0; i < BUF_LEN; i++) { + usermap[i] = i & 0xff; + kernelmap[i] = i & 0xff; + } + + for (src_off = 0; src_off < MAX_OFFSET; src_off++) { + for (dst_off = 0; dst_off < MAX_OFFSET; dst_off++) { + for (len = 1; len < MAX_OFFSET - max(src_off, dst_off); len++) { + + memmove(usermap + dst_off, usermap + src_off, len); + TEST_MEMMOVE(kernelmap + dst_off, kernelmap + src_off, len); + if (memcmp(usermap, kernelmap, MAX_OFFSET) != 0) { + printf("memmove failed at %ld %ld %ld\n", + src_off, dst_off, len); + abort(); + } + } + } + } + return 0; +} + +int main(void) +{ + return test_harness(testcase_run, "memmove"); +} diff --git a/tools/testing/selftests/powerpc/include/reg.h b/tools/testing/selftests/powerpc/include/reg.h index c0f2742a3a59..c422be8a42b2 100644 --- a/tools/testing/selftests/powerpc/include/reg.h +++ b/tools/testing/selftests/powerpc/include/reg.h @@ -52,6 +52,9 @@ #define SPRN_TFHAR 0x80 /* Transaction Failure Handler Addr */ #define SPRN_TAR 0x32f /* Target Address Register */ +#define PVR_VER(pvr) (((pvr) >> 16) & 0xFFFF) +#define SPRN_PVR 0x11F + #define SPRN_DSCR_PRIV 0x11 /* Privilege State DSCR */ #define SPRN_DSCR 0x03 /* Data Stream Control Register */ #define SPRN_PPR 896 /* Program Priority Register */ @@ -84,6 +87,7 @@ #define TEXASR_ROT 0x0000000002000000 /* MSR register bits */ +#define MSR_HV (1ul << 60) /* Hypervisor state */ #define MSR_TS_S_LG 33 /* Trans Mem state: Suspended */ #define MSR_TS_T_LG 34 /* Trans Mem state: Active */ diff --git a/tools/testing/selftests/powerpc/mce/Makefile b/tools/testing/selftests/powerpc/mce/Makefile new file mode 100644 index 000000000000..2424513982d9 --- /dev/null +++ b/tools/testing/selftests/powerpc/mce/Makefile @@ -0,0 +1,7 @@ +#SPDX-License-Identifier: GPL-2.0-or-later + +TEST_GEN_PROGS := inject-ra-err + +include ../../lib.mk + +$(TEST_GEN_PROGS): ../harness.c diff --git a/tools/testing/selftests/powerpc/mce/inject-ra-err.c b/tools/testing/selftests/powerpc/mce/inject-ra-err.c new file mode 100644 index 000000000000..94323c34d9a6 --- /dev/null +++ b/tools/testing/selftests/powerpc/mce/inject-ra-err.c @@ -0,0 +1,65 @@ +// SPDX-License-Identifier: GPL-2.0-or-later + +#include <errno.h> +#include <fcntl.h> +#include <signal.h> +#include <stdio.h> +#include <string.h> +#include <sys/ioctl.h> +#include <sys/mman.h> +#include <sys/stat.h> +#include <sys/types.h> +#include <unistd.h> + +#include "vas-api.h" +#include "utils.h" + +static bool faulted; + +static void sigbus_handler(int n, siginfo_t *info, void *ctxt_v) +{ + ucontext_t *ctxt = (ucontext_t *)ctxt_v; + struct pt_regs *regs = ctxt->uc_mcontext.regs; + + faulted = true; + regs->nip += 4; +} + +static int test_ra_error(void) +{ + struct vas_tx_win_open_attr attr; + int fd, *paste_addr; + char *devname = "/dev/crypto/nx-gzip"; + struct sigaction act = { + .sa_sigaction = sigbus_handler, + .sa_flags = SA_SIGINFO, + }; + + memset(&attr, 0, sizeof(attr)); + attr.version = 1; + attr.vas_id = 0; + + SKIP_IF(access(devname, F_OK)); + + fd = open(devname, O_RDWR); + FAIL_IF(fd < 0); + FAIL_IF(ioctl(fd, VAS_TX_WIN_OPEN, &attr) < 0); + FAIL_IF(sigaction(SIGBUS, &act, NULL) != 0); + + paste_addr = mmap(NULL, 4096, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0ULL); + + /* The following assignment triggers exception */ + mb(); + *paste_addr = 1; + mb(); + + FAIL_IF(!faulted); + + return 0; +} + +int main(void) +{ + return test_harness(test_ra_error, "inject-ra-err"); +} + diff --git a/tools/testing/selftests/powerpc/mce/vas-api.h b/tools/testing/selftests/powerpc/mce/vas-api.h new file mode 120000 index 000000000000..1455c1bcd351 --- /dev/null +++ b/tools/testing/selftests/powerpc/mce/vas-api.h @@ -0,0 +1 @@ +../../../../../arch/powerpc/include/uapi/asm/vas-api.h
\ No newline at end of file diff --git a/tools/testing/selftests/powerpc/papr_attributes/.gitignore b/tools/testing/selftests/powerpc/papr_attributes/.gitignore new file mode 100644 index 000000000000..d5f42b6d9e99 --- /dev/null +++ b/tools/testing/selftests/powerpc/papr_attributes/.gitignore @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only +attr_test diff --git a/tools/testing/selftests/powerpc/papr_attributes/Makefile b/tools/testing/selftests/powerpc/papr_attributes/Makefile new file mode 100644 index 000000000000..e899712d49db --- /dev/null +++ b/tools/testing/selftests/powerpc/papr_attributes/Makefile @@ -0,0 +1,7 @@ +# SPDX-License-Identifier: GPL-2.0 +TEST_GEN_PROGS := attr_test + +top_srcdir = ../../../../.. +include ../../lib.mk + +$(TEST_GEN_PROGS): ../harness.c ../utils.c
\ No newline at end of file diff --git a/tools/testing/selftests/powerpc/papr_attributes/attr_test.c b/tools/testing/selftests/powerpc/papr_attributes/attr_test.c new file mode 100644 index 000000000000..bab0dc06e90b --- /dev/null +++ b/tools/testing/selftests/powerpc/papr_attributes/attr_test.c @@ -0,0 +1,107 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * PAPR Energy attributes sniff test + * This checks if the papr folders and contents are populated relating to + * the energy and frequency attributes + * + * Copyright 2022, Pratik Rajesh Sampat, IBM Corp. + */ + +#include <stdio.h> +#include <string.h> +#include <dirent.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <unistd.h> +#include <stdlib.h> + +#include "utils.h" + +enum energy_freq_attrs { + POWER_PERFORMANCE_MODE = 1, + IDLE_POWER_SAVER_STATUS = 2, + MIN_FREQ = 3, + STAT_FREQ = 4, + MAX_FREQ = 6, + PROC_FOLDING_STATUS = 8 +}; + +enum type { + INVALID, + STR_VAL, + NUM_VAL +}; + +int value_type(int id) +{ + int val_type; + + switch (id) { + case POWER_PERFORMANCE_MODE: + case IDLE_POWER_SAVER_STATUS: + val_type = STR_VAL; + break; + case MIN_FREQ: + case STAT_FREQ: + case MAX_FREQ: + case PROC_FOLDING_STATUS: + val_type = NUM_VAL; + break; + default: + val_type = INVALID; + } + + return val_type; +} + +int verify_energy_info(void) +{ + const char *path = "/sys/firmware/papr/energy_scale_info"; + struct dirent *entry; + struct stat s; + DIR *dirp; + + if (stat(path, &s) || !S_ISDIR(s.st_mode)) + return -1; + dirp = opendir(path); + + while ((entry = readdir(dirp)) != NULL) { + char file_name[64]; + int id, attr_type; + FILE *f; + + if (strcmp(entry->d_name, ".") == 0 || + strcmp(entry->d_name, "..") == 0) + continue; + + id = atoi(entry->d_name); + attr_type = value_type(id); + if (attr_type == INVALID) + return -1; + + /* Check if the files exist and have data in them */ + sprintf(file_name, "%s/%d/desc", path, id); + f = fopen(file_name, "r"); + if (!f || fgetc(f) == EOF) + return -1; + + sprintf(file_name, "%s/%d/value", path, id); + f = fopen(file_name, "r"); + if (!f || fgetc(f) == EOF) + return -1; + + if (attr_type == STR_VAL) { + sprintf(file_name, "%s/%d/value_desc", path, id); + f = fopen(file_name, "r"); + if (!f || fgetc(f) == EOF) + return -1; + } + } + + return 0; +} + +int main(void) +{ + return test_harness(verify_energy_info, "papr_attributes"); +} diff --git a/tools/testing/selftests/powerpc/pmu/Makefile b/tools/testing/selftests/powerpc/pmu/Makefile index 904672fb78dd..edbd96d3b2ab 100644 --- a/tools/testing/selftests/powerpc/pmu/Makefile +++ b/tools/testing/selftests/powerpc/pmu/Makefile @@ -8,7 +8,7 @@ EXTRA_SOURCES := ../harness.c event.c lib.c ../utils.c top_srcdir = ../../../../.. include ../../lib.mk -all: $(TEST_GEN_PROGS) ebb +all: $(TEST_GEN_PROGS) ebb sampling_tests $(TEST_GEN_PROGS): $(EXTRA_SOURCES) @@ -26,25 +26,32 @@ DEFAULT_RUN_TESTS := $(RUN_TESTS) override define RUN_TESTS $(DEFAULT_RUN_TESTS) TARGET=ebb; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET run_tests + TARGET=sampling_tests; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET run_tests endef DEFAULT_EMIT_TESTS := $(EMIT_TESTS) override define EMIT_TESTS $(DEFAULT_EMIT_TESTS) TARGET=ebb; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -s -C $$TARGET emit_tests + TARGET=sampling_tests; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -s -C $$TARGET emit_tests endef DEFAULT_INSTALL_RULE := $(INSTALL_RULE) override define INSTALL_RULE $(DEFAULT_INSTALL_RULE) TARGET=ebb; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET install + TARGET=sampling_tests; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET install endef clean: $(RM) $(TEST_GEN_PROGS) $(OUTPUT)/loop.o TARGET=ebb; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET clean + TARGET=sampling_tests; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET clean ebb: TARGET=$@; BUILD_TARGET=$$OUTPUT/$$TARGET; mkdir -p $$BUILD_TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -k -C $$TARGET all -.PHONY: all run_tests clean ebb +sampling_tests: + TARGET=$@; BUILD_TARGET=$$OUTPUT/$$TARGET; mkdir -p $$BUILD_TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -k -C $$TARGET all + +.PHONY: all run_tests clean ebb sampling_tests diff --git a/tools/testing/selftests/powerpc/pmu/event.c b/tools/testing/selftests/powerpc/pmu/event.c index 48e3a413b15d..0c1c1bdba081 100644 --- a/tools/testing/selftests/powerpc/pmu/event.c +++ b/tools/testing/selftests/powerpc/pmu/event.c @@ -8,6 +8,7 @@ #include <sys/syscall.h> #include <string.h> #include <stdio.h> +#include <stdbool.h> #include <sys/ioctl.h> #include "event.h" @@ -20,7 +21,8 @@ int perf_event_open(struct perf_event_attr *attr, pid_t pid, int cpu, group_fd, flags); } -void event_init_opts(struct event *e, u64 config, int type, char *name) +static void __event_init_opts(struct event *e, u64 config, + int type, char *name, bool sampling) { memset(e, 0, sizeof(*e)); @@ -32,6 +34,16 @@ void event_init_opts(struct event *e, u64 config, int type, char *name) /* This has to match the structure layout in the header */ e->attr.read_format = PERF_FORMAT_TOTAL_TIME_ENABLED | \ PERF_FORMAT_TOTAL_TIME_RUNNING; + if (sampling) { + e->attr.sample_period = 1000; + e->attr.sample_type = PERF_SAMPLE_REGS_INTR; + e->attr.disabled = 1; + } +} + +void event_init_opts(struct event *e, u64 config, int type, char *name) +{ + __event_init_opts(e, config, type, name, false); } void event_init_named(struct event *e, u64 config, char *name) @@ -44,6 +56,11 @@ void event_init(struct event *e, u64 config) event_init_opts(e, config, PERF_TYPE_RAW, "event"); } +void event_init_sampling(struct event *e, u64 config) +{ + __event_init_opts(e, config, PERF_TYPE_RAW, "event", true); +} + #define PERF_CURRENT_PID 0 #define PERF_NO_PID -1 #define PERF_NO_CPU -1 diff --git a/tools/testing/selftests/powerpc/pmu/event.h b/tools/testing/selftests/powerpc/pmu/event.h index 302eaab51706..51aad0b6d9ad 100644 --- a/tools/testing/selftests/powerpc/pmu/event.h +++ b/tools/testing/selftests/powerpc/pmu/event.h @@ -22,11 +22,17 @@ struct event { u64 running; u64 enabled; } result; + /* + * mmap buffer used while recording sample. + * Accessed as "struct perf_event_mmap_page" + */ + void *mmap_buffer; }; void event_init(struct event *e, u64 config); void event_init_named(struct event *e, u64 config, char *name); void event_init_opts(struct event *e, u64 config, int type, char *name); +void event_init_sampling(struct event *e, u64 config); int event_open_with_options(struct event *e, pid_t pid, int cpu, int group_fd); int event_open_with_group(struct event *e, int group_fd); int event_open_with_pid(struct event *e, pid_t pid); diff --git a/tools/testing/selftests/powerpc/pmu/sampling_tests/.gitignore b/tools/testing/selftests/powerpc/pmu/sampling_tests/.gitignore new file mode 100644 index 000000000000..0fce5a694684 --- /dev/null +++ b/tools/testing/selftests/powerpc/pmu/sampling_tests/.gitignore @@ -0,0 +1,11 @@ +mmcr0_exceptionbits_test +mmcr0_cc56run_test +mmcr0_pmccext_test +mmcr0_pmcjce_test +mmcr0_fc56_pmc1ce_test +mmcr0_fc56_pmc56_test +mmcr1_comb_test +mmcr2_l2l3_test +mmcr2_fcs_fch_test +mmcr3_src_test +mmcra_thresh_marked_sample_test diff --git a/tools/testing/selftests/powerpc/pmu/sampling_tests/Makefile b/tools/testing/selftests/powerpc/pmu/sampling_tests/Makefile new file mode 100644 index 000000000000..a785c6a173b9 --- /dev/null +++ b/tools/testing/selftests/powerpc/pmu/sampling_tests/Makefile @@ -0,0 +1,12 @@ +# SPDX-License-Identifier: GPL-2.0 +CFLAGS += -m64 + +TEST_GEN_PROGS := mmcr0_exceptionbits_test mmcr0_cc56run_test mmcr0_pmccext_test \ + mmcr0_pmcjce_test mmcr0_fc56_pmc1ce_test mmcr0_fc56_pmc56_test \ + mmcr1_comb_test mmcr2_l2l3_test mmcr2_fcs_fch_test \ + mmcr3_src_test mmcra_thresh_marked_sample_test + +top_srcdir = ../../../../../.. +include ../../../lib.mk + +$(TEST_GEN_PROGS): ../../harness.c ../../utils.c ../event.c ../lib.c misc.c misc.h ../loop.S diff --git a/tools/testing/selftests/powerpc/pmu/sampling_tests/misc.c b/tools/testing/selftests/powerpc/pmu/sampling_tests/misc.c new file mode 100644 index 000000000000..fca054bbc094 --- /dev/null +++ b/tools/testing/selftests/powerpc/pmu/sampling_tests/misc.c @@ -0,0 +1,412 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright 2022, Athira Rajeev, IBM Corp. + * Copyright 2022, Madhavan Srinivasan, IBM Corp. + * Copyright 2022, Kajol Jain, IBM Corp. + */ + +#include <unistd.h> +#include <sys/syscall.h> +#include <string.h> +#include <stdio.h> +#include <sys/ioctl.h> +#include <sys/mman.h> +#include <stdlib.h> +#include <ctype.h> + +#include "misc.h" + +#define PAGE_SIZE sysconf(_SC_PAGESIZE) + +/* Storage for platform version */ +int pvr; +u64 platform_extended_mask; + +/* Mask and Shift for Event code fields */ +int ev_mask_pmcxsel, ev_shift_pmcxsel; //pmcxsel field +int ev_mask_marked, ev_shift_marked; //marked filed +int ev_mask_comb, ev_shift_comb; //combine field +int ev_mask_unit, ev_shift_unit; //unit field +int ev_mask_pmc, ev_shift_pmc; //pmc field +int ev_mask_cache, ev_shift_cache; //Cache sel field +int ev_mask_sample, ev_shift_sample; //Random sampling field +int ev_mask_thd_sel, ev_shift_thd_sel; //thresh_sel field +int ev_mask_thd_start, ev_shift_thd_start; //thresh_start field +int ev_mask_thd_stop, ev_shift_thd_stop; //thresh_stop field +int ev_mask_thd_cmp, ev_shift_thd_cmp; //thresh cmp field +int ev_mask_sm, ev_shift_sm; //SDAR mode field +int ev_mask_rsq, ev_shift_rsq; //radix scope qual field +int ev_mask_l2l3, ev_shift_l2l3; //l2l3 sel field +int ev_mask_mmcr3_src, ev_shift_mmcr3_src; //mmcr3 field + +static void init_ev_encodes(void) +{ + ev_mask_pmcxsel = 0xff; + ev_shift_pmcxsel = 0; + ev_mask_marked = 1; + ev_shift_marked = 8; + ev_mask_unit = 0xf; + ev_shift_unit = 12; + ev_mask_pmc = 0xf; + ev_shift_pmc = 16; + ev_mask_sample = 0x1f; + ev_shift_sample = 24; + ev_mask_thd_sel = 0x7; + ev_shift_thd_sel = 29; + ev_mask_thd_start = 0xf; + ev_shift_thd_start = 36; + ev_mask_thd_stop = 0xf; + ev_shift_thd_stop = 32; + + switch (pvr) { + case POWER10: + ev_mask_rsq = 1; + ev_shift_rsq = 9; + ev_mask_comb = 3; + ev_shift_comb = 10; + ev_mask_cache = 3; + ev_shift_cache = 20; + ev_mask_sm = 0x3; + ev_shift_sm = 22; + ev_mask_l2l3 = 0x1f; + ev_shift_l2l3 = 40; + ev_mask_mmcr3_src = 0x7fff; + ev_shift_mmcr3_src = 45; + break; + case POWER9: + ev_mask_comb = 3; + ev_shift_comb = 10; + ev_mask_cache = 0xf; + ev_shift_cache = 20; + ev_mask_thd_cmp = 0x3ff; + ev_shift_thd_cmp = 40; + ev_mask_sm = 0x3; + ev_shift_sm = 50; + break; + default: + FAIL_IF_EXIT(1); + } +} + +/* Return the extended regs mask value */ +static u64 perf_get_platform_reg_mask(void) +{ + if (have_hwcap2(PPC_FEATURE2_ARCH_3_1)) + return PERF_POWER10_MASK; + if (have_hwcap2(PPC_FEATURE2_ARCH_3_00)) + return PERF_POWER9_MASK; + + return -1; +} + +int check_extended_regs_support(void) +{ + int fd; + struct event event; + + event_init(&event, 0x1001e); + + event.attr.type = 4; + event.attr.sample_period = 1; + event.attr.disabled = 1; + event.attr.sample_type = PERF_SAMPLE_REGS_INTR; + event.attr.sample_regs_intr = platform_extended_mask; + + fd = event_open(&event); + if (fd != -1) + return 0; + + return -1; +} + +int check_pvr_for_sampling_tests(void) +{ + pvr = PVR_VER(mfspr(SPRN_PVR)); + + platform_extended_mask = perf_get_platform_reg_mask(); + + /* + * Check for supported platforms + * for sampling test + */ + if ((pvr != POWER10) && (pvr != POWER9)) + goto out; + + /* + * Check PMU driver registered by looking for + * PPC_FEATURE2_EBB bit in AT_HWCAP2 + */ + if (!have_hwcap2(PPC_FEATURE2_EBB)) + goto out; + + /* check if platform supports extended regs */ + if (check_extended_regs_support()) + goto out; + + init_ev_encodes(); + return 0; +out: + printf("%s: Sampling tests un-supported\n", __func__); + return -1; +} +/* + * Allocate mmap buffer of "mmap_pages" number of + * pages. + */ +void *event_sample_buf_mmap(int fd, int mmap_pages) +{ + size_t page_size = sysconf(_SC_PAGESIZE); + size_t mmap_size; + void *buff; + + if (mmap_pages <= 0) + return NULL; + + if (fd <= 0) + return NULL; + + mmap_size = page_size * (1 + mmap_pages); + buff = mmap(NULL, mmap_size, + PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0); + + if (buff == MAP_FAILED) { + perror("mmap() failed."); + return NULL; + } + return buff; +} + +/* + * Post process the mmap buffer. + * - If sample_count != NULL then return count of total + * number of samples present in the mmap buffer. + * - If sample_count == NULL then return the address + * of first sample from the mmap buffer + */ +void *__event_read_samples(void *sample_buff, size_t *size, u64 *sample_count) +{ + size_t page_size = sysconf(_SC_PAGESIZE); + struct perf_event_header *header = sample_buff + page_size; + struct perf_event_mmap_page *metadata_page = sample_buff; + unsigned long data_head, data_tail; + + /* + * PERF_RECORD_SAMPLE: + * struct { + * struct perf_event_header hdr; + * u64 data[]; + * }; + */ + + data_head = metadata_page->data_head; + /* sync memory before reading sample */ + mb(); + data_tail = metadata_page->data_tail; + + /* Check for sample_count */ + if (sample_count) + *sample_count = 0; + + while (1) { + /* + * Reads the mmap data buffer by moving + * the data_tail to know the last read data. + * data_head points to head in data buffer. + * refer "struct perf_event_mmap_page" in + * "include/uapi/linux/perf_event.h". + */ + if (data_head - data_tail < sizeof(header)) + return NULL; + + data_tail += sizeof(header); + if (header->type == PERF_RECORD_SAMPLE) { + *size = (header->size - sizeof(header)); + if (!sample_count) + return sample_buff + page_size + data_tail; + data_tail += *size; + *sample_count += 1; + } else { + *size = (header->size - sizeof(header)); + if ((metadata_page->data_tail + *size) > metadata_page->data_head) + data_tail = metadata_page->data_head; + else + data_tail += *size; + } + header = (struct perf_event_header *)((void *)header + header->size); + } + return NULL; +} + +int collect_samples(void *sample_buff) +{ + u64 sample_count; + size_t size = 0; + + __event_read_samples(sample_buff, &size, &sample_count); + return sample_count; +} + +static void *perf_read_first_sample(void *sample_buff, size_t *size) +{ + return __event_read_samples(sample_buff, size, NULL); +} + +u64 *get_intr_regs(struct event *event, void *sample_buff) +{ + u64 type = event->attr.sample_type; + u64 *intr_regs; + size_t size = 0; + + if ((type ^ PERF_SAMPLE_REGS_INTR)) + return NULL; + + intr_regs = (u64 *)perf_read_first_sample(sample_buff, &size); + if (!intr_regs) + return NULL; + + /* + * First entry in the sample buffer used to specify + * PERF_SAMPLE_REGS_ABI_64, skip perf regs abi to access + * interrupt registers. + */ + ++intr_regs; + + return intr_regs; +} + +static const unsigned int __perf_reg_mask(const char *register_name) +{ + if (!strcmp(register_name, "R0")) + return 0; + else if (!strcmp(register_name, "R1")) + return 1; + else if (!strcmp(register_name, "R2")) + return 2; + else if (!strcmp(register_name, "R3")) + return 3; + else if (!strcmp(register_name, "R4")) + return 4; + else if (!strcmp(register_name, "R5")) + return 5; + else if (!strcmp(register_name, "R6")) + return 6; + else if (!strcmp(register_name, "R7")) + return 7; + else if (!strcmp(register_name, "R8")) + return 8; + else if (!strcmp(register_name, "R9")) + return 9; + else if (!strcmp(register_name, "R10")) + return 10; + else if (!strcmp(register_name, "R11")) + return 11; + else if (!strcmp(register_name, "R12")) + return 12; + else if (!strcmp(register_name, "R13")) + return 13; + else if (!strcmp(register_name, "R14")) + return 14; + else if (!strcmp(register_name, "R15")) + return 15; + else if (!strcmp(register_name, "R16")) + return 16; + else if (!strcmp(register_name, "R17")) + return 17; + else if (!strcmp(register_name, "R18")) + return 18; + else if (!strcmp(register_name, "R19")) + return 19; + else if (!strcmp(register_name, "R20")) + return 20; + else if (!strcmp(register_name, "R21")) + return 21; + else if (!strcmp(register_name, "R22")) + return 22; + else if (!strcmp(register_name, "R23")) + return 23; + else if (!strcmp(register_name, "R24")) + return 24; + else if (!strcmp(register_name, "R25")) + return 25; + else if (!strcmp(register_name, "R26")) + return 26; + else if (!strcmp(register_name, "R27")) + return 27; + else if (!strcmp(register_name, "R28")) + return 28; + else if (!strcmp(register_name, "R29")) + return 29; + else if (!strcmp(register_name, "R30")) + return 30; + else if (!strcmp(register_name, "R31")) + return 31; + else if (!strcmp(register_name, "NIP")) + return 32; + else if (!strcmp(register_name, "MSR")) + return 33; + else if (!strcmp(register_name, "ORIG_R3")) + return 34; + else if (!strcmp(register_name, "CTR")) + return 35; + else if (!strcmp(register_name, "LINK")) + return 36; + else if (!strcmp(register_name, "XER")) + return 37; + else if (!strcmp(register_name, "CCR")) + return 38; + else if (!strcmp(register_name, "SOFTE")) + return 39; + else if (!strcmp(register_name, "TRAP")) + return 40; + else if (!strcmp(register_name, "DAR")) + return 41; + else if (!strcmp(register_name, "DSISR")) + return 42; + else if (!strcmp(register_name, "SIER")) + return 43; + else if (!strcmp(register_name, "MMCRA")) + return 44; + else if (!strcmp(register_name, "MMCR0")) + return 45; + else if (!strcmp(register_name, "MMCR1")) + return 46; + else if (!strcmp(register_name, "MMCR2")) + return 47; + else if (!strcmp(register_name, "MMCR3")) + return 48; + else if (!strcmp(register_name, "SIER2")) + return 49; + else if (!strcmp(register_name, "SIER3")) + return 50; + else if (!strcmp(register_name, "PMC1")) + return 51; + else if (!strcmp(register_name, "PMC2")) + return 52; + else if (!strcmp(register_name, "PMC3")) + return 53; + else if (!strcmp(register_name, "PMC4")) + return 54; + else if (!strcmp(register_name, "PMC5")) + return 55; + else if (!strcmp(register_name, "PMC6")) + return 56; + else if (!strcmp(register_name, "SDAR")) + return 57; + else if (!strcmp(register_name, "SIAR")) + return 58; + else + return -1; +} + +u64 get_reg_value(u64 *intr_regs, char *register_name) +{ + int register_bit_position; + + register_bit_position = __perf_reg_mask(register_name); + + if (register_bit_position < 0 || (!((platform_extended_mask >> + (register_bit_position - 1)) & 1))) + return -1; + + return *(intr_regs + register_bit_position); +} diff --git a/tools/testing/selftests/powerpc/pmu/sampling_tests/misc.h b/tools/testing/selftests/powerpc/pmu/sampling_tests/misc.h new file mode 100644 index 000000000000..7675f3177725 --- /dev/null +++ b/tools/testing/selftests/powerpc/pmu/sampling_tests/misc.h @@ -0,0 +1,227 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright 2022, Athira Rajeev, IBM Corp. + * Copyright 2022, Madhavan Srinivasan, IBM Corp. + * Copyright 2022, Kajol Jain, IBM Corp. + */ + +#include "../event.h" + +#define POWER10 0x80 +#define POWER9 0x4e +#define PERF_POWER9_MASK 0x7f8ffffffffffff +#define PERF_POWER10_MASK 0x7ffffffffffffff + +#define MMCR0_FC56 0x00000010UL /* freeze counters 5 and 6 */ +#define MMCR0_PMCCEXT 0x00000200UL /* PMCCEXT control */ +#define MMCR1_RSQ 0x200000000000ULL /* radix scope qual field */ +#define BHRB_DISABLE 0x2000000000ULL /* MMCRA BHRB DISABLE bit */ + +extern int ev_mask_pmcxsel, ev_shift_pmcxsel; +extern int ev_mask_marked, ev_shift_marked; +extern int ev_mask_comb, ev_shift_comb; +extern int ev_mask_unit, ev_shift_unit; +extern int ev_mask_pmc, ev_shift_pmc; +extern int ev_mask_cache, ev_shift_cache; +extern int ev_mask_sample, ev_shift_sample; +extern int ev_mask_thd_sel, ev_shift_thd_sel; +extern int ev_mask_thd_start, ev_shift_thd_start; +extern int ev_mask_thd_stop, ev_shift_thd_stop; +extern int ev_mask_thd_cmp, ev_shift_thd_cmp; +extern int ev_mask_sm, ev_shift_sm; +extern int ev_mask_rsq, ev_shift_rsq; +extern int ev_mask_l2l3, ev_shift_l2l3; +extern int ev_mask_mmcr3_src, ev_shift_mmcr3_src; +extern int pvr; +extern u64 platform_extended_mask; +extern int check_pvr_for_sampling_tests(void); + +/* + * Event code field extraction macro. + * Raw event code is combination of multiple + * fields. Macro to extract individual fields + * + * x - Raw event code value + * y - Field to extract + */ +#define EV_CODE_EXTRACT(x, y) \ + ((x >> ev_shift_##y) & ev_mask_##y) + +void *event_sample_buf_mmap(int fd, int mmap_pages); +void *__event_read_samples(void *sample_buff, size_t *size, u64 *sample_count); +int collect_samples(void *sample_buff); +u64 *get_intr_regs(struct event *event, void *sample_buff); +u64 get_reg_value(u64 *intr_regs, char *register_name); + +static inline int get_mmcr0_fc56(u64 mmcr0, int pmc) +{ + return (mmcr0 & MMCR0_FC56); +} + +static inline int get_mmcr0_pmccext(u64 mmcr0, int pmc) +{ + return (mmcr0 & MMCR0_PMCCEXT); +} + +static inline int get_mmcr0_pmao(u64 mmcr0, int pmc) +{ + return ((mmcr0 >> 7) & 0x1); +} + +static inline int get_mmcr0_cc56run(u64 mmcr0, int pmc) +{ + return ((mmcr0 >> 8) & 0x1); +} + +static inline int get_mmcr0_pmcjce(u64 mmcr0, int pmc) +{ + return ((mmcr0 >> 14) & 0x1); +} + +static inline int get_mmcr0_pmc1ce(u64 mmcr0, int pmc) +{ + return ((mmcr0 >> 15) & 0x1); +} + +static inline int get_mmcr0_pmae(u64 mmcr0, int pmc) +{ + return ((mmcr0 >> 27) & 0x1); +} + +static inline int get_mmcr1_pmcxsel(u64 mmcr1, int pmc) +{ + return ((mmcr1 >> ((24 - (((pmc) - 1) * 8))) & 0xff)); +} + +static inline int get_mmcr1_unit(u64 mmcr1, int pmc) +{ + return ((mmcr1 >> ((60 - (4 * ((pmc) - 1))))) & 0xf); +} + +static inline int get_mmcr1_comb(u64 mmcr1, int pmc) +{ + return ((mmcr1 >> (38 - ((pmc - 1) * 2))) & 0x3); +} + +static inline int get_mmcr1_cache(u64 mmcr1, int pmc) +{ + return ((mmcr1 >> 46) & 0x3); +} + +static inline int get_mmcr1_rsq(u64 mmcr1, int pmc) +{ + return mmcr1 & MMCR1_RSQ; +} + +static inline int get_mmcr2_fcs(u64 mmcr2, int pmc) +{ + return ((mmcr2 & (1ull << (63 - (((pmc) - 1) * 9)))) >> (63 - (((pmc) - 1) * 9))); +} + +static inline int get_mmcr2_fcp(u64 mmcr2, int pmc) +{ + return ((mmcr2 & (1ull << (62 - (((pmc) - 1) * 9)))) >> (62 - (((pmc) - 1) * 9))); +} + +static inline int get_mmcr2_fcpc(u64 mmcr2, int pmc) +{ + return ((mmcr2 & (1ull << (61 - (((pmc) - 1) * 9)))) >> (61 - (((pmc) - 1) * 9))); +} + +static inline int get_mmcr2_fcm1(u64 mmcr2, int pmc) +{ + return ((mmcr2 & (1ull << (60 - (((pmc) - 1) * 9)))) >> (60 - (((pmc) - 1) * 9))); +} + +static inline int get_mmcr2_fcm0(u64 mmcr2, int pmc) +{ + return ((mmcr2 & (1ull << (59 - (((pmc) - 1) * 9)))) >> (59 - (((pmc) - 1) * 9))); +} + +static inline int get_mmcr2_fcwait(u64 mmcr2, int pmc) +{ + return ((mmcr2 & (1ull << (58 - (((pmc) - 1) * 9)))) >> (58 - (((pmc) - 1) * 9))); +} + +static inline int get_mmcr2_fch(u64 mmcr2, int pmc) +{ + return ((mmcr2 & (1ull << (57 - (((pmc) - 1) * 9)))) >> (57 - (((pmc) - 1) * 9))); +} + +static inline int get_mmcr2_fcti(u64 mmcr2, int pmc) +{ + return ((mmcr2 & (1ull << (56 - (((pmc) - 1) * 9)))) >> (56 - (((pmc) - 1) * 9))); +} + +static inline int get_mmcr2_fcta(u64 mmcr2, int pmc) +{ + return ((mmcr2 & (1ull << (55 - (((pmc) - 1) * 9)))) >> (55 - (((pmc) - 1) * 9))); +} + +static inline int get_mmcr2_l2l3(u64 mmcr2, int pmc) +{ + if (pvr == POWER10) + return ((mmcr2 & 0xf8) >> 3); + return 0; +} + +static inline int get_mmcr3_src(u64 mmcr3, int pmc) +{ + if (pvr != POWER10) + return 0; + return ((mmcr3 >> ((49 - (15 * ((pmc) - 1))))) & 0x7fff); +} + +static inline int get_mmcra_thd_cmp(u64 mmcra, int pmc) +{ + if (pvr == POWER10) + return ((mmcra >> 45) & 0x7ff); + return ((mmcra >> 45) & 0x3ff); +} + +static inline int get_mmcra_sm(u64 mmcra, int pmc) +{ + return ((mmcra >> 42) & 0x3); +} + +static inline int get_mmcra_bhrb_disable(u64 mmcra, int pmc) +{ + if (pvr == POWER10) + return mmcra & BHRB_DISABLE; + return 0; +} + +static inline int get_mmcra_ifm(u64 mmcra, int pmc) +{ + return ((mmcra >> 30) & 0x3); +} + +static inline int get_mmcra_thd_sel(u64 mmcra, int pmc) +{ + return ((mmcra >> 16) & 0x7); +} + +static inline int get_mmcra_thd_start(u64 mmcra, int pmc) +{ + return ((mmcra >> 12) & 0xf); +} + +static inline int get_mmcra_thd_stop(u64 mmcra, int pmc) +{ + return ((mmcra >> 8) & 0xf); +} + +static inline int get_mmcra_rand_samp_elig(u64 mmcra, int pmc) +{ + return ((mmcra >> 4) & 0x7); +} + +static inline int get_mmcra_sample_mode(u64 mmcra, int pmc) +{ + return ((mmcra >> 1) & 0x3); +} + +static inline int get_mmcra_marked(u64 mmcra, int pmc) +{ + return mmcra & 0x1; +} diff --git a/tools/testing/selftests/powerpc/pmu/sampling_tests/mmcr0_cc56run_test.c b/tools/testing/selftests/powerpc/pmu/sampling_tests/mmcr0_cc56run_test.c new file mode 100644 index 000000000000..ae4172f83817 --- /dev/null +++ b/tools/testing/selftests/powerpc/pmu/sampling_tests/mmcr0_cc56run_test.c @@ -0,0 +1,59 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright 2022, Athira Rajeev, IBM Corp. + */ + +#include <stdio.h> +#include <stdlib.h> + +#include "../event.h" +#include "misc.h" +#include "utils.h" + +extern void thirty_two_instruction_loop(int loops); + +/* + * A perf sampling test for mmcr0 + * field: cc56run. + */ +static int mmcr0_cc56run(void) +{ + struct event event; + u64 *intr_regs; + + /* Check for platform support for the test */ + SKIP_IF(check_pvr_for_sampling_tests()); + SKIP_IF(!have_hwcap2(PPC_FEATURE2_ARCH_3_1)); + + /* Init the event for the sampling test */ + event_init_sampling(&event, 0x500fa); + event.attr.sample_regs_intr = platform_extended_mask; + FAIL_IF(event_open(&event)); + event.mmap_buffer = event_sample_buf_mmap(event.fd, 1); + + FAIL_IF(event_enable(&event)); + + /* workload to make the event overflow */ + thirty_two_instruction_loop(10000); + + FAIL_IF(event_disable(&event)); + + /* Check for sample count */ + FAIL_IF(!collect_samples(event.mmap_buffer)); + + intr_regs = get_intr_regs(&event, event.mmap_buffer); + + /* Check for intr_regs */ + FAIL_IF(!intr_regs); + + /* Verify that cc56run bit is set in MMCR0 */ + FAIL_IF(!get_mmcr0_cc56run(get_reg_value(intr_regs, "MMCR0"), 5)); + + event_close(&event); + return 0; +} + +int main(void) +{ + return test_harness(mmcr0_cc56run, "mmcr0_cc56run"); +} diff --git a/tools/testing/selftests/powerpc/pmu/sampling_tests/mmcr0_exceptionbits_test.c b/tools/testing/selftests/powerpc/pmu/sampling_tests/mmcr0_exceptionbits_test.c new file mode 100644 index 000000000000..982aa56d2171 --- /dev/null +++ b/tools/testing/selftests/powerpc/pmu/sampling_tests/mmcr0_exceptionbits_test.c @@ -0,0 +1,59 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright 2022, Athira Rajeev, IBM Corp. + */ + +#include <stdio.h> +#include <stdlib.h> + +#include "../event.h" +#include "misc.h" +#include "utils.h" + +extern void thirty_two_instruction_loop(int loops); + +/* + * A perf sampling test for mmcr0 + * fields : pmae, pmao. + */ +static int mmcr0_exceptionbits(void) +{ + struct event event; + u64 *intr_regs; + + /* Check for platform support for the test */ + SKIP_IF(check_pvr_for_sampling_tests()); + + /* Init the event for the sampling test */ + event_init_sampling(&event, 0x500fa); + event.attr.sample_regs_intr = platform_extended_mask; + FAIL_IF(event_open(&event)); + event.mmap_buffer = event_sample_buf_mmap(event.fd, 1); + + FAIL_IF(event_enable(&event)); + + /* workload to make the event overflow */ + thirty_two_instruction_loop(10000); + + FAIL_IF(event_disable(&event)); + + /* Check for sample count */ + FAIL_IF(!collect_samples(event.mmap_buffer)); + + intr_regs = get_intr_regs(&event, event.mmap_buffer); + + /* Check for intr_regs */ + FAIL_IF(!intr_regs); + + /* Verify that pmae is cleared and pmao is set in MMCR0 */ + FAIL_IF(get_mmcr0_pmae(get_reg_value(intr_regs, "MMCR0"), 5)); + FAIL_IF(!get_mmcr0_pmao(get_reg_value(intr_regs, "MMCR0"), 5)); + + event_close(&event); + return 0; +} + +int main(void) +{ + return test_harness(mmcr0_exceptionbits, "mmcr0_exceptionbits"); +} diff --git a/tools/testing/selftests/powerpc/pmu/sampling_tests/mmcr0_fc56_pmc1ce_test.c b/tools/testing/selftests/powerpc/pmu/sampling_tests/mmcr0_fc56_pmc1ce_test.c new file mode 100644 index 000000000000..1c1813c182c0 --- /dev/null +++ b/tools/testing/selftests/powerpc/pmu/sampling_tests/mmcr0_fc56_pmc1ce_test.c @@ -0,0 +1,59 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright 2022, Athira Rajeev, IBM Corp. + */ + +#include <stdio.h> +#include <stdlib.h> + +#include "../event.h" +#include "misc.h" +#include "utils.h" + +extern void thirty_two_instruction_loop(int loops); + +/* + * A perf sampling test for mmcr0 + * fields: fc56, pmc1ce. + */ +static int mmcr0_fc56_pmc1ce(void) +{ + struct event event; + u64 *intr_regs; + + /* Check for platform support for the test */ + SKIP_IF(check_pvr_for_sampling_tests()); + + /* Init the event for the sampling test */ + event_init_sampling(&event, 0x1001e); + event.attr.sample_regs_intr = platform_extended_mask; + FAIL_IF(event_open(&event)); + event.mmap_buffer = event_sample_buf_mmap(event.fd, 1); + + FAIL_IF(event_enable(&event)); + + /* workload to make the event overflow */ + thirty_two_instruction_loop(10000); + + FAIL_IF(event_disable(&event)); + + /* Check for sample count */ + FAIL_IF(!collect_samples(event.mmap_buffer)); + + intr_regs = get_intr_regs(&event, event.mmap_buffer); + + /* Check for intr_regs */ + FAIL_IF(!intr_regs); + + /* Verify that fc56, pmc1ce fields are set in MMCR0 */ + FAIL_IF(!get_mmcr0_fc56(get_reg_value(intr_regs, "MMCR0"), 1)); + FAIL_IF(!get_mmcr0_pmc1ce(get_reg_value(intr_regs, "MMCR0"), 1)); + + event_close(&event); + return 0; +} + +int main(void) +{ + return test_harness(mmcr0_fc56_pmc1ce, "mmcr0_fc56_pmc1ce"); +} diff --git a/tools/testing/selftests/powerpc/pmu/sampling_tests/mmcr0_fc56_pmc56_test.c b/tools/testing/selftests/powerpc/pmu/sampling_tests/mmcr0_fc56_pmc56_test.c new file mode 100644 index 000000000000..332d24b5ab9c --- /dev/null +++ b/tools/testing/selftests/powerpc/pmu/sampling_tests/mmcr0_fc56_pmc56_test.c @@ -0,0 +1,58 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright 2022, Athira Rajeev, IBM Corp. + */ + +#include <stdio.h> +#include <stdlib.h> + +#include "../event.h" +#include "misc.h" +#include "utils.h" + +extern void thirty_two_instruction_loop(int loops); + +/* + * A perf sampling test for mmcr0 + * fields: fc56_pmc56 + */ +static int mmcr0_fc56_pmc56(void) +{ + struct event event; + u64 *intr_regs; + + /* Check for platform support for the test */ + SKIP_IF(check_pvr_for_sampling_tests()); + + /* Init the event for the sampling test */ + event_init_sampling(&event, 0x500fa); + event.attr.sample_regs_intr = platform_extended_mask; + FAIL_IF(event_open(&event)); + event.mmap_buffer = event_sample_buf_mmap(event.fd, 1); + + FAIL_IF(event_enable(&event)); + + /* workload to make the event overflow */ + thirty_two_instruction_loop(10000); + + FAIL_IF(event_disable(&event)); + + /* Check for sample count */ + FAIL_IF(!collect_samples(event.mmap_buffer)); + + intr_regs = get_intr_regs(&event, event.mmap_buffer); + + /* Check for intr_regs */ + FAIL_IF(!intr_regs); + + /* Verify that fc56 is not set in MMCR0 when using PMC5 */ + FAIL_IF(get_mmcr0_fc56(get_reg_value(intr_regs, "MMCR0"), 5)); + + event_close(&event); + return 0; +} + +int main(void) +{ + return test_harness(mmcr0_fc56_pmc56, "mmcr0_fc56_pmc56"); +} diff --git a/tools/testing/selftests/powerpc/pmu/sampling_tests/mmcr0_pmccext_test.c b/tools/testing/selftests/powerpc/pmu/sampling_tests/mmcr0_pmccext_test.c new file mode 100644 index 000000000000..dfd186cd8eec --- /dev/null +++ b/tools/testing/selftests/powerpc/pmu/sampling_tests/mmcr0_pmccext_test.c @@ -0,0 +1,59 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright 2022, Athira Rajeev, IBM Corp. + */ + +#include <stdio.h> +#include <stdlib.h> + +#include "../event.h" +#include "misc.h" +#include "utils.h" + +extern void thirty_two_instruction_loop(int loops); + +/* + * A perf sampling test for mmcr0 + * field: pmccext + */ +static int mmcr0_pmccext(void) +{ + struct event event; + u64 *intr_regs; + + /* Check for platform support for the test */ + SKIP_IF(check_pvr_for_sampling_tests()); + SKIP_IF(!have_hwcap2(PPC_FEATURE2_ARCH_3_1)); + + /* Init the event for the sampling test */ + event_init_sampling(&event, 0x4001e); + event.attr.sample_regs_intr = platform_extended_mask; + FAIL_IF(event_open(&event)); + event.mmap_buffer = event_sample_buf_mmap(event.fd, 1); + + FAIL_IF(event_enable(&event)); + + /* workload to make the event overflow */ + thirty_two_instruction_loop(10000); + + FAIL_IF(event_disable(&event)); + + /* Check for sample count */ + FAIL_IF(!collect_samples(event.mmap_buffer)); + + intr_regs = get_intr_regs(&event, event.mmap_buffer); + + /* Check for intr_regs */ + FAIL_IF(!intr_regs); + + /* Verify that pmccext field is set in MMCR0 */ + FAIL_IF(!get_mmcr0_pmccext(get_reg_value(intr_regs, "MMCR0"), 4)); + + event_close(&event); + return 0; +} + +int main(void) +{ + return test_harness(mmcr0_pmccext, "mmcr0_pmccext"); +} diff --git a/tools/testing/selftests/powerpc/pmu/sampling_tests/mmcr0_pmcjce_test.c b/tools/testing/selftests/powerpc/pmu/sampling_tests/mmcr0_pmcjce_test.c new file mode 100644 index 000000000000..fdd8ed9bf725 --- /dev/null +++ b/tools/testing/selftests/powerpc/pmu/sampling_tests/mmcr0_pmcjce_test.c @@ -0,0 +1,58 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright 2022, Athira Rajeev, IBM Corp. + */ + +#include <stdio.h> +#include <stdlib.h> + +#include "../event.h" +#include "misc.h" +#include "utils.h" + +extern void thirty_two_instruction_loop(int loops); + +/* + * A perf sampling test for mmcr0 + * field: pmcjce + */ +static int mmcr0_pmcjce(void) +{ + struct event event; + u64 *intr_regs; + + /* Check for platform support for the test */ + SKIP_IF(check_pvr_for_sampling_tests()); + + /* Init the event for the sampling test */ + event_init_sampling(&event, 0x500fa); + event.attr.sample_regs_intr = platform_extended_mask; + FAIL_IF(event_open(&event)); + event.mmap_buffer = event_sample_buf_mmap(event.fd, 1); + + FAIL_IF(event_enable(&event)); + + /* workload to make the event overflow */ + thirty_two_instruction_loop(10000); + + FAIL_IF(event_disable(&event)); + + /* Check for sample count */ + FAIL_IF(!collect_samples(event.mmap_buffer)); + + intr_regs = get_intr_regs(&event, event.mmap_buffer); + + /* Check for intr_regs */ + FAIL_IF(!intr_regs); + + /* Verify that pmcjce field is set in MMCR0 */ + FAIL_IF(!get_mmcr0_pmcjce(get_reg_value(intr_regs, "MMCR0"), 5)); + + event_close(&event); + return 0; +} + +int main(void) +{ + return test_harness(mmcr0_pmcjce, "mmcr0_pmcjce"); +} diff --git a/tools/testing/selftests/powerpc/pmu/sampling_tests/mmcr1_comb_test.c b/tools/testing/selftests/powerpc/pmu/sampling_tests/mmcr1_comb_test.c new file mode 100644 index 000000000000..5aea6499ee9a --- /dev/null +++ b/tools/testing/selftests/powerpc/pmu/sampling_tests/mmcr1_comb_test.c @@ -0,0 +1,66 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright 2022, Athira Rajeev, IBM Corp. + */ + +#include <stdio.h> +#include <stdlib.h> + +#include "../event.h" +#include "misc.h" +#include "utils.h" + +/* All successful D-side store dispatches for this thread that were L2 Miss */ +#define EventCode 0x46880 + +extern void thirty_two_instruction_loop_with_ll_sc(u64 loops, u64 *ll_sc_target); + +/* + * A perf sampling test for mmcr1 + * fields : comb. + */ +static int mmcr1_comb(void) +{ + struct event event; + u64 *intr_regs; + u64 dummy; + + /* Check for platform support for the test */ + SKIP_IF(check_pvr_for_sampling_tests()); + + /* Init the event for the sampling test */ + event_init_sampling(&event, EventCode); + event.attr.sample_regs_intr = platform_extended_mask; + FAIL_IF(event_open(&event)); + event.mmap_buffer = event_sample_buf_mmap(event.fd, 1); + + FAIL_IF(event_enable(&event)); + + /* workload to make the event overflow */ + thirty_two_instruction_loop_with_ll_sc(10000000, &dummy); + + FAIL_IF(event_disable(&event)); + + /* Check for sample count */ + FAIL_IF(!collect_samples(event.mmap_buffer)); + + intr_regs = get_intr_regs(&event, event.mmap_buffer); + + /* Check for intr_regs */ + FAIL_IF(!intr_regs); + + /* + * Verify that comb field match with + * corresponding event code fields + */ + FAIL_IF(EV_CODE_EXTRACT(event.attr.config, comb) != + get_mmcr1_comb(get_reg_value(intr_regs, "MMCR1"), 4)); + + event_close(&event); + return 0; +} + +int main(void) +{ + return test_harness(mmcr1_comb, "mmcr1_comb"); +} diff --git a/tools/testing/selftests/powerpc/pmu/sampling_tests/mmcr2_fcs_fch_test.c b/tools/testing/selftests/powerpc/pmu/sampling_tests/mmcr2_fcs_fch_test.c new file mode 100644 index 000000000000..4e242fd61b25 --- /dev/null +++ b/tools/testing/selftests/powerpc/pmu/sampling_tests/mmcr2_fcs_fch_test.c @@ -0,0 +1,85 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright 2022, Madhavan Srinivasan, IBM Corp. + */ + +#include <signal.h> +#include <stdio.h> +#include <stdlib.h> +#include <sys/types.h> + +#include "../event.h" +#include "misc.h" +#include "utils.h" + +extern void thirty_two_instruction_loop(int loops); + +static bool is_hv; + +static void sig_usr2_handler(int signum, siginfo_t *info, void *data) +{ + ucontext_t *uctx = data; + + is_hv = !!(uctx->uc_mcontext.gp_regs[PT_MSR] & MSR_HV); +} + +/* + * A perf sampling test for mmcr2 + * fields : fcs, fch. + */ +static int mmcr2_fcs_fch(void) +{ + struct sigaction sigact = { + .sa_sigaction = sig_usr2_handler, + .sa_flags = SA_SIGINFO + }; + struct event event; + u64 *intr_regs; + + FAIL_IF(sigaction(SIGUSR2, &sigact, NULL)); + FAIL_IF(kill(getpid(), SIGUSR2)); + + /* Check for platform support for the test */ + SKIP_IF(check_pvr_for_sampling_tests()); + + /* Init the event for the sampling test */ + event_init_sampling(&event, 0x1001e); + event.attr.sample_regs_intr = platform_extended_mask; + event.attr.exclude_kernel = 1; + FAIL_IF(event_open(&event)); + event.mmap_buffer = event_sample_buf_mmap(event.fd, 1); + + FAIL_IF(event_enable(&event)); + + /* workload to make the event overflow */ + thirty_two_instruction_loop(10000); + + FAIL_IF(event_disable(&event)); + + /* Check for sample count */ + FAIL_IF(!collect_samples(event.mmap_buffer)); + + intr_regs = get_intr_regs(&event, event.mmap_buffer); + + /* Check for intr_regs */ + FAIL_IF(!intr_regs); + + /* + * Verify that fcs and fch field of MMCR2 match + * with corresponding modifier fields. + */ + if (is_hv) + FAIL_IF(event.attr.exclude_kernel != + get_mmcr2_fch(get_reg_value(intr_regs, "MMCR2"), 1)); + else + FAIL_IF(event.attr.exclude_kernel != + get_mmcr2_fcs(get_reg_value(intr_regs, "MMCR2"), 1)); + + event_close(&event); + return 0; +} + +int main(void) +{ + return test_harness(mmcr2_fcs_fch, "mmcr2_fcs_fch"); +} diff --git a/tools/testing/selftests/powerpc/pmu/sampling_tests/mmcr2_l2l3_test.c b/tools/testing/selftests/powerpc/pmu/sampling_tests/mmcr2_l2l3_test.c new file mode 100644 index 000000000000..ceca597016b2 --- /dev/null +++ b/tools/testing/selftests/powerpc/pmu/sampling_tests/mmcr2_l2l3_test.c @@ -0,0 +1,74 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright 2022, Madhavan Srinivasan, IBM Corp. + */ + +#include <stdio.h> +#include <stdlib.h> + +#include "../event.h" +#include "misc.h" +#include "utils.h" + +/* All successful D-side store dispatches for this thread */ +#define EventCode 0x010000046080 + +#define MALLOC_SIZE (0x10000 * 10) /* Ought to be enough .. */ + +/* + * A perf sampling test for mmcr2 + * fields : l2l3 + */ +static int mmcr2_l2l3(void) +{ + struct event event; + u64 *intr_regs; + char *p; + int i; + + /* Check for platform support for the test */ + SKIP_IF(check_pvr_for_sampling_tests()); + SKIP_IF(!have_hwcap2(PPC_FEATURE2_ARCH_3_1)); + + /* Init the event for the sampling test */ + event_init_sampling(&event, EventCode); + event.attr.sample_regs_intr = platform_extended_mask; + FAIL_IF(event_open(&event)); + event.mmap_buffer = event_sample_buf_mmap(event.fd, 1); + + FAIL_IF(event_enable(&event)); + + /* workload to make the event overflow */ + p = malloc(MALLOC_SIZE); + FAIL_IF(!p); + + for (i = 0; i < MALLOC_SIZE; i += 0x10000) + p[i] = i; + + FAIL_IF(event_disable(&event)); + + /* Check for sample count */ + FAIL_IF(!collect_samples(event.mmap_buffer)); + + intr_regs = get_intr_regs(&event, event.mmap_buffer); + + /* Check for intr_regs */ + FAIL_IF(!intr_regs); + + /* + * Verify that l2l3 field of MMCR2 match with + * corresponding event code field + */ + FAIL_IF(EV_CODE_EXTRACT(event.attr.config, l2l3) != + get_mmcr2_l2l3(get_reg_value(intr_regs, "MMCR2"), 4)); + + event_close(&event); + free(p); + + return 0; +} + +int main(void) +{ + return test_harness(mmcr2_l2l3, "mmcr2_l2l3"); +} diff --git a/tools/testing/selftests/powerpc/pmu/sampling_tests/mmcr3_src_test.c b/tools/testing/selftests/powerpc/pmu/sampling_tests/mmcr3_src_test.c new file mode 100644 index 000000000000..e154e2a4cc3a --- /dev/null +++ b/tools/testing/selftests/powerpc/pmu/sampling_tests/mmcr3_src_test.c @@ -0,0 +1,67 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright 2022, Kajol Jain, IBM Corp. + */ + +#include <stdio.h> +#include <stdlib.h> + +#include "../event.h" +#include "misc.h" +#include "utils.h" + +extern void thirty_two_instruction_loop_with_ll_sc(u64 loops, u64 *ll_sc_target); + +/* The data cache was reloaded from local core's L3 due to a demand load */ +#define EventCode 0x1340000001c040 + +/* + * A perf sampling test for mmcr3 + * fields. + */ +static int mmcr3_src(void) +{ + struct event event; + u64 *intr_regs; + u64 dummy; + + /* Check for platform support for the test */ + SKIP_IF(check_pvr_for_sampling_tests()); + SKIP_IF(!have_hwcap2(PPC_FEATURE2_ARCH_3_1)); + + /* Init the event for the sampling test */ + event_init_sampling(&event, EventCode); + event.attr.sample_regs_intr = platform_extended_mask; + FAIL_IF(event_open(&event)); + event.mmap_buffer = event_sample_buf_mmap(event.fd, 1); + + FAIL_IF(event_enable(&event)); + + /* workload to make event overflow */ + thirty_two_instruction_loop_with_ll_sc(1000000, &dummy); + + FAIL_IF(event_disable(&event)); + + /* Check for sample count */ + FAIL_IF(!collect_samples(event.mmap_buffer)); + + intr_regs = get_intr_regs(&event, event.mmap_buffer); + + /* Check for intr_regs */ + FAIL_IF(!intr_regs); + + /* + * Verify that src field of MMCR3 match with + * corresponding event code field + */ + FAIL_IF(EV_CODE_EXTRACT(event.attr.config, mmcr3_src) != + get_mmcr3_src(get_reg_value(intr_regs, "MMCR3"), 1)); + + event_close(&event); + return 0; +} + +int main(void) +{ + return test_harness(mmcr3_src, "mmcr3_src"); +} diff --git a/tools/testing/selftests/powerpc/pmu/sampling_tests/mmcra_thresh_marked_sample_test.c b/tools/testing/selftests/powerpc/pmu/sampling_tests/mmcra_thresh_marked_sample_test.c new file mode 100644 index 000000000000..022cc1655eb5 --- /dev/null +++ b/tools/testing/selftests/powerpc/pmu/sampling_tests/mmcra_thresh_marked_sample_test.c @@ -0,0 +1,80 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright 2022, Kajol Jain, IBM Corp. + */ + +#include <stdio.h> +#include <stdlib.h> + +#include "../event.h" +#include "misc.h" +#include "utils.h" + +/* + * Primary PMU event used here is PM_MRK_INST_CMPL (0x401e0) + * Threshold event selection used is issue to complete for cycles + * Sampling criteria is Load only sampling + */ +#define EventCode 0x35340401e0 + +extern void thirty_two_instruction_loop_with_ll_sc(u64 loops, u64 *ll_sc_target); + +/* A perf sampling test to test mmcra fields */ +static int mmcra_thresh_marked_sample(void) +{ + struct event event; + u64 *intr_regs; + u64 dummy; + + /* Check for platform support for the test */ + SKIP_IF(check_pvr_for_sampling_tests()); + + /* Init the event for the sampling test */ + event_init_sampling(&event, EventCode); + event.attr.sample_regs_intr = platform_extended_mask; + FAIL_IF(event_open(&event)); + event.mmap_buffer = event_sample_buf_mmap(event.fd, 1); + + FAIL_IF(event_enable(&event)); + + /* workload to make the event overflow */ + thirty_two_instruction_loop_with_ll_sc(1000000, &dummy); + + FAIL_IF(event_disable(&event)); + + /* Check for sample count */ + FAIL_IF(!collect_samples(event.mmap_buffer)); + + intr_regs = get_intr_regs(&event, event.mmap_buffer); + + /* Check for intr_regs */ + FAIL_IF(!intr_regs); + + /* + * Verify that thresh sel/start/stop, marked, random sample + * eligibility, sdar mode and sample mode fields match with + * the corresponding event code fields + */ + FAIL_IF(EV_CODE_EXTRACT(event.attr.config, thd_sel) != + get_mmcra_thd_sel(get_reg_value(intr_regs, "MMCRA"), 4)); + FAIL_IF(EV_CODE_EXTRACT(event.attr.config, thd_start) != + get_mmcra_thd_start(get_reg_value(intr_regs, "MMCRA"), 4)); + FAIL_IF(EV_CODE_EXTRACT(event.attr.config, thd_stop) != + get_mmcra_thd_stop(get_reg_value(intr_regs, "MMCRA"), 4)); + FAIL_IF(EV_CODE_EXTRACT(event.attr.config, marked) != + get_mmcra_marked(get_reg_value(intr_regs, "MMCRA"), 4)); + FAIL_IF(EV_CODE_EXTRACT(event.attr.config, sample >> 2) != + get_mmcra_rand_samp_elig(get_reg_value(intr_regs, "MMCRA"), 4)); + FAIL_IF(EV_CODE_EXTRACT(event.attr.config, sample & 0x3) != + get_mmcra_sample_mode(get_reg_value(intr_regs, "MMCRA"), 4)); + FAIL_IF(EV_CODE_EXTRACT(event.attr.config, sm) != + get_mmcra_sm(get_reg_value(intr_regs, "MMCRA"), 4)); + + event_close(&event); + return 0; +} + +int main(void) +{ + return test_harness(mmcra_thresh_marked_sample, "mmcra_thresh_marked_sample"); +} diff --git a/tools/testing/selftests/powerpc/security/spectre_v2.c b/tools/testing/selftests/powerpc/security/spectre_v2.c index 83647b8277e7..d42ca8c676c3 100644 --- a/tools/testing/selftests/powerpc/security/spectre_v2.c +++ b/tools/testing/selftests/powerpc/security/spectre_v2.c @@ -125,8 +125,6 @@ static enum spectre_v2_state get_sysfs_state(void) #define PM_BR_PRED_PCACHE 0x048a0 // P9 only #define PM_BR_MPRED_PCACHE 0x048b0 // P9 only -#define SPRN_PVR 287 - int spectre_v2_test(void) { enum spectre_v2_state state; diff --git a/tools/testing/selftests/ptp/testptp.c b/tools/testing/selftests/ptp/testptp.c index c0f6a062364d..198ad5f32187 100644 --- a/tools/testing/selftests/ptp/testptp.c +++ b/tools/testing/selftests/ptp/testptp.c @@ -133,6 +133,7 @@ static void usage(char *progname) " 0 - none\n" " 1 - external time stamp\n" " 2 - periodic output\n" + " -n val shift the ptp clock time by 'val' nanoseconds\n" " -p val enable output with a period of 'val' nanoseconds\n" " -H val set output phase to 'val' nanoseconds (requires -p)\n" " -w val set output pulse width to 'val' nanoseconds (requires -p)\n" @@ -165,6 +166,7 @@ int main(int argc, char *argv[]) clockid_t clkid; int adjfreq = 0x7fffffff; int adjtime = 0; + int adjns = 0; int capabilities = 0; int extts = 0; int flagtest = 0; @@ -186,7 +188,7 @@ int main(int argc, char *argv[]) progname = strrchr(argv[0], '/'); progname = progname ? 1+progname : argv[0]; - while (EOF != (c = getopt(argc, argv, "cd:e:f:ghH:i:k:lL:p:P:sSt:T:w:z"))) { + while (EOF != (c = getopt(argc, argv, "cd:e:f:ghH:i:k:lL:n:p:P:sSt:T:w:z"))) { switch (c) { case 'c': capabilities = 1; @@ -223,6 +225,9 @@ int main(int argc, char *argv[]) return -1; } break; + case 'n': + adjns = atoi(optarg); + break; case 'p': perout = atoll(optarg); break; @@ -305,11 +310,16 @@ int main(int argc, char *argv[]) } } - if (adjtime) { + if (adjtime || adjns) { memset(&tx, 0, sizeof(tx)); - tx.modes = ADJ_SETOFFSET; + tx.modes = ADJ_SETOFFSET | ADJ_NANO; tx.time.tv_sec = adjtime; - tx.time.tv_usec = 0; + tx.time.tv_usec = adjns; + while (tx.time.tv_usec < 0) { + tx.time.tv_sec -= 1; + tx.time.tv_usec += 1000000000; + } + if (clock_adjtime(clkid, &tx) < 0) { perror("clock_adjtime"); } else { diff --git a/tools/testing/selftests/rcutorture/bin/console-badness.sh b/tools/testing/selftests/rcutorture/bin/console-badness.sh index e6a132df6172..69f8a5958cef 100755 --- a/tools/testing/selftests/rcutorture/bin/console-badness.sh +++ b/tools/testing/selftests/rcutorture/bin/console-badness.sh @@ -10,7 +10,7 @@ # # Authors: Paul E. McKenney <paulmck@kernel.org> -egrep 'Badness|WARNING:|Warn|BUG|===========|Call Trace:|Oops:|detected stalls on CPUs/tasks:|self-detected stall on CPU|Stall ended before state dump start|\?\?\? Writer stall state|rcu_.*kthread starved for|!!!' | +egrep 'Badness|WARNING:|Warn|BUG|===========|BUG: KCSAN:|Call Trace:|Oops:|detected stalls on CPUs/tasks:|self-detected stall on CPU|Stall ended before state dump start|\?\?\? Writer stall state|rcu_.*kthread starved for|!!!' | grep -v 'ODEBUG: ' | grep -v 'This means that this is a DEBUG kernel and it is' | grep -v 'Warning: unable to open an initial console' | diff --git a/tools/testing/selftests/rcutorture/bin/kvm-again.sh b/tools/testing/selftests/rcutorture/bin/kvm-again.sh index 5a0023d183da..0941f1ddab65 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-again.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-again.sh @@ -47,8 +47,8 @@ else exit 1 fi -KVM="`pwd`/tools/testing/selftests/rcutorture"; export KVM -PATH=${KVM}/bin:$PATH; export PATH +RCUTORTURE="`pwd`/tools/testing/selftests/rcutorture"; export RCUTORTURE +PATH=${RCUTORTURE}/bin:$PATH; export PATH . functions.sh dryrun= diff --git a/tools/testing/selftests/rcutorture/bin/kvm-check-branches.sh b/tools/testing/selftests/rcutorture/bin/kvm-check-branches.sh index 370406bbfeed..f17000a2ccf1 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-check-branches.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-check-branches.sh @@ -49,8 +49,8 @@ fi mkdir $resdir/$ds echo Results directory: $resdir/$ds -KVM="`pwd`/tools/testing/selftests/rcutorture"; export KVM -PATH=${KVM}/bin:$PATH; export PATH +RCUTORTURE="`pwd`/tools/testing/selftests/rcutorture"; export RCUTORTURE +PATH=${RCUTORTURE}/bin:$PATH; export PATH . functions.sh echo Using all `identify_qemu_vcpus` CPUs. diff --git a/tools/testing/selftests/rcutorture/bin/kvm-end-run-stats.sh b/tools/testing/selftests/rcutorture/bin/kvm-end-run-stats.sh index e4a00779b8c6..ee886b40a5d2 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-end-run-stats.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-end-run-stats.sh @@ -22,8 +22,8 @@ T=${TMPDIR-/tmp}/kvm-end-run-stats.sh.$$ trap 'rm -rf $T' 0 mkdir $T -KVM="`pwd`/tools/testing/selftests/rcutorture"; export KVM -PATH=${KVM}/bin:$PATH; export PATH +RCUTORTURE="`pwd`/tools/testing/selftests/rcutorture"; export RCUTORTURE +PATH=${RCUTORTURE}/bin:$PATH; export PATH . functions.sh default_starttime="`get_starttime`" starttime="${2-default_starttime}" diff --git a/tools/testing/selftests/rcutorture/bin/kvm-find-errors.sh b/tools/testing/selftests/rcutorture/bin/kvm-find-errors.sh index 2e9e9e2eedb6..5f682fc892dd 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-find-errors.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-find-errors.sh @@ -30,10 +30,16 @@ editor=${EDITOR-vi} files= for i in ${rundir}/*/Make.out do + scenariodir="`dirname $i`" + scenariobasedir="`echo ${scenariodir} | sed -e 's/\.[0-9]*$//'`" if egrep -q "error:|warning:|^ld: .*undefined reference to" < $i then egrep "error:|warning:|^ld: .*undefined reference to" < $i > $i.diags files="$files $i.diags $i" + elif ! test -f ${scenariobasedir}/vmlinux + then + echo No ${scenariobasedir}/vmlinux file > $i.diags + files="$files $i.diags $i" fi done if test -n "$files" diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh index 1c4c2c727dad..43e1387234d1 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh @@ -25,7 +25,7 @@ stopstate="`grep 'End-test grace-period state: g' $i/console.log 2> /dev/null | tail -1 | sed -e 's/^\[[ 0-9.]*] //' | awk '{ print \"[\" $1 \" \" $5 \" \" $6 \" \" $7 \"]\"; }' | tr -d '\012\015'`" -fwdprog="`grep 'rcu_torture_fwd_prog n_max_cbs: ' $i/console.log 2> /dev/null | sed -e 's/^\[[^]]*] //' | sort -k3nr | head -1 | awk '{ print $2 " " $3 }'`" +fwdprog="`grep 'rcu_torture_fwd_prog n_max_cbs: ' $i/console.log 2> /dev/null | sed -e 's/^\[[^]]*] //' | sort -k3nr | head -1 | awk '{ print $2 " " $3 }' | tr -d '\015'`" if test -z "$ngps" then echo "$configfile ------- " $stopstate diff --git a/tools/testing/selftests/rcutorture/bin/kvm-remote.sh b/tools/testing/selftests/rcutorture/bin/kvm-remote.sh index e09b1bc78708..8c4c1e4792d0 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-remote.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-remote.sh @@ -19,8 +19,8 @@ then exit 1 fi -KVM="`pwd`/tools/testing/selftests/rcutorture"; export KVM -PATH=${KVM}/bin:$PATH; export PATH +RCUTORTURE="`pwd`/tools/testing/selftests/rcutorture"; export RCUTORTURE +PATH=${RCUTORTURE}/bin:$PATH; export PATH . functions.sh starttime="`get_starttime`" @@ -108,8 +108,8 @@ else cat $T/kvm-again.sh.out | tee -a "$oldrun/remote-log" exit 2 fi - cp -a "$rundir" "$KVM/res/" - oldrun="$KVM/res/$ds" + cp -a "$rundir" "$RCUTORTURE/res/" + oldrun="$RCUTORTURE/res/$ds" fi echo | tee -a "$oldrun/remote-log" echo " ----" kvm-again.sh output: "(`date`)" | tee -a "$oldrun/remote-log" @@ -155,18 +155,23 @@ do echo Downloading tarball to $i `date` | tee -a "$oldrun/remote-log" cat $T/binres.tgz | ssh $i "cd /tmp; tar -xzf -" ret=$? - if test "$ret" -ne 0 - then - echo Unable to download $T/binres.tgz to system $i, waiting and then retrying. | tee -a "$oldrun/remote-log" + tries=0 + while test "$ret" -ne 0 + do + echo Unable to download $T/binres.tgz to system $i, waiting and then retrying. $tries prior retries. | tee -a "$oldrun/remote-log" sleep 60 cat $T/binres.tgz | ssh $i "cd /tmp; tar -xzf -" ret=$? if test "$ret" -ne 0 then - echo Unable to download $T/binres.tgz to system $i, giving up. | tee -a "$oldrun/remote-log" - exit 10 + if test "$tries" > 5 + then + echo Unable to download $T/binres.tgz to system $i, giving up. | tee -a "$oldrun/remote-log" + exit 10 + fi fi - fi + tries=$((tries+1)) + done done # Function to check for presence of a file on the specified system. diff --git a/tools/testing/selftests/rcutorture/bin/kvm.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh index 6de0c183db5b..55b2c1533282 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm.sh @@ -25,15 +25,15 @@ LANG=en_US.UTF-8; export LANG dur=$((30*60)) dryrun="" -KVM="`pwd`/tools/testing/selftests/rcutorture"; export KVM -PATH=${KVM}/bin:$PATH; export PATH +RCUTORTURE="`pwd`/tools/testing/selftests/rcutorture"; export RCUTORTURE +PATH=${RCUTORTURE}/bin:$PATH; export PATH . functions.sh TORTURE_ALLOTED_CPUS="`identify_qemu_vcpus`" TORTURE_DEFCONFIG=defconfig TORTURE_BOOT_IMAGE="" TORTURE_BUILDONLY= -TORTURE_INITRD="$KVM/initrd"; export TORTURE_INITRD +TORTURE_INITRD="$RCUTORTURE/initrd"; export TORTURE_INITRD TORTURE_KCONFIG_ARG="" TORTURE_KCONFIG_GDB_ARG="" TORTURE_BOOT_GDB_ARG="" @@ -262,7 +262,7 @@ else exit 1 fi -CONFIGFRAG=${KVM}/configs/${TORTURE_SUITE}; export CONFIGFRAG +CONFIGFRAG=${RCUTORTURE}/configs/${TORTURE_SUITE}; export CONFIGFRAG defaultconfigs="`tr '\012' ' ' < $CONFIGFRAG/CFLIST`" if test -z "$configs" @@ -272,7 +272,7 @@ fi if test -z "$resdir" then - resdir=$KVM/res + resdir=$RCUTORTURE/res fi # Create a file of test-name/#cpus pairs, sorted by decreasing #cpus. @@ -280,7 +280,7 @@ configs_derep= for CF in $configs do case $CF in - [0-9]\**|[0-9][0-9]\**|[0-9][0-9][0-9]\**) + [0-9]\**|[0-9][0-9]\**|[0-9][0-9][0-9]\**|[0-9][0-9][0-9][0-9]\**) config_reps=`echo $CF | sed -e 's/\*.*$//'` CF1=`echo $CF | sed -e 's/^[^*]*\*//'` ;; @@ -386,7 +386,7 @@ END { # Generate a script to execute the tests in appropriate batches. cat << ___EOF___ > $T/script CONFIGFRAG="$CONFIGFRAG"; export CONFIGFRAG -KVM="$KVM"; export KVM +RCUTORTURE="$RCUTORTURE"; export RCUTORTURE PATH="$PATH"; export PATH TORTURE_ALLOTED_CPUS="$TORTURE_ALLOTED_CPUS"; export TORTURE_ALLOTED_CPUS TORTURE_BOOT_IMAGE="$TORTURE_BOOT_IMAGE"; export TORTURE_BOOT_IMAGE @@ -569,7 +569,7 @@ ___EOF___ awk < $T/cfgcpu.pack \ -v TORTURE_BUILDONLY="$TORTURE_BUILDONLY" \ -v CONFIGDIR="$CONFIGFRAG/" \ - -v KVM="$KVM" \ + -v RCUTORTURE="$RCUTORTURE" \ -v ncpus=$cpus \ -v jitter="$jitter" \ -v rd=$resdir/$ds/ \ diff --git a/tools/testing/selftests/rcutorture/bin/parse-console.sh b/tools/testing/selftests/rcutorture/bin/parse-console.sh index 9f624bd53c27..822eb037a057 100755 --- a/tools/testing/selftests/rcutorture/bin/parse-console.sh +++ b/tools/testing/selftests/rcutorture/bin/parse-console.sh @@ -138,6 +138,16 @@ then then summary="$summary Bugs: $n_bugs" fi + n_kcsan=`egrep -c 'BUG: KCSAN: ' $file` + if test "$n_kcsan" -ne 0 + then + if test "$n_bugs" = "$n_kcsan" + then + summary="$summary (all bugs kcsan)" + else + summary="$summary KCSAN: $n_kcsan" + fi + fi n_calltrace=`grep -c 'Call Trace:' $file` if test "$n_calltrace" -ne 0 then diff --git a/tools/testing/selftests/rcutorture/bin/torture.sh b/tools/testing/selftests/rcutorture/bin/torture.sh index eae88aacca2a..bfe09e2829c8 100755 --- a/tools/testing/selftests/rcutorture/bin/torture.sh +++ b/tools/testing/selftests/rcutorture/bin/torture.sh @@ -13,8 +13,8 @@ scriptname=$0 args="$*" -KVM="`pwd`/tools/testing/selftests/rcutorture"; export KVM -PATH=${KVM}/bin:$PATH; export PATH +RCUTORTURE="`pwd`/tools/testing/selftests/rcutorture"; export RCUTORTURE +PATH=${RCUTORTURE}/bin:$PATH; export PATH . functions.sh TORTURE_ALLOTED_CPUS="`identify_qemu_vcpus`" @@ -37,7 +37,7 @@ configs_scftorture= kcsan_kmake_args= # Default compression, duration, and apportionment. -compress_kasan_vmlinux="`identify_qemu_vcpus`" +compress_concurrency="`identify_qemu_vcpus`" duration_base=10 duration_rcutorture_frac=7 duration_locktorture_frac=1 @@ -67,12 +67,12 @@ function doyesno () { usage () { echo "Usage: $scriptname optional arguments:" - echo " --compress-kasan-vmlinux concurrency" + echo " --compress-concurrency concurrency" echo " --configs-rcutorture \"config-file list w/ repeat factor (3*TINY01)\"" echo " --configs-locktorture \"config-file list w/ repeat factor (10*LOCK01)\"" echo " --configs-scftorture \"config-file list w/ repeat factor (2*CFLIST)\"" - echo " --doall" - echo " --doallmodconfig / --do-no-allmodconfig" + echo " --do-all" + echo " --do-allmodconfig / --do-no-allmodconfig" echo " --do-clocksourcewd / --do-no-clocksourcewd" echo " --do-kasan / --do-no-kasan" echo " --do-kcsan / --do-no-kcsan" @@ -91,9 +91,9 @@ usage () { while test $# -gt 0 do case "$1" in - --compress-kasan-vmlinux) - checkarg --compress-kasan-vmlinux "(concurrency level)" $# "$2" '^[0-9][0-9]*$' '^error' - compress_kasan_vmlinux=$2 + --compress-concurrency) + checkarg --compress-concurrency "(concurrency level)" $# "$2" '^[0-9][0-9]*$' '^error' + compress_concurrency=$2 shift ;; --config-rcutorture|--configs-rcutorture) @@ -414,8 +414,14 @@ nfailures=0 echo FAILURES: | tee -a $T/log if test -s "$T/failures" then - cat "$T/failures" | tee -a $T/log + awk < "$T/failures" -v sq="'" '{ print "echo " sq $0 sq; print "sed -e " sq "1,/^ --- .* Test summary:$/d" sq " " $2 "/log | grep Summary: | sed -e " sq "s/^[^S]*/ /" sq; }' | sh | tee -a $T/log | tee "$T/failuresum" nfailures="`wc -l "$T/failures" | awk '{ print $1 }'`" + grep "^ Summary: " "$T/failuresum" | + grep -v '^ Summary: Bugs: [0-9]* (all bugs kcsan)$' > "$T/nonkcsan" + if test -s "$T/nonkcsan" + then + nonkcsanbug="yes" + fi ret=2 fi if test "$do_kcsan" = "yes" @@ -424,12 +430,16 @@ then fi echo Started at $startdate, ended at `date`, duration `get_starttime_duration $starttime`. | tee -a $T/log echo Summary: Successes: $nsuccesses Failures: $nfailures. | tee -a $T/log +if test -z "$nonkcsanbug" && test -s "$T/failuresum" +then + echo " All bugs were KCSAN failures." +fi tdir="`cat $T/successes $T/failures | head -1 | awk '{ print $NF }' | sed -e 's,/[^/]\+/*$,,'`" -if test -n "$tdir" && test $compress_kasan_vmlinux -gt 0 +if test -n "$tdir" && test $compress_concurrency -gt 0 then # KASAN vmlinux files can approach 1GB in size, so compress them. - echo Looking for KASAN files to compress: `date` > "$tdir/log-xz" 2>&1 - find "$tdir" -type d -name '*-kasan' -print > $T/xz-todo + echo Looking for K[AC]SAN files to compress: `date` > "$tdir/log-xz" 2>&1 + find "$tdir" -type d -name '*-k[ac]san' -print > $T/xz-todo ncompresses=0 batchno=1 if test -s $T/xz-todo @@ -447,7 +457,7 @@ then do xz "$j" >> "$tdir/log-xz" 2>&1 & ncompresses=$((ncompresses+1)) - if test $ncompresses -ge $compress_kasan_vmlinux + if test $ncompresses -ge $compress_concurrency then echo Waiting for batch $batchno of $ncompresses compressions `date` | tee -a "$tdir/log-xz" | tee -a $T/log wait diff --git a/tools/testing/selftests/rcutorture/configs/rcu/RUDE01 b/tools/testing/selftests/rcutorture/configs/rcu/RUDE01 index 3ca112444ce7..7093422050f6 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/RUDE01 +++ b/tools/testing/selftests/rcutorture/configs/rcu/RUDE01 @@ -1,5 +1,5 @@ CONFIG_SMP=y -CONFIG_NR_CPUS=4 +CONFIG_NR_CPUS=3 CONFIG_HOTPLUG_CPU=y CONFIG_PREEMPT_NONE=n CONFIG_PREEMPT_VOLUNTARY=n diff --git a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-N.boot b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-N.boot index 238bfe3bd0cc..ce0694fd9b92 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-N.boot +++ b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-N.boot @@ -1 +1,2 @@ rcutorture.torture_type=srcu +rcutorture.fwd_progress=3 diff --git a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-P.boot b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-P.boot index ce48c7b82673..2db39f298d18 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-P.boot +++ b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-P.boot @@ -1,2 +1,4 @@ rcutorture.torture_type=srcud rcupdate.rcu_self_test=1 +rcutorture.fwd_progress=3 +srcutree.big_cpu_lim=5 diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TRACE01 b/tools/testing/selftests/rcutorture/configs/rcu/TRACE01 index 34c8ff5a12f2..e4d74e5fc1d0 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TRACE01 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TRACE01 @@ -1,5 +1,5 @@ CONFIG_SMP=y -CONFIG_NR_CPUS=4 +CONFIG_NR_CPUS=5 CONFIG_HOTPLUG_CPU=y CONFIG_PREEMPT_NONE=y CONFIG_PREEMPT_VOLUNTARY=n diff --git a/tools/testing/selftests/rseq/Makefile b/tools/testing/selftests/rseq/Makefile index 2af9d39a9716..215e1067f037 100644 --- a/tools/testing/selftests/rseq/Makefile +++ b/tools/testing/selftests/rseq/Makefile @@ -6,7 +6,7 @@ endif CFLAGS += -O2 -Wall -g -I./ -I../../../../usr/include/ -L$(OUTPUT) -Wl,-rpath=./ \ $(CLANG_FLAGS) -LDLIBS += -lpthread +LDLIBS += -lpthread -ldl # Own dependencies because we only want to build against 1st prerequisite, but # still track changes to header files and depend on shared object. diff --git a/tools/testing/selftests/rseq/basic_percpu_ops_test.c b/tools/testing/selftests/rseq/basic_percpu_ops_test.c index b953a52ff706..517756afc2a4 100644 --- a/tools/testing/selftests/rseq/basic_percpu_ops_test.c +++ b/tools/testing/selftests/rseq/basic_percpu_ops_test.c @@ -167,7 +167,7 @@ struct percpu_list_node *this_cpu_list_pop(struct percpu_list *list, for (;;) { struct percpu_list_node *head; intptr_t *targetptr, expectnot, *load; - off_t offset; + long offset; int ret, cpu; cpu = rseq_cpu_start(); diff --git a/tools/testing/selftests/rseq/compiler.h b/tools/testing/selftests/rseq/compiler.h new file mode 100644 index 000000000000..876eb6a7f75b --- /dev/null +++ b/tools/testing/selftests/rseq/compiler.h @@ -0,0 +1,30 @@ +/* SPDX-License-Identifier: LGPL-2.1-only OR MIT */ +/* + * rseq/compiler.h + * + * Work-around asm goto compiler bugs. + * + * (C) Copyright 2021 - Mathieu Desnoyers <mathieu.desnoyers@efficios.com> + */ + +#ifndef RSEQ_COMPILER_H +#define RSEQ_COMPILER_H + +/* + * gcc prior to 4.8.2 miscompiles asm goto. + * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=58670 + * + * gcc prior to 8.1.0 miscompiles asm goto at O1. + * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=103908 + * + * clang prior to version 13.0.1 miscompiles asm goto at O2. + * https://github.com/llvm/llvm-project/issues/52735 + * + * Work around these issues by adding a volatile inline asm with + * memory clobber in the fallthrough after the asm goto and at each + * label target. Emit this for all compilers in case other similar + * issues are found in the future. + */ +#define rseq_after_asm_goto() asm volatile ("" : : : "memory") + +#endif /* RSEQ_COMPILER_H_ */ diff --git a/tools/testing/selftests/rseq/param_test.c b/tools/testing/selftests/rseq/param_test.c index 699ad5f93c34..ef29bc16f358 100644 --- a/tools/testing/selftests/rseq/param_test.c +++ b/tools/testing/selftests/rseq/param_test.c @@ -161,7 +161,7 @@ unsigned int yield_mod_cnt, nr_abort; " cbnz " INJECT_ASM_REG ", 222b\n" \ "333:\n" -#elif __PPC__ +#elif defined(__PPC__) #define RSEQ_INJECT_INPUT \ , [loop_cnt_1]"m"(loop_cnt[1]) \ @@ -207,6 +207,29 @@ unsigned int yield_mod_cnt, nr_abort; "addiu " INJECT_ASM_REG ", -1\n\t" \ "bnez " INJECT_ASM_REG ", 222b\n\t" \ "333:\n\t" +#elif defined(__riscv) + +#define RSEQ_INJECT_INPUT \ + , [loop_cnt_1]"m"(loop_cnt[1]) \ + , [loop_cnt_2]"m"(loop_cnt[2]) \ + , [loop_cnt_3]"m"(loop_cnt[3]) \ + , [loop_cnt_4]"m"(loop_cnt[4]) \ + , [loop_cnt_5]"m"(loop_cnt[5]) \ + , [loop_cnt_6]"m"(loop_cnt[6]) + +#define INJECT_ASM_REG "t1" + +#define RSEQ_INJECT_CLOBBER \ + , INJECT_ASM_REG + +#define RSEQ_INJECT_ASM(n) \ + "lw " INJECT_ASM_REG ", %[loop_cnt_" #n "]\n\t" \ + "beqz " INJECT_ASM_REG ", 333f\n\t" \ + "222:\n\t" \ + "addi " INJECT_ASM_REG "," INJECT_ASM_REG ", -1\n\t" \ + "bnez " INJECT_ASM_REG ", 222b\n\t" \ + "333:\n\t" + #else #error unsupported target @@ -368,9 +391,7 @@ void *test_percpu_spinlock_thread(void *arg) abort(); reps = thread_data->reps; for (i = 0; i < reps; i++) { - int cpu = rseq_cpu_start(); - - cpu = rseq_this_cpu_lock(&data->lock); + int cpu = rseq_this_cpu_lock(&data->lock); data->c[cpu].count++; rseq_percpu_unlock(&data->lock, cpu); #ifndef BENCHMARK @@ -551,7 +572,7 @@ struct percpu_list_node *this_cpu_list_pop(struct percpu_list *list, for (;;) { struct percpu_list_node *head; intptr_t *targetptr, expectnot, *load; - off_t offset; + long offset; int ret; cpu = rseq_cpu_start(); diff --git a/tools/testing/selftests/rseq/rseq-abi.h b/tools/testing/selftests/rseq/rseq-abi.h new file mode 100644 index 000000000000..a8c44d9af71f --- /dev/null +++ b/tools/testing/selftests/rseq/rseq-abi.h @@ -0,0 +1,151 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ +#ifndef _RSEQ_ABI_H +#define _RSEQ_ABI_H + +/* + * rseq-abi.h + * + * Restartable sequences system call API + * + * Copyright (c) 2015-2022 Mathieu Desnoyers <mathieu.desnoyers@efficios.com> + */ + +#include <linux/types.h> +#include <asm/byteorder.h> + +enum rseq_abi_cpu_id_state { + RSEQ_ABI_CPU_ID_UNINITIALIZED = -1, + RSEQ_ABI_CPU_ID_REGISTRATION_FAILED = -2, +}; + +enum rseq_abi_flags { + RSEQ_ABI_FLAG_UNREGISTER = (1 << 0), +}; + +enum rseq_abi_cs_flags_bit { + RSEQ_ABI_CS_FLAG_NO_RESTART_ON_PREEMPT_BIT = 0, + RSEQ_ABI_CS_FLAG_NO_RESTART_ON_SIGNAL_BIT = 1, + RSEQ_ABI_CS_FLAG_NO_RESTART_ON_MIGRATE_BIT = 2, +}; + +enum rseq_abi_cs_flags { + RSEQ_ABI_CS_FLAG_NO_RESTART_ON_PREEMPT = + (1U << RSEQ_ABI_CS_FLAG_NO_RESTART_ON_PREEMPT_BIT), + RSEQ_ABI_CS_FLAG_NO_RESTART_ON_SIGNAL = + (1U << RSEQ_ABI_CS_FLAG_NO_RESTART_ON_SIGNAL_BIT), + RSEQ_ABI_CS_FLAG_NO_RESTART_ON_MIGRATE = + (1U << RSEQ_ABI_CS_FLAG_NO_RESTART_ON_MIGRATE_BIT), +}; + +/* + * struct rseq_abi_cs is aligned on 4 * 8 bytes to ensure it is always + * contained within a single cache-line. It is usually declared as + * link-time constant data. + */ +struct rseq_abi_cs { + /* Version of this structure. */ + __u32 version; + /* enum rseq_abi_cs_flags */ + __u32 flags; + __u64 start_ip; + /* Offset from start_ip. */ + __u64 post_commit_offset; + __u64 abort_ip; +} __attribute__((aligned(4 * sizeof(__u64)))); + +/* + * struct rseq_abi is aligned on 4 * 8 bytes to ensure it is always + * contained within a single cache-line. + * + * A single struct rseq_abi per thread is allowed. + */ +struct rseq_abi { + /* + * Restartable sequences cpu_id_start field. Updated by the + * kernel. Read by user-space with single-copy atomicity + * semantics. This field should only be read by the thread which + * registered this data structure. Aligned on 32-bit. Always + * contains a value in the range of possible CPUs, although the + * value may not be the actual current CPU (e.g. if rseq is not + * initialized). This CPU number value should always be compared + * against the value of the cpu_id field before performing a rseq + * commit or returning a value read from a data structure indexed + * using the cpu_id_start value. + */ + __u32 cpu_id_start; + /* + * Restartable sequences cpu_id field. Updated by the kernel. + * Read by user-space with single-copy atomicity semantics. This + * field should only be read by the thread which registered this + * data structure. Aligned on 32-bit. Values + * RSEQ_CPU_ID_UNINITIALIZED and RSEQ_CPU_ID_REGISTRATION_FAILED + * have a special semantic: the former means "rseq uninitialized", + * and latter means "rseq initialization failed". This value is + * meant to be read within rseq critical sections and compared + * with the cpu_id_start value previously read, before performing + * the commit instruction, or read and compared with the + * cpu_id_start value before returning a value loaded from a data + * structure indexed using the cpu_id_start value. + */ + __u32 cpu_id; + /* + * Restartable sequences rseq_cs field. + * + * Contains NULL when no critical section is active for the current + * thread, or holds a pointer to the currently active struct rseq_cs. + * + * Updated by user-space, which sets the address of the currently + * active rseq_cs at the beginning of assembly instruction sequence + * block, and set to NULL by the kernel when it restarts an assembly + * instruction sequence block, as well as when the kernel detects that + * it is preempting or delivering a signal outside of the range + * targeted by the rseq_cs. Also needs to be set to NULL by user-space + * before reclaiming memory that contains the targeted struct rseq_cs. + * + * Read and set by the kernel. Set by user-space with single-copy + * atomicity semantics. This field should only be updated by the + * thread which registered this data structure. Aligned on 64-bit. + */ + union { + __u64 ptr64; + + /* + * The "arch" field provides architecture accessor for + * the ptr field based on architecture pointer size and + * endianness. + */ + struct { +#ifdef __LP64__ + __u64 ptr; +#elif defined(__BYTE_ORDER) ? (__BYTE_ORDER == __BIG_ENDIAN) : defined(__BIG_ENDIAN) + __u32 padding; /* Initialized to zero. */ + __u32 ptr; +#else + __u32 ptr; + __u32 padding; /* Initialized to zero. */ +#endif + } arch; + } rseq_cs; + + /* + * Restartable sequences flags field. + * + * This field should only be updated by the thread which + * registered this data structure. Read by the kernel. + * Mainly used for single-stepping through rseq critical sections + * with debuggers. + * + * - RSEQ_ABI_CS_FLAG_NO_RESTART_ON_PREEMPT + * Inhibit instruction sequence block restart on preemption + * for this thread. + * - RSEQ_ABI_CS_FLAG_NO_RESTART_ON_SIGNAL + * Inhibit instruction sequence block restart on signal + * delivery for this thread. + * - RSEQ_ABI_CS_FLAG_NO_RESTART_ON_MIGRATE + * Inhibit instruction sequence block restart on migration for + * this thread. + */ + __u32 flags; +} __attribute__((aligned(4 * sizeof(__u64)))); + +#endif /* _RSEQ_ABI_H */ diff --git a/tools/testing/selftests/rseq/rseq-arm.h b/tools/testing/selftests/rseq/rseq-arm.h index 5943c816c07c..893a11eca9d5 100644 --- a/tools/testing/selftests/rseq/rseq-arm.h +++ b/tools/testing/selftests/rseq/rseq-arm.h @@ -147,14 +147,11 @@ do { \ teardown \ "b %l[" __rseq_str(cmpfail_label) "]\n\t" -#define rseq_workaround_gcc_asm_size_guess() __asm__ __volatile__("") - static inline __attribute__((always_inline)) int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu) { RSEQ_INJECT_C(9) - rseq_workaround_gcc_asm_size_guess(); __asm__ __volatile__ goto ( RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */ RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail]) @@ -185,8 +182,8 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu) "5:\n\t" : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), [v] "m" (*v), [expect] "r" (expect), [newv] "r" (newv) @@ -198,30 +195,31 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu) , error1, error2 #endif ); - rseq_workaround_gcc_asm_size_guess(); + rseq_after_asm_goto(); return 0; abort: - rseq_workaround_gcc_asm_size_guess(); + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: - rseq_workaround_gcc_asm_size_guess(); + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } static inline __attribute__((always_inline)) int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot, - off_t voffp, intptr_t *load, int cpu) + long voffp, intptr_t *load, int cpu) { RSEQ_INJECT_C(9) - rseq_workaround_gcc_asm_size_guess(); __asm__ __volatile__ goto ( RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */ RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail]) @@ -255,8 +253,8 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot, "5:\n\t" : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), /* final store input */ [v] "m" (*v), [expectnot] "r" (expectnot), @@ -270,19 +268,21 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot, , error1, error2 #endif ); - rseq_workaround_gcc_asm_size_guess(); + rseq_after_asm_goto(); return 0; abort: - rseq_workaround_gcc_asm_size_guess(); + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: - rseq_workaround_gcc_asm_size_guess(); + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -292,7 +292,6 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu) { RSEQ_INJECT_C(9) - rseq_workaround_gcc_asm_size_guess(); __asm__ __volatile__ goto ( RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */ #ifdef RSEQ_COMPARE_TWICE @@ -316,8 +315,8 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu) "5:\n\t" : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), [v] "m" (*v), [count] "Ir" (count) RSEQ_INJECT_INPUT @@ -328,14 +327,15 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu) , error1 #endif ); - rseq_workaround_gcc_asm_size_guess(); + rseq_after_asm_goto(); return 0; abort: - rseq_workaround_gcc_asm_size_guess(); + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); #endif } @@ -347,7 +347,6 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect, { RSEQ_INJECT_C(9) - rseq_workaround_gcc_asm_size_guess(); __asm__ __volatile__ goto ( RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */ RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail]) @@ -381,8 +380,8 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect, "5:\n\t" : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), /* try store input */ [v2] "m" (*v2), [newv2] "r" (newv2), @@ -398,19 +397,21 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect, , error1, error2 #endif ); - rseq_workaround_gcc_asm_size_guess(); + rseq_after_asm_goto(); return 0; abort: - rseq_workaround_gcc_asm_size_guess(); + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: - rseq_workaround_gcc_asm_size_guess(); + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -422,7 +423,6 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect, { RSEQ_INJECT_C(9) - rseq_workaround_gcc_asm_size_guess(); __asm__ __volatile__ goto ( RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */ RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail]) @@ -457,8 +457,8 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect, "5:\n\t" : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), /* try store input */ [v2] "m" (*v2), [newv2] "r" (newv2), @@ -474,19 +474,21 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect, , error1, error2 #endif ); - rseq_workaround_gcc_asm_size_guess(); + rseq_after_asm_goto(); return 0; abort: - rseq_workaround_gcc_asm_size_guess(); + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: - rseq_workaround_gcc_asm_size_guess(); + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -498,7 +500,6 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect, { RSEQ_INJECT_C(9) - rseq_workaround_gcc_asm_size_guess(); __asm__ __volatile__ goto ( RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */ RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail]) @@ -537,8 +538,8 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect, "5:\n\t" : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), /* cmp2 input */ [v2] "m" (*v2), [expect2] "r" (expect2), @@ -554,21 +555,24 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect, , error1, error2, error3 #endif ); - rseq_workaround_gcc_asm_size_guess(); + rseq_after_asm_goto(); return 0; abort: - rseq_workaround_gcc_asm_size_guess(); + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: - rseq_workaround_gcc_asm_size_guess(); + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("1st expected value comparison failed"); error3: + rseq_after_asm_goto(); rseq_bug("2nd expected value comparison failed"); #endif } @@ -582,7 +586,6 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect, RSEQ_INJECT_C(9) - rseq_workaround_gcc_asm_size_guess(); __asm__ __volatile__ goto ( RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */ RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail]) @@ -657,8 +660,8 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect, "8:\n\t" : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), /* final store input */ [v] "m" (*v), [expect] "r" (expect), @@ -678,21 +681,21 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect, , error1, error2 #endif ); - rseq_workaround_gcc_asm_size_guess(); + rseq_after_asm_goto(); return 0; abort: - rseq_workaround_gcc_asm_size_guess(); + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: - rseq_workaround_gcc_asm_size_guess(); + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: - rseq_workaround_gcc_asm_size_guess(); + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: - rseq_workaround_gcc_asm_size_guess(); + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -706,7 +709,6 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect, RSEQ_INJECT_C(9) - rseq_workaround_gcc_asm_size_guess(); __asm__ __volatile__ goto ( RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */ RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail]) @@ -782,8 +784,8 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect, "8:\n\t" : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), /* final store input */ [v] "m" (*v), [expect] "r" (expect), @@ -803,21 +805,21 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect, , error1, error2 #endif ); - rseq_workaround_gcc_asm_size_guess(); + rseq_after_asm_goto(); return 0; abort: - rseq_workaround_gcc_asm_size_guess(); + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: - rseq_workaround_gcc_asm_size_guess(); + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: - rseq_workaround_gcc_asm_size_guess(); + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: - rseq_workaround_gcc_asm_size_guess(); + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } diff --git a/tools/testing/selftests/rseq/rseq-arm64.h b/tools/testing/selftests/rseq/rseq-arm64.h index 200dae9e4208..cbe190a4d005 100644 --- a/tools/testing/selftests/rseq/rseq-arm64.h +++ b/tools/testing/selftests/rseq/rseq-arm64.h @@ -230,8 +230,8 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu) RSEQ_ASM_DEFINE_ABORT(4, abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "Qo" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "Qo" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), [v] "Qo" (*v), [expect] "r" (expect), [newv] "r" (newv) @@ -242,24 +242,28 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu) , error1, error2 #endif ); - + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } static inline __attribute__((always_inline)) int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot, - off_t voffp, intptr_t *load, int cpu) + long voffp, intptr_t *load, int cpu) { RSEQ_INJECT_C(9) @@ -287,8 +291,8 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot, RSEQ_ASM_DEFINE_ABORT(4, abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "Qo" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "Qo" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), [v] "Qo" (*v), [expectnot] "r" (expectnot), [load] "Qo" (*load), @@ -300,16 +304,21 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot, , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -337,8 +346,8 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu) RSEQ_ASM_DEFINE_ABORT(4, abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "Qo" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "Qo" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), [v] "Qo" (*v), [count] "r" (count) RSEQ_INJECT_INPUT @@ -348,12 +357,15 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu) , error1 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); #endif } @@ -388,8 +400,8 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect, RSEQ_ASM_DEFINE_ABORT(4, abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "Qo" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "Qo" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), [expect] "r" (expect), [v] "Qo" (*v), [newv] "r" (newv), @@ -402,17 +414,21 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect, , error1, error2 #endif ); - + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -447,8 +463,8 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect, RSEQ_ASM_DEFINE_ABORT(4, abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "Qo" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "Qo" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), [expect] "r" (expect), [v] "Qo" (*v), [newv] "r" (newv), @@ -461,17 +477,21 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect, , error1, error2 #endif ); - + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -508,8 +528,8 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect, RSEQ_ASM_DEFINE_ABORT(4, abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "Qo" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "Qo" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), [v] "Qo" (*v), [expect] "r" (expect), [v2] "Qo" (*v2), @@ -522,19 +542,24 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect, , error1, error2, error3 #endif ); - + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); error3: + rseq_after_asm_goto(); rseq_bug("2nd expected value comparison failed"); #endif } @@ -569,8 +594,8 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect, RSEQ_ASM_DEFINE_ABORT(4, abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "Qo" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "Qo" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), [expect] "r" (expect), [v] "Qo" (*v), [newv] "r" (newv), @@ -584,17 +609,21 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect, , error1, error2 #endif ); - + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -629,8 +658,8 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect, RSEQ_ASM_DEFINE_ABORT(4, abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "Qo" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "Qo" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), [expect] "r" (expect), [v] "Qo" (*v), [newv] "r" (newv), @@ -644,17 +673,21 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect, , error1, error2 #endif ); - + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } diff --git a/tools/testing/selftests/rseq/rseq-generic-thread-pointer.h b/tools/testing/selftests/rseq/rseq-generic-thread-pointer.h new file mode 100644 index 000000000000..38c584661571 --- /dev/null +++ b/tools/testing/selftests/rseq/rseq-generic-thread-pointer.h @@ -0,0 +1,25 @@ +/* SPDX-License-Identifier: LGPL-2.1-only OR MIT */ +/* + * rseq-generic-thread-pointer.h + * + * (C) Copyright 2021 - Mathieu Desnoyers <mathieu.desnoyers@efficios.com> + */ + +#ifndef _RSEQ_GENERIC_THREAD_POINTER +#define _RSEQ_GENERIC_THREAD_POINTER + +#ifdef __cplusplus +extern "C" { +#endif + +/* Use gcc builtin thread pointer. */ +static inline void *rseq_thread_pointer(void) +{ + return __builtin_thread_pointer(); +} + +#ifdef __cplusplus +} +#endif + +#endif diff --git a/tools/testing/selftests/rseq/rseq-mips.h b/tools/testing/selftests/rseq/rseq-mips.h index e989e7c14b09..878739fae2fd 100644 --- a/tools/testing/selftests/rseq/rseq-mips.h +++ b/tools/testing/selftests/rseq/rseq-mips.h @@ -154,14 +154,11 @@ do { \ teardown \ "b %l[" __rseq_str(cmpfail_label) "]\n\t" -#define rseq_workaround_gcc_asm_size_guess() __asm__ __volatile__("") - static inline __attribute__((always_inline)) int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu) { RSEQ_INJECT_C(9) - rseq_workaround_gcc_asm_size_guess(); __asm__ __volatile__ goto ( RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */ RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail]) @@ -190,8 +187,8 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu) "5:\n\t" : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), [v] "m" (*v), [expect] "r" (expect), [newv] "r" (newv) @@ -203,14 +200,11 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu) , error1, error2 #endif ); - rseq_workaround_gcc_asm_size_guess(); return 0; abort: - rseq_workaround_gcc_asm_size_guess(); RSEQ_INJECT_FAILED return -1; cmpfail: - rseq_workaround_gcc_asm_size_guess(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: @@ -222,11 +216,10 @@ error2: static inline __attribute__((always_inline)) int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot, - off_t voffp, intptr_t *load, int cpu) + long voffp, intptr_t *load, int cpu) { RSEQ_INJECT_C(9) - rseq_workaround_gcc_asm_size_guess(); __asm__ __volatile__ goto ( RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */ RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail]) @@ -258,8 +251,8 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot, "5:\n\t" : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), /* final store input */ [v] "m" (*v), [expectnot] "r" (expectnot), @@ -273,14 +266,11 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot, , error1, error2 #endif ); - rseq_workaround_gcc_asm_size_guess(); return 0; abort: - rseq_workaround_gcc_asm_size_guess(); RSEQ_INJECT_FAILED return -1; cmpfail: - rseq_workaround_gcc_asm_size_guess(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: @@ -295,7 +285,6 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu) { RSEQ_INJECT_C(9) - rseq_workaround_gcc_asm_size_guess(); __asm__ __volatile__ goto ( RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */ #ifdef RSEQ_COMPARE_TWICE @@ -319,8 +308,8 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu) "5:\n\t" : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), [v] "m" (*v), [count] "Ir" (count) RSEQ_INJECT_INPUT @@ -331,10 +320,8 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu) , error1 #endif ); - rseq_workaround_gcc_asm_size_guess(); return 0; abort: - rseq_workaround_gcc_asm_size_guess(); RSEQ_INJECT_FAILED return -1; #ifdef RSEQ_COMPARE_TWICE @@ -350,7 +337,6 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect, { RSEQ_INJECT_C(9) - rseq_workaround_gcc_asm_size_guess(); __asm__ __volatile__ goto ( RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */ RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail]) @@ -382,8 +368,8 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect, "5:\n\t" : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), /* try store input */ [v2] "m" (*v2), [newv2] "r" (newv2), @@ -399,14 +385,11 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect, , error1, error2 #endif ); - rseq_workaround_gcc_asm_size_guess(); return 0; abort: - rseq_workaround_gcc_asm_size_guess(); RSEQ_INJECT_FAILED return -1; cmpfail: - rseq_workaround_gcc_asm_size_guess(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: @@ -423,7 +406,6 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect, { RSEQ_INJECT_C(9) - rseq_workaround_gcc_asm_size_guess(); __asm__ __volatile__ goto ( RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */ RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail]) @@ -456,8 +438,8 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect, "5:\n\t" : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), /* try store input */ [v2] "m" (*v2), [newv2] "r" (newv2), @@ -473,14 +455,11 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect, , error1, error2 #endif ); - rseq_workaround_gcc_asm_size_guess(); return 0; abort: - rseq_workaround_gcc_asm_size_guess(); RSEQ_INJECT_FAILED return -1; cmpfail: - rseq_workaround_gcc_asm_size_guess(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: @@ -497,7 +476,6 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect, { RSEQ_INJECT_C(9) - rseq_workaround_gcc_asm_size_guess(); __asm__ __volatile__ goto ( RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */ RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail]) @@ -532,8 +510,8 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect, "5:\n\t" : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), /* cmp2 input */ [v2] "m" (*v2), [expect2] "r" (expect2), @@ -549,14 +527,11 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect, , error1, error2, error3 #endif ); - rseq_workaround_gcc_asm_size_guess(); return 0; abort: - rseq_workaround_gcc_asm_size_guess(); RSEQ_INJECT_FAILED return -1; cmpfail: - rseq_workaround_gcc_asm_size_guess(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: @@ -577,7 +552,6 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect, RSEQ_INJECT_C(9) - rseq_workaround_gcc_asm_size_guess(); __asm__ __volatile__ goto ( RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */ RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail]) @@ -649,8 +623,8 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect, "8:\n\t" : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), /* final store input */ [v] "m" (*v), [expect] "r" (expect), @@ -670,21 +644,16 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect, , error1, error2 #endif ); - rseq_workaround_gcc_asm_size_guess(); return 0; abort: - rseq_workaround_gcc_asm_size_guess(); RSEQ_INJECT_FAILED return -1; cmpfail: - rseq_workaround_gcc_asm_size_guess(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: - rseq_workaround_gcc_asm_size_guess(); rseq_bug("cpu_id comparison failed"); error2: - rseq_workaround_gcc_asm_size_guess(); rseq_bug("expected value comparison failed"); #endif } @@ -698,7 +667,6 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect, RSEQ_INJECT_C(9) - rseq_workaround_gcc_asm_size_guess(); __asm__ __volatile__ goto ( RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */ RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail]) @@ -771,8 +739,8 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect, "8:\n\t" : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), /* final store input */ [v] "m" (*v), [expect] "r" (expect), @@ -792,21 +760,16 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect, , error1, error2 #endif ); - rseq_workaround_gcc_asm_size_guess(); return 0; abort: - rseq_workaround_gcc_asm_size_guess(); RSEQ_INJECT_FAILED return -1; cmpfail: - rseq_workaround_gcc_asm_size_guess(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: - rseq_workaround_gcc_asm_size_guess(); rseq_bug("cpu_id comparison failed"); error2: - rseq_workaround_gcc_asm_size_guess(); rseq_bug("expected value comparison failed"); #endif } diff --git a/tools/testing/selftests/rseq/rseq-ppc-thread-pointer.h b/tools/testing/selftests/rseq/rseq-ppc-thread-pointer.h new file mode 100644 index 000000000000..263eee84fb76 --- /dev/null +++ b/tools/testing/selftests/rseq/rseq-ppc-thread-pointer.h @@ -0,0 +1,30 @@ +/* SPDX-License-Identifier: LGPL-2.1-only OR MIT */ +/* + * rseq-ppc-thread-pointer.h + * + * (C) Copyright 2021 - Mathieu Desnoyers <mathieu.desnoyers@efficios.com> + */ + +#ifndef _RSEQ_PPC_THREAD_POINTER +#define _RSEQ_PPC_THREAD_POINTER + +#ifdef __cplusplus +extern "C" { +#endif + +static inline void *rseq_thread_pointer(void) +{ +#ifdef __powerpc64__ + register void *__result asm ("r13"); +#else + register void *__result asm ("r2"); +#endif + asm ("" : "=r" (__result)); + return __result; +} + +#ifdef __cplusplus +} +#endif + +#endif diff --git a/tools/testing/selftests/rseq/rseq-ppc.h b/tools/testing/selftests/rseq/rseq-ppc.h index 76be90196fe4..bab8e0b9fb11 100644 --- a/tools/testing/selftests/rseq/rseq-ppc.h +++ b/tools/testing/selftests/rseq/rseq-ppc.h @@ -47,10 +47,13 @@ do { \ #ifdef __PPC64__ -#define STORE_WORD "std " -#define LOAD_WORD "ld " -#define LOADX_WORD "ldx " -#define CMP_WORD "cmpd " +#define RSEQ_STORE_LONG(arg) "std%U[" __rseq_str(arg) "]%X[" __rseq_str(arg) "] " /* To memory ("m" constraint) */ +#define RSEQ_STORE_INT(arg) "stw%U[" __rseq_str(arg) "]%X[" __rseq_str(arg) "] " /* To memory ("m" constraint) */ +#define RSEQ_LOAD_LONG(arg) "ld%U[" __rseq_str(arg) "]%X[" __rseq_str(arg) "] " /* From memory ("m" constraint) */ +#define RSEQ_LOAD_INT(arg) "lwz%U[" __rseq_str(arg) "]%X[" __rseq_str(arg) "] " /* From memory ("m" constraint) */ +#define RSEQ_LOADX_LONG "ldx " /* From base register ("b" constraint) */ +#define RSEQ_CMP_LONG "cmpd " +#define RSEQ_CMP_LONG_INT "cmpdi " #define __RSEQ_ASM_DEFINE_TABLE(label, version, flags, \ start_ip, post_commit_offset, abort_ip) \ @@ -89,10 +92,13 @@ do { \ #else /* #ifdef __PPC64__ */ -#define STORE_WORD "stw " -#define LOAD_WORD "lwz " -#define LOADX_WORD "lwzx " -#define CMP_WORD "cmpw " +#define RSEQ_STORE_LONG(arg) "stw%U[" __rseq_str(arg) "]%X[" __rseq_str(arg) "] " /* To memory ("m" constraint) */ +#define RSEQ_STORE_INT(arg) RSEQ_STORE_LONG(arg) /* To memory ("m" constraint) */ +#define RSEQ_LOAD_LONG(arg) "lwz%U[" __rseq_str(arg) "]%X[" __rseq_str(arg) "] " /* From memory ("m" constraint) */ +#define RSEQ_LOAD_INT(arg) RSEQ_LOAD_LONG(arg) /* From memory ("m" constraint) */ +#define RSEQ_LOADX_LONG "lwzx " /* From base register ("b" constraint) */ +#define RSEQ_CMP_LONG "cmpw " +#define RSEQ_CMP_LONG_INT "cmpwi " #define __RSEQ_ASM_DEFINE_TABLE(label, version, flags, \ start_ip, post_commit_offset, abort_ip) \ @@ -125,7 +131,7 @@ do { \ RSEQ_INJECT_ASM(1) \ "lis %%r17, (" __rseq_str(cs_label) ")@ha\n\t" \ "addi %%r17, %%r17, (" __rseq_str(cs_label) ")@l\n\t" \ - "stw %%r17, %[" __rseq_str(rseq_cs) "]\n\t" \ + RSEQ_STORE_INT(rseq_cs) "%%r17, %[" __rseq_str(rseq_cs) "]\n\t" \ __rseq_str(label) ":\n\t" #endif /* #ifdef __PPC64__ */ @@ -136,7 +142,7 @@ do { \ #define RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, label) \ RSEQ_INJECT_ASM(2) \ - "lwz %%r17, %[" __rseq_str(current_cpu_id) "]\n\t" \ + RSEQ_LOAD_INT(current_cpu_id) "%%r17, %[" __rseq_str(current_cpu_id) "]\n\t" \ "cmpw cr7, %[" __rseq_str(cpu_id) "], %%r17\n\t" \ "bne- cr7, " __rseq_str(label) "\n\t" @@ -153,25 +159,25 @@ do { \ * RSEQ_ASM_OP_* (else): doesn't have hard-code registers(unless cr7) */ #define RSEQ_ASM_OP_CMPEQ(var, expect, label) \ - LOAD_WORD "%%r17, %[" __rseq_str(var) "]\n\t" \ - CMP_WORD "cr7, %%r17, %[" __rseq_str(expect) "]\n\t" \ + RSEQ_LOAD_LONG(var) "%%r17, %[" __rseq_str(var) "]\n\t" \ + RSEQ_CMP_LONG "cr7, %%r17, %[" __rseq_str(expect) "]\n\t" \ "bne- cr7, " __rseq_str(label) "\n\t" #define RSEQ_ASM_OP_CMPNE(var, expectnot, label) \ - LOAD_WORD "%%r17, %[" __rseq_str(var) "]\n\t" \ - CMP_WORD "cr7, %%r17, %[" __rseq_str(expectnot) "]\n\t" \ + RSEQ_LOAD_LONG(var) "%%r17, %[" __rseq_str(var) "]\n\t" \ + RSEQ_CMP_LONG "cr7, %%r17, %[" __rseq_str(expectnot) "]\n\t" \ "beq- cr7, " __rseq_str(label) "\n\t" #define RSEQ_ASM_OP_STORE(value, var) \ - STORE_WORD "%[" __rseq_str(value) "], %[" __rseq_str(var) "]\n\t" + RSEQ_STORE_LONG(var) "%[" __rseq_str(value) "], %[" __rseq_str(var) "]\n\t" /* Load @var to r17 */ #define RSEQ_ASM_OP_R_LOAD(var) \ - LOAD_WORD "%%r17, %[" __rseq_str(var) "]\n\t" + RSEQ_LOAD_LONG(var) "%%r17, %[" __rseq_str(var) "]\n\t" /* Store r17 to @var */ #define RSEQ_ASM_OP_R_STORE(var) \ - STORE_WORD "%%r17, %[" __rseq_str(var) "]\n\t" + RSEQ_STORE_LONG(var) "%%r17, %[" __rseq_str(var) "]\n\t" /* Add @count to r17 */ #define RSEQ_ASM_OP_R_ADD(count) \ @@ -179,11 +185,11 @@ do { \ /* Load (r17 + voffp) to r17 */ #define RSEQ_ASM_OP_R_LOADX(voffp) \ - LOADX_WORD "%%r17, %[" __rseq_str(voffp) "], %%r17\n\t" + RSEQ_LOADX_LONG "%%r17, %[" __rseq_str(voffp) "], %%r17\n\t" /* TODO: implement a faster memcpy. */ #define RSEQ_ASM_OP_R_MEMCPY() \ - "cmpdi %%r19, 0\n\t" \ + RSEQ_CMP_LONG_INT "%%r19, 0\n\t" \ "beq 333f\n\t" \ "addi %%r20, %%r20, -1\n\t" \ "addi %%r21, %%r21, -1\n\t" \ @@ -191,16 +197,16 @@ do { \ "lbzu %%r18, 1(%%r20)\n\t" \ "stbu %%r18, 1(%%r21)\n\t" \ "addi %%r19, %%r19, -1\n\t" \ - "cmpdi %%r19, 0\n\t" \ + RSEQ_CMP_LONG_INT "%%r19, 0\n\t" \ "bne 222b\n\t" \ "333:\n\t" \ #define RSEQ_ASM_OP_R_FINAL_STORE(var, post_commit_label) \ - STORE_WORD "%%r17, %[" __rseq_str(var) "]\n\t" \ + RSEQ_STORE_LONG(var) "%%r17, %[" __rseq_str(var) "]\n\t" \ __rseq_str(post_commit_label) ":\n\t" #define RSEQ_ASM_OP_FINAL_STORE(value, var, post_commit_label) \ - STORE_WORD "%[" __rseq_str(value) "], %[" __rseq_str(var) "]\n\t" \ + RSEQ_STORE_LONG(var) "%[" __rseq_str(value) "], %[" __rseq_str(var) "]\n\t" \ __rseq_str(post_commit_label) ":\n\t" static inline __attribute__((always_inline)) @@ -235,8 +241,8 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu) RSEQ_ASM_DEFINE_ABORT(4, abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), [v] "m" (*v), [expect] "r" (expect), [newv] "r" (newv) @@ -248,23 +254,28 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu) , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } static inline __attribute__((always_inline)) int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot, - off_t voffp, intptr_t *load, int cpu) + long voffp, intptr_t *load, int cpu) { RSEQ_INJECT_C(9) @@ -301,8 +312,8 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot, RSEQ_ASM_DEFINE_ABORT(4, abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), /* final store input */ [v] "m" (*v), [expectnot] "r" (expectnot), @@ -316,16 +327,21 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot, , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -359,8 +375,8 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu) RSEQ_ASM_DEFINE_ABORT(4, abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), /* final store input */ [v] "m" (*v), [count] "r" (count) @@ -372,12 +388,15 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu) , error1 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); #endif } @@ -419,8 +438,8 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect, RSEQ_ASM_DEFINE_ABORT(4, abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), /* try store input */ [v2] "m" (*v2), [newv2] "r" (newv2), @@ -436,16 +455,21 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect, , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -489,8 +513,8 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect, RSEQ_ASM_DEFINE_ABORT(4, abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), /* try store input */ [v2] "m" (*v2), [newv2] "r" (newv2), @@ -506,16 +530,21 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect, , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -560,8 +589,8 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect, RSEQ_ASM_DEFINE_ABORT(4, abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), /* cmp2 input */ [v2] "m" (*v2), [expect2] "r" (expect2), @@ -577,18 +606,24 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect, , error1, error2, error3 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("1st expected value comparison failed"); error3: + rseq_after_asm_goto(); rseq_bug("2nd expected value comparison failed"); #endif } @@ -635,8 +670,8 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect, RSEQ_ASM_DEFINE_ABORT(4, abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), /* final store input */ [v] "m" (*v), [expect] "r" (expect), @@ -653,16 +688,21 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect, , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -711,8 +751,8 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect, RSEQ_ASM_DEFINE_ABORT(4, abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), /* final store input */ [v] "m" (*v), [expect] "r" (expect), @@ -729,23 +769,23 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect, , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } -#undef STORE_WORD -#undef LOAD_WORD -#undef LOADX_WORD -#undef CMP_WORD - #endif /* !RSEQ_SKIP_FASTPATH */ diff --git a/tools/testing/selftests/rseq/rseq-riscv.h b/tools/testing/selftests/rseq/rseq-riscv.h new file mode 100644 index 000000000000..b86642f90d7f --- /dev/null +++ b/tools/testing/selftests/rseq/rseq-riscv.h @@ -0,0 +1,677 @@ +/* SPDX-License-Identifier: LGPL-2.1 OR MIT */ +/* + * Select the instruction "csrw mhartid, x0" as the RSEQ_SIG. Unlike + * other architectures, the ebreak instruction has no immediate field for + * distinguishing purposes. Hence, ebreak is not suitable as RSEQ_SIG. + * "csrw mhartid, x0" can also satisfy the RSEQ requirement because it + * is an uncommon instruction and will raise an illegal instruction + * exception when executed in all modes. + */ +#include <endian.h> + +#if defined(__BYTE_ORDER) ? (__BYTE_ORDER == __LITTLE_ENDIAN) : defined(__LITTLE_ENDIAN) +#define RSEQ_SIG 0xf1401073 /* csrr mhartid, x0 */ +#else +#error "Currently, RSEQ only supports Little-Endian version" +#endif + +#if __riscv_xlen == 64 +#define __REG_SEL(a, b) a +#elif __riscv_xlen == 32 +#define __REG_SEL(a, b) b +#endif + +#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) +#define RSEQ_ASM_TMP_REG_1 "t6" +#define RSEQ_ASM_TMP_REG_2 "t5" +#define RSEQ_ASM_TMP_REG_3 "t4" +#define RSEQ_ASM_TMP_REG_4 "t3" + +#define rseq_smp_load_acquire(p) \ +__extension__ ({ \ + __typeof(*(p)) ____p1 = RSEQ_READ_ONCE(*(p)); \ + RISCV_FENCE(r, rw) \ + ____p1; \ +}) + +#define rseq_smp_acquire__after_ctrl_dep() rseq_smp_rmb() + +#define rseq_smp_store_release(p, v) \ +do { \ + RISCV_FENCE(rw, w); \ + RSEQ_WRITE_ONCE(*(p), v); \ +} while (0) + +#ifdef RSEQ_SKIP_FASTPATH +#include "rseq-skip.h" +#else /* !RSEQ_SKIP_FASTPATH */ + +#define __RSEQ_ASM_DEFINE_TABLE(label, version, flags, start_ip, \ + post_commit_offset, abort_ip) \ + ".pushsection __rseq_cs, \"aw\"\n" \ + ".balign 32\n" \ + __rseq_str(label) ":\n" \ + ".long " __rseq_str(version) ", " __rseq_str(flags) "\n" \ + ".quad " __rseq_str(start_ip) ", " \ + __rseq_str(post_commit_offset) ", " \ + __rseq_str(abort_ip) "\n" \ + ".popsection\n\t" \ + ".pushsection __rseq_cs_ptr_array, \"aw\"\n" \ + ".quad " __rseq_str(label) "b\n" \ + ".popsection\n" + +#define RSEQ_ASM_DEFINE_TABLE(label, start_ip, post_commit_ip, abort_ip) \ + __RSEQ_ASM_DEFINE_TABLE(label, 0x0, 0x0, start_ip, \ + ((post_commit_ip) - (start_ip)), abort_ip) + +/* + * Exit points of a rseq critical section consist of all instructions outside + * of the critical section where a critical section can either branch to or + * reach through the normal course of its execution. The abort IP and the + * post-commit IP are already part of the __rseq_cs section and should not be + * explicitly defined as additional exit points. Knowing all exit points is + * useful to assist debuggers stepping over the critical section. + */ +#define RSEQ_ASM_DEFINE_EXIT_POINT(start_ip, exit_ip) \ + ".pushsection __rseq_exit_point_array, \"aw\"\n" \ + ".quad " __rseq_str(start_ip) ", " __rseq_str(exit_ip) "\n" \ + ".popsection\n" + +#define RSEQ_ASM_STORE_RSEQ_CS(label, cs_label, rseq_cs) \ + RSEQ_INJECT_ASM(1) \ + "la "RSEQ_ASM_TMP_REG_1 ", " __rseq_str(cs_label) "\n" \ + REG_S RSEQ_ASM_TMP_REG_1 ", %[" __rseq_str(rseq_cs) "]\n" \ + __rseq_str(label) ":\n" + +#define RSEQ_ASM_DEFINE_ABORT(label, abort_label) \ + "j 222f\n" \ + ".balign 4\n" \ + ".long " __rseq_str(RSEQ_SIG) "\n" \ + __rseq_str(label) ":\n" \ + "j %l[" __rseq_str(abort_label) "]\n" \ + "222:\n" + +#define RSEQ_ASM_OP_STORE(value, var) \ + REG_S "%[" __rseq_str(value) "], %[" __rseq_str(var) "]\n" + +#define RSEQ_ASM_OP_CMPEQ(var, expect, label) \ + REG_L RSEQ_ASM_TMP_REG_1 ", %[" __rseq_str(var) "]\n" \ + "bne "RSEQ_ASM_TMP_REG_1 ", %[" __rseq_str(expect) "] ," \ + __rseq_str(label) "\n" + +#define RSEQ_ASM_OP_CMPEQ32(var, expect, label) \ + "lw "RSEQ_ASM_TMP_REG_1 ", %[" __rseq_str(var) "]\n" \ + "bne "RSEQ_ASM_TMP_REG_1 ", %[" __rseq_str(expect) "] ," \ + __rseq_str(label) "\n" + +#define RSEQ_ASM_OP_CMPNE(var, expect, label) \ + REG_L RSEQ_ASM_TMP_REG_1 ", %[" __rseq_str(var) "]\n" \ + "beq "RSEQ_ASM_TMP_REG_1 ", %[" __rseq_str(expect) "] ," \ + __rseq_str(label) "\n" + +#define RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, label) \ + RSEQ_INJECT_ASM(2) \ + RSEQ_ASM_OP_CMPEQ32(current_cpu_id, cpu_id, label) + +#define RSEQ_ASM_OP_R_LOAD(var) \ + REG_L RSEQ_ASM_TMP_REG_1 ", %[" __rseq_str(var) "]\n" + +#define RSEQ_ASM_OP_R_STORE(var) \ + REG_S RSEQ_ASM_TMP_REG_1 ", %[" __rseq_str(var) "]\n" + +#define RSEQ_ASM_OP_R_LOAD_OFF(offset) \ + "add "RSEQ_ASM_TMP_REG_1 ", %[" __rseq_str(offset) "], " \ + RSEQ_ASM_TMP_REG_1 "\n" \ + REG_L RSEQ_ASM_TMP_REG_1 ", (" RSEQ_ASM_TMP_REG_1 ")\n" + +#define RSEQ_ASM_OP_R_ADD(count) \ + "add "RSEQ_ASM_TMP_REG_1 ", " RSEQ_ASM_TMP_REG_1 \ + ", %[" __rseq_str(count) "]\n" + +#define RSEQ_ASM_OP_FINAL_STORE(value, var, post_commit_label) \ + RSEQ_ASM_OP_STORE(value, var) \ + __rseq_str(post_commit_label) ":\n" + +#define RSEQ_ASM_OP_FINAL_STORE_RELEASE(value, var, post_commit_label) \ + "fence rw, w\n" \ + RSEQ_ASM_OP_STORE(value, var) \ + __rseq_str(post_commit_label) ":\n" + +#define RSEQ_ASM_OP_R_FINAL_STORE(var, post_commit_label) \ + REG_S RSEQ_ASM_TMP_REG_1 ", %[" __rseq_str(var) "]\n" \ + __rseq_str(post_commit_label) ":\n" + +#define RSEQ_ASM_OP_R_BAD_MEMCPY(dst, src, len) \ + "beqz %[" __rseq_str(len) "], 333f\n" \ + "mv " RSEQ_ASM_TMP_REG_1 ", %[" __rseq_str(len) "]\n" \ + "mv " RSEQ_ASM_TMP_REG_2 ", %[" __rseq_str(src) "]\n" \ + "mv " RSEQ_ASM_TMP_REG_3 ", %[" __rseq_str(dst) "]\n" \ + "222:\n" \ + "lb " RSEQ_ASM_TMP_REG_4 ", 0(" RSEQ_ASM_TMP_REG_2 ")\n" \ + "sb " RSEQ_ASM_TMP_REG_4 ", 0(" RSEQ_ASM_TMP_REG_3 ")\n" \ + "addi " RSEQ_ASM_TMP_REG_1 ", " RSEQ_ASM_TMP_REG_1 ", -1\n" \ + "addi " RSEQ_ASM_TMP_REG_2 ", " RSEQ_ASM_TMP_REG_2 ", 1\n" \ + "addi " RSEQ_ASM_TMP_REG_3 ", " RSEQ_ASM_TMP_REG_3 ", 1\n" \ + "bnez " RSEQ_ASM_TMP_REG_1 ", 222b\n" \ + "333:\n" + +#define RSEQ_ASM_OP_R_DEREF_ADDV(ptr, off, post_commit_label) \ + "mv " RSEQ_ASM_TMP_REG_1 ", %[" __rseq_str(ptr) "]\n" \ + RSEQ_ASM_OP_R_ADD(off) \ + REG_L RSEQ_ASM_TMP_REG_1 ", 0(" RSEQ_ASM_TMP_REG_1 ")\n" \ + RSEQ_ASM_OP_R_ADD(inc) \ + __rseq_str(post_commit_label) ":\n" + +static inline __always_inline +int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu) +{ + RSEQ_INJECT_C(9) + + __asm__ __volatile__ goto(RSEQ_ASM_DEFINE_TABLE(1, 2f, 3f, 4f) + RSEQ_ASM_DEFINE_EXIT_POINT(2f, "%l[cmpfail]") +#ifdef RSEQ_COMPARE_TWICE + RSEQ_ASM_DEFINE_EXIT_POINT(2f, "%l[error1]") + RSEQ_ASM_DEFINE_EXIT_POINT(2f, "%l[error2]") +#endif + RSEQ_ASM_STORE_RSEQ_CS(2, 1b, rseq_cs) + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f) + RSEQ_INJECT_ASM(3) + RSEQ_ASM_OP_CMPEQ(v, expect, "%l[cmpfail]") + RSEQ_INJECT_ASM(4) +#ifdef RSEQ_COMPARE_TWICE + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, "%l[error1]") + RSEQ_ASM_OP_CMPEQ(v, expect, "%l[error2]") +#endif + RSEQ_ASM_OP_FINAL_STORE(newv, v, 3) + RSEQ_INJECT_ASM(5) + RSEQ_ASM_DEFINE_ABORT(4, abort) + : /* gcc asm goto does not allow outputs */ + : [cpu_id] "r" (cpu), + [current_cpu_id] "m" (__rseq_abi.cpu_id), + [rseq_cs] "m" (__rseq_abi.rseq_cs), + [v] "m" (*v), + [expect] "r" (expect), + [newv] "r" (newv) + RSEQ_INJECT_INPUT + : "memory", RSEQ_ASM_TMP_REG_1 + RSEQ_INJECT_CLOBBER + : abort, cmpfail +#ifdef RSEQ_COMPARE_TWICE + , error1, error2 +#endif + ); + + return 0; +abort: + RSEQ_INJECT_FAILED + return -1; +cmpfail: + return 1; +#ifdef RSEQ_COMPARE_TWICE +error1: + rseq_bug("cpu_id comparison failed"); +error2: + rseq_bug("expected value comparison failed"); +#endif +} + +static inline __always_inline +int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot, + off_t voffp, intptr_t *load, int cpu) +{ + RSEQ_INJECT_C(9) + + __asm__ __volatile__ goto(RSEQ_ASM_DEFINE_TABLE(1, 2f, 3f, 4f) + RSEQ_ASM_DEFINE_EXIT_POINT(2f, "%l[cmpfail]") +#ifdef RSEQ_COMPARE_TWICE + RSEQ_ASM_DEFINE_EXIT_POINT(2f, "%l[error1]") + RSEQ_ASM_DEFINE_EXIT_POINT(2f, "%l[error2]") +#endif + RSEQ_ASM_STORE_RSEQ_CS(2, 1b, rseq_cs) + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f) + RSEQ_INJECT_ASM(3) + RSEQ_ASM_OP_CMPNE(v, expectnot, "%l[cmpfail]") + RSEQ_INJECT_ASM(4) +#ifdef RSEQ_COMPARE_TWICE + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, "%l[error1]") + RSEQ_ASM_OP_CMPNE(v, expectnot, "%l[error2]") +#endif + RSEQ_ASM_OP_R_LOAD(v) + RSEQ_ASM_OP_R_STORE(load) + RSEQ_ASM_OP_R_LOAD_OFF(voffp) + RSEQ_ASM_OP_R_FINAL_STORE(v, 3) + RSEQ_INJECT_ASM(5) + RSEQ_ASM_DEFINE_ABORT(4, abort) + : /* gcc asm goto does not allow outputs */ + : [cpu_id] "r" (cpu), + [current_cpu_id] "m" (__rseq_abi.cpu_id), + [rseq_cs] "m" (__rseq_abi.rseq_cs), + [v] "m" (*v), + [expectnot] "r" (expectnot), + [load] "m" (*load), + [voffp] "r" (voffp) + RSEQ_INJECT_INPUT + : "memory", RSEQ_ASM_TMP_REG_1 + RSEQ_INJECT_CLOBBER + : abort, cmpfail +#ifdef RSEQ_COMPARE_TWICE + , error1, error2 +#endif + ); + return 0; +abort: + RSEQ_INJECT_FAILED + return -1; +cmpfail: + return 1; +#ifdef RSEQ_COMPARE_TWICE +error1: + rseq_bug("cpu_id comparison failed"); +error2: + rseq_bug("expected value comparison failed"); +#endif +} + +static inline __always_inline +int rseq_addv(intptr_t *v, intptr_t count, int cpu) +{ + RSEQ_INJECT_C(9) + + __asm__ __volatile__ goto(RSEQ_ASM_DEFINE_TABLE(1, 2f, 3f, 4f) +#ifdef RSEQ_COMPARE_TWICE + RSEQ_ASM_DEFINE_EXIT_POINT(2f, "%l[error1]") +#endif + RSEQ_ASM_STORE_RSEQ_CS(2, 1b, rseq_cs) + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f) + RSEQ_INJECT_ASM(3) +#ifdef RSEQ_COMPARE_TWICE + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, "%l[error1]") +#endif + RSEQ_ASM_OP_R_LOAD(v) + RSEQ_ASM_OP_R_ADD(count) + RSEQ_ASM_OP_R_FINAL_STORE(v, 3) + RSEQ_INJECT_ASM(4) + RSEQ_ASM_DEFINE_ABORT(4, abort) + : /* gcc asm goto does not allow outputs */ + : [cpu_id] "r" (cpu), + [current_cpu_id] "m" (__rseq_abi.cpu_id), + [rseq_cs] "m" (__rseq_abi.rseq_cs), + [v] "m" (*v), + [count] "r" (count) + RSEQ_INJECT_INPUT + : "memory", RSEQ_ASM_TMP_REG_1 + RSEQ_INJECT_CLOBBER + : abort +#ifdef RSEQ_COMPARE_TWICE + , error1 +#endif + ); + return 0; +abort: + RSEQ_INJECT_FAILED + return -1; +#ifdef RSEQ_COMPARE_TWICE +error1: + rseq_bug("cpu_id comparison failed"); +#endif +} + +static inline __always_inline +int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect, + intptr_t *v2, intptr_t newv2, + intptr_t newv, int cpu) +{ + RSEQ_INJECT_C(9) + + __asm__ __volatile__ goto(RSEQ_ASM_DEFINE_TABLE(1, 2f, 3f, 4f) + RSEQ_ASM_DEFINE_EXIT_POINT(2f, "%l[cmpfail]") +#ifdef RSEQ_COMPARE_TWICE + RSEQ_ASM_DEFINE_EXIT_POINT(2f, "%l[error1]") + RSEQ_ASM_DEFINE_EXIT_POINT(2f, "%l[error2]") +#endif + RSEQ_ASM_STORE_RSEQ_CS(2, 1b, rseq_cs) + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f) + RSEQ_INJECT_ASM(3) + RSEQ_ASM_OP_CMPEQ(v, expect, "%l[cmpfail]") + RSEQ_INJECT_ASM(4) +#ifdef RSEQ_COMPARE_TWICE + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, "%l[error1]") + RSEQ_ASM_OP_CMPEQ(v, expect, "%l[error2]") +#endif + RSEQ_ASM_OP_STORE(newv2, v2) + RSEQ_INJECT_ASM(5) + RSEQ_ASM_OP_FINAL_STORE(newv, v, 3) + RSEQ_INJECT_ASM(6) + RSEQ_ASM_DEFINE_ABORT(4, abort) + : /* gcc asm goto does not allow outputs */ + : [cpu_id] "r" (cpu), + [current_cpu_id] "m" (__rseq_abi.cpu_id), + [rseq_cs] "m" (__rseq_abi.rseq_cs), + [expect] "r" (expect), + [v] "m" (*v), + [newv] "r" (newv), + [v2] "m" (*v2), + [newv2] "r" (newv2) + RSEQ_INJECT_INPUT + : "memory", RSEQ_ASM_TMP_REG_1 + RSEQ_INJECT_CLOBBER + : abort, cmpfail +#ifdef RSEQ_COMPARE_TWICE + , error1, error2 +#endif + ); + + return 0; +abort: + RSEQ_INJECT_FAILED + return -1; +cmpfail: + return 1; +#ifdef RSEQ_COMPARE_TWICE +error1: + rseq_bug("cpu_id comparison failed"); +error2: + rseq_bug("expected value comparison failed"); +#endif +} + +static inline __always_inline +int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect, + intptr_t *v2, intptr_t newv2, + intptr_t newv, int cpu) +{ + RSEQ_INJECT_C(9) + + __asm__ __volatile__ goto(RSEQ_ASM_DEFINE_TABLE(1, 2f, 3f, 4f) + RSEQ_ASM_DEFINE_EXIT_POINT(2f, "%l[cmpfail]") +#ifdef RSEQ_COMPARE_TWICE + RSEQ_ASM_DEFINE_EXIT_POINT(2f, "%l[error1]") + RSEQ_ASM_DEFINE_EXIT_POINT(2f, "%l[error2]") +#endif + RSEQ_ASM_STORE_RSEQ_CS(2, 1b, rseq_cs) + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f) + RSEQ_INJECT_ASM(3) + RSEQ_ASM_OP_CMPEQ(v, expect, "%l[cmpfail]") + RSEQ_INJECT_ASM(4) +#ifdef RSEQ_COMPARE_TWICE + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, "%l[error1]") + RSEQ_ASM_OP_CMPEQ(v, expect, "%l[error2]") +#endif + RSEQ_ASM_OP_STORE(newv2, v2) + RSEQ_INJECT_ASM(5) + RSEQ_ASM_OP_FINAL_STORE_RELEASE(newv, v, 3) + RSEQ_INJECT_ASM(6) + RSEQ_ASM_DEFINE_ABORT(4, abort) + : /* gcc asm goto does not allow outputs */ + : [cpu_id] "r" (cpu), + [current_cpu_id] "m" (__rseq_abi.cpu_id), + [rseq_cs] "m" (__rseq_abi.rseq_cs), + [expect] "r" (expect), + [v] "m" (*v), + [newv] "r" (newv), + [v2] "m" (*v2), + [newv2] "r" (newv2) + RSEQ_INJECT_INPUT + : "memory", RSEQ_ASM_TMP_REG_1 + RSEQ_INJECT_CLOBBER + : abort, cmpfail +#ifdef RSEQ_COMPARE_TWICE + , error1, error2 +#endif + ); + + return 0; +abort: + RSEQ_INJECT_FAILED + return -1; +cmpfail: + return 1; +#ifdef RSEQ_COMPARE_TWICE +error1: + rseq_bug("cpu_id comparison failed"); +error2: + rseq_bug("expected value comparison failed"); +#endif +} + +static inline __always_inline +int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect, + intptr_t *v2, intptr_t expect2, + intptr_t newv, int cpu) +{ + RSEQ_INJECT_C(9) + + __asm__ __volatile__ goto(RSEQ_ASM_DEFINE_TABLE(1, 2f, 3f, 4f) + RSEQ_ASM_DEFINE_EXIT_POINT(2f, "%l[cmpfail]") +#ifdef RSEQ_COMPARE_TWICE + RSEQ_ASM_DEFINE_EXIT_POINT(2f, "%l[error1]") + RSEQ_ASM_DEFINE_EXIT_POINT(2f, "%l[error2]") + RSEQ_ASM_DEFINE_EXIT_POINT(2f, "%l[error3]") +#endif + RSEQ_ASM_STORE_RSEQ_CS(2, 1b, rseq_cs) + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f) + RSEQ_INJECT_ASM(3) + RSEQ_ASM_OP_CMPEQ(v, expect, "%l[cmpfail]") + RSEQ_INJECT_ASM(4) + RSEQ_ASM_OP_CMPEQ(v2, expect2, "%l[cmpfail]") + RSEQ_INJECT_ASM(5) +#ifdef RSEQ_COMPARE_TWICE + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, "%l[error1]") + RSEQ_ASM_OP_CMPEQ(v, expect, "%l[error2]") + RSEQ_ASM_OP_CMPEQ(v2, expect2, "%l[error3]") +#endif + RSEQ_ASM_OP_FINAL_STORE(newv, v, 3) + RSEQ_INJECT_ASM(6) + RSEQ_ASM_DEFINE_ABORT(4, abort) + : /* gcc asm goto does not allow outputs */ + : [cpu_id] "r" (cpu), + [current_cpu_id] "m" (__rseq_abi.cpu_id), + [rseq_cs] "m" (__rseq_abi.rseq_cs), + [v] "m" (*v), + [expect] "r" (expect), + [v2] "m" (*v2), + [expect2] "r" (expect2), + [newv] "r" (newv) + RSEQ_INJECT_INPUT + : "memory", RSEQ_ASM_TMP_REG_1 + RSEQ_INJECT_CLOBBER + : abort, cmpfail +#ifdef RSEQ_COMPARE_TWICE + , error1, error2, error3 +#endif + ); + + return 0; +abort: + RSEQ_INJECT_FAILED + return -1; +cmpfail: + return 1; +#ifdef RSEQ_COMPARE_TWICE +error1: + rseq_bug("cpu_id comparison failed"); +error2: + rseq_bug("expected value comparison failed"); +error3: + rseq_bug("2nd expected value comparison failed"); +#endif +} + +static inline __always_inline +int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect, + void *dst, void *src, size_t len, + intptr_t newv, int cpu) +{ + RSEQ_INJECT_C(9) + __asm__ __volatile__ goto(RSEQ_ASM_DEFINE_TABLE(1, 2f, 3f, 4f) + RSEQ_ASM_DEFINE_EXIT_POINT(2f, "%l[cmpfail]") +#ifdef RSEQ_COMPARE_TWICE + RSEQ_ASM_DEFINE_EXIT_POINT(2f, "%l[error1]") + RSEQ_ASM_DEFINE_EXIT_POINT(2f, "%l[error2]") +#endif + RSEQ_ASM_STORE_RSEQ_CS(2, 1b, rseq_cs) + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f) + RSEQ_INJECT_ASM(3) + RSEQ_ASM_OP_CMPEQ(v, expect, "%l[cmpfail]") + RSEQ_INJECT_ASM(4) +#ifdef RSEQ_COMPARE_TWICE + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, "%l[error1]") + RSEQ_ASM_OP_CMPEQ(v, expect, "%l[error2]") +#endif + RSEQ_ASM_OP_R_BAD_MEMCPY(dst, src, len) + RSEQ_INJECT_ASM(5) + RSEQ_ASM_OP_FINAL_STORE(newv, v, 3) + RSEQ_INJECT_ASM(6) + RSEQ_ASM_DEFINE_ABORT(4, abort) + : /* gcc asm goto does not allow outputs */ + : [cpu_id] "r" (cpu), + [current_cpu_id] "m" (__rseq_abi.cpu_id), + [rseq_cs] "m" (__rseq_abi.rseq_cs), + [expect] "r" (expect), + [v] "m" (*v), + [newv] "r" (newv), + [dst] "r" (dst), + [src] "r" (src), + [len] "r" (len) + RSEQ_INJECT_INPUT + : "memory", RSEQ_ASM_TMP_REG_1, RSEQ_ASM_TMP_REG_2, + RSEQ_ASM_TMP_REG_3, RSEQ_ASM_TMP_REG_4 + RSEQ_INJECT_CLOBBER + : abort, cmpfail +#ifdef RSEQ_COMPARE_TWICE + , error1, error2 +#endif + ); + + return 0; +abort: + RSEQ_INJECT_FAILED + return -1; +cmpfail: + return 1; +#ifdef RSEQ_COMPARE_TWICE +error1: + rseq_bug("cpu_id comparison failed"); +error2: + rseq_bug("expected value comparison failed"); +#endif +} + +static inline __always_inline +int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect, + void *dst, void *src, size_t len, + intptr_t newv, int cpu) +{ + RSEQ_INJECT_C(9) + + __asm__ __volatile__ goto(RSEQ_ASM_DEFINE_TABLE(1, 2f, 3f, 4f) + RSEQ_ASM_DEFINE_EXIT_POINT(2f, "%l[cmpfail]") +#ifdef RSEQ_COMPARE_TWICE + RSEQ_ASM_DEFINE_EXIT_POINT(2f, "%l[error1]") + RSEQ_ASM_DEFINE_EXIT_POINT(2f, "%l[error2]") +#endif + RSEQ_ASM_STORE_RSEQ_CS(2, 1b, rseq_cs) + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f) + RSEQ_INJECT_ASM(3) + RSEQ_ASM_OP_CMPEQ(v, expect, "%l[cmpfail]") + RSEQ_INJECT_ASM(4) +#ifdef RSEQ_COMPARE_TWICE + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, "%l[error1]") + RSEQ_ASM_OP_CMPEQ(v, expect, "%l[error2]") +#endif + RSEQ_ASM_OP_R_BAD_MEMCPY(dst, src, len) + RSEQ_INJECT_ASM(5) + RSEQ_ASM_OP_FINAL_STORE_RELEASE(newv, v, 3) + RSEQ_INJECT_ASM(6) + RSEQ_ASM_DEFINE_ABORT(4, abort) + : /* gcc asm goto does not allow outputs */ + : [cpu_id] "r" (cpu), + [current_cpu_id] "m" (__rseq_abi.cpu_id), + [rseq_cs] "m" (__rseq_abi.rseq_cs), + [expect] "r" (expect), + [v] "m" (*v), + [newv] "r" (newv), + [dst] "r" (dst), + [src] "r" (src), + [len] "r" (len) + RSEQ_INJECT_INPUT + : "memory", RSEQ_ASM_TMP_REG_1, RSEQ_ASM_TMP_REG_2, + RSEQ_ASM_TMP_REG_3, RSEQ_ASM_TMP_REG_4 + RSEQ_INJECT_CLOBBER + : abort, cmpfail +#ifdef RSEQ_COMPARE_TWICE + , error1, error2 +#endif + ); + + return 0; +abort: + RSEQ_INJECT_FAILED + return -1; +cmpfail: + return 1; +#ifdef RSEQ_COMPARE_TWICE +error1: + rseq_bug("cpu_id comparison failed"); +error2: + rseq_bug("expected value comparison failed"); +#endif +} + +#define RSEQ_ARCH_HAS_OFFSET_DEREF_ADDV + +/* + * pval = *(ptr+off) + * *pval += inc; + */ +static inline __always_inline +int rseq_offset_deref_addv(intptr_t *ptr, off_t off, intptr_t inc, int cpu) +{ + RSEQ_INJECT_C(9) + + __asm__ __volatile__ goto(RSEQ_ASM_DEFINE_TABLE(1, 2f, 3f, 4f) +#ifdef RSEQ_COMPARE_TWICE + RSEQ_ASM_DEFINE_EXIT_POINT(2f, "%l[error1]") +#endif + RSEQ_ASM_STORE_RSEQ_CS(2, 1b, rseq_cs) + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f) + RSEQ_INJECT_ASM(3) +#ifdef RSEQ_COMPARE_TWICE + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, "%l[error1]") +#endif + RSEQ_ASM_OP_R_DEREF_ADDV(ptr, off, 3) + RSEQ_INJECT_ASM(4) + RSEQ_ASM_DEFINE_ABORT(4, abort) + : /* gcc asm goto does not allow outputs */ + : [cpu_id] "r" (cpu), + [current_cpu_id] "m" (__rseq_abi.cpu_id), + [rseq_cs] "m" (__rseq_abi.rseq_cs), + [ptr] "r" (ptr), + [off] "er" (off), + [inc] "er" (inc) + RSEQ_INJECT_INPUT + : "memory", RSEQ_ASM_TMP_REG_1 + RSEQ_INJECT_CLOBBER + : abort +#ifdef RSEQ_COMPARE_TWICE + , error1 +#endif + ); + return 0; +abort: + RSEQ_INJECT_FAILED + return -1; +#ifdef RSEQ_COMPARE_TWICE +error1: + rseq_bug("cpu_id comparison failed"); +#endif +} + +#endif /* !RSEQ_SKIP_FASTPATH */ diff --git a/tools/testing/selftests/rseq/rseq-s390.h b/tools/testing/selftests/rseq/rseq-s390.h index 8ef94ad1cbb4..4e6dc5f0cb42 100644 --- a/tools/testing/selftests/rseq/rseq-s390.h +++ b/tools/testing/selftests/rseq/rseq-s390.h @@ -165,8 +165,8 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu) RSEQ_ASM_DEFINE_ABORT(4, "", abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), [v] "m" (*v), [expect] "r" (expect), [newv] "r" (newv) @@ -178,16 +178,21 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu) , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -198,7 +203,7 @@ error2: */ static inline __attribute__((always_inline)) int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot, - off_t voffp, intptr_t *load, int cpu) + long voffp, intptr_t *load, int cpu) { RSEQ_INJECT_C(9) @@ -233,8 +238,8 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot, RSEQ_ASM_DEFINE_ABORT(4, "", abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), /* final store input */ [v] "m" (*v), [expectnot] "r" (expectnot), @@ -248,16 +253,21 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot, , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -288,8 +298,8 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu) RSEQ_ASM_DEFINE_ABORT(4, "", abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), /* final store input */ [v] "m" (*v), [count] "r" (count) @@ -301,12 +311,15 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu) , error1 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); #endif } @@ -347,8 +360,8 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect, RSEQ_ASM_DEFINE_ABORT(4, "", abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), /* try store input */ [v2] "m" (*v2), [newv2] "r" (newv2), @@ -364,16 +377,21 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect, , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -426,8 +444,8 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect, RSEQ_ASM_DEFINE_ABORT(4, "", abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), /* cmp2 input */ [v2] "m" (*v2), [expect2] "r" (expect2), @@ -443,18 +461,24 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect, , error1, error2, error3 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("1st expected value comparison failed"); error3: + rseq_after_asm_goto(); rseq_bug("2nd expected value comparison failed"); #endif } @@ -534,8 +558,8 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect, #endif : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), /* final store input */ [v] "m" (*v), [expect] "r" (expect), @@ -555,16 +579,21 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect, , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } diff --git a/tools/testing/selftests/rseq/rseq-skip.h b/tools/testing/selftests/rseq/rseq-skip.h index 72750b5905a9..7b53dac1fcdd 100644 --- a/tools/testing/selftests/rseq/rseq-skip.h +++ b/tools/testing/selftests/rseq/rseq-skip.h @@ -13,7 +13,7 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu) static inline __attribute__((always_inline)) int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot, - off_t voffp, intptr_t *load, int cpu) + long voffp, intptr_t *load, int cpu) { return -1; } diff --git a/tools/testing/selftests/rseq/rseq-thread-pointer.h b/tools/testing/selftests/rseq/rseq-thread-pointer.h new file mode 100644 index 000000000000..977c25d758b2 --- /dev/null +++ b/tools/testing/selftests/rseq/rseq-thread-pointer.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: LGPL-2.1-only OR MIT */ +/* + * rseq-thread-pointer.h + * + * (C) Copyright 2021 - Mathieu Desnoyers <mathieu.desnoyers@efficios.com> + */ + +#ifndef _RSEQ_THREAD_POINTER +#define _RSEQ_THREAD_POINTER + +#if defined(__x86_64__) || defined(__i386__) +#include "rseq-x86-thread-pointer.h" +#elif defined(__PPC__) +#include "rseq-ppc-thread-pointer.h" +#else +#include "rseq-generic-thread-pointer.h" +#endif + +#endif diff --git a/tools/testing/selftests/rseq/rseq-x86-thread-pointer.h b/tools/testing/selftests/rseq/rseq-x86-thread-pointer.h new file mode 100644 index 000000000000..d3133587d996 --- /dev/null +++ b/tools/testing/selftests/rseq/rseq-x86-thread-pointer.h @@ -0,0 +1,40 @@ +/* SPDX-License-Identifier: LGPL-2.1-only OR MIT */ +/* + * rseq-x86-thread-pointer.h + * + * (C) Copyright 2021 - Mathieu Desnoyers <mathieu.desnoyers@efficios.com> + */ + +#ifndef _RSEQ_X86_THREAD_POINTER +#define _RSEQ_X86_THREAD_POINTER + +#include <features.h> + +#ifdef __cplusplus +extern "C" { +#endif + +#if __GNUC_PREREQ (11, 1) +static inline void *rseq_thread_pointer(void) +{ + return __builtin_thread_pointer(); +} +#else +static inline void *rseq_thread_pointer(void) +{ + void *__result; + +# ifdef __x86_64__ + __asm__ ("mov %%fs:0, %0" : "=r" (__result)); +# else + __asm__ ("mov %%gs:0, %0" : "=r" (__result)); +# endif + return __result; +} +#endif /* !GCC 11 */ + +#ifdef __cplusplus +} +#endif + +#endif diff --git a/tools/testing/selftests/rseq/rseq-x86.h b/tools/testing/selftests/rseq/rseq-x86.h index 640411518e46..bd01dc41ca13 100644 --- a/tools/testing/selftests/rseq/rseq-x86.h +++ b/tools/testing/selftests/rseq/rseq-x86.h @@ -28,6 +28,8 @@ #ifdef __x86_64__ +#define RSEQ_ASM_TP_SEGMENT %%fs + #define rseq_smp_mb() \ __asm__ __volatile__ ("lock; addl $0,-128(%%rsp)" ::: "memory", "cc") #define rseq_smp_rmb() rseq_barrier() @@ -123,14 +125,14 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu) RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2]) #endif /* Start rseq by storing table entry pointer into rseq_cs. */ - RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi])) - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f) + RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset])) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f) RSEQ_INJECT_ASM(3) "cmpq %[v], %[expect]\n\t" "jnz %l[cmpfail]\n\t" RSEQ_INJECT_ASM(4) #ifdef RSEQ_COMPARE_TWICE - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1]) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1]) "cmpq %[v], %[expect]\n\t" "jnz %l[error2]\n\t" #endif @@ -141,7 +143,7 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu) RSEQ_ASM_DEFINE_ABORT(4, "", abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [rseq_abi] "r" (&__rseq_abi), + [rseq_offset] "r" (rseq_offset), [v] "m" (*v), [expect] "r" (expect), [newv] "r" (newv) @@ -152,16 +154,21 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu) , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -172,7 +179,7 @@ error2: */ static inline __attribute__((always_inline)) int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot, - off_t voffp, intptr_t *load, int cpu) + long voffp, intptr_t *load, int cpu) { RSEQ_INJECT_C(9) @@ -184,15 +191,15 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot, RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2]) #endif /* Start rseq by storing table entry pointer into rseq_cs. */ - RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi])) - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f) + RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset])) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f) RSEQ_INJECT_ASM(3) "movq %[v], %%rbx\n\t" "cmpq %%rbx, %[expectnot]\n\t" "je %l[cmpfail]\n\t" RSEQ_INJECT_ASM(4) #ifdef RSEQ_COMPARE_TWICE - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1]) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1]) "movq %[v], %%rbx\n\t" "cmpq %%rbx, %[expectnot]\n\t" "je %l[error2]\n\t" @@ -207,7 +214,7 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot, RSEQ_ASM_DEFINE_ABORT(4, "", abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [rseq_abi] "r" (&__rseq_abi), + [rseq_offset] "r" (rseq_offset), /* final store input */ [v] "m" (*v), [expectnot] "r" (expectnot), @@ -220,16 +227,21 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot, , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -245,11 +257,11 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu) RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error1]) #endif /* Start rseq by storing table entry pointer into rseq_cs. */ - RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi])) - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f) + RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset])) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f) RSEQ_INJECT_ASM(3) #ifdef RSEQ_COMPARE_TWICE - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1]) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1]) #endif /* final store */ "addq %[count], %[v]\n\t" @@ -258,7 +270,7 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu) RSEQ_ASM_DEFINE_ABORT(4, "", abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [rseq_abi] "r" (&__rseq_abi), + [rseq_offset] "r" (rseq_offset), /* final store input */ [v] "m" (*v), [count] "er" (count) @@ -269,12 +281,15 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu) , error1 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); #endif } @@ -286,7 +301,7 @@ error1: * *pval += inc; */ static inline __attribute__((always_inline)) -int rseq_offset_deref_addv(intptr_t *ptr, off_t off, intptr_t inc, int cpu) +int rseq_offset_deref_addv(intptr_t *ptr, long off, intptr_t inc, int cpu) { RSEQ_INJECT_C(9) @@ -296,11 +311,11 @@ int rseq_offset_deref_addv(intptr_t *ptr, off_t off, intptr_t inc, int cpu) RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error1]) #endif /* Start rseq by storing table entry pointer into rseq_cs. */ - RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi])) - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f) + RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset])) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f) RSEQ_INJECT_ASM(3) #ifdef RSEQ_COMPARE_TWICE - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1]) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1]) #endif /* get p+v */ "movq %[ptr], %%rbx\n\t" @@ -314,7 +329,7 @@ int rseq_offset_deref_addv(intptr_t *ptr, off_t off, intptr_t inc, int cpu) RSEQ_ASM_DEFINE_ABORT(4, "", abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [rseq_abi] "r" (&__rseq_abi), + [rseq_offset] "r" (rseq_offset), /* final store input */ [ptr] "m" (*ptr), [off] "er" (off), @@ -351,14 +366,14 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect, RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2]) #endif /* Start rseq by storing table entry pointer into rseq_cs. */ - RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi])) - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f) + RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset])) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f) RSEQ_INJECT_ASM(3) "cmpq %[v], %[expect]\n\t" "jnz %l[cmpfail]\n\t" RSEQ_INJECT_ASM(4) #ifdef RSEQ_COMPARE_TWICE - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1]) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1]) "cmpq %[v], %[expect]\n\t" "jnz %l[error2]\n\t" #endif @@ -372,7 +387,7 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect, RSEQ_ASM_DEFINE_ABORT(4, "", abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [rseq_abi] "r" (&__rseq_abi), + [rseq_offset] "r" (rseq_offset), /* try store input */ [v2] "m" (*v2), [newv2] "r" (newv2), @@ -387,16 +402,21 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect, , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -426,8 +446,8 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect, RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error3]) #endif /* Start rseq by storing table entry pointer into rseq_cs. */ - RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi])) - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f) + RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset])) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f) RSEQ_INJECT_ASM(3) "cmpq %[v], %[expect]\n\t" "jnz %l[cmpfail]\n\t" @@ -436,7 +456,7 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect, "jnz %l[cmpfail]\n\t" RSEQ_INJECT_ASM(5) #ifdef RSEQ_COMPARE_TWICE - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1]) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1]) "cmpq %[v], %[expect]\n\t" "jnz %l[error2]\n\t" "cmpq %[v2], %[expect2]\n\t" @@ -449,7 +469,7 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect, RSEQ_ASM_DEFINE_ABORT(4, "", abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [rseq_abi] "r" (&__rseq_abi), + [rseq_offset] "r" (rseq_offset), /* cmp2 input */ [v2] "m" (*v2), [expect2] "r" (expect2), @@ -464,18 +484,24 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect, , error1, error2, error3 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("1st expected value comparison failed"); error3: + rseq_after_asm_goto(); rseq_bug("2nd expected value comparison failed"); #endif } @@ -500,14 +526,14 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect, "movq %[dst], %[rseq_scratch1]\n\t" "movq %[len], %[rseq_scratch2]\n\t" /* Start rseq by storing table entry pointer into rseq_cs. */ - RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi])) - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f) + RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset])) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f) RSEQ_INJECT_ASM(3) "cmpq %[v], %[expect]\n\t" "jnz 5f\n\t" RSEQ_INJECT_ASM(4) #ifdef RSEQ_COMPARE_TWICE - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 6f) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 6f) "cmpq %[v], %[expect]\n\t" "jnz 7f\n\t" #endif @@ -555,7 +581,7 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect, #endif : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [rseq_abi] "r" (&__rseq_abi), + [rseq_offset] "r" (rseq_offset), /* final store input */ [v] "m" (*v), [expect] "r" (expect), @@ -574,16 +600,21 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect, , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -600,7 +631,9 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect, #endif /* !RSEQ_SKIP_FASTPATH */ -#elif __i386__ +#elif defined(__i386__) + +#define RSEQ_ASM_TP_SEGMENT %%gs #define rseq_smp_mb() \ __asm__ __volatile__ ("lock; addl $0,-128(%%esp)" ::: "memory", "cc") @@ -701,14 +734,14 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu) RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2]) #endif /* Start rseq by storing table entry pointer into rseq_cs. */ - RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi])) - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f) + RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset])) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f) RSEQ_INJECT_ASM(3) "cmpl %[v], %[expect]\n\t" "jnz %l[cmpfail]\n\t" RSEQ_INJECT_ASM(4) #ifdef RSEQ_COMPARE_TWICE - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1]) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1]) "cmpl %[v], %[expect]\n\t" "jnz %l[error2]\n\t" #endif @@ -719,7 +752,7 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu) RSEQ_ASM_DEFINE_ABORT(4, "", abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [rseq_abi] "r" (&__rseq_abi), + [rseq_offset] "r" (rseq_offset), [v] "m" (*v), [expect] "r" (expect), [newv] "r" (newv) @@ -730,16 +763,21 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu) , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -750,7 +788,7 @@ error2: */ static inline __attribute__((always_inline)) int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot, - off_t voffp, intptr_t *load, int cpu) + long voffp, intptr_t *load, int cpu) { RSEQ_INJECT_C(9) @@ -762,15 +800,15 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot, RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2]) #endif /* Start rseq by storing table entry pointer into rseq_cs. */ - RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi])) - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f) + RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset])) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f) RSEQ_INJECT_ASM(3) "movl %[v], %%ebx\n\t" "cmpl %%ebx, %[expectnot]\n\t" "je %l[cmpfail]\n\t" RSEQ_INJECT_ASM(4) #ifdef RSEQ_COMPARE_TWICE - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1]) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1]) "movl %[v], %%ebx\n\t" "cmpl %%ebx, %[expectnot]\n\t" "je %l[error2]\n\t" @@ -785,7 +823,7 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot, RSEQ_ASM_DEFINE_ABORT(4, "", abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [rseq_abi] "r" (&__rseq_abi), + [rseq_offset] "r" (rseq_offset), /* final store input */ [v] "m" (*v), [expectnot] "r" (expectnot), @@ -798,16 +836,21 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot, , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -823,11 +866,11 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu) RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error1]) #endif /* Start rseq by storing table entry pointer into rseq_cs. */ - RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi])) - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f) + RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset])) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f) RSEQ_INJECT_ASM(3) #ifdef RSEQ_COMPARE_TWICE - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1]) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1]) #endif /* final store */ "addl %[count], %[v]\n\t" @@ -836,7 +879,7 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu) RSEQ_ASM_DEFINE_ABORT(4, "", abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [rseq_abi] "r" (&__rseq_abi), + [rseq_offset] "r" (rseq_offset), /* final store input */ [v] "m" (*v), [count] "ir" (count) @@ -847,12 +890,15 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu) , error1 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); #endif } @@ -872,14 +918,14 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect, RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2]) #endif /* Start rseq by storing table entry pointer into rseq_cs. */ - RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi])) - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f) + RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset])) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f) RSEQ_INJECT_ASM(3) "cmpl %[v], %[expect]\n\t" "jnz %l[cmpfail]\n\t" RSEQ_INJECT_ASM(4) #ifdef RSEQ_COMPARE_TWICE - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1]) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1]) "cmpl %[v], %[expect]\n\t" "jnz %l[error2]\n\t" #endif @@ -894,7 +940,7 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect, RSEQ_ASM_DEFINE_ABORT(4, "", abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [rseq_abi] "r" (&__rseq_abi), + [rseq_offset] "r" (rseq_offset), /* try store input */ [v2] "m" (*v2), [newv2] "m" (newv2), @@ -909,16 +955,21 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect, , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -938,15 +989,15 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect, RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2]) #endif /* Start rseq by storing table entry pointer into rseq_cs. */ - RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi])) - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f) + RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset])) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f) RSEQ_INJECT_ASM(3) "movl %[expect], %%eax\n\t" "cmpl %[v], %%eax\n\t" "jnz %l[cmpfail]\n\t" RSEQ_INJECT_ASM(4) #ifdef RSEQ_COMPARE_TWICE - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1]) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1]) "movl %[expect], %%eax\n\t" "cmpl %[v], %%eax\n\t" "jnz %l[error2]\n\t" @@ -962,7 +1013,7 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect, RSEQ_ASM_DEFINE_ABORT(4, "", abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [rseq_abi] "r" (&__rseq_abi), + [rseq_offset] "r" (rseq_offset), /* try store input */ [v2] "m" (*v2), [newv2] "r" (newv2), @@ -977,16 +1028,21 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect, , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif @@ -1008,8 +1064,8 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect, RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error3]) #endif /* Start rseq by storing table entry pointer into rseq_cs. */ - RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi])) - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f) + RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset])) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f) RSEQ_INJECT_ASM(3) "cmpl %[v], %[expect]\n\t" "jnz %l[cmpfail]\n\t" @@ -1018,7 +1074,7 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect, "jnz %l[cmpfail]\n\t" RSEQ_INJECT_ASM(5) #ifdef RSEQ_COMPARE_TWICE - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1]) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1]) "cmpl %[v], %[expect]\n\t" "jnz %l[error2]\n\t" "cmpl %[expect2], %[v2]\n\t" @@ -1032,7 +1088,7 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect, RSEQ_ASM_DEFINE_ABORT(4, "", abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [rseq_abi] "r" (&__rseq_abi), + [rseq_offset] "r" (rseq_offset), /* cmp2 input */ [v2] "m" (*v2), [expect2] "r" (expect2), @@ -1047,18 +1103,24 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect, , error1, error2, error3 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("1st expected value comparison failed"); error3: + rseq_after_asm_goto(); rseq_bug("2nd expected value comparison failed"); #endif } @@ -1084,15 +1146,15 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect, "movl %[dst], %[rseq_scratch1]\n\t" "movl %[len], %[rseq_scratch2]\n\t" /* Start rseq by storing table entry pointer into rseq_cs. */ - RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi])) - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f) + RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset])) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f) RSEQ_INJECT_ASM(3) "movl %[expect], %%eax\n\t" "cmpl %%eax, %[v]\n\t" "jnz 5f\n\t" RSEQ_INJECT_ASM(4) #ifdef RSEQ_COMPARE_TWICE - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 6f) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 6f) "movl %[expect], %%eax\n\t" "cmpl %%eax, %[v]\n\t" "jnz 7f\n\t" @@ -1142,7 +1204,7 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect, #endif : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [rseq_abi] "r" (&__rseq_abi), + [rseq_offset] "r" (rseq_offset), /* final store input */ [v] "m" (*v), [expect] "m" (expect), @@ -1161,16 +1223,21 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect, , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -1196,15 +1263,15 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect, "movl %[dst], %[rseq_scratch1]\n\t" "movl %[len], %[rseq_scratch2]\n\t" /* Start rseq by storing table entry pointer into rseq_cs. */ - RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi])) - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f) + RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset])) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f) RSEQ_INJECT_ASM(3) "movl %[expect], %%eax\n\t" "cmpl %%eax, %[v]\n\t" "jnz 5f\n\t" RSEQ_INJECT_ASM(4) #ifdef RSEQ_COMPARE_TWICE - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 6f) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 6f) "movl %[expect], %%eax\n\t" "cmpl %%eax, %[v]\n\t" "jnz 7f\n\t" @@ -1255,7 +1322,7 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect, #endif : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [rseq_abi] "r" (&__rseq_abi), + [rseq_offset] "r" (rseq_offset), /* final store input */ [v] "m" (*v), [expect] "m" (expect), @@ -1274,16 +1341,21 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect, , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } diff --git a/tools/testing/selftests/rseq/rseq.c b/tools/testing/selftests/rseq/rseq.c index fb440dfca158..986b9458efb2 100644 --- a/tools/testing/selftests/rseq/rseq.c +++ b/tools/testing/selftests/rseq/rseq.c @@ -26,130 +26,124 @@ #include <assert.h> #include <signal.h> #include <limits.h> +#include <dlfcn.h> +#include <stddef.h> #include "../kselftest.h" #include "rseq.h" -__thread volatile struct rseq __rseq_abi = { - .cpu_id = RSEQ_CPU_ID_UNINITIALIZED, -}; - -/* - * Shared with other libraries. This library may take rseq ownership if it is - * still 0 when executing the library constructor. Set to 1 by library - * constructor when handling rseq. Set to 0 in destructor if handling rseq. - */ -int __rseq_handled; - -/* Whether this library have ownership of rseq registration. */ -static int rseq_ownership; +static const ptrdiff_t *libc_rseq_offset_p; +static const unsigned int *libc_rseq_size_p; +static const unsigned int *libc_rseq_flags_p; -static __thread volatile uint32_t __rseq_refcount; +/* Offset from the thread pointer to the rseq area. */ +ptrdiff_t rseq_offset; -static void signal_off_save(sigset_t *oldset) -{ - sigset_t set; - int ret; +/* Size of the registered rseq area. 0 if the registration was + unsuccessful. */ +unsigned int rseq_size = -1U; - sigfillset(&set); - ret = pthread_sigmask(SIG_BLOCK, &set, oldset); - if (ret) - abort(); -} +/* Flags used during rseq registration. */ +unsigned int rseq_flags; -static void signal_restore(sigset_t oldset) -{ - int ret; +static int rseq_ownership; - ret = pthread_sigmask(SIG_SETMASK, &oldset, NULL); - if (ret) - abort(); -} +static +__thread struct rseq_abi __rseq_abi __attribute__((tls_model("initial-exec"))) = { + .cpu_id = RSEQ_ABI_CPU_ID_UNINITIALIZED, +}; -static int sys_rseq(volatile struct rseq *rseq_abi, uint32_t rseq_len, +static int sys_rseq(struct rseq_abi *rseq_abi, uint32_t rseq_len, int flags, uint32_t sig) { return syscall(__NR_rseq, rseq_abi, rseq_len, flags, sig); } -int rseq_register_current_thread(void) +int rseq_available(void) { - int rc, ret = 0; - sigset_t oldset; + int rc; - if (!rseq_ownership) + rc = sys_rseq(NULL, 0, 0, 0); + if (rc != -1) + abort(); + switch (errno) { + case ENOSYS: return 0; - signal_off_save(&oldset); - if (__rseq_refcount == UINT_MAX) { - ret = -1; - goto end; - } - if (__rseq_refcount++) - goto end; - rc = sys_rseq(&__rseq_abi, sizeof(struct rseq), 0, RSEQ_SIG); - if (!rc) { - assert(rseq_current_cpu_raw() >= 0); - goto end; + case EINVAL: + return 1; + default: + abort(); } - if (errno != EBUSY) - __rseq_abi.cpu_id = RSEQ_CPU_ID_REGISTRATION_FAILED; - ret = -1; - __rseq_refcount--; -end: - signal_restore(oldset); - return ret; } -int rseq_unregister_current_thread(void) +int rseq_register_current_thread(void) { - int rc, ret = 0; - sigset_t oldset; + int rc; - if (!rseq_ownership) + if (!rseq_ownership) { + /* Treat libc's ownership as a successful registration. */ return 0; - signal_off_save(&oldset); - if (!__rseq_refcount) { - ret = -1; - goto end; } - if (--__rseq_refcount) - goto end; - rc = sys_rseq(&__rseq_abi, sizeof(struct rseq), - RSEQ_FLAG_UNREGISTER, RSEQ_SIG); - if (!rc) - goto end; - __rseq_refcount = 1; - ret = -1; -end: - signal_restore(oldset); - return ret; + rc = sys_rseq(&__rseq_abi, sizeof(struct rseq_abi), 0, RSEQ_SIG); + if (rc) + return -1; + assert(rseq_current_cpu_raw() >= 0); + return 0; } -int32_t rseq_fallback_current_cpu(void) +int rseq_unregister_current_thread(void) { - int32_t cpu; + int rc; - cpu = sched_getcpu(); - if (cpu < 0) { - perror("sched_getcpu()"); - abort(); + if (!rseq_ownership) { + /* Treat libc's ownership as a successful unregistration. */ + return 0; } - return cpu; + rc = sys_rseq(&__rseq_abi, sizeof(struct rseq_abi), RSEQ_ABI_FLAG_UNREGISTER, RSEQ_SIG); + if (rc) + return -1; + return 0; } -void __attribute__((constructor)) rseq_init(void) +static __attribute__((constructor)) +void rseq_init(void) { - /* Check whether rseq is handled by another library. */ - if (__rseq_handled) + libc_rseq_offset_p = dlsym(RTLD_NEXT, "__rseq_offset"); + libc_rseq_size_p = dlsym(RTLD_NEXT, "__rseq_size"); + libc_rseq_flags_p = dlsym(RTLD_NEXT, "__rseq_flags"); + if (libc_rseq_size_p && libc_rseq_offset_p && libc_rseq_flags_p) { + /* rseq registration owned by glibc */ + rseq_offset = *libc_rseq_offset_p; + rseq_size = *libc_rseq_size_p; + rseq_flags = *libc_rseq_flags_p; + return; + } + if (!rseq_available()) return; - __rseq_handled = 1; rseq_ownership = 1; + rseq_offset = (void *)&__rseq_abi - rseq_thread_pointer(); + rseq_size = sizeof(struct rseq_abi); + rseq_flags = 0; } -void __attribute__((destructor)) rseq_fini(void) +static __attribute__((destructor)) +void rseq_exit(void) { if (!rseq_ownership) return; - __rseq_handled = 0; + rseq_offset = 0; + rseq_size = -1U; rseq_ownership = 0; } + +int32_t rseq_fallback_current_cpu(void) +{ + int32_t cpu; + + cpu = sched_getcpu(); + if (cpu < 0) { + perror("sched_getcpu()"); + abort(); + } + return cpu; +} diff --git a/tools/testing/selftests/rseq/rseq.h b/tools/testing/selftests/rseq/rseq.h index 3f63eb362b92..6f7513384bf5 100644 --- a/tools/testing/selftests/rseq/rseq.h +++ b/tools/testing/selftests/rseq/rseq.h @@ -16,7 +16,9 @@ #include <errno.h> #include <stdio.h> #include <stdlib.h> -#include <linux/rseq.h> +#include <stddef.h> +#include "rseq-abi.h" +#include "compiler.h" /* * Empty code injection macros, override when testing. @@ -43,8 +45,20 @@ #define RSEQ_INJECT_FAILED #endif -extern __thread volatile struct rseq __rseq_abi; -extern int __rseq_handled; +#include "rseq-thread-pointer.h" + +/* Offset from the thread pointer to the rseq area. */ +extern ptrdiff_t rseq_offset; +/* Size of the registered rseq area. 0 if the registration was + unsuccessful. */ +extern unsigned int rseq_size; +/* Flags used during rseq registration. */ +extern unsigned int rseq_flags; + +static inline struct rseq_abi *rseq_get_abi(void) +{ + return (struct rseq_abi *) ((uintptr_t) rseq_thread_pointer() + rseq_offset); +} #define rseq_likely(x) __builtin_expect(!!(x), 1) #define rseq_unlikely(x) __builtin_expect(!!(x), 0) @@ -79,6 +93,8 @@ extern int __rseq_handled; #include <rseq-mips.h> #elif defined(__s390__) #include <rseq-s390.h> +#elif defined(__riscv) +#include <rseq-riscv.h> #else #error unsupported target #endif @@ -108,7 +124,7 @@ int32_t rseq_fallback_current_cpu(void); */ static inline int32_t rseq_current_cpu_raw(void) { - return RSEQ_ACCESS_ONCE(__rseq_abi.cpu_id); + return RSEQ_ACCESS_ONCE(rseq_get_abi()->cpu_id); } /* @@ -124,7 +140,7 @@ static inline int32_t rseq_current_cpu_raw(void) */ static inline uint32_t rseq_cpu_start(void) { - return RSEQ_ACCESS_ONCE(__rseq_abi.cpu_id_start); + return RSEQ_ACCESS_ONCE(rseq_get_abi()->cpu_id_start); } static inline uint32_t rseq_current_cpu(void) @@ -139,11 +155,7 @@ static inline uint32_t rseq_current_cpu(void) static inline void rseq_clear_rseq_cs(void) { -#ifdef __LP64__ - __rseq_abi.rseq_cs.ptr = 0; -#else - __rseq_abi.rseq_cs.ptr.ptr32 = 0; -#endif + RSEQ_WRITE_ONCE(rseq_get_abi()->rseq_cs.arch.ptr, 0); } /* diff --git a/tools/testing/selftests/rtc/rtctest.c b/tools/testing/selftests/rtc/rtctest.c index 66af608fb4c6..2b9d929a24ed 100644 --- a/tools/testing/selftests/rtc/rtctest.c +++ b/tools/testing/selftests/rtc/rtctest.c @@ -20,6 +20,8 @@ #define NUM_UIE 3 #define ALARM_DELTA 3 +#define READ_LOOP_DURATION_SEC 30 +#define READ_LOOP_SLEEP_MS 11 static char *rtc_file = "/dev/rtc0"; @@ -49,6 +51,70 @@ TEST_F(rtc, date_read) { rtc_tm.tm_hour, rtc_tm.tm_min, rtc_tm.tm_sec); } +static time_t rtc_time_to_timestamp(struct rtc_time *rtc_time) +{ + struct tm tm_time = { + .tm_sec = rtc_time->tm_sec, + .tm_min = rtc_time->tm_min, + .tm_hour = rtc_time->tm_hour, + .tm_mday = rtc_time->tm_mday, + .tm_mon = rtc_time->tm_mon, + .tm_year = rtc_time->tm_year, + }; + + return mktime(&tm_time); +} + +static void nanosleep_with_retries(long ns) +{ + struct timespec req = { + .tv_sec = 0, + .tv_nsec = ns, + }; + struct timespec rem; + + while (nanosleep(&req, &rem) != 0) { + req.tv_sec = rem.tv_sec; + req.tv_nsec = rem.tv_nsec; + } +} + +TEST_F_TIMEOUT(rtc, date_read_loop, READ_LOOP_DURATION_SEC + 2) { + int rc; + long iter_count = 0; + struct rtc_time rtc_tm; + time_t start_rtc_read, prev_rtc_read; + + TH_LOG("Continuously reading RTC time for %ds (with %dms breaks after every read).", + READ_LOOP_DURATION_SEC, READ_LOOP_SLEEP_MS); + + rc = ioctl(self->fd, RTC_RD_TIME, &rtc_tm); + ASSERT_NE(-1, rc); + start_rtc_read = rtc_time_to_timestamp(&rtc_tm); + prev_rtc_read = start_rtc_read; + + do { + time_t rtc_read; + + rc = ioctl(self->fd, RTC_RD_TIME, &rtc_tm); + ASSERT_NE(-1, rc); + + rtc_read = rtc_time_to_timestamp(&rtc_tm); + /* Time should not go backwards */ + ASSERT_LE(prev_rtc_read, rtc_read); + /* Time should not increase more then 1s at a time */ + ASSERT_GE(prev_rtc_read + 1, rtc_read); + + /* Sleep 11ms to avoid killing / overheating the RTC */ + nanosleep_with_retries(READ_LOOP_SLEEP_MS * 1000000); + + prev_rtc_read = rtc_read; + iter_count++; + } while (prev_rtc_read <= start_rtc_read + READ_LOOP_DURATION_SEC); + + TH_LOG("Performed %ld RTC time reads.", iter_count); +} + TEST_F_TIMEOUT(rtc, uie_read, NUM_UIE + 2) { int i, rc, irq = 0; unsigned long data; diff --git a/tools/testing/selftests/rtc/settings b/tools/testing/selftests/rtc/settings index ba4d85f74cd6..0c1a2075d5f3 100644 --- a/tools/testing/selftests/rtc/settings +++ b/tools/testing/selftests/rtc/settings @@ -1 +1 @@ -timeout=90 +timeout=210 diff --git a/tools/testing/selftests/seccomp/Makefile b/tools/testing/selftests/seccomp/Makefile index 0ebfe8b0e147..585f7a0c10cb 100644 --- a/tools/testing/selftests/seccomp/Makefile +++ b/tools/testing/selftests/seccomp/Makefile @@ -1,5 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 -CFLAGS += -Wl,-no-as-needed -Wall +CFLAGS += -Wl,-no-as-needed -Wall -isystem ../../../../usr/include/ LDFLAGS += -lpthread TEST_GEN_PROGS := seccomp_bpf seccomp_benchmark diff --git a/tools/testing/selftests/sgx/Makefile b/tools/testing/selftests/sgx/Makefile index 2956584e1e37..75af864e07b6 100644 --- a/tools/testing/selftests/sgx/Makefile +++ b/tools/testing/selftests/sgx/Makefile @@ -4,7 +4,7 @@ include ../lib.mk .PHONY: all clean -CAN_BUILD_X86_64 := $(shell ../x86/check_cc.sh $(CC) \ +CAN_BUILD_X86_64 := $(shell ../x86/check_cc.sh "$(CC)" \ ../x86/trivial_64bit_program.c) ifndef OBJCOPY diff --git a/tools/testing/selftests/sgx/load.c b/tools/testing/selftests/sgx/load.c index 9d4322c946e2..006b464c8fc9 100644 --- a/tools/testing/selftests/sgx/load.c +++ b/tools/testing/selftests/sgx/load.c @@ -21,7 +21,7 @@ void encl_delete(struct encl *encl) { - struct encl_segment *heap_seg = &encl->segment_tbl[encl->nr_segments - 1]; + struct encl_segment *heap_seg; if (encl->encl_base) munmap((void *)encl->encl_base, encl->encl_size); @@ -32,10 +32,11 @@ void encl_delete(struct encl *encl) if (encl->fd) close(encl->fd); - munmap(heap_seg->src, heap_seg->size); - - if (encl->segment_tbl) + if (encl->segment_tbl) { + heap_seg = &encl->segment_tbl[encl->nr_segments - 1]; + munmap(heap_seg->src, heap_seg->size); free(encl->segment_tbl); + } memset(encl, 0, sizeof(*encl)); } diff --git a/tools/testing/selftests/sgx/main.c b/tools/testing/selftests/sgx/main.c index 370c4995f7c4..dd74fa42302e 100644 --- a/tools/testing/selftests/sgx/main.c +++ b/tools/testing/selftests/sgx/main.c @@ -146,7 +146,8 @@ static bool setup_test_encl(unsigned long heap_size, struct encl *encl, if (!encl_load("test_encl.elf", encl, heap_size)) { encl_delete(encl); - TH_LOG("Failed to load the test enclave.\n"); + TH_LOG("Failed to load the test enclave."); + return false; } if (!encl_measure(encl)) @@ -185,8 +186,6 @@ static bool setup_test_encl(unsigned long heap_size, struct encl *encl, return true; err: - encl_delete(encl); - for (i = 0; i < encl->nr_segments; i++) { seg = &encl->segment_tbl[i]; @@ -205,7 +204,9 @@ err: fclose(maps_file); } - TH_LOG("Failed to initialize the test enclave.\n"); + TH_LOG("Failed to initialize the test enclave."); + + encl_delete(encl); return false; } diff --git a/tools/testing/selftests/tc-testing/tdc_config.py b/tools/testing/selftests/tc-testing/tdc_config.py index ea04f04c173e..ccb0f06ef9e3 100644 --- a/tools/testing/selftests/tc-testing/tdc_config.py +++ b/tools/testing/selftests/tc-testing/tdc_config.py @@ -21,7 +21,7 @@ NAMES = { 'BATCH_FILE': './batch.txt', 'BATCH_DIR': 'tmp', # Length of time in seconds to wait before terminating a command - 'TIMEOUT': 12, + 'TIMEOUT': 24, # Name of the namespace to use 'NS': 'tcut', # Directory containing eBPF test programs diff --git a/tools/testing/selftests/tpm2/tpm2.py b/tools/testing/selftests/tpm2/tpm2.py index f34486cd7342..057a4f49c79d 100644 --- a/tools/testing/selftests/tpm2/tpm2.py +++ b/tools/testing/selftests/tpm2/tpm2.py @@ -56,6 +56,7 @@ TSS2_RESMGR_TPM_RC_LAYER = (11 << TSS2_RC_LAYER_SHIFT) TPM2_CAP_HANDLES = 0x00000001 TPM2_CAP_COMMANDS = 0x00000002 +TPM2_CAP_PCRS = 0x00000005 TPM2_CAP_TPM_PROPERTIES = 0x00000006 TPM2_PT_FIXED = 0x100 @@ -712,3 +713,33 @@ class Client: pt += 1 return handles + + def get_cap_pcrs(self): + pcr_banks = {} + + fmt = '>HII III' + + cmd = struct.pack(fmt, + TPM2_ST_NO_SESSIONS, + struct.calcsize(fmt), + TPM2_CC_GET_CAPABILITY, + TPM2_CAP_PCRS, 0, 1) + rsp = self.send_cmd(cmd)[10:] + _, _, cnt = struct.unpack('>BII', rsp[:9]) + rsp = rsp[9:] + + # items are TPMS_PCR_SELECTION's + for i in range(0, cnt): + hash, sizeOfSelect = struct.unpack('>HB', rsp[:3]) + rsp = rsp[3:] + + pcrSelect = 0 + if sizeOfSelect > 0: + pcrSelect, = struct.unpack('%ds' % sizeOfSelect, + rsp[:sizeOfSelect]) + rsp = rsp[sizeOfSelect:] + pcrSelect = int.from_bytes(pcrSelect, byteorder='big') + + pcr_banks[hash] = pcrSelect + + return pcr_banks diff --git a/tools/testing/selftests/tpm2/tpm2_tests.py b/tools/testing/selftests/tpm2/tpm2_tests.py index 9d764306887b..ffe98b5c8d22 100644 --- a/tools/testing/selftests/tpm2/tpm2_tests.py +++ b/tools/testing/selftests/tpm2/tpm2_tests.py @@ -27,7 +27,17 @@ class SmokeTest(unittest.TestCase): result = self.client.unseal(self.root_key, blob, auth, None) self.assertEqual(data, result) + def determine_bank_alg(self, mask): + pcr_banks = self.client.get_cap_pcrs() + for bank_alg, pcrSelection in pcr_banks.items(): + if pcrSelection & mask == mask: + return bank_alg + return None + def test_seal_with_policy(self): + bank_alg = self.determine_bank_alg(1 << 16) + self.assertIsNotNone(bank_alg) + handle = self.client.start_auth_session(tpm2.TPM2_SE_TRIAL) data = ('X' * 64).encode() @@ -35,7 +45,7 @@ class SmokeTest(unittest.TestCase): pcrs = [16] try: - self.client.policy_pcr(handle, pcrs) + self.client.policy_pcr(handle, pcrs, bank_alg=bank_alg) self.client.policy_password(handle) policy_dig = self.client.get_policy_digest(handle) @@ -47,7 +57,7 @@ class SmokeTest(unittest.TestCase): handle = self.client.start_auth_session(tpm2.TPM2_SE_POLICY) try: - self.client.policy_pcr(handle, pcrs) + self.client.policy_pcr(handle, pcrs, bank_alg=bank_alg) self.client.policy_password(handle) result = self.client.unseal(self.root_key, blob, auth, handle) @@ -72,6 +82,9 @@ class SmokeTest(unittest.TestCase): self.assertEqual(rc, tpm2.TPM2_RC_AUTH_FAIL) def test_unseal_with_wrong_policy(self): + bank_alg = self.determine_bank_alg(1 << 16 | 1 << 1) + self.assertIsNotNone(bank_alg) + handle = self.client.start_auth_session(tpm2.TPM2_SE_TRIAL) data = ('X' * 64).encode() @@ -79,7 +92,7 @@ class SmokeTest(unittest.TestCase): pcrs = [16] try: - self.client.policy_pcr(handle, pcrs) + self.client.policy_pcr(handle, pcrs, bank_alg=bank_alg) self.client.policy_password(handle) policy_dig = self.client.get_policy_digest(handle) @@ -91,13 +104,13 @@ class SmokeTest(unittest.TestCase): # Extend first a PCR that is not part of the policy and try to unseal. # This should succeed. - ds = tpm2.get_digest_size(tpm2.TPM2_ALG_SHA1) - self.client.extend_pcr(1, ('X' * ds).encode()) + ds = tpm2.get_digest_size(bank_alg) + self.client.extend_pcr(1, ('X' * ds).encode(), bank_alg=bank_alg) handle = self.client.start_auth_session(tpm2.TPM2_SE_POLICY) try: - self.client.policy_pcr(handle, pcrs) + self.client.policy_pcr(handle, pcrs, bank_alg=bank_alg) self.client.policy_password(handle) result = self.client.unseal(self.root_key, blob, auth, handle) @@ -109,14 +122,14 @@ class SmokeTest(unittest.TestCase): # Then, extend a PCR that is part of the policy and try to unseal. # This should fail. - self.client.extend_pcr(16, ('X' * ds).encode()) + self.client.extend_pcr(16, ('X' * ds).encode(), bank_alg=bank_alg) handle = self.client.start_auth_session(tpm2.TPM2_SE_POLICY) rc = 0 try: - self.client.policy_pcr(handle, pcrs) + self.client.policy_pcr(handle, pcrs, bank_alg=bank_alg) self.client.policy_password(handle) result = self.client.unseal(self.root_key, blob, auth, handle) @@ -302,3 +315,19 @@ class AsyncTest(unittest.TestCase): log.debug("Calling get_cap in a NON_BLOCKING mode") async_client.get_cap(tpm2.TPM2_CAP_HANDLES, tpm2.HR_LOADED_SESSION) async_client.close() + + def test_flush_invalid_context(self): + log = logging.getLogger(__name__) + log.debug(sys._getframe().f_code.co_name) + + async_client = tpm2.Client(tpm2.Client.FLAG_SPACE | tpm2.Client.FLAG_NONBLOCK) + log.debug("Calling flush_context passing in an invalid handle ") + handle = 0x80123456 + rc = 0 + try: + async_client.flush_context(handle) + except OSError as e: + rc = e.errno + + self.assertEqual(rc, 22) + async_client.close() diff --git a/tools/testing/selftests/user_events/Makefile b/tools/testing/selftests/user_events/Makefile new file mode 100644 index 000000000000..c765d8635d9a --- /dev/null +++ b/tools/testing/selftests/user_events/Makefile @@ -0,0 +1,9 @@ +# SPDX-License-Identifier: GPL-2.0 +CFLAGS += -Wl,-no-as-needed -Wall -I../../../../usr/include +LDLIBS += -lrt -lpthread -lm + +TEST_GEN_PROGS = ftrace_test dyn_test perf_test + +TEST_FILES := settings + +include ../lib.mk diff --git a/tools/testing/selftests/user_events/dyn_test.c b/tools/testing/selftests/user_events/dyn_test.c new file mode 100644 index 000000000000..d6265d14cd51 --- /dev/null +++ b/tools/testing/selftests/user_events/dyn_test.c @@ -0,0 +1,130 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * User Events Dyn Events Test Program + * + * Copyright (c) 2021 Beau Belgrave <beaub@linux.microsoft.com> + */ + +#include <errno.h> +#include <linux/user_events.h> +#include <stdio.h> +#include <stdlib.h> +#include <fcntl.h> +#include <sys/ioctl.h> +#include <sys/stat.h> +#include <unistd.h> + +#include "../kselftest_harness.h" + +const char *dyn_file = "/sys/kernel/debug/tracing/dynamic_events"; +const char *clear = "!u:__test_event"; + +static int Append(const char *value) +{ + int fd = open(dyn_file, O_RDWR | O_APPEND); + int ret = write(fd, value, strlen(value)); + + close(fd); + return ret; +} + +#define CLEAR() \ +do { \ + int ret = Append(clear); \ + if (ret == -1) \ + ASSERT_EQ(ENOENT, errno); \ +} while (0) + +#define TEST_PARSE(x) \ +do { \ + ASSERT_NE(-1, Append(x)); \ + CLEAR(); \ +} while (0) + +#define TEST_NPARSE(x) ASSERT_EQ(-1, Append(x)) + +FIXTURE(user) { +}; + +FIXTURE_SETUP(user) { + CLEAR(); +} + +FIXTURE_TEARDOWN(user) { + CLEAR(); +} + +TEST_F(user, basic_types) { + /* All should work */ + TEST_PARSE("u:__test_event u64 a"); + TEST_PARSE("u:__test_event u32 a"); + TEST_PARSE("u:__test_event u16 a"); + TEST_PARSE("u:__test_event u8 a"); + TEST_PARSE("u:__test_event char a"); + TEST_PARSE("u:__test_event unsigned char a"); + TEST_PARSE("u:__test_event int a"); + TEST_PARSE("u:__test_event unsigned int a"); + TEST_PARSE("u:__test_event short a"); + TEST_PARSE("u:__test_event unsigned short a"); + TEST_PARSE("u:__test_event char[20] a"); + TEST_PARSE("u:__test_event unsigned char[20] a"); + TEST_PARSE("u:__test_event char[0x14] a"); + TEST_PARSE("u:__test_event unsigned char[0x14] a"); + /* Bad size format should fail */ + TEST_NPARSE("u:__test_event char[aa] a"); + /* Large size should fail */ + TEST_NPARSE("u:__test_event char[9999] a"); + /* Long size string should fail */ + TEST_NPARSE("u:__test_event char[0x0000000000001] a"); +} + +TEST_F(user, loc_types) { + /* All should work */ + TEST_PARSE("u:__test_event __data_loc char[] a"); + TEST_PARSE("u:__test_event __data_loc unsigned char[] a"); + TEST_PARSE("u:__test_event __rel_loc char[] a"); + TEST_PARSE("u:__test_event __rel_loc unsigned char[] a"); +} + +TEST_F(user, size_types) { + /* Should work */ + TEST_PARSE("u:__test_event struct custom a 20"); + /* Size not specified on struct should fail */ + TEST_NPARSE("u:__test_event struct custom a"); + /* Size specified on non-struct should fail */ + TEST_NPARSE("u:__test_event char a 20"); +} + +TEST_F(user, flags) { + /* Should work */ + TEST_PARSE("u:__test_event:BPF_ITER u32 a"); + /* Forward compat */ + TEST_PARSE("u:__test_event:BPF_ITER,FLAG_FUTURE u32 a"); +} + +TEST_F(user, matching) { + /* Register */ + ASSERT_NE(-1, Append("u:__test_event struct custom a 20")); + /* Should not match */ + TEST_NPARSE("!u:__test_event struct custom b"); + /* Should match */ + TEST_PARSE("!u:__test_event struct custom a"); + /* Multi field reg */ + ASSERT_NE(-1, Append("u:__test_event u32 a; u32 b")); + /* Non matching cases */ + TEST_NPARSE("!u:__test_event u32 a"); + TEST_NPARSE("!u:__test_event u32 b"); + TEST_NPARSE("!u:__test_event u32 a; u32 "); + TEST_NPARSE("!u:__test_event u32 a; u32 a"); + /* Matching case */ + TEST_PARSE("!u:__test_event u32 a; u32 b"); + /* Register */ + ASSERT_NE(-1, Append("u:__test_event u32 a; u32 b")); + /* Ensure trailing semi-colon case */ + TEST_PARSE("!u:__test_event u32 a; u32 b;"); +} + +int main(int argc, char **argv) +{ + return test_harness_run(argc, argv); +} diff --git a/tools/testing/selftests/user_events/ftrace_test.c b/tools/testing/selftests/user_events/ftrace_test.c new file mode 100644 index 000000000000..a80fb5ef61d5 --- /dev/null +++ b/tools/testing/selftests/user_events/ftrace_test.c @@ -0,0 +1,452 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * User Events FTrace Test Program + * + * Copyright (c) 2021 Beau Belgrave <beaub@linux.microsoft.com> + */ + +#include <errno.h> +#include <linux/user_events.h> +#include <stdio.h> +#include <stdlib.h> +#include <fcntl.h> +#include <sys/ioctl.h> +#include <sys/stat.h> +#include <unistd.h> + +#include "../kselftest_harness.h" + +const char *data_file = "/sys/kernel/debug/tracing/user_events_data"; +const char *status_file = "/sys/kernel/debug/tracing/user_events_status"; +const char *enable_file = "/sys/kernel/debug/tracing/events/user_events/__test_event/enable"; +const char *trace_file = "/sys/kernel/debug/tracing/trace"; +const char *fmt_file = "/sys/kernel/debug/tracing/events/user_events/__test_event/format"; + +static int trace_bytes(void) +{ + int fd = open(trace_file, O_RDONLY); + char buf[256]; + int bytes = 0, got; + + if (fd == -1) + return -1; + + while (true) { + got = read(fd, buf, sizeof(buf)); + + if (got == -1) + return -1; + + if (got == 0) + break; + + bytes += got; + } + + close(fd); + + return bytes; +} + +static int skip_until_empty_line(FILE *fp) +{ + int c, last = 0; + + while (true) { + c = getc(fp); + + if (c == EOF) + break; + + if (last == '\n' && c == '\n') + return 0; + + last = c; + } + + return -1; +} + +static int get_print_fmt(char *buffer, int len) +{ + FILE *fp = fopen(fmt_file, "r"); + char *newline; + + if (!fp) + return -1; + + /* Read until empty line (Skip Common) */ + if (skip_until_empty_line(fp) < 0) + goto err; + + /* Read until empty line (Skip Properties) */ + if (skip_until_empty_line(fp) < 0) + goto err; + + /* Read in print_fmt: */ + if (fgets(buffer, len, fp) == NULL) + goto err; + + newline = strchr(buffer, '\n'); + + if (newline) + *newline = '\0'; + + fclose(fp); + + return 0; +err: + fclose(fp); + + return -1; +} + +static int clear(void) +{ + int fd = open(data_file, O_RDWR); + + if (fd == -1) + return -1; + + if (ioctl(fd, DIAG_IOCSDEL, "__test_event") == -1) + if (errno != ENOENT) + return -1; + + close(fd); + + return 0; +} + +static int check_print_fmt(const char *event, const char *expected) +{ + struct user_reg reg = {0}; + char print_fmt[256]; + int ret; + int fd; + + /* Ensure cleared */ + ret = clear(); + + if (ret != 0) + return ret; + + fd = open(data_file, O_RDWR); + + if (fd == -1) + return fd; + + reg.size = sizeof(reg); + reg.name_args = (__u64)event; + + /* Register should work */ + ret = ioctl(fd, DIAG_IOCSREG, ®); + + close(fd); + + if (ret != 0) + return ret; + + /* Ensure correct print_fmt */ + ret = get_print_fmt(print_fmt, sizeof(print_fmt)); + + if (ret != 0) + return ret; + + return strcmp(print_fmt, expected); +} + +FIXTURE(user) { + int status_fd; + int data_fd; + int enable_fd; +}; + +FIXTURE_SETUP(user) { + self->status_fd = open(status_file, O_RDONLY); + ASSERT_NE(-1, self->status_fd); + + self->data_fd = open(data_file, O_RDWR); + ASSERT_NE(-1, self->data_fd); + + self->enable_fd = -1; +} + +FIXTURE_TEARDOWN(user) { + close(self->status_fd); + close(self->data_fd); + + if (self->enable_fd != -1) { + write(self->enable_fd, "0", sizeof("0")); + close(self->enable_fd); + } + + ASSERT_EQ(0, clear()); +} + +TEST_F(user, register_events) { + struct user_reg reg = {0}; + int page_size = sysconf(_SC_PAGESIZE); + char *status_page; + + reg.size = sizeof(reg); + reg.name_args = (__u64)"__test_event u32 field1; u32 field2"; + + status_page = mmap(NULL, page_size, PROT_READ, MAP_SHARED, + self->status_fd, 0); + + /* Register should work */ + ASSERT_EQ(0, ioctl(self->data_fd, DIAG_IOCSREG, ®)); + ASSERT_EQ(0, reg.write_index); + ASSERT_NE(0, reg.status_index); + + /* Multiple registers should result in same index */ + ASSERT_EQ(0, ioctl(self->data_fd, DIAG_IOCSREG, ®)); + ASSERT_EQ(0, reg.write_index); + ASSERT_NE(0, reg.status_index); + + /* Ensure disabled */ + self->enable_fd = open(enable_file, O_RDWR); + ASSERT_NE(-1, self->enable_fd); + ASSERT_NE(-1, write(self->enable_fd, "0", sizeof("0"))) + + /* MMAP should work and be zero'd */ + ASSERT_NE(MAP_FAILED, status_page); + ASSERT_NE(NULL, status_page); + ASSERT_EQ(0, status_page[reg.status_index]); + + /* Enable event and ensure bits updated in status */ + ASSERT_NE(-1, write(self->enable_fd, "1", sizeof("1"))) + ASSERT_EQ(EVENT_STATUS_FTRACE, status_page[reg.status_index]); + + /* Disable event and ensure bits updated in status */ + ASSERT_NE(-1, write(self->enable_fd, "0", sizeof("0"))) + ASSERT_EQ(0, status_page[reg.status_index]); + + /* File still open should return -EBUSY for delete */ + ASSERT_EQ(-1, ioctl(self->data_fd, DIAG_IOCSDEL, "__test_event")); + ASSERT_EQ(EBUSY, errno); + + /* Delete should work only after close */ + close(self->data_fd); + self->data_fd = open(data_file, O_RDWR); + ASSERT_EQ(0, ioctl(self->data_fd, DIAG_IOCSDEL, "__test_event")); + + /* Unmap should work */ + ASSERT_EQ(0, munmap(status_page, page_size)); +} + +TEST_F(user, write_events) { + struct user_reg reg = {0}; + struct iovec io[3]; + __u32 field1, field2; + int before = 0, after = 0; + + reg.size = sizeof(reg); + reg.name_args = (__u64)"__test_event u32 field1; u32 field2"; + + field1 = 1; + field2 = 2; + + io[0].iov_base = ®.write_index; + io[0].iov_len = sizeof(reg.write_index); + io[1].iov_base = &field1; + io[1].iov_len = sizeof(field1); + io[2].iov_base = &field2; + io[2].iov_len = sizeof(field2); + + /* Register should work */ + ASSERT_EQ(0, ioctl(self->data_fd, DIAG_IOCSREG, ®)); + ASSERT_EQ(0, reg.write_index); + ASSERT_NE(0, reg.status_index); + + /* Write should fail on invalid slot with ENOENT */ + io[0].iov_base = &field2; + io[0].iov_len = sizeof(field2); + ASSERT_EQ(-1, writev(self->data_fd, (const struct iovec *)io, 3)); + ASSERT_EQ(ENOENT, errno); + io[0].iov_base = ®.write_index; + io[0].iov_len = sizeof(reg.write_index); + + /* Enable event */ + self->enable_fd = open(enable_file, O_RDWR); + ASSERT_NE(-1, write(self->enable_fd, "1", sizeof("1"))) + + /* Write should make it out to ftrace buffers */ + before = trace_bytes(); + ASSERT_NE(-1, writev(self->data_fd, (const struct iovec *)io, 3)); + after = trace_bytes(); + ASSERT_GT(after, before); +} + +TEST_F(user, write_fault) { + struct user_reg reg = {0}; + struct iovec io[2]; + int l = sizeof(__u64); + void *anon; + + reg.size = sizeof(reg); + reg.name_args = (__u64)"__test_event u64 anon"; + + anon = mmap(NULL, l, PROT_READ, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); + ASSERT_NE(MAP_FAILED, anon); + + io[0].iov_base = ®.write_index; + io[0].iov_len = sizeof(reg.write_index); + io[1].iov_base = anon; + io[1].iov_len = l; + + /* Register should work */ + ASSERT_EQ(0, ioctl(self->data_fd, DIAG_IOCSREG, ®)); + ASSERT_EQ(0, reg.write_index); + ASSERT_NE(0, reg.status_index); + + /* Write should work normally */ + ASSERT_NE(-1, writev(self->data_fd, (const struct iovec *)io, 2)); + + /* Faulted data should zero fill and work */ + ASSERT_EQ(0, madvise(anon, l, MADV_DONTNEED)); + ASSERT_NE(-1, writev(self->data_fd, (const struct iovec *)io, 2)); + ASSERT_EQ(0, munmap(anon, l)); +} + +TEST_F(user, write_validator) { + struct user_reg reg = {0}; + struct iovec io[3]; + int loc, bytes; + char data[8]; + int before = 0, after = 0; + + reg.size = sizeof(reg); + reg.name_args = (__u64)"__test_event __rel_loc char[] data"; + + /* Register should work */ + ASSERT_EQ(0, ioctl(self->data_fd, DIAG_IOCSREG, ®)); + ASSERT_EQ(0, reg.write_index); + ASSERT_NE(0, reg.status_index); + + io[0].iov_base = ®.write_index; + io[0].iov_len = sizeof(reg.write_index); + io[1].iov_base = &loc; + io[1].iov_len = sizeof(loc); + io[2].iov_base = data; + bytes = snprintf(data, sizeof(data), "Test") + 1; + io[2].iov_len = bytes; + + /* Undersized write should fail */ + ASSERT_EQ(-1, writev(self->data_fd, (const struct iovec *)io, 1)); + ASSERT_EQ(EINVAL, errno); + + /* Enable event */ + self->enable_fd = open(enable_file, O_RDWR); + ASSERT_NE(-1, write(self->enable_fd, "1", sizeof("1"))) + + /* Full in-bounds write should work */ + before = trace_bytes(); + loc = DYN_LOC(0, bytes); + ASSERT_NE(-1, writev(self->data_fd, (const struct iovec *)io, 3)); + after = trace_bytes(); + ASSERT_GT(after, before); + + /* Out of bounds write should fault (offset way out) */ + loc = DYN_LOC(1024, bytes); + ASSERT_EQ(-1, writev(self->data_fd, (const struct iovec *)io, 3)); + ASSERT_EQ(EFAULT, errno); + + /* Out of bounds write should fault (offset 1 byte out) */ + loc = DYN_LOC(1, bytes); + ASSERT_EQ(-1, writev(self->data_fd, (const struct iovec *)io, 3)); + ASSERT_EQ(EFAULT, errno); + + /* Out of bounds write should fault (size way out) */ + loc = DYN_LOC(0, bytes + 1024); + ASSERT_EQ(-1, writev(self->data_fd, (const struct iovec *)io, 3)); + ASSERT_EQ(EFAULT, errno); + + /* Out of bounds write should fault (size 1 byte out) */ + loc = DYN_LOC(0, bytes + 1); + ASSERT_EQ(-1, writev(self->data_fd, (const struct iovec *)io, 3)); + ASSERT_EQ(EFAULT, errno); + + /* Non-Null should fault */ + memset(data, 'A', sizeof(data)); + loc = DYN_LOC(0, bytes); + ASSERT_EQ(-1, writev(self->data_fd, (const struct iovec *)io, 3)); + ASSERT_EQ(EFAULT, errno); +} + +TEST_F(user, print_fmt) { + int ret; + + ret = check_print_fmt("__test_event __rel_loc char[] data", + "print fmt: \"data=%s\", __get_rel_str(data)"); + ASSERT_EQ(0, ret); + + ret = check_print_fmt("__test_event __data_loc char[] data", + "print fmt: \"data=%s\", __get_str(data)"); + ASSERT_EQ(0, ret); + + ret = check_print_fmt("__test_event s64 data", + "print fmt: \"data=%lld\", REC->data"); + ASSERT_EQ(0, ret); + + ret = check_print_fmt("__test_event u64 data", + "print fmt: \"data=%llu\", REC->data"); + ASSERT_EQ(0, ret); + + ret = check_print_fmt("__test_event s32 data", + "print fmt: \"data=%d\", REC->data"); + ASSERT_EQ(0, ret); + + ret = check_print_fmt("__test_event u32 data", + "print fmt: \"data=%u\", REC->data"); + ASSERT_EQ(0, ret); + + ret = check_print_fmt("__test_event int data", + "print fmt: \"data=%d\", REC->data"); + ASSERT_EQ(0, ret); + + ret = check_print_fmt("__test_event unsigned int data", + "print fmt: \"data=%u\", REC->data"); + ASSERT_EQ(0, ret); + + ret = check_print_fmt("__test_event s16 data", + "print fmt: \"data=%d\", REC->data"); + ASSERT_EQ(0, ret); + + ret = check_print_fmt("__test_event u16 data", + "print fmt: \"data=%u\", REC->data"); + ASSERT_EQ(0, ret); + + ret = check_print_fmt("__test_event short data", + "print fmt: \"data=%d\", REC->data"); + ASSERT_EQ(0, ret); + + ret = check_print_fmt("__test_event unsigned short data", + "print fmt: \"data=%u\", REC->data"); + ASSERT_EQ(0, ret); + + ret = check_print_fmt("__test_event s8 data", + "print fmt: \"data=%d\", REC->data"); + ASSERT_EQ(0, ret); + + ret = check_print_fmt("__test_event u8 data", + "print fmt: \"data=%u\", REC->data"); + ASSERT_EQ(0, ret); + + ret = check_print_fmt("__test_event char data", + "print fmt: \"data=%d\", REC->data"); + ASSERT_EQ(0, ret); + + ret = check_print_fmt("__test_event unsigned char data", + "print fmt: \"data=%u\", REC->data"); + ASSERT_EQ(0, ret); + + ret = check_print_fmt("__test_event char[4] data", + "print fmt: \"data=%s\", REC->data"); + ASSERT_EQ(0, ret); +} + +int main(int argc, char **argv) +{ + return test_harness_run(argc, argv); +} diff --git a/tools/testing/selftests/user_events/perf_test.c b/tools/testing/selftests/user_events/perf_test.c new file mode 100644 index 000000000000..26851d51d6bb --- /dev/null +++ b/tools/testing/selftests/user_events/perf_test.c @@ -0,0 +1,168 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * User Events Perf Events Test Program + * + * Copyright (c) 2021 Beau Belgrave <beaub@linux.microsoft.com> + */ + +#include <errno.h> +#include <linux/user_events.h> +#include <linux/perf_event.h> +#include <stdio.h> +#include <stdlib.h> +#include <fcntl.h> +#include <sys/ioctl.h> +#include <sys/stat.h> +#include <unistd.h> +#include <asm/unistd.h> + +#include "../kselftest_harness.h" + +const char *data_file = "/sys/kernel/debug/tracing/user_events_data"; +const char *status_file = "/sys/kernel/debug/tracing/user_events_status"; +const char *id_file = "/sys/kernel/debug/tracing/events/user_events/__test_event/id"; +const char *fmt_file = "/sys/kernel/debug/tracing/events/user_events/__test_event/format"; + +struct event { + __u32 index; + __u32 field1; + __u32 field2; +}; + +static long perf_event_open(struct perf_event_attr *pe, pid_t pid, + int cpu, int group_fd, unsigned long flags) +{ + return syscall(__NR_perf_event_open, pe, pid, cpu, group_fd, flags); +} + +static int get_id(void) +{ + FILE *fp = fopen(id_file, "r"); + int ret, id = 0; + + if (!fp) + return -1; + + ret = fscanf(fp, "%d", &id); + fclose(fp); + + if (ret != 1) + return -1; + + return id; +} + +static int get_offset(void) +{ + FILE *fp = fopen(fmt_file, "r"); + int ret, c, last = 0, offset = 0; + + if (!fp) + return -1; + + /* Read until empty line */ + while (true) { + c = getc(fp); + + if (c == EOF) + break; + + if (last == '\n' && c == '\n') + break; + + last = c; + } + + ret = fscanf(fp, "\tfield:u32 field1;\toffset:%d;", &offset); + fclose(fp); + + if (ret != 1) + return -1; + + return offset; +} + +FIXTURE(user) { + int status_fd; + int data_fd; +}; + +FIXTURE_SETUP(user) { + self->status_fd = open(status_file, O_RDONLY); + ASSERT_NE(-1, self->status_fd); + + self->data_fd = open(data_file, O_RDWR); + ASSERT_NE(-1, self->data_fd); +} + +FIXTURE_TEARDOWN(user) { + close(self->status_fd); + close(self->data_fd); +} + +TEST_F(user, perf_write) { + struct perf_event_attr pe = {0}; + struct user_reg reg = {0}; + int page_size = sysconf(_SC_PAGESIZE); + char *status_page; + struct event event; + struct perf_event_mmap_page *perf_page; + int id, fd, offset; + __u32 *val; + + reg.size = sizeof(reg); + reg.name_args = (__u64)"__test_event u32 field1; u32 field2"; + + status_page = mmap(NULL, page_size, PROT_READ, MAP_SHARED, + self->status_fd, 0); + ASSERT_NE(MAP_FAILED, status_page); + + /* Register should work */ + ASSERT_EQ(0, ioctl(self->data_fd, DIAG_IOCSREG, ®)); + ASSERT_EQ(0, reg.write_index); + ASSERT_NE(0, reg.status_index); + ASSERT_EQ(0, status_page[reg.status_index]); + + /* Id should be there */ + id = get_id(); + ASSERT_NE(-1, id); + offset = get_offset(); + ASSERT_NE(-1, offset); + + pe.type = PERF_TYPE_TRACEPOINT; + pe.size = sizeof(pe); + pe.config = id; + pe.sample_type = PERF_SAMPLE_RAW; + pe.sample_period = 1; + pe.wakeup_events = 1; + + /* Tracepoint attach should work */ + fd = perf_event_open(&pe, 0, -1, -1, 0); + ASSERT_NE(-1, fd); + + perf_page = mmap(NULL, page_size * 2, PROT_READ, MAP_SHARED, fd, 0); + ASSERT_NE(MAP_FAILED, perf_page); + + /* Status should be updated */ + ASSERT_EQ(EVENT_STATUS_PERF, status_page[reg.status_index]); + + event.index = reg.write_index; + event.field1 = 0xc001; + event.field2 = 0xc01a; + + /* Ensure write shows up at correct offset */ + ASSERT_NE(-1, write(self->data_fd, &event, sizeof(event))); + val = (void *)(((char *)perf_page) + perf_page->data_offset); + ASSERT_EQ(PERF_RECORD_SAMPLE, *val); + /* Skip over header and size, move to offset */ + val += 3; + val = (void *)((char *)val) + offset; + /* Ensure correct */ + ASSERT_EQ(event.field1, *val++); + ASSERT_EQ(event.field2, *val++); +} + +int main(int argc, char **argv) +{ + return test_harness_run(argc, argv); +} diff --git a/tools/testing/selftests/user_events/settings b/tools/testing/selftests/user_events/settings new file mode 100644 index 000000000000..ba4d85f74cd6 --- /dev/null +++ b/tools/testing/selftests/user_events/settings @@ -0,0 +1 @@ +timeout=90 diff --git a/tools/testing/selftests/vDSO/vdso_config.h b/tools/testing/selftests/vDSO/vdso_config.h index 6188b16827d1..cdfed403ba13 100644 --- a/tools/testing/selftests/vDSO/vdso_config.h +++ b/tools/testing/selftests/vDSO/vdso_config.h @@ -53,10 +53,6 @@ #if __riscv_xlen == 32 #define VDSO_32BIT 1 #endif -#else /* nds32 */ -#define VDSO_VERSION 4 -#define VDSO_NAMES 1 -#define VDSO_32BIT 1 #endif static const char *versions[6] = { diff --git a/tools/testing/selftests/vDSO/vdso_test_abi.c b/tools/testing/selftests/vDSO/vdso_test_abi.c index 3d603f1394af..883ca85424bc 100644 --- a/tools/testing/selftests/vDSO/vdso_test_abi.c +++ b/tools/testing/selftests/vDSO/vdso_test_abi.c @@ -33,110 +33,114 @@ typedef long (*vdso_clock_gettime_t)(clockid_t clk_id, struct timespec *ts); typedef long (*vdso_clock_getres_t)(clockid_t clk_id, struct timespec *ts); typedef time_t (*vdso_time_t)(time_t *t); -static int vdso_test_gettimeofday(void) +#define VDSO_TEST_PASS_MSG() "\n%s(): PASS\n", __func__ +#define VDSO_TEST_FAIL_MSG(x) "\n%s(): %s FAIL\n", __func__, x +#define VDSO_TEST_SKIP_MSG(x) "\n%s(): SKIP: Could not find %s\n", __func__, x + +static void vdso_test_gettimeofday(void) { /* Find gettimeofday. */ vdso_gettimeofday_t vdso_gettimeofday = (vdso_gettimeofday_t)vdso_sym(version, name[0]); if (!vdso_gettimeofday) { - printf("Could not find %s\n", name[0]); - return KSFT_SKIP; + ksft_test_result_skip(VDSO_TEST_SKIP_MSG(name[0])); + return; } struct timeval tv; long ret = vdso_gettimeofday(&tv, 0); if (ret == 0) { - printf("The time is %lld.%06lld\n", - (long long)tv.tv_sec, (long long)tv.tv_usec); + ksft_print_msg("The time is %lld.%06lld\n", + (long long)tv.tv_sec, (long long)tv.tv_usec); + ksft_test_result_pass(VDSO_TEST_PASS_MSG()); } else { - printf("%s failed\n", name[0]); - return KSFT_FAIL; + ksft_test_result_fail(VDSO_TEST_FAIL_MSG(name[0])); } - - return KSFT_PASS; } -static int vdso_test_clock_gettime(clockid_t clk_id) +static void vdso_test_clock_gettime(clockid_t clk_id) { /* Find clock_gettime. */ vdso_clock_gettime_t vdso_clock_gettime = (vdso_clock_gettime_t)vdso_sym(version, name[1]); if (!vdso_clock_gettime) { - printf("Could not find %s\n", name[1]); - return KSFT_SKIP; + ksft_test_result_skip(VDSO_TEST_SKIP_MSG(name[1])); + return; } struct timespec ts; long ret = vdso_clock_gettime(clk_id, &ts); if (ret == 0) { - printf("The time is %lld.%06lld\n", - (long long)ts.tv_sec, (long long)ts.tv_nsec); + ksft_print_msg("The time is %lld.%06lld\n", + (long long)ts.tv_sec, (long long)ts.tv_nsec); + ksft_test_result_pass(VDSO_TEST_PASS_MSG()); } else { - printf("%s failed\n", name[1]); - return KSFT_FAIL; + ksft_test_result_fail(VDSO_TEST_FAIL_MSG(name[1])); } - - return KSFT_PASS; } -static int vdso_test_time(void) +static void vdso_test_time(void) { /* Find time. */ vdso_time_t vdso_time = (vdso_time_t)vdso_sym(version, name[2]); if (!vdso_time) { - printf("Could not find %s\n", name[2]); - return KSFT_SKIP; + ksft_test_result_skip(VDSO_TEST_SKIP_MSG(name[2])); + return; } long ret = vdso_time(NULL); if (ret > 0) { - printf("The time in hours since January 1, 1970 is %lld\n", + ksft_print_msg("The time in hours since January 1, 1970 is %lld\n", (long long)(ret / 3600)); + ksft_test_result_pass(VDSO_TEST_PASS_MSG()); } else { - printf("%s failed\n", name[2]); - return KSFT_FAIL; + ksft_test_result_fail(VDSO_TEST_FAIL_MSG(name[2])); } - - return KSFT_PASS; } -static int vdso_test_clock_getres(clockid_t clk_id) +static void vdso_test_clock_getres(clockid_t clk_id) { + int clock_getres_fail = 0; + /* Find clock_getres. */ vdso_clock_getres_t vdso_clock_getres = (vdso_clock_getres_t)vdso_sym(version, name[3]); if (!vdso_clock_getres) { - printf("Could not find %s\n", name[3]); - return KSFT_SKIP; + ksft_test_result_skip(VDSO_TEST_SKIP_MSG(name[3])); + return; } struct timespec ts, sys_ts; long ret = vdso_clock_getres(clk_id, &ts); if (ret == 0) { - printf("The resolution is %lld %lld\n", - (long long)ts.tv_sec, (long long)ts.tv_nsec); + ksft_print_msg("The vdso resolution is %lld %lld\n", + (long long)ts.tv_sec, (long long)ts.tv_nsec); } else { - printf("%s failed\n", name[3]); - return KSFT_FAIL; + clock_getres_fail++; } ret = syscall(SYS_clock_getres, clk_id, &sys_ts); - if ((sys_ts.tv_sec != ts.tv_sec) || (sys_ts.tv_nsec != ts.tv_nsec)) { - printf("%s failed\n", name[3]); - return KSFT_FAIL; - } + ksft_print_msg("The syscall resolution is %lld %lld\n", + (long long)sys_ts.tv_sec, (long long)sys_ts.tv_nsec); - return KSFT_PASS; + if ((sys_ts.tv_sec != ts.tv_sec) || (sys_ts.tv_nsec != ts.tv_nsec)) + clock_getres_fail++; + + if (clock_getres_fail > 0) { + ksft_test_result_fail(VDSO_TEST_FAIL_MSG(name[3])); + } else { + ksft_test_result_pass(VDSO_TEST_PASS_MSG()); + } } const char *vdso_clock_name[12] = { @@ -158,36 +162,23 @@ const char *vdso_clock_name[12] = { * This function calls vdso_test_clock_gettime and vdso_test_clock_getres * with different values for clock_id. */ -static inline int vdso_test_clock(clockid_t clock_id) +static inline void vdso_test_clock(clockid_t clock_id) { - int ret0, ret1; - - ret0 = vdso_test_clock_gettime(clock_id); - /* A skipped test is considered passed */ - if (ret0 == KSFT_SKIP) - ret0 = KSFT_PASS; - - ret1 = vdso_test_clock_getres(clock_id); - /* A skipped test is considered passed */ - if (ret1 == KSFT_SKIP) - ret1 = KSFT_PASS; + ksft_print_msg("\nclock_id: %s\n", vdso_clock_name[clock_id]); - ret0 += ret1; + vdso_test_clock_gettime(clock_id); - printf("clock_id: %s", vdso_clock_name[clock_id]); - - if (ret0 > 0) - printf(" [FAIL]\n"); - else - printf(" [PASS]\n"); - - return ret0; + vdso_test_clock_getres(clock_id); } +#define VDSO_TEST_PLAN 16 + int main(int argc, char **argv) { unsigned long sysinfo_ehdr = getauxval(AT_SYSINFO_EHDR); - int ret; + + ksft_print_header(); + ksft_set_plan(VDSO_TEST_PLAN); if (!sysinfo_ehdr) { printf("AT_SYSINFO_EHDR is not present!\n"); @@ -201,44 +192,42 @@ int main(int argc, char **argv) vdso_init_from_sysinfo_ehdr(getauxval(AT_SYSINFO_EHDR)); - ret = vdso_test_gettimeofday(); + vdso_test_gettimeofday(); #if _POSIX_TIMERS > 0 #ifdef CLOCK_REALTIME - ret += vdso_test_clock(CLOCK_REALTIME); + vdso_test_clock(CLOCK_REALTIME); #endif #ifdef CLOCK_BOOTTIME - ret += vdso_test_clock(CLOCK_BOOTTIME); + vdso_test_clock(CLOCK_BOOTTIME); #endif #ifdef CLOCK_TAI - ret += vdso_test_clock(CLOCK_TAI); + vdso_test_clock(CLOCK_TAI); #endif #ifdef CLOCK_REALTIME_COARSE - ret += vdso_test_clock(CLOCK_REALTIME_COARSE); + vdso_test_clock(CLOCK_REALTIME_COARSE); #endif #ifdef CLOCK_MONOTONIC - ret += vdso_test_clock(CLOCK_MONOTONIC); + vdso_test_clock(CLOCK_MONOTONIC); #endif #ifdef CLOCK_MONOTONIC_RAW - ret += vdso_test_clock(CLOCK_MONOTONIC_RAW); + vdso_test_clock(CLOCK_MONOTONIC_RAW); #endif #ifdef CLOCK_MONOTONIC_COARSE - ret += vdso_test_clock(CLOCK_MONOTONIC_COARSE); + vdso_test_clock(CLOCK_MONOTONIC_COARSE); #endif #endif - ret += vdso_test_time(); - - if (ret > 0) - return KSFT_FAIL; + vdso_test_time(); - return KSFT_PASS; + ksft_print_cnts(); + return ksft_get_fail_cnt() == 0 ? KSFT_PASS : KSFT_FAIL; } diff --git a/tools/testing/selftests/vm/.gitignore b/tools/testing/selftests/vm/.gitignore index 2e7e86e85282..d7507f3c7c76 100644 --- a/tools/testing/selftests/vm/.gitignore +++ b/tools/testing/selftests/vm/.gitignore @@ -2,6 +2,8 @@ hugepage-mmap hugepage-mremap hugepage-shm +hugepage-vmemmap +hugetlb-madvise khugepaged map_hugetlb map_populate diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile index 1607322a112c..04a49e876a46 100644 --- a/tools/testing/selftests/vm/Makefile +++ b/tools/testing/selftests/vm/Makefile @@ -1,6 +1,8 @@ # SPDX-License-Identifier: GPL-2.0 # Makefile for vm selftests +LOCAL_HDRS += $(selfdir)/vm/local_config.h $(top_srcdir)/mm/gup_test.h + include local_config.mk uname_M := $(shell uname -m 2>/dev/null || echo not) @@ -23,14 +25,16 @@ MACHINE ?= $(shell echo $(uname_M) | sed -e 's/aarch64.*/arm64/' -e 's/ppc64.*/p # LDLIBS. MAKEFLAGS += --no-builtin-rules -CFLAGS = -Wall -I ../../../../usr/include $(EXTRA_CFLAGS) +CFLAGS = -Wall -I ../../../../usr/include $(EXTRA_CFLAGS) $(KHDR_INCLUDES) LDLIBS = -lrt -lpthread TEST_GEN_FILES = compaction_test TEST_GEN_FILES += gup_test TEST_GEN_FILES += hmm-tests +TEST_GEN_FILES += hugetlb-madvise TEST_GEN_FILES += hugepage-mmap TEST_GEN_FILES += hugepage-mremap TEST_GEN_FILES += hugepage-shm +TEST_GEN_FILES += hugepage-vmemmap TEST_GEN_FILES += khugepaged TEST_GEN_FILES += madv_populate TEST_GEN_FILES += map_fixed_noreplace @@ -49,9 +53,9 @@ TEST_GEN_FILES += split_huge_page_test TEST_GEN_FILES += ksm_tests ifeq ($(MACHINE),x86_64) -CAN_BUILD_I386 := $(shell ./../x86/check_cc.sh $(CC) ../x86/trivial_32bit_program.c -m32) -CAN_BUILD_X86_64 := $(shell ./../x86/check_cc.sh $(CC) ../x86/trivial_64bit_program.c) -CAN_BUILD_WITH_NOPIE := $(shell ./../x86/check_cc.sh $(CC) ../x86/trivial_program.c -no-pie) +CAN_BUILD_I386 := $(shell ./../x86/check_cc.sh "$(CC)" ../x86/trivial_32bit_program.c -m32) +CAN_BUILD_X86_64 := $(shell ./../x86/check_cc.sh "$(CC)" ../x86/trivial_64bit_program.c) +CAN_BUILD_WITH_NOPIE := $(shell ./../x86/check_cc.sh "$(CC)" ../x86/trivial_program.c -no-pie) TARGETS := protection_keys BINARIES_32 := $(TARGETS:%=%_32) @@ -140,10 +144,6 @@ endif $(OUTPUT)/mlock-random-test $(OUTPUT)/memfd_secret: LDLIBS += -lcap -$(OUTPUT)/gup_test: ../../../../mm/gup_test.h - -$(OUTPUT)/hmm-tests: local_config.h - # HMM_EXTRA_LIBS may get set in local_config.mk, or it may be left empty. $(OUTPUT)/hmm-tests: LDLIBS += $(HMM_EXTRA_LIBS) diff --git a/tools/testing/selftests/vm/gup_test.c b/tools/testing/selftests/vm/gup_test.c index fe043f67798b..cda837a14736 100644 --- a/tools/testing/selftests/vm/gup_test.c +++ b/tools/testing/selftests/vm/gup_test.c @@ -10,8 +10,9 @@ #include <assert.h> #include "../../../../mm/gup_test.h" +#include "util.h" + #define MB (1UL << 20) -#define PAGE_SIZE sysconf(_SC_PAGESIZE) /* Just the flags we need, copied from mm.h: */ #define FOLL_WRITE 0x01 /* check pte is writable */ diff --git a/tools/testing/selftests/vm/hugepage-mremap.c b/tools/testing/selftests/vm/hugepage-mremap.c index 2a7c33631a29..1d689084a54b 100644 --- a/tools/testing/selftests/vm/hugepage-mremap.c +++ b/tools/testing/selftests/vm/hugepage-mremap.c @@ -3,9 +3,10 @@ * hugepage-mremap: * * Example of remapping huge page memory in a user application using the - * mremap system call. Code assumes a hugetlbfs filesystem is mounted - * at './huge'. The amount of memory used by this test is decided by a command - * line argument in MBs. If missing, the default amount is 10MB. + * mremap system call. The path to a file in a hugetlbfs filesystem must + * be passed as the last argument to this test. The amount of memory used + * by this test in MBs can optionally be passed as an argument. If no memory + * amount is passed, the default amount is 10MB. * * To make sure the test triggers pmd sharing and goes through the 'unshare' * path in the mremap code use 1GB (1024) or more. @@ -25,7 +26,6 @@ #define DEFAULT_LENGTH_MB 10UL #define MB_TO_BYTES(x) (x * 1024 * 1024) -#define FILE_NAME "huge/hugepagefile" #define PROTECTION (PROT_READ | PROT_WRITE | PROT_EXEC) #define FLAGS (MAP_SHARED | MAP_ANONYMOUS) @@ -107,17 +107,26 @@ static void register_region_with_uffd(char *addr, size_t len) int main(int argc, char *argv[]) { + size_t length; + + if (argc != 2 && argc != 3) { + printf("Usage: %s [length_in_MB] <hugetlb_file>\n", argv[0]); + exit(1); + } + /* Read memory length as the first arg if valid, otherwise fallback to - * the default length. Any additional args are ignored. + * the default length. */ - size_t length = argc > 1 ? (size_t)atoi(argv[1]) : 0UL; + if (argc == 3) + length = argc > 2 ? (size_t)atoi(argv[1]) : 0UL; length = length > 0 ? length : DEFAULT_LENGTH_MB; length = MB_TO_BYTES(length); int ret = 0; - int fd = open(FILE_NAME, O_CREAT | O_RDWR, 0755); + /* last arg is the hugetlb file name */ + int fd = open(argv[argc-1], O_CREAT | O_RDWR, 0755); if (fd < 0) { perror("Open failed"); @@ -169,5 +178,8 @@ int main(int argc, char *argv[]) munmap(addr, length); + close(fd); + unlink(argv[argc-1]); + return ret; } diff --git a/tools/testing/selftests/vm/hugepage-vmemmap.c b/tools/testing/selftests/vm/hugepage-vmemmap.c new file mode 100644 index 000000000000..557bdbd4f87e --- /dev/null +++ b/tools/testing/selftests/vm/hugepage-vmemmap.c @@ -0,0 +1,144 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * A test case of using hugepage memory in a user application using the + * mmap system call with MAP_HUGETLB flag. Before running this program + * make sure the administrator has allocated enough default sized huge + * pages to cover the 2 MB allocation. + */ +#include <stdlib.h> +#include <stdio.h> +#include <unistd.h> +#include <sys/mman.h> +#include <fcntl.h> + +#define MAP_LENGTH (2UL * 1024 * 1024) + +#ifndef MAP_HUGETLB +#define MAP_HUGETLB 0x40000 /* arch specific */ +#endif + +#define PAGE_SIZE 4096 + +#define PAGE_COMPOUND_HEAD (1UL << 15) +#define PAGE_COMPOUND_TAIL (1UL << 16) +#define PAGE_HUGE (1UL << 17) + +#define HEAD_PAGE_FLAGS (PAGE_COMPOUND_HEAD | PAGE_HUGE) +#define TAIL_PAGE_FLAGS (PAGE_COMPOUND_TAIL | PAGE_HUGE) + +#define PM_PFRAME_BITS 55 +#define PM_PFRAME_MASK ~((1UL << PM_PFRAME_BITS) - 1) + +/* + * For ia64 architecture, Linux kernel reserves Region number 4 for hugepages. + * That means the addresses starting with 0x800000... will need to be + * specified. Specifying a fixed address is not required on ppc64, i386 + * or x86_64. + */ +#ifdef __ia64__ +#define MAP_ADDR (void *)(0x8000000000000000UL) +#define MAP_FLAGS (MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB | MAP_FIXED) +#else +#define MAP_ADDR NULL +#define MAP_FLAGS (MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB) +#endif + +static void write_bytes(char *addr, size_t length) +{ + unsigned long i; + + for (i = 0; i < length; i++) + *(addr + i) = (char)i; +} + +static unsigned long virt_to_pfn(void *addr) +{ + int fd; + unsigned long pagemap; + + fd = open("/proc/self/pagemap", O_RDONLY); + if (fd < 0) + return -1UL; + + lseek(fd, (unsigned long)addr / PAGE_SIZE * sizeof(pagemap), SEEK_SET); + read(fd, &pagemap, sizeof(pagemap)); + close(fd); + + return pagemap & ~PM_PFRAME_MASK; +} + +static int check_page_flags(unsigned long pfn) +{ + int fd, i; + unsigned long pageflags; + + fd = open("/proc/kpageflags", O_RDONLY); + if (fd < 0) + return -1; + + lseek(fd, pfn * sizeof(pageflags), SEEK_SET); + + read(fd, &pageflags, sizeof(pageflags)); + if ((pageflags & HEAD_PAGE_FLAGS) != HEAD_PAGE_FLAGS) { + close(fd); + printf("Head page flags (%lx) is invalid\n", pageflags); + return -1; + } + + /* + * pages other than the first page must be tail and shouldn't be head; + * this also verifies kernel has correctly set the fake page_head to tail + * while hugetlb_free_vmemmap is enabled. + */ + for (i = 1; i < MAP_LENGTH / PAGE_SIZE; i++) { + read(fd, &pageflags, sizeof(pageflags)); + if ((pageflags & TAIL_PAGE_FLAGS) != TAIL_PAGE_FLAGS || + (pageflags & HEAD_PAGE_FLAGS) == HEAD_PAGE_FLAGS) { + close(fd); + printf("Tail page flags (%lx) is invalid\n", pageflags); + return -1; + } + } + + close(fd); + + return 0; +} + +int main(int argc, char **argv) +{ + void *addr; + unsigned long pfn; + + addr = mmap(MAP_ADDR, MAP_LENGTH, PROT_READ | PROT_WRITE, MAP_FLAGS, -1, 0); + if (addr == MAP_FAILED) { + perror("mmap"); + exit(1); + } + + /* Trigger allocation of HugeTLB page. */ + write_bytes(addr, MAP_LENGTH); + + pfn = virt_to_pfn(addr); + if (pfn == -1UL) { + munmap(addr, MAP_LENGTH); + perror("virt_to_pfn"); + exit(1); + } + + printf("Returned address is %p whose pfn is %lx\n", addr, pfn); + + if (check_page_flags(pfn) < 0) { + munmap(addr, MAP_LENGTH); + perror("check_page_flags"); + exit(1); + } + + /* munmap() length of MAP_HUGETLB memory must be hugepage aligned */ + if (munmap(addr, MAP_LENGTH)) { + perror("munmap"); + exit(1); + } + + return 0; +} diff --git a/tools/testing/selftests/vm/hugetlb-madvise.c b/tools/testing/selftests/vm/hugetlb-madvise.c new file mode 100644 index 000000000000..6c6af40f5747 --- /dev/null +++ b/tools/testing/selftests/vm/hugetlb-madvise.c @@ -0,0 +1,410 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * hugepage-madvise: + * + * Basic functional testing of madvise MADV_DONTNEED and MADV_REMOVE + * on hugetlb mappings. + * + * Before running this test, make sure the administrator has pre-allocated + * at least MIN_FREE_PAGES hugetlb pages and they are free. In addition, + * the test takes an argument that is the path to a file in a hugetlbfs + * filesystem. Therefore, a hugetlbfs filesystem must be mounted on some + * directory. + */ + +#include <stdlib.h> +#include <stdio.h> +#include <unistd.h> +#include <sys/mman.h> +#define __USE_GNU +#include <fcntl.h> + +#define USAGE "USAGE: %s <hugepagefile_name>\n" +#define MIN_FREE_PAGES 20 +#define NR_HUGE_PAGES 10 /* common number of pages to map/allocate */ + +#define validate_free_pages(exp_free) \ + do { \ + int fhp = get_free_hugepages(); \ + if (fhp != (exp_free)) { \ + printf("Unexpected number of free huge " \ + "pages line %d\n", __LINE__); \ + exit(1); \ + } \ + } while (0) + +unsigned long huge_page_size; +unsigned long base_page_size; + +/* + * default_huge_page_size copied from mlock2-tests.c + */ +unsigned long default_huge_page_size(void) +{ + unsigned long hps = 0; + char *line = NULL; + size_t linelen = 0; + FILE *f = fopen("/proc/meminfo", "r"); + + if (!f) + return 0; + while (getline(&line, &linelen, f) > 0) { + if (sscanf(line, "Hugepagesize: %lu kB", &hps) == 1) { + hps <<= 10; + break; + } + } + + free(line); + fclose(f); + return hps; +} + +unsigned long get_free_hugepages(void) +{ + unsigned long fhp = 0; + char *line = NULL; + size_t linelen = 0; + FILE *f = fopen("/proc/meminfo", "r"); + + if (!f) + return fhp; + while (getline(&line, &linelen, f) > 0) { + if (sscanf(line, "HugePages_Free: %lu", &fhp) == 1) + break; + } + + free(line); + fclose(f); + return fhp; +} + +void write_fault_pages(void *addr, unsigned long nr_pages) +{ + unsigned long i; + + for (i = 0; i < nr_pages; i++) + *((unsigned long *)(addr + (i * huge_page_size))) = i; +} + +void read_fault_pages(void *addr, unsigned long nr_pages) +{ + unsigned long i, tmp; + + for (i = 0; i < nr_pages; i++) + tmp += *((unsigned long *)(addr + (i * huge_page_size))); +} + +int main(int argc, char **argv) +{ + unsigned long free_hugepages; + void *addr, *addr2; + int fd; + int ret; + + if (argc != 2) { + printf(USAGE, argv[0]); + exit(1); + } + + huge_page_size = default_huge_page_size(); + if (!huge_page_size) { + printf("Unable to determine huge page size, exiting!\n"); + exit(1); + } + base_page_size = sysconf(_SC_PAGE_SIZE); + if (!huge_page_size) { + printf("Unable to determine base page size, exiting!\n"); + exit(1); + } + + free_hugepages = get_free_hugepages(); + if (free_hugepages < MIN_FREE_PAGES) { + printf("Not enough free huge pages to test, exiting!\n"); + exit(1); + } + + fd = open(argv[1], O_CREAT | O_RDWR, 0755); + if (fd < 0) { + perror("Open failed"); + exit(1); + } + + /* + * Test validity of MADV_DONTNEED addr and length arguments. mmap + * size is NR_HUGE_PAGES + 2. One page at the beginning and end of + * the mapping will be unmapped so we KNOW there is nothing mapped + * there. + */ + addr = mmap(NULL, (NR_HUGE_PAGES + 2) * huge_page_size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB, + -1, 0); + if (addr == MAP_FAILED) { + perror("mmap"); + exit(1); + } + if (munmap(addr, huge_page_size) || + munmap(addr + (NR_HUGE_PAGES + 1) * huge_page_size, + huge_page_size)) { + perror("munmap"); + exit(1); + } + addr = addr + huge_page_size; + + write_fault_pages(addr, NR_HUGE_PAGES); + validate_free_pages(free_hugepages - NR_HUGE_PAGES); + + /* addr before mapping should fail */ + ret = madvise(addr - base_page_size, NR_HUGE_PAGES * huge_page_size, + MADV_DONTNEED); + if (!ret) { + printf("Unexpected success of madvise call with invalid addr line %d\n", + __LINE__); + exit(1); + } + + /* addr + length after mapping should fail */ + ret = madvise(addr, (NR_HUGE_PAGES * huge_page_size) + base_page_size, + MADV_DONTNEED); + if (!ret) { + printf("Unexpected success of madvise call with invalid length line %d\n", + __LINE__); + exit(1); + } + + (void)munmap(addr, NR_HUGE_PAGES * huge_page_size); + + /* + * Test alignment of MADV_DONTNEED addr and length arguments + */ + addr = mmap(NULL, NR_HUGE_PAGES * huge_page_size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB, + -1, 0); + if (addr == MAP_FAILED) { + perror("mmap"); + exit(1); + } + write_fault_pages(addr, NR_HUGE_PAGES); + validate_free_pages(free_hugepages - NR_HUGE_PAGES); + + /* addr is not huge page size aligned and should fail */ + ret = madvise(addr + base_page_size, + NR_HUGE_PAGES * huge_page_size - base_page_size, + MADV_DONTNEED); + if (!ret) { + printf("Unexpected success of madvise call with unaligned start address %d\n", + __LINE__); + exit(1); + } + + /* addr + length should be aligned up to huge page size */ + if (madvise(addr, + ((NR_HUGE_PAGES - 1) * huge_page_size) + base_page_size, + MADV_DONTNEED)) { + perror("madvise"); + exit(1); + } + + /* should free all pages in mapping */ + validate_free_pages(free_hugepages); + + (void)munmap(addr, NR_HUGE_PAGES * huge_page_size); + + /* + * Test MADV_DONTNEED on anonymous private mapping + */ + addr = mmap(NULL, NR_HUGE_PAGES * huge_page_size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB, + -1, 0); + if (addr == MAP_FAILED) { + perror("mmap"); + exit(1); + } + write_fault_pages(addr, NR_HUGE_PAGES); + validate_free_pages(free_hugepages - NR_HUGE_PAGES); + + if (madvise(addr, NR_HUGE_PAGES * huge_page_size, MADV_DONTNEED)) { + perror("madvise"); + exit(1); + } + + /* should free all pages in mapping */ + validate_free_pages(free_hugepages); + + (void)munmap(addr, NR_HUGE_PAGES * huge_page_size); + + /* + * Test MADV_DONTNEED on private mapping of hugetlb file + */ + if (fallocate(fd, 0, 0, NR_HUGE_PAGES * huge_page_size)) { + perror("fallocate"); + exit(1); + } + validate_free_pages(free_hugepages - NR_HUGE_PAGES); + + addr = mmap(NULL, NR_HUGE_PAGES * huge_page_size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE, fd, 0); + if (addr == MAP_FAILED) { + perror("mmap"); + exit(1); + } + + /* read should not consume any pages */ + read_fault_pages(addr, NR_HUGE_PAGES); + validate_free_pages(free_hugepages - NR_HUGE_PAGES); + + /* madvise should not free any pages */ + if (madvise(addr, NR_HUGE_PAGES * huge_page_size, MADV_DONTNEED)) { + perror("madvise"); + exit(1); + } + validate_free_pages(free_hugepages - NR_HUGE_PAGES); + + /* writes should allocate private pages */ + write_fault_pages(addr, NR_HUGE_PAGES); + validate_free_pages(free_hugepages - (2 * NR_HUGE_PAGES)); + + /* madvise should free private pages */ + if (madvise(addr, NR_HUGE_PAGES * huge_page_size, MADV_DONTNEED)) { + perror("madvise"); + exit(1); + } + validate_free_pages(free_hugepages - NR_HUGE_PAGES); + + /* writes should allocate private pages */ + write_fault_pages(addr, NR_HUGE_PAGES); + validate_free_pages(free_hugepages - (2 * NR_HUGE_PAGES)); + + /* + * The fallocate below certainly should free the pages associated + * with the file. However, pages in the private mapping are also + * freed. This is not the 'correct' behavior, but is expected + * because this is how it has worked since the initial hugetlb + * implementation. + */ + if (fallocate(fd, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, + 0, NR_HUGE_PAGES * huge_page_size)) { + perror("fallocate"); + exit(1); + } + validate_free_pages(free_hugepages); + + (void)munmap(addr, NR_HUGE_PAGES * huge_page_size); + + /* + * Test MADV_DONTNEED on shared mapping of hugetlb file + */ + if (fallocate(fd, 0, 0, NR_HUGE_PAGES * huge_page_size)) { + perror("fallocate"); + exit(1); + } + validate_free_pages(free_hugepages - NR_HUGE_PAGES); + + addr = mmap(NULL, NR_HUGE_PAGES * huge_page_size, + PROT_READ | PROT_WRITE, + MAP_SHARED, fd, 0); + if (addr == MAP_FAILED) { + perror("mmap"); + exit(1); + } + + /* write should not consume any pages */ + write_fault_pages(addr, NR_HUGE_PAGES); + validate_free_pages(free_hugepages - NR_HUGE_PAGES); + + /* madvise should not free any pages */ + if (madvise(addr, NR_HUGE_PAGES * huge_page_size, MADV_DONTNEED)) { + perror("madvise"); + exit(1); + } + validate_free_pages(free_hugepages - NR_HUGE_PAGES); + + /* + * Test MADV_REMOVE on shared mapping of hugetlb file + * + * madvise is same as hole punch and should free all pages. + */ + if (madvise(addr, NR_HUGE_PAGES * huge_page_size, MADV_REMOVE)) { + perror("madvise"); + exit(1); + } + validate_free_pages(free_hugepages); + (void)munmap(addr, NR_HUGE_PAGES * huge_page_size); + + /* + * Test MADV_REMOVE on shared and private mapping of hugetlb file + */ + if (fallocate(fd, 0, 0, NR_HUGE_PAGES * huge_page_size)) { + perror("fallocate"); + exit(1); + } + validate_free_pages(free_hugepages - NR_HUGE_PAGES); + + addr = mmap(NULL, NR_HUGE_PAGES * huge_page_size, + PROT_READ | PROT_WRITE, + MAP_SHARED, fd, 0); + if (addr == MAP_FAILED) { + perror("mmap"); + exit(1); + } + + /* shared write should not consume any additional pages */ + write_fault_pages(addr, NR_HUGE_PAGES); + validate_free_pages(free_hugepages - NR_HUGE_PAGES); + + addr2 = mmap(NULL, NR_HUGE_PAGES * huge_page_size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE, fd, 0); + if (addr2 == MAP_FAILED) { + perror("mmap"); + exit(1); + } + + /* private read should not consume any pages */ + read_fault_pages(addr2, NR_HUGE_PAGES); + validate_free_pages(free_hugepages - NR_HUGE_PAGES); + + /* private write should consume additional pages */ + write_fault_pages(addr2, NR_HUGE_PAGES); + validate_free_pages(free_hugepages - (2 * NR_HUGE_PAGES)); + + /* madvise of shared mapping should not free any pages */ + if (madvise(addr, NR_HUGE_PAGES * huge_page_size, MADV_DONTNEED)) { + perror("madvise"); + exit(1); + } + validate_free_pages(free_hugepages - (2 * NR_HUGE_PAGES)); + + /* madvise of private mapping should free private pages */ + if (madvise(addr2, NR_HUGE_PAGES * huge_page_size, MADV_DONTNEED)) { + perror("madvise"); + exit(1); + } + validate_free_pages(free_hugepages - NR_HUGE_PAGES); + + /* private write should consume additional pages again */ + write_fault_pages(addr2, NR_HUGE_PAGES); + validate_free_pages(free_hugepages - (2 * NR_HUGE_PAGES)); + + /* + * madvise should free both file and private pages although this is + * not correct. private pages should not be freed, but this is + * expected. See comment associated with FALLOC_FL_PUNCH_HOLE call. + */ + if (madvise(addr, NR_HUGE_PAGES * huge_page_size, MADV_REMOVE)) { + perror("madvise"); + exit(1); + } + validate_free_pages(free_hugepages); + + (void)munmap(addr, NR_HUGE_PAGES * huge_page_size); + (void)munmap(addr2, NR_HUGE_PAGES * huge_page_size); + + close(fd); + unlink(argv[1]); + return 0; +} diff --git a/tools/testing/selftests/vm/ksm_tests.c b/tools/testing/selftests/vm/ksm_tests.c index 1436e1a9a3d3..fd85f15869d1 100644 --- a/tools/testing/selftests/vm/ksm_tests.c +++ b/tools/testing/selftests/vm/ksm_tests.c @@ -12,6 +12,7 @@ #include "../kselftest.h" #include "../../../../include/vdso/time64.h" +#include "util.h" #define KSM_SYSFS_PATH "/sys/kernel/mm/ksm/" #define KSM_FP(s) (KSM_SYSFS_PATH s) @@ -22,15 +23,6 @@ #define KSM_MERGE_ACROSS_NODES_DEFAULT true #define MB (1ul << 20) -#define PAGE_SHIFT 12 -#define HPAGE_SHIFT 21 - -#define PAGE_SIZE (1 << PAGE_SHIFT) -#define HPAGE_SIZE (1 << HPAGE_SHIFT) - -#define PAGEMAP_PRESENT(ent) (((ent) & (1ull << 63)) != 0) -#define PAGEMAP_PFN(ent) ((ent) & ((1ull << 55) - 1)) - struct ksm_sysfs { unsigned long max_page_sharing; unsigned long merge_across_nodes; @@ -456,34 +448,6 @@ err_out: return KSFT_FAIL; } -int64_t allocate_transhuge(void *ptr, int pagemap_fd) -{ - uint64_t ent[2]; - - /* drop pmd */ - if (mmap(ptr, HPAGE_SIZE, PROT_READ | PROT_WRITE, - MAP_FIXED | MAP_ANONYMOUS | - MAP_NORESERVE | MAP_PRIVATE, -1, 0) != ptr) - errx(2, "mmap transhuge"); - - if (madvise(ptr, HPAGE_SIZE, MADV_HUGEPAGE)) - err(2, "MADV_HUGEPAGE"); - - /* allocate transparent huge page */ - *(volatile void **)ptr = ptr; - - if (pread(pagemap_fd, ent, sizeof(ent), - (uintptr_t)ptr >> (PAGE_SHIFT - 3)) != sizeof(ent)) - err(2, "read pagemap"); - - if (PAGEMAP_PRESENT(ent[0]) && PAGEMAP_PRESENT(ent[1]) && - PAGEMAP_PFN(ent[0]) + 1 == PAGEMAP_PFN(ent[1]) && - !(PAGEMAP_PFN(ent[0]) & ((1 << (HPAGE_SHIFT - PAGE_SHIFT)) - 1))) - return PAGEMAP_PFN(ent[0]); - - return -1; -} - static int ksm_merge_hugepages_time(int mapping, int prot, int timeout, size_t map_size) { void *map_ptr, *map_ptr_orig; diff --git a/tools/testing/selftests/vm/map_fixed_noreplace.c b/tools/testing/selftests/vm/map_fixed_noreplace.c index d91bde511268..eed44322d1a6 100644 --- a/tools/testing/selftests/vm/map_fixed_noreplace.c +++ b/tools/testing/selftests/vm/map_fixed_noreplace.c @@ -17,9 +17,6 @@ #define MAP_FIXED_NOREPLACE 0x100000 #endif -#define BASE_ADDRESS (256ul * 1024 * 1024) - - static void dump_maps(void) { char cmd[32]; @@ -28,18 +25,46 @@ static void dump_maps(void) system(cmd); } +static unsigned long find_base_addr(unsigned long size) +{ + void *addr; + unsigned long flags; + + flags = MAP_PRIVATE | MAP_ANONYMOUS; + addr = mmap(NULL, size, PROT_NONE, flags, -1, 0); + if (addr == MAP_FAILED) { + printf("Error: couldn't map the space we need for the test\n"); + return 0; + } + + if (munmap(addr, size) != 0) { + printf("Error: couldn't map the space we need for the test\n"); + return 0; + } + return (unsigned long)addr; +} + int main(void) { + unsigned long base_addr; unsigned long flags, addr, size, page_size; char *p; page_size = sysconf(_SC_PAGE_SIZE); + //let's find a base addr that is free before we start the tests + size = 5 * page_size; + base_addr = find_base_addr(size); + if (!base_addr) { + printf("Error: couldn't map the space we need for the test\n"); + return 1; + } + flags = MAP_PRIVATE | MAP_ANONYMOUS | MAP_FIXED_NOREPLACE; // Check we can map all the areas we need below errno = 0; - addr = BASE_ADDRESS; + addr = base_addr; size = 5 * page_size; p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0); @@ -60,7 +85,7 @@ int main(void) printf("unmap() successful\n"); errno = 0; - addr = BASE_ADDRESS + page_size; + addr = base_addr + page_size; size = 3 * page_size; p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0); printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); @@ -80,7 +105,7 @@ int main(void) * +4 | free | new */ errno = 0; - addr = BASE_ADDRESS; + addr = base_addr; size = 5 * page_size; p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0); printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); @@ -101,7 +126,7 @@ int main(void) * +4 | free | */ errno = 0; - addr = BASE_ADDRESS + (2 * page_size); + addr = base_addr + (2 * page_size); size = page_size; p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0); printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); @@ -121,7 +146,7 @@ int main(void) * +4 | free | new */ errno = 0; - addr = BASE_ADDRESS + (3 * page_size); + addr = base_addr + (3 * page_size); size = 2 * page_size; p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0); printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); @@ -141,7 +166,7 @@ int main(void) * +4 | free | */ errno = 0; - addr = BASE_ADDRESS; + addr = base_addr; size = 2 * page_size; p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0); printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); @@ -161,7 +186,7 @@ int main(void) * +4 | free | */ errno = 0; - addr = BASE_ADDRESS; + addr = base_addr; size = page_size; p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0); printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); @@ -181,7 +206,7 @@ int main(void) * +4 | free | new */ errno = 0; - addr = BASE_ADDRESS + (4 * page_size); + addr = base_addr + (4 * page_size); size = page_size; p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0); printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); @@ -192,7 +217,7 @@ int main(void) return 1; } - addr = BASE_ADDRESS; + addr = base_addr; size = 5 * page_size; if (munmap((void *)addr, size) != 0) { dump_maps(); diff --git a/tools/testing/selftests/vm/memfd_secret.c b/tools/testing/selftests/vm/memfd_secret.c index 93e7e7ffed33..957b9e18c729 100644 --- a/tools/testing/selftests/vm/memfd_secret.c +++ b/tools/testing/selftests/vm/memfd_secret.c @@ -282,7 +282,7 @@ int main(int argc, char *argv[]) close(fd); - ksft_exit(!ksft_get_fail_cnt()); + ksft_finished(); } #else /* __NR_memfd_secret */ diff --git a/tools/testing/selftests/vm/run_vmtests.sh b/tools/testing/selftests/vm/run_vmtests.sh index 75d401741394..3b265f140c25 100755 --- a/tools/testing/selftests/vm/run_vmtests.sh +++ b/tools/testing/selftests/vm/run_vmtests.sh @@ -111,13 +111,37 @@ fi echo "-----------------------" echo "running hugepage-mremap" echo "-----------------------" -./hugepage-mremap 256 +./hugepage-mremap $mnt/huge_mremap if [ $? -ne 0 ]; then echo "[FAIL]" exitcode=1 else echo "[PASS]" fi +rm -f $mnt/huge_mremap + +echo "------------------------" +echo "running hugepage-vmemmap" +echo "------------------------" +./hugepage-vmemmap +if [ $? -ne 0 ]; then + echo "[FAIL]" + exitcode=1 +else + echo "[PASS]" +fi + +echo "-----------------------" +echo "running hugetlb-madvise" +echo "-----------------------" +./hugetlb-madvise $mnt/madvise-test +if [ $? -ne 0 ]; then + echo "[FAIL]" + exitcode=1 +else + echo "[PASS]" +fi +rm -f $mnt/madvise-test echo "NOTE: The above hugetlb tests provide minimal coverage. Use" echo " https://github.com/libhugetlbfs/libhugetlbfs.git for" @@ -184,14 +208,13 @@ echo "running userfaultfd_hugetlb" echo "---------------------------" # Test requires source and destination huge pages. Size of source # (half_ufd_size_MB) is passed as argument to test. -./userfaultfd hugetlb $half_ufd_size_MB 32 $mnt/ufd_test_file +./userfaultfd hugetlb $half_ufd_size_MB 32 if [ $? -ne 0 ]; then echo "[FAIL]" exitcode=1 else echo "[PASS]" fi -rm -f $mnt/ufd_test_file echo "-------------------------" echo "running userfaultfd_shmem" diff --git a/tools/testing/selftests/vm/transhuge-stress.c b/tools/testing/selftests/vm/transhuge-stress.c index 5e4c036f6ad3..e3f00adb1b82 100644 --- a/tools/testing/selftests/vm/transhuge-stress.c +++ b/tools/testing/selftests/vm/transhuge-stress.c @@ -15,67 +15,46 @@ #include <fcntl.h> #include <string.h> #include <sys/mman.h> +#include "util.h" -#define PAGE_SHIFT 12 -#define HPAGE_SHIFT 21 - -#define PAGE_SIZE (1 << PAGE_SHIFT) -#define HPAGE_SIZE (1 << HPAGE_SHIFT) - -#define PAGEMAP_PRESENT(ent) (((ent) & (1ull << 63)) != 0) -#define PAGEMAP_PFN(ent) ((ent) & ((1ull << 55) - 1)) - -int pagemap_fd; - -int64_t allocate_transhuge(void *ptr) -{ - uint64_t ent[2]; - - /* drop pmd */ - if (mmap(ptr, HPAGE_SIZE, PROT_READ | PROT_WRITE, - MAP_FIXED | MAP_ANONYMOUS | - MAP_NORESERVE | MAP_PRIVATE, -1, 0) != ptr) - errx(2, "mmap transhuge"); - - if (madvise(ptr, HPAGE_SIZE, MADV_HUGEPAGE)) - err(2, "MADV_HUGEPAGE"); - - /* allocate transparent huge page */ - *(volatile void **)ptr = ptr; - - if (pread(pagemap_fd, ent, sizeof(ent), - (uintptr_t)ptr >> (PAGE_SHIFT - 3)) != sizeof(ent)) - err(2, "read pagemap"); - - if (PAGEMAP_PRESENT(ent[0]) && PAGEMAP_PRESENT(ent[1]) && - PAGEMAP_PFN(ent[0]) + 1 == PAGEMAP_PFN(ent[1]) && - !(PAGEMAP_PFN(ent[0]) & ((1 << (HPAGE_SHIFT - PAGE_SHIFT)) - 1))) - return PAGEMAP_PFN(ent[0]); - - return -1; -} +int backing_fd = -1; +int mmap_flags = MAP_ANONYMOUS | MAP_NORESERVE | MAP_PRIVATE; +#define PROT_RW (PROT_READ | PROT_WRITE) int main(int argc, char **argv) { size_t ram, len; void *ptr, *p; struct timespec a, b; + int i = 0; + char *name = NULL; double s; uint8_t *map; size_t map_len; + int pagemap_fd; ram = sysconf(_SC_PHYS_PAGES); if (ram > SIZE_MAX / sysconf(_SC_PAGESIZE) / 4) ram = SIZE_MAX / 4; else ram *= sysconf(_SC_PAGESIZE); + len = ram; + + while (++i < argc) { + if (!strcmp(argv[i], "-h")) + errx(1, "usage: %s [size in MiB]", argv[0]); + else if (!strcmp(argv[i], "-f")) + name = argv[++i]; + else + len = atoll(argv[i]) << 20; + } - if (argc == 1) - len = ram; - else if (!strcmp(argv[1], "-h")) - errx(1, "usage: %s [size in MiB]", argv[0]); - else - len = atoll(argv[1]) << 20; + if (name) { + backing_fd = open(name, O_RDWR); + if (backing_fd == -1) + errx(2, "open %s", name); + mmap_flags = MAP_SHARED; + } warnx("allocate %zd transhuge pages, using %zd MiB virtual memory" " and %zd MiB of ram", len >> HPAGE_SHIFT, len >> 20, @@ -86,8 +65,7 @@ int main(int argc, char **argv) err(2, "open pagemap"); len -= len % HPAGE_SIZE; - ptr = mmap(NULL, len + HPAGE_SIZE, PROT_READ | PROT_WRITE, - MAP_ANONYMOUS | MAP_NORESERVE | MAP_PRIVATE, -1, 0); + ptr = mmap(NULL, len + HPAGE_SIZE, PROT_RW, mmap_flags, backing_fd, 0); if (ptr == MAP_FAILED) err(2, "initial mmap"); ptr += HPAGE_SIZE - (uintptr_t)ptr % HPAGE_SIZE; @@ -109,7 +87,7 @@ int main(int argc, char **argv) for (p = ptr; p < ptr + len; p += HPAGE_SIZE) { int64_t pfn; - pfn = allocate_transhuge(p); + pfn = allocate_transhuge(p, pagemap_fd); if (pfn < 0) { nr_failed++; diff --git a/tools/testing/selftests/vm/userfaultfd.c b/tools/testing/selftests/vm/userfaultfd.c index d3fd24f9fae8..92a4516f8f0d 100644 --- a/tools/testing/selftests/vm/userfaultfd.c +++ b/tools/testing/selftests/vm/userfaultfd.c @@ -46,6 +46,7 @@ #include <signal.h> #include <poll.h> #include <string.h> +#include <linux/mman.h> #include <sys/mman.h> #include <sys/syscall.h> #include <sys/ioctl.h> @@ -88,7 +89,6 @@ static bool test_uffdio_minor = false; static bool map_shared; static int shm_fd; static int huge_fd; -static char *huge_fd_off0; static unsigned long long *count_verify; static int uffd = -1; static int uffd_flags, finished, *pipefd; @@ -119,14 +119,17 @@ struct uffd_stats { ~(unsigned long)(sizeof(unsigned long long) \ - 1))) +#define swap(a, b) \ + do { typeof(a) __tmp = (a); (a) = (b); (b) = __tmp; } while (0) + const char *examples = "# Run anonymous memory test on 100MiB region with 99999 bounces:\n" "./userfaultfd anon 100 99999\n\n" "# Run share memory test on 1GiB region with 99 bounces:\n" "./userfaultfd shmem 1000 99\n\n" - "# Run hugetlb memory test on 256MiB region with 50 bounces (using /dev/hugepages/hugefile):\n" - "./userfaultfd hugetlb 256 50 /dev/hugepages/hugefile\n\n" - "# Run the same hugetlb test but using shmem:\n" + "# Run hugetlb memory test on 256MiB region with 50 bounces:\n" + "./userfaultfd hugetlb 256 50\n\n" + "# Run the same hugetlb test but using shared file:\n" "./userfaultfd hugetlb_shared 256 50 /dev/hugepages/hugefile\n\n" "# 10MiB-~6GiB 999 bounces anonymous test, " "continue forever unless an error triggers\n" @@ -223,10 +226,13 @@ static void noop_alias_mapping(__u64 *start, size_t len, unsigned long offset) static void hugetlb_release_pages(char *rel_area) { - if (fallocate(huge_fd, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, - rel_area == huge_fd_off0 ? 0 : nr_pages * page_size, - nr_pages * page_size)) - err("fallocate() failed"); + if (!map_shared) { + if (madvise(rel_area, nr_pages * page_size, MADV_DONTNEED)) + err("madvise(MADV_DONTNEED) failed"); + } else { + if (madvise(rel_area, nr_pages * page_size, MADV_REMOVE)) + err("madvise(MADV_REMOVE) failed"); + } } static void hugetlb_allocate_area(void **alloc_area) @@ -234,26 +240,37 @@ static void hugetlb_allocate_area(void **alloc_area) void *area_alias = NULL; char **alloc_area_alias; - *alloc_area = mmap(NULL, nr_pages * page_size, PROT_READ | PROT_WRITE, - (map_shared ? MAP_SHARED : MAP_PRIVATE) | - MAP_HUGETLB | - (*alloc_area == area_src ? 0 : MAP_NORESERVE), - huge_fd, *alloc_area == area_src ? 0 : - nr_pages * page_size); + if (!map_shared) + *alloc_area = mmap(NULL, + nr_pages * page_size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB | + (*alloc_area == area_src ? 0 : MAP_NORESERVE), + -1, + 0); + else + *alloc_area = mmap(NULL, + nr_pages * page_size, + PROT_READ | PROT_WRITE, + MAP_SHARED | + (*alloc_area == area_src ? 0 : MAP_NORESERVE), + huge_fd, + *alloc_area == area_src ? 0 : nr_pages * page_size); if (*alloc_area == MAP_FAILED) err("mmap of hugetlbfs file failed"); if (map_shared) { - area_alias = mmap(NULL, nr_pages * page_size, PROT_READ | PROT_WRITE, - MAP_SHARED | MAP_HUGETLB, - huge_fd, *alloc_area == area_src ? 0 : - nr_pages * page_size); + area_alias = mmap(NULL, + nr_pages * page_size, + PROT_READ | PROT_WRITE, + MAP_SHARED, + huge_fd, + *alloc_area == area_src ? 0 : nr_pages * page_size); if (area_alias == MAP_FAILED) err("mmap of hugetlb file alias failed"); } if (*alloc_area == area_src) { - huge_fd_off0 = *alloc_area; alloc_area_alias = &area_src_alias; } else { alloc_area_alias = &area_dst_alias; @@ -266,12 +283,7 @@ static void hugetlb_alias_mapping(__u64 *start, size_t len, unsigned long offset { if (!map_shared) return; - /* - * We can't zap just the pagetable with hugetlbfs because - * MADV_DONTEED won't work. So exercise -EEXIST on a alias - * mapping where the pagetables are not established initially, - * this way we'll exercise the -EEXEC at the fs level. - */ + *start = (unsigned long) area_dst_alias + offset; } @@ -424,7 +436,6 @@ static void uffd_test_ctx_clear(void) uffd = -1; } - huge_fd_off0 = NULL; munmap_area((void **)&area_src); munmap_area((void **)&area_src_alias); munmap_area((void **)&area_dst); @@ -539,7 +550,7 @@ static void continue_range(int ufd, __u64 start, __u64 len) static void *locking_thread(void *arg) { unsigned long cpu = (unsigned long) arg; - unsigned long page_nr = *(&(page_nr)); /* uninitialized warning */ + unsigned long page_nr; unsigned long long count; if (!(bounces & BOUNCE_RANDOM)) { @@ -922,10 +933,7 @@ static int faulting_process(int signal_test) struct sigaction act; unsigned long signalled = 0; - if (test_type != TEST_HUGETLB) - split_nr_pages = (nr_pages + 1) / 2; - else - split_nr_pages = nr_pages; + split_nr_pages = (nr_pages + 1) / 2; if (signal_test) { sigbuf = &jbuf; @@ -982,9 +990,6 @@ static int faulting_process(int signal_test) if (signal_test) return signalled != split_nr_pages; - if (test_type == TEST_HUGETLB) - return 0; - area_dst = mremap(area_dst, nr_pages * page_size, nr_pages * page_size, MREMAP_MAYMOVE | MREMAP_FIXED, area_src); if (area_dst == MAP_FAILED) @@ -1417,6 +1422,7 @@ static void userfaultfd_pagemap_test(unsigned int test_pgsize) static int userfaultfd_stress(void) { void *area; + char *tmp_area; unsigned long nr; struct uffdio_register uffdio_register; struct uffd_stats uffd_stats[nr_cpus]; @@ -1527,9 +1533,13 @@ static int userfaultfd_stress(void) count_verify[nr], nr); /* prepare next bounce */ - swap(area_src, area_dst); + tmp_area = area_src; + area_src = area_dst; + area_dst = tmp_area; - swap(area_src_alias, area_dst_alias); + tmp_area = area_src_alias; + area_src_alias = area_dst_alias; + area_dst_alias = tmp_area; uffd_stats_report(uffd_stats, nr_cpus); } @@ -1667,7 +1677,7 @@ int main(int argc, char **argv) } nr_pages = nr_pages_per_cpu * nr_cpus; - if (test_type == TEST_HUGETLB) { + if (test_type == TEST_HUGETLB && map_shared) { if (argc < 5) usage(); huge_fd = open(argv[4], O_CREAT | O_RDWR, 0755); diff --git a/tools/testing/selftests/vm/util.h b/tools/testing/selftests/vm/util.h new file mode 100644 index 000000000000..b27d26199334 --- /dev/null +++ b/tools/testing/selftests/vm/util.h @@ -0,0 +1,69 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __KSELFTEST_VM_UTIL_H +#define __KSELFTEST_VM_UTIL_H + +#include <stdint.h> +#include <sys/mman.h> +#include <err.h> +#include <string.h> /* ffsl() */ +#include <unistd.h> /* _SC_PAGESIZE */ + +static unsigned int __page_size; +static unsigned int __page_shift; + +static inline unsigned int page_size(void) +{ + if (!__page_size) + __page_size = sysconf(_SC_PAGESIZE); + return __page_size; +} + +static inline unsigned int page_shift(void) +{ + if (!__page_shift) + __page_shift = (ffsl(page_size()) - 1); + return __page_shift; +} + +#define PAGE_SHIFT (page_shift()) +#define PAGE_SIZE (page_size()) +/* + * On ppc64 this will only work with radix 2M hugepage size + */ +#define HPAGE_SHIFT 21 +#define HPAGE_SIZE (1 << HPAGE_SHIFT) + +#define PAGEMAP_PRESENT(ent) (((ent) & (1ull << 63)) != 0) +#define PAGEMAP_PFN(ent) ((ent) & ((1ull << 55) - 1)) + + +static inline int64_t allocate_transhuge(void *ptr, int pagemap_fd) +{ + uint64_t ent[2]; + + /* drop pmd */ + if (mmap(ptr, HPAGE_SIZE, PROT_READ | PROT_WRITE, + MAP_FIXED | MAP_ANONYMOUS | + MAP_NORESERVE | MAP_PRIVATE, -1, 0) != ptr) + errx(2, "mmap transhuge"); + + if (madvise(ptr, HPAGE_SIZE, MADV_HUGEPAGE)) + err(2, "MADV_HUGEPAGE"); + + /* allocate transparent huge page */ + *(volatile void **)ptr = ptr; + + if (pread(pagemap_fd, ent, sizeof(ent), + (uintptr_t)ptr >> (PAGE_SHIFT - 3)) != sizeof(ent)) + err(2, "read pagemap"); + + if (PAGEMAP_PRESENT(ent[0]) && PAGEMAP_PRESENT(ent[1]) && + PAGEMAP_PFN(ent[0]) + 1 == PAGEMAP_PFN(ent[1]) && + !(PAGEMAP_PFN(ent[0]) & ((1 << (HPAGE_SHIFT - PAGE_SHIFT)) - 1))) + return PAGEMAP_PFN(ent[0]); + + return -1; +} + +#endif diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile index 8a1f62ab3c8e..53df7d3893d3 100644 --- a/tools/testing/selftests/x86/Makefile +++ b/tools/testing/selftests/x86/Makefile @@ -6,9 +6,9 @@ include ../lib.mk .PHONY: all all_32 all_64 warn_32bit_failure clean UNAME_M := $(shell uname -m) -CAN_BUILD_I386 := $(shell ./check_cc.sh $(CC) trivial_32bit_program.c -m32) -CAN_BUILD_X86_64 := $(shell ./check_cc.sh $(CC) trivial_64bit_program.c) -CAN_BUILD_WITH_NOPIE := $(shell ./check_cc.sh $(CC) trivial_program.c -no-pie) +CAN_BUILD_I386 := $(shell ./check_cc.sh "$(CC)" trivial_32bit_program.c -m32) +CAN_BUILD_X86_64 := $(shell ./check_cc.sh "$(CC)" trivial_64bit_program.c) +CAN_BUILD_WITH_NOPIE := $(shell ./check_cc.sh "$(CC)" trivial_program.c -no-pie) TARGETS_C_BOTHBITS := single_step_syscall sysret_ss_attrs syscall_nt test_mremap_vdso \ check_initial_reg_state sigreturn iopl ioperm \ diff --git a/tools/testing/selftests/x86/check_cc.sh b/tools/testing/selftests/x86/check_cc.sh index 3e2089c8cf54..8c669c0d662e 100755 --- a/tools/testing/selftests/x86/check_cc.sh +++ b/tools/testing/selftests/x86/check_cc.sh @@ -7,7 +7,7 @@ CC="$1" TESTPROG="$2" shift 2 -if "$CC" -o /dev/null "$TESTPROG" -O0 "$@" 2>/dev/null; then +if [ -n "$CC" ] && $CC -o /dev/null "$TESTPROG" -O0 "$@" 2>/dev/null; then echo 1 else echo 0 diff --git a/tools/testing/selftests/zram/zram.sh b/tools/testing/selftests/zram/zram.sh index 232e958ec454..b0b91d9b0dc2 100755 --- a/tools/testing/selftests/zram/zram.sh +++ b/tools/testing/selftests/zram/zram.sh @@ -2,9 +2,6 @@ # SPDX-License-Identifier: GPL-2.0 TCID="zram.sh" -# Kselftest framework requirement - SKIP code is 4. -ksft_skip=4 - . ./zram_lib.sh run_zram () { @@ -18,14 +15,4 @@ echo "" check_prereqs -# check zram module exists -MODULE_PATH=/lib/modules/`uname -r`/kernel/drivers/block/zram/zram.ko -if [ -f $MODULE_PATH ]; then - run_zram -elif [ -b /dev/zram0 ]; then - run_zram -else - echo "$TCID : No zram.ko module or /dev/zram0 device file not found" - echo "$TCID : CONFIG_ZRAM is not set" - exit $ksft_skip -fi +run_zram diff --git a/tools/testing/selftests/zram/zram01.sh b/tools/testing/selftests/zram/zram01.sh index 114863d9fb87..8f4affe34f3e 100755 --- a/tools/testing/selftests/zram/zram01.sh +++ b/tools/testing/selftests/zram/zram01.sh @@ -33,9 +33,7 @@ zram_algs="lzo" zram_fill_fs() { - local mem_free0=$(free -m | awk 'NR==2 {print $4}') - - for i in $(seq 0 $(($dev_num - 1))); do + for i in $(seq $dev_start $dev_end); do echo "fill zram$i..." local b=0 while [ true ]; do @@ -45,29 +43,17 @@ zram_fill_fs() b=$(($b + 1)) done echo "zram$i can be filled with '$b' KB" - done - local mem_free1=$(free -m | awk 'NR==2 {print $4}') - local used_mem=$(($mem_free0 - $mem_free1)) + local mem_used_total=`awk '{print $3}' "/sys/block/zram$i/mm_stat"` + local v=$((100 * 1024 * $b / $mem_used_total)) + if [ "$v" -lt 100 ]; then + echo "FAIL compression ratio: 0.$v:1" + ERR_CODE=-1 + return + fi - local total_size=0 - for sm in $zram_sizes; do - local s=$(echo $sm | sed 's/M//') - total_size=$(($total_size + $s)) + echo "zram compression ratio: $(echo "scale=2; $v / 100 " | bc):1: OK" done - - echo "zram used ${used_mem}M, zram disk sizes ${total_size}M" - - local v=$((100 * $total_size / $used_mem)) - - if [ "$v" -lt 100 ]; then - echo "FAIL compression ratio: 0.$v:1" - ERR_CODE=-1 - zram_cleanup - return - fi - - echo "zram compression ratio: $(echo "scale=2; $v / 100 " | bc):1: OK" } check_prereqs @@ -81,7 +67,6 @@ zram_mount zram_fill_fs zram_cleanup -zram_unload if [ $ERR_CODE -ne 0 ]; then echo "$TCID : [FAIL]" diff --git a/tools/testing/selftests/zram/zram02.sh b/tools/testing/selftests/zram/zram02.sh index e83b404807c0..2418b0c4ed13 100755 --- a/tools/testing/selftests/zram/zram02.sh +++ b/tools/testing/selftests/zram/zram02.sh @@ -36,7 +36,6 @@ zram_set_memlimit zram_makeswap zram_swapoff zram_cleanup -zram_unload if [ $ERR_CODE -ne 0 ]; then echo "$TCID : [FAIL]" diff --git a/tools/testing/selftests/zram/zram_lib.sh b/tools/testing/selftests/zram/zram_lib.sh index 6f872f266fd1..21ec1966de76 100755 --- a/tools/testing/selftests/zram/zram_lib.sh +++ b/tools/testing/selftests/zram/zram_lib.sh @@ -5,12 +5,17 @@ # Author: Alexey Kodanev <alexey.kodanev@oracle.com> # Modified: Naresh Kamboju <naresh.kamboju@linaro.org> -MODULE=0 dev_makeswap=-1 dev_mounted=-1 - +dev_start=0 +dev_end=-1 +module_load=-1 +sys_control=-1 # Kselftest framework requirement - SKIP code is 4. ksft_skip=4 +kernel_version=`uname -r | cut -d'.' -f1,2` +kernel_major=${kernel_version%.*} +kernel_minor=${kernel_version#*.} trap INT @@ -25,68 +30,104 @@ check_prereqs() fi } +kernel_gte() +{ + major=${1%.*} + minor=${1#*.} + + if [ $kernel_major -gt $major ]; then + return 0 + elif [[ $kernel_major -eq $major && $kernel_minor -ge $minor ]]; then + return 0 + fi + + return 1 +} + zram_cleanup() { echo "zram cleanup" local i= - for i in $(seq 0 $dev_makeswap); do + for i in $(seq $dev_start $dev_makeswap); do swapoff /dev/zram$i done - for i in $(seq 0 $dev_mounted); do + for i in $(seq $dev_start $dev_mounted); do umount /dev/zram$i done - for i in $(seq 0 $(($dev_num - 1))); do + for i in $(seq $dev_start $dev_end); do echo 1 > /sys/block/zram${i}/reset rm -rf zram$i done -} + if [ $sys_control -eq 1 ]; then + for i in $(seq $dev_start $dev_end); do + echo $i > /sys/class/zram-control/hot_remove + done + fi -zram_unload() -{ - if [ $MODULE -ne 0 ] ; then - echo "zram rmmod zram" + if [ $module_load -eq 1 ]; then rmmod zram > /dev/null 2>&1 fi } zram_load() { - # check zram module exists - MODULE_PATH=/lib/modules/`uname -r`/kernel/drivers/block/zram/zram.ko - if [ -f $MODULE_PATH ]; then - MODULE=1 - echo "create '$dev_num' zram device(s)" - modprobe zram num_devices=$dev_num - if [ $? -ne 0 ]; then - echo "failed to insert zram module" - exit 1 - fi - - dev_num_created=$(ls /dev/zram* | wc -w) + echo "create '$dev_num' zram device(s)" + + # zram module loaded, new kernel + if [ -d "/sys/class/zram-control" ]; then + echo "zram modules already loaded, kernel supports" \ + "zram-control interface" + dev_start=$(ls /dev/zram* | wc -w) + dev_end=$(($dev_start + $dev_num - 1)) + sys_control=1 + + for i in $(seq $dev_start $dev_end); do + cat /sys/class/zram-control/hot_add > /dev/null + done + + echo "all zram devices (/dev/zram$dev_start~$dev_end" \ + "successfully created" + return 0 + fi - if [ "$dev_num_created" -ne "$dev_num" ]; then - echo "unexpected num of devices: $dev_num_created" - ERR_CODE=-1 + # detect old kernel or built-in + modprobe zram num_devices=$dev_num + if [ ! -d "/sys/class/zram-control" ]; then + if grep -q '^zram' /proc/modules; then + rmmod zram > /dev/null 2>&1 + if [ $? -ne 0 ]; then + echo "zram module is being used on old kernel" \ + "without zram-control interface" + exit $ksft_skip + fi else - echo "zram load module successful" + echo "test needs CONFIG_ZRAM=m on old kernel without" \ + "zram-control interface" + exit $ksft_skip fi - elif [ -b /dev/zram0 ]; then - echo "/dev/zram0 device file found: OK" - else - echo "ERROR: No zram.ko module or no /dev/zram0 device found" - echo "$TCID : CONFIG_ZRAM is not set" - exit 1 + modprobe zram num_devices=$dev_num fi + + module_load=1 + dev_end=$(($dev_num - 1)) + echo "all zram devices (/dev/zram0~$dev_end) successfully created" } zram_max_streams() { echo "set max_comp_streams to zram device(s)" - local i=0 + kernel_gte 4.7 + if [ $? -eq 0 ]; then + echo "The device attribute max_comp_streams was"\ + "deprecated in 4.7" + return 0 + fi + + local i=$dev_start for max_s in $zram_max_streams; do local sys_path="/sys/block/zram${i}/max_comp_streams" echo $max_s > $sys_path || \ @@ -98,7 +139,7 @@ zram_max_streams() echo "FAIL can't set max_streams '$max_s', get $max_stream" i=$(($i + 1)) - echo "$sys_path = '$max_streams' ($i/$dev_num)" + echo "$sys_path = '$max_streams'" done echo "zram max streams: OK" @@ -108,15 +149,16 @@ zram_compress_alg() { echo "test that we can set compression algorithm" - local algs=$(cat /sys/block/zram0/comp_algorithm) + local i=$dev_start + local algs=$(cat /sys/block/zram${i}/comp_algorithm) echo "supported algs: $algs" - local i=0 + for alg in $zram_algs; do local sys_path="/sys/block/zram${i}/comp_algorithm" echo "$alg" > $sys_path || \ echo "FAIL can't set '$alg' to $sys_path" i=$(($i + 1)) - echo "$sys_path = '$alg' ($i/$dev_num)" + echo "$sys_path = '$alg'" done echo "zram set compression algorithm: OK" @@ -125,14 +167,14 @@ zram_compress_alg() zram_set_disksizes() { echo "set disk size to zram device(s)" - local i=0 + local i=$dev_start for ds in $zram_sizes; do local sys_path="/sys/block/zram${i}/disksize" echo "$ds" > $sys_path || \ echo "FAIL can't set '$ds' to $sys_path" i=$(($i + 1)) - echo "$sys_path = '$ds' ($i/$dev_num)" + echo "$sys_path = '$ds'" done echo "zram set disksizes: OK" @@ -142,14 +184,14 @@ zram_set_memlimit() { echo "set memory limit to zram device(s)" - local i=0 + local i=$dev_start for ds in $zram_mem_limits; do local sys_path="/sys/block/zram${i}/mem_limit" echo "$ds" > $sys_path || \ echo "FAIL can't set '$ds' to $sys_path" i=$(($i + 1)) - echo "$sys_path = '$ds' ($i/$dev_num)" + echo "$sys_path = '$ds'" done echo "zram set memory limit: OK" @@ -158,8 +200,8 @@ zram_set_memlimit() zram_makeswap() { echo "make swap with zram device(s)" - local i=0 - for i in $(seq 0 $(($dev_num - 1))); do + local i=$dev_start + for i in $(seq $dev_start $dev_end); do mkswap /dev/zram$i > err.log 2>&1 if [ $? -ne 0 ]; then cat err.log @@ -182,7 +224,7 @@ zram_makeswap() zram_swapoff() { local i= - for i in $(seq 0 $dev_makeswap); do + for i in $(seq $dev_start $dev_end); do swapoff /dev/zram$i > err.log 2>&1 if [ $? -ne 0 ]; then cat err.log @@ -196,7 +238,7 @@ zram_swapoff() zram_makefs() { - local i=0 + local i=$dev_start for fs in $zram_filesystems; do # if requested fs not supported default it to ext2 which mkfs.$fs > /dev/null 2>&1 || fs=ext2 @@ -215,7 +257,7 @@ zram_makefs() zram_mount() { local i=0 - for i in $(seq 0 $(($dev_num - 1))); do + for i in $(seq $dev_start $dev_end); do echo "mount /dev/zram$i" mkdir zram$i mount /dev/zram$i zram$i > /dev/null || \ diff --git a/tools/testing/vsock/vsock_test.c b/tools/testing/vsock/vsock_test.c index 2a3638c0a008..dc577461afc2 100644 --- a/tools/testing/vsock/vsock_test.c +++ b/tools/testing/vsock/vsock_test.c @@ -16,6 +16,8 @@ #include <linux/kernel.h> #include <sys/types.h> #include <sys/socket.h> +#include <time.h> +#include <sys/mman.h> #include "timeout.h" #include "control.h" @@ -391,6 +393,209 @@ static void test_seqpacket_msg_trunc_server(const struct test_opts *opts) close(fd); } +static time_t current_nsec(void) +{ + struct timespec ts; + + if (clock_gettime(CLOCK_REALTIME, &ts)) { + perror("clock_gettime(3) failed"); + exit(EXIT_FAILURE); + } + + return (ts.tv_sec * 1000000000ULL) + ts.tv_nsec; +} + +#define RCVTIMEO_TIMEOUT_SEC 1 +#define READ_OVERHEAD_NSEC 250000000 /* 0.25 sec */ + +static void test_seqpacket_timeout_client(const struct test_opts *opts) +{ + int fd; + struct timeval tv; + char dummy; + time_t read_enter_ns; + time_t read_overhead_ns; + + fd = vsock_seqpacket_connect(opts->peer_cid, 1234); + if (fd < 0) { + perror("connect"); + exit(EXIT_FAILURE); + } + + tv.tv_sec = RCVTIMEO_TIMEOUT_SEC; + tv.tv_usec = 0; + + if (setsockopt(fd, SOL_SOCKET, SO_RCVTIMEO, (void *)&tv, sizeof(tv)) == -1) { + perror("setsockopt 'SO_RCVTIMEO'"); + exit(EXIT_FAILURE); + } + + read_enter_ns = current_nsec(); + + if (read(fd, &dummy, sizeof(dummy)) != -1) { + fprintf(stderr, + "expected 'dummy' read(2) failure\n"); + exit(EXIT_FAILURE); + } + + if (errno != EAGAIN) { + perror("EAGAIN expected"); + exit(EXIT_FAILURE); + } + + read_overhead_ns = current_nsec() - read_enter_ns - + 1000000000ULL * RCVTIMEO_TIMEOUT_SEC; + + if (read_overhead_ns > READ_OVERHEAD_NSEC) { + fprintf(stderr, + "too much time in read(2), %lu > %i ns\n", + read_overhead_ns, READ_OVERHEAD_NSEC); + exit(EXIT_FAILURE); + } + + control_writeln("WAITDONE"); + close(fd); +} + +static void test_seqpacket_timeout_server(const struct test_opts *opts) +{ + int fd; + + fd = vsock_seqpacket_accept(VMADDR_CID_ANY, 1234, NULL); + if (fd < 0) { + perror("accept"); + exit(EXIT_FAILURE); + } + + control_expectln("WAITDONE"); + close(fd); +} + +#define BUF_PATTERN_1 'a' +#define BUF_PATTERN_2 'b' + +static void test_seqpacket_invalid_rec_buffer_client(const struct test_opts *opts) +{ + int fd; + unsigned char *buf1; + unsigned char *buf2; + int buf_size = getpagesize() * 3; + + fd = vsock_seqpacket_connect(opts->peer_cid, 1234); + if (fd < 0) { + perror("connect"); + exit(EXIT_FAILURE); + } + + buf1 = malloc(buf_size); + if (!buf1) { + perror("'malloc()' for 'buf1'"); + exit(EXIT_FAILURE); + } + + buf2 = malloc(buf_size); + if (!buf2) { + perror("'malloc()' for 'buf2'"); + exit(EXIT_FAILURE); + } + + memset(buf1, BUF_PATTERN_1, buf_size); + memset(buf2, BUF_PATTERN_2, buf_size); + + if (send(fd, buf1, buf_size, 0) != buf_size) { + perror("send failed"); + exit(EXIT_FAILURE); + } + + if (send(fd, buf2, buf_size, 0) != buf_size) { + perror("send failed"); + exit(EXIT_FAILURE); + } + + close(fd); +} + +static void test_seqpacket_invalid_rec_buffer_server(const struct test_opts *opts) +{ + int fd; + unsigned char *broken_buf; + unsigned char *valid_buf; + int page_size = getpagesize(); + int buf_size = page_size * 3; + ssize_t res; + int prot = PROT_READ | PROT_WRITE; + int flags = MAP_PRIVATE | MAP_ANONYMOUS; + int i; + + fd = vsock_seqpacket_accept(VMADDR_CID_ANY, 1234, NULL); + if (fd < 0) { + perror("accept"); + exit(EXIT_FAILURE); + } + + /* Setup first buffer. */ + broken_buf = mmap(NULL, buf_size, prot, flags, -1, 0); + if (broken_buf == MAP_FAILED) { + perror("mmap for 'broken_buf'"); + exit(EXIT_FAILURE); + } + + /* Unmap "hole" in buffer. */ + if (munmap(broken_buf + page_size, page_size)) { + perror("'broken_buf' setup"); + exit(EXIT_FAILURE); + } + + valid_buf = mmap(NULL, buf_size, prot, flags, -1, 0); + if (valid_buf == MAP_FAILED) { + perror("mmap for 'valid_buf'"); + exit(EXIT_FAILURE); + } + + /* Try to fill buffer with unmapped middle. */ + res = read(fd, broken_buf, buf_size); + if (res != -1) { + fprintf(stderr, + "expected 'broken_buf' read(2) failure, got %zi\n", + res); + exit(EXIT_FAILURE); + } + + if (errno != ENOMEM) { + perror("unexpected errno of 'broken_buf'"); + exit(EXIT_FAILURE); + } + + /* Try to fill valid buffer. */ + res = read(fd, valid_buf, buf_size); + if (res < 0) { + perror("unexpected 'valid_buf' read(2) failure"); + exit(EXIT_FAILURE); + } + + if (res != buf_size) { + fprintf(stderr, + "invalid 'valid_buf' read(2), expected %i, got %zi\n", + buf_size, res); + exit(EXIT_FAILURE); + } + + for (i = 0; i < buf_size; i++) { + if (valid_buf[i] != BUF_PATTERN_2) { + fprintf(stderr, + "invalid pattern for 'valid_buf' at %i, expected %hhX, got %hhX\n", + i, BUF_PATTERN_2, valid_buf[i]); + exit(EXIT_FAILURE); + } + } + + /* Unmap buffers. */ + munmap(broken_buf, page_size); + munmap(broken_buf + page_size * 2, page_size); + munmap(valid_buf, buf_size); + close(fd); +} + static struct test_case test_cases[] = { { .name = "SOCK_STREAM connection reset", @@ -431,6 +636,16 @@ static struct test_case test_cases[] = { .run_client = test_seqpacket_msg_trunc_client, .run_server = test_seqpacket_msg_trunc_server, }, + { + .name = "SOCK_SEQPACKET timeout", + .run_client = test_seqpacket_timeout_client, + .run_server = test_seqpacket_timeout_server, + }, + { + .name = "SOCK_SEQPACKET invalid receive buffer", + .run_client = test_seqpacket_invalid_rec_buffer_client, + .run_server = test_seqpacket_invalid_rec_buffer_server, + }, {}, }; |